diff --git a/.claude/plans/aws-service-coverage-100.plan.md b/.claude/plans/aws-service-coverage-100.plan.md
new file mode 100644
index 00000000..d520d632
--- /dev/null
+++ b/.claude/plans/aws-service-coverage-100.plan.md
@@ -0,0 +1,192 @@
+# Plan: Repeatable AWS Service Onboarding
+
+**Source PRD**: `.claude/prds/aws-service-coverage-100.prd.md`
+**Selected Milestone**: 1 — Onboarding cost is known
+**Complexity**: Medium (small diffs; the measurement, not the code, is the deliverable)
+
+## Summary
+
+The service-onboarding pipeline already exists end to end — per-service model
+download, a codegen scaffolder that writes a self-registering provider and
+refuses to clobber a hand-written one, config that auto-enables every registered
+service, and a main loop that needs no edit per service. Milestone 1 is therefore
+a **repair-and-measure** job, not a build-a-tool job.
+
+Two defects make the existing pipeline unusable and one makes its output dishonest:
+the import generator gates on a file no service has, so it empties `imports.go`;
+the scaffolded provider declines in a way that never reaches the CRUD engine, so
+a new service serves zero operations; and the fidelity manifest would publish
+those zero-op services as `auto-crud` anyway. Fixing all three is under 30 lines.
+The remaining work is removing the one genuinely repetitive step (a hand-written
+boto3 fixture per service — there are already 104) and then running the whole
+path on one real service with a stopwatch.
+
+## Findings That Shape the Plan
+
+| Finding | Evidence | Consequence |
+|---|---|---|
+| **`generate-imports.sh` skips every service dir.** It requires `register.go`; zero of 103 services have one — they register from an `init()` inside `provider.go`. | `scripts/generate-imports.sh:19`; `ls internal/services/*/register.go` → no matches; 103 dirs vs 103 entries in the committed `cmd/devcloud/imports.go` | Running the script today writes an **empty import block**. The weekly sync workflow runs it (`.github/workflows/smithy-sync.yml:37`) before its test step, so that job has been failing every week rather than opening sync PRs. No new service can be reached until this is fixed. |
+| **The scaffold declines the wrong way.** It returns `generated.ErrNotImplemented`; the CRUD fallback is reached only on `plugin.ErrUnhandledOp`. | `internal/codegen/templates/scaffold_provider.go.tmpl:31` vs `internal/gateway/router.go:61` | A freshly scaffolded service serves **zero** operations and cannot meet the PRD's quality floor as generated. One-line fix. |
+| **The fidelity manifest does not check engine wiring.** An op is labelled `auto-crud` from the model-derived CRUD registry alone. | `internal/codegen/gen_fidelity.go:95-104` (`tierFor` consults only the `hand` and `crud` maps) | A scaffolded service would be published as `auto-crud` while returning an error at runtime — the manifest overstating coverage is the PRD's top-ranked risk, and this is the mechanism. |
+| Services are auto-enabled and auto-started; no per-service config or `main.go` edit. | `internal/config/config.go:122` (no `services` block ⇒ all enabled); `cmd/devcloud/main.go:102` iterates `registry.RegisteredServices()` | `docs/contributing.md` step 7 ("Update main.go") is dead. Two of its ten documented steps do not apply. |
+| **104 near-identical boto3 fixtures are hand-written**, each a one-line wrapper over a shared helper. | `tests/compatibility/conftest.py:126` (`_make_client`), 104 `*_client(devcloud_server)` definitions | This is the single largest per-service cost and the only step that genuinely scales with 330 services. One parameterized fixture removes it. |
+| The scaffolder already refuses to overwrite a hand-written provider. | `internal/codegen/generator.go:65` (`os.Stat` guard, comment states the intent) | Re-running codegen over the whole tree is safe; no quarantine mechanism needs inventing. |
+| **338 upstream models are missing locally** (431 upstream vs 93 in-tree). | `comm` over the `aws-sdk-go-v2/aws-models` listing vs `smithy-models/` | Confirms the PRD's ~330 figure. Upstream filenames are hyphenated (`api-gateway`, `app-mesh`) while package names are not — the download script takes the **upstream filename**, and the package name comes from the model's service id. They differ. |
+
+## Patterns to Mirror
+
+| Category | Source | Pattern |
+|---|---|---|
+| Generated file | `cmd/devcloud/imports.go:1` | `// Code generated by <script>. DO NOT EDIT.` header |
+| Scaffold safety | `internal/codegen/generator.go:65` | `os.Stat` guard with a comment naming what it protects — never overwrite hand-written code |
+| Script failure | `scripts/download-smithy-models.sh:79-88` | Exit non-zero rather than a silent green no-op, with a comment naming the silent failure it prevents |
+| Conformance test | `cmd/devcloud/conformance_test.go:24` | Iterate the live registry, `t.Errorf` per violation (not `Fatal`), conservative floor constant with a comment explaining the number |
+| Codegen classification | `internal/codegen/gen_crud_meta.go` | Skip rather than guess when confidence is low; sorted iteration for reproducible output |
+| Compat test | `tests/compatibility/test_verifiedpermissions.py` | One call per operation, assert `resp["ResponseMetadata"]["HTTPStatusCode"] == 200` |
+| Go test framework | 125 `_test.go` files | `stretchr/testify` `assert`/`require`, table-driven |
+| Changelog | `changes/unreleased/*.yaml` | Changie entry per change |
+
+## Files to Change
+
+| File | Action | Why |
+|---|---|---|
+| `scripts/generate-imports.sh` | UPDATE | Gate on the package being a registering service, not on `register.go`. Fail non-zero if the generated list is implausibly short, mirroring the download script's anti-silent-no-op rule. |
+| `cmd/devcloud/imports_test.go` | CREATE | Fail the build if `imports.go` drifts from the service directories — so the generator can never silently gut it again |
+| `internal/codegen/templates/scaffold_provider.go.tmpl` | UPDATE | Return `plugin.ErrUnhandledOp` so a scaffolded service reaches the CRUD engine; carry `cfg.DataDir` in `Init` like hand-written providers |
+| `internal/codegen/scan_handverified.go` | UPDATE | Additionally report, per service, whether its provider is engine-wired (returns `plugin.ErrUnhandledOp`) |
+| `internal/codegen/gen_fidelity.go` | UPDATE | Label `auto-crud` only for engine-wired services; otherwise `unimplemented` |
+| `internal/codegen/scan_handverified_test.go` + a `gen_fidelity` test | UPDATE / CREATE | Cases: wired service ⇒ `auto-crud`; unwired service ⇒ `unimplemented` |
+| `tests/compatibility/conftest.py` | UPDATE | Add one parameterized client fixture over the existing `_make_client`; leave the 104 named fixtures untouched |
+| `tests/compatibility/test_service_smoke.py` | CREATE | Per-service smoke test proving the service routes and serves ≥1 operation |
+| `docs/contributing.md` | UPDATE | Rewrite "Adding a New AWS Service" to the real (now working) steps; delete the two dead ones |
+| `changes/unreleased/Fixed-*.yaml` | CREATE | Changie entries for the import generator and scaffold fixes |
+
+## Tasks
+
+### Task 1: Repair the import generator
+- **Action**: Replace the `register.go` existence check with a check that the
+  package actually registers a service (a `DefaultRegistry.Register(` occurrence
+  in any `.go` file in the directory). After generation, exit non-zero if fewer
+  services were written than a conservative floor — an empty or near-empty
+  `imports.go` must fail loudly, never regenerate green.
+- **Mirror**: `scripts/download-smithy-models.sh:79-88` — the closing block that
+  exits non-zero with a comment naming the silent no-op it prevents.
+- **Validate**: `bash scripts/generate-imports.sh && git diff --exit-code cmd/devcloud/imports.go`
+  — the regenerated file must be byte-identical to what is committed today.
+- **Watch**: the current header does not emit the SPDX line the committed file
+  carries (`scripts/add-spdx-header.sh` adds it separately). Either emit it in
+  the header or run the SPDX script after, or the idempotency check fails on a
+  one-line diff.
+
+### Task 2: Lock `imports.go` against drift
+- **Action**: A Go test asserting every `internal/services/*` package that
+  registers a service appears in `imports.go`, and vice versa.
+- **Mirror**: `cmd/devcloud/conformance_test.go:24` — per-violation `t.Errorf`,
+  a floor constant with a comment explaining the number.
+- **Validate**: `go test ./cmd/devcloud/...`; delete one line from `imports.go`
+  and confirm the test fails.
+
+### Task 3: Make the scaffold meet the quality floor
+- **Action**: In the scaffold template, return `plugin.ErrUnhandledOp` from
+  `HandleRequest` instead of `generated.ErrNotImplemented`, and store
+  `cfg.DataDir` in `Init`. This is what makes a new JSON-protocol service serve
+  its CRUD-shaped operations the moment it is scaffolded.
+- **Mirror**: `docs/crud-engine.md` — "a provider opts in by returning
+  `plugin.ErrUnhandledOp` from its dispatch `default:` case".
+- **Validate**: scaffold one service into a scratch directory, build, start the
+  server, and confirm a `Create*` call returns 200 rather than an error.
+- **Note (corrected during implementation)**: the engine's scope is narrower
+  than "JSON-family". `crud.JSONProtocol` (`internal/shared/crud/crud.go:71`)
+  matches only protocols starting with `json`, so **`rest-json` is out too**,
+  not just Query / EC2 Query / REST-XML. Locally only 39 of 93 models (42%) are
+  `awsJson1_0` / `awsJson1_1`; `rest-json` adds another 27 that a scaffold
+  cannot serve. This shrinks Milestone 4's addressable set and is PRD Open
+  Question 1 — **not** resolved here, see Open Decisions.
+
+### Task 4: Stop the manifest overstating coverage
+- **Action**: Extend the provider scan to record whether each service's dispatch
+  returns `plugin.ErrUnhandledOp`. In `tierFor`, an operation is `auto-crud`
+  only when its service is engine-wired; otherwise it stays `unimplemented`.
+- **Mirror**: `gen_crud_meta.go` — classify only what can be established, skip
+  rather than guess.
+- **Validate**: `make codegen && git diff --stat` — expect **no change** to
+  today's manifest, since all 46 JSON services are already wired. A non-empty
+  diff means the wiring detection is wrong, not that the manifest was wrong.
+- **Why it matters**: without this, Task 3's fix is unverifiable and every
+  scaffolded service inflates the published coverage number.
+
+### Task 5: Remove the per-service fixture cost
+- **Action**: Add one parameterized boto3 client fixture built on the existing
+  `_make_client`, plus a smoke test that, for each service under test, issues one
+  request and asserts the service is routed and serves at least one operation.
+  Leave the 104 existing named fixtures alone — they back real tests, not
+  scaffolding, and rewriting them is out of scope.
+- **Mirror**: `tests/compatibility/conftest.py:126` (`_make_client`) and the
+  assertion style of `test_verifiedpermissions.py`.
+- **Validate**: `make test-compat` — the existing 775 tests stay green and the
+  new smoke test passes for at least one scaffolded service.
+- **Watch**: the smoke test must fail for a service that routes but serves
+  nothing. Confirm by pointing it at a service scaffolded *before* Task 3.
+
+### Task 6: Measure the baseline — the actual deliverable
+- **Action**: Take one JSON-protocol AWS service that is not currently
+  registered, run the full repaired path with a stopwatch, and record each
+  stage: model download, `make codegen` with `-scaffold-output`, import
+  regeneration, build, smoke test, docs. Record wall-clock, lines of
+  hand-written code, and anything that required a human decision. Write the
+  number and the breakdown into the PRD's Success Metrics table.
+- **Validate**: a second, different service reproduces the number within a
+  reasonable margin. One data point is an anecdote.
+- **Output**: the per-service cost figure that Milestone 2 sizes against and
+  that Milestone 3 uses to decide whether 330 services is affordable.
+
+## Validation
+
+```bash
+bash scripts/generate-imports.sh && git diff --exit-code cmd/devcloud/imports.go
+make codegen && git diff --stat          # expect no manifest change from Task 4
+make build
+CGO_ENABLED=0 go test ./...
+make test-compat                          # 775 boto3 tests must stay green
+make stats                                # service count unchanged until Task 6
+make codegen && git diff --exit-code      # generation is idempotent
+```
+
+## Risks
+
+| Risk | Likelihood | Mitigation |
+|---|---|---|
+| Task 1 regenerates `imports.go` with a real diff (SPDX line, ordering), masking whether the fix is correct | High | Make byte-identical regeneration the explicit pass condition; resolve the SPDX gap before touching anything else |
+| Task 3 makes 338 future services serve plausible-but-empty responses, accelerating the breadth-without-depth risk the PRD ranks first | High | This is the intended behaviour of the chosen quality floor, not a defect — Task 4 is the control that keeps the published number honest. Do not merge Task 3 without Task 4. |
+| Task 4's wiring detection misclassifies a provider with an unusual dispatch shape, silently demoting live operations to `unimplemented` | Medium | The no-diff validation over today's 46 wired services is the check; any diff blocks the merge |
+| The weekly sync workflow starts opening PRs again and immediately floods with scaffolded services | Medium | Verify what the repaired workflow produces before merging Task 1; the sync scaffolds from `smithy-models/`, which still holds only 93 models, so nothing new appears until models are added deliberately |
+| The measured baseline is fast but unrepresentative — an easy service chosen first | Medium | Task 6 requires two services; prefer one small and one large rather than two small |
+| Repairing the import generator surfaces that the weekly sync has been failing for a long time, with a backlog of upstream model drift | Medium | Expected. Land the repair first and review the resulting model diff as its own change, not inside this milestone |
+
+## Acceptance
+
+- [ ] All tasks complete
+- [ ] `bash scripts/generate-imports.sh` reproduces the committed `imports.go` byte for byte, and fails loudly on an implausibly short result
+- [ ] A test fails if `imports.go` drifts from the service directories
+- [ ] A freshly scaffolded JSON-protocol service serves its CRUD operations with no hand-written code
+- [ ] The fidelity manifest reports `auto-crud` only for engine-wired services; regenerating produces no diff against today's manifest
+- [ ] `make test-compat` green; a service that routes but serves nothing fails the smoke test
+- [ ] The per-service onboarding cost is a recorded number, reproduced on a second service, written into the PRD
+- [ ] Patterns mirrored (generated-file header, loud-failure scripts, conformance-test style), not reinvented
+
+## Open Decisions for the User
+
+1. **Is the broken weekly sync in scope here, or its own fix?** Task 1 repairs
+   the cause. Whatever upstream model drift accumulated while the job was failing
+   is a separate, potentially large diff that should not ride along in this
+   milestone.
+2. **Which service is the measurement subject?** The plan needs one small and one
+   larger JSON-protocol service not currently registered. `accessanalyzer` is a
+   reasonable first candidate; confirm its protocol after download.
+3. **Non-JSON protocols stay unresolved.** The scaffold fix only helps
+   JSON-family services, so the quality floor remains unreachable for roughly 29%
+   of the surface. That is PRD Open Question 1 and Milestone 5 — flagged here so
+   it is not mistaken for something this milestone closes.
+4. **Should the 104 hand-written fixtures be consolidated?** The plan says no —
+   they back real tests and the parameterized fixture only serves new services.
+   Say so if a consolidation pass is wanted instead.
diff --git a/.claude/plans/fidelity-manifest.plan.md b/.claude/plans/fidelity-manifest.plan.md
new file mode 100644
index 00000000..ff24f0f1
--- /dev/null
+++ b/.claude/plans/fidelity-manifest.plan.md
@@ -0,0 +1,117 @@
+# Plan: Per-Operation Fidelity Manifest
+
+**Source PRD**: `.claude/prds/aws-v1-stabilization.prd.md`
+**Selected Milestone**: 1 — Fidelity manifest
+**Complexity**: Large (1–2 days; Task 1 alone regenerates ~90 packages)
+
+## Summary
+
+Emit a generated, machine-verified manifest declaring every operation's fidelity tier (`hand-verified` / `auto-crud` / `unimplemented`), publish it as docs plus an admin API endpoint, and lock it with a test that fails if any operation is unclassified.
+
+Three mechanical inputs already exist and only need joining: the Smithy models (universe), `crud.RegisteredOps()` (auto-crud), and the `case "OpName"` dispatch literals in each provider (hand-verified). Two prerequisites block a truthful manifest — the parser drops resource-attached operations, and two services carry no op-name literals at all.
+
+## Findings That Shape the Plan
+
+| Finding | Evidence | Consequence |
+|---|---|---|
+| Parser only walks `service.operations`, ignoring `resource` shapes — 285 operations invisible across 5 models (**bedrock 0 of 101**, lambda 19/85, ecs 12/76, transfer 29/71, sso-admin 67/79) | `internal/codegen/parser.go:112`; analysis over `smithy-models/*.json` | The op universe under-reports. `bedrock/provider.go:114` already carries the workaround comment *"since bedrock router is empty"*. Must fix first or the manifest's denominator lies. |
+| 101 of 103 providers dispatch on op-name string literals | `grep -c 'case "'` per service | Hand-verified tier is mechanically extractable for nearly the whole surface. |
+| **s3 and bedrock** route purely on method+path, zero op-name literals | `internal/services/s3/provider.go:89`, `internal/services/bedrock/provider.go:114` | These two need an explicit declared op list; everything else is derived. |
+| 11 services have no Smithy model | `account cloudcontrol codeconnections dms identitystore mediaconvert pipes s3tables scheduler serverlessrepo verifiedpermissions` | Their `unimplemented` tail is not enumerable. Manifest must say so rather than imply full coverage. |
+| `crud.RegisteredOps(service)` already exposes the auto-crud set | `internal/shared/crud/crud.go:62` | No new plumbing for tier 2. |
+| Generated `OperationRoutes` is dead code — only referenced by a codegen test | `internal/codegen/gen_router_test.go:19` | Available to repurpose or delete; not load-bearing. |
+| Admin API is a plain `http.ServeMux` with 3 routes | `internal/admin/api.go:33-35` | Adding `/devcloud/api/fidelity` is a few lines. |
+
+## Patterns to Mirror
+
+| Category | Source | Pattern |
+|---|---|---|
+| Generated file | `internal/generated/crudregistry/registry_gen.go:1-9` | `// Code generated by devcloud codegen. DO NOT EDIT.` + SPDX header, one aggregate file, package doc explaining why it is aggregate |
+| Codegen entry | `internal/codegen/gen_crud_meta.go:145` | `Generate*` method renders a template then `format.Source`; returns `(string, error)` |
+| Classification | `internal/codegen/gen_crud_meta.go:104` | Iterate `model.Operations` in sorted order for reproducible output; skip rather than guess when confidence is low |
+| Conformance test | `cmd/devcloud/conformance_test.go:24` | Iterate the live registry, `t.Errorf` per violation (not `Fatal`), conservative floor constant with a comment explaining the choice |
+| Test framework | 125 `_test.go` files use `stretchr/testify` | `assert.*` / `require.*`, table-driven |
+| Admin handler | `internal/admin/api.go:33` | `mux.HandleFunc("/devcloud/api/x", d.handleX)`, JSON response |
+| Error convention | `docs/plugin-api.md:96-102` | Unknown op → `InvalidAction` 400, never a false success |
+| Changelog | `changes/unreleased/Added-*.yaml` | Changie entry per change (`make changelog`) |
+
+## Files to Change
+
+| File | Action | Why |
+|---|---|---|
+| `internal/codegen/parser.go` | UPDATE | Walk `resource` shapes (`operations`, `collectionOperations`, lifecycle members) so the 285 hidden ops enter `model.Operations` |
+| `internal/codegen/parser_test.go` | UPDATE | Case: a model whose ops hang off a resource shape |
+| `internal/codegen/gen_fidelity.go` | CREATE | Join universe + auto-crud + hand-verified into `FidelityData`; render + `format.Source` |
+| `internal/codegen/scan_handverified.go` | CREATE | `go/ast` walk over `internal/services/*` collecting case literals from the `op`/`action` switch inside `HandleRequest`; holds the s3/bedrock override map |
+| `internal/codegen/templates/fidelity_manifest.go.tmpl` | CREATE | Renders the aggregate manifest |
+| `internal/generated/fidelity/manifest_gen.go` | CREATE (generated) | The artifact: `map[service]map[op]Tier` + `Lookup(service, op)` |
+| `internal/generated/fidelity/manifest_test.go` | CREATE | Coverage test — fails if any op is unclassified or a declared override is absent from the model |
+| `cmd/codegen/main.go` | UPDATE | Wire the new generator into `make codegen` |
+| `internal/admin/api.go` + `api_test.go` | UPDATE | `GET /devcloud/api/fidelity[?service=]` |
+| `docs/fidelity-manifest.md` | CREATE | Tier definitions, how to read it, how to regenerate |
+| `docs/crud-engine.md`, `docs/services-matrix.md` | UPDATE | Link the manifest as the authoritative per-op answer |
+| `changes/unreleased/Added-*.yaml` | CREATE | Changie entry |
+
+## Tasks
+
+### Task 1: Parse resource-attached operations
+- **Action**: In `parser.go`, after collecting `service.operations`, walk each `resource` shape and append its `operations`, `collectionOperations`, and lifecycle targets (`create` / `read` / `update` / `delete` / `list`). Dedupe by shape FQN; keep the existing sort.
+- **Mirror**: existing collection loop at `parser.go:112`, sorted for reproducibility.
+- **Validate**: `go test ./internal/codegen/...`, then `make codegen && make build && make test && make test-compat`. Expect ~285 new ops; bedrock goes 0 → 101.
+- **Watch**: regeneration adds new ops to the CRUD registry, so some operations that returned `InvalidAction` will start returning plausible auto-crud responses. That is a **behavior change** — review the `registry_gen.go` diff before accepting it, and decide whether bedrock's 101 newly-visible ops should be engine-wired at all.
+
+### Task 2: Extract hand-verified operations
+- **Action**: New codegen-side scanner using `go/parser` + `ast.Inspect`, scoped to the `HandleRequest` method body of each `internal/services/*` package: collect string literals from `case` clauses of the switch whose tag is the op variable. Ignore unrelated switches (e.g. `dynamodb/expression.go:527`).
+- **Mirror**: `gen_crud_meta.go` classification style — skip what cannot be classified with confidence rather than guessing.
+- **Override**: a small explicit map for `s3` and `bedrock` (path-routed, no literals), with a comment naming the ceiling and the upgrade path (declare ops next to the provider if the list grows).
+- **Validate**: unit test asserting a known service resolves its known ops (e.g. `acm` includes `DescribeCertificate`, `sqs` includes `SendMessage`), and that `s3` / `bedrock` resolve from the override.
+
+### Task 3: Generate the manifest
+- **Action**: Join per service — universe (model ops, or `hand-verified ∪ auto-crud` when no model exists), `crud.RegisteredOps`, and the Task 2 set. Precedence is **hand-verified > auto-crud > unimplemented** (hand-written always wins, per `docs/crud-engine.md:37`). Emit `internal/generated/fidelity/manifest_gen.go` with counts per tier, a `ModelBacked bool` per service, and `Lookup(service, op) Tier`.
+- **Mirror**: `GenerateCRUDRegistry` (`gen_crud_meta.go:145`) and the aggregate-file rationale in `registry_gen.go:5-7`.
+- **Validate**: `make codegen` is idempotent — running twice leaves the tree clean (`git diff --exit-code`).
+
+### Task 4: Lock it with a test
+- **Action**: `manifest_test.go` asserts (a) every entry has a non-empty tier from the closed set, (b) every op in `crud.RegisteredOps` appears as `auto-crud` **or** `hand-verified`, (c) every override op exists in its service's universe, (d) a conservative floor on service and op counts.
+- **Mirror**: `cmd/devcloud/conformance_test.go:24` — per-violation `t.Errorf`, floor constant with a comment.
+- **Validate**: `go test ./internal/generated/fidelity/...`; deliberately corrupt one entry and confirm the test fails.
+
+### Task 5: Publish
+- **Action**: Add `GET /devcloud/api/fidelity` (optional `?service=`) returning the manifest as JSON. Write `docs/fidelity-manifest.md`; link it from `crud-engine.md` and `services-matrix.md`. Add the Changie entry.
+- **Mirror**: `internal/admin/api.go:33-35` handler + `api_test.go` style.
+- **Validate**: `go test ./internal/admin/...`; `make run` then `curl -s localhost:4747/devcloud/api/fidelity | head`.
+
+## Validation
+
+```bash
+make codegen && git diff --stat          # review the regenerated surface
+make build
+make test
+make test-compat                          # 729 boto3 tests must stay green
+go test ./internal/codegen/... ./internal/generated/fidelity/... ./internal/admin/...
+make codegen && git diff --exit-code      # generation is idempotent
+```
+
+## Risks
+
+| Risk | Likelihood | Mitigation |
+|---|---|---|
+| Task 1 silently widens auto-crud coverage — ops that honestly returned `InvalidAction` begin returning plausible responses | High | Review the `registry_gen.go` diff explicitly; decide per newly-exposed service whether engine-wiring is wanted before merging |
+| Large regenerated diff hides a real break | Medium | Land Task 1 as its own commit gated on `make test-compat`; nothing else in the same commit |
+| AST scanner misses a provider with a non-standard dispatch shape (beyond s3/bedrock) | Medium | Task 4's floor check plus a per-service assertion that any service with 0 hand-verified ops is on the override list — a new silent zero fails the build |
+| Manifest asserts "100% classified" over an incomplete universe (11 model-less services) | Medium | Carry `ModelBacked: false` per service and state the limit in `docs/fidelity-manifest.md`; do not claim enumerable `unimplemented` where no model exists |
+| Manifest drifts from code | Low | Generated only, never hand-edited; idempotency check in CI |
+
+## Acceptance
+
+- [ ] All tasks complete
+- [ ] Validation passes, including `make test-compat` green
+- [ ] Every operation carries a tier from the closed set; the test fails if any does not
+- [ ] `s3` and `bedrock` classified via explicit override, documented as such
+- [ ] Patterns mirrored (generated-file header, codegen `Generate*` shape, conformance-test style), not reinvented
+
+## Open Decisions for the User
+
+1. **Task 1 in or out of this milestone?** It is the only thing standing between the manifest and a truthful denominator, but it is also the largest and riskiest diff. Splitting it out ships a manifest whose `unimplemented` counts are wrong for 5 services.
+2. **Do newly-visible bedrock / lambda / ecs ops get engine-wired?** Fixing the parser makes them classifiable; whether they should be *served* is a separate call.
+3. **Endpoint, docs, or both?** Plan assumes both (the admin mux makes the endpoint nearly free). Say so if docs-only is preferred.
diff --git a/.claude/plans/promotion-pass.plan.md b/.claude/plans/promotion-pass.plan.md
new file mode 100644
index 00000000..9f46ce8d
--- /dev/null
+++ b/.claude/plans/promotion-pass.plan.md
@@ -0,0 +1,142 @@
+# Plan: High-Value Promotion Pass
+
+**Source PRD**: `.claude/prds/aws-v1-stabilization.prd.md`
+**Selected Milestone**: 3 — High-value promotion pass
+**Complexity**: Small (half a day) — *after* cutting the milestone to what the data supports
+
+## Summary
+
+The milestone assumed a long list of frequently-called operations sitting at `auto-crud`
+that users would want promoted. Now that the manifest exists, that list can be read instead
+of guessed — and it is almost empty. What remains worth promoting is **8 tag operations
+across 3 services**, where DevCloud is simply inconsistent with itself.
+
+The rest of this plan argues for *not* doing the bulk of the milestone, and for replacing
+it with a written promotion policy.
+
+## The finding that reshapes this milestone
+
+957 `auto-crud` operations sit in 19 services; the top four hold 67% of them:
+
+| Service | auto-crud | hand-verified | Tier |
+|---|---:|---:|---|
+| sagemaker | 280 | 65 | 3 |
+| glue | 169 | 65 | 3 |
+| ssm | 112 | 19 | 2 |
+| cloudwatchlogs | 79 | 23 | 2 |
+| ecr | 31 | 25 | 2 |
+| eventbridge | 29 | 24 | 2 |
+| dynamodb | 28 | 20 | **1** |
+| cloudwatch | 20 | 20 | 2 |
+| kms | 14 | 28 | 2 |
+
+Reading what those operations actually *are* is what changes the plan. The Tier 1 service's
+28 are: `CreateBackup`, `CreateGlobalTable`, `DescribeContributorInsights`,
+`DescribeKinesisStreamingDestination`, `ListExports`, `UpdateTableReplicaAutoScaling` …
+— backup, global replication, export/import and operational insight. A developer running
+`put_item` and `query` against a local DynamoDB never calls one of them. The same holds
+elsewhere: kms's are CloudHSM custom key stores and key rotation; cloudwatch's are Insight
+Rules and Metric Streams; ecr's are pull-through cache, registry policy and signing
+configuration.
+
+**The operations that matter in a local inner loop are already hand-verified.** s3, sqs,
+lambda, iam and sts have zero `auto-crud` operations — nothing left to promote.
+
+So "promote the top-N high-value operations" describes work that mostly does not exist. The
+one genuine gap is narrower and sharper.
+
+### The real gap: tag operations
+
+| Operation | Still `auto-crud` in |
+|---|---|
+| `TagResource` | cloudwatch, eventbridge, kms |
+| `UntagResource` | cloudwatch, eventbridge, kms |
+| `ListTagsForResource` | cloudwatch, eventbridge |
+
+**64 services already implement these by hand** on the shared `TagStore`
+(`internal/shared/tags.go`). These three are the stragglers — not a judgement call about
+value, just an inconsistency. Tagging is also something local code genuinely does, and
+`auto-crud` handles it badly: the engine echoes input rather than persisting tags against
+an ARN, so `TagResource` followed by `ListTagsForResource` does not round-trip correctly.
+
+## Patterns to Mirror
+
+| Category | Source | Pattern |
+|---|---|---|
+| Tag dispatch | `internal/services/ecr/provider.go:118-123` | `case "TagResource": return p.handleTagResource(params)` — three cases delegating to handlers |
+| Tag storage | `internal/shared/tags.go:26-71` | `NewTagStore(db)` with `AddTags` / `RemoveTags` / `ListTags` / `DeleteAllTags`, keyed by ARN |
+| ARN building | `internal/shared/arn.go` | shared ARN construction rather than per-service string building |
+| Compat test | `tests/compatibility/test_ecr.py` | boto3 round-trip: tag → list → untag → list |
+| Tier movement | `internal/generated/fidelity/manifest_gen.go` | regenerating reclassifies automatically; no manual bookkeeping |
+
+## Files to Change
+
+| File | Action | Why |
+|---|---|---|
+| `internal/services/kms/provider.go` (+ store) | UPDATE | Add the tag cases on `TagStore` |
+| `internal/services/cloudwatch/provider.go` (+ store) | UPDATE | Same |
+| `internal/services/eventbridge/provider.go` (+ store) | UPDATE | Same |
+| `tests/compatibility/test_{kms,cloudwatch,eventbridge}.py` | UPDATE | boto3 tag round-trip per service |
+| `internal/generated/fidelity/manifest_gen.go` | REGENERATE | 8 operations move `auto-crud` → `hand-verified` |
+| `docs/fidelity-manifest.md` | UPDATE | Add the promotion policy section (Task 3) |
+| `changes/unreleased/Added-*.yaml` | CREATE | Changie fragment |
+
+## Tasks
+
+### Task 1: Promote the tag operations
+- **Action**: For kms, cloudwatch and eventbridge, wire `TagResource` / `UntagResource` /
+  `ListTagsForResource` onto the shared `TagStore`, keyed by the resource ARN the service
+  already builds. kms names its lister `ListResourceTags` — also `auto-crud`, so include it.
+- **Mirror**: `internal/services/ecr/provider.go:118-123` plus its handlers.
+- **Validate**: `go test ./internal/services/{kms,cloudwatch,eventbridge}/`.
+
+### Task 2: Prove the round-trip in boto3
+- **Action**: Per service, a compat test that tags a real resource, lists tags, untags, and
+  lists again — the round-trip `auto-crud` cannot do.
+- **Mirror**: `tests/compatibility/test_ecr.py`.
+- **Validate**: `make test-compat` stays green and covers the new paths.
+
+### Task 3: Write the promotion policy instead of promoting more
+- **Action**: A section in `docs/fidelity-manifest.md` stating how an operation moves from
+  `auto-crud` to `hand-verified`: **on request, with the requester's use case**, via a
+  GitHub issue — not by maintainer guesswork. Point at the manifest as the way to check a
+  tier before filing. Record explicitly that the remaining ~949 `auto-crud` operations are
+  overwhelmingly operational/replication surface with no inner-loop role, and that v1.0
+  ships them declared rather than implemented.
+- **Validate**: the claim matches the manifest; no promise the repo cannot keep.
+
+### Task 4: Regenerate and confirm the move
+- **Action**: `make codegen`; verify the 8 operations changed tier and nothing else did.
+- **Validate**: `git diff internal/generated/fidelity/` shows exactly the expected lines.
+
+## Validation
+
+```bash
+go test ./...
+make test-compat
+make codegen && git diff --stat internal/generated/fidelity/
+```
+
+## Risks
+
+| Risk | Likelihood | Mitigation |
+|---|---|---|
+| Promoting tags changes behaviour for callers relying on the engine's echo | Low | The engine never persisted tags; a real round-trip is strictly more correct. Compat tests pin the new behaviour |
+| "We promoted only 8 operations" reads as a thin milestone | High | It is the honest read of the data. The deliverable is the policy plus the manifest, not a promotion count |
+| A service's ARN construction differs from what TagStore expects | Medium | Reuse `internal/shared/arn.go`; assert the ARN in a unit test before wiring the handler |
+
+## Acceptance
+
+- [ ] Tag operations serve real, persisted tags across kms, cloudwatch, eventbridge
+- [ ] boto3 round-trip (tag → list → untag → list) passes per service
+- [ ] Manifest regenerated; exactly those operations moved tier
+- [ ] Promotion policy documented, with the remaining auto-crud surface characterised honestly
+- [ ] `make test-compat` green
+
+## Open Decision
+
+**Is cutting the milestone to 8 operations acceptable?** The alternative is promoting all
+313 `auto-crud` operations in Tier 1/2 services — weeks of work on backup, global-table,
+Insight Rule and pull-through-cache surface that a local development companion has no
+inner-loop use for. My recommendation is the cut: ship the manifest's honesty plus the tag
+fix, and let real requests drive promotion in 1.x.
diff --git a/.claude/plans/release-hardening.plan.md b/.claude/plans/release-hardening.plan.md
new file mode 100644
index 00000000..f2f5bb18
--- /dev/null
+++ b/.claude/plans/release-hardening.plan.md
@@ -0,0 +1,170 @@
+# Plan: Release Process Hardened
+
+**Source PRD**: `.claude/prds/aws-v1-stabilization.prd.md`
+**Selected Milestone**: 4 — Release process hardened
+**Complexity**: Small (half a day)
+
+## Summary
+
+`docs/release.md` already documents SemVer, Changie and GoReleaser end to end, so the
+*procedure* exists. What is missing is enforcement: four defects let a bad v1.0 ship today,
+and every one of them is caught by a check the repo does not run. This plan adds the checks
+and turns the prose into a pre-flight checklist.
+
+## The four defects that block a trustworthy v1.0 tag
+
+Each was reproduced against the current tree.
+
+### 1. The fidelity manifest can drift silently — the headline v1.0 artifact
+
+`internal/generated/fidelity/manifest_gen.go` is committed (one of 370 tracked files under
+`internal/generated`), generated from provider dispatch by `make codegen`. **No CI job
+verifies the committed output still matches its sources.**
+
+`cmd/devcloud/fidelity_test.go` guards the manifest in three directions — floors
+(`minServices 100`, `minOperations 6000`, line 28-31), every registered service present
+(line 68), every CRUD-engine operation classified (line 79). None of them fire when a
+contributor adds a `case "NewOp":` to a provider's dispatch switch and forgets to
+regenerate: the operation is simply absent, and absence from a 7,475-entry map is invisible.
+
+The PRD's primary metric is *"100% of reachable operations carry a declared fidelity tier,
+enforced by a test that fails the build if any operation is unclassified"*. It is enforced
+for two of the three ways an operation becomes reachable.
+
+### 2. Eight changelog fragments render broken links
+
+`.changie.yaml` declares `Issue` as `type: int, minInt: 1` and `changeFormat` interpolates
+it twice. Eight fragments carry `Issue: ""`. Verified with `changie batch v9.9.9 --dry-run`:
+
+```
+* Per-operation fidelity manifest ... ([#](https://github.com/skyoo2003/devcloud/issues/))
+```
+
+`changie batch` exits 0 — it does not validate custom fields on hand-written fragments. Those
+eight lines would ship in `CHANGELOG.md` and in the v1.0 GitHub Release notes verbatim. All
+eight are from this session's two PRs and are trivially fixable; the durable fix is the check.
+
+### 3. One fragment is in a directory nothing reads
+
+`.changes/unreleased/Fixed-113.yaml` sits beside the real `changes/unreleased/` (25
+fragments). `.changie.yaml` sets `changesDir: changes`, so this fragment is silently
+excluded from every release.
+
+### 4. Pushing a tag publishes without running the test suite
+
+`.github/workflows/release.yml` verifies `changes/<tag>.md` exists (line 49-55) and then
+runs GoReleaser. It has no `needs:` on CI. `ci.yml` does trigger on `tags: ["v*"]`, but the
+two workflows race — a red tag still publishes binaries, container images and a Homebrew
+formula. `compat.yml` does not run on tags at all.
+
+## Patterns to Mirror
+
+| Category | Source | Pattern |
+|---|---|---|
+| Release-blocking guard | `.github/workflows/release.yml:49-55` | Shell check + `::error::` annotation naming the fix command, then `exit 1` |
+| Conservative test floor | `cmd/devcloud/fidelity_test.go:28-31` | Assert a floor, not an exact count; `t.Errorf` per violation so all failures surface |
+| Docs cross-link | `docs/release.md:15-16` | Table row per pipeline, linking the workflow file |
+| Deprecation in practice | `internal/config/config.go:138-145` | Honour the old key one release, warn, then remove |
+
+## Files to Change
+
+| File | Action | Why |
+|---|---|---|
+| `.github/workflows/ci.yml` | UPDATE | New `codegen-drift` job: regenerate, fail on diff |
+| `.github/workflows/release.yml` | UPDATE | Gate publishing on the test suite; validate fragment issue numbers |
+| `changes/unreleased/*.yaml` (8) | UPDATE | Fill the empty `Issue` fields (#126) |
+| `.changes/unreleased/Fixed-113.yaml` | MOVE | Into `changes/unreleased/` so it reaches a release |
+| `docs/release.md` | UPDATE | Pre-flight checklist; deprecation step; link the policy |
+| `.goreleaser.yaml` | UPDATE | Ship `docs/` in the archive — "versioned docs", by tag |
+| `changes/unreleased/Changed-*.yaml` | CREATE | Changie fragment for this work |
+
+## Tasks
+
+### Task 1: Close the codegen-drift hole
+- **Action**: add a `codegen-drift` job to `ci.yml` — `make codegen`, then
+  `git diff --exit-code internal/generated`. On failure, `::error::` telling the contributor
+  to run `make codegen` and commit.
+- **Mirror**: the error-annotation style of `release.yml:52-53`.
+- **Validate**: add `case "Bogus":` to any provider, push → job fails. Revert → green.
+- **Note**: this is the check that makes the PRD's primary metric true rather than
+  approximately true. It belongs in CI, not in a Go test, because it needs the generator to
+  run against the working tree.
+
+### Task 2: Validate changelog fragments
+- **Action**: extend the existing "Verify changie release notes exist" step in
+  `release.yml` to also reject a batched version file containing `issues/)` — the signature
+  of an empty issue number. One `grep -q`, no new tooling.
+- **Validate**: `grep -c 'issues/)' changes/v9.9.9.md` on a dry batch returns 8 before the
+  fragment fix, 0 after.
+
+### Task 3: Fix the fragments and the stray directory
+- **Action**: set `Issue: "126"` on the eight empty fragments; `git mv` the stray
+  `.changes/unreleased/Fixed-113.yaml` into `changes/unreleased/` and remove the empty
+  `.changes/` tree.
+- **Validate**: `changie batch v9.9.9 --dry-run | grep -c 'issues/)'` → 0, and the batch
+  includes 26 entries.
+
+### Task 4: Gate the release on green tests
+- **Action**: add a `test` job to `release.yml` that runs `CGO_ENABLED=1 go test ./...`, and
+  `needs: test` on the release job. Skip on `dry_run` only if the dry run is meant to be
+  fast — default is to run it there too.
+- **Decision**: duplicate the job rather than `workflow_run` on CI. A `workflow_run` trigger
+  cannot block a tag push, and reusable-workflow plumbing costs more than a 12-line job.
+- **Validate**: dispatch the workflow with `dry_run: true` on a commit with a deliberately
+  failing test → no artifacts published.
+
+### Task 5: Turn release.md into a checklist
+- **Action**: add a **Pre-flight** section ahead of "Cutting a release" — main green,
+  `make codegen` clean, `make test-compat` green, every fragment has an issue number,
+  `changes/unreleased/` non-empty, and *"if this release removes a deprecated key, confirm it
+  shipped with a warning in the previous release"* (the `dashboard` → `admin` precedent at
+  `internal/config/config.go:138-145`). Cross-link `docs/compatibility-policy.md`.
+- **Dependency**: the deprecation *policy text* is Milestone 2's Task 1. This plan links to
+  it; if M2 lands after this, leave the link and land M2's file to resolve it.
+
+### Task 6: Versioned docs, the lazy version
+- **Action**: add `docs/` to `.goreleaser.yaml:31-34`'s archive `files:` list. Docs are then
+  versioned by tag — reading docs at `v1.0.0` gives v1.0 docs, and the downloaded archive
+  carries the fidelity manifest and compatibility policy matching the binary.
+- **Skipped**: a versioned docs site (Docusaurus/mkdocs + per-version builds). Add when docs
+  need to be browsable without a checkout — not before v1.0.
+
+## Validation
+
+```bash
+# defect reproduction, before the fix
+changie batch v9.9.9 --dry-run | grep -c 'issues/)'   # 8 -> 0 after Task 3
+
+# the new guard
+make codegen && git diff --exit-code internal/generated
+
+# unchanged guardrails
+CGO_ENABLED=1 go test ./... && make test-compat
+golangci-lint run ./...
+```
+
+## Risks
+
+| Risk | Likelihood | Mitigation |
+|---|---|---|
+| `make codegen` is not byte-reproducible (map iteration order, timestamps) — the drift job flakes | Medium | Verify by running it twice on a clean tree before wiring CI; if unstable, sort at generation time rather than relaxing the check |
+| Codegen needs `smithy-models/` present in CI | Medium | Already checked in; confirm the job does not need `smithy-sync.yml`'s network fetch |
+| Duplicating the test job slows tag pushes by ~1 min | Low | Accepted — a wrong publish costs more than a minute |
+| `docs/` in the archive bloats it | Low | Docs are markdown; measured impact is tens of KB |
+
+## Acceptance
+
+- [ ] A provider dispatch case added without `make codegen` fails CI
+- [ ] `changie batch --dry-run` produces zero empty issue links
+- [ ] `Fixed-113.yaml` reaches the changelog; no stray `.changes/` tree
+- [ ] A red commit cannot publish a release
+- [ ] `docs/release.md` opens with a pre-flight checklist, including the deprecation check
+- [ ] `make test-compat` green
+
+## Open Decision
+
+**Does the drift job run `make codegen` (all 104 services, from `smithy-models/`) or only the
+fidelity scan?** Full codegen is the honest check but is the slower and more fragile of the
+two. Default: full codegen, on the grounds that stale generated code is a release defect
+whether or not it is the manifest. Fall back to a fidelity-only job if the full run proves
+non-reproducible.
diff --git a/.claude/plans/stability-policy.plan.md b/.claude/plans/stability-policy.plan.md
new file mode 100644
index 00000000..8ea3dca9
--- /dev/null
+++ b/.claude/plans/stability-policy.plan.md
@@ -0,0 +1,168 @@
+# Plan: v1.0 Stability Policy
+
+**Source PRD**: `.claude/prds/aws-v1-stabilization.prd.md`
+**Selected Milestone**: 2 — Stability policy published
+**Complexity**: Small (half a day)
+
+> Refreshed 2026-08-09 against the tree at `6d5e66b`, after #126/#127/#128 landed.
+> The earlier draft of this plan predated them and cited stale counts and a stray
+> `.changes/` tree that #127 removed.
+
+## Summary
+
+Write down what v1.0 promises across the **surfaces users actually touch**, and lock the
+promise with tests that fail on drift. The repo already documents a v1.x guarantee, but it
+covers the wrong thing.
+
+## The finding that shapes this plan
+
+`docs/plugin-api.md:128-139` is the only stability policy in the repo, and it guarantees
+`ServicePlugin`, `PluginConfig`, `Response`, `Resource` and the `ProtocolType` constants
+across v1.x. Every one of those lives in `internal/plugin` — and the same document says so
+at `docs/plugin-api.md:7-9`: *"The package lives under `internal/` for that reason."*
+
+Go forbids importing `internal/` from another module. **The only documented v1.0 guarantee
+therefore applies to nobody.** It is worth keeping — it constrains in-tree contributors —
+but it is not the promise a user of v1.0 needs.
+
+The surfaces a user is actually exposed to, none of which carry a policy today:
+
+| Surface | Inventory (verified in tree) |
+|---|---|
+| HTTP wire behaviour | AWS API on port 4747; 775 boto3 compat tests — `docs/services-matrix.md:3` |
+| Config file | `server.port`, `services.<id>.{enabled,data_dir}`, `admin.enabled`, `logging.{level,format}` — `internal/config/config.go:27-73` |
+| Config, deprecated | `dashboard.enabled` (warns, still honoured) — `config.go:33-37,140-145` |
+| Config, removed | `auth.enabled` (warns, ignored) — `config.go:39-43,153-160` |
+| Environment | `DEVCLOUD_PORT`, `DEVCLOUD_SERVICES`, `DEVCLOUD_DATA_DIR` — `config.go:227-237` |
+| CLI | `-config` — `cmd/devcloud/main.go:33` |
+| Admin API | `/devcloud/api/{services,services/,logs,fidelity}` — `internal/admin/api.go:34-37` |
+| Fidelity tiers | `hand-verified` / `auto-crud` / `unimplemented` as names with meaning — `docs/fidelity-manifest.md` |
+
+### The second finding: the admin snapshot tests do not snapshot anything
+
+`internal/admin/api_test.go:75` decodes the response into the internal `serviceInfo` struct.
+Renaming a JSON tag renames it on both sides of the assertion, so the test stays green while
+every consumer breaks. Same for `TestAPI_Fidelity`. Task 3 exists because of this.
+
+## Resolved decisions
+
+**Wire-behaviour guarantee is compat-suite-scoped** (PRD open question #2, and this plan's
+prior open decision). 1.x guarantees the response shape of hand-verified operations *that
+`tests/compatibility/` covers*. The suite is the enforcement; prose is not. Hand-verified
+operations with no test get best-effort language, not a promise. This keeps the Phase 2
+IR/`ModelSource` refactor unblocked, which is the risk the PRD flags as Medium/High.
+
+**Service coverage additions are minor-version, not breaking** (PRD open question #3).
+Adding a service or promoting `unimplemented` → served only adds surface.
+
+**Fidelity manifest ships as both docs and a runtime endpoint** (PRD open question #4).
+Already true: `docs/fidelity-manifest.md` + `/devcloud/api/fidelity`. The policy documents
+it rather than deciding it.
+
+## Patterns to Mirror
+
+| Category | Source | Pattern |
+|---|---|---|
+| Policy prose | `docs/plugin-api.md:128-139` | Bulleted guarantee, then "any breaking change requires a major bump" |
+| Deprecation in practice | `internal/config/config.go:140-145` | Honour the old key one release, warn, document the migration |
+| Drift test | `cmd/devcloud/fidelity_test.go:24-50` | Closed set + conservative floor, `t.Errorf` per violation so all failures surface |
+| Docs index | `docs/README.md:7-12` | One line per doc with a "what it is" clause |
+
+## Files to Change
+
+| File | Action | Why |
+|---|---|---|
+| `docs/compatibility-policy.md` | CREATE | The v1.0 promise: guaranteed, not guaranteed, deprecation procedure |
+| `internal/config/config_test.go` | UPDATE | Snapshot guaranteed config keys + env vars — removing one fails the build |
+| `internal/admin/api_test.go` | UPDATE | Snapshot route set and response keys via `map[string]any`, not the internal struct |
+| `docs/plugin-api.md` | UPDATE | Scope its guarantee to in-tree contributors; link the user-facing policy |
+| `docs/README.md` | UPDATE | Index the new doc; also fix "101 services" → 104 and add the missing `plugin-api` / `crud-engine` / `fidelity-manifest` rows |
+| `README.md` | UPDATE | Index the new doc in the `docs/` quick-links block (lines 60-67) |
+| `docs/release.md` | UPDATE | Resolve the dangling cross-link the pre-flight checklist expects — closes M4's residual |
+| `changes/unreleased/Added-*.yaml` | CREATE | Changie fragment with a non-empty `Issue` (`release.yml:225` rejects otherwise) |
+
+## Tasks
+
+### Task 1: Write the policy
+- **Action**: `docs/compatibility-policy.md` with three sections.
+  - **Guaranteed across 1.x** — config keys and env vars keep their meaning; admin API
+    responses only gain fields, never remove or repurpose one; the three tier names keep
+    their meaning; hand-verified operations covered by `tests/compatibility/` keep their
+    response shape; `-config` keeps its meaning.
+  - **Not guaranteed** — `auto-crud` response *content* (948 operations, "plausible, not
+    faithful", per `docs/crud-engine.md`); hand-verified operations with no compat test;
+    in-memory/on-disk store durability across restarts and versions; `unimplemented` →
+    served transitions; new service coverage; error message wording; anything under
+    `internal/`, explicitly including the Phase 2 IR and `ModelSource` work.
+  - **Deprecation procedure** — one-release overlap with a runtime warning before removal,
+    mirroring `dashboard` → `admin` (`config.go:140-145`) and the removed `auth` key
+    (`config.go:153-160`); removal without that overlap is a major bump.
+- **Mirror**: the bulleted-guarantee shape of `docs/plugin-api.md:128-139`.
+- **Validate**: every claim traceable to a file:line in the inventory table above. No promise
+  the repo has no mechanism to keep.
+
+### Task 2: Lock the config surface
+- **Action**: table-driven test asserting each guaranteed key parses onto the expected field,
+  each of the three env vars overrides as documented, and the deprecated/removed keys still
+  warn. One case per guaranteed surface element.
+- **Mirror**: `TestLoadConfig_DefaultFile` (`config_test.go:116`), `TestParse_DeprecatedDashboardKey`
+  (`:200`), `TestParse_RemovedAuthKeyWarns` (`:213`).
+- **Validate**: delete a field from `Config` → the test fails to compile or asserts false.
+
+### Task 3: Lock the admin surface
+- **Action**: assert the exact route set (4 paths), and decode each response into
+  `map[string]any` to assert the documented **keys are present** — not into the internal
+  struct, which is what makes the current tests blind to renames.
+- **Mirror**: the request/recorder setup of `TestAPI_Services` (`api_test.go:54`); the
+  per-violation `t.Errorf` style of `fidelity_test.go`.
+- **Validate**: rename a JSON tag in `internal/admin/api.go` → test fails. It does not today.
+
+### Task 4: Cross-link and publish
+- **Action**: scope `docs/plugin-api.md:128` to in-tree contributors and link the new policy;
+  add the policy to both index files, correcting `docs/README.md`'s stale service count and
+  missing rows while there; cross-link from `docs/release.md`'s pre-flight checklist, which
+  M4 wrote expecting this file; add the Changie fragment.
+
+## Validation
+
+```bash
+CGO_ENABLED=0 go test ./internal/config/ ./internal/admin/ ./cmd/devcloud/
+CGO_ENABLED=0 go test ./... && make test-compat
+golangci-lint run ./...
+
+# the fragment must satisfy the release gate
+changie batch v9.9.9 --dry-run | grep -c 'issues/)'   # 0
+
+# no dead links in the new doc
+grep -o '](\.\./[^)]*' docs/compatibility-policy.md | cut -d'(' -f2 | while read -r p; do
+  [ -e "docs/$p" ] || echo "dead: $p"
+done
+```
+
+## Risks
+
+| Risk | Likelihood | Mitigation |
+|---|---|---|
+| Policy over-promises and blocks the Phase 2 refactor | Medium | Guarantee user-facing surfaces only; state in writing that `internal/`, the IR layer and `ModelSource` are unconstrained across 1.x |
+| "hand-verified keeps its response shape" is stronger than the code can hold | Medium | Resolved above — scoped to what the 775-test compat suite covers; the suite is the enforcement |
+| Snapshot tests become churn on every additive change | Low | Assert key *presence*, never full payload equality — additive change stays green by construction |
+| `docs/README.md` fixes balloon the diff | Low | Limit to the service count and the three missing rows; anything else is a separate issue |
+
+## Acceptance
+
+- [x] `docs/compatibility-policy.md` states guaranteed / not-guaranteed / deprecation per surface
+- [x] Wire guarantee is compat-suite-scoped and says so
+- [x] `plugin-api.md`'s guarantee is scoped to in-tree contributors
+- [x] Renaming an admin JSON tag or dropping a config key fails the build — reproduced both:
+      `json:"resourceCount"` → `resource_count` and `yaml:"format"` → `fmt`, each failing with a
+      message naming the policy, then reverted
+- [x] `docs/release.md`'s pre-flight cross-link resolves — M4 residual closed
+- [x] `CGO_ENABLED=0 go test ./...` green; boto3 suite 775 passed
+- [x] Changie fragment present with a non-empty issue number (`#129`); dry batch renders 29
+      entries, 0 dead issue links
+
+## Follow-on (not this plan)
+
+M4 is otherwise complete (#127). After this lands, the only remaining milestone is **M5 —
+tag v1.0**, which is the pre-flight checklist at `docs/release.md:38-65`, then
+`make changelog VERSION=v1.0.0` and a tag push.
diff --git a/.claude/plans/v1-tag.plan.md b/.claude/plans/v1-tag.plan.md
new file mode 100644
index 00000000..116eb90f
--- /dev/null
+++ b/.claude/plans/v1-tag.plan.md
@@ -0,0 +1,204 @@
+# Plan: v1.0 Tagged
+
+**Source PRD**: `.claude/prds/aws-v1-stabilization.prd.md`
+**Selected Milestone**: 5 — v1.0 tagged
+**Complexity**: Small (~2 hours, most of it waiting on the release workflow)
+
+## Summary
+
+Milestones 1–4 built everything the tag depends on: the fidelity manifest, the compatibility
+policy, the promotion pass and policy, and a release workflow that refuses to publish off a red
+commit. The pre-flight in `docs/release.md` passes locally today, verified below.
+
+What is left is not engineering. It is three documents that still declare the project pre-1.0
+and would ship *inside* the v1.0 archive saying so, PRD bookkeeping that contradicts what M3
+delivered, one unexercised step in the release path, and the execution itself.
+
+## Pre-flight, run against the current tree (2026-08-11, `4ffafe0`)
+
+| Check | Command | Result |
+|---|---|---|
+| Go tests | `CGO_ENABLED=0 go test ./...` | pass |
+| boto3 compatibility | `make test-compat` | **775 passed** in 10.45s |
+| Fragments carry issue numbers | `grep -L 'Issue: "[0-9]' changes/unreleased/*.yaml` | no output |
+| Release notes render | `changie batch v1.0.0 --dry-run` | 33 entries, **0** empty issue links |
+| `changes/unreleased/` non-empty | `ls` | 33 fragments |
+| Codegen drift | `rm -rf internal/generated && make codegen` | **not run** — mutates the tree; Task 1 |
+
+Only the drift check is outstanding, and the release workflow re-runs it on the tag
+(`release.yml:85-112`) before anything publishes.
+
+## What actually blocks the tag
+
+### 1. Three files ship inside the v1.0 archive announcing that v1.0 has not happened
+
+`.goreleaser.yaml:31-49` puts the whole `docs/` tree and `GOVERNANCE.md` in every archive —
+added in #127 and **not yet in any release**, so v1.0 is the first tag where these are user-facing
+artifacts rather than repo files.
+
+- `docs/roadmap.md:30` — `- [ ] v1.0 release (pending maintainer tag)`
+- `docs/roadmap.md:78` — `| 0.x ← current | AWS services, unstable API |`
+- `GOVERNANCE.md:5,11` — `## Current state (0.x)` … *"while the project is pre-1.0"*
+
+Unpacking `devcloud_v1.0.0_linux_amd64.tar.gz` would hand a user a roadmap saying the release
+they just downloaded is pending, and a governance doc calling the API unstable — directly
+contradicting `docs/compatibility-policy.md`, which ships beside it.
+
+### 2. GoReleaser is the one step in the release path with no rehearsal
+
+The `dry_run` dispatch cannot rehearse an unreleased version: `resolve` checks out
+`github.event.inputs.tag` (`release.yml:41-44`), so the tag must already exist — and any `v*`
+tag push publishes for real (`release.yml:3-6`). The three gate jobs cover tests, drift and
+compat; GoReleaser itself has not run since `.goreleaser.yaml` gained `docs`, `dockers_v2` and
+the archive file list.
+
+Fix is local, not more CI: `goreleaser release --snapshot --clean --skip=publish,docker`.
+
+### 3. No release candidate — and the config would mis-publish one anyway
+
+`.goreleaser.yaml` sets no `release.prerelease`, so it defaults to `false`. A `v1.0.0-rc1` tag
+would publish as a **full latest release**, push the Homebrew formula (`brews:` has no
+`skip_upload: auto`), and move `latest-alpine`, `v1-alpine` and `v1.0-alpine`
+(`.goreleaser.yaml:88-92`).
+
+**Decision: no rc.** The defect class that made v0.2.0's binaries unusable (#128 — every
+published binary exited at startup) is now caught before publishing, because the `compat` gate
+builds with `CGO_ENABLED=0` and runs all 775 boto3 tests against that exact binary
+(`release.yml:130-134`). An rc would cost a `prerelease: auto` change plus brew/tag guards for
+coverage the gates already provide. If the maintainer wants one anyway, that config change lands
+first — it is a prerequisite, not an option.
+
+### 4. The PRD contradicts its own delivered milestone
+
+Success Metrics row 3 still reads *"TBD — count and selection criteria to be set during /plan"*
+and Open Question 1 is unchecked, although M3 answered both: **8 tag operations promoted**, and
+promotion is on request with a stated use case
+(`.claude/plans/promotion-pass.plan.md:11,99-101`). Tagging v1.0 against a PRD whose primary
+artifact is honesty, while the PRD itself is stale, is the one inconsistency worth closing.
+
+## Patterns to Mirror
+
+| Category | Source | Pattern |
+|---|---|---|
+| Release procedure | `docs/release.md:70-104` | batch → merge → commit `chore(release): vX.Y.Z` → tag → push; tag must match `changes/<tag>.md` |
+| Changelog fragment | `changes/unreleased/*.yaml` | `kind` + one-line `body` + `Issue: "<n>"`, written by `changie new` |
+| Doc cross-link | `docs/release.md:64-65` | link the policy file that owns the rule rather than restating it |
+| Milestone bookkeeping | `.claude/prds/aws-v1-stabilization.prd.md:64-67` | status cell `complete` + relative link to the plan |
+
+## Files to Change
+
+| File | Action | Why |
+|---|---|---|
+| `docs/roadmap.md` | UPDATE | Tick the v1.0 box; move the current marker to `1.x` |
+| `GOVERNANCE.md` | UPDATE | Drop the `0.x` / pre-1.0 framing |
+| `.claude/prds/aws-v1-stabilization.prd.md` | UPDATE | Fill metric row 3 and Open Question 1 from M3; M5 status |
+| `changes/unreleased/Documentation-*.yaml` | CREATE | Fragment for the doc corrections |
+| `changes/v1.0.0.md` | CREATE | `changie batch v1.0.0` output |
+| `CHANGELOG.md` | UPDATE | `changie merge` output |
+
+Nothing under `internal/` changes. If this plan touches Go code, something was missed in M1–M4.
+
+## Tasks
+
+### Task 1: Finish the pre-flight
+- **Action**: `rm -rf internal/generated && make codegen && git status --porcelain internal/generated`
+  → prints nothing. Clear the tree first, as CI does (`release.yml:100-104`) — regenerating in
+  place leaves a retired output looking current.
+- **Validate**: empty output. Any diff means commit the regeneration before going further.
+
+### Task 2: Retire the pre-1.0 framing from what ships
+- **Action**: `docs/roadmap.md:30` → `- [x] v1.0 release`; `:78` → `| 1.x ← current | AWS depth,
+  stable plugin API |` with the `0.x` row kept as history (`AWS services, unstable API`).
+  `GOVERNANCE.md:5` → `## Current state`; drop the "pre-1.0" sentence at `:11` — the maintainer
+  model is not what changes at 1.0.
+- **Mirror**: `docs/compatibility-policy.md:1-12`, which already speaks in the present tense
+  about what 1.x guarantees.
+- **Validate**: `grep -rn '0\.x\|pre-1\.0\|pending maintainer tag' docs/ *.md` returns only the
+  historical roadmap row.
+
+### Task 3: Reconcile the PRD with what shipped
+- **Action**: Success Metrics row 3 → `8 operations` promoted, criteria = *the manifest's own
+  data: services with remaining `auto-crud` operations a local inner loop actually reaches*;
+  measured by the manifest tier diff. Tick Open Question 1 with the M3 answer and link
+  `.claude/plans/promotion-pass.plan.md`.
+- **Validate**: no `TBD` remains in the PRD.
+
+### Task 4: Rehearse GoReleaser locally
+- **Action**:
+  ```sh
+  HOMEBREW_TAP_OWNER=skyoo2003 HOMEBREW_TAP_REPO=homebrew-tap HOMEBREW_TAP_TOKEN=dummy \
+    goreleaser release --snapshot --clean --skip=publish,docker
+  ```
+- **Validate**: 6 archives in `dist/`, and
+  `tar tzf dist/devcloud_*_linux_amd64.tar.gz | grep -c '^docs/'` is non-zero — the #127 change
+  proven before it reaches a user, not after.
+- **Note**: `--skip=docker` only because the image build needs a running daemon; the release
+  workflow builds it, and a broken Dockerfile fails the job before publishing.
+
+### Task 5: Cut the release
+- **Action**: follow `docs/release.md:70-104` verbatim, `VERSION=v1.0.0`:
+  `changie batch v1.0.0` → `changie merge` → commit `chore(release): v1.0.0` → push `main` →
+  `git tag v1.0.0 && git push origin v1.0.0`.
+- **Validate**: `changes/v1.0.0.md` holds exactly one `## [v1.0.0](…)` heading and 33 `* ` entries
+  — the two properties `release.yml:184-200` enforces.
+- **Note**: Tasks 2 and 3 must be committed *before* batching, so their fragment is in the notes
+  and the corrected docs are in the archive.
+
+### Task 6: Verify what was published
+- **Action**: after the workflow goes green —
+  1. `curl -sL https://github.com/skyoo2003/devcloud/releases/download/v1.0.0/devcloud_v1.0.0_darwin_arm64.tar.gz | tar tz | grep docs/compatibility-policy.md`
+  2. unpack, run `./devcloud &`, then
+     `curl -s localhost:4747/devcloud/api/fidelity | head` — the manifest endpoint the release
+     promises, answering from the published binary
+  3. `docker run --rm ghcr.io/skyoo2003/devcloud:v1.0.0-alpine` starts
+  4. `brew install skyoo2003/tap/devcloud && devcloud -h`
+- **Why**: v0.2.0 passed CI and shipped binaries that could not start (#128). The gates now catch
+  that class, but the Homebrew formula and the container image are still only exercised at publish
+  time. Ten minutes here is the difference between finding out and being told.
+
+### Task 7: Close the milestone
+- **Action**: PRD milestone 5 → `complete`; add a `changes/unreleased/` fragment only if anything
+  in Task 6 required a fix.
+- **Validate**: `git tag --list 'v1.0.0'` and the GitHub Release both exist.
+
+## Validation
+
+```bash
+# pre-flight (Task 1)
+rm -rf internal/generated && make codegen && git status --porcelain internal/generated
+CGO_ENABLED=0 go test ./... && make test-compat
+
+# notes (Task 5)
+changie batch v1.0.0 --dry-run | grep -c '^\* '        # 34 after the Task 2 fragment
+changie batch v1.0.0 --dry-run | grep -c 'issues/)'    # 0
+
+# archive (Task 4)
+tar tzf dist/devcloud_*_linux_amd64.tar.gz | grep -c '^docs/'
+```
+
+## Risks
+
+| Risk | Likelihood | Mitigation |
+|---|---|---|
+| GoReleaser fails mid-publish, leaving a partial release under a burned tag | Low | Task 4 rehearses it locally first; recovery is delete the release + tag and re-push the same tag, before anything consumes it |
+| Homebrew tap push fails on token/permissions — the one step no gate covers | Medium | Task 6 checks it; a tap fix is a tap-repo commit, it does not invalidate the release |
+| `make codegen` is not byte-reproducible and Task 1 shows spurious drift | Low | The same job has been green in CI since M4; a diff here is real |
+| v1.0 goes out with ~2,200 `auto-crud` operations and reads as overclaiming | Medium | Already mitigated by design — the manifest is generated and served at `/devcloud/api/fidelity`, and the compatibility policy states plainly that `auto-crud` carries no behavioural promise |
+| 1.x then blocks the Phase 2 refactor | Medium | The wire promise is scoped to the 775 compat-suite tests; `internal/` is explicitly outside the user contract (`plugin-api.md:128-135`) |
+
+## Acceptance
+
+- [ ] No shipped file describes DevCloud as pre-1.0
+- [ ] PRD carries no `TBD`; Open Question 1 answered
+- [ ] Local GoReleaser snapshot produces archives containing `docs/`
+- [ ] `v1.0.0` tagged, workflow green, GitHub Release notes = `changes/v1.0.0.md`
+- [ ] Published binary, container image and Homebrew formula each verified to start
+- [ ] PRD milestone 5 marked `complete`
+
+## Open Decision
+
+**Straight to `v1.0.0`, or `v1.0.0-rc1` first?** This plan assumes straight to v1.0.0 — the gates
+cover the failure mode an rc would catch, and `.goreleaser.yaml` would currently mis-publish an rc
+as the latest stable release. Choosing an rc means landing `release.prerelease: auto` plus
+`skip_upload: auto` on `brews:` and prerelease-aware docker tags first, which is a change to the
+release config on the eve of the release it is meant to de-risk.
diff --git a/.claude/prds/aws-service-coverage-100.prd.md b/.claude/prds/aws-service-coverage-100.prd.md
new file mode 100644
index 00000000..d8ab97b2
--- /dev/null
+++ b/.claude/prds/aws-service-coverage-100.prd.md
@@ -0,0 +1,148 @@
+# AWS Service Coverage 100%
+
+## Problem
+
+DevCloud registers 104 AWS services. Upstream `aws-sdk-go-v2/aws-models` publishes
+431. Roughly three quarters of the AWS surface is not routed at all — an SDK call
+to an unregistered service does not reach a provider, it is simply not a service
+DevCloud knows. Developers hit that wall silently and fall back to real AWS, which
+is the exact cost and iteration-speed problem DevCloud exists to remove.
+
+The cost of leaving this unsolved is credibility at the evaluation step: "how many
+services does it support" is the first filter a team applies when choosing a local
+cloud runtime, and 104 loses that filter before depth is ever examined. It also
+blocks the multi-CSP roadmap — Azure and GCP expansion is only defensible once AWS,
+the reference provider, is complete.
+
+## Evidence
+
+- **Assumption — needs validation via user research.** No issue backlog, support
+  ticket, or usage telemetry currently substantiates demand for specific missing
+  services. The 104 vs 431 gap is a measured fact; the claim that closing it
+  changes adoption is not yet evidenced.
+- Measured today: 104 registered services, 93 with an in-tree model, 7,481 known
+  operations (4,498 hand-verified / 950 auto-crud / 2,033 unimplemented).
+- Measured today: 431 model files exist upstream. ~71% of in-tree models use a
+  JSON-family protocol; ~29% use Query, EC2 Query, or REST-XML.
+
+**Validation owed before Milestone 3 commits budget**: which of the ~330 missing
+services are actually reached for. Recommended methods — issue-template telemetry
+on "service not supported", a public poll, or instrumenting unrouted-service
+requests in the gateway.
+
+## Users
+
+- **Primary — boto3 application developers** running integration tests locally.
+  Trigger: a test touches a service DevCloud does not register, so the test is
+  skipped, mocked, or pointed at real AWS.
+- **Primary — platform engineers using Terraform/CDK.** Trigger: a stack contains
+  one resource type DevCloud cannot serve, and the whole plan/apply fails, not
+  just that resource.
+- **Primary — CI pipeline operators.** Trigger: a portion of the integration suite
+  must run against a billed AWS account because DevCloud does not cover it,
+  splitting the pipeline and its credentials.
+- **Not for**: teams needing production-grade behavioural parity. This work
+  increases breadth, not depth. Anyone depending on validation semantics,
+  cross-resource integrity, or business logic in a newly added service is
+  explicitly not served by it.
+
+## Hypothesis
+
+We believe **registering every AWS service published upstream, each meeting a
+stated minimum quality floor**, will **remove "that service isn't supported" as a
+reason to fall back to real AWS** for **boto3 developers, IaC engineers, and CI
+operators**.
+
+We'll know we're right when **the count of registered services equals the upstream
+model count, every registered service passes at least one boto3 compatibility test,
+and the rate of unrouted-service requests observed at the gateway trends to zero**.
+
+## Success Metrics
+
+| Metric | Target | How measured |
+|---|---|---|
+| Registered AWS services | 431 (100% of upstream models) | registered plugin count vs. upstream model count, asserted in CI |
+| Services meeting the quality floor | 100% of registered | fidelity manifest reports ≥1 served operation **and** a passing compatibility test exists for the service |
+| Per-service onboarding cost | TBD — baseline set in Milestone 1, target set from it | wall-clock time from service name to merged, measured across Milestone 2 |
+| Unrouted-service request rate | trends to zero | TBD — requires gateway instrumentation that does not exist yet |
+| Compatibility suite runtime | stays within an agreed CI budget | CI job duration; budget is an open question below |
+
+## Scope
+
+**MVP** — A repeatable, measured service-onboarding capability, proven by taking
+one complete AWS service category from zero to the quality floor. The MVP answers
+one question: *what does adding a single service actually cost once the repetitive
+work is automated?* If that number is small, the remaining ~310 services are an
+arithmetic problem rather than a research problem. If it is not small, the 100%
+target is re-scoped before any bulk investment.
+
+**Quality floor** — a service counts as "covered" only when both hold:
+1. CRUD-shaped operations are served from a real store; everything else returns a
+   clean AWS error rather than a fabricated success.
+2. At least one boto3 compatibility test exercises the service and passes in CI.
+
+**Out of scope**
+- **Azure / GCP expansion** — deferred to the multi-CSP phase. AWS completion is
+  its precondition, not its companion.
+- **Depth on newly added services** — no business logic, validation, or
+  cross-resource integrity. The floor is the ceiling for this effort.
+
+**Deliberately left in scope but unresolved** — filling the 2,033 existing
+`unimplemented` operations, non-JSON-protocol services, and cross-service
+integration for new services were each offered as exclusions and not taken. They
+are not out of scope, but none is funded by the MVP. See Open Questions.
+
+## Delivery Milestones
+
+<!-- Business outcomes, not engineering tasks. /plan turns each into a plan. -->
+<!-- Status: pending | in-progress | complete -->
+
+| # | Milestone | Outcome | Status | Plan |
+|---|---|---|---|---|
+| 1 | Onboarding cost is known | Adding one AWS service is a single bounded operation with a measured wall-clock cost, not a bespoke effort. The baseline number exists. | in-progress | `.claude/plans/aws-service-coverage-100.plan.md` |
+| 2 | One category proven end to end | Every service in one AWS category is registered and meets the quality floor. Per-service cost is confirmed against the Milestone 1 estimate. | pending | — |
+| 3 | Demand validated, or target re-scoped | The assumption in Evidence is tested. Either the remaining services are confirmed as wanted, or the 100% target is publicly narrowed before bulk investment. | pending | — |
+| 4 | JSON-protocol surface complete | Every upstream JSON-protocol AWS service is registered and meets the floor. | pending | — |
+| 5 | Non-JSON surface resolved | Query / EC2 Query / REST-XML services either meet a stated floor or are excluded from the "100%" claim in published docs. No silent gap. | pending | — |
+| 6 | Coverage claim published and gated | Public docs state the coverage figure and its real depth. CI fails if a registered service drops below the floor or the count regresses. | pending | — |
+
+## Open Questions
+
+- [ ] **Does the "100%" claim include non-JSON-protocol services?** The chosen
+      quality floor depends on generic CRUD serving, which today applies only to
+      JSON-family protocols — roughly 29% of models are Query, EC2 Query, or
+      REST-XML. Either the floor gains a second definition for those, or "100%"
+      means "100% of JSON-protocol services". This changes the denominator and
+      must be settled before Milestone 4.
+- [ ] **Is 431 the right denominator?** The upstream directory includes runtime
+      split-outs and variants that are not separate services from a user's point
+      of view. The target number needs a defensible definition.
+- [ ] **What is the CI budget ceiling?** +~330 compatibility tests and ~330
+      registered plugins will lengthen every CI run. If the suite outgrows the
+      budget, the per-service test requirement needs a different execution model.
+- [ ] **What does 431 registered services cost at runtime?** Binary size, image
+      size, startup time, and idle memory are currently sized for 104. The
+      zero-config, single-binary promise is a stated product property and could
+      break before the coverage target is reached.
+- [ ] **Does the fidelity manifest remain usable at ~30,000 entries?** It is
+      already noted as too large to return unfiltered at 7,481.
+- [ ] **What is the sustaining cost?** The weekly upstream sync currently reviews
+      93 models. At 431, routine model churn becomes an ongoing maintenance load
+      that no one has budgeted.
+- [ ] **Who owns the ongoing work?** Scope at this size is explicitly noted in the
+      project's own guiding principles as beyond a single maintainer.
+
+## Risks
+
+| Risk | Likelihood | Impact | Mitigation |
+|---|---|---|---|
+| Breadth-without-depth backlash — "431 services" is read as a capability claim, then a user finds most operations are store-backed stubs with no logic, and trusts nothing | High | High | Publish the depth split next to the count everywhere the count appears; never state the service number without the fidelity breakdown; keep the "clean error, never a false success" guarantee absolute |
+| Building ~330 services nobody asked for | High | High | Milestone 3 gates bulk investment on demand validation; the MVP deliberately costs one category, not 330 services |
+| Non-JSON services cannot meet the stated floor, leaving a silent gap inside a "100%" claim | High | Medium | Milestone 5 forces an explicit, published resolution; no partial claim ships |
+| CI runtime or cost becomes the binding constraint | Medium | Medium | Set the budget ceiling as an explicit target before Milestone 4; treat suite runtime as a tracked metric, not a side effect |
+| Single-binary / zero-config property breaks under 431 services | Medium | High | Measure binary size, startup, and idle memory as part of Milestone 2, while the sample is still 20 services |
+| Upstream model churn across 431 models exceeds review capacity | Medium | High | Size the sustaining load from Milestone 2's category before committing to Milestone 4 |
+| Multi-CSP roadmap stalls behind an AWS target that keeps expanding | Medium | Medium | Milestone 3 provides a sanctioned off-ramp to narrow the target rather than defer the roadmap indefinitely |
+
+---
+*Status: DRAFT — requirements only. Implementation planning pending via /plan.*
diff --git a/.claude/prds/aws-v1-stabilization.prd.md b/.claude/prds/aws-v1-stabilization.prd.md
new file mode 100644
index 00000000..74e65fbd
--- /dev/null
+++ b/.claude/prds/aws-v1-stabilization.prd.md
@@ -0,0 +1,93 @@
+# AWS Surface Stabilization — DevCloud v1.0
+
+> Roadmap: [Phase 1 — AWS Depth & Stabilization](../../docs/roadmap.md#phase-1--aws-depth--stabilization-complete-shipped-as-v10)
+
+## Problem
+
+DevCloud's Phase 1 engineering checklist is 9 of 10 complete — 104 services, 729 green boto3 compatibility tests, a finalized `ServicePlugin` API. The single open box is `v1.0 release (pending maintainer tag)`. The blocker is not missing code; it is that **no agreed, published bar exists for what v1.0 promises**, and ~2,200 operations are served by a generic CRUD engine at deliberately "plausible, not faithful" fidelity with no per-operation signal telling a user which is which.
+
+Leaving this unsolved means the project stays at 0.x indefinitely: the maintainer cannot tag with confidence, and Phase 2's internal refactor (IR, `ModelSource`) will churn the codebase with no stable line for users to sit on.
+
+## Evidence
+
+Measured from the repository (2026-08-09):
+
+- 104 services registered, 4,484 dispatch cases — `make stats`
+- 729 boto3 compatibility tests across 111 files, green in CI; a failing test fails the build — `docs/services-matrix.md:3,64`
+- ~2,200 operations across 46 JSON-protocol services served by the CRUD fallback engine, documented as **"plausible, not faithful"** with no validation, cross-resource integrity, or pagination correctness — `docs/crud-engine.md:8,48`
+- Fidelity tiers (`hand-verified` / `auto-crud` / `unimplemented`) are *defined in prose* but not emitted as a per-operation artifact a user can query — `docs/crud-engine.md:29-35`
+- Latest tag v0.2.0 (2026-04-21); `[Unreleased]` section is empty — `git tag`, `CHANGELOG.md:9`
+
+**Assumption — needs validation via user research or issue triage**: that end users (boto3 developers, CI teams) are blocked by the 0.x version or by fidelity opacity. No user quotes, tickets, or telemetry support this today. This PRD is maintainer-driven; user demand is unmeasured.
+
+## Users
+
+- **Primary**: the DevCloud maintainer, at the moment of deciding whether to tag v1.0 — needs an explicit, testable definition of "v1.0-ready" and a compatibility contract they can stand behind across the 1.x line.
+- **Secondary (unvalidated)**: boto3 application developers and CI teams who would consume the fidelity manifest to know which operations they can trust.
+- **Not for**: contributors adding *new* services (the surface is assumed frozen at its current breadth for this release), and anyone needing production-grade or behavior-faithful AWS emulation.
+
+## Hypothesis
+
+We believe **an explicit, machine-verified compatibility contract — a per-operation fidelity manifest, a published stability policy, and a repeatable release process** will **turn "is this ready?" from a judgment call into a passing test** for **the maintainer**.
+
+We'll know we're right when **100% of reachable operations carry a declared fidelity tier, enforced by a test that fails the build if any operation is unclassified — and v1.0 is tagged.**
+
+## Success Metrics
+
+| Metric | Target | How measured |
+|---|---|---|
+| **Primary** — operations with a declared fidelity tier | 100% | Generated manifest + a conformance test that fails if any reachable operation is unclassified |
+| boto3 compatibility suite | stays 100% green | `make test-compat` in CI (existing guardrail) |
+| High-value auto-crud ops promoted to hand-verified | **8**, selected from the manifest rather than guessed — the tag operations (`TagResource`, `UntagResource`, `ListTagsForResource`) still `auto-crud` in cloudwatch, eventbridge and kms while their siblings were hand-written | Manifest tier diff between v0.2.0 and v1.0 |
+| Breaking `ServicePlugin` changes after tag | 0 across the 1.x line | Existing plugin conformance test + release review |
+
+## Scope
+
+**MVP** — all three of:
+
+1. **Fidelity manifest** — a generated, published artifact declaring every reachable operation's tier (`hand-verified` / `auto-crud` / `unimplemented`), with a test that fails on any unclassified operation.
+2. **Stability policy** — a written v1.0 compatibility contract stating what is guaranteed across 1.x (plugin API surface, and the extent of any wire-behavior promise) and what explicitly is not.
+3. **Promotion pass + release hardening** — an agreed shortlist of high-value auto-crud operations promoted to hand-verified with compatibility tests, plus a repeatable release checklist, upgrade/deprecation policy, and versioned docs.
+
+**Out of scope**
+
+- **All Phase 2 items** (IR layer, `ModelSource` interface, provider namespacing, per-provider auth adapters) — deferred to 1.x/2.0; v1.0 exists precisely to give users a stable line *before* that refactor.
+- **Behavioral parity with real AWS** — no input validation, business logic, eventual-consistency timing, or rate limits on engine-served operations. "Plausible, not faithful" stays the documented stance; the manifest makes it legible rather than eliminating it.
+
+## Delivery Milestones
+
+<!-- Business outcomes, not engineering tasks. /plan turns each into a plan. -->
+<!-- Status: pending | in-progress | complete -->
+
+| # | Milestone | Outcome | Status | Plan |
+|---|---|---|---|---|
+| 1 | Fidelity manifest | Any user can look up any operation and see exactly how much to trust it; no operation is silently unclassified | complete | [fidelity-manifest.plan.md](../plans/fidelity-manifest.plan.md) |
+| 2 | Stability policy published | The v1.0 promise is written down and bounded — maintainer and users agree on what 1.x will not break | complete | [stability-policy.plan.md](../plans/stability-policy.plan.md) |
+| 3 | High-value promotion pass | The operations users hit most return hand-verified responses instead of plausible ones | complete | [promotion-pass.plan.md](../plans/promotion-pass.plan.md) |
+| 4 | Release process hardened | Tagging a release is a checklist, not a judgment call; deprecations follow a stated policy | complete | [release-hardening.plan.md](../plans/release-hardening.plan.md) |
+| 5 | v1.0 tagged | DevCloud ships a version users can depend on, ahead of the Phase 2 refactor | complete | [v1-tag.plan.md](../plans/v1-tag.plan.md) |
+
+## Open Questions
+
+- [x] Which operations make the promotion shortlist, and how many? **8 operations across 3 services, and the shortlist was read off the manifest instead of guessed.** The premise was wrong: the operations a local inner loop actually calls are already hand-verified — s3, sqs, lambda, iam and sts have zero `auto-crud` operations. Of the 957 remaining, the bulk is operational and replication surface (sagemaker 280, glue 169) that no inner loop touches. The one real gap was tag operations left at `auto-crud` in cloudwatch, eventbridge and kms. Further promotion is **on request with a stated use case**, per the policy in `docs/fidelity-manifest.md` — not maintainer guesswork. See `.claude/plans/promotion-pass.plan.md`.
+- [x] Does the stability guarantee cover only the `ServicePlugin` API, or also wire behavior of hand-verified operations? **Both, but the wire promise is compat-suite-scoped** — 1.x guarantees the response shape of hand-verified operations covered by `tests/compatibility/` (775 tests); uncovered hand-verified operations get best-effort language, not a promise. Keeps the Phase 2 refactor unblocked. See `.claude/plans/stability-policy.plan.md`.
+- [x] Is adding new service coverage in or out of scope for v1.0? **Not blocking the tag, and additive when it happens** — new services and `unimplemented` → served transitions are minor-version changes, never breaking.
+- [x] Does the fidelity manifest ship as documentation, a queryable runtime endpoint, or both? **Both, already shipped** in #126 — `docs/fidelity-manifest.md` and `GET /devcloud/api/fidelity`.
+
+## Risks
+
+| Risk | Likelihood | Impact | Mitigation |
+|---|---|---|---|
+| Shipping 1.0 with ~2,200 "plausible, not faithful" operations damages trust despite the manifest | Medium | High | Manifest is prominent and machine-generated, not buried prose; stability policy states explicitly that `auto-crud` carries no behavioral promise |
+| The v1.0 stability promise over-commits and blocks the Phase 2 refactor | Medium | High | Scope the guarantee narrowly and in writing (open question above) before tagging |
+| Promotion shortlist is chosen on guesswork and misses what users actually call | High | Medium | Treat the shortlist as explicitly provisional; derive from issue triage, and revisit in 1.x rather than blocking the tag |
+| Manifest drifts from reality as services change | Medium | Medium | Generate it from source, never hand-maintain; enforce with a build-failing test |
+| Primary user need is unvalidated (maintainer-driven, no user evidence) | High | Low | Cost of being wrong is low — the work is honesty and process, useful regardless of demand |
+
+---
+*Status: DELIVERED — v1.0.0 tagged 2026-08-11 on `2109922`. All five milestones complete.*
+
+*Post-release note: the first v1.0.0 tag published binaries that registered no services —
+`.goreleaser.yaml` built `cmd/devcloud/main.go` instead of the package, dropping `imports.go`.
+Caught by the plan's own artifact-verification step, fixed in #131, and v1.0.0 was withdrawn and
+re-tagged. The compat gate now builds with GoReleaser, so the tested binary is the shipped one.*
diff --git a/.claude/tdd/aws-service-coverage-100.tdd.md b/.claude/tdd/aws-service-coverage-100.tdd.md
new file mode 100644
index 00000000..3e66c9e1
--- /dev/null
+++ b/.claude/tdd/aws-service-coverage-100.tdd.md
@@ -0,0 +1,196 @@
+# TDD Evidence: Repeatable AWS Service Onboarding
+
+**Source plan**: `.claude/plans/aws-service-coverage-100.plan.md`
+**Source PRD**: `.claude/prds/aws-service-coverage-100.prd.md` — Milestone 1, "Onboarding cost is known"
+**Branch**: `feat/repeatable-service-onboarding`
+**Commits**: `56e1867` (RED) → `9a53664` (GREEN) → `4881772` → `113ac22`
+
+## User journeys
+
+Extracted from the plan's tasks; none invented here.
+
+| # | Journey | Plan task |
+|---|---|---|
+| J1 | As a maintainer, regenerating `imports.go` returns exactly what is committed, so the weekly sync cannot erase service registration | Task 1 |
+| J2 | If `imports.go` drifts from the service directories, the build fails, so a dropped service is never silently unreachable | Task 2 |
+| J3 | As a contributor, a scaffolded JSON-protocol service serves its CRUD operations immediately, with no hand-written dispatch | Task 3 |
+| J4 | `auto-crud` in the manifest means the operation is actually served, so published coverage is not inflated | Task 4 |
+| J5 | Adding a service needs a name in a list, not a hand-written boto3 fixture | Task 5 |
+| J6 | The per-service onboarding cost is a measured number, not an estimate | Task 6 |
+
+## Task report
+
+### Task 1 — Repair the import generator
+
+Ran `scripts/generate-imports.sh` against a scratch tree and compared with the committed file.
+
+**RED** (`CGO_ENABLED=0 go test ./cmd/devcloud/ -run TestGenerateImportsReproducesCommittedFile`):
+
+```
+--- FAIL: TestGenerateImportsReproducesCommittedFile
+    expected: "// Code generated ...\n// SPDX-License-Identifier: Apache-2.0\npackage main\n\nimport (\n\t_ \"...services/account\"\n ... 103 entries ...
+    actual  : "// Code generated ...\npackage main\n\nimport ()\n"
+```
+
+Two defects in one output: the import block is empty, and the SPDX line is missing. The empty block is the load-bearing one — an unimported package never runs its `init()`, so every service was unregistered, and only in the built binary.
+
+**GREEN**: gate on the package calling `DefaultRegistry.Register` instead of on a `register.go` filename no service has ever had. Supporting changes: build into a temp file and `mv` on success; refuse below `MIN_SERVICES` (default 50); delegate SPDX to `scripts/add-spdx-header.sh`.
+
+```
+$ bash scripts/generate-imports.sh && git diff --exit-code cmd/devcloud/imports.go
+Generated ./cmd/devcloud/imports.go with 103 services
+IDEMPOTENT: committed file reproduced exactly
+
+$ MIN_SERVICES=200 bash scripts/generate-imports.sh; git diff --exit-code cmd/devcloud/imports.go
+ERROR: found 103 registering service package(s), expected at least 200.
+Refusing to write a gutted ./cmd/devcloud/imports.go; it is unchanged.
+exit=1
+GUARD OK: imports.go untouched after refusal
+```
+
+**Guaranteed**: the generator reproduces the committed file byte for byte, and a run that would gut the file exits non-zero without touching it.
+
+### Task 2 — Lock `imports.go` against drift
+
+`TestImportsCoverEveryRegisteredService` compares the registering service directories with the blank imports, both directions, behind a floor of 50.
+
+**No RED phase** — it passes on the current tree because no drift exists today. It is a regression lock, not a reproducer. Recorded as such rather than presented as a RED→GREEN cycle.
+
+### Task 3 — Make the scaffold meet the quality floor
+
+**RED** (executed, `-run TestGenerateScaffold`):
+
+```
+--- FAIL: TestGenerateScaffoldOptsIntoCRUDEngine
+    rendered scaffold does not contain "plugin.ErrUnhandledOp"
+    (it contains: return nil, generated.ErrNotImplemented)
+--- FAIL: TestGenerateScaffoldKeepsDataDir
+    rendered scaffold does not contain "cfg.DataDir"
+```
+
+**GREEN**: template returns `plugin.ErrUnhandledOp`; `Init` stores `cfg.DataDir`.
+
+One test assertion was corrected during the GREEN step: `NotContains(output, "ErrNotImplemented")` was too broad — it forbade the string anywhere, including the scaffold's own doc comment explaining why declining that way serves nothing. Tightened to the return statement (`return nil, generated.ErrNotImplemented`), which keeps the regression value and stops the assertion colliding with documentation.
+
+**Guaranteed**: a scaffolded provider reaches the CRUD engine and keeps its data directory.
+
+### Task 4 — Stop the manifest overstating coverage
+
+**RED** (compile-time, the failure mode the skill permits):
+
+```
+internal/codegen/gen_fidelity_test.go:47: unknown field EngineWired in struct literal of type ProviderScan
+internal/codegen/gen_fidelity_test.go:55: cannot use providers (map[string]ProviderScan) as map[string][]string
+internal/codegen/scan_handverified_test.go:178: scans[id].EngineWired undefined
+```
+
+The failure is the missing contract, not unrelated breakage: `tierFor` labelled an operation `auto-crud` from CRUD-registry membership alone, and membership means *classifiable*, never *reachable*.
+
+**GREEN**: `ProviderScan.EngineWired`, detected by a receiver-scoped AST walk for `plugin.ErrUnhandledOp` reusing the same method traversal as the operation scan; `BuildFidelityData` takes the `ProviderScan` map directly.
+
+**Key validation — the manifest did not change.**
+
+```
+$ make codegen && git status --porcelain
+(no entries under internal/generated/)
+```
+
+A byte-identical manifest proves the wiring detection agrees with all 46 engine-wired JSON services and demoted no live operation. Idempotency confirmed by hash across two consecutive runs.
+
+### Task 5 — Remove the per-service fixture cost
+
+Added `service_client`, one parameterized boto3 factory fixture, and `test_service_smoke.py`, which picks a parameterless `List*`/`Describe*` operation from the service model and asserts HTTP 200.
+
+Verified in **both** directions:
+
+```
+$ pytest test_service_smoke.py
+test_service_serves_at_least_one_operation[comprehend] PASSED
+
+# after reverting the provider to generated.ErrNotImplemented:
+E  Failed: comprehend.ListDatasets is routed but not served:
+   {'Message': 'operation not implemented', 'Code': 'InternalError'}
+FAILED test_service_serves_at_least_one_operation[comprehend]
+```
+
+The negative case exposed a second consequence of the old scaffold: it returned **HTTP 500 `InternalError`**, so a pre-fix scaffolded service also broke the project's "unimplemented operations return a clean AWS error, never a false success" guarantee.
+
+The 104 existing named fixtures were deliberately left alone — they back real tests, not scaffolding.
+
+### Task 6 — Measured baseline
+
+`comprehend` (`awsJson1_1`), end to end on this machine:
+
+| Stage | Time |
+|---|---|
+| model download | 0s |
+| codegen + scaffold | 2s |
+| import regeneration | 0s |
+| build | 1s |
+| **total** | **3s** |
+
+- Hand-written lines: **0**
+- Generated: 53 lines in `internal/services/comprehend/provider.go`, plus the generated package
+- Manifest: 49 `auto-crud`, 36 `unimplemented`, 0 `hand-verified` — matching what the smoke test confirms is served
+
+**This number does not hold for every service.** See "Known gaps" below.
+
+Two existing invariants needed updating, both encoding "every service is hand-written":
+`TestScanProviders` (`scan_handverified_test.go:71`) and `TestFidelityManifestCoverage` (`fidelity_test.go:58`) required at least one hand-verified operation per service. A scaffolded service legitimately has none. The invariant is now "every service serves something — hand-verified **or** engine-served", which is stronger: zero of both is the real defect, and that is what these checks now catch.
+
+## Test specification
+
+| # | What is guaranteed | Test | Type | Result | Evidence |
+|---|---|---|---|---|---|
+| 1 | Regenerating `imports.go` reproduces the committed file byte for byte | `cmd/devcloud/imports_test.go:TestGenerateImportsReproducesCommittedFile` | integration | PASS | `go test ./cmd/devcloud/` |
+| 2 | Every registering service package is blank-imported, and nothing else | `cmd/devcloud/imports_test.go:TestImportsCoverEveryRegisteredService` | unit | PASS | `go test ./cmd/devcloud/` |
+| 3 | A run that would gut `imports.go` exits non-zero and leaves it unchanged | manual, `MIN_SERVICES=200` | integration | PASS | output quoted above |
+| 4 | A scaffolded provider opts into the CRUD engine | `internal/codegen/gen_scaffold_test.go:TestGenerateScaffoldOptsIntoCRUDEngine` | unit | PASS | `go test ./internal/codegen/` |
+| 5 | A scaffolded provider keeps `cfg.DataDir` | `internal/codegen/gen_scaffold_test.go:TestGenerateScaffoldKeepsDataDir` | unit | PASS | `go test ./internal/codegen/` |
+| 6 | The scan reports which providers reach the CRUD engine | `internal/codegen/scan_handverified_test.go:TestScanProvidersDetectsEngineWiring` | unit | PASS | `go test ./internal/codegen/` |
+| 7 | An unwired provider's CRUD-shaped operations are `unimplemented`, not `auto-crud` | `internal/codegen/gen_fidelity_test.go:TestBuildFidelityDataRequiresEngineWiring` | unit | PASS | `go test ./internal/codegen/` |
+| 8 | Hand-verified outranks both other tiers regardless of wiring | `internal/codegen/gen_fidelity_test.go:TestBuildFidelityDataHandVerifiedBeatsWiring` | unit | PASS | `go test ./internal/codegen/` |
+| 9 | Every routed service serves at least one operation | `cmd/devcloud/fidelity_test.go:TestFidelityManifestCoverage` | unit | PASS | `go test ./cmd/devcloud/` |
+| 10 | A scaffolded service answers a real boto3 call with 200 | `tests/compatibility/test_service_smoke.py` | e2e | PASS | `make test-compat` |
+| 11 | A service that is routed but serves nothing fails the smoke test | same test, provider temporarily reverted | e2e | PASS (fails as designed) | output quoted above |
+
+## Coverage
+
+```
+$ go test -cover ./internal/codegen/
+ok  internal/codegen  coverage: 77.7% of statements
+
+$ go tool cover -func
+BuildFidelityData   100.0%
+tierFor             100.0%
+sortedKeys          100.0%
+GenerateScaffold    100.0%
+wiresCRUDEngine     100.0%
+ScanProviders        76.9%
+```
+
+Every function changed in this run is at 100% except `ScanProviders` (76.9%; the gap is filesystem error paths). `cmd/devcloud` reports 0.0% because it is `package main` whose tests exercise generated data rather than `main`'s statements — pre-existing, not introduced here.
+
+Full suite:
+
+```
+$ CGO_ENABLED=0 go test ./...        → 110 packages ok, 0 failures
+$ make test-compat                   → 776 passed in 9.47s  (775 baseline + 1 smoke)
+$ make codegen (twice, hashed)       → IDEMPOTENT
+```
+
+## Known gaps
+
+1. **The 3-second figure is the clean case, not the average.** `rekognition` was attempted as the plan's second measurement subject and **failed**: `UnknownService: rekognitionservice`. Its `X-Amz-Target` prefix is `RekognitionService`, and `normalizeServiceID` (`internal/gateway/protocol.go:124`) is a hand-maintained alias map — **63 case clauses covering ~150 alias strings for 103 services**. Roughly half of all services needed a hand-written entry in a gateway switch. `comprehend` only worked because its prefix is `Comprehend_20171127`, which the existing date-suffix logic already strips. The alias is derivable from the model (the service shape name plus `aws.api#service.arnNamespace`), but a blanket "strip `service` suffix" rule is unsafe — `elasticsearchservice` is a real service ID. Resolving this is a scope decision, recorded and awaiting the user.
+2. **`rekognition` artifacts were removed**, not left half-added: shipping a registered service that answers nothing would violate the PRD's own quality floor. Reproducible in ~5s with the rollback command in the commit history.
+3. **The CRUD engine is narrower than "JSON-family".** `crud.JSONProtocol` (`internal/shared/crud/crud.go:71`) matches only protocols starting with `json`, so `rest-json` services **cannot** be engine-served. The plan overstated this as "non-JSON protocols (Query / EC2 Query / REST-XML) are out of scope". Locally only 39 of 93 models (42%) are `awsJson1_0`/`awsJson1_1`; `rest-json` adds another 27 that are equally unreachable. This narrows Milestone 4's addressable set and should be corrected in the plan and PRD.
+4. **No changelog entries.** `.changie.yaml` requires a `Custom.Issue` integer used to build the CHANGELOG link, and the convention in `changes/unreleased/` is to use the PR number, which does not exist yet. Deliberately not guessed.
+5. **No separate RED checkpoint commit for Tasks 3–4.** The repo's `go-vet` pre-commit hook refuses a tree that does not compile, and the Task 4 RED *was* a compile failure. Committing it would have required `--no-verify` and left a commit that breaks CI for anyone checking it out. The RED output is preserved verbatim in commit `4881772` and above.
+
+## Merge evidence
+
+If these four commits are squashed, this file is the surviving record. Summary for the PR body:
+
+- **RED**: `imports.go` regenerated as `import ()` (empty); scaffold returned `generated.ErrNotImplemented` and dropped `cfg.DataDir`; `ProviderScan`/`BuildFidelityData` had no notion of engine wiring, so `tierFor` labelled `auto-crud` from registry membership alone.
+- **GREEN**: 11 guarantees above; `go test ./...` 110 packages; `make test-compat` 776 passed; `make codegen` produces **no manifest diff**, proving the wiring detection demoted no live operation.
+- **Refactor**: none beyond the assertion correction noted in Task 3; the changes were small enough that no separate refactor pass was warranted.
diff --git a/changes/unreleased/Added-20260905-152603.yaml b/changes/unreleased/Added-20260905-152603.yaml
new file mode 100644
index 00000000..b1562812
--- /dev/null
+++ b/changes/unreleased/Added-20260905-152603.yaml
@@ -0,0 +1,5 @@
+kind: Added
+body: 'Amazon Comprehend, served by the generic CRUD engine (49 operations auto-crud, 36 unimplemented). Unimplemented operations return a clean AWS error, never a fabricated success'
+time: 2026-09-05T15:26:03.000000+09:00
+custom:
+    Issue: "136"
diff --git a/changes/unreleased/Fixed-20260905-152600.yaml b/changes/unreleased/Fixed-20260905-152600.yaml
new file mode 100644
index 00000000..c8ce03fe
--- /dev/null
+++ b/changes/unreleased/Fixed-20260905-152600.yaml
@@ -0,0 +1,5 @@
+kind: Fixed
+body: 'Service registration is no longer silently dropped: `scripts/generate-imports.sh` gated on a `register.go` file that no service has, so every run wrote an empty import block and the built binary registered nothing. It now gates on the package actually calling `Register`, and refuses to write a gutted file instead of reporting success'
+time: 2026-09-05T15:26:00.000000+09:00
+custom:
+    Issue: "136"
diff --git a/changes/unreleased/Fixed-20260905-152601.yaml b/changes/unreleased/Fixed-20260905-152601.yaml
new file mode 100644
index 00000000..4579e621
--- /dev/null
+++ b/changes/unreleased/Fixed-20260905-152601.yaml
@@ -0,0 +1,5 @@
+kind: Fixed
+body: 'A newly scaffolded service now serves its CRUD-shaped operations instead of failing every call: the generated provider declined with an error the gateway never routes to the CRUD engine, so the service was registered and routed but answered HTTP 500 for everything'
+time: 2026-09-05T15:26:01.000000+09:00
+custom:
+    Issue: "136"
diff --git a/changes/unreleased/Fixed-20260905-152602.yaml b/changes/unreleased/Fixed-20260905-152602.yaml
new file mode 100644
index 00000000..53f8f411
--- /dev/null
+++ b/changes/unreleased/Fixed-20260905-152602.yaml
@@ -0,0 +1,5 @@
+kind: Fixed
+body: 'The fidelity manifest no longer reports `auto-crud` for operations the binary refuses. A tier was assigned from CRUD-registry membership alone, which says an operation is classifiable rather than reachable; it now requires the owning provider to actually hand unimplemented operations to the engine'
+time: 2026-09-05T15:26:02.000000+09:00
+custom:
+    Issue: "136"
diff --git a/cmd/codegen/main.go b/cmd/codegen/main.go
index 0d93e9a4..680abfe1 100644
--- a/cmd/codegen/main.go
+++ b/cmd/codegen/main.go
@@ -168,13 +168,8 @@ func writeFidelityManifest(
 	providers map[string]codegen.ProviderScan,
 	crudServices []codegen.CRUDServiceData,
 ) error {
-	handVerified := make(map[string][]string, len(providers))
-	for id, scan := range providers {
-		handVerified[id] = scan.Operations
-	}
-
 	content, err := gen.GenerateFidelityManifest(
-		codegen.BuildFidelityData(modelOps, handVerified, crudServices),
+		codegen.BuildFidelityData(modelOps, providers, crudServices),
 	)
 	if err != nil {
 		return err
diff --git a/cmd/devcloud/fidelity_test.go b/cmd/devcloud/fidelity_test.go
index 1b4e1085..dc26d620 100644
--- a/cmd/devcloud/fidelity_test.go
+++ b/cmd/devcloud/fidelity_test.go
@@ -42,20 +42,26 @@ func TestFidelityManifestCoverage(t *testing.T) {
 		}
 		operations += len(svc.Operations)
 
-		handVerified := 0
+		served := 0
 		for op, tier := range svc.Operations {
 			if !validTiers[tier] {
 				t.Errorf("%s/%s: tier %q is not a declared tier", id, op, tier)
 			}
-			if tier == fidelity.TierHandVerified {
-				handVerified++
+			if tier == fidelity.TierHandVerified || tier == fidelity.TierAutoCRUD {
+				served++
 			}
 		}
-		// A service with nothing hand-verified means the scan lost its provider —
-		// most likely a new path-routing provider that needs a pathRoutedOps
-		// entry in internal/codegen/scan_handverified.go.
-		if handVerified == 0 {
-			t.Errorf("%s: no hand-verified operations; the dispatch scan probably missed this provider", id)
+		// Every routed service must serve something. Hand-verified operations and
+		// engine-served ones both count: a scaffolded service legitimately
+		// implements nothing by hand and is served entirely by the CRUD engine.
+		//
+		// Zero of both is the real defect — a service registered and routed that
+		// answers nothing. That happens when the dispatch scan loses a provider
+		// (a new path-routing provider needs a pathRoutedOps entry in
+		// internal/codegen/scan_handverified.go) or when a provider declines
+		// without returning plugin.ErrUnhandledOp, so it never reaches the engine.
+		if served == 0 {
+			t.Errorf("%s: serves no operations — neither hand-verified nor engine-served", id)
 		}
 	}
 	if operations < minOperations {
diff --git a/cmd/devcloud/imports.go b/cmd/devcloud/imports.go
index 275c0e4a..33de98b9 100644
--- a/cmd/devcloud/imports.go
+++ b/cmd/devcloud/imports.go
@@ -31,6 +31,7 @@ import (
 	_ "github.com/skyoo2003/devcloud/internal/services/codepipeline"
 	_ "github.com/skyoo2003/devcloud/internal/services/cognitoidentity"
 	_ "github.com/skyoo2003/devcloud/internal/services/cognitoidentityprovider"
+	_ "github.com/skyoo2003/devcloud/internal/services/comprehend"
 	_ "github.com/skyoo2003/devcloud/internal/services/configservice"
 	_ "github.com/skyoo2003/devcloud/internal/services/costexplorer"
 	_ "github.com/skyoo2003/devcloud/internal/services/dms"
diff --git a/cmd/devcloud/imports_test.go b/cmd/devcloud/imports_test.go
new file mode 100644
index 00000000..3f2bb0ce
--- /dev/null
+++ b/cmd/devcloud/imports_test.go
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: Apache-2.0
+
+package main
+
+import (
+	"go/parser"
+	"go/token"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"sort"
+	"strconv"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// repoRoot resolves the repository root from this package's directory so the
+// tests can reach scripts/ and internal/services/ without a hardcoded path.
+func repoRoot(t *testing.T) string {
+	t.Helper()
+	root, err := filepath.Abs("../..")
+	require.NoError(t, err)
+	return root
+}
+
+// registeringServiceDirs returns the internal/services package names that
+// register a service. Registration lives in an init() inside provider.go rather
+// than a dedicated file, so scanning the directory's sources is the only
+// reliable signal for which packages must be imported.
+func registeringServiceDirs(t *testing.T) []string {
+	t.Helper()
+	servicesDir := filepath.Join(repoRoot(t), "internal", "services")
+	entries, err := os.ReadDir(servicesDir)
+	require.NoError(t, err)
+
+	var pkgs []string
+	for _, entry := range entries {
+		if !entry.IsDir() {
+			continue
+		}
+		files, err := os.ReadDir(filepath.Join(servicesDir, entry.Name()))
+		require.NoError(t, err)
+		for _, f := range files {
+			name := f.Name()
+			if f.IsDir() || !strings.HasSuffix(name, ".go") || strings.HasSuffix(name, "_test.go") {
+				continue
+			}
+			src, err := os.ReadFile(filepath.Join(servicesDir, entry.Name(), name))
+			require.NoError(t, err)
+			if strings.Contains(string(src), "DefaultRegistry.Register(") {
+				pkgs = append(pkgs, entry.Name())
+				break
+			}
+		}
+	}
+	sort.Strings(pkgs)
+	return pkgs
+}
+
+// importedServicePackages reads the blank service imports out of imports.go.
+func importedServicePackages(t *testing.T) []string {
+	t.Helper()
+	const prefix = "github.com/skyoo2003/devcloud/internal/services/"
+
+	path := filepath.Join(repoRoot(t), "cmd", "devcloud", "imports.go")
+	file, err := parser.ParseFile(token.NewFileSet(), path, nil, parser.ImportsOnly)
+	require.NoError(t, err)
+
+	var pkgs []string
+	for _, spec := range file.Imports {
+		imported, err := strconv.Unquote(spec.Path.Value)
+		require.NoError(t, err)
+		if after, found := strings.CutPrefix(imported, prefix); found {
+			pkgs = append(pkgs, after)
+		}
+	}
+	sort.Strings(pkgs)
+	return pkgs
+}
+
+// TestGenerateImportsReproducesCommittedFile is the guard on the generator
+// itself: regenerating imports.go must produce exactly what is committed. The
+// weekly Smithy sync runs this generator before its test step, so a generator
+// that silently writes a shorter file takes every service out of the binary.
+//
+// It runs against a scratch tree rather than the repository, so a broken
+// generator cannot overwrite the committed file while proving that it is broken.
+func TestGenerateImportsReproducesCommittedFile(t *testing.T) {
+	root := repoRoot(t)
+
+	work := t.TempDir()
+	require.NoError(t, os.MkdirAll(filepath.Join(work, "cmd", "devcloud"), 0o755))
+	require.NoError(t, os.MkdirAll(filepath.Join(work, "internal"), 0o755))
+	require.NoError(t, os.Symlink(
+		filepath.Join(root, "internal", "services"),
+		filepath.Join(work, "internal", "services"),
+	))
+
+	cmd := exec.Command("bash", filepath.Join(root, "scripts", "generate-imports.sh"))
+	cmd.Dir = work
+	out, err := cmd.CombinedOutput()
+	require.NoError(t, err, "generator exited non-zero:\n%s", out)
+
+	got, err := os.ReadFile(filepath.Join(work, "cmd", "devcloud", "imports.go"))
+	require.NoError(t, err)
+	want, err := os.ReadFile(filepath.Join(root, "cmd", "devcloud", "imports.go"))
+	require.NoError(t, err)
+
+	assert.Equal(t, string(want), string(got),
+		"regenerating imports.go must reproduce the committed file byte for byte")
+}
+
+// TestImportsCoverEveryRegisteredService locks imports.go against drift in
+// either direction. A service package that is not imported never runs its
+// init(), so it is registered nowhere and unreachable at runtime — silently, and
+// only in the built binary.
+func TestImportsCoverEveryRegisteredService(t *testing.T) {
+	registered := registeringServiceDirs(t)
+	imported := importedServicePackages(t)
+
+	// Conservative floor, mirroring conformance_test.go: a collapse in the
+	// service surface should fail here loudly rather than pass an empty
+	// comparison against an equally empty imports.go.
+	const minServices = 50
+	require.GreaterOrEqual(t, len(registered), minServices,
+		"found %d registering service packages, want >= %d", len(registered), minServices)
+
+	assert.Equal(t, registered, imported,
+		"every service package that registers must be blank-imported in imports.go, and nothing else")
+}
diff --git a/internal/codegen/gen_fidelity.go b/internal/codegen/gen_fidelity.go
index 3054c4a2..3433cb76 100644
--- a/internal/codegen/gen_fidelity.go
+++ b/internal/codegen/gen_fidelity.go
@@ -40,9 +40,15 @@ type FidelityOpData struct {
 // Precedence is hand-verified > auto-crud > unimplemented, mirroring the runtime:
 // the CRUD engine is reached only when a provider's dispatch falls through, so a
 // hand-written implementation always wins. See docs/crud-engine.md.
+//
+// Registry membership alone does not earn the auto-crud label. It says an
+// operation is *classifiable*, while the engine is reached at runtime only for
+// providers that return plugin.ErrUnhandledOp — so an unwired provider's
+// CRUD-shaped operations are refused, and calling them auto-crud would publish
+// coverage the binary does not serve.
 func BuildFidelityData(
 	modelOps map[string][]string,
-	handVerified map[string][]string,
+	providers map[string]ProviderScan,
 	autoCRUD []CRUDServiceData,
 ) FidelityData {
 	crudOps := make(map[string]map[string]bool, len(autoCRUD))
@@ -55,10 +61,20 @@ func BuildFidelityData(
 	}
 
 	data := FidelityData{}
-	for _, serviceID := range sortedKeys(handVerified) {
-		hand := make(map[string]bool, len(handVerified[serviceID]))
+	for _, serviceID := range sortedKeys(providers) {
+		provider := providers[serviceID]
+
+		// Reachable, not merely classifiable: an unwired provider serves none of
+		// the registry's operations, so its served set is empty and its
+		// CRUD-shaped operations fall through to unimplemented.
+		var served map[string]bool
+		if provider.EngineWired {
+			served = crudOps[serviceID]
+		}
+
+		hand := make(map[string]bool, len(provider.Operations))
 		universe := make(map[string]bool)
-		for _, op := range handVerified[serviceID] {
+		for _, op := range provider.Operations {
 			hand[op] = true
 			universe[op] = true
 		}
@@ -79,7 +95,7 @@ func BuildFidelityData(
 		for _, name := range names {
 			ops = append(ops, FidelityOpData{
 				Name:      name,
-				TierConst: tierFor(name, hand, crudOps[serviceID]),
+				TierConst: tierFor(name, hand, served),
 			})
 		}
 
@@ -92,18 +108,22 @@ func BuildFidelityData(
 	return data
 }
 
-func tierFor(op string, hand, crud map[string]bool) string {
+// tierFor labels one operation. served holds the engine-servable operations of
+// an engine-wired provider, and is empty for a provider the engine never
+// reaches — so an unwired service can only produce hand-verified or
+// unimplemented, never auto-crud.
+func tierFor(op string, hand, served map[string]bool) string {
 	switch {
 	case hand[op]:
 		return "HandVerified"
-	case crud[op]:
+	case served[op]:
 		return "AutoCRUD"
 	default:
 		return "Unimplemented"
 	}
 }
 
-func sortedKeys(m map[string][]string) []string {
+func sortedKeys[V any](m map[string]V) []string {
 	keys := make([]string, 0, len(m))
 	for k := range m {
 		keys = append(keys, k)
diff --git a/internal/codegen/gen_fidelity_test.go b/internal/codegen/gen_fidelity_test.go
new file mode 100644
index 00000000..acc96c49
--- /dev/null
+++ b/internal/codegen/gen_fidelity_test.go
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: Apache-2.0
+
+// internal/codegen/gen_fidelity_test.go
+package codegen
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// tierOf finds one operation's tier in the built data.
+func tierOf(t *testing.T, data FidelityData, serviceID, op string) string {
+	t.Helper()
+	for _, svc := range data.Services {
+		if svc.ServiceID != serviceID {
+			continue
+		}
+		for _, o := range svc.Ops {
+			if o.Name == op {
+				return o.TierConst
+			}
+		}
+		require.Failf(t, "operation missing", "%s/%s is absent from the manifest", serviceID, op)
+	}
+	require.Failf(t, "service missing", "%s is absent from the manifest", serviceID)
+	return ""
+}
+
+// TestBuildFidelityDataRequiresEngineWiring is the guard against the manifest
+// overstating coverage.
+//
+// Being in the CRUD registry only means an operation is *classifiable* — the
+// engine is reached at runtime only for providers that return
+// plugin.ErrUnhandledOp. Labelling an operation auto-crud on registry
+// membership alone publishes "this is served" for a provider that refuses it,
+// which is exactly what a freshly scaffolded service would look like.
+func TestBuildFidelityDataRequiresEngineWiring(t *testing.T) {
+	modelOps := map[string][]string{
+		"wired":   {"CreateThing"},
+		"unwired": {"CreateThing"},
+	}
+	// Neither service hand-implements anything; the only difference is whether
+	// its dispatch reaches the engine.
+	providers := map[string]ProviderScan{
+		"wired":   {EngineWired: true},
+		"unwired": {EngineWired: false},
+	}
+	autoCRUD := []CRUDServiceData{
+		{ServiceID: "wired", Ops: []crudOpData{{Op: "CreateThing", Verb: "Create"}}},
+		{ServiceID: "unwired", Ops: []crudOpData{{Op: "CreateThing", Verb: "Create"}}},
+	}
+
+	data := BuildFidelityData(modelOps, providers, autoCRUD)
+
+	assert.Equal(t, "AutoCRUD", tierOf(t, data, "wired", "CreateThing"),
+		"an engine-wired provider's CRUD-shaped operation is served, so auto-crud is truthful")
+	assert.Equal(t, "Unimplemented", tierOf(t, data, "unwired", "CreateThing"),
+		"a provider that never reaches the engine serves nothing, whatever the CRUD registry says")
+}
+
+// TestBuildFidelityDataHandVerifiedBeatsWiring keeps the documented precedence:
+// a hand-written implementation always wins, and it does not depend on engine
+// wiring because such an operation never falls through to the engine at all.
+func TestBuildFidelityDataHandVerifiedBeatsWiring(t *testing.T) {
+	modelOps := map[string][]string{"svc": {"CreateThing"}}
+	providers := map[string]ProviderScan{
+		"svc": {Operations: []string{"CreateThing"}, EngineWired: false},
+	}
+	autoCRUD := []CRUDServiceData{
+		{ServiceID: "svc", Ops: []crudOpData{{Op: "CreateThing", Verb: "Create"}}},
+	}
+
+	data := BuildFidelityData(modelOps, providers, autoCRUD)
+
+	assert.Equal(t, "HandVerified", tierOf(t, data, "svc", "CreateThing"),
+		"hand-verified outranks both auto-crud and unimplemented")
+}
diff --git a/internal/codegen/gen_scaffold_test.go b/internal/codegen/gen_scaffold_test.go
new file mode 100644
index 00000000..5937e831
--- /dev/null
+++ b/internal/codegen/gen_scaffold_test.go
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: Apache-2.0
+
+// internal/codegen/gen_scaffold_test.go
+package codegen
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// TestGenerateScaffoldOptsIntoCRUDEngine pins the one line that decides whether
+// a newly scaffolded service serves anything at all.
+//
+// The gateway routes to the generic CRUD engine only when a provider returns
+// plugin.ErrUnhandledOp (internal/gateway/router.go). Any other error is a plain
+// refusal, so a scaffold that declines differently is registered, routed, and
+// serves zero operations — while the fidelity manifest still advertises its
+// CRUD-shaped operations as auto-crud.
+func TestGenerateScaffoldOptsIntoCRUDEngine(t *testing.T) {
+	model := loadTestModel(t)
+	gen := NewGenerator("templates")
+
+	output, err := gen.GenerateScaffold("s3", model)
+	require.NoError(t, err)
+
+	// Assert on the return statement, not on the string anywhere in the file:
+	// the scaffold's doc comment names the wrong-way error on purpose, to say
+	// why declining that way serves nothing.
+	assert.Contains(t, output, "return nil, plugin.ErrUnhandledOp",
+		"a scaffolded provider must opt into the CRUD engine, or it serves nothing")
+	assert.NotContains(t, output, "return nil, generated.ErrNotImplemented",
+		"ErrNotImplemented is a refusal the gateway never routes to the CRUD engine")
+}
+
+// TestGenerateScaffoldKeepsDataDir checks the scaffold carries the data
+// directory it is handed, matching what hand-written providers do in Init. A
+// scaffold that drops it forces the first contributor who needs persistence to
+// rewrite Init before writing any behaviour.
+func TestGenerateScaffoldKeepsDataDir(t *testing.T) {
+	model := loadTestModel(t)
+	gen := NewGenerator("templates")
+
+	output, err := gen.GenerateScaffold("s3", model)
+	require.NoError(t, err)
+
+	assert.Contains(t, output, "cfg.DataDir",
+		"Init must keep the configured data directory, as hand-written providers do")
+}
diff --git a/internal/codegen/scan_handverified.go b/internal/codegen/scan_handverified.go
index ab9d70fc..246782b8 100644
--- a/internal/codegen/scan_handverified.go
+++ b/internal/codegen/scan_handverified.go
@@ -70,6 +70,12 @@ var pathRoutedOps = map[string][]string{
 type ProviderScan struct {
 	// Operations are the operation names the provider dispatches by hand.
 	Operations []string
+	// EngineWired reports whether the provider hands the operations it does not
+	// implement to the generic CRUD engine, by returning plugin.ErrUnhandledOp.
+	// Only a wired provider's CRUD-shaped operations are actually served, so
+	// this is what separates a truthful auto-crud label from a claim: the CRUD
+	// registry says an operation is *classifiable*, never that it is reachable.
+	EngineWired bool
 }
 
 // ScanProviders returns, per registered service ID, the operations its provider
@@ -104,7 +110,10 @@ func ScanProviders(servicesDir string) (map[string]ProviderScan, error) {
 			return nil, err
 		}
 		for id, recvType := range pkg.serviceTypes {
-			result[id] = ProviderScan{Operations: opsFor(id, pkg.dispatchedOps(recvType))}
+			result[id] = ProviderScan{
+				Operations:  opsFor(id, pkg.dispatchedOps(recvType)),
+				EngineWired: pkg.wiresCRUDEngine(recvType),
+			}
 		}
 	}
 	return result, nil
@@ -203,6 +212,42 @@ func (p packageScan) dispatchedOps(recvType string) map[string]bool {
 	return ops
 }
 
+// wiresCRUDEngine reports whether a provider type opts into the generic CRUD
+// engine, by returning plugin.ErrUnhandledOp anywhere in its dispatch.
+//
+// It walks the same methods as dispatchedOps, and for the same reason: scoping
+// to one receiver's dispatch is what stops a package registering two services
+// (iam also registers sts) from crediting one with the other's wiring.
+func (p packageScan) wiresCRUDEngine(recvType string) bool {
+	visited := make(map[string]bool)
+	wired := false
+
+	var walk func(name string)
+	walk = func(name string) {
+		fn := p.methods[recvType][name]
+		if fn == nil || fn.Body == nil || visited[name] || wired {
+			return
+		}
+		visited[name] = true
+
+		ast.Inspect(fn.Body, func(n ast.Node) bool {
+			sel, ok := n.(*ast.SelectorExpr)
+			if !ok || sel.Sel.Name != "ErrUnhandledOp" {
+				return true
+			}
+			if ident, isIdent := sel.X.(*ast.Ident); isIdent && ident.Name == "plugin" {
+				wired = true
+			}
+			return true
+		})
+		for _, delegate := range delegateCalls(fn) {
+			walk(delegate)
+		}
+	}
+	walk("HandleRequest")
+	return wired
+}
+
 // collectCaseLiterals reads the case literals of every keyed switch in a body.
 // Keyed is the point: `switch op { case "GetItem": }` dispatches, whereas a
 // tagless `switch { case remaining == 0: }` is control flow whose cases are
diff --git a/internal/codegen/scan_handverified_test.go b/internal/codegen/scan_handverified_test.go
index e418c5b9..bef430ba 100644
--- a/internal/codegen/scan_handverified_test.go
+++ b/internal/codegen/scan_handverified_test.go
@@ -66,9 +66,14 @@ func TestScanProviders(t *testing.T) {
 	assert.Contains(t, got["s3"], "PutObject")
 	assert.Contains(t, got["bedrock"], "InvokeModel")
 
-	// No service is silently empty — an empty set means the scan lost a provider.
+	// No service is silently empty — an empty set means the scan lost a
+	// provider, unless the provider hand-implements nothing on purpose and is
+	// served entirely by the CRUD engine, which is what a scaffolded service is.
 	for id, ops := range got {
-		assert.NotEmpty(t, ops, "%s resolved no hand-verified operations", id)
+		if scans[id].EngineWired {
+			continue
+		}
+		assert.NotEmpty(t, ops, "%s resolved no hand-verified operations and is not engine-wired, so it serves nothing", id)
 	}
 }
 
@@ -165,6 +170,26 @@ func TestPathRoutedOverridesAreReal(t *testing.T) {
 	}
 }
 
+// TestScanProvidersDetectsEngineWiring checks the scan reports whether a
+// provider reaches the generic CRUD engine. Only a provider that returns
+// plugin.ErrUnhandledOp does; the rest decline in their own vocabulary and are
+// served by nothing, so the fidelity manifest must not call their CRUD-shaped
+// operations auto-crud.
+func TestScanProvidersDetectsEngineWiring(t *testing.T) {
+	scans, err := ScanProviders("../services")
+	require.NoError(t, err)
+
+	for _, id := range []string{"codebuild", "organizations", "kinesis"} {
+		assert.True(t, scans[id].EngineWired,
+			"%s returns plugin.ErrUnhandledOp, so it must be reported as engine-wired", id)
+	}
+	// Path-routed and Query-protocol providers that answer their own default.
+	for _, id := range []string{"s3", "iam", "route53"} {
+		assert.False(t, scans[id].EngineWired,
+			"%s never returns plugin.ErrUnhandledOp, so it must not be reported as engine-wired", id)
+	}
+}
+
 // TestScanProvidersIsDeterministic keeps generated output stable across runs.
 func TestScanProvidersIsDeterministic(t *testing.T) {
 	first, err := ScanProviders("../services")
diff --git a/internal/codegen/templates/scaffold_provider.go.tmpl b/internal/codegen/templates/scaffold_provider.go.tmpl
index 3caceafa..23932f38 100644
--- a/internal/codegen/templates/scaffold_provider.go.tmpl
+++ b/internal/codegen/templates/scaffold_provider.go.tmpl
@@ -13,6 +13,7 @@ import (
 // Provider implements the {{ .ServiceName }} service.
 type Provider struct {
 	generated.BaseProvider
+	dataDir string
 }
 
 func (p *Provider) ServiceID() string      { return "{{ .ServiceID }}" }
@@ -20,6 +21,7 @@ func (p *Provider) ServiceName() string    { return "{{ .ServiceName }}" }
 func (p *Provider) Protocol() plugin.ProtocolType { return plugin.{{ .ProtocolConst }} }
 
 func (p *Provider) Init(cfg plugin.PluginConfig) error {
+	p.dataDir = cfg.DataDir
 	return nil
 }
 
@@ -27,8 +29,17 @@ func (p *Provider) Shutdown(ctx context.Context) error {
 	return nil
 }
 
+// HandleRequest implements nothing by hand and says so, which is what hands the
+// request to the generic CRUD engine (see docs/crud-engine.md). A scaffolded
+// service therefore serves its CRUD-shaped operations from the moment it is
+// generated; anything the engine cannot classify still returns an honest
+// InvalidAction rather than a fabricated success.
+//
+// Declining any other way — including generated.ErrNotImplemented — is a plain
+// refusal the gateway never routes to the engine, leaving the service
+// registered, routed, and serving zero operations.
 func (p *Provider) HandleRequest(ctx context.Context, op string, req *http.Request) (*plugin.Response, error) {
-	return nil, generated.ErrNotImplemented
+	return nil, plugin.ErrUnhandledOp
 }
 
 func (p *Provider) ListResources(ctx context.Context) ([]plugin.Resource, error) {
diff --git a/internal/generated/comprehend/base_provider.go b/internal/generated/comprehend/base_provider.go
new file mode 100644
index 00000000..28f2b96c
--- /dev/null
+++ b/internal/generated/comprehend/base_provider.go
@@ -0,0 +1,352 @@
+// Code generated by devcloud codegen. DO NOT EDIT.
+// SPDX-License-Identifier: Apache-2.0
+package comprehend
+
+import (
+	"context"
+	"fmt"
+)
+
+var ErrNotImplemented = fmt.Errorf("operation not implemented")
+
+type BaseProvider struct{}
+
+func (b *BaseProvider) BatchDetectDominantLanguage(ctx context.Context, input *BatchDetectDominantLanguageRequest) (*BatchDetectDominantLanguageResponse, error) {
+	return nil, fmt.Errorf("BatchDetectDominantLanguage: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) BatchDetectEntities(ctx context.Context, input *BatchDetectEntitiesRequest) (*BatchDetectEntitiesResponse, error) {
+	return nil, fmt.Errorf("BatchDetectEntities: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) BatchDetectKeyPhrases(ctx context.Context, input *BatchDetectKeyPhrasesRequest) (*BatchDetectKeyPhrasesResponse, error) {
+	return nil, fmt.Errorf("BatchDetectKeyPhrases: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) BatchDetectSentiment(ctx context.Context, input *BatchDetectSentimentRequest) (*BatchDetectSentimentResponse, error) {
+	return nil, fmt.Errorf("BatchDetectSentiment: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) BatchDetectSyntax(ctx context.Context, input *BatchDetectSyntaxRequest) (*BatchDetectSyntaxResponse, error) {
+	return nil, fmt.Errorf("BatchDetectSyntax: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) BatchDetectTargetedSentiment(ctx context.Context, input *BatchDetectTargetedSentimentRequest) (*BatchDetectTargetedSentimentResponse, error) {
+	return nil, fmt.Errorf("BatchDetectTargetedSentiment: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ClassifyDocument(ctx context.Context, input *ClassifyDocumentRequest) (*ClassifyDocumentResponse, error) {
+	return nil, fmt.Errorf("ClassifyDocument: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ContainsPiiEntities(ctx context.Context, input *ContainsPiiEntitiesRequest) (*ContainsPiiEntitiesResponse, error) {
+	return nil, fmt.Errorf("ContainsPiiEntities: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) CreateDataset(ctx context.Context, input *CreateDatasetRequest) (*CreateDatasetResponse, error) {
+	return nil, fmt.Errorf("CreateDataset: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) CreateDocumentClassifier(ctx context.Context, input *CreateDocumentClassifierRequest) (*CreateDocumentClassifierResponse, error) {
+	return nil, fmt.Errorf("CreateDocumentClassifier: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) CreateEndpoint(ctx context.Context, input *CreateEndpointRequest) (*CreateEndpointResponse, error) {
+	return nil, fmt.Errorf("CreateEndpoint: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) CreateEntityRecognizer(ctx context.Context, input *CreateEntityRecognizerRequest) (*CreateEntityRecognizerResponse, error) {
+	return nil, fmt.Errorf("CreateEntityRecognizer: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) CreateFlywheel(ctx context.Context, input *CreateFlywheelRequest) (*CreateFlywheelResponse, error) {
+	return nil, fmt.Errorf("CreateFlywheel: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DeleteDocumentClassifier(ctx context.Context, input *DeleteDocumentClassifierRequest) (*DeleteDocumentClassifierResponse, error) {
+	return nil, fmt.Errorf("DeleteDocumentClassifier: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DeleteEndpoint(ctx context.Context, input *DeleteEndpointRequest) (*DeleteEndpointResponse, error) {
+	return nil, fmt.Errorf("DeleteEndpoint: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DeleteEntityRecognizer(ctx context.Context, input *DeleteEntityRecognizerRequest) (*DeleteEntityRecognizerResponse, error) {
+	return nil, fmt.Errorf("DeleteEntityRecognizer: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DeleteFlywheel(ctx context.Context, input *DeleteFlywheelRequest) (*DeleteFlywheelResponse, error) {
+	return nil, fmt.Errorf("DeleteFlywheel: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DeleteResourcePolicy(ctx context.Context, input *DeleteResourcePolicyRequest) (*DeleteResourcePolicyResponse, error) {
+	return nil, fmt.Errorf("DeleteResourcePolicy: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeDataset(ctx context.Context, input *DescribeDatasetRequest) (*DescribeDatasetResponse, error) {
+	return nil, fmt.Errorf("DescribeDataset: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeDocumentClassificationJob(ctx context.Context, input *DescribeDocumentClassificationJobRequest) (*DescribeDocumentClassificationJobResponse, error) {
+	return nil, fmt.Errorf("DescribeDocumentClassificationJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeDocumentClassifier(ctx context.Context, input *DescribeDocumentClassifierRequest) (*DescribeDocumentClassifierResponse, error) {
+	return nil, fmt.Errorf("DescribeDocumentClassifier: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeDominantLanguageDetectionJob(ctx context.Context, input *DescribeDominantLanguageDetectionJobRequest) (*DescribeDominantLanguageDetectionJobResponse, error) {
+	return nil, fmt.Errorf("DescribeDominantLanguageDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeEndpoint(ctx context.Context, input *DescribeEndpointRequest) (*DescribeEndpointResponse, error) {
+	return nil, fmt.Errorf("DescribeEndpoint: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeEntitiesDetectionJob(ctx context.Context, input *DescribeEntitiesDetectionJobRequest) (*DescribeEntitiesDetectionJobResponse, error) {
+	return nil, fmt.Errorf("DescribeEntitiesDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeEntityRecognizer(ctx context.Context, input *DescribeEntityRecognizerRequest) (*DescribeEntityRecognizerResponse, error) {
+	return nil, fmt.Errorf("DescribeEntityRecognizer: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeEventsDetectionJob(ctx context.Context, input *DescribeEventsDetectionJobRequest) (*DescribeEventsDetectionJobResponse, error) {
+	return nil, fmt.Errorf("DescribeEventsDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeFlywheel(ctx context.Context, input *DescribeFlywheelRequest) (*DescribeFlywheelResponse, error) {
+	return nil, fmt.Errorf("DescribeFlywheel: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeFlywheelIteration(ctx context.Context, input *DescribeFlywheelIterationRequest) (*DescribeFlywheelIterationResponse, error) {
+	return nil, fmt.Errorf("DescribeFlywheelIteration: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeKeyPhrasesDetectionJob(ctx context.Context, input *DescribeKeyPhrasesDetectionJobRequest) (*DescribeKeyPhrasesDetectionJobResponse, error) {
+	return nil, fmt.Errorf("DescribeKeyPhrasesDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribePiiEntitiesDetectionJob(ctx context.Context, input *DescribePiiEntitiesDetectionJobRequest) (*DescribePiiEntitiesDetectionJobResponse, error) {
+	return nil, fmt.Errorf("DescribePiiEntitiesDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeResourcePolicy(ctx context.Context, input *DescribeResourcePolicyRequest) (*DescribeResourcePolicyResponse, error) {
+	return nil, fmt.Errorf("DescribeResourcePolicy: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeSentimentDetectionJob(ctx context.Context, input *DescribeSentimentDetectionJobRequest) (*DescribeSentimentDetectionJobResponse, error) {
+	return nil, fmt.Errorf("DescribeSentimentDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeTargetedSentimentDetectionJob(ctx context.Context, input *DescribeTargetedSentimentDetectionJobRequest) (*DescribeTargetedSentimentDetectionJobResponse, error) {
+	return nil, fmt.Errorf("DescribeTargetedSentimentDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DescribeTopicsDetectionJob(ctx context.Context, input *DescribeTopicsDetectionJobRequest) (*DescribeTopicsDetectionJobResponse, error) {
+	return nil, fmt.Errorf("DescribeTopicsDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DetectDominantLanguage(ctx context.Context, input *DetectDominantLanguageRequest) (*DetectDominantLanguageResponse, error) {
+	return nil, fmt.Errorf("DetectDominantLanguage: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DetectEntities(ctx context.Context, input *DetectEntitiesRequest) (*DetectEntitiesResponse, error) {
+	return nil, fmt.Errorf("DetectEntities: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DetectKeyPhrases(ctx context.Context, input *DetectKeyPhrasesRequest) (*DetectKeyPhrasesResponse, error) {
+	return nil, fmt.Errorf("DetectKeyPhrases: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DetectPiiEntities(ctx context.Context, input *DetectPiiEntitiesRequest) (*DetectPiiEntitiesResponse, error) {
+	return nil, fmt.Errorf("DetectPiiEntities: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DetectSentiment(ctx context.Context, input *DetectSentimentRequest) (*DetectSentimentResponse, error) {
+	return nil, fmt.Errorf("DetectSentiment: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DetectSyntax(ctx context.Context, input *DetectSyntaxRequest) (*DetectSyntaxResponse, error) {
+	return nil, fmt.Errorf("DetectSyntax: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DetectTargetedSentiment(ctx context.Context, input *DetectTargetedSentimentRequest) (*DetectTargetedSentimentResponse, error) {
+	return nil, fmt.Errorf("DetectTargetedSentiment: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) DetectToxicContent(ctx context.Context, input *DetectToxicContentRequest) (*DetectToxicContentResponse, error) {
+	return nil, fmt.Errorf("DetectToxicContent: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ImportModel(ctx context.Context, input *ImportModelRequest) (*ImportModelResponse, error) {
+	return nil, fmt.Errorf("ImportModel: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListDatasets(ctx context.Context, input *ListDatasetsRequest) (*ListDatasetsResponse, error) {
+	return nil, fmt.Errorf("ListDatasets: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListDocumentClassificationJobs(ctx context.Context, input *ListDocumentClassificationJobsRequest) (*ListDocumentClassificationJobsResponse, error) {
+	return nil, fmt.Errorf("ListDocumentClassificationJobs: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListDocumentClassifierSummaries(ctx context.Context, input *ListDocumentClassifierSummariesRequest) (*ListDocumentClassifierSummariesResponse, error) {
+	return nil, fmt.Errorf("ListDocumentClassifierSummaries: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListDocumentClassifiers(ctx context.Context, input *ListDocumentClassifiersRequest) (*ListDocumentClassifiersResponse, error) {
+	return nil, fmt.Errorf("ListDocumentClassifiers: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListDominantLanguageDetectionJobs(ctx context.Context, input *ListDominantLanguageDetectionJobsRequest) (*ListDominantLanguageDetectionJobsResponse, error) {
+	return nil, fmt.Errorf("ListDominantLanguageDetectionJobs: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListEndpoints(ctx context.Context, input *ListEndpointsRequest) (*ListEndpointsResponse, error) {
+	return nil, fmt.Errorf("ListEndpoints: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListEntitiesDetectionJobs(ctx context.Context, input *ListEntitiesDetectionJobsRequest) (*ListEntitiesDetectionJobsResponse, error) {
+	return nil, fmt.Errorf("ListEntitiesDetectionJobs: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListEntityRecognizerSummaries(ctx context.Context, input *ListEntityRecognizerSummariesRequest) (*ListEntityRecognizerSummariesResponse, error) {
+	return nil, fmt.Errorf("ListEntityRecognizerSummaries: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListEntityRecognizers(ctx context.Context, input *ListEntityRecognizersRequest) (*ListEntityRecognizersResponse, error) {
+	return nil, fmt.Errorf("ListEntityRecognizers: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListEventsDetectionJobs(ctx context.Context, input *ListEventsDetectionJobsRequest) (*ListEventsDetectionJobsResponse, error) {
+	return nil, fmt.Errorf("ListEventsDetectionJobs: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListFlywheelIterationHistory(ctx context.Context, input *ListFlywheelIterationHistoryRequest) (*ListFlywheelIterationHistoryResponse, error) {
+	return nil, fmt.Errorf("ListFlywheelIterationHistory: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListFlywheels(ctx context.Context, input *ListFlywheelsRequest) (*ListFlywheelsResponse, error) {
+	return nil, fmt.Errorf("ListFlywheels: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListKeyPhrasesDetectionJobs(ctx context.Context, input *ListKeyPhrasesDetectionJobsRequest) (*ListKeyPhrasesDetectionJobsResponse, error) {
+	return nil, fmt.Errorf("ListKeyPhrasesDetectionJobs: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListPiiEntitiesDetectionJobs(ctx context.Context, input *ListPiiEntitiesDetectionJobsRequest) (*ListPiiEntitiesDetectionJobsResponse, error) {
+	return nil, fmt.Errorf("ListPiiEntitiesDetectionJobs: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListSentimentDetectionJobs(ctx context.Context, input *ListSentimentDetectionJobsRequest) (*ListSentimentDetectionJobsResponse, error) {
+	return nil, fmt.Errorf("ListSentimentDetectionJobs: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListTagsForResource(ctx context.Context, input *ListTagsForResourceRequest) (*ListTagsForResourceResponse, error) {
+	return nil, fmt.Errorf("ListTagsForResource: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListTargetedSentimentDetectionJobs(ctx context.Context, input *ListTargetedSentimentDetectionJobsRequest) (*ListTargetedSentimentDetectionJobsResponse, error) {
+	return nil, fmt.Errorf("ListTargetedSentimentDetectionJobs: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) ListTopicsDetectionJobs(ctx context.Context, input *ListTopicsDetectionJobsRequest) (*ListTopicsDetectionJobsResponse, error) {
+	return nil, fmt.Errorf("ListTopicsDetectionJobs: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) PutResourcePolicy(ctx context.Context, input *PutResourcePolicyRequest) (*PutResourcePolicyResponse, error) {
+	return nil, fmt.Errorf("PutResourcePolicy: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StartDocumentClassificationJob(ctx context.Context, input *StartDocumentClassificationJobRequest) (*StartDocumentClassificationJobResponse, error) {
+	return nil, fmt.Errorf("StartDocumentClassificationJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StartDominantLanguageDetectionJob(ctx context.Context, input *StartDominantLanguageDetectionJobRequest) (*StartDominantLanguageDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StartDominantLanguageDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StartEntitiesDetectionJob(ctx context.Context, input *StartEntitiesDetectionJobRequest) (*StartEntitiesDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StartEntitiesDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StartEventsDetectionJob(ctx context.Context, input *StartEventsDetectionJobRequest) (*StartEventsDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StartEventsDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StartFlywheelIteration(ctx context.Context, input *StartFlywheelIterationRequest) (*StartFlywheelIterationResponse, error) {
+	return nil, fmt.Errorf("StartFlywheelIteration: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StartKeyPhrasesDetectionJob(ctx context.Context, input *StartKeyPhrasesDetectionJobRequest) (*StartKeyPhrasesDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StartKeyPhrasesDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StartPiiEntitiesDetectionJob(ctx context.Context, input *StartPiiEntitiesDetectionJobRequest) (*StartPiiEntitiesDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StartPiiEntitiesDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StartSentimentDetectionJob(ctx context.Context, input *StartSentimentDetectionJobRequest) (*StartSentimentDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StartSentimentDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StartTargetedSentimentDetectionJob(ctx context.Context, input *StartTargetedSentimentDetectionJobRequest) (*StartTargetedSentimentDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StartTargetedSentimentDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StartTopicsDetectionJob(ctx context.Context, input *StartTopicsDetectionJobRequest) (*StartTopicsDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StartTopicsDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StopDominantLanguageDetectionJob(ctx context.Context, input *StopDominantLanguageDetectionJobRequest) (*StopDominantLanguageDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StopDominantLanguageDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StopEntitiesDetectionJob(ctx context.Context, input *StopEntitiesDetectionJobRequest) (*StopEntitiesDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StopEntitiesDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StopEventsDetectionJob(ctx context.Context, input *StopEventsDetectionJobRequest) (*StopEventsDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StopEventsDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StopKeyPhrasesDetectionJob(ctx context.Context, input *StopKeyPhrasesDetectionJobRequest) (*StopKeyPhrasesDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StopKeyPhrasesDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StopPiiEntitiesDetectionJob(ctx context.Context, input *StopPiiEntitiesDetectionJobRequest) (*StopPiiEntitiesDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StopPiiEntitiesDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StopSentimentDetectionJob(ctx context.Context, input *StopSentimentDetectionJobRequest) (*StopSentimentDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StopSentimentDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StopTargetedSentimentDetectionJob(ctx context.Context, input *StopTargetedSentimentDetectionJobRequest) (*StopTargetedSentimentDetectionJobResponse, error) {
+	return nil, fmt.Errorf("StopTargetedSentimentDetectionJob: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StopTrainingDocumentClassifier(ctx context.Context, input *StopTrainingDocumentClassifierRequest) (*StopTrainingDocumentClassifierResponse, error) {
+	return nil, fmt.Errorf("StopTrainingDocumentClassifier: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) StopTrainingEntityRecognizer(ctx context.Context, input *StopTrainingEntityRecognizerRequest) (*StopTrainingEntityRecognizerResponse, error) {
+	return nil, fmt.Errorf("StopTrainingEntityRecognizer: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) TagResource(ctx context.Context, input *TagResourceRequest) (*TagResourceResponse, error) {
+	return nil, fmt.Errorf("TagResource: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) UntagResource(ctx context.Context, input *UntagResourceRequest) (*UntagResourceResponse, error) {
+	return nil, fmt.Errorf("UntagResource: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) UpdateEndpoint(ctx context.Context, input *UpdateEndpointRequest) (*UpdateEndpointResponse, error) {
+	return nil, fmt.Errorf("UpdateEndpoint: %w", ErrNotImplemented)
+}
+
+func (b *BaseProvider) UpdateFlywheel(ctx context.Context, input *UpdateFlywheelRequest) (*UpdateFlywheelResponse, error) {
+	return nil, fmt.Errorf("UpdateFlywheel: %w", ErrNotImplemented)
+}
diff --git a/internal/generated/comprehend/errors.go b/internal/generated/comprehend/errors.go
new file mode 100644
index 00000000..184d6656
--- /dev/null
+++ b/internal/generated/comprehend/errors.go
@@ -0,0 +1,277 @@
+// Code generated by devcloud codegen. DO NOT EDIT.
+// SPDX-License-Identifier: Apache-2.0
+package comprehend
+
+import "fmt"
+
+// BatchSizeLimitExceededException is returned with HTTP status 400.
+type BatchSizeLimitExceededException struct {
+	Message string
+}
+
+func (e *BatchSizeLimitExceededException) Error() string {
+	return fmt.Sprintf("BatchSizeLimitExceededException: %s", e.Message)
+}
+
+func (e *BatchSizeLimitExceededException) ErrorCode() string {
+	return "BatchSizeLimitExceededException"
+}
+
+func (e *BatchSizeLimitExceededException) HTTPStatus() int {
+	return 400
+}
+
+// ConcurrentModificationException is returned with HTTP status 400.
+type ConcurrentModificationException struct {
+	Message string
+}
+
+func (e *ConcurrentModificationException) Error() string {
+	return fmt.Sprintf("ConcurrentModificationException: %s", e.Message)
+}
+
+func (e *ConcurrentModificationException) ErrorCode() string {
+	return "ConcurrentModificationException"
+}
+
+func (e *ConcurrentModificationException) HTTPStatus() int {
+	return 400
+}
+
+// InternalServerException is returned with HTTP status 500.
+type InternalServerException struct {
+	Message string
+}
+
+func (e *InternalServerException) Error() string {
+	return fmt.Sprintf("InternalServerException: %s", e.Message)
+}
+
+func (e *InternalServerException) ErrorCode() string {
+	return "InternalServerException"
+}
+
+func (e *InternalServerException) HTTPStatus() int {
+	return 500
+}
+
+// InvalidFilterException is returned with HTTP status 400.
+type InvalidFilterException struct {
+	Message string
+}
+
+func (e *InvalidFilterException) Error() string {
+	return fmt.Sprintf("InvalidFilterException: %s", e.Message)
+}
+
+func (e *InvalidFilterException) ErrorCode() string {
+	return "InvalidFilterException"
+}
+
+func (e *InvalidFilterException) HTTPStatus() int {
+	return 400
+}
+
+// InvalidRequestException is returned with HTTP status 400.
+type InvalidRequestException struct {
+	Message string
+}
+
+func (e *InvalidRequestException) Error() string {
+	return fmt.Sprintf("InvalidRequestException: %s", e.Message)
+}
+
+func (e *InvalidRequestException) ErrorCode() string {
+	return "InvalidRequestException"
+}
+
+func (e *InvalidRequestException) HTTPStatus() int {
+	return 400
+}
+
+// JobNotFoundException is returned with HTTP status 404.
+type JobNotFoundException struct {
+	Message string
+}
+
+func (e *JobNotFoundException) Error() string {
+	return fmt.Sprintf("JobNotFoundException: %s", e.Message)
+}
+
+func (e *JobNotFoundException) ErrorCode() string {
+	return "JobNotFoundException"
+}
+
+func (e *JobNotFoundException) HTTPStatus() int {
+	return 404
+}
+
+// KmsKeyValidationException is returned with HTTP status 400.
+type KmsKeyValidationException struct {
+	Message string
+}
+
+func (e *KmsKeyValidationException) Error() string {
+	return fmt.Sprintf("KmsKeyValidationException: %s", e.Message)
+}
+
+func (e *KmsKeyValidationException) ErrorCode() string {
+	return "KmsKeyValidationException"
+}
+
+func (e *KmsKeyValidationException) HTTPStatus() int {
+	return 400
+}
+
+// ResourceInUseException is returned with HTTP status 400.
+type ResourceInUseException struct {
+	Message string
+}
+
+func (e *ResourceInUseException) Error() string {
+	return fmt.Sprintf("ResourceInUseException: %s", e.Message)
+}
+
+func (e *ResourceInUseException) ErrorCode() string {
+	return "ResourceInUseException"
+}
+
+func (e *ResourceInUseException) HTTPStatus() int {
+	return 400
+}
+
+// ResourceLimitExceededException is returned with HTTP status 400.
+type ResourceLimitExceededException struct {
+	Message string
+}
+
+func (e *ResourceLimitExceededException) Error() string {
+	return fmt.Sprintf("ResourceLimitExceededException: %s", e.Message)
+}
+
+func (e *ResourceLimitExceededException) ErrorCode() string {
+	return "ResourceLimitExceededException"
+}
+
+func (e *ResourceLimitExceededException) HTTPStatus() int {
+	return 400
+}
+
+// ResourceNotFoundException is returned with HTTP status 404.
+type ResourceNotFoundException struct {
+	Message string
+}
+
+func (e *ResourceNotFoundException) Error() string {
+	return fmt.Sprintf("ResourceNotFoundException: %s", e.Message)
+}
+
+func (e *ResourceNotFoundException) ErrorCode() string {
+	return "ResourceNotFoundException"
+}
+
+func (e *ResourceNotFoundException) HTTPStatus() int {
+	return 404
+}
+
+// ResourceUnavailableException is returned with HTTP status 404.
+type ResourceUnavailableException struct {
+	Message string
+}
+
+func (e *ResourceUnavailableException) Error() string {
+	return fmt.Sprintf("ResourceUnavailableException: %s", e.Message)
+}
+
+func (e *ResourceUnavailableException) ErrorCode() string {
+	return "ResourceUnavailableException"
+}
+
+func (e *ResourceUnavailableException) HTTPStatus() int {
+	return 404
+}
+
+// TextSizeLimitExceededException is returned with HTTP status 400.
+type TextSizeLimitExceededException struct {
+	Message string
+}
+
+func (e *TextSizeLimitExceededException) Error() string {
+	return fmt.Sprintf("TextSizeLimitExceededException: %s", e.Message)
+}
+
+func (e *TextSizeLimitExceededException) ErrorCode() string {
+	return "TextSizeLimitExceededException"
+}
+
+func (e *TextSizeLimitExceededException) HTTPStatus() int {
+	return 400
+}
+
+// TooManyRequestsException is returned with HTTP status 429.
+type TooManyRequestsException struct {
+	Message string
+}
+
+func (e *TooManyRequestsException) Error() string {
+	return fmt.Sprintf("TooManyRequestsException: %s", e.Message)
+}
+
+func (e *TooManyRequestsException) ErrorCode() string {
+	return "TooManyRequestsException"
+}
+
+func (e *TooManyRequestsException) HTTPStatus() int {
+	return 429
+}
+
+// TooManyTagKeysException is returned with HTTP status 400.
+type TooManyTagKeysException struct {
+	Message string
+}
+
+func (e *TooManyTagKeysException) Error() string {
+	return fmt.Sprintf("TooManyTagKeysException: %s", e.Message)
+}
+
+func (e *TooManyTagKeysException) ErrorCode() string {
+	return "TooManyTagKeysException"
+}
+
+func (e *TooManyTagKeysException) HTTPStatus() int {
+	return 400
+}
+
+// TooManyTagsException is returned with HTTP status 400.
+type TooManyTagsException struct {
+	Message string
+}
+
+func (e *TooManyTagsException) Error() string {
+	return fmt.Sprintf("TooManyTagsException: %s", e.Message)
+}
+
+func (e *TooManyTagsException) ErrorCode() string {
+	return "TooManyTagsException"
+}
+
+func (e *TooManyTagsException) HTTPStatus() int {
+	return 400
+}
+
+// UnsupportedLanguageException is returned with HTTP status 400.
+type UnsupportedLanguageException struct {
+	Message string
+}
+
+func (e *UnsupportedLanguageException) Error() string {
+	return fmt.Sprintf("UnsupportedLanguageException: %s", e.Message)
+}
+
+func (e *UnsupportedLanguageException) ErrorCode() string {
+	return "UnsupportedLanguageException"
+}
+
+func (e *UnsupportedLanguageException) HTTPStatus() int {
+	return 400
+}
diff --git a/internal/generated/comprehend/router.go b/internal/generated/comprehend/router.go
new file mode 100644
index 00000000..0a804368
--- /dev/null
+++ b/internal/generated/comprehend/router.go
@@ -0,0 +1,238 @@
+// Code generated by devcloud codegen. DO NOT EDIT.
+// SPDX-License-Identifier: Apache-2.0
+package comprehend
+
+import (
+	"net/url"
+	"strings"
+)
+
+// PathParams holds the URL path parameters extracted by the router.
+type PathParams map[string]string
+
+// OperationRoute maps an HTTP method and URI pattern to an operation name.
+type OperationRoute struct {
+	Method    string
+	Pattern   string
+	Operation string
+}
+
+// OperationRoutes is the list of all routes for this service.
+var OperationRoutes = []OperationRoute{
+	{Method: "", Pattern: "", Operation: "BatchDetectDominantLanguage"},
+	{Method: "", Pattern: "", Operation: "BatchDetectEntities"},
+	{Method: "", Pattern: "", Operation: "BatchDetectKeyPhrases"},
+	{Method: "", Pattern: "", Operation: "BatchDetectSentiment"},
+	{Method: "", Pattern: "", Operation: "BatchDetectSyntax"},
+	{Method: "", Pattern: "", Operation: "BatchDetectTargetedSentiment"},
+	{Method: "", Pattern: "", Operation: "ClassifyDocument"},
+	{Method: "", Pattern: "", Operation: "ContainsPiiEntities"},
+	{Method: "", Pattern: "", Operation: "CreateDataset"},
+	{Method: "", Pattern: "", Operation: "CreateDocumentClassifier"},
+	{Method: "", Pattern: "", Operation: "CreateEndpoint"},
+	{Method: "", Pattern: "", Operation: "CreateEntityRecognizer"},
+	{Method: "", Pattern: "", Operation: "CreateFlywheel"},
+	{Method: "", Pattern: "", Operation: "DeleteDocumentClassifier"},
+	{Method: "", Pattern: "", Operation: "DeleteEndpoint"},
+	{Method: "", Pattern: "", Operation: "DeleteEntityRecognizer"},
+	{Method: "", Pattern: "", Operation: "DeleteFlywheel"},
+	{Method: "", Pattern: "", Operation: "DeleteResourcePolicy"},
+	{Method: "", Pattern: "", Operation: "DescribeDataset"},
+	{Method: "", Pattern: "", Operation: "DescribeDocumentClassificationJob"},
+	{Method: "", Pattern: "", Operation: "DescribeDocumentClassifier"},
+	{Method: "", Pattern: "", Operation: "DescribeDominantLanguageDetectionJob"},
+	{Method: "", Pattern: "", Operation: "DescribeEndpoint"},
+	{Method: "", Pattern: "", Operation: "DescribeEntitiesDetectionJob"},
+	{Method: "", Pattern: "", Operation: "DescribeEntityRecognizer"},
+	{Method: "", Pattern: "", Operation: "DescribeEventsDetectionJob"},
+	{Method: "", Pattern: "", Operation: "DescribeFlywheel"},
+	{Method: "", Pattern: "", Operation: "DescribeFlywheelIteration"},
+	{Method: "", Pattern: "", Operation: "DescribeKeyPhrasesDetectionJob"},
+	{Method: "", Pattern: "", Operation: "DescribePiiEntitiesDetectionJob"},
+	{Method: "", Pattern: "", Operation: "DescribeResourcePolicy"},
+	{Method: "", Pattern: "", Operation: "DescribeSentimentDetectionJob"},
+	{Method: "", Pattern: "", Operation: "DescribeTargetedSentimentDetectionJob"},
+	{Method: "", Pattern: "", Operation: "DescribeTopicsDetectionJob"},
+	{Method: "", Pattern: "", Operation: "DetectDominantLanguage"},
+	{Method: "", Pattern: "", Operation: "DetectEntities"},
+	{Method: "", Pattern: "", Operation: "DetectKeyPhrases"},
+	{Method: "", Pattern: "", Operation: "DetectPiiEntities"},
+	{Method: "", Pattern: "", Operation: "DetectSentiment"},
+	{Method: "", Pattern: "", Operation: "DetectSyntax"},
+	{Method: "", Pattern: "", Operation: "DetectTargetedSentiment"},
+	{Method: "", Pattern: "", Operation: "DetectToxicContent"},
+	{Method: "", Pattern: "", Operation: "ImportModel"},
+	{Method: "", Pattern: "", Operation: "ListDatasets"},
+	{Method: "", Pattern: "", Operation: "ListDocumentClassificationJobs"},
+	{Method: "", Pattern: "", Operation: "ListDocumentClassifierSummaries"},
+	{Method: "", Pattern: "", Operation: "ListDocumentClassifiers"},
+	{Method: "", Pattern: "", Operation: "ListDominantLanguageDetectionJobs"},
+	{Method: "", Pattern: "", Operation: "ListEndpoints"},
+	{Method: "", Pattern: "", Operation: "ListEntitiesDetectionJobs"},
+	{Method: "", Pattern: "", Operation: "ListEntityRecognizerSummaries"},
+	{Method: "", Pattern: "", Operation: "ListEntityRecognizers"},
+	{Method: "", Pattern: "", Operation: "ListEventsDetectionJobs"},
+	{Method: "", Pattern: "", Operation: "ListFlywheelIterationHistory"},
+	{Method: "", Pattern: "", Operation: "ListFlywheels"},
+	{Method: "", Pattern: "", Operation: "ListKeyPhrasesDetectionJobs"},
+	{Method: "", Pattern: "", Operation: "ListPiiEntitiesDetectionJobs"},
+	{Method: "", Pattern: "", Operation: "ListSentimentDetectionJobs"},
+	{Method: "", Pattern: "", Operation: "ListTagsForResource"},
+	{Method: "", Pattern: "", Operation: "ListTargetedSentimentDetectionJobs"},
+	{Method: "", Pattern: "", Operation: "ListTopicsDetectionJobs"},
+	{Method: "", Pattern: "", Operation: "PutResourcePolicy"},
+	{Method: "", Pattern: "", Operation: "StartDocumentClassificationJob"},
+	{Method: "", Pattern: "", Operation: "StartDominantLanguageDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StartEntitiesDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StartEventsDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StartFlywheelIteration"},
+	{Method: "", Pattern: "", Operation: "StartKeyPhrasesDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StartPiiEntitiesDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StartSentimentDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StartTargetedSentimentDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StartTopicsDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StopDominantLanguageDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StopEntitiesDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StopEventsDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StopKeyPhrasesDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StopPiiEntitiesDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StopSentimentDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StopTargetedSentimentDetectionJob"},
+	{Method: "", Pattern: "", Operation: "StopTrainingDocumentClassifier"},
+	{Method: "", Pattern: "", Operation: "StopTrainingEntityRecognizer"},
+	{Method: "", Pattern: "", Operation: "TagResource"},
+	{Method: "", Pattern: "", Operation: "UntagResource"},
+	{Method: "", Pattern: "", Operation: "UpdateEndpoint"},
+	{Method: "", Pattern: "", Operation: "UpdateFlywheel"},
+}
+
+// MatchOperation returns the operation name and extracted path parameters for
+// the given HTTP method and request URI. It returns ("", nil) if no route
+// matches.
+//
+// Pass req.URL.RequestURI(), not req.URL.Path: some AWS operations are
+// distinguished only by a query string (".../tagging?Operation=Tag"), and a
+// bare path can never satisfy those routes.
+func MatchOperation(method, uri string) (string, PathParams) {
+	// Two passes. A route that constrains the query is more specific than one
+	// that does not, and OperationRoutes is ordered by operation name rather
+	// than specificity — so trying constrained routes first keeps
+	// ".../distribution" from shadowing ".../distribution?WithTags".
+	for _, constrained := range []bool{true, false} {
+		for _, route := range OperationRoutes {
+			if route.Method != method || strings.Contains(route.Pattern, "?") != constrained {
+				continue
+			}
+			if params, ok := matchURI(route.Pattern, uri); ok {
+				return route.Operation, params
+			}
+		}
+	}
+	return "", nil
+}
+
+// matchURI matches a request URI against a pattern that may contain {Label} and
+// {Label+} (greedy) segments, and may constrain the query string after a "?".
+// Returns the extracted parameters and true on match, or nil and false
+// otherwise.
+func matchURI(pattern, uri string) (PathParams, bool) {
+	patPath, patQuery, _ := strings.Cut(pattern, "?")
+	uriPath, uriQuery, _ := strings.Cut(uri, "?")
+	if !matchQuery(patQuery, uriQuery) {
+		return nil, false
+	}
+
+	patParts := splitPath(patPath)
+	pathParts := splitPath(uriPath)
+
+	params := PathParams{}
+	pi := 0
+	for i, pat := range patParts {
+		if strings.HasPrefix(pat, "{") && strings.HasSuffix(pat, "+}") {
+			// Greedy label: consumes all remaining path segments.
+			label := pat[1 : len(pat)-2]
+			if pi >= len(pathParts) {
+				return nil, false
+			}
+			params[label] = joinPath(pathParts[pi:])
+			pi = len(pathParts)
+			// Greedy must be the last pattern segment.
+			if i != len(patParts)-1 {
+				return nil, false
+			}
+		} else if strings.HasPrefix(pat, "{") && strings.HasSuffix(pat, "}") {
+			// Single-segment label.
+			label := pat[1 : len(pat)-1]
+			if pi >= len(pathParts) {
+				return nil, false
+			}
+			params[label] = pathParts[pi]
+			pi++
+		} else {
+			// Literal segment.
+			if pi >= len(pathParts) || pathParts[pi] != pat {
+				return nil, false
+			}
+			pi++
+		}
+	}
+	if pi != len(pathParts) {
+		return nil, false
+	}
+	return params, true
+}
+
+// matchQuery reports whether a request's query string satisfies the constraint
+// a route pattern carries after its "?". Each "&"-separated term is either a
+// bare key that must be present ("?WithTags") or a key=value that must be
+// present with that value ("?Operation=Tag"). An empty constraint matches
+// anything, which is every route that has no "?".
+func matchQuery(constraint, query string) bool {
+	if constraint == "" {
+		return true
+	}
+	// ParseQuery returns what it could parse alongside any error, so a
+	// malformed tail cannot hide a valid term earlier in the string.
+	values, _ := url.ParseQuery(query)
+	for _, term := range strings.Split(constraint, "&") {
+		if term == "" {
+			continue
+		}
+		key, want, hasValue := strings.Cut(term, "=")
+		got, present := values[key]
+		if !present {
+			return false
+		}
+		if !hasValue {
+			continue
+		}
+		matched := false
+		for _, v := range got {
+			if v == want {
+				matched = true
+				break
+			}
+		}
+		if !matched {
+			return false
+		}
+	}
+	return true
+}
+
+// splitPath splits a URI path into non-empty segments.
+func splitPath(path string) []string {
+	parts := strings.Split(strings.Trim(path, "/"), "/")
+	out := parts[:0]
+	for _, p := range parts {
+		if p != "" {
+			out = append(out, p)
+		}
+	}
+	return out
+}
+
+// joinPath joins path segments back with "/" separators.
+func joinPath(parts []string) string {
+	return strings.Join(parts, "/")
+}
diff --git a/internal/generated/comprehend/types.go b/internal/generated/comprehend/types.go
new file mode 100644
index 00000000..8b82ad11
--- /dev/null
+++ b/internal/generated/comprehend/types.go
@@ -0,0 +1,1862 @@
+// Code generated by devcloud codegen. DO NOT EDIT.
+// SPDX-License-Identifier: Apache-2.0
+package comprehend
+
+import (
+	"time"
+)
+
+type AugmentedManifestsListItem struct {
+	AnnotationDataS3Uri  string             `json:"annotationDataS3Uri" xml:"AnnotationDataS3Uri"`
+	AttributeNames       AttributeNamesList `json:"attributeNames" xml:"AttributeNames"`
+	DocumentType         string             `json:"documentType" xml:"DocumentType"`
+	S3Uri                string             `json:"s3Uri" xml:"S3Uri"`
+	SourceDocumentsS3Uri string             `json:"sourceDocumentsS3Uri" xml:"SourceDocumentsS3Uri"`
+	Split                string             `json:"split" xml:"Split"`
+}
+
+type BatchDetectDominantLanguageItemResult struct {
+	Index     int32                   `json:"index" xml:"Index"`
+	Languages ListOfDominantLanguages `json:"languages" xml:"Languages"`
+}
+
+type BatchDetectDominantLanguageRequest struct {
+	TextList CustomerInputStringList `json:"textList" xml:"TextList"`
+}
+
+type BatchDetectDominantLanguageResponse struct {
+	ErrorList  BatchItemErrorList                 `json:"errorList" xml:"ErrorList"`
+	ResultList ListOfDetectDominantLanguageResult `json:"resultList" xml:"ResultList"`
+}
+
+type BatchDetectEntitiesItemResult struct {
+	Entities ListOfEntities `json:"entities" xml:"Entities"`
+	Index    int32          `json:"index" xml:"Index"`
+}
+
+type BatchDetectEntitiesRequest struct {
+	LanguageCode string                  `json:"languageCode" xml:"LanguageCode"`
+	TextList     CustomerInputStringList `json:"textList" xml:"TextList"`
+}
+
+type BatchDetectEntitiesResponse struct {
+	ErrorList  BatchItemErrorList         `json:"errorList" xml:"ErrorList"`
+	ResultList ListOfDetectEntitiesResult `json:"resultList" xml:"ResultList"`
+}
+
+type BatchDetectKeyPhrasesItemResult struct {
+	Index      int32            `json:"index" xml:"Index"`
+	KeyPhrases ListOfKeyPhrases `json:"keyPhrases" xml:"KeyPhrases"`
+}
+
+type BatchDetectKeyPhrasesRequest struct {
+	LanguageCode string                  `json:"languageCode" xml:"LanguageCode"`
+	TextList     CustomerInputStringList `json:"textList" xml:"TextList"`
+}
+
+type BatchDetectKeyPhrasesResponse struct {
+	ErrorList  BatchItemErrorList           `json:"errorList" xml:"ErrorList"`
+	ResultList ListOfDetectKeyPhrasesResult `json:"resultList" xml:"ResultList"`
+}
+
+type BatchDetectSentimentItemResult struct {
+	Index          int32           `json:"index" xml:"Index"`
+	Sentiment      string          `json:"sentiment" xml:"Sentiment"`
+	SentimentScore *SentimentScore `json:"sentimentScore" xml:"SentimentScore"`
+}
+
+type BatchDetectSentimentRequest struct {
+	LanguageCode string                  `json:"languageCode" xml:"LanguageCode"`
+	TextList     CustomerInputStringList `json:"textList" xml:"TextList"`
+}
+
+type BatchDetectSentimentResponse struct {
+	ErrorList  BatchItemErrorList          `json:"errorList" xml:"ErrorList"`
+	ResultList ListOfDetectSentimentResult `json:"resultList" xml:"ResultList"`
+}
+
+type BatchDetectSyntaxItemResult struct {
+	Index        int32              `json:"index" xml:"Index"`
+	SyntaxTokens ListOfSyntaxTokens `json:"syntaxTokens" xml:"SyntaxTokens"`
+}
+
+type BatchDetectSyntaxRequest struct {
+	LanguageCode string                  `json:"languageCode" xml:"LanguageCode"`
+	TextList     CustomerInputStringList `json:"textList" xml:"TextList"`
+}
+
+type BatchDetectSyntaxResponse struct {
+	ErrorList  BatchItemErrorList       `json:"errorList" xml:"ErrorList"`
+	ResultList ListOfDetectSyntaxResult `json:"resultList" xml:"ResultList"`
+}
+
+type BatchDetectTargetedSentimentItemResult struct {
+	Entities ListOfTargetedSentimentEntities `json:"entities" xml:"Entities"`
+	Index    int32                           `json:"index" xml:"Index"`
+}
+
+type BatchDetectTargetedSentimentRequest struct {
+	LanguageCode string                  `json:"languageCode" xml:"LanguageCode"`
+	TextList     CustomerInputStringList `json:"textList" xml:"TextList"`
+}
+
+type BatchDetectTargetedSentimentResponse struct {
+	ErrorList  BatchItemErrorList                  `json:"errorList" xml:"ErrorList"`
+	ResultList ListOfDetectTargetedSentimentResult `json:"resultList" xml:"ResultList"`
+}
+
+type BatchItemError struct {
+	ErrorCode    string `json:"errorCode" xml:"ErrorCode"`
+	ErrorMessage string `json:"errorMessage" xml:"ErrorMessage"`
+	Index        int32  `json:"index" xml:"Index"`
+}
+
+type Block struct {
+	BlockType     string              `json:"blockType" xml:"BlockType"`
+	Geometry      *Geometry           `json:"geometry" xml:"Geometry"`
+	Id            string              `json:"id" xml:"Id"`
+	Page          int32               `json:"page" xml:"Page"`
+	Relationships ListOfRelationships `json:"relationships" xml:"Relationships"`
+	Text          string              `json:"text" xml:"Text"`
+}
+
+type BlockReference struct {
+	BeginOffset int32             `json:"beginOffset" xml:"BeginOffset"`
+	BlockId     string            `json:"blockId" xml:"BlockId"`
+	ChildBlocks ListOfChildBlocks `json:"childBlocks" xml:"ChildBlocks"`
+	EndOffset   int32             `json:"endOffset" xml:"EndOffset"`
+}
+
+type BoundingBox struct {
+	Height float32 `json:"height" xml:"Height"`
+	Left   float32 `json:"left" xml:"Left"`
+	Top    float32 `json:"top" xml:"Top"`
+	Width  float32 `json:"width" xml:"Width"`
+}
+
+type ChildBlock struct {
+	BeginOffset  int32  `json:"beginOffset" xml:"BeginOffset"`
+	ChildBlockId string `json:"childBlockId" xml:"ChildBlockId"`
+	EndOffset    int32  `json:"endOffset" xml:"EndOffset"`
+}
+
+type ClassifierEvaluationMetrics struct {
+	Accuracy       float64 `json:"accuracy" xml:"Accuracy"`
+	F1Score        float64 `json:"f1Score" xml:"F1Score"`
+	HammingLoss    float64 `json:"hammingLoss" xml:"HammingLoss"`
+	MicroF1Score   float64 `json:"microF1Score" xml:"MicroF1Score"`
+	MicroPrecision float64 `json:"microPrecision" xml:"MicroPrecision"`
+	MicroRecall    float64 `json:"microRecall" xml:"MicroRecall"`
+	Precision      float64 `json:"precision" xml:"Precision"`
+	Recall         float64 `json:"recall" xml:"Recall"`
+}
+
+type ClassifierMetadata struct {
+	EvaluationMetrics        *ClassifierEvaluationMetrics `json:"evaluationMetrics" xml:"EvaluationMetrics"`
+	NumberOfLabels           int32                        `json:"numberOfLabels" xml:"NumberOfLabels"`
+	NumberOfTestDocuments    int32                        `json:"numberOfTestDocuments" xml:"NumberOfTestDocuments"`
+	NumberOfTrainedDocuments int32                        `json:"numberOfTrainedDocuments" xml:"NumberOfTrainedDocuments"`
+}
+
+type ClassifyDocumentRequest struct {
+	Bytes                []byte                `json:"bytes" xml:"Bytes"`
+	DocumentReaderConfig *DocumentReaderConfig `json:"documentReaderConfig" xml:"DocumentReaderConfig"`
+	EndpointArn          string                `json:"endpointArn" xml:"EndpointArn"`
+	Text                 string                `json:"text" xml:"Text"`
+}
+
+type ClassifyDocumentResponse struct {
+	Classes          ListOfClasses      `json:"classes" xml:"Classes"`
+	DocumentMetadata *DocumentMetadata  `json:"documentMetadata" xml:"DocumentMetadata"`
+	DocumentType     ListOfDocumentType `json:"documentType" xml:"DocumentType"`
+	Errors           ListOfErrors       `json:"errors" xml:"Errors"`
+	Labels           ListOfLabels       `json:"labels" xml:"Labels"`
+	Warnings         ListOfWarnings     `json:"warnings" xml:"Warnings"`
+}
+
+type ContainsPiiEntitiesRequest struct {
+	LanguageCode string `json:"languageCode" xml:"LanguageCode"`
+	Text         string `json:"text" xml:"Text"`
+}
+
+type ContainsPiiEntitiesResponse struct {
+	Labels ListOfEntityLabels `json:"labels" xml:"Labels"`
+}
+
+type CreateDatasetRequest struct {
+	ClientRequestToken string                  `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DatasetName        string                  `json:"datasetName" xml:"DatasetName"`
+	DatasetType        string                  `json:"datasetType" xml:"DatasetType"`
+	Description        string                  `json:"description" xml:"Description"`
+	FlywheelArn        string                  `json:"flywheelArn" xml:"FlywheelArn"`
+	InputDataConfig    *DatasetInputDataConfig `json:"inputDataConfig" xml:"InputDataConfig"`
+	Tags               TagList                 `json:"tags" xml:"Tags"`
+}
+
+type CreateDatasetResponse struct {
+	DatasetArn string `json:"datasetArn" xml:"DatasetArn"`
+}
+
+type CreateDocumentClassifierRequest struct {
+	ClientRequestToken     string                              `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DataAccessRoleArn      string                              `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	DocumentClassifierName string                              `json:"documentClassifierName" xml:"DocumentClassifierName"`
+	InputDataConfig        *DocumentClassifierInputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	LanguageCode           string                              `json:"languageCode" xml:"LanguageCode"`
+	Mode                   string                              `json:"mode" xml:"Mode"`
+	ModelKmsKeyId          string                              `json:"modelKmsKeyId" xml:"ModelKmsKeyId"`
+	ModelPolicy            string                              `json:"modelPolicy" xml:"ModelPolicy"`
+	OutputDataConfig       *DocumentClassifierOutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	Tags                   TagList                             `json:"tags" xml:"Tags"`
+	VersionName            string                              `json:"versionName" xml:"VersionName"`
+	VolumeKmsKeyId         string                              `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig              *VpcConfig                          `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type CreateDocumentClassifierResponse struct {
+	DocumentClassifierArn string `json:"documentClassifierArn" xml:"DocumentClassifierArn"`
+}
+
+type CreateEndpointRequest struct {
+	ClientRequestToken    string  `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DataAccessRoleArn     string  `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	DesiredInferenceUnits int32   `json:"desiredInferenceUnits" xml:"DesiredInferenceUnits"`
+	EndpointName          string  `json:"endpointName" xml:"EndpointName"`
+	FlywheelArn           string  `json:"flywheelArn" xml:"FlywheelArn"`
+	ModelArn              string  `json:"modelArn" xml:"ModelArn"`
+	Tags                  TagList `json:"tags" xml:"Tags"`
+}
+
+type CreateEndpointResponse struct {
+	EndpointArn string `json:"endpointArn" xml:"EndpointArn"`
+	ModelArn    string `json:"modelArn" xml:"ModelArn"`
+}
+
+type CreateEntityRecognizerRequest struct {
+	ClientRequestToken string                           `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DataAccessRoleArn  string                           `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	InputDataConfig    *EntityRecognizerInputDataConfig `json:"inputDataConfig" xml:"InputDataConfig"`
+	LanguageCode       string                           `json:"languageCode" xml:"LanguageCode"`
+	ModelKmsKeyId      string                           `json:"modelKmsKeyId" xml:"ModelKmsKeyId"`
+	ModelPolicy        string                           `json:"modelPolicy" xml:"ModelPolicy"`
+	RecognizerName     string                           `json:"recognizerName" xml:"RecognizerName"`
+	Tags               TagList                          `json:"tags" xml:"Tags"`
+	VersionName        string                           `json:"versionName" xml:"VersionName"`
+	VolumeKmsKeyId     string                           `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig          *VpcConfig                       `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type CreateEntityRecognizerResponse struct {
+	EntityRecognizerArn string `json:"entityRecognizerArn" xml:"EntityRecognizerArn"`
+}
+
+type CreateFlywheelRequest struct {
+	ActiveModelArn     string              `json:"activeModelArn" xml:"ActiveModelArn"`
+	ClientRequestToken string              `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DataAccessRoleArn  string              `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	DataLakeS3Uri      string              `json:"dataLakeS3Uri" xml:"DataLakeS3Uri"`
+	DataSecurityConfig *DataSecurityConfig `json:"dataSecurityConfig" xml:"DataSecurityConfig"`
+	FlywheelName       string              `json:"flywheelName" xml:"FlywheelName"`
+	ModelType          string              `json:"modelType" xml:"ModelType"`
+	Tags               TagList             `json:"tags" xml:"Tags"`
+	TaskConfig         *TaskConfig         `json:"taskConfig" xml:"TaskConfig"`
+}
+
+type CreateFlywheelResponse struct {
+	ActiveModelArn string `json:"activeModelArn" xml:"ActiveModelArn"`
+	FlywheelArn    string `json:"flywheelArn" xml:"FlywheelArn"`
+}
+
+type DataSecurityConfig struct {
+	DataLakeKmsKeyId string     `json:"dataLakeKmsKeyId" xml:"DataLakeKmsKeyId"`
+	ModelKmsKeyId    string     `json:"modelKmsKeyId" xml:"ModelKmsKeyId"`
+	VolumeKmsKeyId   string     `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig        *VpcConfig `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type DatasetAugmentedManifestsListItem struct {
+	AnnotationDataS3Uri  string             `json:"annotationDataS3Uri" xml:"AnnotationDataS3Uri"`
+	AttributeNames       AttributeNamesList `json:"attributeNames" xml:"AttributeNames"`
+	DocumentType         string             `json:"documentType" xml:"DocumentType"`
+	S3Uri                string             `json:"s3Uri" xml:"S3Uri"`
+	SourceDocumentsS3Uri string             `json:"sourceDocumentsS3Uri" xml:"SourceDocumentsS3Uri"`
+}
+
+type DatasetDocumentClassifierInputDataConfig struct {
+	LabelDelimiter string `json:"labelDelimiter" xml:"LabelDelimiter"`
+	S3Uri          string `json:"s3Uri" xml:"S3Uri"`
+}
+
+type DatasetEntityRecognizerAnnotations struct {
+	S3Uri string `json:"s3Uri" xml:"S3Uri"`
+}
+
+type DatasetEntityRecognizerDocuments struct {
+	InputFormat string `json:"inputFormat" xml:"InputFormat"`
+	S3Uri       string `json:"s3Uri" xml:"S3Uri"`
+}
+
+type DatasetEntityRecognizerEntityList struct {
+	S3Uri string `json:"s3Uri" xml:"S3Uri"`
+}
+
+type DatasetEntityRecognizerInputDataConfig struct {
+	Annotations *DatasetEntityRecognizerAnnotations `json:"annotations" xml:"Annotations"`
+	Documents   *DatasetEntityRecognizerDocuments   `json:"documents" xml:"Documents"`
+	EntityList  *DatasetEntityRecognizerEntityList  `json:"entityList" xml:"EntityList"`
+}
+
+type DatasetFilter struct {
+	CreationTimeAfter  time.Time `json:"creationTimeAfter" xml:"CreationTimeAfter"`
+	CreationTimeBefore time.Time `json:"creationTimeBefore" xml:"CreationTimeBefore"`
+	DatasetType        string    `json:"datasetType" xml:"DatasetType"`
+	Status             string    `json:"status" xml:"Status"`
+}
+
+type DatasetInputDataConfig struct {
+	AugmentedManifests                DatasetAugmentedManifestsList             `json:"augmentedManifests" xml:"AugmentedManifests"`
+	DataFormat                        string                                    `json:"dataFormat" xml:"DataFormat"`
+	DocumentClassifierInputDataConfig *DatasetDocumentClassifierInputDataConfig `json:"documentClassifierInputDataConfig" xml:"DocumentClassifierInputDataConfig"`
+	EntityRecognizerInputDataConfig   *DatasetEntityRecognizerInputDataConfig   `json:"entityRecognizerInputDataConfig" xml:"EntityRecognizerInputDataConfig"`
+}
+
+type DatasetProperties struct {
+	CreationTime      time.Time `json:"creationTime" xml:"CreationTime"`
+	DatasetArn        string    `json:"datasetArn" xml:"DatasetArn"`
+	DatasetName       string    `json:"datasetName" xml:"DatasetName"`
+	DatasetS3Uri      string    `json:"datasetS3Uri" xml:"DatasetS3Uri"`
+	DatasetType       string    `json:"datasetType" xml:"DatasetType"`
+	Description       string    `json:"description" xml:"Description"`
+	EndTime           time.Time `json:"endTime" xml:"EndTime"`
+	Message           string    `json:"message" xml:"Message"`
+	NumberOfDocuments int64     `json:"numberOfDocuments" xml:"NumberOfDocuments"`
+	Status            string    `json:"status" xml:"Status"`
+}
+
+type DeleteDocumentClassifierRequest struct {
+	DocumentClassifierArn string `json:"documentClassifierArn" xml:"DocumentClassifierArn"`
+}
+
+type DeleteDocumentClassifierResponse struct {
+}
+
+type DeleteEndpointRequest struct {
+	EndpointArn string `json:"endpointArn" xml:"EndpointArn"`
+}
+
+type DeleteEndpointResponse struct {
+}
+
+type DeleteEntityRecognizerRequest struct {
+	EntityRecognizerArn string `json:"entityRecognizerArn" xml:"EntityRecognizerArn"`
+}
+
+type DeleteEntityRecognizerResponse struct {
+}
+
+type DeleteFlywheelRequest struct {
+	FlywheelArn string `json:"flywheelArn" xml:"FlywheelArn"`
+}
+
+type DeleteFlywheelResponse struct {
+}
+
+type DeleteResourcePolicyRequest struct {
+	PolicyRevisionId string `json:"policyRevisionId" xml:"PolicyRevisionId"`
+	ResourceArn      string `json:"resourceArn" xml:"ResourceArn"`
+}
+
+type DeleteResourcePolicyResponse struct {
+}
+
+type DescribeDatasetRequest struct {
+	DatasetArn string `json:"datasetArn" xml:"DatasetArn"`
+}
+
+type DescribeDatasetResponse struct {
+	DatasetProperties *DatasetProperties `json:"datasetProperties" xml:"DatasetProperties"`
+}
+
+type DescribeDocumentClassificationJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type DescribeDocumentClassificationJobResponse struct {
+	DocumentClassificationJobProperties *DocumentClassificationJobProperties `json:"documentClassificationJobProperties" xml:"DocumentClassificationJobProperties"`
+}
+
+type DescribeDocumentClassifierRequest struct {
+	DocumentClassifierArn string `json:"documentClassifierArn" xml:"DocumentClassifierArn"`
+}
+
+type DescribeDocumentClassifierResponse struct {
+	DocumentClassifierProperties *DocumentClassifierProperties `json:"documentClassifierProperties" xml:"DocumentClassifierProperties"`
+}
+
+type DescribeDominantLanguageDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type DescribeDominantLanguageDetectionJobResponse struct {
+	DominantLanguageDetectionJobProperties *DominantLanguageDetectionJobProperties `json:"dominantLanguageDetectionJobProperties" xml:"DominantLanguageDetectionJobProperties"`
+}
+
+type DescribeEndpointRequest struct {
+	EndpointArn string `json:"endpointArn" xml:"EndpointArn"`
+}
+
+type DescribeEndpointResponse struct {
+	EndpointProperties *EndpointProperties `json:"endpointProperties" xml:"EndpointProperties"`
+}
+
+type DescribeEntitiesDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type DescribeEntitiesDetectionJobResponse struct {
+	EntitiesDetectionJobProperties *EntitiesDetectionJobProperties `json:"entitiesDetectionJobProperties" xml:"EntitiesDetectionJobProperties"`
+}
+
+type DescribeEntityRecognizerRequest struct {
+	EntityRecognizerArn string `json:"entityRecognizerArn" xml:"EntityRecognizerArn"`
+}
+
+type DescribeEntityRecognizerResponse struct {
+	EntityRecognizerProperties *EntityRecognizerProperties `json:"entityRecognizerProperties" xml:"EntityRecognizerProperties"`
+}
+
+type DescribeEventsDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type DescribeEventsDetectionJobResponse struct {
+	EventsDetectionJobProperties *EventsDetectionJobProperties `json:"eventsDetectionJobProperties" xml:"EventsDetectionJobProperties"`
+}
+
+type DescribeFlywheelIterationRequest struct {
+	FlywheelArn         string `json:"flywheelArn" xml:"FlywheelArn"`
+	FlywheelIterationId string `json:"flywheelIterationId" xml:"FlywheelIterationId"`
+}
+
+type DescribeFlywheelIterationResponse struct {
+	FlywheelIterationProperties *FlywheelIterationProperties `json:"flywheelIterationProperties" xml:"FlywheelIterationProperties"`
+}
+
+type DescribeFlywheelRequest struct {
+	FlywheelArn string `json:"flywheelArn" xml:"FlywheelArn"`
+}
+
+type DescribeFlywheelResponse struct {
+	FlywheelProperties *FlywheelProperties `json:"flywheelProperties" xml:"FlywheelProperties"`
+}
+
+type DescribeKeyPhrasesDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type DescribeKeyPhrasesDetectionJobResponse struct {
+	KeyPhrasesDetectionJobProperties *KeyPhrasesDetectionJobProperties `json:"keyPhrasesDetectionJobProperties" xml:"KeyPhrasesDetectionJobProperties"`
+}
+
+type DescribePiiEntitiesDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type DescribePiiEntitiesDetectionJobResponse struct {
+	PiiEntitiesDetectionJobProperties *PiiEntitiesDetectionJobProperties `json:"piiEntitiesDetectionJobProperties" xml:"PiiEntitiesDetectionJobProperties"`
+}
+
+type DescribeResourcePolicyRequest struct {
+	ResourceArn string `json:"resourceArn" xml:"ResourceArn"`
+}
+
+type DescribeResourcePolicyResponse struct {
+	CreationTime     time.Time `json:"creationTime" xml:"CreationTime"`
+	LastModifiedTime time.Time `json:"lastModifiedTime" xml:"LastModifiedTime"`
+	PolicyRevisionId string    `json:"policyRevisionId" xml:"PolicyRevisionId"`
+	ResourcePolicy   string    `json:"resourcePolicy" xml:"ResourcePolicy"`
+}
+
+type DescribeSentimentDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type DescribeSentimentDetectionJobResponse struct {
+	SentimentDetectionJobProperties *SentimentDetectionJobProperties `json:"sentimentDetectionJobProperties" xml:"SentimentDetectionJobProperties"`
+}
+
+type DescribeTargetedSentimentDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type DescribeTargetedSentimentDetectionJobResponse struct {
+	TargetedSentimentDetectionJobProperties *TargetedSentimentDetectionJobProperties `json:"targetedSentimentDetectionJobProperties" xml:"TargetedSentimentDetectionJobProperties"`
+}
+
+type DescribeTopicsDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type DescribeTopicsDetectionJobResponse struct {
+	TopicsDetectionJobProperties *TopicsDetectionJobProperties `json:"topicsDetectionJobProperties" xml:"TopicsDetectionJobProperties"`
+}
+
+type DetectDominantLanguageRequest struct {
+	Text string `json:"text" xml:"Text"`
+}
+
+type DetectDominantLanguageResponse struct {
+	Languages ListOfDominantLanguages `json:"languages" xml:"Languages"`
+}
+
+type DetectEntitiesRequest struct {
+	Bytes                []byte                `json:"bytes" xml:"Bytes"`
+	DocumentReaderConfig *DocumentReaderConfig `json:"documentReaderConfig" xml:"DocumentReaderConfig"`
+	EndpointArn          string                `json:"endpointArn" xml:"EndpointArn"`
+	LanguageCode         string                `json:"languageCode" xml:"LanguageCode"`
+	Text                 string                `json:"text" xml:"Text"`
+}
+
+type DetectEntitiesResponse struct {
+	Blocks           ListOfBlocks       `json:"blocks" xml:"Blocks"`
+	DocumentMetadata *DocumentMetadata  `json:"documentMetadata" xml:"DocumentMetadata"`
+	DocumentType     ListOfDocumentType `json:"documentType" xml:"DocumentType"`
+	Entities         ListOfEntities     `json:"entities" xml:"Entities"`
+	Errors           ListOfErrors       `json:"errors" xml:"Errors"`
+}
+
+type DetectKeyPhrasesRequest struct {
+	LanguageCode string `json:"languageCode" xml:"LanguageCode"`
+	Text         string `json:"text" xml:"Text"`
+}
+
+type DetectKeyPhrasesResponse struct {
+	KeyPhrases ListOfKeyPhrases `json:"keyPhrases" xml:"KeyPhrases"`
+}
+
+type DetectPiiEntitiesRequest struct {
+	LanguageCode string `json:"languageCode" xml:"LanguageCode"`
+	Text         string `json:"text" xml:"Text"`
+}
+
+type DetectPiiEntitiesResponse struct {
+	Entities ListOfPiiEntities `json:"entities" xml:"Entities"`
+}
+
+type DetectSentimentRequest struct {
+	LanguageCode string `json:"languageCode" xml:"LanguageCode"`
+	Text         string `json:"text" xml:"Text"`
+}
+
+type DetectSentimentResponse struct {
+	Sentiment      string          `json:"sentiment" xml:"Sentiment"`
+	SentimentScore *SentimentScore `json:"sentimentScore" xml:"SentimentScore"`
+}
+
+type DetectSyntaxRequest struct {
+	LanguageCode string `json:"languageCode" xml:"LanguageCode"`
+	Text         string `json:"text" xml:"Text"`
+}
+
+type DetectSyntaxResponse struct {
+	SyntaxTokens ListOfSyntaxTokens `json:"syntaxTokens" xml:"SyntaxTokens"`
+}
+
+type DetectTargetedSentimentRequest struct {
+	LanguageCode string `json:"languageCode" xml:"LanguageCode"`
+	Text         string `json:"text" xml:"Text"`
+}
+
+type DetectTargetedSentimentResponse struct {
+	Entities ListOfTargetedSentimentEntities `json:"entities" xml:"Entities"`
+}
+
+type DetectToxicContentRequest struct {
+	LanguageCode string             `json:"languageCode" xml:"LanguageCode"`
+	TextSegments ListOfTextSegments `json:"textSegments" xml:"TextSegments"`
+}
+
+type DetectToxicContentResponse struct {
+	ResultList ListOfToxicLabels `json:"resultList" xml:"ResultList"`
+}
+
+type DocumentClass struct {
+	Name  string  `json:"name" xml:"Name"`
+	Page  int32   `json:"page" xml:"Page"`
+	Score float32 `json:"score" xml:"Score"`
+}
+
+type DocumentClassificationConfig struct {
+	Labels LabelsList `json:"labels" xml:"Labels"`
+	Mode   string     `json:"mode" xml:"Mode"`
+}
+
+type DocumentClassificationJobFilter struct {
+	JobName          string    `json:"jobName" xml:"JobName"`
+	JobStatus        string    `json:"jobStatus" xml:"JobStatus"`
+	SubmitTimeAfter  time.Time `json:"submitTimeAfter" xml:"SubmitTimeAfter"`
+	SubmitTimeBefore time.Time `json:"submitTimeBefore" xml:"SubmitTimeBefore"`
+}
+
+type DocumentClassificationJobProperties struct {
+	DataAccessRoleArn     string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	DocumentClassifierArn string            `json:"documentClassifierArn" xml:"DocumentClassifierArn"`
+	EndTime               time.Time         `json:"endTime" xml:"EndTime"`
+	FlywheelArn           string            `json:"flywheelArn" xml:"FlywheelArn"`
+	InputDataConfig       *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobArn                string            `json:"jobArn" xml:"JobArn"`
+	JobId                 string            `json:"jobId" xml:"JobId"`
+	JobName               string            `json:"jobName" xml:"JobName"`
+	JobStatus             string            `json:"jobStatus" xml:"JobStatus"`
+	Message               string            `json:"message" xml:"Message"`
+	OutputDataConfig      *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	SubmitTime            time.Time         `json:"submitTime" xml:"SubmitTime"`
+	VolumeKmsKeyId        string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig             *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type DocumentClassifierDocuments struct {
+	S3Uri     string `json:"s3Uri" xml:"S3Uri"`
+	TestS3Uri string `json:"testS3Uri" xml:"TestS3Uri"`
+}
+
+type DocumentClassifierFilter struct {
+	DocumentClassifierName string    `json:"documentClassifierName" xml:"DocumentClassifierName"`
+	Status                 string    `json:"status" xml:"Status"`
+	SubmitTimeAfter        time.Time `json:"submitTimeAfter" xml:"SubmitTimeAfter"`
+	SubmitTimeBefore       time.Time `json:"submitTimeBefore" xml:"SubmitTimeBefore"`
+}
+
+type DocumentClassifierInputDataConfig struct {
+	AugmentedManifests   DocumentClassifierAugmentedManifestsList `json:"augmentedManifests" xml:"AugmentedManifests"`
+	DataFormat           string                                   `json:"dataFormat" xml:"DataFormat"`
+	DocumentReaderConfig *DocumentReaderConfig                    `json:"documentReaderConfig" xml:"DocumentReaderConfig"`
+	DocumentType         string                                   `json:"documentType" xml:"DocumentType"`
+	Documents            *DocumentClassifierDocuments             `json:"documents" xml:"Documents"`
+	LabelDelimiter       string                                   `json:"labelDelimiter" xml:"LabelDelimiter"`
+	S3Uri                string                                   `json:"s3Uri" xml:"S3Uri"`
+	TestS3Uri            string                                   `json:"testS3Uri" xml:"TestS3Uri"`
+}
+
+type DocumentClassifierOutputDataConfig struct {
+	FlywheelStatsS3Prefix string `json:"flywheelStatsS3Prefix" xml:"FlywheelStatsS3Prefix"`
+	KmsKeyId              string `json:"kmsKeyId" xml:"KmsKeyId"`
+	S3Uri                 string `json:"s3Uri" xml:"S3Uri"`
+}
+
+type DocumentClassifierProperties struct {
+	ClassifierMetadata    *ClassifierMetadata                 `json:"classifierMetadata" xml:"ClassifierMetadata"`
+	DataAccessRoleArn     string                              `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	DocumentClassifierArn string                              `json:"documentClassifierArn" xml:"DocumentClassifierArn"`
+	EndTime               time.Time                           `json:"endTime" xml:"EndTime"`
+	FlywheelArn           string                              `json:"flywheelArn" xml:"FlywheelArn"`
+	InputDataConfig       *DocumentClassifierInputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	LanguageCode          string                              `json:"languageCode" xml:"LanguageCode"`
+	Message               string                              `json:"message" xml:"Message"`
+	Mode                  string                              `json:"mode" xml:"Mode"`
+	ModelKmsKeyId         string                              `json:"modelKmsKeyId" xml:"ModelKmsKeyId"`
+	OutputDataConfig      *DocumentClassifierOutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	SourceModelArn        string                              `json:"sourceModelArn" xml:"SourceModelArn"`
+	Status                string                              `json:"status" xml:"Status"`
+	SubmitTime            time.Time                           `json:"submitTime" xml:"SubmitTime"`
+	TrainingEndTime       time.Time                           `json:"trainingEndTime" xml:"TrainingEndTime"`
+	TrainingStartTime     time.Time                           `json:"trainingStartTime" xml:"TrainingStartTime"`
+	VersionName           string                              `json:"versionName" xml:"VersionName"`
+	VolumeKmsKeyId        string                              `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig             *VpcConfig                          `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type DocumentClassifierSummary struct {
+	DocumentClassifierName string    `json:"documentClassifierName" xml:"DocumentClassifierName"`
+	LatestVersionCreatedAt time.Time `json:"latestVersionCreatedAt" xml:"LatestVersionCreatedAt"`
+	LatestVersionName      string    `json:"latestVersionName" xml:"LatestVersionName"`
+	LatestVersionStatus    string    `json:"latestVersionStatus" xml:"LatestVersionStatus"`
+	NumberOfVersions       int32     `json:"numberOfVersions" xml:"NumberOfVersions"`
+}
+
+type DocumentLabel struct {
+	Name  string  `json:"name" xml:"Name"`
+	Page  int32   `json:"page" xml:"Page"`
+	Score float32 `json:"score" xml:"Score"`
+}
+
+type DocumentMetadata struct {
+	ExtractedCharacters ListOfExtractedCharacters `json:"extractedCharacters" xml:"ExtractedCharacters"`
+	Pages               int32                     `json:"pages" xml:"Pages"`
+}
+
+type DocumentReaderConfig struct {
+	DocumentReadAction string                         `json:"documentReadAction" xml:"DocumentReadAction"`
+	DocumentReadMode   string                         `json:"documentReadMode" xml:"DocumentReadMode"`
+	FeatureTypes       ListOfDocumentReadFeatureTypes `json:"featureTypes" xml:"FeatureTypes"`
+}
+
+type DocumentTypeListItem struct {
+	Page int32  `json:"page" xml:"Page"`
+	Type string `json:"type" xml:"Type"`
+}
+
+type DominantLanguage struct {
+	LanguageCode string  `json:"languageCode" xml:"LanguageCode"`
+	Score        float32 `json:"score" xml:"Score"`
+}
+
+type DominantLanguageDetectionJobFilter struct {
+	JobName          string    `json:"jobName" xml:"JobName"`
+	JobStatus        string    `json:"jobStatus" xml:"JobStatus"`
+	SubmitTimeAfter  time.Time `json:"submitTimeAfter" xml:"SubmitTimeAfter"`
+	SubmitTimeBefore time.Time `json:"submitTimeBefore" xml:"SubmitTimeBefore"`
+}
+
+type DominantLanguageDetectionJobProperties struct {
+	DataAccessRoleArn string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	EndTime           time.Time         `json:"endTime" xml:"EndTime"`
+	InputDataConfig   *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobArn            string            `json:"jobArn" xml:"JobArn"`
+	JobId             string            `json:"jobId" xml:"JobId"`
+	JobName           string            `json:"jobName" xml:"JobName"`
+	JobStatus         string            `json:"jobStatus" xml:"JobStatus"`
+	Message           string            `json:"message" xml:"Message"`
+	OutputDataConfig  *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	SubmitTime        time.Time         `json:"submitTime" xml:"SubmitTime"`
+	VolumeKmsKeyId    string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig         *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type EndpointFilter struct {
+	CreationTimeAfter  time.Time `json:"creationTimeAfter" xml:"CreationTimeAfter"`
+	CreationTimeBefore time.Time `json:"creationTimeBefore" xml:"CreationTimeBefore"`
+	ModelArn           string    `json:"modelArn" xml:"ModelArn"`
+	Status             string    `json:"status" xml:"Status"`
+}
+
+type EndpointProperties struct {
+	CreationTime             time.Time `json:"creationTime" xml:"CreationTime"`
+	CurrentInferenceUnits    int32     `json:"currentInferenceUnits" xml:"CurrentInferenceUnits"`
+	DataAccessRoleArn        string    `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	DesiredDataAccessRoleArn string    `json:"desiredDataAccessRoleArn" xml:"DesiredDataAccessRoleArn"`
+	DesiredInferenceUnits    int32     `json:"desiredInferenceUnits" xml:"DesiredInferenceUnits"`
+	DesiredModelArn          string    `json:"desiredModelArn" xml:"DesiredModelArn"`
+	EndpointArn              string    `json:"endpointArn" xml:"EndpointArn"`
+	FlywheelArn              string    `json:"flywheelArn" xml:"FlywheelArn"`
+	LastModifiedTime         time.Time `json:"lastModifiedTime" xml:"LastModifiedTime"`
+	Message                  string    `json:"message" xml:"Message"`
+	ModelArn                 string    `json:"modelArn" xml:"ModelArn"`
+	Status                   string    `json:"status" xml:"Status"`
+}
+
+type EntitiesDetectionJobFilter struct {
+	JobName          string    `json:"jobName" xml:"JobName"`
+	JobStatus        string    `json:"jobStatus" xml:"JobStatus"`
+	SubmitTimeAfter  time.Time `json:"submitTimeAfter" xml:"SubmitTimeAfter"`
+	SubmitTimeBefore time.Time `json:"submitTimeBefore" xml:"SubmitTimeBefore"`
+}
+
+type EntitiesDetectionJobProperties struct {
+	DataAccessRoleArn   string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	EndTime             time.Time         `json:"endTime" xml:"EndTime"`
+	EntityRecognizerArn string            `json:"entityRecognizerArn" xml:"EntityRecognizerArn"`
+	FlywheelArn         string            `json:"flywheelArn" xml:"FlywheelArn"`
+	InputDataConfig     *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobArn              string            `json:"jobArn" xml:"JobArn"`
+	JobId               string            `json:"jobId" xml:"JobId"`
+	JobName             string            `json:"jobName" xml:"JobName"`
+	JobStatus           string            `json:"jobStatus" xml:"JobStatus"`
+	LanguageCode        string            `json:"languageCode" xml:"LanguageCode"`
+	Message             string            `json:"message" xml:"Message"`
+	OutputDataConfig    *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	SubmitTime          time.Time         `json:"submitTime" xml:"SubmitTime"`
+	VolumeKmsKeyId      string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig           *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type Entity struct {
+	BeginOffset     int32                 `json:"beginOffset" xml:"BeginOffset"`
+	BlockReferences ListOfBlockReferences `json:"blockReferences" xml:"BlockReferences"`
+	EndOffset       int32                 `json:"endOffset" xml:"EndOffset"`
+	Score           float32               `json:"score" xml:"Score"`
+	Text            string                `json:"text" xml:"Text"`
+	Type            string                `json:"type" xml:"Type"`
+}
+
+type EntityLabel struct {
+	Name  string  `json:"name" xml:"Name"`
+	Score float32 `json:"score" xml:"Score"`
+}
+
+type EntityRecognitionConfig struct {
+	EntityTypes EntityTypesList `json:"entityTypes" xml:"EntityTypes"`
+}
+
+type EntityRecognizerAnnotations struct {
+	S3Uri     string `json:"s3Uri" xml:"S3Uri"`
+	TestS3Uri string `json:"testS3Uri" xml:"TestS3Uri"`
+}
+
+type EntityRecognizerDocuments struct {
+	InputFormat string `json:"inputFormat" xml:"InputFormat"`
+	S3Uri       string `json:"s3Uri" xml:"S3Uri"`
+	TestS3Uri   string `json:"testS3Uri" xml:"TestS3Uri"`
+}
+
+type EntityRecognizerEntityList struct {
+	S3Uri string `json:"s3Uri" xml:"S3Uri"`
+}
+
+type EntityRecognizerEvaluationMetrics struct {
+	F1Score   float64 `json:"f1Score" xml:"F1Score"`
+	Precision float64 `json:"precision" xml:"Precision"`
+	Recall    float64 `json:"recall" xml:"Recall"`
+}
+
+type EntityRecognizerFilter struct {
+	RecognizerName   string    `json:"recognizerName" xml:"RecognizerName"`
+	Status           string    `json:"status" xml:"Status"`
+	SubmitTimeAfter  time.Time `json:"submitTimeAfter" xml:"SubmitTimeAfter"`
+	SubmitTimeBefore time.Time `json:"submitTimeBefore" xml:"SubmitTimeBefore"`
+}
+
+type EntityRecognizerInputDataConfig struct {
+	Annotations        *EntityRecognizerAnnotations           `json:"annotations" xml:"Annotations"`
+	AugmentedManifests EntityRecognizerAugmentedManifestsList `json:"augmentedManifests" xml:"AugmentedManifests"`
+	DataFormat         string                                 `json:"dataFormat" xml:"DataFormat"`
+	Documents          *EntityRecognizerDocuments             `json:"documents" xml:"Documents"`
+	EntityList         *EntityRecognizerEntityList            `json:"entityList" xml:"EntityList"`
+	EntityTypes        EntityTypesList                        `json:"entityTypes" xml:"EntityTypes"`
+}
+
+type EntityRecognizerMetadata struct {
+	EntityTypes              EntityRecognizerMetadataEntityTypesList `json:"entityTypes" xml:"EntityTypes"`
+	EvaluationMetrics        *EntityRecognizerEvaluationMetrics      `json:"evaluationMetrics" xml:"EvaluationMetrics"`
+	NumberOfTestDocuments    int32                                   `json:"numberOfTestDocuments" xml:"NumberOfTestDocuments"`
+	NumberOfTrainedDocuments int32                                   `json:"numberOfTrainedDocuments" xml:"NumberOfTrainedDocuments"`
+}
+
+type EntityRecognizerMetadataEntityTypesListItem struct {
+	EvaluationMetrics     *EntityTypesEvaluationMetrics `json:"evaluationMetrics" xml:"EvaluationMetrics"`
+	NumberOfTrainMentions int32                         `json:"numberOfTrainMentions" xml:"NumberOfTrainMentions"`
+	Type                  string                        `json:"type" xml:"Type"`
+}
+
+type EntityRecognizerOutputDataConfig struct {
+	FlywheelStatsS3Prefix string `json:"flywheelStatsS3Prefix" xml:"FlywheelStatsS3Prefix"`
+}
+
+type EntityRecognizerProperties struct {
+	DataAccessRoleArn   string                            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	EndTime             time.Time                         `json:"endTime" xml:"EndTime"`
+	EntityRecognizerArn string                            `json:"entityRecognizerArn" xml:"EntityRecognizerArn"`
+	FlywheelArn         string                            `json:"flywheelArn" xml:"FlywheelArn"`
+	InputDataConfig     *EntityRecognizerInputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	LanguageCode        string                            `json:"languageCode" xml:"LanguageCode"`
+	Message             string                            `json:"message" xml:"Message"`
+	ModelKmsKeyId       string                            `json:"modelKmsKeyId" xml:"ModelKmsKeyId"`
+	OutputDataConfig    *EntityRecognizerOutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	RecognizerMetadata  *EntityRecognizerMetadata         `json:"recognizerMetadata" xml:"RecognizerMetadata"`
+	SourceModelArn      string                            `json:"sourceModelArn" xml:"SourceModelArn"`
+	Status              string                            `json:"status" xml:"Status"`
+	SubmitTime          time.Time                         `json:"submitTime" xml:"SubmitTime"`
+	TrainingEndTime     time.Time                         `json:"trainingEndTime" xml:"TrainingEndTime"`
+	TrainingStartTime   time.Time                         `json:"trainingStartTime" xml:"TrainingStartTime"`
+	VersionName         string                            `json:"versionName" xml:"VersionName"`
+	VolumeKmsKeyId      string                            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig           *VpcConfig                        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type EntityRecognizerSummary struct {
+	LatestVersionCreatedAt time.Time `json:"latestVersionCreatedAt" xml:"LatestVersionCreatedAt"`
+	LatestVersionName      string    `json:"latestVersionName" xml:"LatestVersionName"`
+	LatestVersionStatus    string    `json:"latestVersionStatus" xml:"LatestVersionStatus"`
+	NumberOfVersions       int32     `json:"numberOfVersions" xml:"NumberOfVersions"`
+	RecognizerName         string    `json:"recognizerName" xml:"RecognizerName"`
+}
+
+type EntityTypesEvaluationMetrics struct {
+	F1Score   float64 `json:"f1Score" xml:"F1Score"`
+	Precision float64 `json:"precision" xml:"Precision"`
+	Recall    float64 `json:"recall" xml:"Recall"`
+}
+
+type EntityTypesListItem struct {
+	Type string `json:"type" xml:"Type"`
+}
+
+type ErrorsListItem struct {
+	ErrorCode    string `json:"errorCode" xml:"ErrorCode"`
+	ErrorMessage string `json:"errorMessage" xml:"ErrorMessage"`
+	Page         int32  `json:"page" xml:"Page"`
+}
+
+type EventsDetectionJobFilter struct {
+	JobName          string    `json:"jobName" xml:"JobName"`
+	JobStatus        string    `json:"jobStatus" xml:"JobStatus"`
+	SubmitTimeAfter  time.Time `json:"submitTimeAfter" xml:"SubmitTimeAfter"`
+	SubmitTimeBefore time.Time `json:"submitTimeBefore" xml:"SubmitTimeBefore"`
+}
+
+type EventsDetectionJobProperties struct {
+	DataAccessRoleArn string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	EndTime           time.Time         `json:"endTime" xml:"EndTime"`
+	InputDataConfig   *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobArn            string            `json:"jobArn" xml:"JobArn"`
+	JobId             string            `json:"jobId" xml:"JobId"`
+	JobName           string            `json:"jobName" xml:"JobName"`
+	JobStatus         string            `json:"jobStatus" xml:"JobStatus"`
+	LanguageCode      string            `json:"languageCode" xml:"LanguageCode"`
+	Message           string            `json:"message" xml:"Message"`
+	OutputDataConfig  *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	SubmitTime        time.Time         `json:"submitTime" xml:"SubmitTime"`
+	TargetEventTypes  TargetEventTypes  `json:"targetEventTypes" xml:"TargetEventTypes"`
+}
+
+type ExtractedCharactersListItem struct {
+	Count int32 `json:"count" xml:"Count"`
+	Page  int32 `json:"page" xml:"Page"`
+}
+
+type FlywheelFilter struct {
+	CreationTimeAfter  time.Time `json:"creationTimeAfter" xml:"CreationTimeAfter"`
+	CreationTimeBefore time.Time `json:"creationTimeBefore" xml:"CreationTimeBefore"`
+	Status             string    `json:"status" xml:"Status"`
+}
+
+type FlywheelIterationFilter struct {
+	CreationTimeAfter  time.Time `json:"creationTimeAfter" xml:"CreationTimeAfter"`
+	CreationTimeBefore time.Time `json:"creationTimeBefore" xml:"CreationTimeBefore"`
+}
+
+type FlywheelIterationProperties struct {
+	CreationTime               time.Time                       `json:"creationTime" xml:"CreationTime"`
+	EndTime                    time.Time                       `json:"endTime" xml:"EndTime"`
+	EvaluatedModelArn          string                          `json:"evaluatedModelArn" xml:"EvaluatedModelArn"`
+	EvaluatedModelMetrics      *FlywheelModelEvaluationMetrics `json:"evaluatedModelMetrics" xml:"EvaluatedModelMetrics"`
+	EvaluationManifestS3Prefix string                          `json:"evaluationManifestS3Prefix" xml:"EvaluationManifestS3Prefix"`
+	FlywheelArn                string                          `json:"flywheelArn" xml:"FlywheelArn"`
+	FlywheelIterationId        string                          `json:"flywheelIterationId" xml:"FlywheelIterationId"`
+	Message                    string                          `json:"message" xml:"Message"`
+	Status                     string                          `json:"status" xml:"Status"`
+	TrainedModelArn            string                          `json:"trainedModelArn" xml:"TrainedModelArn"`
+	TrainedModelMetrics        *FlywheelModelEvaluationMetrics `json:"trainedModelMetrics" xml:"TrainedModelMetrics"`
+}
+
+type FlywheelModelEvaluationMetrics struct {
+	AverageAccuracy  float64 `json:"averageAccuracy" xml:"AverageAccuracy"`
+	AverageF1Score   float64 `json:"averageF1Score" xml:"AverageF1Score"`
+	AveragePrecision float64 `json:"averagePrecision" xml:"AveragePrecision"`
+	AverageRecall    float64 `json:"averageRecall" xml:"AverageRecall"`
+}
+
+type FlywheelProperties struct {
+	ActiveModelArn          string              `json:"activeModelArn" xml:"ActiveModelArn"`
+	CreationTime            time.Time           `json:"creationTime" xml:"CreationTime"`
+	DataAccessRoleArn       string              `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	DataLakeS3Uri           string              `json:"dataLakeS3Uri" xml:"DataLakeS3Uri"`
+	DataSecurityConfig      *DataSecurityConfig `json:"dataSecurityConfig" xml:"DataSecurityConfig"`
+	FlywheelArn             string              `json:"flywheelArn" xml:"FlywheelArn"`
+	LastModifiedTime        time.Time           `json:"lastModifiedTime" xml:"LastModifiedTime"`
+	LatestFlywheelIteration string              `json:"latestFlywheelIteration" xml:"LatestFlywheelIteration"`
+	Message                 string              `json:"message" xml:"Message"`
+	ModelType               string              `json:"modelType" xml:"ModelType"`
+	Status                  string              `json:"status" xml:"Status"`
+	TaskConfig              *TaskConfig         `json:"taskConfig" xml:"TaskConfig"`
+}
+
+type FlywheelSummary struct {
+	ActiveModelArn          string    `json:"activeModelArn" xml:"ActiveModelArn"`
+	CreationTime            time.Time `json:"creationTime" xml:"CreationTime"`
+	DataLakeS3Uri           string    `json:"dataLakeS3Uri" xml:"DataLakeS3Uri"`
+	FlywheelArn             string    `json:"flywheelArn" xml:"FlywheelArn"`
+	LastModifiedTime        time.Time `json:"lastModifiedTime" xml:"LastModifiedTime"`
+	LatestFlywheelIteration string    `json:"latestFlywheelIteration" xml:"LatestFlywheelIteration"`
+	Message                 string    `json:"message" xml:"Message"`
+	ModelType               string    `json:"modelType" xml:"ModelType"`
+	Status                  string    `json:"status" xml:"Status"`
+}
+
+type Geometry struct {
+	BoundingBox *BoundingBox `json:"boundingBox" xml:"BoundingBox"`
+	Polygon     Polygon      `json:"polygon" xml:"Polygon"`
+}
+
+type ImportModelRequest struct {
+	DataAccessRoleArn string  `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	ModelKmsKeyId     string  `json:"modelKmsKeyId" xml:"ModelKmsKeyId"`
+	ModelName         string  `json:"modelName" xml:"ModelName"`
+	SourceModelArn    string  `json:"sourceModelArn" xml:"SourceModelArn"`
+	Tags              TagList `json:"tags" xml:"Tags"`
+	VersionName       string  `json:"versionName" xml:"VersionName"`
+}
+
+type ImportModelResponse struct {
+	ModelArn string `json:"modelArn" xml:"ModelArn"`
+}
+
+type InputDataConfig struct {
+	DocumentReaderConfig *DocumentReaderConfig `json:"documentReaderConfig" xml:"DocumentReaderConfig"`
+	InputFormat          string                `json:"inputFormat" xml:"InputFormat"`
+	S3Uri                string                `json:"s3Uri" xml:"S3Uri"`
+}
+
+type InvalidRequestDetail struct {
+	Reason string `json:"reason" xml:"Reason"`
+}
+
+type KeyPhrase struct {
+	BeginOffset int32   `json:"beginOffset" xml:"BeginOffset"`
+	EndOffset   int32   `json:"endOffset" xml:"EndOffset"`
+	Score       float32 `json:"score" xml:"Score"`
+	Text        string  `json:"text" xml:"Text"`
+}
+
+type KeyPhrasesDetectionJobFilter struct {
+	JobName          string    `json:"jobName" xml:"JobName"`
+	JobStatus        string    `json:"jobStatus" xml:"JobStatus"`
+	SubmitTimeAfter  time.Time `json:"submitTimeAfter" xml:"SubmitTimeAfter"`
+	SubmitTimeBefore time.Time `json:"submitTimeBefore" xml:"SubmitTimeBefore"`
+}
+
+type KeyPhrasesDetectionJobProperties struct {
+	DataAccessRoleArn string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	EndTime           time.Time         `json:"endTime" xml:"EndTime"`
+	InputDataConfig   *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobArn            string            `json:"jobArn" xml:"JobArn"`
+	JobId             string            `json:"jobId" xml:"JobId"`
+	JobName           string            `json:"jobName" xml:"JobName"`
+	JobStatus         string            `json:"jobStatus" xml:"JobStatus"`
+	LanguageCode      string            `json:"languageCode" xml:"LanguageCode"`
+	Message           string            `json:"message" xml:"Message"`
+	OutputDataConfig  *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	SubmitTime        time.Time         `json:"submitTime" xml:"SubmitTime"`
+	VolumeKmsKeyId    string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig         *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type ListDatasetsRequest struct {
+	Filter      *DatasetFilter `json:"filter" xml:"Filter"`
+	FlywheelArn string         `json:"flywheelArn" xml:"FlywheelArn"`
+	MaxResults  int32          `json:"maxResults" xml:"MaxResults"`
+	NextToken   string         `json:"nextToken" xml:"NextToken"`
+}
+
+type ListDatasetsResponse struct {
+	DatasetPropertiesList DatasetPropertiesList `json:"datasetPropertiesList" xml:"DatasetPropertiesList"`
+	NextToken             string                `json:"nextToken" xml:"NextToken"`
+}
+
+type ListDocumentClassificationJobsRequest struct {
+	Filter     *DocumentClassificationJobFilter `json:"filter" xml:"Filter"`
+	MaxResults int32                            `json:"maxResults" xml:"MaxResults"`
+	NextToken  string                           `json:"nextToken" xml:"NextToken"`
+}
+
+type ListDocumentClassificationJobsResponse struct {
+	DocumentClassificationJobPropertiesList DocumentClassificationJobPropertiesList `json:"documentClassificationJobPropertiesList" xml:"DocumentClassificationJobPropertiesList"`
+	NextToken                               string                                  `json:"nextToken" xml:"NextToken"`
+}
+
+type ListDocumentClassifierSummariesRequest struct {
+	MaxResults int32  `json:"maxResults" xml:"MaxResults"`
+	NextToken  string `json:"nextToken" xml:"NextToken"`
+}
+
+type ListDocumentClassifierSummariesResponse struct {
+	DocumentClassifierSummariesList DocumentClassifierSummariesList `json:"documentClassifierSummariesList" xml:"DocumentClassifierSummariesList"`
+	NextToken                       string                          `json:"nextToken" xml:"NextToken"`
+}
+
+type ListDocumentClassifiersRequest struct {
+	Filter     *DocumentClassifierFilter `json:"filter" xml:"Filter"`
+	MaxResults int32                     `json:"maxResults" xml:"MaxResults"`
+	NextToken  string                    `json:"nextToken" xml:"NextToken"`
+}
+
+type ListDocumentClassifiersResponse struct {
+	DocumentClassifierPropertiesList DocumentClassifierPropertiesList `json:"documentClassifierPropertiesList" xml:"DocumentClassifierPropertiesList"`
+	NextToken                        string                           `json:"nextToken" xml:"NextToken"`
+}
+
+type ListDominantLanguageDetectionJobsRequest struct {
+	Filter     *DominantLanguageDetectionJobFilter `json:"filter" xml:"Filter"`
+	MaxResults int32                               `json:"maxResults" xml:"MaxResults"`
+	NextToken  string                              `json:"nextToken" xml:"NextToken"`
+}
+
+type ListDominantLanguageDetectionJobsResponse struct {
+	DominantLanguageDetectionJobPropertiesList DominantLanguageDetectionJobPropertiesList `json:"dominantLanguageDetectionJobPropertiesList" xml:"DominantLanguageDetectionJobPropertiesList"`
+	NextToken                                  string                                     `json:"nextToken" xml:"NextToken"`
+}
+
+type ListEndpointsRequest struct {
+	Filter     *EndpointFilter `json:"filter" xml:"Filter"`
+	MaxResults int32           `json:"maxResults" xml:"MaxResults"`
+	NextToken  string          `json:"nextToken" xml:"NextToken"`
+}
+
+type ListEndpointsResponse struct {
+	EndpointPropertiesList EndpointPropertiesList `json:"endpointPropertiesList" xml:"EndpointPropertiesList"`
+	NextToken              string                 `json:"nextToken" xml:"NextToken"`
+}
+
+type ListEntitiesDetectionJobsRequest struct {
+	Filter     *EntitiesDetectionJobFilter `json:"filter" xml:"Filter"`
+	MaxResults int32                       `json:"maxResults" xml:"MaxResults"`
+	NextToken  string                      `json:"nextToken" xml:"NextToken"`
+}
+
+type ListEntitiesDetectionJobsResponse struct {
+	EntitiesDetectionJobPropertiesList EntitiesDetectionJobPropertiesList `json:"entitiesDetectionJobPropertiesList" xml:"EntitiesDetectionJobPropertiesList"`
+	NextToken                          string                             `json:"nextToken" xml:"NextToken"`
+}
+
+type ListEntityRecognizerSummariesRequest struct {
+	MaxResults int32  `json:"maxResults" xml:"MaxResults"`
+	NextToken  string `json:"nextToken" xml:"NextToken"`
+}
+
+type ListEntityRecognizerSummariesResponse struct {
+	EntityRecognizerSummariesList EntityRecognizerSummariesList `json:"entityRecognizerSummariesList" xml:"EntityRecognizerSummariesList"`
+	NextToken                     string                        `json:"nextToken" xml:"NextToken"`
+}
+
+type ListEntityRecognizersRequest struct {
+	Filter     *EntityRecognizerFilter `json:"filter" xml:"Filter"`
+	MaxResults int32                   `json:"maxResults" xml:"MaxResults"`
+	NextToken  string                  `json:"nextToken" xml:"NextToken"`
+}
+
+type ListEntityRecognizersResponse struct {
+	EntityRecognizerPropertiesList EntityRecognizerPropertiesList `json:"entityRecognizerPropertiesList" xml:"EntityRecognizerPropertiesList"`
+	NextToken                      string                         `json:"nextToken" xml:"NextToken"`
+}
+
+type ListEventsDetectionJobsRequest struct {
+	Filter     *EventsDetectionJobFilter `json:"filter" xml:"Filter"`
+	MaxResults int32                     `json:"maxResults" xml:"MaxResults"`
+	NextToken  string                    `json:"nextToken" xml:"NextToken"`
+}
+
+type ListEventsDetectionJobsResponse struct {
+	EventsDetectionJobPropertiesList EventsDetectionJobPropertiesList `json:"eventsDetectionJobPropertiesList" xml:"EventsDetectionJobPropertiesList"`
+	NextToken                        string                           `json:"nextToken" xml:"NextToken"`
+}
+
+type ListFlywheelIterationHistoryRequest struct {
+	Filter      *FlywheelIterationFilter `json:"filter" xml:"Filter"`
+	FlywheelArn string                   `json:"flywheelArn" xml:"FlywheelArn"`
+	MaxResults  int32                    `json:"maxResults" xml:"MaxResults"`
+	NextToken   string                   `json:"nextToken" xml:"NextToken"`
+}
+
+type ListFlywheelIterationHistoryResponse struct {
+	FlywheelIterationPropertiesList FlywheelIterationPropertiesList `json:"flywheelIterationPropertiesList" xml:"FlywheelIterationPropertiesList"`
+	NextToken                       string                          `json:"nextToken" xml:"NextToken"`
+}
+
+type ListFlywheelsRequest struct {
+	Filter     *FlywheelFilter `json:"filter" xml:"Filter"`
+	MaxResults int32           `json:"maxResults" xml:"MaxResults"`
+	NextToken  string          `json:"nextToken" xml:"NextToken"`
+}
+
+type ListFlywheelsResponse struct {
+	FlywheelSummaryList FlywheelSummaryList `json:"flywheelSummaryList" xml:"FlywheelSummaryList"`
+	NextToken           string              `json:"nextToken" xml:"NextToken"`
+}
+
+type ListKeyPhrasesDetectionJobsRequest struct {
+	Filter     *KeyPhrasesDetectionJobFilter `json:"filter" xml:"Filter"`
+	MaxResults int32                         `json:"maxResults" xml:"MaxResults"`
+	NextToken  string                        `json:"nextToken" xml:"NextToken"`
+}
+
+type ListKeyPhrasesDetectionJobsResponse struct {
+	KeyPhrasesDetectionJobPropertiesList KeyPhrasesDetectionJobPropertiesList `json:"keyPhrasesDetectionJobPropertiesList" xml:"KeyPhrasesDetectionJobPropertiesList"`
+	NextToken                            string                               `json:"nextToken" xml:"NextToken"`
+}
+
+type ListPiiEntitiesDetectionJobsRequest struct {
+	Filter     *PiiEntitiesDetectionJobFilter `json:"filter" xml:"Filter"`
+	MaxResults int32                          `json:"maxResults" xml:"MaxResults"`
+	NextToken  string                         `json:"nextToken" xml:"NextToken"`
+}
+
+type ListPiiEntitiesDetectionJobsResponse struct {
+	NextToken                             string                                `json:"nextToken" xml:"NextToken"`
+	PiiEntitiesDetectionJobPropertiesList PiiEntitiesDetectionJobPropertiesList `json:"piiEntitiesDetectionJobPropertiesList" xml:"PiiEntitiesDetectionJobPropertiesList"`
+}
+
+type ListSentimentDetectionJobsRequest struct {
+	Filter     *SentimentDetectionJobFilter `json:"filter" xml:"Filter"`
+	MaxResults int32                        `json:"maxResults" xml:"MaxResults"`
+	NextToken  string                       `json:"nextToken" xml:"NextToken"`
+}
+
+type ListSentimentDetectionJobsResponse struct {
+	NextToken                           string                              `json:"nextToken" xml:"NextToken"`
+	SentimentDetectionJobPropertiesList SentimentDetectionJobPropertiesList `json:"sentimentDetectionJobPropertiesList" xml:"SentimentDetectionJobPropertiesList"`
+}
+
+type ListTagsForResourceRequest struct {
+	ResourceArn string `json:"resourceArn" xml:"ResourceArn"`
+}
+
+type ListTagsForResourceResponse struct {
+	ResourceArn string  `json:"resourceArn" xml:"ResourceArn"`
+	Tags        TagList `json:"tags" xml:"Tags"`
+}
+
+type ListTargetedSentimentDetectionJobsRequest struct {
+	Filter     *TargetedSentimentDetectionJobFilter `json:"filter" xml:"Filter"`
+	MaxResults int32                                `json:"maxResults" xml:"MaxResults"`
+	NextToken  string                               `json:"nextToken" xml:"NextToken"`
+}
+
+type ListTargetedSentimentDetectionJobsResponse struct {
+	NextToken                                   string                                      `json:"nextToken" xml:"NextToken"`
+	TargetedSentimentDetectionJobPropertiesList TargetedSentimentDetectionJobPropertiesList `json:"targetedSentimentDetectionJobPropertiesList" xml:"TargetedSentimentDetectionJobPropertiesList"`
+}
+
+type ListTopicsDetectionJobsRequest struct {
+	Filter     *TopicsDetectionJobFilter `json:"filter" xml:"Filter"`
+	MaxResults int32                     `json:"maxResults" xml:"MaxResults"`
+	NextToken  string                    `json:"nextToken" xml:"NextToken"`
+}
+
+type ListTopicsDetectionJobsResponse struct {
+	NextToken                        string                           `json:"nextToken" xml:"NextToken"`
+	TopicsDetectionJobPropertiesList TopicsDetectionJobPropertiesList `json:"topicsDetectionJobPropertiesList" xml:"TopicsDetectionJobPropertiesList"`
+}
+
+type MentionSentiment struct {
+	Sentiment      string          `json:"sentiment" xml:"Sentiment"`
+	SentimentScore *SentimentScore `json:"sentimentScore" xml:"SentimentScore"`
+}
+
+type OutputDataConfig struct {
+	KmsKeyId string `json:"kmsKeyId" xml:"KmsKeyId"`
+	S3Uri    string `json:"s3Uri" xml:"S3Uri"`
+}
+
+type PartOfSpeechTag struct {
+	Score float32 `json:"score" xml:"Score"`
+	Tag   string  `json:"tag" xml:"Tag"`
+}
+
+type PiiEntitiesDetectionJobFilter struct {
+	JobName          string    `json:"jobName" xml:"JobName"`
+	JobStatus        string    `json:"jobStatus" xml:"JobStatus"`
+	SubmitTimeAfter  time.Time `json:"submitTimeAfter" xml:"SubmitTimeAfter"`
+	SubmitTimeBefore time.Time `json:"submitTimeBefore" xml:"SubmitTimeBefore"`
+}
+
+type PiiEntitiesDetectionJobProperties struct {
+	DataAccessRoleArn string               `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	EndTime           time.Time            `json:"endTime" xml:"EndTime"`
+	InputDataConfig   *InputDataConfig     `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobArn            string               `json:"jobArn" xml:"JobArn"`
+	JobId             string               `json:"jobId" xml:"JobId"`
+	JobName           string               `json:"jobName" xml:"JobName"`
+	JobStatus         string               `json:"jobStatus" xml:"JobStatus"`
+	LanguageCode      string               `json:"languageCode" xml:"LanguageCode"`
+	Message           string               `json:"message" xml:"Message"`
+	Mode              string               `json:"mode" xml:"Mode"`
+	OutputDataConfig  *PiiOutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	RedactionConfig   *RedactionConfig     `json:"redactionConfig" xml:"RedactionConfig"`
+	SubmitTime        time.Time            `json:"submitTime" xml:"SubmitTime"`
+}
+
+type PiiEntity struct {
+	BeginOffset int32   `json:"beginOffset" xml:"BeginOffset"`
+	EndOffset   int32   `json:"endOffset" xml:"EndOffset"`
+	Score       float32 `json:"score" xml:"Score"`
+	Type        string  `json:"type" xml:"Type"`
+}
+
+type PiiOutputDataConfig struct {
+	KmsKeyId string `json:"kmsKeyId" xml:"KmsKeyId"`
+	S3Uri    string `json:"s3Uri" xml:"S3Uri"`
+}
+
+type Point struct {
+	X float32 `json:"x" xml:"X"`
+	Y float32 `json:"y" xml:"Y"`
+}
+
+type PutResourcePolicyRequest struct {
+	PolicyRevisionId string `json:"policyRevisionId" xml:"PolicyRevisionId"`
+	ResourceArn      string `json:"resourceArn" xml:"ResourceArn"`
+	ResourcePolicy   string `json:"resourcePolicy" xml:"ResourcePolicy"`
+}
+
+type PutResourcePolicyResponse struct {
+	PolicyRevisionId string `json:"policyRevisionId" xml:"PolicyRevisionId"`
+}
+
+type RedactionConfig struct {
+	MaskCharacter  string               `json:"maskCharacter" xml:"MaskCharacter"`
+	MaskMode       string               `json:"maskMode" xml:"MaskMode"`
+	PiiEntityTypes ListOfPiiEntityTypes `json:"piiEntityTypes" xml:"PiiEntityTypes"`
+}
+
+type RelationshipsListItem struct {
+	Ids  StringList `json:"ids" xml:"Ids"`
+	Type string     `json:"type" xml:"Type"`
+}
+
+type SentimentDetectionJobFilter struct {
+	JobName          string    `json:"jobName" xml:"JobName"`
+	JobStatus        string    `json:"jobStatus" xml:"JobStatus"`
+	SubmitTimeAfter  time.Time `json:"submitTimeAfter" xml:"SubmitTimeAfter"`
+	SubmitTimeBefore time.Time `json:"submitTimeBefore" xml:"SubmitTimeBefore"`
+}
+
+type SentimentDetectionJobProperties struct {
+	DataAccessRoleArn string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	EndTime           time.Time         `json:"endTime" xml:"EndTime"`
+	InputDataConfig   *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobArn            string            `json:"jobArn" xml:"JobArn"`
+	JobId             string            `json:"jobId" xml:"JobId"`
+	JobName           string            `json:"jobName" xml:"JobName"`
+	JobStatus         string            `json:"jobStatus" xml:"JobStatus"`
+	LanguageCode      string            `json:"languageCode" xml:"LanguageCode"`
+	Message           string            `json:"message" xml:"Message"`
+	OutputDataConfig  *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	SubmitTime        time.Time         `json:"submitTime" xml:"SubmitTime"`
+	VolumeKmsKeyId    string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig         *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type SentimentScore struct {
+	Mixed    float32 `json:"mixed" xml:"Mixed"`
+	Negative float32 `json:"negative" xml:"Negative"`
+	Neutral  float32 `json:"neutral" xml:"Neutral"`
+	Positive float32 `json:"positive" xml:"Positive"`
+}
+
+type StartDocumentClassificationJobRequest struct {
+	ClientRequestToken    string            `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DataAccessRoleArn     string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	DocumentClassifierArn string            `json:"documentClassifierArn" xml:"DocumentClassifierArn"`
+	FlywheelArn           string            `json:"flywheelArn" xml:"FlywheelArn"`
+	InputDataConfig       *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobName               string            `json:"jobName" xml:"JobName"`
+	OutputDataConfig      *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	Tags                  TagList           `json:"tags" xml:"Tags"`
+	VolumeKmsKeyId        string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig             *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type StartDocumentClassificationJobResponse struct {
+	DocumentClassifierArn string `json:"documentClassifierArn" xml:"DocumentClassifierArn"`
+	JobArn                string `json:"jobArn" xml:"JobArn"`
+	JobId                 string `json:"jobId" xml:"JobId"`
+	JobStatus             string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StartDominantLanguageDetectionJobRequest struct {
+	ClientRequestToken string            `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DataAccessRoleArn  string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	InputDataConfig    *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobName            string            `json:"jobName" xml:"JobName"`
+	OutputDataConfig   *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	Tags               TagList           `json:"tags" xml:"Tags"`
+	VolumeKmsKeyId     string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig          *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type StartDominantLanguageDetectionJobResponse struct {
+	JobArn    string `json:"jobArn" xml:"JobArn"`
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StartEntitiesDetectionJobRequest struct {
+	ClientRequestToken  string            `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DataAccessRoleArn   string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	EntityRecognizerArn string            `json:"entityRecognizerArn" xml:"EntityRecognizerArn"`
+	FlywheelArn         string            `json:"flywheelArn" xml:"FlywheelArn"`
+	InputDataConfig     *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobName             string            `json:"jobName" xml:"JobName"`
+	LanguageCode        string            `json:"languageCode" xml:"LanguageCode"`
+	OutputDataConfig    *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	Tags                TagList           `json:"tags" xml:"Tags"`
+	VolumeKmsKeyId      string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig           *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type StartEntitiesDetectionJobResponse struct {
+	EntityRecognizerArn string `json:"entityRecognizerArn" xml:"EntityRecognizerArn"`
+	JobArn              string `json:"jobArn" xml:"JobArn"`
+	JobId               string `json:"jobId" xml:"JobId"`
+	JobStatus           string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StartEventsDetectionJobRequest struct {
+	ClientRequestToken string            `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DataAccessRoleArn  string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	InputDataConfig    *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobName            string            `json:"jobName" xml:"JobName"`
+	LanguageCode       string            `json:"languageCode" xml:"LanguageCode"`
+	OutputDataConfig   *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	Tags               TagList           `json:"tags" xml:"Tags"`
+	TargetEventTypes   TargetEventTypes  `json:"targetEventTypes" xml:"TargetEventTypes"`
+}
+
+type StartEventsDetectionJobResponse struct {
+	JobArn    string `json:"jobArn" xml:"JobArn"`
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StartFlywheelIterationRequest struct {
+	ClientRequestToken string `json:"clientRequestToken" xml:"ClientRequestToken"`
+	FlywheelArn        string `json:"flywheelArn" xml:"FlywheelArn"`
+}
+
+type StartFlywheelIterationResponse struct {
+	FlywheelArn         string `json:"flywheelArn" xml:"FlywheelArn"`
+	FlywheelIterationId string `json:"flywheelIterationId" xml:"FlywheelIterationId"`
+}
+
+type StartKeyPhrasesDetectionJobRequest struct {
+	ClientRequestToken string            `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DataAccessRoleArn  string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	InputDataConfig    *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobName            string            `json:"jobName" xml:"JobName"`
+	LanguageCode       string            `json:"languageCode" xml:"LanguageCode"`
+	OutputDataConfig   *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	Tags               TagList           `json:"tags" xml:"Tags"`
+	VolumeKmsKeyId     string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig          *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type StartKeyPhrasesDetectionJobResponse struct {
+	JobArn    string `json:"jobArn" xml:"JobArn"`
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StartPiiEntitiesDetectionJobRequest struct {
+	ClientRequestToken string            `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DataAccessRoleArn  string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	InputDataConfig    *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobName            string            `json:"jobName" xml:"JobName"`
+	LanguageCode       string            `json:"languageCode" xml:"LanguageCode"`
+	Mode               string            `json:"mode" xml:"Mode"`
+	OutputDataConfig   *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	RedactionConfig    *RedactionConfig  `json:"redactionConfig" xml:"RedactionConfig"`
+	Tags               TagList           `json:"tags" xml:"Tags"`
+}
+
+type StartPiiEntitiesDetectionJobResponse struct {
+	JobArn    string `json:"jobArn" xml:"JobArn"`
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StartSentimentDetectionJobRequest struct {
+	ClientRequestToken string            `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DataAccessRoleArn  string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	InputDataConfig    *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobName            string            `json:"jobName" xml:"JobName"`
+	LanguageCode       string            `json:"languageCode" xml:"LanguageCode"`
+	OutputDataConfig   *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	Tags               TagList           `json:"tags" xml:"Tags"`
+	VolumeKmsKeyId     string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig          *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type StartSentimentDetectionJobResponse struct {
+	JobArn    string `json:"jobArn" xml:"JobArn"`
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StartTargetedSentimentDetectionJobRequest struct {
+	ClientRequestToken string            `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DataAccessRoleArn  string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	InputDataConfig    *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobName            string            `json:"jobName" xml:"JobName"`
+	LanguageCode       string            `json:"languageCode" xml:"LanguageCode"`
+	OutputDataConfig   *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	Tags               TagList           `json:"tags" xml:"Tags"`
+	VolumeKmsKeyId     string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig          *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type StartTargetedSentimentDetectionJobResponse struct {
+	JobArn    string `json:"jobArn" xml:"JobArn"`
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StartTopicsDetectionJobRequest struct {
+	ClientRequestToken string            `json:"clientRequestToken" xml:"ClientRequestToken"`
+	DataAccessRoleArn  string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	InputDataConfig    *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobName            string            `json:"jobName" xml:"JobName"`
+	NumberOfTopics     int32             `json:"numberOfTopics" xml:"NumberOfTopics"`
+	OutputDataConfig   *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	Tags               TagList           `json:"tags" xml:"Tags"`
+	VolumeKmsKeyId     string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig          *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type StartTopicsDetectionJobResponse struct {
+	JobArn    string `json:"jobArn" xml:"JobArn"`
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StopDominantLanguageDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type StopDominantLanguageDetectionJobResponse struct {
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StopEntitiesDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type StopEntitiesDetectionJobResponse struct {
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StopEventsDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type StopEventsDetectionJobResponse struct {
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StopKeyPhrasesDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type StopKeyPhrasesDetectionJobResponse struct {
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StopPiiEntitiesDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type StopPiiEntitiesDetectionJobResponse struct {
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StopSentimentDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type StopSentimentDetectionJobResponse struct {
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StopTargetedSentimentDetectionJobRequest struct {
+	JobId string `json:"jobId" xml:"JobId"`
+}
+
+type StopTargetedSentimentDetectionJobResponse struct {
+	JobId     string `json:"jobId" xml:"JobId"`
+	JobStatus string `json:"jobStatus" xml:"JobStatus"`
+}
+
+type StopTrainingDocumentClassifierRequest struct {
+	DocumentClassifierArn string `json:"documentClassifierArn" xml:"DocumentClassifierArn"`
+}
+
+type StopTrainingDocumentClassifierResponse struct {
+}
+
+type StopTrainingEntityRecognizerRequest struct {
+	EntityRecognizerArn string `json:"entityRecognizerArn" xml:"EntityRecognizerArn"`
+}
+
+type StopTrainingEntityRecognizerResponse struct {
+}
+
+type SyntaxToken struct {
+	BeginOffset  int32            `json:"beginOffset" xml:"BeginOffset"`
+	EndOffset    int32            `json:"endOffset" xml:"EndOffset"`
+	PartOfSpeech *PartOfSpeechTag `json:"partOfSpeech" xml:"PartOfSpeech"`
+	Text         string           `json:"text" xml:"Text"`
+	TokenId      int32            `json:"tokenId" xml:"TokenId"`
+}
+
+type Tag struct {
+	Key   string `json:"key" xml:"Key"`
+	Value string `json:"value" xml:"Value"`
+}
+
+type TagResourceRequest struct {
+	ResourceArn string  `json:"resourceArn" xml:"ResourceArn"`
+	Tags        TagList `json:"tags" xml:"Tags"`
+}
+
+type TagResourceResponse struct {
+}
+
+type TargetedSentimentDetectionJobFilter struct {
+	JobName          string    `json:"jobName" xml:"JobName"`
+	JobStatus        string    `json:"jobStatus" xml:"JobStatus"`
+	SubmitTimeAfter  time.Time `json:"submitTimeAfter" xml:"SubmitTimeAfter"`
+	SubmitTimeBefore time.Time `json:"submitTimeBefore" xml:"SubmitTimeBefore"`
+}
+
+type TargetedSentimentDetectionJobProperties struct {
+	DataAccessRoleArn string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	EndTime           time.Time         `json:"endTime" xml:"EndTime"`
+	InputDataConfig   *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobArn            string            `json:"jobArn" xml:"JobArn"`
+	JobId             string            `json:"jobId" xml:"JobId"`
+	JobName           string            `json:"jobName" xml:"JobName"`
+	JobStatus         string            `json:"jobStatus" xml:"JobStatus"`
+	LanguageCode      string            `json:"languageCode" xml:"LanguageCode"`
+	Message           string            `json:"message" xml:"Message"`
+	OutputDataConfig  *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	SubmitTime        time.Time         `json:"submitTime" xml:"SubmitTime"`
+	VolumeKmsKeyId    string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig         *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type TargetedSentimentEntity struct {
+	DescriptiveMentionIndex ListOfDescriptiveMentionIndices `json:"descriptiveMentionIndex" xml:"DescriptiveMentionIndex"`
+	Mentions                ListOfMentions                  `json:"mentions" xml:"Mentions"`
+}
+
+type TargetedSentimentMention struct {
+	BeginOffset      int32             `json:"beginOffset" xml:"BeginOffset"`
+	EndOffset        int32             `json:"endOffset" xml:"EndOffset"`
+	GroupScore       float32           `json:"groupScore" xml:"GroupScore"`
+	MentionSentiment *MentionSentiment `json:"mentionSentiment" xml:"MentionSentiment"`
+	Score            float32           `json:"score" xml:"Score"`
+	Text             string            `json:"text" xml:"Text"`
+	Type             string            `json:"type" xml:"Type"`
+}
+
+type TaskConfig struct {
+	DocumentClassificationConfig *DocumentClassificationConfig `json:"documentClassificationConfig" xml:"DocumentClassificationConfig"`
+	EntityRecognitionConfig      *EntityRecognitionConfig      `json:"entityRecognitionConfig" xml:"EntityRecognitionConfig"`
+	LanguageCode                 string                        `json:"languageCode" xml:"LanguageCode"`
+}
+
+type TextSegment struct {
+	Text string `json:"text" xml:"Text"`
+}
+
+type TopicsDetectionJobFilter struct {
+	JobName          string    `json:"jobName" xml:"JobName"`
+	JobStatus        string    `json:"jobStatus" xml:"JobStatus"`
+	SubmitTimeAfter  time.Time `json:"submitTimeAfter" xml:"SubmitTimeAfter"`
+	SubmitTimeBefore time.Time `json:"submitTimeBefore" xml:"SubmitTimeBefore"`
+}
+
+type TopicsDetectionJobProperties struct {
+	DataAccessRoleArn string            `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	EndTime           time.Time         `json:"endTime" xml:"EndTime"`
+	InputDataConfig   *InputDataConfig  `json:"inputDataConfig" xml:"InputDataConfig"`
+	JobArn            string            `json:"jobArn" xml:"JobArn"`
+	JobId             string            `json:"jobId" xml:"JobId"`
+	JobName           string            `json:"jobName" xml:"JobName"`
+	JobStatus         string            `json:"jobStatus" xml:"JobStatus"`
+	Message           string            `json:"message" xml:"Message"`
+	NumberOfTopics    int32             `json:"numberOfTopics" xml:"NumberOfTopics"`
+	OutputDataConfig  *OutputDataConfig `json:"outputDataConfig" xml:"OutputDataConfig"`
+	SubmitTime        time.Time         `json:"submitTime" xml:"SubmitTime"`
+	VolumeKmsKeyId    string            `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig         *VpcConfig        `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type ToxicContent struct {
+	Name  string  `json:"name" xml:"Name"`
+	Score float32 `json:"score" xml:"Score"`
+}
+
+type ToxicLabels struct {
+	Labels   ListOfToxicContent `json:"labels" xml:"Labels"`
+	Toxicity float32            `json:"toxicity" xml:"Toxicity"`
+}
+
+type UntagResourceRequest struct {
+	ResourceArn string     `json:"resourceArn" xml:"ResourceArn"`
+	TagKeys     TagKeyList `json:"tagKeys" xml:"TagKeys"`
+}
+
+type UntagResourceResponse struct {
+}
+
+type UpdateDataSecurityConfig struct {
+	ModelKmsKeyId  string     `json:"modelKmsKeyId" xml:"ModelKmsKeyId"`
+	VolumeKmsKeyId string     `json:"volumeKmsKeyId" xml:"VolumeKmsKeyId"`
+	VpcConfig      *VpcConfig `json:"vpcConfig" xml:"VpcConfig"`
+}
+
+type UpdateEndpointRequest struct {
+	DesiredDataAccessRoleArn string `json:"desiredDataAccessRoleArn" xml:"DesiredDataAccessRoleArn"`
+	DesiredInferenceUnits    int32  `json:"desiredInferenceUnits" xml:"DesiredInferenceUnits"`
+	DesiredModelArn          string `json:"desiredModelArn" xml:"DesiredModelArn"`
+	EndpointArn              string `json:"endpointArn" xml:"EndpointArn"`
+	FlywheelArn              string `json:"flywheelArn" xml:"FlywheelArn"`
+}
+
+type UpdateEndpointResponse struct {
+	DesiredModelArn string `json:"desiredModelArn" xml:"DesiredModelArn"`
+}
+
+type UpdateFlywheelRequest struct {
+	ActiveModelArn     string                    `json:"activeModelArn" xml:"ActiveModelArn"`
+	DataAccessRoleArn  string                    `json:"dataAccessRoleArn" xml:"DataAccessRoleArn"`
+	DataSecurityConfig *UpdateDataSecurityConfig `json:"dataSecurityConfig" xml:"DataSecurityConfig"`
+	FlywheelArn        string                    `json:"flywheelArn" xml:"FlywheelArn"`
+}
+
+type UpdateFlywheelResponse struct {
+	FlywheelProperties *FlywheelProperties `json:"flywheelProperties" xml:"FlywheelProperties"`
+}
+
+type VpcConfig struct {
+	SecurityGroupIds SecurityGroupIds `json:"securityGroupIds" xml:"SecurityGroupIds"`
+	Subnets          Subnets          `json:"subnets" xml:"Subnets"`
+}
+
+type WarningsListItem struct {
+	Page        int32  `json:"page" xml:"Page"`
+	WarnCode    string `json:"warnCode" xml:"WarnCode"`
+	WarnMessage string `json:"warnMessage" xml:"WarnMessage"`
+}
+
+type AttributeNamesList []string
+
+type BatchItemErrorList []*BatchItemError
+
+type CustomerInputStringList []string
+
+type DatasetAugmentedManifestsList []*DatasetAugmentedManifestsListItem
+
+type DatasetPropertiesList []*DatasetProperties
+
+type DocumentClassificationJobPropertiesList []*DocumentClassificationJobProperties
+
+type DocumentClassifierAugmentedManifestsList []*AugmentedManifestsListItem
+
+type DocumentClassifierPropertiesList []*DocumentClassifierProperties
+
+type DocumentClassifierSummariesList []*DocumentClassifierSummary
+
+type DominantLanguageDetectionJobPropertiesList []*DominantLanguageDetectionJobProperties
+
+type EndpointPropertiesList []*EndpointProperties
+
+type EntitiesDetectionJobPropertiesList []*EntitiesDetectionJobProperties
+
+type EntityRecognizerAugmentedManifestsList []*AugmentedManifestsListItem
+
+type EntityRecognizerMetadataEntityTypesList []*EntityRecognizerMetadataEntityTypesListItem
+
+type EntityRecognizerPropertiesList []*EntityRecognizerProperties
+
+type EntityRecognizerSummariesList []*EntityRecognizerSummary
+
+type EntityTypesList []*EntityTypesListItem
+
+type EventsDetectionJobPropertiesList []*EventsDetectionJobProperties
+
+type FlywheelIterationPropertiesList []*FlywheelIterationProperties
+
+type FlywheelSummaryList []*FlywheelSummary
+
+type KeyPhrasesDetectionJobPropertiesList []*KeyPhrasesDetectionJobProperties
+
+type LabelsList []string
+
+type ListOfBlockReferences []*BlockReference
+
+type ListOfBlocks []*Block
+
+type ListOfChildBlocks []*ChildBlock
+
+type ListOfClasses []*DocumentClass
+
+type ListOfDescriptiveMentionIndices []int32
+
+type ListOfDetectDominantLanguageResult []*BatchDetectDominantLanguageItemResult
+
+type ListOfDetectEntitiesResult []*BatchDetectEntitiesItemResult
+
+type ListOfDetectKeyPhrasesResult []*BatchDetectKeyPhrasesItemResult
+
+type ListOfDetectSentimentResult []*BatchDetectSentimentItemResult
+
+type ListOfDetectSyntaxResult []*BatchDetectSyntaxItemResult
+
+type ListOfDetectTargetedSentimentResult []*BatchDetectTargetedSentimentItemResult
+
+type ListOfDocumentReadFeatureTypes []string
+
+type ListOfDocumentType []*DocumentTypeListItem
+
+type ListOfDominantLanguages []*DominantLanguage
+
+type ListOfEntities []*Entity
+
+type ListOfEntityLabels []*EntityLabel
+
+type ListOfErrors []*ErrorsListItem
+
+type ListOfExtractedCharacters []*ExtractedCharactersListItem
+
+type ListOfKeyPhrases []*KeyPhrase
+
+type ListOfLabels []*DocumentLabel
+
+type ListOfMentions []*TargetedSentimentMention
+
+type ListOfPiiEntities []*PiiEntity
+
+type ListOfPiiEntityTypes []string
+
+type ListOfRelationships []*RelationshipsListItem
+
+type ListOfSyntaxTokens []*SyntaxToken
+
+type ListOfTargetedSentimentEntities []*TargetedSentimentEntity
+
+type ListOfTextSegments []*TextSegment
+
+type ListOfToxicContent []*ToxicContent
+
+type ListOfToxicLabels []*ToxicLabels
+
+type ListOfWarnings []*WarningsListItem
+
+type PiiEntitiesDetectionJobPropertiesList []*PiiEntitiesDetectionJobProperties
+
+type Polygon []*Point
+
+type SecurityGroupIds []string
+
+type SentimentDetectionJobPropertiesList []*SentimentDetectionJobProperties
+
+type StringList []string
+
+type Subnets []string
+
+type TagKeyList []string
+
+type TagList []*Tag
+
+type TargetEventTypes []string
+
+type TargetedSentimentDetectionJobPropertiesList []*TargetedSentimentDetectionJobProperties
+
+type TopicsDetectionJobPropertiesList []*TopicsDetectionJobProperties
diff --git a/internal/generated/crudregistry/registry_gen.go b/internal/generated/crudregistry/registry_gen.go
index a1d13e83..e690e32d 100644
--- a/internal/generated/crudregistry/registry_gen.go
+++ b/internal/generated/crudregistry/registry_gen.go
@@ -587,6 +587,57 @@ func init() {
 		"UpdateUserPoolClient":                 {Verb: "Update", Resource: "UserPoolClient", OutputListKey: "", OutputItemKey: "UserPoolClient"},
 		"UpdateUserPoolDomain":                 {Verb: "Update", Resource: "UserPoolDomain", OutputListKey: "", OutputItemKey: ""},
 	})
+	crud.Register("comprehend", map[string]crud.OpMeta{
+		"CreateDataset":                         {Verb: "Create", Resource: "Dataset", OutputListKey: "", OutputItemKey: ""},
+		"CreateDocumentClassifier":              {Verb: "Create", Resource: "DocumentClassifier", OutputListKey: "", OutputItemKey: ""},
+		"CreateEndpoint":                        {Verb: "Create", Resource: "Endpoint", OutputListKey: "", OutputItemKey: ""},
+		"CreateEntityRecognizer":                {Verb: "Create", Resource: "EntityRecognizer", OutputListKey: "", OutputItemKey: ""},
+		"CreateFlywheel":                        {Verb: "Create", Resource: "Flywheel", OutputListKey: "", OutputItemKey: ""},
+		"DeleteDocumentClassifier":              {Verb: "Delete", Resource: "DocumentClassifier", OutputListKey: "", OutputItemKey: ""},
+		"DeleteEndpoint":                        {Verb: "Delete", Resource: "Endpoint", OutputListKey: "", OutputItemKey: ""},
+		"DeleteEntityRecognizer":                {Verb: "Delete", Resource: "EntityRecognizer", OutputListKey: "", OutputItemKey: ""},
+		"DeleteFlywheel":                        {Verb: "Delete", Resource: "Flywheel", OutputListKey: "", OutputItemKey: ""},
+		"DeleteResourcePolicy":                  {Verb: "Delete", Resource: "ResourcePolicy", OutputListKey: "", OutputItemKey: ""},
+		"DescribeDataset":                       {Verb: "Get", Resource: "Dataset", OutputListKey: "", OutputItemKey: "DatasetProperties"},
+		"DescribeDocumentClassificationJob":     {Verb: "Get", Resource: "DocumentClassificationJob", OutputListKey: "", OutputItemKey: "DocumentClassificationJobProperties"},
+		"DescribeDocumentClassifier":            {Verb: "Get", Resource: "DocumentClassifier", OutputListKey: "", OutputItemKey: "DocumentClassifierProperties"},
+		"DescribeDominantLanguageDetectionJob":  {Verb: "Get", Resource: "DominantLanguageDetectionJob", OutputListKey: "", OutputItemKey: "DominantLanguageDetectionJobProperties"},
+		"DescribeEndpoint":                      {Verb: "Get", Resource: "Endpoint", OutputListKey: "", OutputItemKey: "EndpointProperties"},
+		"DescribeEntitiesDetectionJob":          {Verb: "Get", Resource: "EntitiesDetectionJob", OutputListKey: "", OutputItemKey: "EntitiesDetectionJobProperties"},
+		"DescribeEntityRecognizer":              {Verb: "Get", Resource: "EntityRecognizer", OutputListKey: "", OutputItemKey: "EntityRecognizerProperties"},
+		"DescribeEventsDetectionJob":            {Verb: "Get", Resource: "EventsDetectionJob", OutputListKey: "", OutputItemKey: "EventsDetectionJobProperties"},
+		"DescribeFlywheel":                      {Verb: "Get", Resource: "Flywheel", OutputListKey: "", OutputItemKey: "FlywheelProperties"},
+		"DescribeFlywheelIteration":             {Verb: "Get", Resource: "FlywheelIteration", OutputListKey: "", OutputItemKey: "FlywheelIterationProperties"},
+		"DescribeKeyPhrasesDetectionJob":        {Verb: "Get", Resource: "KeyPhrasesDetectionJob", OutputListKey: "", OutputItemKey: "KeyPhrasesDetectionJobProperties"},
+		"DescribePiiEntitiesDetectionJob":       {Verb: "Get", Resource: "PiiEntitiesDetectionJob", OutputListKey: "", OutputItemKey: "PiiEntitiesDetectionJobProperties"},
+		"DescribeResourcePolicy":                {Verb: "Get", Resource: "ResourcePolicy", OutputListKey: "", OutputItemKey: ""},
+		"DescribeSentimentDetectionJob":         {Verb: "Get", Resource: "SentimentDetectionJob", OutputListKey: "", OutputItemKey: "SentimentDetectionJobProperties"},
+		"DescribeTargetedSentimentDetectionJob": {Verb: "Get", Resource: "TargetedSentimentDetectionJob", OutputListKey: "", OutputItemKey: "TargetedSentimentDetectionJobProperties"},
+		"DescribeTopicsDetectionJob":            {Verb: "Get", Resource: "TopicsDetectionJob", OutputListKey: "", OutputItemKey: "TopicsDetectionJobProperties"},
+		"ListDatasets":                          {Verb: "List", Resource: "Dataset", OutputListKey: "DatasetPropertiesList", OutputItemKey: ""},
+		"ListDocumentClassificationJobs":        {Verb: "List", Resource: "DocumentClassificationJob", OutputListKey: "DocumentClassificationJobPropertiesList", OutputItemKey: ""},
+		"ListDocumentClassifierSummaries":       {Verb: "List", Resource: "DocumentClassifierSummary", OutputListKey: "DocumentClassifierSummariesList", OutputItemKey: ""},
+		"ListDocumentClassifiers":               {Verb: "List", Resource: "DocumentClassifier", OutputListKey: "DocumentClassifierPropertiesList", OutputItemKey: ""},
+		"ListDominantLanguageDetectionJobs":     {Verb: "List", Resource: "DominantLanguageDetectionJob", OutputListKey: "DominantLanguageDetectionJobPropertiesList", OutputItemKey: ""},
+		"ListEndpoints":                         {Verb: "List", Resource: "Endpoint", OutputListKey: "EndpointPropertiesList", OutputItemKey: ""},
+		"ListEntitiesDetectionJobs":             {Verb: "List", Resource: "EntitiesDetectionJob", OutputListKey: "EntitiesDetectionJobPropertiesList", OutputItemKey: ""},
+		"ListEntityRecognizerSummaries":         {Verb: "List", Resource: "EntityRecognizerSummary", OutputListKey: "EntityRecognizerSummariesList", OutputItemKey: ""},
+		"ListEntityRecognizers":                 {Verb: "List", Resource: "EntityRecognizer", OutputListKey: "EntityRecognizerPropertiesList", OutputItemKey: ""},
+		"ListEventsDetectionJobs":               {Verb: "List", Resource: "EventsDetectionJob", OutputListKey: "EventsDetectionJobPropertiesList", OutputItemKey: ""},
+		"ListFlywheelIterationHistory":          {Verb: "List", Resource: "FlywheelIterationHistory", OutputListKey: "FlywheelIterationPropertiesList", OutputItemKey: ""},
+		"ListFlywheels":                         {Verb: "List", Resource: "Flywheel", OutputListKey: "FlywheelSummaryList", OutputItemKey: ""},
+		"ListKeyPhrasesDetectionJobs":           {Verb: "List", Resource: "KeyPhrasesDetectionJob", OutputListKey: "KeyPhrasesDetectionJobPropertiesList", OutputItemKey: ""},
+		"ListPiiEntitiesDetectionJobs":          {Verb: "List", Resource: "PiiEntitiesDetectionJob", OutputListKey: "PiiEntitiesDetectionJobPropertiesList", OutputItemKey: ""},
+		"ListSentimentDetectionJobs":            {Verb: "List", Resource: "SentimentDetectionJob", OutputListKey: "SentimentDetectionJobPropertiesList", OutputItemKey: ""},
+		"ListTagsForResource":                   {Verb: "List", Resource: "TagsForResource", OutputListKey: "Tags", OutputItemKey: ""},
+		"ListTargetedSentimentDetectionJobs":    {Verb: "List", Resource: "TargetedSentimentDetectionJob", OutputListKey: "TargetedSentimentDetectionJobPropertiesList", OutputItemKey: ""},
+		"ListTopicsDetectionJobs":               {Verb: "List", Resource: "TopicsDetectionJob", OutputListKey: "TopicsDetectionJobPropertiesList", OutputItemKey: ""},
+		"PutResourcePolicy":                     {Verb: "Update", Resource: "ResourcePolicy", OutputListKey: "", OutputItemKey: ""},
+		"TagResource":                           {Verb: "Tag", Resource: "Resource", OutputListKey: "", OutputItemKey: ""},
+		"UntagResource":                         {Verb: "Untag", Resource: "Resource", OutputListKey: "", OutputItemKey: ""},
+		"UpdateEndpoint":                        {Verb: "Update", Resource: "Endpoint", OutputListKey: "", OutputItemKey: ""},
+		"UpdateFlywheel":                        {Verb: "Update", Resource: "Flywheel", OutputListKey: "", OutputItemKey: "FlywheelProperties"},
+	})
 	crud.Register("configservice", map[string]crud.OpMeta{
 		"BatchGetAggregateResourceConfig":               {Verb: "List", Resource: "AggregateResourceConfig", OutputListKey: "BaseConfigurationItems", OutputItemKey: ""},
 		"BatchGetResourceConfig":                        {Verb: "List", Resource: "ResourceConfig", OutputListKey: "baseConfigurationItems", OutputItemKey: ""},
diff --git a/internal/generated/fidelity/manifest_gen.go b/internal/generated/fidelity/manifest_gen.go
index a28cfb62..7e59d5da 100644
--- a/internal/generated/fidelity/manifest_gen.go
+++ b/internal/generated/fidelity/manifest_gen.go
@@ -1861,6 +1861,93 @@ var Services = map[string]Service{
 		"VerifySoftwareToken":                  TierUnimplemented,
 		"VerifyUserAttribute":                  TierUnimplemented,
 	}},
+	"comprehend": {ModelBacked: true, Operations: map[string]Tier{
+		"BatchDetectDominantLanguage":           TierUnimplemented,
+		"BatchDetectEntities":                   TierUnimplemented,
+		"BatchDetectKeyPhrases":                 TierUnimplemented,
+		"BatchDetectSentiment":                  TierUnimplemented,
+		"BatchDetectSyntax":                     TierUnimplemented,
+		"BatchDetectTargetedSentiment":          TierUnimplemented,
+		"ClassifyDocument":                      TierUnimplemented,
+		"ContainsPiiEntities":                   TierUnimplemented,
+		"CreateDataset":                         TierAutoCRUD,
+		"CreateDocumentClassifier":              TierAutoCRUD,
+		"CreateEndpoint":                        TierAutoCRUD,
+		"CreateEntityRecognizer":                TierAutoCRUD,
+		"CreateFlywheel":                        TierAutoCRUD,
+		"DeleteDocumentClassifier":              TierAutoCRUD,
+		"DeleteEndpoint":                        TierAutoCRUD,
+		"DeleteEntityRecognizer":                TierAutoCRUD,
+		"DeleteFlywheel":                        TierAutoCRUD,
+		"DeleteResourcePolicy":                  TierAutoCRUD,
+		"DescribeDataset":                       TierAutoCRUD,
+		"DescribeDocumentClassificationJob":     TierAutoCRUD,
+		"DescribeDocumentClassifier":            TierAutoCRUD,
+		"DescribeDominantLanguageDetectionJob":  TierAutoCRUD,
+		"DescribeEndpoint":                      TierAutoCRUD,
+		"DescribeEntitiesDetectionJob":          TierAutoCRUD,
+		"DescribeEntityRecognizer":              TierAutoCRUD,
+		"DescribeEventsDetectionJob":            TierAutoCRUD,
+		"DescribeFlywheel":                      TierAutoCRUD,
+		"DescribeFlywheelIteration":             TierAutoCRUD,
+		"DescribeKeyPhrasesDetectionJob":        TierAutoCRUD,
+		"DescribePiiEntitiesDetectionJob":       TierAutoCRUD,
+		"DescribeResourcePolicy":                TierAutoCRUD,
+		"DescribeSentimentDetectionJob":         TierAutoCRUD,
+		"DescribeTargetedSentimentDetectionJob": TierAutoCRUD,
+		"DescribeTopicsDetectionJob":            TierAutoCRUD,
+		"DetectDominantLanguage":                TierUnimplemented,
+		"DetectEntities":                        TierUnimplemented,
+		"DetectKeyPhrases":                      TierUnimplemented,
+		"DetectPiiEntities":                     TierUnimplemented,
+		"DetectSentiment":                       TierUnimplemented,
+		"DetectSyntax":                          TierUnimplemented,
+		"DetectTargetedSentiment":               TierUnimplemented,
+		"DetectToxicContent":                    TierUnimplemented,
+		"ImportModel":                           TierUnimplemented,
+		"ListDatasets":                          TierAutoCRUD,
+		"ListDocumentClassificationJobs":        TierAutoCRUD,
+		"ListDocumentClassifierSummaries":       TierAutoCRUD,
+		"ListDocumentClassifiers":               TierAutoCRUD,
+		"ListDominantLanguageDetectionJobs":     TierAutoCRUD,
+		"ListEndpoints":                         TierAutoCRUD,
+		"ListEntitiesDetectionJobs":             TierAutoCRUD,
+		"ListEntityRecognizerSummaries":         TierAutoCRUD,
+		"ListEntityRecognizers":                 TierAutoCRUD,
+		"ListEventsDetectionJobs":               TierAutoCRUD,
+		"ListFlywheelIterationHistory":          TierAutoCRUD,
+		"ListFlywheels":                         TierAutoCRUD,
+		"ListKeyPhrasesDetectionJobs":           TierAutoCRUD,
+		"ListPiiEntitiesDetectionJobs":          TierAutoCRUD,
+		"ListSentimentDetectionJobs":            TierAutoCRUD,
+		"ListTagsForResource":                   TierAutoCRUD,
+		"ListTargetedSentimentDetectionJobs":    TierAutoCRUD,
+		"ListTopicsDetectionJobs":               TierAutoCRUD,
+		"PutResourcePolicy":                     TierAutoCRUD,
+		"StartDocumentClassificationJob":        TierUnimplemented,
+		"StartDominantLanguageDetectionJob":     TierUnimplemented,
+		"StartEntitiesDetectionJob":             TierUnimplemented,
+		"StartEventsDetectionJob":               TierUnimplemented,
+		"StartFlywheelIteration":                TierUnimplemented,
+		"StartKeyPhrasesDetectionJob":           TierUnimplemented,
+		"StartPiiEntitiesDetectionJob":          TierUnimplemented,
+		"StartSentimentDetectionJob":            TierUnimplemented,
+		"StartTargetedSentimentDetectionJob":    TierUnimplemented,
+		"StartTopicsDetectionJob":               TierUnimplemented,
+		"StopDominantLanguageDetectionJob":      TierUnimplemented,
+		"StopEntitiesDetectionJob":              TierUnimplemented,
+		"StopEventsDetectionJob":                TierUnimplemented,
+		"StopKeyPhrasesDetectionJob":            TierUnimplemented,
+		"StopPiiEntitiesDetectionJob":           TierUnimplemented,
+		"StopSentimentDetectionJob":             TierUnimplemented,
+		"StopTargetedSentimentDetectionJob":     TierUnimplemented,
+		"StopTrainingDocumentClassifier":        TierUnimplemented,
+		"StopTrainingEntityRecognizer":          TierUnimplemented,
+		"TagResource":                           TierAutoCRUD,
+		"UntagResource":                         TierAutoCRUD,
+		"UpdateEndpoint":                        TierAutoCRUD,
+		"UpdateFlywheel":                        TierAutoCRUD,
+	}},
 	"configservice": {ModelBacked: true, Operations: map[string]Tier{
 		"AssociateResourceTypes":                        TierUnimplemented,
 		"BatchGetAggregateResourceConfig":               TierAutoCRUD,
diff --git a/internal/services/comprehend/provider.go b/internal/services/comprehend/provider.go
new file mode 100644
index 00000000..11bf076a
--- /dev/null
+++ b/internal/services/comprehend/provider.go
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: Apache-2.0
+
+package comprehend
+
+import (
+	"context"
+	"net/http"
+
+	generated "github.com/skyoo2003/devcloud/internal/generated/comprehend"
+	"github.com/skyoo2003/devcloud/internal/plugin"
+)
+
+// Provider implements the Comprehend_20171127 service.
+type Provider struct {
+	generated.BaseProvider
+	dataDir string
+}
+
+func (p *Provider) ServiceID() string             { return "comprehend" }
+func (p *Provider) ServiceName() string           { return "Comprehend_20171127" }
+func (p *Provider) Protocol() plugin.ProtocolType { return plugin.ProtocolJSON11 }
+
+func (p *Provider) Init(cfg plugin.PluginConfig) error {
+	p.dataDir = cfg.DataDir
+	return nil
+}
+
+func (p *Provider) Shutdown(ctx context.Context) error {
+	return nil
+}
+
+// HandleRequest implements nothing by hand and says so, which is what hands the
+// request to the generic CRUD engine (see docs/crud-engine.md). A scaffolded
+// service therefore serves its CRUD-shaped operations from the moment it is
+// generated; anything the engine cannot classify still returns an honest
+// InvalidAction rather than a fabricated success.
+//
+// Declining any other way — including generated.ErrNotImplemented — is a plain
+// refusal the gateway never routes to the engine, leaving the service
+// registered, routed, and serving zero operations.
+func (p *Provider) HandleRequest(ctx context.Context, op string, req *http.Request) (*plugin.Response, error) {
+	return nil, plugin.ErrUnhandledOp
+}
+
+func (p *Provider) ListResources(ctx context.Context) ([]plugin.Resource, error) {
+	return []plugin.Resource{}, nil
+}
+
+func init() {
+	plugin.DefaultRegistry.Register("comprehend", func() plugin.ServicePlugin {
+		return &Provider{}
+	})
+}
diff --git a/scripts/generate-imports.sh b/scripts/generate-imports.sh
index f3bb8ec4..cb2e4bd5 100755
--- a/scripts/generate-imports.sh
+++ b/scripts/generate-imports.sh
@@ -1,28 +1,73 @@
 #!/usr/bin/env bash
 # scripts/generate-imports.sh
 # Generates cmd/devcloud/imports.go with blank imports for all services.
+#
+# A service package is only registered if this file imports it: registration
+# happens in an init(), which never runs for a package nothing imports. So a
+# short or empty imports.go does not degrade the binary, it empties it — and
+# only in the built artefact, where nothing else notices.
 set -euo pipefail
 
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 SERVICES_DIR="./internal/services"
 OUTPUT="./cmd/devcloud/imports.go"
 
-cat > "$OUTPUT" << 'HEADER'
+# Build into a temp file first: the floor check below has to be able to refuse
+# without having already truncated a good imports.go. Same reasoning as
+# download-smithy-models.sh — a failed run must leave the committed file alone.
+tmp="$(mktemp)"
+trap 'rm -f "$tmp"' EXIT
+
+cat > "$tmp" << 'HEADER'
 // Code generated by scripts/generate-imports.sh. DO NOT EDIT.
 package main
 
 import (
 HEADER
 
+count=0
 for dir in "$SERVICES_DIR"/*/; do
   pkg=$(basename "$dir")
-  # Skip directories without register.go
-  if [ ! -f "${dir}register.go" ]; then
-    continue
-  fi
-  echo "	_ \"github.com/skyoo2003/devcloud/internal/services/${pkg}\"" >> "$OUTPUT"
+
+  # Gate on the package actually calling Register, not on a filename.
+  # Registration lives in an init() inside provider.go; no service has ever had
+  # a register.go, so gating on that filename skipped all of them and emitted an
+  # empty import block. _test.go is excluded so a test that merely mentions
+  # Register cannot qualify a package that does not register.
+  registers=0
+  for f in "$dir"*.go; do
+    [ -f "$f" ] || continue
+    case "$f" in *_test.go) continue ;; esac
+    if grep -q 'DefaultRegistry\.Register(' "$f"; then
+      registers=1
+      break
+    fi
+  done
+  [ "$registers" -eq 1 ] || continue
+
+  echo "	_ \"github.com/skyoo2003/devcloud/internal/services/${pkg}\"" >> "$tmp"
+  count=$((count + 1))
 done
 
-echo ")" >> "$OUTPUT"
+echo ")" >> "$tmp"
+
+# Every service package is committed, so a run that finds almost none has a
+# broken gate rather than a shrunken fleet. Exiting non-zero is the point: the
+# weekly sync workflow regenerates this file, and a silent green run that wrote
+# an empty import block is exactly the failure this check exists to stop.
+MIN_SERVICES="${MIN_SERVICES:-50}"
+if [ "$count" -lt "$MIN_SERVICES" ]; then
+  echo "ERROR: found ${count} registering service package(s) under ${SERVICES_DIR}, expected at least ${MIN_SERVICES}." >&2
+  echo "Refusing to write a gutted ${OUTPUT}; it is unchanged." >&2
+  exit 1
+fi
+
+mv "$tmp" "$OUTPUT"
+trap - EXIT
 
 gofmt -w "$OUTPUT"
-echo "Generated $OUTPUT"
+# Reuse the repo's SPDX rule rather than restating it here: that script already
+# knows to keep the "Code generated" marker on line 1 and insert SPDX on line 2.
+bash "${SCRIPT_DIR}/add-spdx-header.sh" "$OUTPUT"
+
+echo "Generated $OUTPUT with ${count} services"
diff --git a/smithy-models/comprehend.json b/smithy-models/comprehend.json
new file mode 100644
index 00000000..09e3be8d
--- /dev/null
+++ b/smithy-models/comprehend.json
@@ -0,0 +1,13893 @@
+{
+    "smithy": "2.0",
+    "metadata": {
+        "suppressions": [
+            {
+                "id": "HttpMethodSemantics",
+                "namespace": "*"
+            },
+            {
+                "id": "HttpResponseCodeSemantics",
+                "namespace": "*"
+            },
+            {
+                "id": "PaginatedTrait",
+                "namespace": "*"
+            },
+            {
+                "id": "HttpHeaderTrait",
+                "namespace": "*"
+            },
+            {
+                "id": "HttpUriConflict",
+                "namespace": "*"
+            },
+            {
+                "id": "Service",
+                "namespace": "*"
+            }
+        ]
+    },
+    "shapes": {
+        "com.amazonaws.comprehend#AnyLengthString": {
+            "type": "string"
+        },
+        "com.amazonaws.comprehend#AttributeNamesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#AttributeNamesListItem"
+            }
+        },
+        "com.amazonaws.comprehend#AttributeNamesListItem": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 63
+                },
+                "smithy.api#pattern": "^[a-zA-Z0-9](-*[a-zA-Z0-9])*$"
+            }
+        },
+        "com.amazonaws.comprehend#AugmentedManifestsDocumentTypeFormat": {
+            "type": "enum",
+            "members": {
+                "PLAIN_TEXT_DOCUMENT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PLAIN_TEXT_DOCUMENT"
+                    }
+                },
+                "SEMI_STRUCTURED_DOCUMENT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "SEMI_STRUCTURED_DOCUMENT"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#AugmentedManifestsListItem": {
+            "type": "structure",
+            "members": {
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon S3 location of the augmented manifest file.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "Split": {
+                    "target": "com.amazonaws.comprehend#Split",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The purpose of the data you've provided in the augmented manifest. You can either train or\n      test this data. If you don't specify, the default is train.</p>\n         <p>TRAIN - all of the documents in the manifest will be used for training. If no test\n      documents are provided, Amazon Comprehend will automatically reserve a portion of the training\n      documents for testing.</p>\n         <p> TEST - all of the documents in the manifest will be used for testing.</p>"
+                    }
+                },
+                "AttributeNames": {
+                    "target": "com.amazonaws.comprehend#AttributeNamesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The JSON attribute that contains the annotations for your training documents. The number\n      of attribute names that you specify depends on whether your augmented manifest file is the\n      output of a single labeling job or a chained labeling job.</p>\n         <p>If your file is the output of a single labeling job, specify the LabelAttributeName key\n      that was used when the job was created in Ground Truth.</p>\n         <p>If your file is the output of a chained labeling job, specify the LabelAttributeName key\n      for one or more jobs in the chain. Each LabelAttributeName key provides the annotations from\n      an individual job.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "AnnotationDataS3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The S3 prefix to the annotation files that are referred in the augmented manifest\n      file.</p>"
+                    }
+                },
+                "SourceDocumentsS3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The S3 prefix to the source files (PDFs) that are referred to in the augmented manifest\n      file.</p>"
+                    }
+                },
+                "DocumentType": {
+                    "target": "com.amazonaws.comprehend#AugmentedManifestsDocumentTypeFormat",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The type of augmented manifest. PlainTextDocument or SemiStructuredDocument. If you don't\n      specify, the default is PlainTextDocument. </p>\n         <ul>\n            <li>\n               <p>\n                  <code>PLAIN_TEXT_DOCUMENT</code> A document type that represents any unicode text that\n          is encoded in UTF-8.</p>\n            </li>\n            <li>\n               <p>\n                  <code>SEMI_STRUCTURED_DOCUMENT</code> A document type with positional and structural\n          context, like a PDF. For training with Amazon Comprehend, only PDFs are supported. For\n          inference, Amazon Comprehend support PDFs, DOCX and TXT.</p>\n            </li>\n         </ul>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>An augmented manifest file that provides training data for your custom model. An augmented\n      manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectDominantLanguage": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#BatchDetectDominantLanguageRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#BatchDetectDominantLanguageResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#BatchSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Determines the dominant language of the input text for a batch of documents. For a list\n      of languages that Amazon Comprehend can detect, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-languages.html\">Amazon Comprehend Supported Languages</a>.\n    </p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectDominantLanguageItemResult": {
+            "type": "structure",
+            "members": {
+                "Index": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based index of the document in the input list.</p>"
+                    }
+                },
+                "Languages": {
+                    "target": "com.amazonaws.comprehend#ListOfDominantLanguages",
+                    "traits": {
+                        "smithy.api#documentation": "<p>One or more <a>DominantLanguage</a> objects describing the dominant\n      languages in the document.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The result of calling the  operation.\n      The operation returns one object for each document that is successfully processed by the\n      operation.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectDominantLanguageRequest": {
+            "type": "structure",
+            "members": {
+                "TextList": {
+                    "target": "com.amazonaws.comprehend#CustomerInputStringList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25\n      documents. Each document should contain at least 20 characters. The maximum size of each document is 5 KB.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectDominantLanguageResponse": {
+            "type": "structure",
+            "members": {
+                "ResultList": {
+                    "target": "com.amazonaws.comprehend#ListOfDetectDominantLanguageResult",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list of  objects\n      containing the results of the operation. The results are sorted in ascending order by the\n        <code>Index</code> field and match the order of the documents in the input list. If all of\n      the documents contain an error, the <code>ResultList</code> is empty.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ErrorList": {
+                    "target": "com.amazonaws.comprehend#BatchItemErrorList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing one  object for each document\n      that contained an error. The results are sorted in ascending order by the <code>Index</code>\n      field and match the order of the documents in the input list. If there are no errors in the\n      batch, the <code>ErrorList</code> is empty.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {},
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectEntities": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#BatchDetectEntitiesRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#BatchDetectEntitiesResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#BatchSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Inspects the text of a batch of documents for named entities and returns information\n      about them. For more information about named entities, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-entities.html\">Entities</a> in the Comprehend Developer Guide.\n    </p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectEntitiesItemResult": {
+            "type": "structure",
+            "members": {
+                "Index": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based index of the document in the input list.</p>"
+                    }
+                },
+                "Entities": {
+                    "target": "com.amazonaws.comprehend#ListOfEntities",
+                    "traits": {
+                        "smithy.api#documentation": "<p>One or more <a>Entity</a> objects, one for each entity detected in the\n      document.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The result of calling the  operation. The\n      operation returns one object for each document that is successfully processed by the\n      operation.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectEntitiesRequest": {
+            "type": "structure",
+            "members": {
+                "TextList": {
+                    "target": "com.amazonaws.comprehend#CustomerInputStringList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25\n      documents. The maximum size of each document is 5 KB.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. You can specify any of the primary languages\n      supported by Amazon Comprehend. All documents must be in the same language.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectEntitiesResponse": {
+            "type": "structure",
+            "members": {
+                "ResultList": {
+                    "target": "com.amazonaws.comprehend#ListOfDetectEntitiesResult",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list of  objects containing the\n      results of the operation. The results are sorted in ascending order by the <code>Index</code>\n      field and match the order of the documents in the input list. If all of the documents contain\n      an error, the <code>ResultList</code> is empty.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ErrorList": {
+                    "target": "com.amazonaws.comprehend#BatchItemErrorList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing one  object for each document\n      that contained an error. The results are sorted in ascending order by the <code>Index</code>\n      field and match the order of the documents in the input list. If there are no errors in the\n      batch, the <code>ErrorList</code> is empty.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {},
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectKeyPhrases": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#BatchDetectKeyPhrasesRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#BatchDetectKeyPhrasesResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#BatchSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Detects the key noun phrases found in a batch of documents.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectKeyPhrasesItemResult": {
+            "type": "structure",
+            "members": {
+                "Index": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based index of the document in the input list.</p>"
+                    }
+                },
+                "KeyPhrases": {
+                    "target": "com.amazonaws.comprehend#ListOfKeyPhrases",
+                    "traits": {
+                        "smithy.api#documentation": "<p>One or more <a>KeyPhrase</a> objects, one for each key phrase detected in\n      the document.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The result of calling the  operation. The\n      operation returns one object for each document that is successfully processed by the\n      operation.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectKeyPhrasesRequest": {
+            "type": "structure",
+            "members": {
+                "TextList": {
+                    "target": "com.amazonaws.comprehend#CustomerInputStringList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25\n      documents. The maximum size of each document is 5 KB.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. You can specify any of the primary languages\n      supported by Amazon Comprehend. All documents must be in the same language.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectKeyPhrasesResponse": {
+            "type": "structure",
+            "members": {
+                "ResultList": {
+                    "target": "com.amazonaws.comprehend#ListOfDetectKeyPhrasesResult",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list of  objects containing the\n      results of the operation. The results are sorted in ascending order by the <code>Index</code>\n      field and match the order of the documents in the input list. If all of the documents contain\n      an error, the <code>ResultList</code> is empty.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ErrorList": {
+                    "target": "com.amazonaws.comprehend#BatchItemErrorList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing one  object for each document\n      that contained an error. The results are sorted in ascending order by the <code>Index</code>\n      field and match the order of the documents in the input list. If there are no errors in the\n      batch, the <code>ErrorList</code> is empty.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {},
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectSentiment": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#BatchDetectSentimentRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#BatchDetectSentimentResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#BatchSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Inspects a batch of documents and returns an inference of the prevailing sentiment,\n        <code>POSITIVE</code>, <code>NEUTRAL</code>, <code>MIXED</code>, or <code>NEGATIVE</code>,\n      in each one.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectSentimentItemResult": {
+            "type": "structure",
+            "members": {
+                "Index": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based index of the document in the input list.</p>"
+                    }
+                },
+                "Sentiment": {
+                    "target": "com.amazonaws.comprehend#SentimentType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The sentiment detected in the document.</p>"
+                    }
+                },
+                "SentimentScore": {
+                    "target": "com.amazonaws.comprehend#SentimentScore",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The level of confidence that Amazon Comprehend has in the accuracy of its sentiment\n      detection.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The result of calling the  operation. The\n      operation returns one object for each document that is successfully processed by the\n      operation.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectSentimentRequest": {
+            "type": "structure",
+            "members": {
+                "TextList": {
+                    "target": "com.amazonaws.comprehend#CustomerInputStringList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25\n      documents. The maximum size of each document is 5 KB. </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. You can specify any of the primary languages\n      supported by Amazon Comprehend. All documents must be in the same language.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectSentimentResponse": {
+            "type": "structure",
+            "members": {
+                "ResultList": {
+                    "target": "com.amazonaws.comprehend#ListOfDetectSentimentResult",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list of  objects containing the\n      results of the operation. The results are sorted in ascending order by the <code>Index</code>\n      field and match the order of the documents in the input list. If all of the documents contain\n      an error, the <code>ResultList</code> is empty.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ErrorList": {
+                    "target": "com.amazonaws.comprehend#BatchItemErrorList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing one  object for each document\n      that contained an error. The results are sorted in ascending order by the <code>Index</code>\n      field and match the order of the documents in the input list. If there are no errors in the\n      batch, the <code>ErrorList</code> is empty.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {},
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectSyntax": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#BatchDetectSyntaxRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#BatchDetectSyntaxResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#BatchSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Inspects the text of a batch of documents for the syntax and part of speech of the words\n      in the document and returns information about them. For more information, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-syntax.html\">Syntax</a> in the Comprehend Developer Guide.\n    </p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectSyntaxItemResult": {
+            "type": "structure",
+            "members": {
+                "Index": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based index of the document in the input list.</p>"
+                    }
+                },
+                "SyntaxTokens": {
+                    "target": "com.amazonaws.comprehend#ListOfSyntaxTokens",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The syntax tokens for the words in the document, one token for each word.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The result of calling the  operation. The\n      operation returns one object that is successfully processed by the operation.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectSyntaxRequest": {
+            "type": "structure",
+            "members": {
+                "TextList": {
+                    "target": "com.amazonaws.comprehend#CustomerInputStringList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25\n      documents. The maximum size for each document is 5 KB.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#SyntaxLanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. You can specify any of the following languages\n      supported by Amazon Comprehend: German (\"de\"), English (\"en\"), Spanish (\"es\"), French (\"fr\"),\n      Italian (\"it\"), or Portuguese (\"pt\"). All documents must be in the same language.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectSyntaxResponse": {
+            "type": "structure",
+            "members": {
+                "ResultList": {
+                    "target": "com.amazonaws.comprehend#ListOfDetectSyntaxResult",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list of  objects containing the\n      results of the operation. The results are sorted in ascending order by the <code>Index</code>\n      field and match the order of the documents in the input list. If all of the documents contain\n      an error, the <code>ResultList</code> is empty.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ErrorList": {
+                    "target": "com.amazonaws.comprehend#BatchItemErrorList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing one  object for each document that\n      contained an error. The results are sorted in ascending order by the <code>Index</code> field\n      and match the order of the documents in the input list. If there are no errors in the batch,\n      the <code>ErrorList</code> is empty.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {},
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectTargetedSentiment": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#BatchDetectTargetedSentimentRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#BatchDetectTargetedSentimentResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#BatchSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Inspects a batch of documents and returns a sentiment analysis\n      for each entity identified in the documents.</p>\n         <p>For more information about targeted sentiment, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-targeted-sentiment.html\">Targeted sentiment</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectTargetedSentimentItemResult": {
+            "type": "structure",
+            "members": {
+                "Index": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based index of this result in the input list.</p>"
+                    }
+                },
+                "Entities": {
+                    "target": "com.amazonaws.comprehend#ListOfTargetedSentimentEntities",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An array of targeted sentiment entities.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Analysis results for one of the documents in the batch.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectTargetedSentimentRequest": {
+            "type": "structure",
+            "members": {
+                "TextList": {
+                    "target": "com.amazonaws.comprehend#CustomerInputStringList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the UTF-8 encoded text of the input documents.\n      The list can contain a maximum of 25 documents. The maximum size of each document is 5 KB.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. Currently, English is the only supported language.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#BatchDetectTargetedSentimentResponse": {
+            "type": "structure",
+            "members": {
+                "ResultList": {
+                    "target": "com.amazonaws.comprehend#ListOfDetectTargetedSentimentResult",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list of objects containing the results of the operation.\n      The results are sorted in ascending order by the <code>Index</code> field and match the order of the documents in the input list.\n      If all of the documents contain an error, the <code>ResultList</code> is empty.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ErrorList": {
+                    "target": "com.amazonaws.comprehend#BatchItemErrorList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>List of errors that the operation can return.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {},
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#BatchItemError": {
+            "type": "structure",
+            "members": {
+                "Index": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based index of the document in the input list.</p>"
+                    }
+                },
+                "ErrorCode": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The numeric error code of the error.</p>"
+                    }
+                },
+                "ErrorMessage": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A text description of the error.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Describes an error that occurred while processing a document in a batch. The operation\n      returns on <code>BatchItemError</code> object for each document that contained an\n      error.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#BatchItemErrorList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#BatchItemError"
+            }
+        },
+        "com.amazonaws.comprehend#BatchSizeLimitExceededException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The number of documents in the request exceeds the limit of 25. Try your request again\n      with fewer documents.</p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 400
+            }
+        },
+        "com.amazonaws.comprehend#Block": {
+            "type": "structure",
+            "members": {
+                "Id": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Unique identifier for the block.</p>"
+                    }
+                },
+                "BlockType": {
+                    "target": "com.amazonaws.comprehend#BlockType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The block represents a line of text or one word of text.</p>\n         <ul>\n            <li>\n               <p>WORD - A word that's detected on a document page.\n        A word is one or more ISO basic Latin script characters that aren't separated by spaces.</p>\n            </li>\n            <li>\n               <p>LINE - A string of tab-delimited, contiguous words\n        that are detected on a document page</p>\n            </li>\n         </ul>"
+                    }
+                },
+                "Text": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The word or line of text extracted from the block.</p>"
+                    }
+                },
+                "Page": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Page number where the block appears.</p>"
+                    }
+                },
+                "Geometry": {
+                    "target": "com.amazonaws.comprehend#Geometry",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Co-ordinates of the rectangle or polygon that contains the text.</p>"
+                    }
+                },
+                "Relationships": {
+                    "target": "com.amazonaws.comprehend#ListOfRelationships",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list of child blocks of the current block.\n      For example, a LINE object has child blocks for each WORD block that's part of the line of text. </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Information about each word or line of text in the input document.</p>\n         <p>For additional information, see <a href=\"https://docs.aws.amazon.com/textract/latest/dg/API_Block.html\">Block</a> in the Amazon Textract API reference.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#BlockReference": {
+            "type": "structure",
+            "members": {
+                "BlockId": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Unique identifier for the block.</p>"
+                    }
+                },
+                "BeginOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Offset of the start of the block within its parent block.</p>"
+                    }
+                },
+                "EndOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Offset of the end of the block within its parent block.</p>"
+                    }
+                },
+                "ChildBlocks": {
+                    "target": "com.amazonaws.comprehend#ListOfChildBlocks",
+                    "traits": {
+                        "smithy.api#documentation": "<p>List of child blocks within this block.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>A reference to a block. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#BlockType": {
+            "type": "enum",
+            "members": {
+                "LINE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "LINE"
+                    }
+                },
+                "WORD": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "WORD"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#BoundingBox": {
+            "type": "structure",
+            "members": {
+                "Height": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The height of the bounding box as a ratio of the overall document page height.</p>"
+                    }
+                },
+                "Left": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The left coordinate of the bounding box as a ratio of overall document page width.</p>"
+                    }
+                },
+                "Top": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The top coordinate of the bounding box as a ratio of overall document page height.</p>"
+                    }
+                },
+                "Width": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The width of the bounding box as a ratio of the overall document page width.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The bounding box around the detected page\n     or around an element on a document page.\n    The left (x-coordinate) and top (y-coordinate) are coordinates that\n      represent the top and left sides of the bounding box. Note that the upper-left\n      corner of the image is the origin (0,0). </p>\n         <p>For additional information, see <a href=\"https://docs.aws.amazon.com/textract/latest/dg/API_BoundingBox.html\">BoundingBox</a> in the Amazon Textract API reference.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#ChildBlock": {
+            "type": "structure",
+            "members": {
+                "ChildBlockId": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Unique identifier for the child block.</p>"
+                    }
+                },
+                "BeginOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Offset of the start of the child block within its parent block.</p>"
+                    }
+                },
+                "EndOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Offset of the end of the child block within its parent block.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Nested block contained within a block.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#ClassifierEvaluationMetrics": {
+            "type": "structure",
+            "members": {
+                "Accuracy": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The fraction of the labels that were correct recognized. It is computed by dividing the\n      number of labels in the test documents that were correctly recognized by the total number of\n      labels in the test documents.</p>"
+                    }
+                },
+                "Precision": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A measure of the usefulness of the classifier results in the test data. High precision\n      means that the classifier returned substantially more relevant results than irrelevant\n      ones.</p>"
+                    }
+                },
+                "Recall": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A measure of how complete the classifier results are for the test data. High recall means\n      that the classifier returned most of the relevant results. </p>"
+                    }
+                },
+                "F1Score": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A measure of how accurate the classifier results are for the test data. It is derived from\n      the <code>Precision</code> and <code>Recall</code> values. The <code>F1Score</code> is the\n      harmonic average of the two scores. The highest score is 1, and the worst score is 0. </p>"
+                    }
+                },
+                "MicroPrecision": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A measure of the usefulness of the recognizer results in the test data. High precision\n      means that the recognizer returned substantially more relevant results than irrelevant ones.\n      Unlike the Precision metric which comes from averaging the precision of all available labels,\n      this is based on the overall score of all precision scores added together.</p>"
+                    }
+                },
+                "MicroRecall": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A measure of how complete the classifier results are for the test data. High recall means\n      that the classifier returned most of the relevant results. Specifically, this indicates how\n      many of the correct categories in the text that the model can predict. It is a percentage of\n      correct categories in the text that can found. Instead of averaging the recall scores of all\n      labels (as with Recall), micro Recall is based on the overall score of all recall scores added\n      together.</p>"
+                    }
+                },
+                "MicroF1Score": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A measure of how accurate the classifier results are for the test data. It is a\n      combination of the <code>Micro Precision</code> and <code>Micro Recall</code> values. The\n        <code>Micro F1Score</code> is the harmonic mean of the two scores. The highest score is 1,\n      and the worst score is 0.</p>"
+                    }
+                },
+                "HammingLoss": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Indicates the fraction of labels that are incorrectly predicted. Also seen as the fraction\n      of wrong labels compared to the total number of labels. Scores closer to zero are\n      better.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Describes the result metrics for the test data associated with an documentation\n      classifier.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#ClassifierMetadata": {
+            "type": "structure",
+            "members": {
+                "NumberOfLabels": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The number of labels in the input data. </p>"
+                    }
+                },
+                "NumberOfTrainedDocuments": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The number of documents in the input data that were used to train the classifier.\n      Typically this is 80 to 90 percent of the input documents.</p>"
+                    }
+                },
+                "NumberOfTestDocuments": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The number of documents in the input data that were used to test the classifier. Typically\n      this is 10 to 20 percent of the input documents, up to 10,000 documents.</p>"
+                    }
+                },
+                "EvaluationMetrics": {
+                    "target": "com.amazonaws.comprehend#ClassifierEvaluationMetrics",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Describes the result metrics for the test data associated with an documentation\n      classifier.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information about a document classifier.</p>",
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#ClassifyDocument": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ClassifyDocumentRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ClassifyDocumentResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceUnavailableException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Creates a classification request to analyze a single document in real-time. <code>ClassifyDocument</code> \n      supports the following model types:</p>\n         <ul>\n            <li>\n               <p>Custom classifier - a custom model that you have created and trained. \n        For input, you can provide plain text, a single-page document (PDF, Word, or image), or \n        Amazon Textract API output. For more information, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-document-classification.html\">Custom classification</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>\n            </li>\n            <li>\n               <p>Prompt safety classifier - Amazon Comprehend provides a pre-trained model for classifying \n        input prompts for generative AI applications. \n        For input, you provide English plain text input.\n        For prompt safety classification, the response includes only the <code>Classes</code> field.\n        For more information about prompt safety classifiers, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/trust-safety.html#prompt-classification\">Prompt safety classification</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>\n            </li>\n         </ul>\n         <p>If the system detects errors while processing a page in the input document,\n      the API response includes an <code>Errors</code> field that describes the errors.</p>\n         <p>If the system detects a document-level error in your input document, the API returns an\n      <code>InvalidRequestException</code> error response.\n      For details about this exception, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/idp-inputs-sync-err.html\">\n        Errors in semi-structured documents</a> in the Comprehend Developer Guide.\n    </p>"
+            }
+        },
+        "com.amazonaws.comprehend#ClassifyDocumentRequest": {
+            "type": "structure",
+            "members": {
+                "Text": {
+                    "target": "com.amazonaws.comprehend#CustomerInputString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The document text to be analyzed. If you enter text using this parameter,\n      do not use the <code>Bytes</code> parameter.</p>"
+                    }
+                },
+                "EndpointArn": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierEndpointArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the endpoint. </p>\n         <p>For prompt safety classification, Amazon Comprehend provides the endpoint ARN. For more information about prompt safety classifiers, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/trust-safety.html#prompt-classification\">Prompt safety classification</a> in the <i>Amazon Comprehend Developer Guide</i>\n         </p>\n         <p>For custom classification, you create an endpoint for your custom model. For more information, \n      see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/using-endpoints.html\">Using Amazon Comprehend endpoints</a>.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "Bytes": {
+                    "target": "com.amazonaws.comprehend#SemiStructuredDocumentBlob",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Use the <code>Bytes</code> parameter to input a text, PDF, Word or image file.</p>\n         <p>When you classify a document using a custom model, you can also use the <code>Bytes</code> parameter to input an Amazon Textract <code>DetectDocumentText</code>\n        or <code>AnalyzeDocument</code> output file.</p>\n         <p>To classify a document using the prompt safety classifier, use the <code>Text</code> parameter for input.</p>\n         <p>Provide the input document as a sequence of base64-encoded bytes.\n      If your code uses an Amazon Web Services SDK to classify documents, the SDK may encode\n      the document file bytes for you. </p>\n         <p>The maximum length of this field depends on the input document type. For details, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/idp-inputs-sync.html\">\n        Inputs for real-time custom analysis</a> in the Comprehend Developer Guide. </p>\n         <p>If you use the <code>Bytes</code> parameter, do not use the <code>Text</code> parameter.</p>"
+                    }
+                },
+                "DocumentReaderConfig": {
+                    "target": "com.amazonaws.comprehend#DocumentReaderConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Provides configuration parameters to override the default actions for extracting text\n      from PDF documents and image files.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ClassifyDocumentResponse": {
+            "type": "structure",
+            "members": {
+                "Classes": {
+                    "target": "com.amazonaws.comprehend#ListOfClasses",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The classes used by the document being analyzed. These are used for models trained in multi-class mode.\n      Individual classes are mutually exclusive and each document is expected to have only a\n      single class assigned to it. For example, an animal can be a dog or a cat, but not both at the\n      same time. </p>\n         <p>For prompt safety classification, the response includes only two classes (SAFE_PROMPT and UNSAFE_PROMPT), \n      along with a confidence score for each class. The value range of the score is zero to one, where one is the highest confidence.</p>"
+                    }
+                },
+                "Labels": {
+                    "target": "com.amazonaws.comprehend#ListOfLabels",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The labels used in the document being analyzed. These are used for multi-label trained\n      models. Individual labels represent different categories that are related in some manner and\n      are not mutually exclusive. For example, a movie can be just an action movie, or it can be an\n      action movie, a science fiction movie, and a comedy, all at the same time. </p>"
+                    }
+                },
+                "DocumentMetadata": {
+                    "target": "com.amazonaws.comprehend#DocumentMetadata",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Extraction information about the document. This field is present\n      in the response only if your request includes the <code>Byte</code> parameter. </p>"
+                    }
+                },
+                "DocumentType": {
+                    "target": "com.amazonaws.comprehend#ListOfDocumentType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The document type for each page in the input document. This field is present\n      in the response only if your request includes the <code>Byte</code> parameter. </p>"
+                    }
+                },
+                "Errors": {
+                    "target": "com.amazonaws.comprehend#ListOfErrors",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Page-level errors that the system detected while processing the input document.\n      The field is empty if the system encountered no errors.</p>"
+                    }
+                },
+                "Warnings": {
+                    "target": "com.amazonaws.comprehend#ListOfWarnings",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Warnings detected while processing the input document.\n      The response includes a warning if there is a mismatch between the input document type \n      and the model type associated with the endpoint that you specified. The response can also include\n       warnings for individual pages that have a mismatch. </p>\n         <p>The field is empty if the system generated no warnings.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {},
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#ClientRequestTokenString": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 64
+                },
+                "smithy.api#pattern": "^[a-zA-Z0-9-]+$"
+            }
+        },
+        "com.amazonaws.comprehend#ComprehendArn": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 256
+                },
+                "smithy.api#pattern": "^arn:aws(-[^:]+)?:comprehend:[a-zA-Z0-9-]*:[0-9]{12}:[a-zA-Z0-9-]{1,64}/[a-zA-Z0-9](-*[a-zA-Z0-9])*((/dataset/[a-zA-Z0-9](-*[a-zA-Z0-9])*)|(/version/[a-zA-Z0-9](-*[a-zA-Z0-9])*))?$"
+            }
+        },
+        "com.amazonaws.comprehend#ComprehendArnName": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 63
+                },
+                "smithy.api#pattern": "^[a-zA-Z0-9](-*[a-zA-Z0-9])*$"
+            }
+        },
+        "com.amazonaws.comprehend#ComprehendDatasetArn": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 256
+                },
+                "smithy.api#pattern": "^arn:aws(-[^:]+)?:comprehend:[a-zA-Z0-9-]*:[0-9]{12}:flywheel/[a-zA-Z0-9](-*[a-zA-Z0-9])*/dataset/[a-zA-Z0-9](-*[a-zA-Z0-9])*$"
+            }
+        },
+        "com.amazonaws.comprehend#ComprehendEndpointArn": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 256
+                },
+                "smithy.api#pattern": "^arn:aws(-[^:]+)?:comprehend:[a-zA-Z0-9-]*:[0-9]{12}:(document-classifier-endpoint|entity-recognizer-endpoint)/[a-zA-Z0-9](-*[a-zA-Z0-9])*$"
+            }
+        },
+        "com.amazonaws.comprehend#ComprehendEndpointName": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 40
+                },
+                "smithy.api#pattern": "^[a-zA-Z0-9](-*[a-zA-Z0-9])*$"
+            }
+        },
+        "com.amazonaws.comprehend#ComprehendFlywheelArn": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 256
+                },
+                "smithy.api#pattern": "^arn:aws(-[^:]+)?:comprehend:[a-zA-Z0-9-]*:[0-9]{12}:flywheel/[a-zA-Z0-9](-*[a-zA-Z0-9])*$"
+            }
+        },
+        "com.amazonaws.comprehend#ComprehendModelArn": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 256
+                },
+                "smithy.api#pattern": "^arn:aws(-[^:]+)?:comprehend:[a-zA-Z0-9-]*:[0-9]{12}:(document-classifier|entity-recognizer)/[a-zA-Z0-9](-*[a-zA-Z0-9])*(/version/[a-zA-Z0-9](-*[a-zA-Z0-9])*)?$"
+            }
+        },
+        "com.amazonaws.comprehend#Comprehend_20171127": {
+            "type": "service",
+            "version": "2017-11-27",
+            "operations": [
+                {
+                    "target": "com.amazonaws.comprehend#BatchDetectDominantLanguage"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#BatchDetectEntities"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#BatchDetectKeyPhrases"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#BatchDetectSentiment"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#BatchDetectSyntax"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#BatchDetectTargetedSentiment"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ClassifyDocument"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ContainsPiiEntities"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#CreateDataset"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#CreateDocumentClassifier"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#CreateEndpoint"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#CreateEntityRecognizer"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#CreateFlywheel"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DeleteDocumentClassifier"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DeleteEndpoint"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DeleteEntityRecognizer"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DeleteFlywheel"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DeleteResourcePolicy"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeDataset"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeDocumentClassificationJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeDocumentClassifier"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeDominantLanguageDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeEndpoint"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeEntitiesDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeEntityRecognizer"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeEventsDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeFlywheel"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeFlywheelIteration"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeKeyPhrasesDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribePiiEntitiesDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeResourcePolicy"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeSentimentDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeTargetedSentimentDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DescribeTopicsDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DetectDominantLanguage"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DetectEntities"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DetectKeyPhrases"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DetectPiiEntities"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DetectSentiment"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DetectSyntax"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DetectTargetedSentiment"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#DetectToxicContent"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ImportModel"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListDatasets"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListDocumentClassificationJobs"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListDocumentClassifiers"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListDocumentClassifierSummaries"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListDominantLanguageDetectionJobs"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListEndpoints"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListEntitiesDetectionJobs"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListEntityRecognizers"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListEntityRecognizerSummaries"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListEventsDetectionJobs"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListFlywheelIterationHistory"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListFlywheels"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListKeyPhrasesDetectionJobs"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListPiiEntitiesDetectionJobs"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListSentimentDetectionJobs"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListTagsForResource"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListTargetedSentimentDetectionJobs"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ListTopicsDetectionJobs"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#PutResourcePolicy"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StartDocumentClassificationJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StartDominantLanguageDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StartEntitiesDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StartEventsDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StartFlywheelIteration"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StartKeyPhrasesDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StartPiiEntitiesDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StartSentimentDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StartTargetedSentimentDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StartTopicsDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StopDominantLanguageDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StopEntitiesDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StopEventsDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StopKeyPhrasesDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StopPiiEntitiesDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StopSentimentDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StopTargetedSentimentDetectionJob"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StopTrainingDocumentClassifier"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#StopTrainingEntityRecognizer"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TagResource"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UntagResource"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UpdateEndpoint"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UpdateFlywheel"
+                }
+            ],
+            "traits": {
+                "aws.api#service": {
+                    "sdkId": "Comprehend",
+                    "arnNamespace": "comprehend",
+                    "cloudFormationName": "Comprehend",
+                    "cloudTrailEventSource": "comprehend.amazonaws.com",
+                    "endpointPrefix": "comprehend"
+                },
+                "aws.auth#sigv4": {
+                    "name": "comprehend"
+                },
+                "aws.protocols#awsJson1_1": {},
+                "smithy.api#documentation": "<p>Amazon Comprehend is an Amazon Web Services service for gaining insight into the content of documents.\n      Use these actions to determine the topics contained in your documents, the topics they\n      discuss, the predominant sentiment expressed in them, the predominant language used, and\n      more.</p>",
+                "smithy.api#title": "Amazon Comprehend",
+                "smithy.rules#endpointBdd": {
+                    "version": "1.1",
+                    "parameters": {
+                        "Region": {
+                            "builtIn": "AWS::Region",
+                            "required": false,
+                            "documentation": "The AWS region used to dispatch the request.",
+                            "type": "string"
+                        },
+                        "UseDualStack": {
+                            "builtIn": "AWS::UseDualStack",
+                            "required": true,
+                            "default": false,
+                            "documentation": "When true, use the dual-stack endpoint. If the configured endpoint does not support dual-stack, dispatching the request MAY return an error.",
+                            "type": "boolean"
+                        },
+                        "UseFIPS": {
+                            "builtIn": "AWS::UseFIPS",
+                            "required": true,
+                            "default": false,
+                            "documentation": "When true, send this request to the FIPS-compliant regional endpoint. If the configured endpoint does not have a FIPS compliant endpoint, dispatching the request will return an error.",
+                            "type": "boolean"
+                        },
+                        "Endpoint": {
+                            "builtIn": "SDK::Endpoint",
+                            "required": false,
+                            "documentation": "Override the endpoint used to send this request",
+                            "type": "string"
+                        }
+                    },
+                    "conditions": [
+                        {
+                            "fn": "isSet",
+                            "argv": [
+                                {
+                                    "ref": "Endpoint"
+                                }
+                            ]
+                        },
+                        {
+                            "fn": "isSet",
+                            "argv": [
+                                {
+                                    "ref": "Region"
+                                }
+                            ]
+                        },
+                        {
+                            "fn": "aws.partition",
+                            "argv": [
+                                {
+                                    "ref": "Region"
+                                }
+                            ],
+                            "assign": "PartitionResult"
+                        },
+                        {
+                            "fn": "booleanEquals",
+                            "argv": [
+                                {
+                                    "ref": "UseFIPS"
+                                },
+                                true
+                            ]
+                        },
+                        {
+                            "fn": "booleanEquals",
+                            "argv": [
+                                {
+                                    "ref": "UseDualStack"
+                                },
+                                true
+                            ]
+                        },
+                        {
+                            "fn": "booleanEquals",
+                            "argv": [
+                                {
+                                    "fn": "getAttr",
+                                    "argv": [
+                                        {
+                                            "ref": "PartitionResult"
+                                        },
+                                        "supportsDualStack"
+                                    ]
+                                },
+                                true
+                            ]
+                        },
+                        {
+                            "fn": "booleanEquals",
+                            "argv": [
+                                {
+                                    "fn": "getAttr",
+                                    "argv": [
+                                        {
+                                            "ref": "PartitionResult"
+                                        },
+                                        "supportsFIPS"
+                                    ]
+                                },
+                                true
+                            ]
+                        }
+                    ],
+                    "results": [
+                        {
+                            "conditions": [],
+                            "error": "Invalid Configuration: FIPS and custom endpoint are not supported",
+                            "type": "error"
+                        },
+                        {
+                            "conditions": [],
+                            "error": "Invalid Configuration: Dualstack and custom endpoint are not supported",
+                            "type": "error"
+                        },
+                        {
+                            "conditions": [],
+                            "endpoint": {
+                                "url": {
+                                    "ref": "Endpoint"
+                                },
+                                "properties": {},
+                                "headers": {}
+                            },
+                            "type": "endpoint"
+                        },
+                        {
+                            "conditions": [],
+                            "endpoint": {
+                                "url": "https://comprehend-fips.{Region}.{PartitionResult#dualStackDnsSuffix}",
+                                "properties": {},
+                                "headers": {}
+                            },
+                            "type": "endpoint"
+                        },
+                        {
+                            "conditions": [],
+                            "error": "FIPS and DualStack are enabled, but this partition does not support one or both",
+                            "type": "error"
+                        },
+                        {
+                            "conditions": [],
+                            "endpoint": {
+                                "url": "https://comprehend-fips.{Region}.{PartitionResult#dnsSuffix}",
+                                "properties": {},
+                                "headers": {}
+                            },
+                            "type": "endpoint"
+                        },
+                        {
+                            "conditions": [],
+                            "error": "FIPS is enabled but this partition does not support FIPS",
+                            "type": "error"
+                        },
+                        {
+                            "conditions": [],
+                            "endpoint": {
+                                "url": "https://comprehend.{Region}.{PartitionResult#dualStackDnsSuffix}",
+                                "properties": {},
+                                "headers": {}
+                            },
+                            "type": "endpoint"
+                        },
+                        {
+                            "conditions": [],
+                            "error": "DualStack is enabled but this partition does not support DualStack",
+                            "type": "error"
+                        },
+                        {
+                            "conditions": [],
+                            "endpoint": {
+                                "url": "https://comprehend.{Region}.{PartitionResult#dnsSuffix}",
+                                "properties": {},
+                                "headers": {}
+                            },
+                            "type": "endpoint"
+                        },
+                        {
+                            "conditions": [],
+                            "error": "Invalid Configuration: Missing Region",
+                            "type": "error"
+                        }
+                    ],
+                    "root": 2,
+                    "nodeCount": 13,
+                    "nodes": "/////wAAAAH/////AAAAAAAAAAwAAAADAAAAAQAAAAQF9eELAAAAAgAAAAUF9eELAAAAAwAAAAgAAAAGAAAABAAAAAcF9eEKAAAABQX14QgF9eEJAAAABAAAAAoAAAAJAAAABgX14QYF9eEHAAAABQAAAAsF9eEFAAAABgX14QQF9eEFAAAAAwX14QEAAAANAAAABAX14QIF9eED"
+                },
+                "smithy.rules#endpointRuleSet": {
+                    "version": "1.0",
+                    "parameters": {
+                        "Region": {
+                            "builtIn": "AWS::Region",
+                            "required": false,
+                            "documentation": "The AWS region used to dispatch the request.",
+                            "type": "string"
+                        },
+                        "UseDualStack": {
+                            "builtIn": "AWS::UseDualStack",
+                            "required": true,
+                            "default": false,
+                            "documentation": "When true, use the dual-stack endpoint. If the configured endpoint does not support dual-stack, dispatching the request MAY return an error.",
+                            "type": "boolean"
+                        },
+                        "UseFIPS": {
+                            "builtIn": "AWS::UseFIPS",
+                            "required": true,
+                            "default": false,
+                            "documentation": "When true, send this request to the FIPS-compliant regional endpoint. If the configured endpoint does not have a FIPS compliant endpoint, dispatching the request will return an error.",
+                            "type": "boolean"
+                        },
+                        "Endpoint": {
+                            "builtIn": "SDK::Endpoint",
+                            "required": false,
+                            "documentation": "Override the endpoint used to send this request",
+                            "type": "string"
+                        }
+                    },
+                    "rules": [
+                        {
+                            "conditions": [
+                                {
+                                    "fn": "isSet",
+                                    "argv": [
+                                        {
+                                            "ref": "Endpoint"
+                                        }
+                                    ]
+                                }
+                            ],
+                            "rules": [
+                                {
+                                    "conditions": [
+                                        {
+                                            "fn": "booleanEquals",
+                                            "argv": [
+                                                {
+                                                    "ref": "UseFIPS"
+                                                },
+                                                true
+                                            ]
+                                        }
+                                    ],
+                                    "error": "Invalid Configuration: FIPS and custom endpoint are not supported",
+                                    "type": "error"
+                                },
+                                {
+                                    "conditions": [
+                                        {
+                                            "fn": "booleanEquals",
+                                            "argv": [
+                                                {
+                                                    "ref": "UseDualStack"
+                                                },
+                                                true
+                                            ]
+                                        }
+                                    ],
+                                    "error": "Invalid Configuration: Dualstack and custom endpoint are not supported",
+                                    "type": "error"
+                                },
+                                {
+                                    "conditions": [],
+                                    "endpoint": {
+                                        "url": {
+                                            "ref": "Endpoint"
+                                        },
+                                        "properties": {},
+                                        "headers": {}
+                                    },
+                                    "type": "endpoint"
+                                }
+                            ],
+                            "type": "tree"
+                        },
+                        {
+                            "conditions": [
+                                {
+                                    "fn": "isSet",
+                                    "argv": [
+                                        {
+                                            "ref": "Region"
+                                        }
+                                    ]
+                                }
+                            ],
+                            "rules": [
+                                {
+                                    "conditions": [
+                                        {
+                                            "fn": "aws.partition",
+                                            "argv": [
+                                                {
+                                                    "ref": "Region"
+                                                }
+                                            ],
+                                            "assign": "PartitionResult"
+                                        }
+                                    ],
+                                    "rules": [
+                                        {
+                                            "conditions": [
+                                                {
+                                                    "fn": "booleanEquals",
+                                                    "argv": [
+                                                        {
+                                                            "ref": "UseFIPS"
+                                                        },
+                                                        true
+                                                    ]
+                                                },
+                                                {
+                                                    "fn": "booleanEquals",
+                                                    "argv": [
+                                                        {
+                                                            "ref": "UseDualStack"
+                                                        },
+                                                        true
+                                                    ]
+                                                }
+                                            ],
+                                            "rules": [
+                                                {
+                                                    "conditions": [
+                                                        {
+                                                            "fn": "booleanEquals",
+                                                            "argv": [
+                                                                true,
+                                                                {
+                                                                    "fn": "getAttr",
+                                                                    "argv": [
+                                                                        {
+                                                                            "ref": "PartitionResult"
+                                                                        },
+                                                                        "supportsFIPS"
+                                                                    ]
+                                                                }
+                                                            ]
+                                                        },
+                                                        {
+                                                            "fn": "booleanEquals",
+                                                            "argv": [
+                                                                true,
+                                                                {
+                                                                    "fn": "getAttr",
+                                                                    "argv": [
+                                                                        {
+                                                                            "ref": "PartitionResult"
+                                                                        },
+                                                                        "supportsDualStack"
+                                                                    ]
+                                                                }
+                                                            ]
+                                                        }
+                                                    ],
+                                                    "rules": [
+                                                        {
+                                                            "conditions": [],
+                                                            "endpoint": {
+                                                                "url": "https://comprehend-fips.{Region}.{PartitionResult#dualStackDnsSuffix}",
+                                                                "properties": {},
+                                                                "headers": {}
+                                                            },
+                                                            "type": "endpoint"
+                                                        }
+                                                    ],
+                                                    "type": "tree"
+                                                },
+                                                {
+                                                    "conditions": [],
+                                                    "error": "FIPS and DualStack are enabled, but this partition does not support one or both",
+                                                    "type": "error"
+                                                }
+                                            ],
+                                            "type": "tree"
+                                        },
+                                        {
+                                            "conditions": [
+                                                {
+                                                    "fn": "booleanEquals",
+                                                    "argv": [
+                                                        {
+                                                            "ref": "UseFIPS"
+                                                        },
+                                                        true
+                                                    ]
+                                                }
+                                            ],
+                                            "rules": [
+                                                {
+                                                    "conditions": [
+                                                        {
+                                                            "fn": "booleanEquals",
+                                                            "argv": [
+                                                                {
+                                                                    "fn": "getAttr",
+                                                                    "argv": [
+                                                                        {
+                                                                            "ref": "PartitionResult"
+                                                                        },
+                                                                        "supportsFIPS"
+                                                                    ]
+                                                                },
+                                                                true
+                                                            ]
+                                                        }
+                                                    ],
+                                                    "rules": [
+                                                        {
+                                                            "conditions": [],
+                                                            "endpoint": {
+                                                                "url": "https://comprehend-fips.{Region}.{PartitionResult#dnsSuffix}",
+                                                                "properties": {},
+                                                                "headers": {}
+                                                            },
+                                                            "type": "endpoint"
+                                                        }
+                                                    ],
+                                                    "type": "tree"
+                                                },
+                                                {
+                                                    "conditions": [],
+                                                    "error": "FIPS is enabled but this partition does not support FIPS",
+                                                    "type": "error"
+                                                }
+                                            ],
+                                            "type": "tree"
+                                        },
+                                        {
+                                            "conditions": [
+                                                {
+                                                    "fn": "booleanEquals",
+                                                    "argv": [
+                                                        {
+                                                            "ref": "UseDualStack"
+                                                        },
+                                                        true
+                                                    ]
+                                                }
+                                            ],
+                                            "rules": [
+                                                {
+                                                    "conditions": [
+                                                        {
+                                                            "fn": "booleanEquals",
+                                                            "argv": [
+                                                                true,
+                                                                {
+                                                                    "fn": "getAttr",
+                                                                    "argv": [
+                                                                        {
+                                                                            "ref": "PartitionResult"
+                                                                        },
+                                                                        "supportsDualStack"
+                                                                    ]
+                                                                }
+                                                            ]
+                                                        }
+                                                    ],
+                                                    "rules": [
+                                                        {
+                                                            "conditions": [],
+                                                            "endpoint": {
+                                                                "url": "https://comprehend.{Region}.{PartitionResult#dualStackDnsSuffix}",
+                                                                "properties": {},
+                                                                "headers": {}
+                                                            },
+                                                            "type": "endpoint"
+                                                        }
+                                                    ],
+                                                    "type": "tree"
+                                                },
+                                                {
+                                                    "conditions": [],
+                                                    "error": "DualStack is enabled but this partition does not support DualStack",
+                                                    "type": "error"
+                                                }
+                                            ],
+                                            "type": "tree"
+                                        },
+                                        {
+                                            "conditions": [],
+                                            "endpoint": {
+                                                "url": "https://comprehend.{Region}.{PartitionResult#dnsSuffix}",
+                                                "properties": {},
+                                                "headers": {}
+                                            },
+                                            "type": "endpoint"
+                                        }
+                                    ],
+                                    "type": "tree"
+                                }
+                            ],
+                            "type": "tree"
+                        },
+                        {
+                            "conditions": [],
+                            "error": "Invalid Configuration: Missing Region",
+                            "type": "error"
+                        }
+                    ]
+                },
+                "smithy.rules#endpointTests": {
+                    "testCases": [
+                        {
+                            "documentation": "For region ap-northeast-1 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.ap-northeast-1.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "ap-northeast-1",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region ap-northeast-2 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.ap-northeast-2.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "ap-northeast-2",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region ap-south-1 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.ap-south-1.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "ap-south-1",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region ap-southeast-1 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.ap-southeast-1.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "ap-southeast-1",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region ap-southeast-2 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.ap-southeast-2.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "ap-southeast-2",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region ca-central-1 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.ca-central-1.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "ca-central-1",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region eu-central-1 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.eu-central-1.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "eu-central-1",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region eu-west-1 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.eu-west-1.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "eu-west-1",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region eu-west-2 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.eu-west-2.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "eu-west-2",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-east-1 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.us-east-1.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-east-1",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-east-1 with FIPS enabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend-fips.us-east-1.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-east-1",
+                                "UseFIPS": true,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-east-2 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.us-east-2.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-east-2",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-east-2 with FIPS enabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend-fips.us-east-2.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-east-2",
+                                "UseFIPS": true,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-west-2 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.us-west-2.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-west-2",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-west-2 with FIPS enabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend-fips.us-west-2.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-west-2",
+                                "UseFIPS": true,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-east-1 with FIPS enabled and DualStack enabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend-fips.us-east-1.api.aws"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-east-1",
+                                "UseFIPS": true,
+                                "UseDualStack": true
+                            }
+                        },
+                        {
+                            "documentation": "For region us-east-1 with FIPS disabled and DualStack enabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.us-east-1.api.aws"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-east-1",
+                                "UseFIPS": false,
+                                "UseDualStack": true
+                            }
+                        },
+                        {
+                            "documentation": "For region cn-north-1 with FIPS enabled and DualStack enabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend-fips.cn-north-1.api.amazonwebservices.com.cn"
+                                }
+                            },
+                            "params": {
+                                "Region": "cn-north-1",
+                                "UseFIPS": true,
+                                "UseDualStack": true
+                            }
+                        },
+                        {
+                            "documentation": "For region cn-north-1 with FIPS enabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend-fips.cn-north-1.amazonaws.com.cn"
+                                }
+                            },
+                            "params": {
+                                "Region": "cn-north-1",
+                                "UseFIPS": true,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region cn-north-1 with FIPS disabled and DualStack enabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.cn-north-1.api.amazonwebservices.com.cn"
+                                }
+                            },
+                            "params": {
+                                "Region": "cn-north-1",
+                                "UseFIPS": false,
+                                "UseDualStack": true
+                            }
+                        },
+                        {
+                            "documentation": "For region cn-north-1 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.cn-north-1.amazonaws.com.cn"
+                                }
+                            },
+                            "params": {
+                                "Region": "cn-north-1",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-gov-west-1 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.us-gov-west-1.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-gov-west-1",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-gov-west-1 with FIPS enabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend-fips.us-gov-west-1.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-gov-west-1",
+                                "UseFIPS": true,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-gov-east-1 with FIPS enabled and DualStack enabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend-fips.us-gov-east-1.api.aws"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-gov-east-1",
+                                "UseFIPS": true,
+                                "UseDualStack": true
+                            }
+                        },
+                        {
+                            "documentation": "For region us-gov-east-1 with FIPS enabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend-fips.us-gov-east-1.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-gov-east-1",
+                                "UseFIPS": true,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-gov-east-1 with FIPS disabled and DualStack enabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.us-gov-east-1.api.aws"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-gov-east-1",
+                                "UseFIPS": false,
+                                "UseDualStack": true
+                            }
+                        },
+                        {
+                            "documentation": "For region us-gov-east-1 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.us-gov-east-1.amazonaws.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-gov-east-1",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-iso-east-1 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.us-iso-east-1.c2s.ic.gov"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-iso-east-1",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-iso-east-1 with FIPS enabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend-fips.us-iso-east-1.c2s.ic.gov"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-iso-east-1",
+                                "UseFIPS": true,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-isob-east-1 with FIPS enabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend-fips.us-isob-east-1.sc2s.sgov.gov"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-isob-east-1",
+                                "UseFIPS": true,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For region us-isob-east-1 with FIPS disabled and DualStack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://comprehend.us-isob-east-1.sc2s.sgov.gov"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-isob-east-1",
+                                "UseFIPS": false,
+                                "UseDualStack": false
+                            }
+                        },
+                        {
+                            "documentation": "For custom endpoint with region set and fips disabled and dualstack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://example.com"
+                                }
+                            },
+                            "params": {
+                                "Region": "us-east-1",
+                                "UseFIPS": false,
+                                "UseDualStack": false,
+                                "Endpoint": "https://example.com"
+                            }
+                        },
+                        {
+                            "documentation": "For custom endpoint with region not set and fips disabled and dualstack disabled",
+                            "expect": {
+                                "endpoint": {
+                                    "url": "https://example.com"
+                                }
+                            },
+                            "params": {
+                                "UseFIPS": false,
+                                "UseDualStack": false,
+                                "Endpoint": "https://example.com"
+                            }
+                        },
+                        {
+                            "documentation": "For custom endpoint with fips enabled and dualstack disabled",
+                            "expect": {
+                                "error": "Invalid Configuration: FIPS and custom endpoint are not supported"
+                            },
+                            "params": {
+                                "Region": "us-east-1",
+                                "UseFIPS": true,
+                                "UseDualStack": false,
+                                "Endpoint": "https://example.com"
+                            }
+                        },
+                        {
+                            "documentation": "For custom endpoint with fips disabled and dualstack enabled",
+                            "expect": {
+                                "error": "Invalid Configuration: Dualstack and custom endpoint are not supported"
+                            },
+                            "params": {
+                                "Region": "us-east-1",
+                                "UseFIPS": false,
+                                "UseDualStack": true,
+                                "Endpoint": "https://example.com"
+                            }
+                        },
+                        {
+                            "documentation": "Missing region",
+                            "expect": {
+                                "error": "Invalid Configuration: Missing Region"
+                            }
+                        }
+                    ],
+                    "version": "1.0"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ConcurrentModificationException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Concurrent modification of the tags associated with an Amazon Comprehend resource is not\n      supported. </p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 400
+            }
+        },
+        "com.amazonaws.comprehend#ContainsPiiEntities": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ContainsPiiEntitiesRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ContainsPiiEntitiesResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Analyzes input text for the presence of personally identifiable information (PII) and\n      returns the labels of identified PII entity types such as name, address, bank account number,\n      or phone number.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#ContainsPiiEntitiesRequest": {
+            "type": "structure",
+            "members": {
+                "Text": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A UTF-8 text string. The maximum string size is 100 KB.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ContainsPiiEntitiesResponse": {
+            "type": "structure",
+            "members": {
+                "Labels": {
+                    "target": "com.amazonaws.comprehend#ListOfEntityLabels",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The labels used in the document being analyzed. Individual labels represent personally\n      identifiable information (PII) entity types.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#CreateDataset": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#CreateDatasetRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#CreateDatasetResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Creates a dataset to upload training or test data for a model associated with a flywheel.\n      For more information about datasets, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/flywheels-about.html\">\n      Flywheel overview</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#CreateDatasetRequest": {
+            "type": "structure",
+            "members": {
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel of the flywheel to receive the data.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DatasetName": {
+                    "target": "com.amazonaws.comprehend#ComprehendArnName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Name of the dataset.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DatasetType": {
+                    "target": "com.amazonaws.comprehend#DatasetType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The dataset type. You can specify that the data in a dataset is for training\n      the model or for testing the model.</p>"
+                    }
+                },
+                "Description": {
+                    "target": "com.amazonaws.comprehend#Description",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Description of the dataset.</p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#DatasetInputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Information about the input data configuration. The type of input data varies based\n      on the format of the input and whether the data is for a classifier model or an entity recognition model.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A unique identifier for the request. If you don't set the client request token, Amazon\n      Comprehend generates one.</p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags for the dataset.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#CreateDatasetResponse": {
+            "type": "structure",
+            "members": {
+                "DatasetArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendDatasetArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The ARN of the dataset.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#CreateDocumentClassifier": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#CreateDocumentClassifierRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#CreateDocumentClassifierResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Creates a new document classifier that you can use to categorize documents. To create a\n      classifier, you provide a set of training documents that are labeled with the categories that you\n      want to use. For more information, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/training-classifier-model.html\">Training classifier models</a> \n      in the Comprehend Developer Guide.\n    </p>"
+            }
+        },
+        "com.amazonaws.comprehend#CreateDocumentClassifierRequest": {
+            "type": "structure",
+            "members": {
+                "DocumentClassifierName": {
+                    "target": "com.amazonaws.comprehend#ComprehendArnName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name of the document classifier.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "VersionName": {
+                    "target": "com.amazonaws.comprehend#VersionName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The version name given to the newly created classifier. Version names can have a maximum\n      of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The\n      version name must be unique among all models with the same classifier name in the Amazon Web Services account/Amazon Web Services Region.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags to associate with the document classifier. A tag is a key-value\n      pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with\n      \"Sales\" as the key might be added to a resource to indicate its use by the sales department.\n    </p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierInputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the format and location of the input data for the job.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierOutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the location for the output files from a custom classifier job.\n      This parameter is required for a request that creates a native document model.</p>"
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A unique identifier for the request. If you don't set the client request token, Amazon\n      Comprehend generates one.</p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. You can specify any of the languages\n      supported by Amazon Comprehend. All documents must be in the same language.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Configuration parameters for an optional private Virtual Private Cloud (VPC) containing\n      the resources you are using for your custom classifier. For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                },
+                "Mode": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierMode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Indicates the mode in which the classifier will be trained. The classifier can be trained\n      in multi-class (single-label) mode or multi-label mode. \n      Multi-class mode identifies a single class label for each document and\n      multi-label mode identifies one or more class labels for each document. Multiple\n      labels for an individual document are separated by a delimiter. The default delimiter between\n      labels is a pipe (|).</p>"
+                    }
+                },
+                "ModelKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the KMS key that Amazon Comprehend uses to encrypt\n      trained custom models. The ModelKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "ModelPolicy": {
+                    "target": "com.amazonaws.comprehend#Policy",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The resource-based policy to attach to your custom document classifier model. You can use\n      this policy to allow another Amazon Web Services account to import your custom model.</p>\n         <p>Provide your policy as a JSON body that you enter as a UTF-8 encoded string without line\n      breaks. To provide valid JSON, enclose the attribute names and values in double quotes. If the\n      JSON body is also enclosed in double quotes, then you must escape the double quotes that are\n      inside the policy:</p>\n         <p>\n            <code>\"{\\\"attribute\\\": \\\"value\\\", \\\"attribute\\\": [\\\"value\\\"]}\"</code>\n         </p>\n         <p>To avoid escaping quotes, you can use single quotes to enclose the policy and double\n      quotes to enclose the JSON names and values:</p>\n         <p>\n            <code>'{\"attribute\": \"value\", \"attribute\": [\"value\"]}'</code>\n         </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#CreateDocumentClassifierResponse": {
+            "type": "structure",
+            "members": {
+                "DocumentClassifierArn": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) that identifies the document classifier.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#CreateEndpoint": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#CreateEndpointRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#CreateEndpointResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceUnavailableException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Creates a model-specific endpoint for synchronous inference for a previously trained\n      custom model \n      For information about endpoints, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/manage-endpoints.html\">Managing endpoints</a>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#CreateEndpointRequest": {
+            "type": "structure",
+            "members": {
+                "EndpointName": {
+                    "target": "com.amazonaws.comprehend#ComprehendEndpointName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>This is the descriptive suffix that becomes part of the <code>EndpointArn</code> used for\n      all subsequent requests to this resource. </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the model to which the endpoint will be\n      attached.</p>"
+                    }
+                },
+                "DesiredInferenceUnits": {
+                    "target": "com.amazonaws.comprehend#InferenceUnitsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p> The desired number of inference units to be used by the model using this endpoint.\n      \n      Each inference unit represents of a throughput of 100 characters per second.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An idempotency token provided by the customer. If this token matches a previous endpoint\n      creation request, Amazon Comprehend will not return a <code>ResourceInUseException</code>.\n    </p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags to associate with the endpoint. A tag is a key-value pair that adds\n      metadata to the endpoint. For example, a tag with \"Sales\" as the key might be added to an\n      endpoint to indicate its use by the sales department. </p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to trained custom models encrypted with a customer\n      managed key (ModelKmsKeyId).</p>"
+                    }
+                },
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel to which the endpoint will be\n      attached.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#CreateEndpointResponse": {
+            "type": "structure",
+            "members": {
+                "EndpointArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendEndpointArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the endpoint being created.</p>"
+                    }
+                },
+                "ModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the model to which the endpoint is\n      attached.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#CreateEntityRecognizer": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#CreateEntityRecognizerRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#CreateEntityRecognizerResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Creates an entity recognizer using submitted files. After your\n        <code>CreateEntityRecognizer</code> request is submitted, you can check job status using the\n        <code>DescribeEntityRecognizer</code> API. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#CreateEntityRecognizerRequest": {
+            "type": "structure",
+            "members": {
+                "RecognizerName": {
+                    "target": "com.amazonaws.comprehend#ComprehendArnName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name given to the newly created recognizer. Recognizer names can be a maximum of 256\n      characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The name\n      must be unique in the account/Region.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "VersionName": {
+                    "target": "com.amazonaws.comprehend#VersionName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The version name given to the newly created recognizer. Version names can be a maximum of\n      256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The\n      version name must be unique among all models with the same recognizer name in the account/Region.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags to associate with the entity recognizer. A tag is a key-value pair\n      that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with\n      \"Sales\" as the key might be added to a resource to indicate its use by the sales department.\n    </p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerInputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the format and location of the input data. The S3 bucket containing the input\n      data must be located in the same Region as the entity recognizer being created. </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p> A unique identifier for the request. If you don't set the client request token, Amazon\n      Comprehend generates one.</p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p> You can specify any of the following languages: English\n      (\"en\"), Spanish (\"es\"), French (\"fr\"), Italian (\"it\"), German (\"de\"), or Portuguese (\"pt\").\n      If you plan to use this entity recognizer with PDF, Word, or image input files, you must\n      specify English as the language.\n      All training documents must be in the same language.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Configuration parameters for an optional private Virtual Private Cloud (VPC) containing\n      the resources you are using for your custom entity recognizer. For more information, see\n      <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                },
+                "ModelKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the KMS key that Amazon Comprehend uses to encrypt\n      trained custom models. The ModelKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "ModelPolicy": {
+                    "target": "com.amazonaws.comprehend#Policy",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The JSON resource-based policy to attach to your custom entity recognizer model. You can\n      use this policy to allow another Amazon Web Services account to import your custom model.</p>\n         <p>Provide your JSON as a UTF-8 encoded string without line breaks. To provide valid JSON for\n      your policy, enclose the attribute names and values in double quotes. If the JSON body is also\n      enclosed in double quotes, then you must escape the double quotes that are inside the\n      policy:</p>\n         <p>\n            <code>\"{\\\"attribute\\\": \\\"value\\\", \\\"attribute\\\": [\\\"value\\\"]}\"</code>\n         </p>\n         <p>To avoid escaping quotes, you can use single quotes to enclose the policy and double\n      quotes to enclose the JSON names and values:</p>\n         <p>\n            <code>'{\"attribute\": \"value\", \"attribute\": [\"value\"]}'</code>\n         </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#CreateEntityRecognizerResponse": {
+            "type": "structure",
+            "members": {
+                "EntityRecognizerArn": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) that identifies the entity recognizer.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#CreateFlywheel": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#CreateFlywheelRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#CreateFlywheelResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceUnavailableException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>A flywheel is an Amazon Web Services resource that orchestrates the ongoing training of a model for custom classification\n      or custom entity recognition. You can create a flywheel to start with an existing trained model, or\n      Comprehend can create and train a new model.</p>\n         <p>When you create the flywheel, Comprehend creates a data lake in your account. The data lake holds the training\n      data and test data for all versions of the model.</p>\n         <p>To use a flywheel with an existing trained model, you specify the active model version. Comprehend copies the model's\n      training data and test data into the flywheel's data lake.</p>\n         <p>To use the flywheel with a new model, you need to provide a dataset for training data (and optional test data)\n      when you create the flywheel.</p>\n         <p>For more information about flywheels, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/flywheels-about.html\">\n      Flywheel overview</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#CreateFlywheelRequest": {
+            "type": "structure",
+            "members": {
+                "FlywheelName": {
+                    "target": "com.amazonaws.comprehend#ComprehendArnName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Name for the flywheel.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ActiveModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>To associate an existing model with the flywheel, specify the Amazon Resource Number (ARN) of the model version.\n      Do not set <code>TaskConfig</code> or <code>ModelType</code> if you specify an <code>ActiveModelArn</code>.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend the permissions required to access the flywheel data in the data lake.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "TaskConfig": {
+                    "target": "com.amazonaws.comprehend#TaskConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Configuration about the model associated with the flywheel.\n      You need to set <code>TaskConfig</code> if you are creating a flywheel for a new model.</p>"
+                    }
+                },
+                "ModelType": {
+                    "target": "com.amazonaws.comprehend#ModelType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The model type. You need to set <code>ModelType</code> if you are creating a flywheel for a new model.</p>"
+                    }
+                },
+                "DataLakeS3Uri": {
+                    "target": "com.amazonaws.comprehend#FlywheelS3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Enter the S3 location for the data lake. You can specify a new S3 bucket or a new folder of an\n    existing S3 bucket. The flywheel creates the data lake at this location.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DataSecurityConfig": {
+                    "target": "com.amazonaws.comprehend#DataSecurityConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Data security configurations.</p>"
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A unique identifier for the request. If you don't set the client request token, Amazon\n      Comprehend generates one.</p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The tags to associate with this flywheel.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#CreateFlywheelResponse": {
+            "type": "structure",
+            "members": {
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel.</p>"
+                    }
+                },
+                "ActiveModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the active model version.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#CustomerInputString": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1
+                },
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#CustomerInputStringList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#CustomerInputString"
+            },
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1
+                },
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#DataSecurityConfig": {
+            "type": "structure",
+            "members": {
+                "ModelKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the KMS key that Amazon Comprehend uses to encrypt\n      trained custom models. The ModelKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the KMS key that Amazon Comprehend uses to encrypt the volume.</p>"
+                    }
+                },
+                "DataLakeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the KMS key that Amazon Comprehend uses to encrypt the data in the data lake.</p>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Data security configuration.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DatasetAugmentedManifestsList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#DatasetAugmentedManifestsListItem"
+            }
+        },
+        "com.amazonaws.comprehend#DatasetAugmentedManifestsListItem": {
+            "type": "structure",
+            "members": {
+                "AttributeNames": {
+                    "target": "com.amazonaws.comprehend#AttributeNamesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The JSON attribute that contains the annotations for your training documents. The number\n      of attribute names that you specify depends on whether your augmented manifest file is the\n      output of a single labeling job or a chained labeling job.</p>\n         <p>If your file is the output of a single labeling job, specify the LabelAttributeName key\n      that was used when the job was created in Ground Truth.</p>\n         <p>If your file is the output of a chained labeling job, specify the LabelAttributeName key\n      for one or more jobs in the chain. Each LabelAttributeName key provides the annotations from\n      an individual job.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon S3 location of the augmented manifest file.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "AnnotationDataS3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The S3 prefix to the annotation files that are referred in the augmented manifest\n      file.</p>"
+                    }
+                },
+                "SourceDocumentsS3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The S3 prefix to the source files (PDFs) that are referred to in the augmented manifest\n      file.</p>"
+                    }
+                },
+                "DocumentType": {
+                    "target": "com.amazonaws.comprehend#AugmentedManifestsDocumentTypeFormat",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The type of augmented manifest. If you don't specify, the default is PlainTextDocument. </p>\n         <p>\n            <code>PLAIN_TEXT_DOCUMENT</code> A document type that represents any unicode text that\n      is encoded in UTF-8.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>An augmented manifest file that provides training data for your custom model.\n      An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DatasetDataFormat": {
+            "type": "enum",
+            "members": {
+                "COMPREHEND_CSV": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "COMPREHEND_CSV"
+                    }
+                },
+                "AUGMENTED_MANIFEST": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "AUGMENTED_MANIFEST"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#DatasetDocumentClassifierInputDataConfig": {
+            "type": "structure",
+            "members": {
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon S3 URI for the input data. The S3 bucket must be in the same Region as the API\n      endpoint that you are calling. The URI can point to a single input file or it can provide the\n      prefix for a collection of input files.</p>\n         <p>For example, if you use the URI <code>S3://bucketName/prefix</code>, if the prefix is a\n      single file, Amazon Comprehend uses that file as input. If more than one file begins with the\n      prefix, Amazon Comprehend uses all of them as input.</p>\n         <p>This parameter is required if you set <code>DataFormat</code> to\n      <code>COMPREHEND_CSV</code>.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "LabelDelimiter": {
+                    "target": "com.amazonaws.comprehend#LabelDelimiter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Indicates the delimiter used to separate each label for training a multi-label classifier.\n      The default delimiter between labels is a pipe (|). You can use a different character as a\n      delimiter (if it's an allowed character) by specifying it under Delimiter for labels. If the\n      training documents use a delimiter other than the default or the delimiter you specify, the\n      labels on that line will be combined to make a single unique label, such as\n      LABELLABELLABEL.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Describes the dataset input data configuration for a document classifier model.</p>\n         <p>For more information on how the input file is formatted, see  <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/prep-classifier-data.html\">Preparing training data</a>\n      in the Comprehend Developer Guide. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#DatasetEntityRecognizerAnnotations": {
+            "type": "structure",
+            "members": {
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Specifies the Amazon S3 location where the training documents for an entity recognizer\n      are located. The URI must be in the same Region as the API endpoint that you are\n      calling.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Describes the annotations associated with a entity recognizer.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DatasetEntityRecognizerDocuments": {
+            "type": "structure",
+            "members": {
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Specifies the Amazon S3 location where the documents for the dataset\n      are located.  </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "InputFormat": {
+                    "target": "com.amazonaws.comprehend#InputFormat",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Specifies how the text in an input file should be processed. This is optional, and the\n      default is ONE_DOC_PER_LINE. ONE_DOC_PER_FILE - Each file is considered a separate document.\n      Use this option when you are processing large documents, such as newspaper articles or\n      scientific papers. ONE_DOC_PER_LINE - Each line in a file is considered a separate document.\n      Use this option when you are processing many short documents, such as text messages.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Describes the documents submitted with a dataset for an entity recognizer model.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DatasetEntityRecognizerEntityList": {
+            "type": "structure",
+            "members": {
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the Amazon S3 location where the entity list is located.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Describes the dataset entity list for an entity recognizer model.</p>\n         <p>For more information on how the input file is formatted, see  <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/prep-training-data-cer.html\">Preparing training data</a>\n      in the Comprehend Developer Guide. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#DatasetEntityRecognizerInputDataConfig": {
+            "type": "structure",
+            "members": {
+                "Annotations": {
+                    "target": "com.amazonaws.comprehend#DatasetEntityRecognizerAnnotations",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The S3 location of the annotation documents for your custom entity recognizer.</p>"
+                    }
+                },
+                "Documents": {
+                    "target": "com.amazonaws.comprehend#DatasetEntityRecognizerDocuments",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The format and location of the training documents for your custom entity\n      recognizer.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "EntityList": {
+                    "target": "com.amazonaws.comprehend#DatasetEntityRecognizerEntityList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The S3 location of the entity list for your custom entity recognizer.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Specifies the format and location of the input data. You must provide either the\n      <code>Annotations</code> parameter or the <code>EntityList</code> parameter.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DatasetFilter": {
+            "type": "structure",
+            "members": {
+                "Status": {
+                    "target": "com.amazonaws.comprehend#DatasetStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filter the datasets based on the dataset status.</p>"
+                    }
+                },
+                "DatasetType": {
+                    "target": "com.amazonaws.comprehend#DatasetType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filter the datasets based on the dataset type.</p>"
+                    }
+                },
+                "CreationTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filter the datasets to include datasets created after the specified time.</p>"
+                    }
+                },
+                "CreationTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filter the datasets to include datasets created before the specified time.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Filter the datasets based on creation time or dataset status.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DatasetInputDataConfig": {
+            "type": "structure",
+            "members": {
+                "AugmentedManifests": {
+                    "target": "com.amazonaws.comprehend#DatasetAugmentedManifestsList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list of augmented manifest files that provide training data for your custom model. An\n      augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground\n      Truth. </p>"
+                    }
+                },
+                "DataFormat": {
+                    "target": "com.amazonaws.comprehend#DatasetDataFormat",
+                    "traits": {
+                        "smithy.api#documentation": "<p>\n            <code>COMPREHEND_CSV</code>: The data format is a two-column CSV file, where the\n      first column contains labels and the second column contains documents.</p>\n         <p>\n            <code>AUGMENTED_MANIFEST</code>: The data format  </p>"
+                    }
+                },
+                "DocumentClassifierInputDataConfig": {
+                    "target": "com.amazonaws.comprehend#DatasetDocumentClassifierInputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The input properties for training a document classifier model. </p>\n         <p>For more information on how the input file is formatted, see  <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/prep-classifier-data.html\">Preparing training data</a>\n      in the Comprehend Developer Guide. </p>"
+                    }
+                },
+                "EntityRecognizerInputDataConfig": {
+                    "target": "com.amazonaws.comprehend#DatasetEntityRecognizerInputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The input properties for training an entity recognizer model.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Specifies the format and location of the input data for the dataset.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DatasetProperties": {
+            "type": "structure",
+            "members": {
+                "DatasetArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendDatasetArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The ARN of the dataset.</p>"
+                    }
+                },
+                "DatasetName": {
+                    "target": "com.amazonaws.comprehend#ComprehendArnName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name of the dataset.</p>"
+                    }
+                },
+                "DatasetType": {
+                    "target": "com.amazonaws.comprehend#DatasetType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The dataset type (training data or test data).</p>"
+                    }
+                },
+                "DatasetS3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The S3 URI where the dataset is stored.</p>"
+                    }
+                },
+                "Description": {
+                    "target": "com.amazonaws.comprehend#Description",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Description of the dataset.</p>"
+                    }
+                },
+                "Status": {
+                    "target": "com.amazonaws.comprehend#DatasetStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The dataset status. While the system creates the dataset, the status is <code>CREATING</code>.\n      When the dataset is ready to use, the status changes to <code>COMPLETED</code>. </p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A description of the status of the dataset.</p>"
+                    }
+                },
+                "NumberOfDocuments": {
+                    "target": "com.amazonaws.comprehend#NumberOfDocuments",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The number of documents in the dataset.</p>"
+                    }
+                },
+                "CreationTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Creation time of the dataset.</p>"
+                    }
+                },
+                "EndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Time when the data from the dataset becomes available in the data lake.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Properties associated with the dataset.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DatasetPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#DatasetProperties"
+            }
+        },
+        "com.amazonaws.comprehend#DatasetStatus": {
+            "type": "enum",
+            "members": {
+                "CREATING": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "CREATING"
+                    }
+                },
+                "COMPLETED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "COMPLETED"
+                    }
+                },
+                "FAILED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "FAILED"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#DatasetType": {
+            "type": "enum",
+            "members": {
+                "TRAIN": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TRAIN"
+                    }
+                },
+                "TEST": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TEST"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#DeleteDocumentClassifier": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DeleteDocumentClassifierRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DeleteDocumentClassifierResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceUnavailableException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Deletes a previously created document classifier</p>\n         <p>Only those classifiers that are in terminated states (IN_ERROR, TRAINED) will be deleted.\n      If an active inference job is using the model, a <code>ResourceInUseException</code> will be\n      returned.</p>\n         <p>This is an asynchronous action that puts the classifier into a DELETING state, and it is\n      then removed by a background job. Once removed, the classifier disappears from your account\n      and is no longer available for use. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#DeleteDocumentClassifierRequest": {
+            "type": "structure",
+            "members": {
+                "DocumentClassifierArn": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) that identifies the document classifier. </p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DeleteDocumentClassifierResponse": {
+            "type": "structure",
+            "members": {},
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DeleteEndpoint": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DeleteEndpointRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DeleteEndpointResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Deletes a model-specific endpoint for a previously-trained custom model. All endpoints\n      must be deleted in order for the model to be deleted.\n      For information about endpoints, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/manage-endpoints.html\">Managing endpoints</a>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DeleteEndpointRequest": {
+            "type": "structure",
+            "members": {
+                "EndpointArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendEndpointArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the endpoint being deleted.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DeleteEndpointResponse": {
+            "type": "structure",
+            "members": {},
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DeleteEntityRecognizer": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DeleteEntityRecognizerRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DeleteEntityRecognizerResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceUnavailableException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Deletes an entity recognizer.</p>\n         <p>Only those recognizers that are in terminated states (IN_ERROR, TRAINED) will be deleted.\n      If an active inference job is using the model, a <code>ResourceInUseException</code> will be\n      returned.</p>\n         <p>This is an asynchronous action that puts the recognizer into a DELETING state, and it is\n      then removed by a background job. Once removed, the recognizer disappears from your account\n      and is no longer available for use. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#DeleteEntityRecognizerRequest": {
+            "type": "structure",
+            "members": {
+                "EntityRecognizerArn": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) that identifies the entity recognizer.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DeleteEntityRecognizerResponse": {
+            "type": "structure",
+            "members": {},
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DeleteFlywheel": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DeleteFlywheelRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DeleteFlywheelResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceUnavailableException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Deletes a flywheel. When you delete the flywheel, Amazon Comprehend\n      does not delete the data lake or the model associated with the flywheel.</p>\n         <p>For more information about flywheels, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/flywheels-about.html\">\n      Flywheel overview</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DeleteFlywheelRequest": {
+            "type": "structure",
+            "members": {
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel to delete.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DeleteFlywheelResponse": {
+            "type": "structure",
+            "members": {},
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DeleteResourcePolicy": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DeleteResourcePolicyRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DeleteResourcePolicyResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Deletes a resource-based policy that is attached to a custom model.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DeleteResourcePolicyRequest": {
+            "type": "structure",
+            "members": {
+                "ResourceArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the custom model version that has the policy to delete.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "PolicyRevisionId": {
+                    "target": "com.amazonaws.comprehend#PolicyRevisionId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The revision ID of the policy to delete.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DeleteResourcePolicyResponse": {
+            "type": "structure",
+            "members": {},
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeDataset": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeDatasetRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeDatasetResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Returns information about the dataset that you specify. \n      For more information about datasets, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/flywheels-about.html\">\n      Flywheel overview</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeDatasetRequest": {
+            "type": "structure",
+            "members": {
+                "DatasetArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendDatasetArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The ARN of the dataset.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeDatasetResponse": {
+            "type": "structure",
+            "members": {
+                "DatasetProperties": {
+                    "target": "com.amazonaws.comprehend#DatasetProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The dataset properties.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeDocumentClassificationJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeDocumentClassificationJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeDocumentClassificationJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets the properties associated with a document classification job. Use this operation to\n      get the status of a classification job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeDocumentClassificationJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier that Amazon Comprehend generated for the job. The  \n      <code>StartDocumentClassificationJob</code> operation returns this identifier in its response.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeDocumentClassificationJobResponse": {
+            "type": "structure",
+            "members": {
+                "DocumentClassificationJobProperties": {
+                    "target": "com.amazonaws.comprehend#DocumentClassificationJobProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An object that describes the properties associated with the document classification\n      job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeDocumentClassifier": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeDocumentClassifierRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeDocumentClassifierResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets the properties associated with a document classifier.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeDocumentClassifierRequest": {
+            "type": "structure",
+            "members": {
+                "DocumentClassifierArn": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) that identifies the document classifier. The  \n      <code>CreateDocumentClassifier</code> operation returns this identifier in its response.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeDocumentClassifierResponse": {
+            "type": "structure",
+            "members": {
+                "DocumentClassifierProperties": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An object that contains the properties associated with a document classifier.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeDominantLanguageDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeDominantLanguageDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeDominantLanguageDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets the properties associated with a dominant language detection job. Use this operation\n      to get the status of a detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeDominantLanguageDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier that Amazon Comprehend generated for the job. The  \n      <code>StartDominantLanguageDetectionJob</code> operation returns this identifier in its response.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeDominantLanguageDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "DominantLanguageDetectionJobProperties": {
+                    "target": "com.amazonaws.comprehend#DominantLanguageDetectionJobProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An object that contains the properties associated with a dominant language detection\n      job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeEndpoint": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeEndpointRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeEndpointResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets the properties associated with a specific endpoint. Use this operation to get the\n      status of an endpoint.\n      For information about endpoints, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/manage-endpoints.html\">Managing endpoints</a>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeEndpointRequest": {
+            "type": "structure",
+            "members": {
+                "EndpointArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendEndpointArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the endpoint being described.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeEndpointResponse": {
+            "type": "structure",
+            "members": {
+                "EndpointProperties": {
+                    "target": "com.amazonaws.comprehend#EndpointProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Describes information associated with the specific endpoint.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeEntitiesDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeEntitiesDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeEntitiesDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets the properties associated with an entities detection job. Use this operation to get\n      the status of a detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeEntitiesDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier that Amazon Comprehend generated for the job. The \n        <code>StartEntitiesDetectionJob</code> operation returns this identifier in its response.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeEntitiesDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "EntitiesDetectionJobProperties": {
+                    "target": "com.amazonaws.comprehend#EntitiesDetectionJobProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An object that contains the properties associated with an entities detection job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeEntityRecognizer": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeEntityRecognizerRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeEntityRecognizerResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Provides details about an entity recognizer including status, S3 buckets containing\n      training data, recognizer metadata, metrics, and so on.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeEntityRecognizerRequest": {
+            "type": "structure",
+            "members": {
+                "EntityRecognizerArn": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) that identifies the entity recognizer.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeEntityRecognizerResponse": {
+            "type": "structure",
+            "members": {
+                "EntityRecognizerProperties": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Describes information associated with an entity recognizer.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeEventsDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeEventsDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeEventsDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets the status and details of an events detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeEventsDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the events detection job.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeEventsDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "EventsDetectionJobProperties": {
+                    "target": "com.amazonaws.comprehend#EventsDetectionJobProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An object that contains the properties associated with an event detection job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeFlywheel": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeFlywheelRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeFlywheelResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Provides configuration information about the flywheel. For more information about flywheels, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/flywheels-about.html\">\n      Flywheel overview</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeFlywheelIteration": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeFlywheelIterationRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeFlywheelIterationResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Retrieve the configuration properties of a flywheel iteration.\n      For more information about flywheels, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/flywheels-about.html\">\n      Flywheel overview</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeFlywheelIterationRequest": {
+            "type": "structure",
+            "members": {
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p></p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "FlywheelIterationId": {
+                    "target": "com.amazonaws.comprehend#FlywheelIterationId",
+                    "traits": {
+                        "smithy.api#documentation": "<p></p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeFlywheelIterationResponse": {
+            "type": "structure",
+            "members": {
+                "FlywheelIterationProperties": {
+                    "target": "com.amazonaws.comprehend#FlywheelIterationProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The configuration properties of a flywheel iteration.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeFlywheelRequest": {
+            "type": "structure",
+            "members": {
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeFlywheelResponse": {
+            "type": "structure",
+            "members": {
+                "FlywheelProperties": {
+                    "target": "com.amazonaws.comprehend#FlywheelProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The flywheel properties.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeKeyPhrasesDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeKeyPhrasesDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeKeyPhrasesDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets the properties associated with a key phrases detection job. Use this operation to get\n      the status of a detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeKeyPhrasesDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier that Amazon Comprehend generated for the job. The \n        <code>StartKeyPhrasesDetectionJob</code> operation returns this identifier in its\n      response.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeKeyPhrasesDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "KeyPhrasesDetectionJobProperties": {
+                    "target": "com.amazonaws.comprehend#KeyPhrasesDetectionJobProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An object that contains the properties associated with a key phrases detection job.\n    </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribePiiEntitiesDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribePiiEntitiesDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribePiiEntitiesDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets the properties associated with a PII entities detection job. For example, you can use\n      this operation to get the job status.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribePiiEntitiesDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier that Amazon Comprehend generated for the job. The  operation returns this identifier in its\n      response.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribePiiEntitiesDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "PiiEntitiesDetectionJobProperties": {
+                    "target": "com.amazonaws.comprehend#PiiEntitiesDetectionJobProperties"
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeResourcePolicy": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeResourcePolicyRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeResourcePolicyResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets the details of a resource-based policy that is attached to a custom model, including\n      the JSON body of the policy.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeResourcePolicyRequest": {
+            "type": "structure",
+            "members": {
+                "ResourceArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the custom model version that has the resource policy.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeResourcePolicyResponse": {
+            "type": "structure",
+            "members": {
+                "ResourcePolicy": {
+                    "target": "com.amazonaws.comprehend#Policy",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The JSON body of the resource-based policy.</p>"
+                    }
+                },
+                "CreationTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time at which the policy was created.</p>"
+                    }
+                },
+                "LastModifiedTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time at which the policy was last modified.</p>"
+                    }
+                },
+                "PolicyRevisionId": {
+                    "target": "com.amazonaws.comprehend#PolicyRevisionId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The revision ID of the policy. Each time you modify a policy, Amazon Comprehend assigns a\n      new revision ID, and it deletes the prior version of the policy.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeSentimentDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeSentimentDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeSentimentDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets the properties associated with a sentiment detection job. Use this operation to get\n      the status of a detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeSentimentDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier that Amazon Comprehend generated for the job. The  operation returns this identifier in its\n      response.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeSentimentDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "SentimentDetectionJobProperties": {
+                    "target": "com.amazonaws.comprehend#SentimentDetectionJobProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An object that contains the properties associated with a sentiment detection job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeTargetedSentimentDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeTargetedSentimentDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeTargetedSentimentDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets the properties associated with a targeted sentiment detection job. Use this operation\n      to get the status of the job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeTargetedSentimentDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier that Amazon Comprehend generated for the job. The  \n      <code>StartTargetedSentimentDetectionJob</code> operation returns this identifier in its\n      response.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeTargetedSentimentDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "TargetedSentimentDetectionJobProperties": {
+                    "target": "com.amazonaws.comprehend#TargetedSentimentDetectionJobProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An object that contains the properties associated with a targeted sentiment detection job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeTopicsDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DescribeTopicsDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DescribeTopicsDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets the properties associated with a topic detection job. Use this operation to get\n      the status of a detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DescribeTopicsDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier assigned by the user to the detection job.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DescribeTopicsDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "TopicsDetectionJobProperties": {
+                    "target": "com.amazonaws.comprehend#TopicsDetectionJobProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The list of properties for the requested job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#Description": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 2048
+                },
+                "smithy.api#pattern": "^([a-zA-Z0-9_])[\\\\a-zA-Z0-9_@#%*+=:?./!\\s-]*$"
+            }
+        },
+        "com.amazonaws.comprehend#DetectDominantLanguage": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DetectDominantLanguageRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DetectDominantLanguageResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Determines the dominant language of the input text. For a list of languages that Amazon\n      Comprehend can detect, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-languages.html\">Amazon Comprehend Supported Languages</a>. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#DetectDominantLanguageRequest": {
+            "type": "structure",
+            "members": {
+                "Text": {
+                    "target": "com.amazonaws.comprehend#CustomerInputString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A UTF-8 text string. The string must contain at least 20 characters. The maximum string size is 100 KB.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectDominantLanguageResponse": {
+            "type": "structure",
+            "members": {
+                "Languages": {
+                    "target": "com.amazonaws.comprehend#ListOfDominantLanguages",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Array of languages that Amazon Comprehend detected in the input text. \n      The array is sorted in descending order of the score \n      (the dominant language is always the first element in the array).</p>\n         <p>For each language, the\n      response returns the RFC 5646 language code and the level of confidence that Amazon Comprehend\n      has in the accuracy of its inference. For more information about RFC 5646, see <a href=\"https://tools.ietf.org/html/rfc5646\">Tags for Identifying Languages</a> on the\n        <i>IETF Tools</i> web site.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {},
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectEntities": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DetectEntitiesRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DetectEntitiesResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceUnavailableException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Detects named entities in input text when you use the pre-trained model.\n      Detects custom entities if you have a custom entity recognition model. </p>\n         <p>\n      When detecting named entities using the pre-trained model, use plain text as the input.\n      For more information about named entities, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-entities.html\">Entities</a> in the Comprehend Developer Guide.</p>\n         <p>When you use a custom entity recognition model,\n      you can input plain text or you can upload a single-page input document (text, PDF, Word, or image). </p>\n         <p>If the system detects errors while processing a page in the input document, the API response\n       includes an entry in <code>Errors</code> for each error. </p>\n         <p>If the system detects a document-level error in your input document, the API returns an\n       <code>InvalidRequestException</code> error response.\n      For details about this exception, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/idp-inputs-sync-err.html\">\n        Errors in semi-structured documents</a> in the Comprehend Developer Guide.\n    </p>"
+            }
+        },
+        "com.amazonaws.comprehend#DetectEntitiesRequest": {
+            "type": "structure",
+            "members": {
+                "Text": {
+                    "target": "com.amazonaws.comprehend#CustomerInputString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A UTF-8 text string. The maximum string size is 100 KB. If you enter text using this parameter,\n    do not use the <code>Bytes</code> parameter.</p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. You can specify any of the primary languages\n      supported by Amazon Comprehend. If your request includes the endpoint for a custom entity recognition model, Amazon\n      Comprehend uses the language of your custom model, and it ignores any language code that you\n      specify here.</p>\n         <p>All input documents must be in the same language.</p>"
+                    }
+                },
+                "EndpointArn": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerEndpointArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name of an endpoint that is associated with a custom entity\n      recognition model. Provide an endpoint if you want to detect entities by using your own custom\n      model instead of the default model that is used by Amazon Comprehend.</p>\n         <p>If you specify an endpoint, Amazon Comprehend uses the language of your custom model, and\n      it ignores any language code that you provide in your request.</p>\n         <p>For information about endpoints, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/manage-endpoints.html\">Managing endpoints</a>.</p>"
+                    }
+                },
+                "Bytes": {
+                    "target": "com.amazonaws.comprehend#SemiStructuredDocumentBlob",
+                    "traits": {
+                        "smithy.api#documentation": "<p>This field applies only when you use a custom entity recognition model that\n      was trained with PDF annotations. For other cases,\n      enter your text input in the <code>Text</code> field.</p>\n         <p>\n      Use the <code>Bytes</code> parameter to input a text, PDF, Word or image file.\n      Using a plain-text file in the <code>Bytes</code> parameter is equivelent to using the\n      <code>Text</code> parameter (the <code>Entities</code> field in the response is identical).</p>\n         <p>You can also use the <code>Bytes</code> parameter to input an Amazon Textract <code>DetectDocumentText</code>\n      or <code>AnalyzeDocument</code> output file.</p>\n         <p>Provide the input document as a sequence of base64-encoded bytes.\n      If your code uses an Amazon Web Services SDK to detect entities, the SDK may encode\n      the document file bytes for you. </p>\n         <p>The maximum length of this field depends on the input document type. For details, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/idp-inputs-sync.html\">\n        Inputs for real-time custom analysis</a> in the Comprehend Developer Guide. </p>\n         <p>If you use the <code>Bytes</code> parameter, do not use the <code>Text</code> parameter.</p>"
+                    }
+                },
+                "DocumentReaderConfig": {
+                    "target": "com.amazonaws.comprehend#DocumentReaderConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Provides configuration parameters to override the default actions for extracting text\n      from PDF documents and image files.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectEntitiesResponse": {
+            "type": "structure",
+            "members": {
+                "Entities": {
+                    "target": "com.amazonaws.comprehend#ListOfEntities",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A collection of entities identified in the input text. For each entity, the response\n      provides the entity text, entity type, where the entity text begins and ends, and the level of\n      confidence that Amazon Comprehend has in the detection. </p>\n         <p>If your request uses a custom entity recognition model, Amazon Comprehend detects the\n      entities that the model is trained to recognize. Otherwise, it detects the default entity\n      types. For a list of default entity types, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-entities.html\">Entities</a> in the Comprehend Developer Guide.\n    </p>"
+                    }
+                },
+                "DocumentMetadata": {
+                    "target": "com.amazonaws.comprehend#DocumentMetadata",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Information about the document, discovered during text extraction. This field is present\n      in the response only if your request used the <code>Byte</code> parameter. </p>"
+                    }
+                },
+                "DocumentType": {
+                    "target": "com.amazonaws.comprehend#ListOfDocumentType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The document type for each page in the input document. This field is present\n      in the response only if your request used the <code>Byte</code> parameter. </p>"
+                    }
+                },
+                "Blocks": {
+                    "target": "com.amazonaws.comprehend#ListOfBlocks",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Information about each block of text in the input document.\n      Blocks are nested. A page block contains a block for each line of text,\n      which contains a block for each word. </p>\n         <p>The <code>Block</code> content for a Word input document does not include a <code>Geometry</code> field.</p>\n         <p>The <code>Block</code> field is not present in the response for plain-text inputs.</p>"
+                    }
+                },
+                "Errors": {
+                    "target": "com.amazonaws.comprehend#ListOfErrors",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Page-level errors that the system detected while processing the input document.\n      The field is empty if the system encountered no errors.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {},
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectKeyPhrases": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DetectKeyPhrasesRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DetectKeyPhrasesResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Detects the key noun phrases found in the text. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#DetectKeyPhrasesRequest": {
+            "type": "structure",
+            "members": {
+                "Text": {
+                    "target": "com.amazonaws.comprehend#CustomerInputString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A UTF-8 text string. The string must contain less than 100 KB of UTF-8 encoded\n      characters.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. You can specify any of the primary languages\n      supported by Amazon Comprehend. All documents must be in the same language.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectKeyPhrasesResponse": {
+            "type": "structure",
+            "members": {
+                "KeyPhrases": {
+                    "target": "com.amazonaws.comprehend#ListOfKeyPhrases",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A collection of key phrases that Amazon Comprehend identified in the input text. For\n      each key phrase, the response provides the text of the key phrase, where the key phrase begins\n      and ends, and the level of confidence that Amazon Comprehend has in the accuracy of the\n      detection. </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {},
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectPiiEntities": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DetectPiiEntitiesRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DetectPiiEntitiesResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Inspects the input text for entities that contain personally identifiable information\n      (PII) and returns information about them.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DetectPiiEntitiesRequest": {
+            "type": "structure",
+            "members": {
+                "Text": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A UTF-8 text string. The maximum string size is 100 KB.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input text.   \n      Enter the language code for English (en) or Spanish (es).</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectPiiEntitiesResponse": {
+            "type": "structure",
+            "members": {
+                "Entities": {
+                    "target": "com.amazonaws.comprehend#ListOfPiiEntities",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A collection of PII entities identified in the input text. For each entity, the response\n      provides the entity type, where the entity text begins and ends, and the level of confidence\n      that Amazon Comprehend has in the detection.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectSentiment": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DetectSentimentRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DetectSentimentResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Inspects text and returns an inference of the prevailing sentiment\n        (<code>POSITIVE</code>, <code>NEUTRAL</code>, <code>MIXED</code>, or <code>NEGATIVE</code>). </p>"
+            }
+        },
+        "com.amazonaws.comprehend#DetectSentimentRequest": {
+            "type": "structure",
+            "members": {
+                "Text": {
+                    "target": "com.amazonaws.comprehend#CustomerInputString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A UTF-8 text string. The maximum string size is 5 KB.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. You can specify any of the primary languages\n      supported by Amazon Comprehend. All documents must be in the same language.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectSentimentResponse": {
+            "type": "structure",
+            "members": {
+                "Sentiment": {
+                    "target": "com.amazonaws.comprehend#SentimentType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The inferred sentiment that Amazon Comprehend has the highest level of confidence\n      in.</p>"
+                    }
+                },
+                "SentimentScore": {
+                    "target": "com.amazonaws.comprehend#SentimentScore",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An object that lists the sentiments, and their corresponding confidence\n      levels.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {},
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectSyntax": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DetectSyntaxRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DetectSyntaxResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Inspects text for syntax and the part of speech of words in the document. For more\n      information, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-syntax.html\">Syntax</a> in the Comprehend Developer Guide.\n    </p>"
+            }
+        },
+        "com.amazonaws.comprehend#DetectSyntaxRequest": {
+            "type": "structure",
+            "members": {
+                "Text": {
+                    "target": "com.amazonaws.comprehend#CustomerInputString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A UTF-8 string. The maximum string size is 5 KB.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#SyntaxLanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language code of the input documents. You can specify any of the following languages\n      supported by Amazon Comprehend: German (\"de\"), English (\"en\"), Spanish (\"es\"), French (\"fr\"),\n      Italian (\"it\"), or Portuguese (\"pt\").</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectSyntaxResponse": {
+            "type": "structure",
+            "members": {
+                "SyntaxTokens": {
+                    "target": "com.amazonaws.comprehend#ListOfSyntaxTokens",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A collection of syntax tokens describing the text. For each token, the response provides\n      the text, the token type, where the text begins and ends, and the level of confidence that\n      Amazon Comprehend has that the token is correct. For a list of token types, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-syntax.html\">Syntax</a> in the Comprehend Developer Guide.\n    </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {},
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectTargetedSentiment": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DetectTargetedSentimentRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DetectTargetedSentimentResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Inspects the input text and returns a sentiment analysis for each entity identified in the text.</p>\n         <p>For more information about targeted sentiment, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-targeted-sentiment.html\">Targeted sentiment</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DetectTargetedSentimentRequest": {
+            "type": "structure",
+            "members": {
+                "Text": {
+                    "target": "com.amazonaws.comprehend#CustomerInputString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A UTF-8 text string. The maximum string length is 5 KB.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. Currently, English is the only supported language.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectTargetedSentimentResponse": {
+            "type": "structure",
+            "members": {
+                "Entities": {
+                    "target": "com.amazonaws.comprehend#ListOfTargetedSentimentEntities",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Targeted sentiment analysis for each of the entities identified in the input text.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {},
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectToxicContent": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#DetectToxicContentRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#DetectToxicContentResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TextSizeLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#UnsupportedLanguageException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Performs toxicity analysis on the list of text strings that you provide as input.\n      The API response contains a results list that matches the size of the input list.\n      For more information about toxicity detection, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/toxicity-detection.html\">Toxicity detection</a> in the <i>Amazon Comprehend Developer Guide</i>.\n    </p>"
+            }
+        },
+        "com.amazonaws.comprehend#DetectToxicContentRequest": {
+            "type": "structure",
+            "members": {
+                "TextSegments": {
+                    "target": "com.amazonaws.comprehend#ListOfTextSegments",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list of up to 10 text strings. Each string has a maximum size of 1 KB, and\n      the maximum size of the list is 10 KB.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input text. Currently, English is the only supported language.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#DetectToxicContentResponse": {
+            "type": "structure",
+            "members": {
+                "ResultList": {
+                    "target": "com.amazonaws.comprehend#ListOfToxicLabels",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Results of the content moderation analysis.\n      Each entry in the results list contains a list of toxic content types identified in \n      the text, along with a confidence score for each content type. \n      The results list also includes a toxicity score for each entry in the results list.\n    </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClass": {
+            "type": "structure",
+            "members": {
+                "Name": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name of the class.</p>"
+                    }
+                },
+                "Score": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The confidence score that Amazon Comprehend has this class correctly attributed.</p>"
+                    }
+                },
+                "Page": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Page number in the input document. This field is present\n      in the response only if your request includes the <code>Byte</code> parameter. </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Specifies the class that categorizes the document being analyzed</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassificationConfig": {
+            "type": "structure",
+            "members": {
+                "Mode": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierMode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Classification mode indicates whether the documents are <code>MULTI_CLASS</code> or <code>MULTI_LABEL</code>.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "Labels": {
+                    "target": "com.amazonaws.comprehend#LabelsList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>One or more labels to associate with the custom classifier.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Configuration required for a document classification model.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassificationJobFilter": {
+            "type": "structure",
+            "members": {
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters on the name of the job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list based on job status. Returns only jobs with the specified status.</p>"
+                    }
+                },
+                "SubmitTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted before the specified time. Jobs are returned in ascending order,\n      oldest to newest.</p>"
+                    }
+                },
+                "SubmitTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted after the specified time. Jobs are returned in descending order,\n      newest to oldest.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information for filtering a list of document classification jobs. For more\n      information, see the  operation. You can\n      provide only one filter parameter in each request.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassificationJobProperties": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier assigned to the document classification job.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the document classification job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:document-classification-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:document-classification-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name that you assigned to the document classification job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The current status of the document classification job. If the status is\n        <code>FAILED</code>, the <code>Message</code> field shows the reason for the failure.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A description of the status of the job.</p>"
+                    }
+                },
+                "SubmitTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the document classification job was submitted for processing.</p>"
+                    }
+                },
+                "EndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the document classification job completed.</p>"
+                    }
+                },
+                "DocumentClassifierArn": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) that identifies the document classifier. </p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The input data configuration that you supplied when you created the document\n      classification job.</p>"
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The output data configuration that you supplied when you created the document\n      classification job.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>"
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Configuration parameters for a private Virtual Private Cloud (VPC) containing the\n      resources you are using for your document classification job. For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                },
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information about a document classification job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassificationJobPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#DocumentClassificationJobProperties"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierArn": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 256
+                },
+                "smithy.api#pattern": "^arn:aws(-[^:]+)?:comprehend:[a-zA-Z0-9-]*:[0-9]{12}:document-classifier/[a-zA-Z0-9](-*[a-zA-Z0-9])*(/version/[a-zA-Z0-9](-*[a-zA-Z0-9])*)?$"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierAugmentedManifestsList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#AugmentedManifestsListItem"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierDataFormat": {
+            "type": "enum",
+            "members": {
+                "COMPREHEND_CSV": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "COMPREHEND_CSV"
+                    }
+                },
+                "AUGMENTED_MANIFEST": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "AUGMENTED_MANIFEST"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierDocumentTypeFormat": {
+            "type": "enum",
+            "members": {
+                "PLAIN_TEXT_DOCUMENT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PLAIN_TEXT_DOCUMENT"
+                    }
+                },
+                "SEMI_STRUCTURED_DOCUMENT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "SEMI_STRUCTURED_DOCUMENT"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierDocuments": {
+            "type": "structure",
+            "members": {
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The S3 URI location of the training documents specified in the S3Uri CSV file.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "TestS3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The S3 URI location of the test documents included in the TestS3Uri CSV file.\n      This field is not required if you do not specify a test CSV file.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The location of the training documents. This parameter is required in a request to create a semi-structured document classification model.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierEndpointArn": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 256
+                },
+                "smithy.api#pattern": "^arn:aws(-[^:]+)?:comprehend:[a-zA-Z0-9-]*:([0-9]{12}|aws):document-classifier-endpoint/[a-zA-Z0-9](-*[a-zA-Z0-9])*$"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierFilter": {
+            "type": "structure",
+            "members": {
+                "Status": {
+                    "target": "com.amazonaws.comprehend#ModelStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of classifiers based on status.</p>"
+                    }
+                },
+                "DocumentClassifierName": {
+                    "target": "com.amazonaws.comprehend#ComprehendArnName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name that you assigned to the document classifier</p>"
+                    }
+                },
+                "SubmitTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of classifiers based on the time that the classifier was submitted for\n      processing. Returns only classifiers submitted before the specified time. Classifiers are\n      returned in ascending order, oldest to newest.</p>"
+                    }
+                },
+                "SubmitTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of classifiers based on the time that the classifier was submitted for\n      processing. Returns only classifiers submitted after the specified time. Classifiers are\n      returned in descending order, newest to oldest.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information for filtering a list of document classifiers. You can only specify\n      one filtering parameter in a request. For more information, see the \n        <code>ListDocumentClassifiers</code> operation.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierInputDataConfig": {
+            "type": "structure",
+            "members": {
+                "DataFormat": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierDataFormat",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The format of your training data:</p>\n         <ul>\n            <li>\n               <p>\n                  <code>COMPREHEND_CSV</code>: A two-column CSV file, where labels are provided in the\n          first column, and documents are provided in the second. If you use this value, you must\n          provide the <code>S3Uri</code> parameter in your request.</p>\n            </li>\n            <li>\n               <p>\n                  <code>AUGMENTED_MANIFEST</code>: A labeled dataset that is produced by Amazon\n          SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON\n          object that contains a training document and its associated labels. </p>\n               <p>If you use this value, you must provide the <code>AugmentedManifests</code> parameter\n          in your request.</p>\n            </li>\n         </ul>\n         <p>If you don't specify a value, Amazon Comprehend uses <code>COMPREHEND_CSV</code> as the\n      default.</p>"
+                    }
+                },
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon S3 URI for the input data. The S3 bucket must be in the same Region as the API\n      endpoint that you are calling. The URI can point to a single input file or it can provide the\n      prefix for a collection of input files.</p>\n         <p>For example, if you use the URI <code>S3://bucketName/prefix</code>, if the prefix is a\n      single file, Amazon Comprehend uses that file as input. If more than one file begins with the\n      prefix, Amazon Comprehend uses all of them as input.</p>\n         <p>This parameter is required if you set <code>DataFormat</code> to\n        <code>COMPREHEND_CSV</code>.</p>"
+                    }
+                },
+                "TestS3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>This specifies the Amazon S3 location that contains the test annotations for the document classifier. \n      The URI must be in the same Amazon Web Services Region as the API endpoint that you are calling. </p>"
+                    }
+                },
+                "LabelDelimiter": {
+                    "target": "com.amazonaws.comprehend#LabelDelimiter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Indicates the delimiter used to separate each label for training a multi-label classifier.\n      The default delimiter between labels is a pipe (|). You can use a different character as a\n      delimiter (if it's an allowed character) by specifying it under Delimiter for labels. If the\n      training documents use a delimiter other than the default or the delimiter you specify, the\n      labels on that line will be combined to make a single unique label, such as\n      LABELLABELLABEL.</p>"
+                    }
+                },
+                "AugmentedManifests": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierAugmentedManifestsList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list of augmented manifest files that provide training data for your custom model. An\n      augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground\n      Truth.</p>\n         <p>This parameter is required if you set <code>DataFormat</code> to\n        <code>AUGMENTED_MANIFEST</code>.</p>"
+                    }
+                },
+                "DocumentType": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierDocumentTypeFormat",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The type of input documents for training the model. Provide plain-text documents to create a plain-text model, and\n    provide semi-structured documents to create a native document model.</p>"
+                    }
+                },
+                "Documents": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierDocuments",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The S3 location of the training documents.  \n      This parameter is required in a request to create a native document model.</p>"
+                    }
+                },
+                "DocumentReaderConfig": {
+                    "target": "com.amazonaws.comprehend#DocumentReaderConfig"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The input properties for training a document classifier. </p>\n         <p>For more information on how the input file is formatted, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/prep-classifier-data.html\">Preparing training data</a> in the Comprehend Developer Guide.\n    </p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierMode": {
+            "type": "enum",
+            "members": {
+                "MULTI_CLASS": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "MULTI_CLASS"
+                    }
+                },
+                "MULTI_LABEL": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "MULTI_LABEL"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierOutputDataConfig": {
+            "type": "structure",
+            "members": {
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>When you use the <code>OutputDataConfig</code> object while creating a custom\n      classifier, you specify the Amazon S3 location where you want to write the confusion matrix\n      and other output files.\n      The URI must be in the same Region as the API endpoint that you are calling. The location is\n      used as the prefix for the actual location of this output file.</p>\n         <p>When the custom classifier job is finished, the service creates the output file in a\n      directory specific to the job. The <code>S3Uri</code> field contains the location of the\n      output file, called <code>output.tar.gz</code>. It is a compressed archive that contains the\n      confusion matrix.</p>"
+                    }
+                },
+                "KmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the\n      output results from an analysis job. The KmsKeyId can be one of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>KMS Key Alias: <code>\"alias/ExampleAlias\"</code>\n               </p>\n            </li>\n            <li>\n               <p>ARN of a KMS Key Alias:\n            <code>\"arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "FlywheelStatsS3Prefix": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon S3 prefix for the data lake location of the flywheel statistics.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provide the location for output data from a custom classifier job. This field is mandatory \n      if you are training a native document model.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierProperties": {
+            "type": "structure",
+            "members": {
+                "DocumentClassifierArn": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) that identifies the document classifier.</p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language code for the language of the documents that the classifier was trained\n      on.</p>"
+                    }
+                },
+                "Status": {
+                    "target": "com.amazonaws.comprehend#ModelStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the document classifier. If the status is <code>TRAINED</code> the\n      classifier is ready to use. If the status is <code>TRAINED_WITH_WARNINGS</code> the\n      classifier training succeeded, but you should review the warnings returned in the \n      <code>CreateDocumentClassifier</code> response.</p>\n         <p>  If the status is <code>FAILED</code> you can see additional\n      information about why the classifier wasn't trained in the <code>Message</code> field.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Additional information about the status of the classifier.</p>"
+                    }
+                },
+                "SubmitTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the document classifier was submitted for training.</p>"
+                    }
+                },
+                "EndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that training the document classifier completed.</p>"
+                    }
+                },
+                "TrainingStartTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Indicates the time when the training starts on documentation classifiers. You are billed\n      for the time interval between this time and the value of TrainingEndTime. </p>"
+                    }
+                },
+                "TrainingEndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that training of the document classifier was completed. Indicates the time when\n      the training completes on documentation classifiers. You are billed for the time interval\n      between this time and the value of TrainingStartTime.</p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierInputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The input data configuration that you supplied when you created the document classifier\n      for training.</p>"
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierOutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Provides output results configuration parameters for custom classifier jobs.</p>"
+                    }
+                },
+                "ClassifierMetadata": {
+                    "target": "com.amazonaws.comprehend#ClassifierMetadata",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Information about the document classifier, including the number of documents used for\n      training the classifier, the number of documents used for test the classifier, and an accuracy\n      rating.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>"
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Configuration parameters for a private Virtual Private Cloud (VPC) containing the\n      resources you are using for your custom classifier. For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                },
+                "Mode": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierMode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Indicates the mode in which the specific classifier was trained. This also indicates the\n      format of input documents and the format of the confusion matrix. Each classifier can only be\n      trained in one mode and this cannot be changed once the classifier is trained.</p>"
+                    }
+                },
+                "ModelKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the KMS key that Amazon Comprehend uses to encrypt\n      trained custom models. The ModelKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VersionName": {
+                    "target": "com.amazonaws.comprehend#VersionName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The version name that you assigned to the document classifier.</p>"
+                    }
+                },
+                "SourceModelArn": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the source model. This model was imported from a\n      different Amazon Web Services account to create the document classifier model in your Amazon Web Services account.</p>"
+                    }
+                },
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information about a document classifier.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#DocumentClassifierProperties"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierSummariesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#DocumentClassifierSummary"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentClassifierSummary": {
+            "type": "structure",
+            "members": {
+                "DocumentClassifierName": {
+                    "target": "com.amazonaws.comprehend#ComprehendArnName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name that you assigned the document classifier.</p>"
+                    }
+                },
+                "NumberOfVersions": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The number of versions you created.</p>"
+                    }
+                },
+                "LatestVersionCreatedAt": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the latest document classifier version was submitted for processing.</p>"
+                    }
+                },
+                "LatestVersionName": {
+                    "target": "com.amazonaws.comprehend#VersionName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The version name you assigned to the latest document classifier version.</p>"
+                    }
+                },
+                "LatestVersionStatus": {
+                    "target": "com.amazonaws.comprehend#ModelStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Provides the status of the latest document classifier version.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Describes information about a document classifier and its versions.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentLabel": {
+            "type": "structure",
+            "members": {
+                "Name": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name of the label.</p>"
+                    }
+                },
+                "Score": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The confidence score that Amazon Comprehend has this label correctly attributed.</p>"
+                    }
+                },
+                "Page": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Page number where the label occurs. This field is present\n      in the response only if your request includes the <code>Byte</code> parameter. </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Specifies one of the label or labels that categorize the document being analyzed.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentMetadata": {
+            "type": "structure",
+            "members": {
+                "Pages": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Number of pages in the document.</p>"
+                    }
+                },
+                "ExtractedCharacters": {
+                    "target": "com.amazonaws.comprehend#ListOfExtractedCharacters",
+                    "traits": {
+                        "smithy.api#documentation": "<p>List of pages in the document, with the number of characters extracted from each page.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Information about the document, discovered during text extraction.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentReadAction": {
+            "type": "enum",
+            "members": {
+                "TEXTRACT_DETECT_DOCUMENT_TEXT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TEXTRACT_DETECT_DOCUMENT_TEXT"
+                    }
+                },
+                "TEXTRACT_ANALYZE_DOCUMENT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TEXTRACT_ANALYZE_DOCUMENT"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#DocumentReadFeatureTypes": {
+            "type": "enum",
+            "members": {
+                "TABLES": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TABLES"
+                    }
+                },
+                "FORMS": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "FORMS"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>TABLES or FORMS</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentReadMode": {
+            "type": "enum",
+            "members": {
+                "SERVICE_DEFAULT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "SERVICE_DEFAULT"
+                    }
+                },
+                "FORCE_DOCUMENT_READ_ACTION": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "FORCE_DOCUMENT_READ_ACTION"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#DocumentReaderConfig": {
+            "type": "structure",
+            "members": {
+                "DocumentReadAction": {
+                    "target": "com.amazonaws.comprehend#DocumentReadAction",
+                    "traits": {
+                        "smithy.api#documentation": "<p>This field defines the Amazon Textract API operation that Amazon Comprehend uses to extract text from PDF files and image files.\n      Enter one of the following values:</p>\n         <ul>\n            <li>\n               <p>\n                  <code>TEXTRACT_DETECT_DOCUMENT_TEXT</code> - The Amazon Comprehend service uses the <code>DetectDocumentText</code>\n           API operation. </p>\n            </li>\n            <li>\n               <p>\n                  <code>TEXTRACT_ANALYZE_DOCUMENT</code> - The Amazon Comprehend service uses the <code>AnalyzeDocument</code>\n          API operation. </p>\n            </li>\n         </ul>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DocumentReadMode": {
+                    "target": "com.amazonaws.comprehend#DocumentReadMode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Determines the text extraction actions for PDF files. Enter one of the following values:</p>\n         <ul>\n            <li>\n               <p>\n                  <code>SERVICE_DEFAULT</code> - use the Amazon Comprehend service defaults for PDF files.</p>\n            </li>\n            <li>\n               <p>\n                  <code>FORCE_DOCUMENT_READ_ACTION</code> - Amazon Comprehend uses the Textract API specified by\n          DocumentReadAction for all PDF files, including digital PDF files. </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "FeatureTypes": {
+                    "target": "com.amazonaws.comprehend#ListOfDocumentReadFeatureTypes",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the type of Amazon Textract features to apply. If you chose <code>TEXTRACT_ANALYZE_DOCUMENT</code>\n      as the read action, you must specify one or both of the following values:</p>\n         <ul>\n            <li>\n               <p>\n                  <code>TABLES</code> - Returns additional information about any tables that are detected in the input document. </p>\n            </li>\n            <li>\n               <p>\n                  <code>FORMS</code> - Returns additional information about any forms that are detected in the input document. </p>\n            </li>\n         </ul>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides configuration parameters to override the default actions for extracting text from PDF documents and image files. </p>\n         <p> By default, Amazon Comprehend performs the following actions to extract text from files, based on the input file type: </p>\n         <ul>\n            <li>\n               <p>\n                  <b>Word files</b> - Amazon Comprehend parser extracts the text. </p>\n            </li>\n            <li>\n               <p>\n                  <b>Digital PDF files</b> - Amazon Comprehend parser extracts the text. </p>\n            </li>\n            <li>\n               <p>\n                  <b>Image files and scanned PDF files</b> - Amazon Comprehend uses the Amazon Textract <code>DetectDocumentText</code>\n          API to extract the text. </p>\n            </li>\n         </ul>\n         <p>\n            <code>DocumentReaderConfig</code> does not apply to plain text files or Word files.</p>\n         <p>\n        For image files and PDF documents, you can override these default actions using the fields listed below.\n        For more information, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/idp-set-textract-options.html\">\n        Setting text extraction options</a> in the Comprehend Developer Guide.\n    </p>"
+            }
+        },
+        "com.amazonaws.comprehend#DocumentType": {
+            "type": "enum",
+            "members": {
+                "NATIVE_PDF": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "NATIVE_PDF"
+                    }
+                },
+                "SCANNED_PDF": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "SCANNED_PDF"
+                    }
+                },
+                "MS_WORD": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "MS_WORD"
+                    }
+                },
+                "IMAGE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "IMAGE"
+                    }
+                },
+                "PLAIN_TEXT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PLAIN_TEXT"
+                    }
+                },
+                "TEXTRACT_DETECT_DOCUMENT_TEXT_JSON": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TEXTRACT_DETECT_DOCUMENT_TEXT_JSON"
+                    }
+                },
+                "TEXTRACT_ANALYZE_DOCUMENT_JSON": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TEXTRACT_ANALYZE_DOCUMENT_JSON"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#DocumentTypeListItem": {
+            "type": "structure",
+            "members": {
+                "Page": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Page number.</p>"
+                    }
+                },
+                "Type": {
+                    "target": "com.amazonaws.comprehend#DocumentType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Document type.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Document type for each page in the document.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DominantLanguage": {
+            "type": "structure",
+            "members": {
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The RFC 5646 language code for the dominant language. For more information about RFC\n      5646, see <a href=\"https://tools.ietf.org/html/rfc5646\">Tags for Identifying\n        Languages</a> on the <i>IETF Tools</i> web site.</p>"
+                    }
+                },
+                "Score": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The level of confidence that Amazon Comprehend has in the accuracy of the\n      detection.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Returns the code for the dominant language in the input text and the level of\n      confidence that Amazon Comprehend has in the accuracy of the detection.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DominantLanguageDetectionJobFilter": {
+            "type": "structure",
+            "members": {
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters on the name of the job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on job status. Returns only jobs with the specified\n      status.</p>"
+                    }
+                },
+                "SubmitTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted before the specified time. Jobs are returned in ascending order,\n      oldest to newest.</p>"
+                    }
+                },
+                "SubmitTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted after the specified time. Jobs are returned in descending order,\n      newest to oldest.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information for filtering a list of dominant language detection jobs. For more\n      information, see the \n      operation.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DominantLanguageDetectionJobProperties": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier assigned to the dominant language detection job.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the dominant language detection job. It is a unique,\n      fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID.\n      The format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:dominant-language-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:dominant-language-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name that you assigned to the dominant language detection job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The current status of the dominant language detection job. If the status is\n        <code>FAILED</code>, the <code>Message</code> field shows the reason for the failure.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A description for the status of a job.</p>"
+                    }
+                },
+                "SubmitTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the dominant language detection job was submitted for processing.</p>"
+                    }
+                },
+                "EndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the dominant language detection job completed.</p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The input data configuration that you supplied when you created the dominant language\n      detection job.</p>"
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The output data configuration that you supplied when you created the dominant language\n      detection job.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>"
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Configuration parameters for a private Virtual Private Cloud (VPC) containing the\n      resources you are using for your dominant language detection job. For more information, see\n      <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information about a dominant language detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#DominantLanguageDetectionJobPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#DominantLanguageDetectionJobProperties"
+            }
+        },
+        "com.amazonaws.comprehend#Double": {
+            "type": "double"
+        },
+        "com.amazonaws.comprehend#EndpointFilter": {
+            "type": "structure",
+            "members": {
+                "ModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the model to which the endpoint is attached.</p>"
+                    }
+                },
+                "Status": {
+                    "target": "com.amazonaws.comprehend#EndpointStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the status of the endpoint being returned. Possible values are: Creating, Ready,\n      Updating, Deleting, Failed.</p>"
+                    }
+                },
+                "CreationTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies a date before which the returned endpoint or endpoints were created.</p>"
+                    }
+                },
+                "CreationTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies a date after which the returned endpoint or endpoints were created.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The filter used to determine which endpoints are returned. You can filter jobs on their\n      name, model, status, or the date and time that they were created. You can only set one filter\n      at a time. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#EndpointProperties": {
+            "type": "structure",
+            "members": {
+                "EndpointArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendEndpointArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the endpoint.</p>"
+                    }
+                },
+                "Status": {
+                    "target": "com.amazonaws.comprehend#EndpointStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the status of the endpoint. Because the endpoint updates and creation are\n      asynchronous, so customers will need to wait for the endpoint to be <code>Ready</code> status\n      before making inference requests.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies a reason for failure in cases of <code>Failed</code> status.</p>"
+                    }
+                },
+                "ModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the model to which the endpoint is attached.</p>"
+                    }
+                },
+                "DesiredModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ARN of the new model to use for updating an existing endpoint. This ARN is going to be\n      different from the model ARN when the update is in progress</p>"
+                    }
+                },
+                "DesiredInferenceUnits": {
+                    "target": "com.amazonaws.comprehend#InferenceUnitsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The desired number of inference units to be used by the model using this endpoint.\n      \n      Each inference unit represents of a throughput of 100 characters per second.</p>"
+                    }
+                },
+                "CurrentInferenceUnits": {
+                    "target": "com.amazonaws.comprehend#InferenceUnitsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The number of inference units currently used by the model using this endpoint.</p>"
+                    }
+                },
+                "CreationTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The creation date and time of the endpoint.</p>"
+                    }
+                },
+                "LastModifiedTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The date and time that the endpoint was last modified.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to trained custom models encrypted with a customer\n      managed key (ModelKmsKeyId).</p>"
+                    }
+                },
+                "DesiredDataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Data access role ARN to use in case the new model is encrypted with a customer KMS\n      key.</p>"
+                    }
+                },
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Specifies information about the specified endpoint.\n      For information about endpoints, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/manage-endpoints.html\">Managing endpoints</a>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EndpointPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#EndpointProperties"
+            }
+        },
+        "com.amazonaws.comprehend#EndpointStatus": {
+            "type": "enum",
+            "members": {
+                "CREATING": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "CREATING"
+                    }
+                },
+                "DELETING": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "DELETING"
+                    }
+                },
+                "FAILED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "FAILED"
+                    }
+                },
+                "IN_SERVICE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "IN_SERVICE"
+                    }
+                },
+                "UPDATING": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "UPDATING"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#EntitiesDetectionJobFilter": {
+            "type": "structure",
+            "members": {
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters on the name of the job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on job status. Returns only jobs with the specified\n      status.</p>"
+                    }
+                },
+                "SubmitTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted before the specified time. Jobs are returned in ascending order,\n      oldest to newest.</p>"
+                    }
+                },
+                "SubmitTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted after the specified time. Jobs are returned in descending order,\n      newest to oldest.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information for filtering a list of dominant language detection jobs. For more\n      information, see the  operation.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntitiesDetectionJobProperties": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier assigned to the entities detection job.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the entities detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:entities-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:entities-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name that you assigned the entities detection job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The current status of the entities detection job. If the status is <code>FAILED</code>,\n      the <code>Message</code> field shows the reason for the failure.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A description of the status of a job.</p>"
+                    }
+                },
+                "SubmitTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the entities detection job was submitted for processing.</p>"
+                    }
+                },
+                "EndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the entities detection job completed</p>"
+                    }
+                },
+                "EntityRecognizerArn": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) that identifies the entity recognizer.</p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The input data configuration that you supplied when you created the entities detection\n      job.</p>"
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The output data configuration that you supplied when you created the entities detection\n      job. </p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language code of the input documents.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>"
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Configuration parameters for a private Virtual Private Cloud (VPC) containing the\n      resources you are using for your entity detection job. For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                },
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the flywheel associated with this job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information about an entities detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntitiesDetectionJobPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#EntitiesDetectionJobProperties"
+            }
+        },
+        "com.amazonaws.comprehend#Entity": {
+            "type": "structure",
+            "members": {
+                "Score": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The level of confidence that Amazon Comprehend has in the accuracy of the\n      detection.</p>"
+                    }
+                },
+                "Type": {
+                    "target": "com.amazonaws.comprehend#EntityType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The entity type. For entity detection using the built-in model, this field contains one of the\n      standard entity types listed below.</p>\n         <p>For custom entity detection, this field contains one of the\n      entity types that you specified when you trained your custom model.</p>"
+                    }
+                },
+                "Text": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The text of the entity.</p>"
+                    }
+                },
+                "BeginOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based offset from the beginning of the source text to the first character in the\n      entity.</p>\n         <p>This field is empty for non-text input.</p>"
+                    }
+                },
+                "EndOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based offset from the beginning of the source text to the last character in the\n      entity.</p>\n         <p>This field is empty for non-text input.</p>"
+                    }
+                },
+                "BlockReferences": {
+                    "target": "com.amazonaws.comprehend#ListOfBlockReferences",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A reference to each block for this entity. This field is empty for plain-text input.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information about an entity. </p>\n         <p> </p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityLabel": {
+            "type": "structure",
+            "members": {
+                "Name": {
+                    "target": "com.amazonaws.comprehend#PiiEntityType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name of the label.</p>"
+                    }
+                },
+                "Score": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The level of confidence that Amazon Comprehend has in the accuracy of the\n      detection.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Specifies one of the label or labels that categorize the personally identifiable\n      information (PII) entity being analyzed.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognitionConfig": {
+            "type": "structure",
+            "members": {
+                "EntityTypes": {
+                    "target": "com.amazonaws.comprehend#EntityTypesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Up to 25 entity types that the model is trained to recognize.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Configuration required for an entity recognition model.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerAnnotations": {
+            "type": "structure",
+            "members": {
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Specifies the Amazon S3 location where the annotations for an entity recognizer are\n      located. The URI must be in the same Region as the API endpoint that you are calling.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "TestS3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Specifies the Amazon S3 location where the test annotations for an entity recognizer are\n      located. The URI must be in the same Region as the API endpoint that you are calling.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Describes the annotations associated with a entity recognizer.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerArn": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 256
+                },
+                "smithy.api#pattern": "^arn:aws(-[^:]+)?:comprehend:[a-zA-Z0-9-]*:[0-9]{12}:entity-recognizer/[a-zA-Z0-9](-*[a-zA-Z0-9])*(/version/[a-zA-Z0-9](-*[a-zA-Z0-9])*)?$"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerAugmentedManifestsList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#AugmentedManifestsListItem"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerDataFormat": {
+            "type": "enum",
+            "members": {
+                "COMPREHEND_CSV": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "COMPREHEND_CSV"
+                    }
+                },
+                "AUGMENTED_MANIFEST": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "AUGMENTED_MANIFEST"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerDocuments": {
+            "type": "structure",
+            "members": {
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Specifies the Amazon S3 location where the training documents for an entity recognizer\n      are located. The URI must be in the same Region as the API endpoint that you are\n      calling.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "TestS3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Specifies the Amazon S3 location where the test documents for an entity recognizer are\n      located. The URI must be in the same Amazon Web Services Region as the API endpoint that you are\n      calling.</p>"
+                    }
+                },
+                "InputFormat": {
+                    "target": "com.amazonaws.comprehend#InputFormat",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Specifies how the text in an input file should be processed. This is optional, and the\n      default is ONE_DOC_PER_LINE. ONE_DOC_PER_FILE - Each file is considered a separate document.\n      Use this option when you are processing large documents, such as newspaper articles or\n      scientific papers. ONE_DOC_PER_LINE - Each line in a file is considered a separate document.\n      Use this option when you are processing many short documents, such as text messages.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Describes the training documents submitted with an entity recognizer.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerEndpointArn": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 256
+                },
+                "smithy.api#pattern": "^arn:aws(-[^:]+)?:comprehend:[a-zA-Z0-9-]*:[0-9]{12}:entity-recognizer-endpoint/[a-zA-Z0-9](-*[a-zA-Z0-9])*$"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerEntityList": {
+            "type": "structure",
+            "members": {
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the Amazon S3 location where the entity list is located. The URI must be in the\n      same Region as the API endpoint that you are calling.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Describes the entity list submitted with an entity recognizer.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerEvaluationMetrics": {
+            "type": "structure",
+            "members": {
+                "Precision": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A measure of the usefulness of the recognizer results in the test data. High precision\n      means that the recognizer returned substantially more relevant results than irrelevant ones.\n    </p>"
+                    }
+                },
+                "Recall": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A measure of how complete the recognizer results are for the test data. High recall means\n      that the recognizer returned most of the relevant results.</p>"
+                    }
+                },
+                "F1Score": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A measure of how accurate the recognizer results are for the test data. It is derived from\n      the <code>Precision</code> and <code>Recall</code> values. The <code>F1Score</code> is the\n      harmonic average of the two scores. For plain text entity recognizer models, the range is 0 to 100,\n      where 100 is the best score. For PDF/Word entity recognizer models, the range is 0 to 1,\n      where 1 is the best score.\n    </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Detailed information about the accuracy of an entity recognizer. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerFilter": {
+            "type": "structure",
+            "members": {
+                "Status": {
+                    "target": "com.amazonaws.comprehend#ModelStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of an entity recognizer.</p>"
+                    }
+                },
+                "RecognizerName": {
+                    "target": "com.amazonaws.comprehend#ComprehendArnName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name that you assigned the entity recognizer.</p>"
+                    }
+                },
+                "SubmitTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of entities based on the time that the list was submitted for processing.\n      Returns only jobs submitted before the specified time. Jobs are returned in descending order,\n      newest to oldest.</p>"
+                    }
+                },
+                "SubmitTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of entities based on the time that the list was submitted for processing.\n      Returns only jobs submitted after the specified time. Jobs are returned in ascending order,\n      oldest to newest.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information for filtering a list of entity recognizers. You can only specify one\n      filtering parameter in a request. For more information, see the \n        <code>ListEntityRecognizers</code> operation./></p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerInputDataConfig": {
+            "type": "structure",
+            "members": {
+                "DataFormat": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerDataFormat",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The format of your training data:</p>\n         <ul>\n            <li>\n               <p>\n                  <code>COMPREHEND_CSV</code>: A CSV file that supplements your training documents. The\n          CSV file contains information about the custom entities that your trained model will\n          detect. The required format of the file depends on whether you are providing annotations\n          or an entity list.</p>\n               <p>If you use this value, you must provide your CSV file by using either the\n            <code>Annotations</code> or <code>EntityList</code> parameters. You must provide your\n          training documents by using the <code>Documents</code> parameter.</p>\n            </li>\n            <li>\n               <p>\n                  <code>AUGMENTED_MANIFEST</code>: A labeled dataset that is produced by Amazon\n          SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON\n          object that contains a training document and its labels. Each label annotates a named\n          entity in the training document. </p>\n               <p>If you use this value, you must provide the <code>AugmentedManifests</code> parameter\n          in your request.</p>\n            </li>\n         </ul>\n         <p>If you don't specify a value, Amazon Comprehend uses <code>COMPREHEND_CSV</code> as the\n      default.</p>"
+                    }
+                },
+                "EntityTypes": {
+                    "target": "com.amazonaws.comprehend#EntityTypesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The entity types in the labeled training data that Amazon Comprehend uses to train the\n      custom entity recognizer. Any entity types that you don't specify are ignored.</p>\n         <p>A maximum of 25 entity types can be used at one time to train an entity recognizer. Entity\n      types must not contain the following invalid characters: \\n (line break), \\\\n (escaped line\n      break), \\r (carriage return), \\\\r (escaped carriage return), \\t (tab), \\\\t (escaped tab),\n      space, and , (comma). </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "Documents": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerDocuments",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The S3 location of the folder that contains the training documents for your custom entity\n      recognizer.</p>\n         <p>This parameter is required if you set <code>DataFormat</code> to\n        <code>COMPREHEND_CSV</code>.</p>"
+                    }
+                },
+                "Annotations": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerAnnotations",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The S3 location of the CSV file that annotates your training documents.</p>"
+                    }
+                },
+                "EntityList": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerEntityList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The S3 location of the CSV file that has the entity list for your custom entity\n      recognizer.</p>"
+                    }
+                },
+                "AugmentedManifests": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerAugmentedManifestsList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list of augmented manifest files that provide training data for your custom model. An\n      augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground\n      Truth.</p>\n         <p>This parameter is required if you set <code>DataFormat</code> to\n        <code>AUGMENTED_MANIFEST</code>.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Specifies the format and location of the input data.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerMetadata": {
+            "type": "structure",
+            "members": {
+                "NumberOfTrainedDocuments": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p> The number of documents in the input data that were used to train the entity recognizer.\n      Typically this is 80 to 90 percent of the input documents.</p>"
+                    }
+                },
+                "NumberOfTestDocuments": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p> The number of documents in the input data that were used to test the entity recognizer.\n      Typically this is 10 to 20 percent of the input documents.</p>"
+                    }
+                },
+                "EvaluationMetrics": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerEvaluationMetrics",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Detailed information about the accuracy of an entity recognizer.</p>"
+                    }
+                },
+                "EntityTypes": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerMetadataEntityTypesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Entity types from the metadata of an entity recognizer.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Detailed information about an entity recognizer.</p>",
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerMetadataEntityTypesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#EntityRecognizerMetadataEntityTypesListItem"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerMetadataEntityTypesListItem": {
+            "type": "structure",
+            "members": {
+                "Type": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Type of entity from the list of entity types in the metadata of an entity recognizer.\n    </p>"
+                    }
+                },
+                "EvaluationMetrics": {
+                    "target": "com.amazonaws.comprehend#EntityTypesEvaluationMetrics",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Detailed information about the accuracy of the entity recognizer for a specific item on\n      the list of entity types. </p>"
+                    }
+                },
+                "NumberOfTrainMentions": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Indicates the number of times the given entity type was seen in the training data. </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Individual item from the list of entity types in the metadata of an entity\n      recognizer.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerOutputDataConfig": {
+            "type": "structure",
+            "members": {
+                "FlywheelStatsS3Prefix": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon S3 prefix for the data lake location of the flywheel statistics.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Output data configuration.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerProperties": {
+            "type": "structure",
+            "members": {
+                "EntityRecognizerArn": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) that identifies the entity recognizer.</p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p> The language of the input documents. All documents must be in the same language. Only\n      English (\"en\") is currently supported.</p>"
+                    }
+                },
+                "Status": {
+                    "target": "com.amazonaws.comprehend#ModelStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Provides the status of the entity recognizer.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p> A description of the status of the recognizer.</p>"
+                    }
+                },
+                "SubmitTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the recognizer was submitted for processing.</p>"
+                    }
+                },
+                "EndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the recognizer creation completed.</p>"
+                    }
+                },
+                "TrainingStartTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that training of the entity recognizer started.</p>"
+                    }
+                },
+                "TrainingEndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that training of the entity recognizer was completed.</p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerInputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The input data properties of an entity recognizer.</p>"
+                    }
+                },
+                "RecognizerMetadata": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerMetadata",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Provides information about an entity recognizer.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p> The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>"
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Configuration parameters for a private Virtual Private Cloud (VPC) containing the\n      resources you are using for your custom entity recognizer. For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                },
+                "ModelKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the KMS key that Amazon Comprehend uses to encrypt\n      trained custom models. The ModelKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VersionName": {
+                    "target": "com.amazonaws.comprehend#VersionName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The version name you assigned to the entity recognizer.</p>"
+                    }
+                },
+                "SourceModelArn": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the source model. This model was imported from a\n      different Amazon Web Services account to create the entity recognizer model in your Amazon Web Services account.</p>"
+                    }
+                },
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel</p>"
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerOutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Output data configuration.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Describes information about an entity recognizer.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#EntityRecognizerProperties"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerSummariesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#EntityRecognizerSummary"
+            }
+        },
+        "com.amazonaws.comprehend#EntityRecognizerSummary": {
+            "type": "structure",
+            "members": {
+                "RecognizerName": {
+                    "target": "com.amazonaws.comprehend#ComprehendArnName",
+                    "traits": {
+                        "smithy.api#documentation": "<p> The name that you assigned the entity recognizer.</p>"
+                    }
+                },
+                "NumberOfVersions": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p> The number of versions you created.</p>"
+                    }
+                },
+                "LatestVersionCreatedAt": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p> The time that the latest entity recognizer version was submitted for processing.</p>"
+                    }
+                },
+                "LatestVersionName": {
+                    "target": "com.amazonaws.comprehend#VersionName",
+                    "traits": {
+                        "smithy.api#documentation": "<p> The version name you assigned to the latest entity recognizer version.</p>"
+                    }
+                },
+                "LatestVersionStatus": {
+                    "target": "com.amazonaws.comprehend#ModelStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Provides the status of the latest entity recognizer version.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p> Describes the information about an entity recognizer and its versions.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityType": {
+            "type": "enum",
+            "members": {
+                "PERSON": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PERSON"
+                    }
+                },
+                "LOCATION": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "LOCATION"
+                    }
+                },
+                "ORGANIZATION": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ORGANIZATION"
+                    }
+                },
+                "COMMERCIAL_ITEM": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "COMMERCIAL_ITEM"
+                    }
+                },
+                "EVENT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "EVENT"
+                    }
+                },
+                "DATE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "DATE"
+                    }
+                },
+                "QUANTITY": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "QUANTITY"
+                    }
+                },
+                "TITLE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TITLE"
+                    }
+                },
+                "OTHER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "OTHER"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#EntityTypeName": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 64
+                },
+                "smithy.api#pattern": "^(?![^\\n\\r\\t,]*\\\\n|\\\\r|\\\\t)[^\\n\\r\\t,]+$"
+            }
+        },
+        "com.amazonaws.comprehend#EntityTypesEvaluationMetrics": {
+            "type": "structure",
+            "members": {
+                "Precision": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A measure of the usefulness of the recognizer results for a specific entity type in the\n      test data. High precision means that the recognizer returned substantially more relevant\n      results than irrelevant ones. </p>"
+                    }
+                },
+                "Recall": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A measure of how complete the recognizer results are for a specific entity type in the\n      test data. High recall means that the recognizer returned most of the relevant results.</p>"
+                    }
+                },
+                "F1Score": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A measure of how accurate the recognizer results are for a specific entity type in the\n      test data. It is derived from the <code>Precision</code> and <code>Recall</code> values. The\n        <code>F1Score</code> is the harmonic average of the two scores. The highest score is 1, and\n      the worst score is 0. </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Detailed information about the accuracy of an entity recognizer for a specific entity\n      type. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#EntityTypesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#EntityTypesListItem"
+            }
+        },
+        "com.amazonaws.comprehend#EntityTypesListItem": {
+            "type": "structure",
+            "members": {
+                "Type": {
+                    "target": "com.amazonaws.comprehend#EntityTypeName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An entity type within a labeled training dataset that Amazon Comprehend uses to train a\n      custom entity recognizer.</p>\n         <p>Entity types must not contain the following invalid characters: \\n (line break), \\\\n\n      (escaped line break, \\r (carriage return), \\\\r (escaped carriage return), \\t (tab), \\\\t\n      (escaped tab), and , (comma).</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>An entity type within a labeled training dataset that Amazon Comprehend uses to train a\n      custom entity recognizer.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#ErrorsListItem": {
+            "type": "structure",
+            "members": {
+                "Page": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Page number where the error occurred.</p>"
+                    }
+                },
+                "ErrorCode": {
+                    "target": "com.amazonaws.comprehend#PageBasedErrorCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Error code for the cause of the error.</p>"
+                    }
+                },
+                "ErrorMessage": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Text message explaining the reason for the error.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Text extraction encountered one or more page-level errors in the input document.</p>\n         <p>The <code>ErrorCode</code> contains one of the following values:</p>\n         <ul>\n            <li>\n               <p>TEXTRACT_BAD_PAGE - Amazon Textract cannot read the page. For more information\n          about page limits in Amazon Textract, see <a href=\"https://docs.aws.amazon.com/textract/latest/dg/limits-document.html\">\n            Page Quotas in Amazon Textract</a>.</p>\n            </li>\n            <li>\n               <p>TEXTRACT_PROVISIONED_THROUGHPUT_EXCEEDED - The number of requests exceeded your throughput limit.\n          For more information about throughput quotas in Amazon Textract, see <a href=\"https://docs.aws.amazon.com/textract/latest/dg/limits-quotas-explained.html\">\n            Default quotas in Amazon Textract</a>.</p>\n            </li>\n            <li>\n               <p>PAGE_CHARACTERS_EXCEEDED - Too many text characters on the page (10,000 characters maximum).</p>\n            </li>\n            <li>\n               <p>PAGE_SIZE_EXCEEDED - The maximum page size is 10 MB.</p>\n            </li>\n            <li>\n               <p>INTERNAL_SERVER_ERROR - The request encountered a service issue. Try the API request again.</p>\n            </li>\n         </ul>"
+            }
+        },
+        "com.amazonaws.comprehend#EventTypeString": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 40
+                },
+                "smithy.api#pattern": "^[A-Z_]*$"
+            }
+        },
+        "com.amazonaws.comprehend#EventsDetectionJobFilter": {
+            "type": "structure",
+            "members": {
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters on the name of the events detection job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on job status. Returns only jobs with the specified\n      status.</p>"
+                    }
+                },
+                "SubmitTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted before the specified time. Jobs are returned in ascending order,\n      oldest to newest.</p>"
+                    }
+                },
+                "SubmitTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted after the specified time. Jobs are returned in descending order,\n      newest to oldest.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information for filtering a list of event detection jobs.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EventsDetectionJobProperties": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier assigned to the events detection job.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the events detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:events-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:events-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name you assigned the events detection job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The current status of the events detection job.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A description of the status of the events detection job.</p>"
+                    }
+                },
+                "SubmitTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the events detection job was submitted for processing.</p>"
+                    }
+                },
+                "EndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the events detection job completed.</p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The input data configuration that you supplied when you created the events detection\n      job.</p>"
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The output data configuration that you supplied when you created the events detection\n      job.</p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language code of the input documents.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>"
+                    }
+                },
+                "TargetEventTypes": {
+                    "target": "com.amazonaws.comprehend#TargetEventTypes",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The types of events that are detected by the job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information about an events detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#EventsDetectionJobPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#EventsDetectionJobProperties"
+            }
+        },
+        "com.amazonaws.comprehend#ExtractedCharactersListItem": {
+            "type": "structure",
+            "members": {
+                "Page": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Page number.</p>"
+                    }
+                },
+                "Count": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Number of characters extracted from each page.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Array of the number of characters extracted from each page.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#Float": {
+            "type": "float"
+        },
+        "com.amazonaws.comprehend#FlywheelFilter": {
+            "type": "structure",
+            "members": {
+                "Status": {
+                    "target": "com.amazonaws.comprehend#FlywheelStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filter the flywheels based on the flywheel status.</p>"
+                    }
+                },
+                "CreationTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filter the flywheels to include flywheels created after the specified time.</p>"
+                    }
+                },
+                "CreationTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filter the flywheels to include flywheels created before the specified time.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Filter the flywheels based on creation time or flywheel status.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#FlywheelIterationFilter": {
+            "type": "structure",
+            "members": {
+                "CreationTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filter the flywheel iterations to include iterations created after the specified time.</p>"
+                    }
+                },
+                "CreationTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filter the flywheel iterations to include iterations created before the specified time.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Filter the flywheel iterations based on creation time.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#FlywheelIterationId": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 63
+                },
+                "smithy.api#pattern": "^[0-9]{8}T[0-9]{6}Z$"
+            }
+        },
+        "com.amazonaws.comprehend#FlywheelIterationProperties": {
+            "type": "structure",
+            "members": {
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p></p>"
+                    }
+                },
+                "FlywheelIterationId": {
+                    "target": "com.amazonaws.comprehend#FlywheelIterationId",
+                    "traits": {
+                        "smithy.api#documentation": "<p></p>"
+                    }
+                },
+                "CreationTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The creation start time of the flywheel iteration.</p>"
+                    }
+                },
+                "EndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The completion time of this flywheel iteration.</p>"
+                    }
+                },
+                "Status": {
+                    "target": "com.amazonaws.comprehend#FlywheelIterationStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the flywheel iteration.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A description of the status of the flywheel iteration.</p>"
+                    }
+                },
+                "EvaluatedModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The ARN of the evaluated model associated with this flywheel iteration.</p>"
+                    }
+                },
+                "EvaluatedModelMetrics": {
+                    "target": "com.amazonaws.comprehend#FlywheelModelEvaluationMetrics"
+                },
+                "TrainedModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The ARN of the trained model associated with this flywheel iteration.</p>"
+                    }
+                },
+                "TrainedModelMetrics": {
+                    "target": "com.amazonaws.comprehend#FlywheelModelEvaluationMetrics",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The metrics associated with the trained model.</p>"
+                    }
+                },
+                "EvaluationManifestS3Prefix": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p></p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The configuration properties of a flywheel iteration.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#FlywheelIterationPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#FlywheelIterationProperties"
+            }
+        },
+        "com.amazonaws.comprehend#FlywheelIterationStatus": {
+            "type": "enum",
+            "members": {
+                "TRAINING": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TRAINING"
+                    }
+                },
+                "EVALUATING": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "EVALUATING"
+                    }
+                },
+                "COMPLETED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "COMPLETED"
+                    }
+                },
+                "FAILED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "FAILED"
+                    }
+                },
+                "STOP_REQUESTED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "STOP_REQUESTED"
+                    }
+                },
+                "STOPPED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "STOPPED"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#FlywheelModelEvaluationMetrics": {
+            "type": "structure",
+            "members": {
+                "AverageF1Score": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The average F1 score from the evaluation metrics.</p>"
+                    }
+                },
+                "AveragePrecision": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Average precision metric for the model.</p>"
+                    }
+                },
+                "AverageRecall": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Average recall metric for the model.</p>"
+                    }
+                },
+                "AverageAccuracy": {
+                    "target": "com.amazonaws.comprehend#Double",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Average accuracy metric for the model.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The evaluation metrics associated with the evaluated model.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#FlywheelProperties": {
+            "type": "structure",
+            "members": {
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel.</p>"
+                    }
+                },
+                "ActiveModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the active model version.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend permission to access the flywheel data.</p>"
+                    }
+                },
+                "TaskConfig": {
+                    "target": "com.amazonaws.comprehend#TaskConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Configuration about the model associated with a flywheel.</p>"
+                    }
+                },
+                "DataLakeS3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Amazon S3 URI of the data lake location. </p>"
+                    }
+                },
+                "DataSecurityConfig": {
+                    "target": "com.amazonaws.comprehend#DataSecurityConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Data security configuration.</p>"
+                    }
+                },
+                "Status": {
+                    "target": "com.amazonaws.comprehend#FlywheelStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the flywheel.</p>"
+                    }
+                },
+                "ModelType": {
+                    "target": "com.amazonaws.comprehend#ModelType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Model type of the flywheel's model.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A description of the status of the flywheel.</p>"
+                    }
+                },
+                "CreationTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Creation time of the flywheel.</p>"
+                    }
+                },
+                "LastModifiedTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Last modified time for the flywheel.</p>"
+                    }
+                },
+                "LatestFlywheelIteration": {
+                    "target": "com.amazonaws.comprehend#FlywheelIterationId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The most recent flywheel iteration.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The flywheel properties.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#FlywheelS3Uri": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 512
+                },
+                "smithy.api#pattern": "^s3://[a-z0-9][\\.\\-a-z0-9]{1,61}[a-z0-9](/.*)?$"
+            }
+        },
+        "com.amazonaws.comprehend#FlywheelStatus": {
+            "type": "enum",
+            "members": {
+                "CREATING": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "CREATING"
+                    }
+                },
+                "ACTIVE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ACTIVE"
+                    }
+                },
+                "UPDATING": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "UPDATING"
+                    }
+                },
+                "DELETING": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "DELETING"
+                    }
+                },
+                "FAILED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "FAILED"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#FlywheelSummary": {
+            "type": "structure",
+            "members": {
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel</p>"
+                    }
+                },
+                "ActiveModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ARN of the active model version for the flywheel.</p>"
+                    }
+                },
+                "DataLakeS3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Amazon S3 URI of the data lake location. </p>"
+                    }
+                },
+                "Status": {
+                    "target": "com.amazonaws.comprehend#FlywheelStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the flywheel.</p>"
+                    }
+                },
+                "ModelType": {
+                    "target": "com.amazonaws.comprehend#ModelType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Model type of the flywheel's model.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A description of the status of the flywheel.</p>"
+                    }
+                },
+                "CreationTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Creation time of the flywheel.</p>"
+                    }
+                },
+                "LastModifiedTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Last modified time for the flywheel.</p>"
+                    }
+                },
+                "LatestFlywheelIteration": {
+                    "target": "com.amazonaws.comprehend#FlywheelIterationId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The most recent flywheel iteration.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Flywheel summary information.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#FlywheelSummaryList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#FlywheelSummary"
+            }
+        },
+        "com.amazonaws.comprehend#Geometry": {
+            "type": "structure",
+            "members": {
+                "BoundingBox": {
+                    "target": "com.amazonaws.comprehend#BoundingBox",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An axis-aligned coarse representation of the location of the recognized item on the\n      document page.</p>"
+                    }
+                },
+                "Polygon": {
+                    "target": "com.amazonaws.comprehend#Polygon",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Within the bounding box, a fine-grained polygon around the recognized item.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Information about the location of items on a document page.</p>\n         <p>For additional information, see <a href=\"https://docs.aws.amazon.com/textract/latest/dg/API_Geometry.html\">Geometry</a> in the Amazon Textract API reference.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#IamRoleArn": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 20,
+                    "max": 2048
+                },
+                "smithy.api#pattern": "^arn:aws(-[^:]+)?:iam::[0-9]{12}:role/.+$"
+            }
+        },
+        "com.amazonaws.comprehend#ImportModel": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ImportModelRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ImportModelResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceUnavailableException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Creates a new custom model that replicates a source custom model that you import. The\n      source model can be in your Amazon Web Services account or another one.</p>\n         <p>If the source model is in another Amazon Web Services account, then it must have a resource-based policy\n      that authorizes you to import it.</p>\n         <p>The source model must be in the same Amazon Web Services Region that you're using when you import. You\n      can't import a model that's in a different Region.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#ImportModelRequest": {
+            "type": "structure",
+            "members": {
+                "SourceModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the custom model to import.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ModelName": {
+                    "target": "com.amazonaws.comprehend#ComprehendArnName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name to assign to the custom model that is created in Amazon Comprehend by this\n      import.</p>"
+                    }
+                },
+                "VersionName": {
+                    "target": "com.amazonaws.comprehend#VersionName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The version name given to the custom model that is created by this import. Version names\n      can have a maximum of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_)\n      are allowed. The version name must be unique among all models with the same classifier name in\n      the account/Region.</p>"
+                    }
+                },
+                "ModelKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the KMS key that Amazon Comprehend uses to encrypt\n      trained custom models. The ModelKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend permission to use Amazon Key Management Service (KMS) to encrypt or decrypt the custom\n      model.</p>"
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags to associate with the custom model that is created by this import. A tag is a\n      key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a\n      tag with \"Sales\" as the key might be added to a resource to indicate its use by the sales\n      department.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ImportModelResponse": {
+            "type": "structure",
+            "members": {
+                "ModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the custom model being imported.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#InferenceUnitsInteger": {
+            "type": "integer",
+            "traits": {
+                "smithy.api#range": {
+                    "min": 1
+                }
+            }
+        },
+        "com.amazonaws.comprehend#InputDataConfig": {
+            "type": "structure",
+            "members": {
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon S3 URI for the input data. The URI must be in same Region as the API\n      endpoint that you are calling. The URI can point to a single input file or it can provide the\n      prefix for a collection of data files. </p>\n         <p>For example, if you use the URI <code>S3://bucketName/prefix</code>, if the prefix is a\n      single file, Amazon Comprehend uses that file as input. If more than one file begins with the\n      prefix, Amazon Comprehend uses all of them as input.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "InputFormat": {
+                    "target": "com.amazonaws.comprehend#InputFormat",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies how the text in an input file should be processed:</p>\n         <ul>\n            <li>\n               <p>\n                  <code>ONE_DOC_PER_FILE</code> - Each file is considered a separate document. Use\n          this option when you are processing large documents, such as newspaper articles or\n          scientific papers.</p>\n            </li>\n            <li>\n               <p>\n                  <code>ONE_DOC_PER_LINE</code> - Each line in a file is considered a separate\n          document. Use this option when you are processing many short documents, such as text\n          messages.</p>\n            </li>\n         </ul>"
+                    }
+                },
+                "DocumentReaderConfig": {
+                    "target": "com.amazonaws.comprehend#DocumentReaderConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Provides configuration parameters to override the default actions for extracting text\n      from PDF documents and image files.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The input properties for an inference job. The document reader config field applies\n      only to non-text inputs for custom analysis.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#InputFormat": {
+            "type": "enum",
+            "members": {
+                "ONE_DOC_PER_FILE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ONE_DOC_PER_FILE"
+                    }
+                },
+                "ONE_DOC_PER_LINE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ONE_DOC_PER_LINE"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#Integer": {
+            "type": "integer"
+        },
+        "com.amazonaws.comprehend#InternalServerException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>An internal server error occurred. Retry your request.</p>",
+                "smithy.api#error": "server",
+                "smithy.api#httpError": 500
+            }
+        },
+        "com.amazonaws.comprehend#InvalidFilterException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The filter specified for the operation is invalid. Specify a different\n      filter.</p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 400
+            }
+        },
+        "com.amazonaws.comprehend#InvalidRequestDetail": {
+            "type": "structure",
+            "members": {
+                "Reason": {
+                    "target": "com.amazonaws.comprehend#InvalidRequestDetailReason",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Reason codes include the following values:</p>\n         <ul>\n            <li>\n               <p>DOCUMENT_SIZE_EXCEEDED - Document size is too large. Check the size of your file and resubmit the request.</p>\n            </li>\n            <li>\n               <p>UNSUPPORTED_DOC_TYPE - Document type is not supported. Check the file type and resubmit the request.</p>\n            </li>\n            <li>\n               <p>PAGE_LIMIT_EXCEEDED - Too many pages in the document. Check the number of pages in your file and resubmit the request.</p>\n            </li>\n            <li>\n               <p>TEXTRACT_ACCESS_DENIED - Access denied to Amazon Textract. Verify that your account has permission to use Amazon Textract API operations and resubmit the request.</p>\n            </li>\n            <li>\n               <p>NOT_TEXTRACT_JSON - Document is not Amazon Textract JSON format. Verify the format and resubmit the request.</p>\n            </li>\n            <li>\n               <p>MISMATCHED_TOTAL_PAGE_COUNT - Check the number of pages in your file and resubmit the request.</p>\n            </li>\n            <li>\n               <p>INVALID_DOCUMENT - Invalid document. Check the file and resubmit the request.</p>\n            </li>\n         </ul>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides additional detail about why the request failed.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#InvalidRequestDetailReason": {
+            "type": "enum",
+            "members": {
+                "DOCUMENT_SIZE_EXCEEDED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "DOCUMENT_SIZE_EXCEEDED"
+                    }
+                },
+                "UNSUPPORTED_DOC_TYPE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "UNSUPPORTED_DOC_TYPE"
+                    }
+                },
+                "PAGE_LIMIT_EXCEEDED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PAGE_LIMIT_EXCEEDED"
+                    }
+                },
+                "TEXTRACT_ACCESS_DENIED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TEXTRACT_ACCESS_DENIED"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#InvalidRequestException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                },
+                "Reason": {
+                    "target": "com.amazonaws.comprehend#InvalidRequestReason"
+                },
+                "Detail": {
+                    "target": "com.amazonaws.comprehend#InvalidRequestDetail"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The request is invalid.</p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 400
+            }
+        },
+        "com.amazonaws.comprehend#InvalidRequestReason": {
+            "type": "enum",
+            "members": {
+                "INVALID_DOCUMENT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "INVALID_DOCUMENT"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#JobId": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 32
+                },
+                "smithy.api#pattern": "^([\\p{L}\\p{Z}\\p{N}_.:/=+\\-%@]*)$"
+            }
+        },
+        "com.amazonaws.comprehend#JobName": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 256
+                },
+                "smithy.api#pattern": "^([\\p{L}\\p{Z}\\p{N}_.:/=+\\-%@]*)$"
+            }
+        },
+        "com.amazonaws.comprehend#JobNotFoundException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The specified job was not found. Check the job ID and try again.</p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 404
+            }
+        },
+        "com.amazonaws.comprehend#JobStatus": {
+            "type": "enum",
+            "members": {
+                "SUBMITTED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "SUBMITTED"
+                    }
+                },
+                "IN_PROGRESS": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "IN_PROGRESS"
+                    }
+                },
+                "COMPLETED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "COMPLETED"
+                    }
+                },
+                "FAILED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "FAILED"
+                    }
+                },
+                "STOP_REQUESTED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "STOP_REQUESTED"
+                    }
+                },
+                "STOPPED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "STOPPED"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#KeyPhrase": {
+            "type": "structure",
+            "members": {
+                "Score": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The level of confidence that Amazon Comprehend has in the accuracy of the\n      detection.</p>"
+                    }
+                },
+                "Text": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The text of a key noun phrase.</p>"
+                    }
+                },
+                "BeginOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based offset from the beginning of the source text to the first character in the\n      key phrase.</p>"
+                    }
+                },
+                "EndOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based offset from the beginning of the source text to the last character in the\n      key phrase.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Describes a key noun phrase.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#KeyPhrasesDetectionJobFilter": {
+            "type": "structure",
+            "members": {
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters on the name of the job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on job status. Returns only jobs with the specified\n      status.</p>"
+                    }
+                },
+                "SubmitTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted before the specified time. Jobs are returned in ascending order,\n      oldest to newest.</p>"
+                    }
+                },
+                "SubmitTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted after the specified time. Jobs are returned in descending order,\n      newest to oldest.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information for filtering a list of dominant language detection jobs. For more\n      information, see the  operation.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#KeyPhrasesDetectionJobProperties": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier assigned to the key phrases detection job.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the key phrases detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:key-phrases-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:key-phrases-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name that you assigned the key phrases detection job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The current status of the key phrases detection job. If the status is <code>FAILED</code>,\n      the <code>Message</code> field shows the reason for the failure.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A description of the status of a job.</p>"
+                    }
+                },
+                "SubmitTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the key phrases detection job was submitted for processing.</p>"
+                    }
+                },
+                "EndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the key phrases detection job completed.</p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The input data configuration that you supplied when you created the key phrases detection\n      job.</p>"
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The output data configuration that you supplied when you created the key phrases detection\n      job.</p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language code of the input documents.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>"
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the KMS key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Configuration parameters for a private Virtual Private Cloud (VPC) containing the\n      resources you are using for your key phrases detection job. For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information about a key phrases detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#KeyPhrasesDetectionJobPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#KeyPhrasesDetectionJobProperties"
+            }
+        },
+        "com.amazonaws.comprehend#KmsKeyId": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 2048
+                },
+                "smithy.api#pattern": "^\\p{ASCII}+$"
+            }
+        },
+        "com.amazonaws.comprehend#KmsKeyValidationException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The KMS customer managed key (CMK) entered cannot be validated. Verify the key and\n      re-enter it.</p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 400
+            }
+        },
+        "com.amazonaws.comprehend#LabelDelimiter": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 1
+                },
+                "smithy.api#pattern": "^[ ~!@#$%^*\\-_+=|\\\\:;\\t>?/]$"
+            }
+        },
+        "com.amazonaws.comprehend#LabelListItem": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 5000
+                },
+                "smithy.api#pattern": "^\\P{C}*$"
+            }
+        },
+        "com.amazonaws.comprehend#LabelsList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#LabelListItem"
+            },
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 1000
+                }
+            }
+        },
+        "com.amazonaws.comprehend#LanguageCode": {
+            "type": "enum",
+            "members": {
+                "EN": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "en"
+                    }
+                },
+                "ES": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "es"
+                    }
+                },
+                "FR": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "fr"
+                    }
+                },
+                "DE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "de"
+                    }
+                },
+                "IT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "it"
+                    }
+                },
+                "PT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "pt"
+                    }
+                },
+                "AR": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ar"
+                    }
+                },
+                "HI": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "hi"
+                    }
+                },
+                "JA": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ja"
+                    }
+                },
+                "KO": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ko"
+                    }
+                },
+                "ZH": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "zh"
+                    }
+                },
+                "ZH_TW": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "zh-TW"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListDatasets": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListDatasetsRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListDatasetsResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>List the datasets that you have configured in this Region. For more information about datasets, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/flywheels-about.html\">\n      Flywheel overview</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListDatasetsRequest": {
+            "type": "structure",
+            "members": {
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel.</p>"
+                    }
+                },
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#DatasetFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the datasets to be returned in the response.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Maximum number of results to return in a response. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListDatasetsResponse": {
+            "type": "structure",
+            "members": {
+                "DatasetPropertiesList": {
+                    "target": "com.amazonaws.comprehend#DatasetPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The dataset properties list.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListDocumentClassificationJobs": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListDocumentClassificationJobsRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListDocumentClassificationJobsResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of the documentation classification jobs that you have submitted.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListDocumentClassificationJobsRequest": {
+            "type": "structure",
+            "members": {
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#DocumentClassificationJobFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the jobs that are returned. You can filter jobs on their names, status, or the\n      date and time that they were submitted. You can only set one filter at a time.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The maximum number of results to return in each page. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListDocumentClassificationJobsResponse": {
+            "type": "structure",
+            "members": {
+                "DocumentClassificationJobPropertiesList": {
+                    "target": "com.amazonaws.comprehend#DocumentClassificationJobPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the properties of each job returned.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListDocumentClassifierSummaries": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListDocumentClassifierSummariesRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListDocumentClassifierSummariesResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of summaries of the document classifiers that you have created</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListDocumentClassifierSummariesRequest": {
+            "type": "structure",
+            "members": {
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The maximum number of results to return on each page. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListDocumentClassifierSummariesResponse": {
+            "type": "structure",
+            "members": {
+                "DocumentClassifierSummariesList": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierSummariesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The list of summaries of document classifiers.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListDocumentClassifiers": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListDocumentClassifiersRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListDocumentClassifiersResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of the document classifiers that you have created.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListDocumentClassifiersRequest": {
+            "type": "structure",
+            "members": {
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the jobs that are returned. You can filter jobs on their name, status, or the date\n      and time that they were submitted. You can only set one filter at a time.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The maximum number of results to return in each page. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListDocumentClassifiersResponse": {
+            "type": "structure",
+            "members": {
+                "DocumentClassifierPropertiesList": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the properties of each job returned.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListDominantLanguageDetectionJobs": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListDominantLanguageDetectionJobsRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListDominantLanguageDetectionJobsResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of the dominant language detection jobs that you have submitted.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListDominantLanguageDetectionJobsRequest": {
+            "type": "structure",
+            "members": {
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#DominantLanguageDetectionJobFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters that jobs that are returned. You can filter jobs on their name, status, or the\n      date and time that they were submitted. You can only set one filter at a time.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The maximum number of results to return in each page. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListDominantLanguageDetectionJobsResponse": {
+            "type": "structure",
+            "members": {
+                "DominantLanguageDetectionJobPropertiesList": {
+                    "target": "com.amazonaws.comprehend#DominantLanguageDetectionJobPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the properties of each job that is returned.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListEndpoints": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListEndpointsRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListEndpointsResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of all existing endpoints that you've created.\n      For information about endpoints, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/manage-endpoints.html\">Managing endpoints</a>.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "items": "EndpointPropertiesList",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListEndpointsRequest": {
+            "type": "structure",
+            "members": {
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#EndpointFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the endpoints that are returned. You can filter endpoints on their name, model,\n      status, or the date and time that they were created. You can only set one filter at a time.\n    </p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The maximum number of results to return in each page. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListEndpointsResponse": {
+            "type": "structure",
+            "members": {
+                "EndpointPropertiesList": {
+                    "target": "com.amazonaws.comprehend#EndpointPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Displays a list of endpoint properties being retrieved by the service in response to the\n      request.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListEntitiesDetectionJobs": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListEntitiesDetectionJobsRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListEntitiesDetectionJobsResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of the entity detection jobs that you have submitted.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListEntitiesDetectionJobsRequest": {
+            "type": "structure",
+            "members": {
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#EntitiesDetectionJobFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the jobs that are returned. You can filter jobs on their name, status, or the date\n      and time that they were submitted. You can only set one filter at a time.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The maximum number of results to return in each page. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListEntitiesDetectionJobsResponse": {
+            "type": "structure",
+            "members": {
+                "EntitiesDetectionJobPropertiesList": {
+                    "target": "com.amazonaws.comprehend#EntitiesDetectionJobPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the properties of each job that is returned.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListEntityRecognizerSummaries": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListEntityRecognizerSummariesRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListEntityRecognizerSummariesResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of summaries for the entity recognizers that you have created.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListEntityRecognizerSummariesRequest": {
+            "type": "structure",
+            "members": {
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The maximum number of results to return on each page. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListEntityRecognizerSummariesResponse": {
+            "type": "structure",
+            "members": {
+                "EntityRecognizerSummariesList": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerSummariesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The list entity recognizer summaries.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListEntityRecognizers": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListEntityRecognizersRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListEntityRecognizersResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of the properties of all entity recognizers that you created, including\n      recognizers currently in training. Allows you to filter the list of recognizers based on\n      criteria such as status and submission time. This call returns up to 500 entity recognizers in\n      the list, with a default number of 100 recognizers in the list.</p>\n         <p>The results of this list are not in any particular order. Please get the list and sort\n      locally if needed.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListEntityRecognizersRequest": {
+            "type": "structure",
+            "members": {
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of entities returned. You can filter on <code>Status</code>,\n        <code>SubmitTimeBefore</code>, or <code>SubmitTimeAfter</code>. You can only set one filter\n      at a time.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p> The maximum number of results to return on each page. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListEntityRecognizersResponse": {
+            "type": "structure",
+            "members": {
+                "EntityRecognizerPropertiesList": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The list of properties of an entity recognizer.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListEventsDetectionJobs": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListEventsDetectionJobsRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListEventsDetectionJobsResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of the events detection jobs that you have submitted.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListEventsDetectionJobsRequest": {
+            "type": "structure",
+            "members": {
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#EventsDetectionJobFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the jobs that are returned. You can filter jobs on their name, status, or the date\n      and time that they were submitted. You can only set one filter at a time.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The maximum number of results to return in each page.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListEventsDetectionJobsResponse": {
+            "type": "structure",
+            "members": {
+                "EventsDetectionJobPropertiesList": {
+                    "target": "com.amazonaws.comprehend#EventsDetectionJobPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the properties of each job that is returned.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListFlywheelIterationHistory": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListFlywheelIterationHistoryRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListFlywheelIterationHistoryResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Information about the history of a flywheel iteration.\n      For more information about flywheels, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/flywheels-about.html\">\n      Flywheel overview</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListFlywheelIterationHistoryRequest": {
+            "type": "structure",
+            "members": {
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The ARN of the flywheel.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#FlywheelIterationFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filter the flywheel iteration history based on creation time.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Next token</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Maximum number of iteration history results to return</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListFlywheelIterationHistoryResponse": {
+            "type": "structure",
+            "members": {
+                "FlywheelIterationPropertiesList": {
+                    "target": "com.amazonaws.comprehend#FlywheelIterationPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>List of flywheel iteration properties</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Next token</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListFlywheels": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListFlywheelsRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListFlywheelsResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of the flywheels that you have created.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListFlywheelsRequest": {
+            "type": "structure",
+            "members": {
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#FlywheelFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the flywheels that are returned. You can filter flywheels on their status,\n      or the date and time that they were submitted. You can only set one filter at a time.\n    </p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Maximum number of results to return in a response. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListFlywheelsResponse": {
+            "type": "structure",
+            "members": {
+                "FlywheelSummaryList": {
+                    "target": "com.amazonaws.comprehend#FlywheelSummaryList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list of flywheel properties retrieved by the service in response to the request.\n       </p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListKeyPhrasesDetectionJobs": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListKeyPhrasesDetectionJobsRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListKeyPhrasesDetectionJobsResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Get a list of key phrase detection jobs that you have submitted.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListKeyPhrasesDetectionJobsRequest": {
+            "type": "structure",
+            "members": {
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#KeyPhrasesDetectionJobFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the jobs that are returned. You can filter jobs on their name, status, or the date\n      and time that they were submitted. You can only set one filter at a time.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The maximum number of results to return in each page. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListKeyPhrasesDetectionJobsResponse": {
+            "type": "structure",
+            "members": {
+                "KeyPhrasesDetectionJobPropertiesList": {
+                    "target": "com.amazonaws.comprehend#KeyPhrasesDetectionJobPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the properties of each job that is returned.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListOfBlockReferences": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#BlockReference"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfBlocks": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#Block"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfChildBlocks": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#ChildBlock"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfClasses": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#DocumentClass"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfDescriptiveMentionIndices": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#Integer"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfDetectDominantLanguageResult": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#BatchDetectDominantLanguageItemResult"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfDetectEntitiesResult": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#BatchDetectEntitiesItemResult"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfDetectKeyPhrasesResult": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#BatchDetectKeyPhrasesItemResult"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfDetectSentimentResult": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#BatchDetectSentimentItemResult"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfDetectSyntaxResult": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#BatchDetectSyntaxItemResult"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfDetectTargetedSentimentResult": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#BatchDetectTargetedSentimentItemResult"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfDocumentReadFeatureTypes": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#DocumentReadFeatureTypes"
+            },
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 2
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListOfDocumentType": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#DocumentTypeListItem"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfDominantLanguages": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#DominantLanguage"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfEntities": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#Entity"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfEntityLabels": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#EntityLabel"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfErrors": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#ErrorsListItem"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfExtractedCharacters": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#ExtractedCharactersListItem"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfKeyPhrases": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#KeyPhrase"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfLabels": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#DocumentLabel"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfMentions": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#TargetedSentimentMention"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfPiiEntities": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#PiiEntity"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfPiiEntityTypes": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#PiiEntityType"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfRelationships": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#RelationshipsListItem"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfSyntaxTokens": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#SyntaxToken"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfTargetedSentimentEntities": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#TargetedSentimentEntity"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfTextSegments": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#TextSegment"
+            },
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1
+                },
+                "smithy.api#sensitive": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListOfToxicContent": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#ToxicContent"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfToxicLabels": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#ToxicLabels"
+            }
+        },
+        "com.amazonaws.comprehend#ListOfWarnings": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#WarningsListItem"
+            }
+        },
+        "com.amazonaws.comprehend#ListPiiEntitiesDetectionJobs": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListPiiEntitiesDetectionJobsRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListPiiEntitiesDetectionJobsResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of the PII entity detection jobs that you have submitted.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "items": "PiiEntitiesDetectionJobPropertiesList",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListPiiEntitiesDetectionJobsRequest": {
+            "type": "structure",
+            "members": {
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#PiiEntitiesDetectionJobFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the jobs that are returned. You can filter jobs on their name, status, or the date\n      and time that they were submitted. You can only set one filter at a time.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The maximum number of results to return in each page.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListPiiEntitiesDetectionJobsResponse": {
+            "type": "structure",
+            "members": {
+                "PiiEntitiesDetectionJobPropertiesList": {
+                    "target": "com.amazonaws.comprehend#PiiEntitiesDetectionJobPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the properties of each job that is returned.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListSentimentDetectionJobs": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListSentimentDetectionJobsRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListSentimentDetectionJobsResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of sentiment detection jobs that you have submitted.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListSentimentDetectionJobsRequest": {
+            "type": "structure",
+            "members": {
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#SentimentDetectionJobFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the jobs that are returned. You can filter jobs on their name, status, or the date\n      and time that they were submitted. You can only set one filter at a time.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The maximum number of results to return in each page. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListSentimentDetectionJobsResponse": {
+            "type": "structure",
+            "members": {
+                "SentimentDetectionJobPropertiesList": {
+                    "target": "com.amazonaws.comprehend#SentimentDetectionJobPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the properties of each job that is returned.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListTagsForResource": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListTagsForResourceRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListTagsForResourceResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Lists all tags associated with a given Amazon Comprehend resource. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#ListTagsForResourceRequest": {
+            "type": "structure",
+            "members": {
+                "ResourceArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the given Amazon Comprehend resource you are querying.\n    </p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListTagsForResourceResponse": {
+            "type": "structure",
+            "members": {
+                "ResourceArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the given Amazon Comprehend resource you are\n      querying.</p>"
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags associated with the Amazon Comprehend resource being queried. A tag is a key-value\n      pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with\n      \"Sales\" as the key might be added to a resource to indicate its use by the sales department.\n    </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListTargetedSentimentDetectionJobs": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListTargetedSentimentDetectionJobsRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListTargetedSentimentDetectionJobsResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of targeted sentiment detection jobs that you have submitted.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListTargetedSentimentDetectionJobsRequest": {
+            "type": "structure",
+            "members": {
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#TargetedSentimentDetectionJobFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the jobs that are returned. You can filter jobs on their name, status, or the date\n      and time that they were submitted. You can only set one filter at a time.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The maximum number of results to return in each page. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListTargetedSentimentDetectionJobsResponse": {
+            "type": "structure",
+            "members": {
+                "TargetedSentimentDetectionJobPropertiesList": {
+                    "target": "com.amazonaws.comprehend#TargetedSentimentDetectionJobPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the properties of each job that is returned.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListTopicsDetectionJobs": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#ListTopicsDetectionJobsRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#ListTopicsDetectionJobsResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidFilterException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Gets a list of the topic detection jobs that you have submitted.</p>",
+                "smithy.api#paginated": {
+                    "inputToken": "NextToken",
+                    "outputToken": "NextToken",
+                    "pageSize": "MaxResults"
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ListTopicsDetectionJobsRequest": {
+            "type": "structure",
+            "members": {
+                "Filter": {
+                    "target": "com.amazonaws.comprehend#TopicsDetectionJobFilter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the jobs that are returned. Jobs can be filtered on their name, status, or the\n      date and time that they were submitted. You can set only one filter at a time.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                },
+                "MaxResults": {
+                    "target": "com.amazonaws.comprehend#MaxResultsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The maximum number of results to return in each page. The default is 100.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#ListTopicsDetectionJobsResponse": {
+            "type": "structure",
+            "members": {
+                "TopicsDetectionJobPropertiesList": {
+                    "target": "com.amazonaws.comprehend#TopicsDetectionJobPropertiesList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A list containing the properties of each job that is returned.</p>"
+                    }
+                },
+                "NextToken": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the next page of results to return.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#MaskCharacter": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 1
+                },
+                "smithy.api#pattern": "^[!@#$%&*]$"
+            }
+        },
+        "com.amazonaws.comprehend#MaxResultsInteger": {
+            "type": "integer",
+            "traits": {
+                "smithy.api#range": {
+                    "min": 1,
+                    "max": 500
+                }
+            }
+        },
+        "com.amazonaws.comprehend#MentionSentiment": {
+            "type": "structure",
+            "members": {
+                "Sentiment": {
+                    "target": "com.amazonaws.comprehend#SentimentType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The sentiment of the mention. </p>"
+                    }
+                },
+                "SentimentScore": {
+                    "target": "com.amazonaws.comprehend#SentimentScore"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Contains the sentiment and sentiment score for one mention of an entity.</p>\n         <p>For more information about targeted sentiment, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-targeted-sentiment.html\">Targeted sentiment</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#ModelStatus": {
+            "type": "enum",
+            "members": {
+                "SUBMITTED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "SUBMITTED"
+                    }
+                },
+                "TRAINING": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TRAINING"
+                    }
+                },
+                "DELETING": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "DELETING"
+                    }
+                },
+                "STOP_REQUESTED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "STOP_REQUESTED"
+                    }
+                },
+                "STOPPED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "STOPPED"
+                    }
+                },
+                "IN_ERROR": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "IN_ERROR"
+                    }
+                },
+                "TRAINED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TRAINED"
+                    }
+                },
+                "TRAINED_WITH_WARNING": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TRAINED_WITH_WARNING"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ModelType": {
+            "type": "enum",
+            "members": {
+                "DOCUMENT_CLASSIFIER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "DOCUMENT_CLASSIFIER"
+                    }
+                },
+                "ENTITY_RECOGNIZER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ENTITY_RECOGNIZER"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#NumberOfDocuments": {
+            "type": "long"
+        },
+        "com.amazonaws.comprehend#NumberOfTopicsInteger": {
+            "type": "integer",
+            "traits": {
+                "smithy.api#range": {
+                    "min": 1,
+                    "max": 100
+                }
+            }
+        },
+        "com.amazonaws.comprehend#OutputDataConfig": {
+            "type": "structure",
+            "members": {
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>When you use the <code>OutputDataConfig</code> object with asynchronous operations, you\n      specify the Amazon S3 location where you want to write the output data. The URI must be in the\n      same Region as the API endpoint that you are calling. The location is used as the prefix for\n      the actual location of the output file.</p>\n         <p>When the topic detection job is finished, the service creates an output file in a\n      directory specific to the job. The <code>S3Uri</code> field contains the location of the\n      output file, called <code>output.tar.gz</code>. It is a compressed archive that contains the\n      ouput of the operation.</p>\n         <p>\n      For a PII entity detection job, the output file is plain text, not a compressed archive.\n      The output file name is the same as the input file, with <code>.out</code> appended at the end.\n    </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "KmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the\n      output results from an analysis job. Specify the Key Id of a symmetric key, because you cannot use an asymmetric\n       key for uploading data to S3.</p>\n         <p>The KmsKeyId can be one of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>KMS Key Alias: <code>\"alias/ExampleAlias\"</code>\n               </p>\n            </li>\n            <li>\n               <p>ARN of a KMS Key Alias:\n            <code>\"arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides configuration parameters for the output of inference jobs.</p>\n         <p></p>"
+            }
+        },
+        "com.amazonaws.comprehend#PageBasedErrorCode": {
+            "type": "enum",
+            "members": {
+                "TEXTRACT_BAD_PAGE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TEXTRACT_BAD_PAGE"
+                    }
+                },
+                "TEXTRACT_PROVISIONED_THROUGHPUT_EXCEEDED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TEXTRACT_PROVISIONED_THROUGHPUT_EXCEEDED"
+                    }
+                },
+                "PAGE_CHARACTERS_EXCEEDED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PAGE_CHARACTERS_EXCEEDED"
+                    }
+                },
+                "PAGE_SIZE_EXCEEDED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PAGE_SIZE_EXCEEDED"
+                    }
+                },
+                "INTERNAL_SERVER_ERROR": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "INTERNAL_SERVER_ERROR"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#PageBasedWarningCode": {
+            "type": "enum",
+            "members": {
+                "INFERENCING_PLAINTEXT_WITH_NATIVE_TRAINED_MODEL": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "INFERENCING_PLAINTEXT_WITH_NATIVE_TRAINED_MODEL"
+                    }
+                },
+                "INFERENCING_NATIVE_DOCUMENT_WITH_PLAINTEXT_TRAINED_MODEL": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "INFERENCING_NATIVE_DOCUMENT_WITH_PLAINTEXT_TRAINED_MODEL"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#PartOfSpeechTag": {
+            "type": "structure",
+            "members": {
+                "Tag": {
+                    "target": "com.amazonaws.comprehend#PartOfSpeechTagType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifies the part of speech that the token represents.</p>"
+                    }
+                },
+                "Score": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The confidence that Amazon Comprehend has that the part of speech was correctly\n      identified.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Identifies the part of speech represented by the token and gives the confidence that\n      Amazon Comprehend has that the part of speech was correctly identified. For more information\n      about the parts of speech that Amazon Comprehend can identify, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-syntax.html\">Syntax</a> in the Comprehend Developer Guide.\n       </p>"
+            }
+        },
+        "com.amazonaws.comprehend#PartOfSpeechTagType": {
+            "type": "enum",
+            "members": {
+                "ADJ": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ADJ"
+                    }
+                },
+                "ADP": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ADP"
+                    }
+                },
+                "ADV": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ADV"
+                    }
+                },
+                "AUX": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "AUX"
+                    }
+                },
+                "CONJ": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "CONJ"
+                    }
+                },
+                "CCONJ": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "CCONJ"
+                    }
+                },
+                "DET": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "DET"
+                    }
+                },
+                "INTJ": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "INTJ"
+                    }
+                },
+                "NOUN": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "NOUN"
+                    }
+                },
+                "NUM": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "NUM"
+                    }
+                },
+                "O": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "O"
+                    }
+                },
+                "PART": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PART"
+                    }
+                },
+                "PRON": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PRON"
+                    }
+                },
+                "PROPN": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PROPN"
+                    }
+                },
+                "PUNCT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PUNCT"
+                    }
+                },
+                "SCONJ": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "SCONJ"
+                    }
+                },
+                "SYM": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "SYM"
+                    }
+                },
+                "VERB": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "VERB"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#PiiEntitiesDetectionJobFilter": {
+            "type": "structure",
+            "members": {
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters on the name of the job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on job status. Returns only jobs with the specified\n      status.</p>"
+                    }
+                },
+                "SubmitTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted before the specified time. Jobs are returned in ascending order,\n      oldest to newest.</p>"
+                    }
+                },
+                "SubmitTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted after the specified time. Jobs are returned in descending order,\n      newest to oldest.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information for filtering a list of PII entity detection jobs.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#PiiEntitiesDetectionJobProperties": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier assigned to the PII entities detection job.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the PII entities detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:pii-entities-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name that you assigned the PII entities detection job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The current status of the PII entities detection job. If the status is\n      <code>FAILED</code>, the <code>Message</code> field shows the reason for the failure.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A description of the status of a job.</p>"
+                    }
+                },
+                "SubmitTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the PII entities detection job was submitted for processing.</p>"
+                    }
+                },
+                "EndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the PII entities detection job completed.</p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The input properties for a PII entities detection job.</p>"
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#PiiOutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The output data configuration that you supplied when you created the PII entities\n      detection job.</p>"
+                    }
+                },
+                "RedactionConfig": {
+                    "target": "com.amazonaws.comprehend#RedactionConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Provides configuration parameters for PII entity redaction.</p>\n         <p>This parameter is required if you set the <code>Mode</code> parameter to\n        <code>ONLY_REDACTION</code>. In that case, you must provide a <code>RedactionConfig</code>\n      definition that includes the <code>PiiEntityTypes</code> parameter.</p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language code of the input documents.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>"
+                    }
+                },
+                "Mode": {
+                    "target": "com.amazonaws.comprehend#PiiEntitiesDetectionMode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies whether the output provides the locations (offsets) of PII entities or a file in\n      which PII entities are redacted.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information about a PII entities detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#PiiEntitiesDetectionJobPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#PiiEntitiesDetectionJobProperties"
+            }
+        },
+        "com.amazonaws.comprehend#PiiEntitiesDetectionMaskMode": {
+            "type": "enum",
+            "members": {
+                "MASK": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "MASK"
+                    }
+                },
+                "REPLACE_WITH_PII_ENTITY_TYPE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "REPLACE_WITH_PII_ENTITY_TYPE"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#PiiEntitiesDetectionMode": {
+            "type": "enum",
+            "members": {
+                "ONLY_REDACTION": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ONLY_REDACTION"
+                    }
+                },
+                "ONLY_OFFSETS": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ONLY_OFFSETS"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#PiiEntity": {
+            "type": "structure",
+            "members": {
+                "Score": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The level of confidence that Amazon Comprehend has in the accuracy of the\n      detection.</p>"
+                    }
+                },
+                "Type": {
+                    "target": "com.amazonaws.comprehend#PiiEntityType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The entity's type.</p>"
+                    }
+                },
+                "BeginOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based offset from the beginning of the source text to the first character in the\n      entity.</p>"
+                    }
+                },
+                "EndOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based offset from the beginning of the source text to the last character in the\n      entity.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information about a PII entity.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#PiiEntityType": {
+            "type": "enum",
+            "members": {
+                "BANK_ACCOUNT_NUMBER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "BANK_ACCOUNT_NUMBER"
+                    }
+                },
+                "BANK_ROUTING": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "BANK_ROUTING"
+                    }
+                },
+                "CREDIT_DEBIT_NUMBER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "CREDIT_DEBIT_NUMBER"
+                    }
+                },
+                "CREDIT_DEBIT_CVV": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "CREDIT_DEBIT_CVV"
+                    }
+                },
+                "CREDIT_DEBIT_EXPIRY": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "CREDIT_DEBIT_EXPIRY"
+                    }
+                },
+                "PIN": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PIN"
+                    }
+                },
+                "EMAIL": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "EMAIL"
+                    }
+                },
+                "ADDRESS": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ADDRESS"
+                    }
+                },
+                "NAME": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "NAME"
+                    }
+                },
+                "PHONE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PHONE"
+                    }
+                },
+                "SSN": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "SSN"
+                    }
+                },
+                "DATE_TIME": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "DATE_TIME"
+                    }
+                },
+                "PASSPORT_NUMBER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PASSPORT_NUMBER"
+                    }
+                },
+                "DRIVER_ID": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "DRIVER_ID"
+                    }
+                },
+                "URL": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "URL"
+                    }
+                },
+                "AGE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "AGE"
+                    }
+                },
+                "USERNAME": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "USERNAME"
+                    }
+                },
+                "PASSWORD": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PASSWORD"
+                    }
+                },
+                "AWS_ACCESS_KEY": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "AWS_ACCESS_KEY"
+                    }
+                },
+                "AWS_SECRET_KEY": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "AWS_SECRET_KEY"
+                    }
+                },
+                "IP_ADDRESS": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "IP_ADDRESS"
+                    }
+                },
+                "MAC_ADDRESS": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "MAC_ADDRESS"
+                    }
+                },
+                "ALL": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ALL"
+                    }
+                },
+                "LICENSE_PLATE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "LICENSE_PLATE"
+                    }
+                },
+                "VEHICLE_IDENTIFICATION_NUMBER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "VEHICLE_IDENTIFICATION_NUMBER"
+                    }
+                },
+                "UK_NATIONAL_INSURANCE_NUMBER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "UK_NATIONAL_INSURANCE_NUMBER"
+                    }
+                },
+                "CA_SOCIAL_INSURANCE_NUMBER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "CA_SOCIAL_INSURANCE_NUMBER"
+                    }
+                },
+                "US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER"
+                    }
+                },
+                "UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER"
+                    }
+                },
+                "IN_PERMANENT_ACCOUNT_NUMBER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "IN_PERMANENT_ACCOUNT_NUMBER"
+                    }
+                },
+                "IN_NREGA": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "IN_NREGA"
+                    }
+                },
+                "INTERNATIONAL_BANK_ACCOUNT_NUMBER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "INTERNATIONAL_BANK_ACCOUNT_NUMBER"
+                    }
+                },
+                "SWIFT_CODE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "SWIFT_CODE"
+                    }
+                },
+                "UK_NATIONAL_HEALTH_SERVICE_NUMBER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "UK_NATIONAL_HEALTH_SERVICE_NUMBER"
+                    }
+                },
+                "CA_HEALTH_NUMBER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "CA_HEALTH_NUMBER"
+                    }
+                },
+                "IN_AADHAAR": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "IN_AADHAAR"
+                    }
+                },
+                "IN_VOTER_NUMBER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "IN_VOTER_NUMBER"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#PiiOutputDataConfig": {
+            "type": "structure",
+            "members": {
+                "S3Uri": {
+                    "target": "com.amazonaws.comprehend#S3Uri",
+                    "traits": {
+                        "smithy.api#documentation": "<p>When you use the <code>PiiOutputDataConfig</code> object with asynchronous operations,\n      you specify the Amazon S3 location where you want to write the output data. </p>\n         <p>\n      For a PII entity detection job, the output file is plain text, not a compressed archive.\n      The output file name is the same as the input file, with <code>.out</code> appended at the end.\n    </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "KmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the\n      output results from an analysis job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides configuration parameters for the output of PII entity detection jobs.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#Point": {
+            "type": "structure",
+            "members": {
+                "X": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The value of the X coordinate for a point on a polygon</p>"
+                    }
+                },
+                "Y": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The value of the Y coordinate for a point on a polygon</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The X and Y coordinates of a point on a document page.</p>\n         <p>For additional information, see <a href=\"https://docs.aws.amazon.com/textract/latest/dg/API_Point.html\">Point</a> in the Amazon Textract API reference.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#Policy": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 20000
+                },
+                "smithy.api#pattern": "^[\\u0009\\u000A\\u000D\\u0020-\\u00FF]+$"
+            }
+        },
+        "com.amazonaws.comprehend#PolicyRevisionId": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 64
+                },
+                "smithy.api#pattern": "^[0-9A-Fa-f]+$"
+            }
+        },
+        "com.amazonaws.comprehend#Polygon": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#Point"
+            }
+        },
+        "com.amazonaws.comprehend#PutResourcePolicy": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#PutResourcePolicyRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#PutResourcePolicyResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Attaches a resource-based policy to a custom model. You can use this policy to authorize\n      an entity in another Amazon Web Services account to import the custom model, which replicates it in Amazon\n      Comprehend in their account.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#PutResourcePolicyRequest": {
+            "type": "structure",
+            "members": {
+                "ResourceArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the custom model to attach the policy to.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ResourcePolicy": {
+                    "target": "com.amazonaws.comprehend#Policy",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The JSON resource-based policy to attach to your custom model. Provide your JSON as a\n      UTF-8 encoded string without line breaks. To provide valid JSON for your policy, enclose the\n      attribute names and values in double quotes. If the JSON body is also enclosed in double\n      quotes, then you must escape the double quotes that are inside the policy:</p>\n         <p>\n            <code>\"{\\\"attribute\\\": \\\"value\\\", \\\"attribute\\\": [\\\"value\\\"]}\"</code>\n         </p>\n         <p>To avoid escaping quotes, you can use single quotes to enclose the policy and double\n      quotes to enclose the JSON names and values:</p>\n         <p>\n            <code>'{\"attribute\": \"value\", \"attribute\": [\"value\"]}'</code>\n         </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "PolicyRevisionId": {
+                    "target": "com.amazonaws.comprehend#PolicyRevisionId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The revision ID that Amazon Comprehend assigned to the policy that you are updating. If\n      you are creating a new policy that has no prior version, don't use this parameter. Amazon\n      Comprehend creates the revision ID for you.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#PutResourcePolicyResponse": {
+            "type": "structure",
+            "members": {
+                "PolicyRevisionId": {
+                    "target": "com.amazonaws.comprehend#PolicyRevisionId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The revision ID of the policy. Each time you modify a policy, Amazon Comprehend assigns a\n      new revision ID, and it deletes the prior version of the policy.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#RedactionConfig": {
+            "type": "structure",
+            "members": {
+                "PiiEntityTypes": {
+                    "target": "com.amazonaws.comprehend#ListOfPiiEntityTypes",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An array of the types of PII entities that Amazon Comprehend detects in the input text for\n      your request.</p>"
+                    }
+                },
+                "MaskMode": {
+                    "target": "com.amazonaws.comprehend#PiiEntitiesDetectionMaskMode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies whether the PII entity is redacted with the mask character or the entity\n      type.</p>"
+                    }
+                },
+                "MaskCharacter": {
+                    "target": "com.amazonaws.comprehend#MaskCharacter",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A character that replaces each character in the redacted PII entity.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides configuration parameters for PII entity redaction.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#RelationshipType": {
+            "type": "enum",
+            "members": {
+                "CHILD": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "CHILD"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#RelationshipsListItem": {
+            "type": "structure",
+            "members": {
+                "Ids": {
+                    "target": "com.amazonaws.comprehend#StringList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Identifers of the child blocks.</p>"
+                    }
+                },
+                "Type": {
+                    "target": "com.amazonaws.comprehend#RelationshipType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Only supported relationship is a child relationship.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>List of child blocks for the current block.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#ResourceInUseException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The specified resource name is already in use. Use a different name and try your request\n      again.</p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 400
+            }
+        },
+        "com.amazonaws.comprehend#ResourceLimitExceededException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The maximum number of resources per account has been exceeded. Review the resources, and\n      then try your request again.</p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 400
+            }
+        },
+        "com.amazonaws.comprehend#ResourceNotFoundException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The specified resource ARN was not found. Check the ARN and try your request again.</p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 404
+            }
+        },
+        "com.amazonaws.comprehend#ResourceUnavailableException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The specified resource is not available. Check the resource and try your request\n      again.</p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 404
+            }
+        },
+        "com.amazonaws.comprehend#S3Uri": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 1024
+                },
+                "smithy.api#pattern": "^s3://[a-z0-9][\\.\\-a-z0-9]{1,61}[a-z0-9](/.*)?$"
+            }
+        },
+        "com.amazonaws.comprehend#SecurityGroupId": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 32
+                },
+                "smithy.api#pattern": "^[-0-9a-zA-Z]+$"
+            }
+        },
+        "com.amazonaws.comprehend#SecurityGroupIds": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#SecurityGroupId"
+            },
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 5
+                }
+            }
+        },
+        "com.amazonaws.comprehend#SemiStructuredDocumentBlob": {
+            "type": "blob",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1
+                }
+            }
+        },
+        "com.amazonaws.comprehend#SentimentDetectionJobFilter": {
+            "type": "structure",
+            "members": {
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters on the name of the job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on job status. Returns only jobs with the specified\n      status.</p>"
+                    }
+                },
+                "SubmitTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted before the specified time. Jobs are returned in ascending order,\n      oldest to newest.</p>"
+                    }
+                },
+                "SubmitTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted after the specified time. Jobs are returned in descending order,\n      newest to oldest.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information for filtering a list of dominant language detection jobs. For more\n      information, see the  operation.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#SentimentDetectionJobProperties": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier assigned to the sentiment detection job.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the sentiment detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:sentiment-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:sentiment-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name that you assigned to the sentiment detection job</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The current status of the sentiment detection job. If the status is <code>FAILED</code>,\n      the <code>Messages</code> field shows the reason for the failure.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A description of the status of a job.</p>"
+                    }
+                },
+                "SubmitTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the sentiment detection job was submitted for processing.</p>"
+                    }
+                },
+                "EndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the sentiment detection job ended.</p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The input data configuration that you supplied when you created the sentiment detection\n      job.</p>"
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The output data configuration that you supplied when you created the sentiment detection\n      job.</p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language code of the input documents.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>"
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Configuration parameters for a private Virtual Private Cloud (VPC) containing the\n      resources you are using for your sentiment detection job. For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information about a sentiment detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#SentimentDetectionJobPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#SentimentDetectionJobProperties"
+            }
+        },
+        "com.amazonaws.comprehend#SentimentScore": {
+            "type": "structure",
+            "members": {
+                "Positive": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The level of confidence that Amazon Comprehend has in the accuracy of its detection of\n      the <code>POSITIVE</code> sentiment.</p>"
+                    }
+                },
+                "Negative": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The level of confidence that Amazon Comprehend has in the accuracy of its detection of\n      the <code>NEGATIVE</code> sentiment.</p>"
+                    }
+                },
+                "Neutral": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The level of confidence that Amazon Comprehend has in the accuracy of its detection of\n      the <code>NEUTRAL</code> sentiment.</p>"
+                    }
+                },
+                "Mixed": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The level of confidence that Amazon Comprehend has in the accuracy of its detection of\n      the <code>MIXED</code> sentiment.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Describes the level of confidence that Amazon Comprehend has in the accuracy of its\n      detection of sentiments.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#SentimentType": {
+            "type": "enum",
+            "members": {
+                "POSITIVE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "POSITIVE"
+                    }
+                },
+                "NEGATIVE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "NEGATIVE"
+                    }
+                },
+                "NEUTRAL": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "NEUTRAL"
+                    }
+                },
+                "MIXED": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "MIXED"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#Split": {
+            "type": "enum",
+            "members": {
+                "TRAIN": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TRAIN"
+                    }
+                },
+                "TEST": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "TEST"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#StartDocumentClassificationJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StartDocumentClassificationJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StartDocumentClassificationJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceUnavailableException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Starts an asynchronous document classification job using a custom classification model.  Use the \n      <code>DescribeDocumentClassificationJob</code>\n          operation to track the progress of the job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StartDocumentClassificationJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the job.</p>"
+                    }
+                },
+                "DocumentClassifierArn": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the document classifier to use to process the\n      job.</p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the format and location of the input data for the job.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies where to send the output files.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A unique identifier for the request. If you do not set the client request token, Amazon\n      Comprehend generates one.</p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Configuration parameters for an optional private Virtual Private Cloud (VPC) containing\n      the resources you are using for your document classification job. For more information, see\n      <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags to associate with the document classification job. A tag is a key-value pair that\n      adds metadata to a resource used by Amazon Comprehend. For example, a tag with \"Sales\" as the\n      key might be added to a resource to indicate its use by the sales department.</p>"
+                    }
+                },
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel associated with the model to use.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartDocumentClassificationJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier generated for the job. To get the status of the job, use this identifier\n      with the <code>DescribeDocumentClassificationJob</code> operation.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the document classification job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:document-classification-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:document-classification-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the job:</p>\n         <ul>\n            <li>\n               <p>SUBMITTED - The job has been received and queued for processing.</p>\n            </li>\n            <li>\n               <p>IN_PROGRESS - Amazon Comprehend is processing the job.</p>\n            </li>\n            <li>\n               <p>COMPLETED - The job was successfully completed and the output is available.</p>\n            </li>\n            <li>\n               <p>FAILED - The job did not complete. For details, use the \n          <code>DescribeDocumentClassificationJob</code> operation.</p>\n            </li>\n            <li>\n               <p>STOP_REQUESTED - Amazon Comprehend has received a stop request for the job and is\n          processing the request.</p>\n            </li>\n            <li>\n               <p>STOPPED - The job was successfully stopped without completing.</p>\n            </li>\n         </ul>"
+                    }
+                },
+                "DocumentClassifierArn": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The ARN of the custom classification model.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartDominantLanguageDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StartDominantLanguageDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StartDominantLanguageDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Starts an asynchronous dominant language detection job for a collection of documents. Use\n      the  operation to track the status\n      of a job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StartDominantLanguageDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the format and location of the input data for the job.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies where to send the output files.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data. For more information, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/security_iam_id-based-policy-examples.html#auth-role-permissions\">Role-based permissions</a>.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An identifier for the job.</p>"
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A unique identifier for the request. If you do not set the client request token, Amazon\n      Comprehend generates one.</p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Configuration parameters for an optional private Virtual Private Cloud (VPC) containing\n      the resources you are using for your dominant language detection job. For more information,\n      see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon VPC</a>. </p>"
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags to associate with the dominant language detection job. A tag is a key-value pair\n      that adds metadata to a resource used by Amazon Comprehend. For example, a tag with \"Sales\" as\n      the key might be added to a resource to indicate its use by the sales department.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartDominantLanguageDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier generated for the job. To get the status of a job, use this identifier with\n      the  operation.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the dominant language detection job. It is a unique,\n      fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID.\n      The format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:dominant-language-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:dominant-language-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the job. </p>\n         <ul>\n            <li>\n               <p>SUBMITTED - The job has been received and is queued for processing.</p>\n            </li>\n            <li>\n               <p>IN_PROGRESS - Amazon Comprehend is processing the job.</p>\n            </li>\n            <li>\n               <p>COMPLETED - The job was successfully completed and the output is available.</p>\n            </li>\n            <li>\n               <p>FAILED - The job did not complete. To get details, use the  operation.</p>\n            </li>\n         </ul>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartEntitiesDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StartEntitiesDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StartEntitiesDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceUnavailableException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Starts an asynchronous entity detection job for a collection of documents. Use the  operation to track the status of a job.</p>\n         <p>This API can be used for either standard entity detection or custom entity recognition. In\n      order to be used for custom entity recognition, the optional <code>EntityRecognizerArn</code>\n      must be used in order to provide access to the recognizer being used to detect the custom\n      entity.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StartEntitiesDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the format and location of the input data for the job.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies where to send the output files.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data. For more information, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/security_iam_id-based-policy-examples.html#auth-role-permissions\">Role-based permissions</a>.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the job.</p>"
+                    }
+                },
+                "EntityRecognizerArn": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) that identifies the specific entity recognizer to be used\n      by the <code>StartEntitiesDetectionJob</code>. This ARN is optional and is only used for a\n      custom entity recognition job.</p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. All documents must be in the same language. You can\n      specify any of the languages supported by Amazon Comprehend. If custom entities recognition is\n      used, this parameter is ignored and the language used for training the model is used\n      instead.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A unique identifier for the request. If you don't set the client request token, Amazon\n      Comprehend generates one.</p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Configuration parameters for an optional private Virtual Private Cloud (VPC) containing\n      the resources you are using for your entity detection job. For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags to associate with the entities detection job. A tag is a key-value pair that adds\n      metadata to a resource used by Amazon Comprehend. For example, a tag with \"Sales\" as the key\n      might be added to a resource to indicate its use by the sales department.</p>"
+                    }
+                },
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel associated with the model to use.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartEntitiesDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier generated for the job. To get the status of job, use this identifier with\n      the  operation.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the entities detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:entities-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:entities-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the job. </p>\n         <ul>\n            <li>\n               <p>SUBMITTED - The job has been received and is queued for processing.</p>\n            </li>\n            <li>\n               <p>IN_PROGRESS - Amazon Comprehend is processing the job.</p>\n            </li>\n            <li>\n               <p>COMPLETED - The job was successfully completed and the output is available.</p>\n            </li>\n            <li>\n               <p>FAILED - The job did not complete. To get details, use the  operation.</p>\n            </li>\n            <li>\n               <p>STOP_REQUESTED - Amazon Comprehend has received a stop request for the job and is\n          processing the request.</p>\n            </li>\n            <li>\n               <p>STOPPED - The job was successfully stopped without completing.</p>\n            </li>\n         </ul>"
+                    }
+                },
+                "EntityRecognizerArn": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The ARN of the custom entity recognition model.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartEventsDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StartEventsDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StartEventsDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Starts an asynchronous event detection job for a collection of documents.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StartEventsDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the format and location of the input data for the job.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies where to send the output files.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the events detection job.</p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language code of the input documents.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An unique identifier for the request. If you don't set the client request token, Amazon\n      Comprehend generates one.</p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "TargetEventTypes": {
+                    "target": "com.amazonaws.comprehend#TargetEventTypes",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The types of events to detect in the input documents.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags to associate with the events detection job. A tag is a key-value pair that adds\n      metadata to a resource used by Amazon Comprehend. For example, a tag with \"Sales\" as the key\n      might be added to a resource to indicate its use by the sales department.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartEventsDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An unique identifier for the request. If you don't set the client request token, Amazon\n      Comprehend generates one.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the events detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:events-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:events-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the events detection job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartFlywheelIteration": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StartFlywheelIterationRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StartFlywheelIterationResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Start the flywheel iteration.This operation uses any new datasets to train a new model version.\n      For more information about flywheels, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/flywheels-about.html\">\n      Flywheel overview</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StartFlywheelIterationRequest": {
+            "type": "structure",
+            "members": {
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The ARN of the flywheel.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A unique identifier for the request. If you don't set the client request token, Amazon\n      Comprehend generates one.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartFlywheelIterationResponse": {
+            "type": "structure",
+            "members": {
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p></p>"
+                    }
+                },
+                "FlywheelIterationId": {
+                    "target": "com.amazonaws.comprehend#FlywheelIterationId",
+                    "traits": {
+                        "smithy.api#documentation": "<p></p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartKeyPhrasesDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StartKeyPhrasesDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StartKeyPhrasesDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Starts an asynchronous key phrase detection job for a collection of documents. Use the\n         operation to track the status of a\n      job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StartKeyPhrasesDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the format and location of the input data for the job.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies where to send the output files.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data. For more information, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/security_iam_id-based-policy-examples.html#auth-role-permissions\">Role-based permissions</a>.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the job.</p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. You can specify any of the primary languages\n      supported by Amazon Comprehend. All documents must be in the same language.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A unique identifier for the request. If you don't set the client request token, Amazon\n      Comprehend generates one.</p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p> Configuration parameters for an optional private Virtual Private Cloud (VPC) containing\n      the resources you are using for your key phrases detection job. For more information, see\n      <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags to associate with the key phrases detection job. A tag is a key-value pair that\n      adds metadata to a resource used by Amazon Comprehend. For example, a tag with \"Sales\" as the\n      key might be added to a resource to indicate its use by the sales department.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartKeyPhrasesDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier generated for the job. To get the status of a job, use this identifier with\n      the  operation.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the key phrase detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:key-phrases-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:key-phrases-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the job. </p>\n         <ul>\n            <li>\n               <p>SUBMITTED - The job has been received and is queued for processing.</p>\n            </li>\n            <li>\n               <p>IN_PROGRESS - Amazon Comprehend is processing the job.</p>\n            </li>\n            <li>\n               <p>COMPLETED - The job was successfully completed and the output is available.</p>\n            </li>\n            <li>\n               <p>FAILED - The job did not complete. To get details, use the  operation.</p>\n            </li>\n         </ul>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartPiiEntitiesDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StartPiiEntitiesDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StartPiiEntitiesDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Starts an asynchronous PII entity detection job for a collection of documents.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StartPiiEntitiesDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The input properties for a PII entities detection job.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Provides configuration parameters for the output of PII entity detection jobs.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "Mode": {
+                    "target": "com.amazonaws.comprehend#PiiEntitiesDetectionMode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies whether the output provides the locations (offsets) of PII entities or a file in\n      which PII entities are redacted.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "RedactionConfig": {
+                    "target": "com.amazonaws.comprehend#RedactionConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Provides configuration parameters for PII entity redaction.</p>\n         <p>This parameter is required if you set the <code>Mode</code> parameter to\n        <code>ONLY_REDACTION</code>. In that case, you must provide a <code>RedactionConfig</code>\n      definition that includes the <code>PiiEntityTypes</code> parameter.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the job.</p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. \n      Enter the language code for English (en) or Spanish (es).</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A unique identifier for the request. If you don't set the client request token, Amazon\n      Comprehend generates one.</p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags to associate with the PII entities detection job. A tag is a key-value pair that\n      adds metadata to a resource used by Amazon Comprehend. For example, a tag with \"Sales\" as the\n      key might be added to a resource to indicate its use by the sales department.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartPiiEntitiesDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier generated for the job.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the PII entity detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:pii-entities-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartSentimentDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StartSentimentDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StartSentimentDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Starts an asynchronous sentiment detection job for a collection of documents. Use the\n         operation to track the status of a\n      job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StartSentimentDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the format and location of the input data for the job.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies where to send the output files. </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data. For more information, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/security_iam_id-based-policy-examples.html#auth-role-permissions\">Role-based permissions</a>.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the job.</p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. You can specify any of the primary languages\n      supported by Amazon Comprehend. All documents must be in the same language.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A unique identifier for the request. If you don't set the client request token, Amazon\n      Comprehend generates one.</p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Configuration parameters for an optional private Virtual Private Cloud (VPC) containing\n      the resources you are using for your sentiment detection job. For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags to associate with the sentiment detection job. A tag is a key-value pair that\n      adds metadata to a resource used by Amazon Comprehend. For example, a tag with \"Sales\" as the\n      key might be added to a resource to indicate its use by the sales department.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartSentimentDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier generated for the job. To get the status of a job, use this identifier with\n      the  operation.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the sentiment detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:sentiment-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:sentiment-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the job. </p>\n         <ul>\n            <li>\n               <p>SUBMITTED - The job has been received and is queued for processing.</p>\n            </li>\n            <li>\n               <p>IN_PROGRESS - Amazon Comprehend is processing the job.</p>\n            </li>\n            <li>\n               <p>COMPLETED - The job was successfully completed and the output is available.</p>\n            </li>\n            <li>\n               <p>FAILED - The job did not complete. To get details, use the  operation.</p>\n            </li>\n         </ul>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartTargetedSentimentDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StartTargetedSentimentDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StartTargetedSentimentDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Starts an asynchronous targeted sentiment detection job for a collection of documents. Use the\n      <code>DescribeTargetedSentimentDetectionJob</code> operation to track the status of a\n      job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StartTargetedSentimentDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#required": {}
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies where to send the output files. </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data. For more information, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/security_iam_id-based-policy-examples.html#auth-role-permissions\">Role-based permissions</a>.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the job.</p>"
+                    }
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language of the input documents. Currently, English is the only supported language.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A unique identifier for the request. If you don't set the client request token, Amazon\n      Comprehend generates one.</p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the KMS key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n          <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig"
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags to associate with the targeted sentiment detection job. A tag is a key-value pair that\n      adds metadata to a resource used by Amazon Comprehend. For example, a tag with \"Sales\" as the\n      key might be added to a resource to indicate its use by the sales department.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartTargetedSentimentDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier generated for the job. To get the status of a job, use this identifier with\n      the <code>DescribeTargetedSentimentDetectionJob</code> operation.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the targeted sentiment detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:targeted-sentiment-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:targeted-sentiment-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the job. </p>\n         <ul>\n            <li>\n               <p>SUBMITTED - The job has been received and is queued for processing.</p>\n            </li>\n            <li>\n               <p>IN_PROGRESS - Amazon Comprehend is processing the job.</p>\n            </li>\n            <li>\n               <p>COMPLETED - The job was successfully completed and the output is available.</p>\n            </li>\n            <li>\n               <p>FAILED - The job did not complete. To get details, use the \n          <code>DescribeTargetedSentimentDetectionJob</code> operation.</p>\n            </li>\n         </ul>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartTopicsDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StartTopicsDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StartTopicsDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Starts an asynchronous topic detection job. Use the\n        <code>DescribeTopicDetectionJob</code> operation to track the status of a job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StartTopicsDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies the format and location of the input data for the job.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Specifies where to send the output files. The output is a compressed archive with two\n      files, <code>topic-terms.csv</code> that lists the terms associated with each topic, and\n        <code>doc-topics.csv</code> that lists the documents associated with each topic</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data. For more information, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/security_iam_id-based-policy-examples.html#auth-role-permissions\">Role-based permissions</a>.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the job.</p>"
+                    }
+                },
+                "NumberOfTopics": {
+                    "target": "com.amazonaws.comprehend#NumberOfTopicsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The number of topics to detect.</p>"
+                    }
+                },
+                "ClientRequestToken": {
+                    "target": "com.amazonaws.comprehend#ClientRequestTokenString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A unique identifier for the request. If you do not set the client request token, Amazon\n      Comprehend generates one.</p>",
+                        "smithy.api#idempotencyToken": {}
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Configuration parameters for an optional private Virtual Private Cloud (VPC) containing\n      the resources you are using for your topic detection job. For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags to associate with the topics detection job. A tag is a key-value pair that adds\n      metadata to a resource used by Amazon Comprehend. For example, a tag with \"Sales\" as the key\n      might be added to a resource to indicate its use by the sales department.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StartTopicsDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier generated for the job. To get the status of the job, use this identifier\n      with the <code>DescribeTopicDetectionJob</code> operation.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the topics detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:topics-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:document-classification-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the job: </p>\n         <ul>\n            <li>\n               <p>SUBMITTED - The job has been received and is queued for processing.</p>\n            </li>\n            <li>\n               <p>IN_PROGRESS - Amazon Comprehend is processing the job.</p>\n            </li>\n            <li>\n               <p>COMPLETED - The job was successfully completed and the output is\n          available.</p>\n            </li>\n            <li>\n               <p>FAILED - The job did not complete. To get details, use the\n            <code>DescribeTopicDetectionJob</code> operation.</p>\n            </li>\n         </ul>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopDominantLanguageDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StopDominantLanguageDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StopDominantLanguageDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Stops a dominant language detection job in progress.</p>\n         <p>If the job state is <code>IN_PROGRESS</code> the job is marked for termination and put\n      into the <code>STOP_REQUESTED</code> state. If the job completes before it can be stopped, it\n      is put into the <code>COMPLETED</code> state; otherwise the job is stopped and put into the\n        <code>STOPPED</code> state.</p>\n         <p>If the job is in the <code>COMPLETED</code> or <code>FAILED</code> state when you call the\n        <code>StopDominantLanguageDetectionJob</code> operation, the operation returns a 400\n      Internal Request Exception. </p>\n         <p>When a job is stopped, any documents already processed are written to the output\n      location.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StopDominantLanguageDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the dominant language detection job to stop.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopDominantLanguageDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the dominant language detection job to stop.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Either <code>STOP_REQUESTED</code> if the job is currently running, or\n        <code>STOPPED</code> if the job was previously stopped with the\n        <code>StopDominantLanguageDetectionJob</code> operation.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopEntitiesDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StopEntitiesDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StopEntitiesDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Stops an entities detection job in progress.</p>\n         <p>If the job state is <code>IN_PROGRESS</code> the job is marked for termination and put\n      into the <code>STOP_REQUESTED</code> state. If the job completes before it can be stopped, it\n      is put into the <code>COMPLETED</code> state; otherwise the job is stopped and put into the\n        <code>STOPPED</code> state.</p>\n         <p>If the job is in the <code>COMPLETED</code> or <code>FAILED</code> state when you call the\n        <code>StopDominantLanguageDetectionJob</code> operation, the operation returns a 400\n      Internal Request Exception. </p>\n         <p>When a job is stopped, any documents already processed are written to the output\n      location.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StopEntitiesDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the entities detection job to stop.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopEntitiesDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the entities detection job to stop.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Either <code>STOP_REQUESTED</code> if the job is currently running, or\n        <code>STOPPED</code> if the job was previously stopped with the\n        <code>StopEntitiesDetectionJob</code> operation.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopEventsDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StopEventsDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StopEventsDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Stops an events detection job in progress.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StopEventsDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the events detection job to stop.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopEventsDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the events detection job to stop.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the events detection job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopKeyPhrasesDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StopKeyPhrasesDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StopKeyPhrasesDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Stops a key phrases detection job in progress.</p>\n         <p>If the job state is <code>IN_PROGRESS</code> the job is marked for termination and put\n      into the <code>STOP_REQUESTED</code> state. If the job completes before it can be stopped, it\n      is put into the <code>COMPLETED</code> state; otherwise the job is stopped and put into the\n        <code>STOPPED</code> state.</p>\n         <p>If the job is in the <code>COMPLETED</code> or <code>FAILED</code> state when you call the\n        <code>StopDominantLanguageDetectionJob</code> operation, the operation returns a 400\n      Internal Request Exception. </p>\n         <p>When a job is stopped, any documents already processed are written to the output\n      location.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StopKeyPhrasesDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the key phrases detection job to stop.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopKeyPhrasesDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the key phrases detection job to stop.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Either <code>STOP_REQUESTED</code> if the job is currently running, or\n        <code>STOPPED</code> if the job was previously stopped with the\n        <code>StopKeyPhrasesDetectionJob</code> operation.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopPiiEntitiesDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StopPiiEntitiesDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StopPiiEntitiesDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Stops a PII entities detection job in progress.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StopPiiEntitiesDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the PII entities detection job to stop.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopPiiEntitiesDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the PII entities detection job to stop.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The status of the PII entities detection job.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopSentimentDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StopSentimentDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StopSentimentDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Stops a sentiment detection job in progress.</p>\n         <p>If the job state is <code>IN_PROGRESS</code>, the job is marked for termination and put\n      into the <code>STOP_REQUESTED</code> state. If the job completes before it can be stopped, it\n      is put into the <code>COMPLETED</code> state; otherwise the job is be stopped and put into the\n        <code>STOPPED</code> state.</p>\n         <p>If the job is in the <code>COMPLETED</code> or <code>FAILED</code> state when you call the\n        <code>StopDominantLanguageDetectionJob</code> operation, the operation returns a 400\n      Internal Request Exception. </p>\n         <p>When a job is stopped, any documents already processed are written to the output\n      location.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StopSentimentDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the sentiment detection job to stop.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopSentimentDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the sentiment detection job to stop.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Either <code>STOP_REQUESTED</code> if the job is currently running, or\n        <code>STOPPED</code> if the job was previously stopped with the\n        <code>StopSentimentDetectionJob</code> operation.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopTargetedSentimentDetectionJob": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StopTargetedSentimentDetectionJobRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StopTargetedSentimentDetectionJobResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#JobNotFoundException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Stops a targeted sentiment detection job in progress.</p>\n         <p>If the job state is <code>IN_PROGRESS</code>, the job is marked for termination and put\n      into the <code>STOP_REQUESTED</code> state. If the job completes before it can be stopped, it\n      is put into the <code>COMPLETED</code> state; otherwise the job is be stopped and put into the\n      <code>STOPPED</code> state.</p>\n         <p>If the job is in the <code>COMPLETED</code> or <code>FAILED</code> state when you call the\n      <code>StopDominantLanguageDetectionJob</code> operation, the operation returns a 400\n      Internal Request Exception. </p>\n         <p>When a job is stopped, any documents already processed are written to the output\n      location.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StopTargetedSentimentDetectionJobRequest": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the targeted sentiment detection job to stop.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopTargetedSentimentDetectionJobResponse": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier of the targeted sentiment detection job to stop.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Either <code>STOP_REQUESTED</code> if the job is currently running, or\n      <code>STOPPED</code> if the job was previously stopped with the\n      <code>StopSentimentDetectionJob</code> operation.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopTrainingDocumentClassifier": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StopTrainingDocumentClassifierRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StopTrainingDocumentClassifierResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Stops a document classifier training job while in progress.</p>\n         <p>If the training job state is <code>TRAINING</code>, the job is marked for termination and\n      put into the <code>STOP_REQUESTED</code> state. If the training job completes before it can be\n      stopped, it is put into the <code>TRAINED</code>; otherwise the training job is stopped and\n      put into the <code>STOPPED</code> state and the service sends back an HTTP 200 response with\n      an empty HTTP body. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#StopTrainingDocumentClassifierRequest": {
+            "type": "structure",
+            "members": {
+                "DocumentClassifierArn": {
+                    "target": "com.amazonaws.comprehend#DocumentClassifierArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) that identifies the document classifier currently being\n      trained.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopTrainingDocumentClassifierResponse": {
+            "type": "structure",
+            "members": {},
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopTrainingEntityRecognizer": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#StopTrainingEntityRecognizerRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#StopTrainingEntityRecognizerResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Stops an entity recognizer training job while in progress.</p>\n         <p>If the training job state is <code>TRAINING</code>, the job is marked for termination and\n      put into the <code>STOP_REQUESTED</code> state. If the training job completes before it can be\n      stopped, it is put into the <code>TRAINED</code>; otherwise the training job is stopped and\n      putted into the <code>STOPPED</code> state and the service sends back an HTTP 200 response\n      with an empty HTTP body.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#StopTrainingEntityRecognizerRequest": {
+            "type": "structure",
+            "members": {
+                "EntityRecognizerArn": {
+                    "target": "com.amazonaws.comprehend#EntityRecognizerArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) that identifies the entity recognizer currently being\n      trained.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#StopTrainingEntityRecognizerResponse": {
+            "type": "structure",
+            "members": {},
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#String": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1
+                }
+            }
+        },
+        "com.amazonaws.comprehend#StringList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#String"
+            }
+        },
+        "com.amazonaws.comprehend#SubnetId": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 32
+                },
+                "smithy.api#pattern": "^[-0-9a-zA-Z]+$"
+            }
+        },
+        "com.amazonaws.comprehend#Subnets": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#SubnetId"
+            },
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 16
+                }
+            }
+        },
+        "com.amazonaws.comprehend#SyntaxLanguageCode": {
+            "type": "enum",
+            "members": {
+                "EN": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "en"
+                    }
+                },
+                "ES": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "es"
+                    }
+                },
+                "FR": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "fr"
+                    }
+                },
+                "DE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "de"
+                    }
+                },
+                "IT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "it"
+                    }
+                },
+                "PT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "pt"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#SyntaxToken": {
+            "type": "structure",
+            "members": {
+                "TokenId": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A unique identifier for a token.</p>"
+                    }
+                },
+                "Text": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The word that was recognized in the source text.</p>"
+                    }
+                },
+                "BeginOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based offset from the beginning of the source text to the first character in the\n      word.</p>"
+                    }
+                },
+                "EndOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The zero-based offset from the beginning of the source text to the last character in the\n      word.</p>"
+                    }
+                },
+                "PartOfSpeech": {
+                    "target": "com.amazonaws.comprehend#PartOfSpeechTag",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Provides the part of speech label and the confidence level that Amazon Comprehend has that\n      the part of speech was correctly identified. For more information, see\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-syntax.html\">Syntax</a> in the Comprehend Developer Guide.\n    </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Represents a work in the input text that was recognized and assigned a part of speech.\n      There is one syntax token record for each word in the source text.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#Tag": {
+            "type": "structure",
+            "members": {
+                "Key": {
+                    "target": "com.amazonaws.comprehend#TagKey",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The initial part of a key-value pair that forms a tag associated with a given resource.\n      For instance, if you want to show which resources are used by which departments, you might use\n      “Department” as the key portion of the pair, with multiple possible values such as “sales,”\n      “legal,” and “administration.” </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "Value": {
+                    "target": "com.amazonaws.comprehend#TagValue",
+                    "traits": {
+                        "smithy.api#documentation": "<p> The second part of a key-value pair that forms a tag associated with a given resource.\n      For instance, if you want to show which resources are used by which departments, you might use\n      “Department” as the initial (key) portion of the pair, with a value of “sales” to indicate the\n      sales department. </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>A key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For\n      example, a tag with the key-value pair ‘Department’:’Sales’ might be added to a resource to\n      indicate its use by a particular department. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#TagKey": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1,
+                    "max": 128
+                }
+            }
+        },
+        "com.amazonaws.comprehend#TagKeyList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#TagKey"
+            }
+        },
+        "com.amazonaws.comprehend#TagList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#Tag"
+            }
+        },
+        "com.amazonaws.comprehend#TagResource": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#TagResourceRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#TagResourceResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#ConcurrentModificationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Associates a specific tag with an Amazon Comprehend resource. A tag is a key-value pair\n      that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with\n      \"Sales\" as the key might be added to a resource to indicate its use by the sales department.\n    </p>"
+            }
+        },
+        "com.amazonaws.comprehend#TagResourceRequest": {
+            "type": "structure",
+            "members": {
+                "ResourceArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the given Amazon Comprehend resource to which you want\n      to associate the tags. </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "Tags": {
+                    "target": "com.amazonaws.comprehend#TagList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Tags being associated with a specific Amazon Comprehend resource. There can be a maximum\n      of 50 tags (both existing and pending) associated with a specific resource. </p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#TagResourceResponse": {
+            "type": "structure",
+            "members": {},
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#TagValue": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 256
+                }
+            }
+        },
+        "com.amazonaws.comprehend#TargetEventTypes": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#EventTypeString"
+            },
+            "traits": {
+                "smithy.api#length": {
+                    "min": 1
+                }
+            }
+        },
+        "com.amazonaws.comprehend#TargetedSentimentDetectionJobFilter": {
+            "type": "structure",
+            "members": {
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters on the name of the job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on job status. Returns only jobs with the specified\n      status.</p>"
+                    }
+                },
+                "SubmitTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted before the specified time. Jobs are returned in ascending order,\n      oldest to newest.</p>"
+                    }
+                },
+                "SubmitTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Returns only jobs submitted after the specified time. Jobs are returned in descending order,\n      newest to oldest.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information for filtering a list of dominant language detection jobs. For more\n      information, see the <code>ListTargetedSentimentDetectionJobs</code> operation.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#TargetedSentimentDetectionJobProperties": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier assigned to the targeted sentiment detection job.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the targeted sentiment detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:targeted-sentiment-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:targeted-sentiment-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name that you assigned to the targeted sentiment detection job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The current status of the targeted sentiment detection job. If the status is <code>FAILED</code>,\n      the <code>Messages</code> field shows the reason for the failure.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A description of the status of a job.</p>"
+                    }
+                },
+                "SubmitTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the targeted sentiment detection job was submitted for processing.</p>"
+                    }
+                },
+                "EndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the targeted sentiment detection job ended.</p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig"
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig"
+                },
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The language code of the input documents.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your input data.</p>"
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the KMS key that Amazon Comprehend uses to encrypt the\n      data on the storage volume attached to the ML compute instance(s) that process the\n      targeted sentiment detection job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n          <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information about a targeted sentiment detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#TargetedSentimentDetectionJobPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#TargetedSentimentDetectionJobProperties"
+            }
+        },
+        "com.amazonaws.comprehend#TargetedSentimentEntity": {
+            "type": "structure",
+            "members": {
+                "DescriptiveMentionIndex": {
+                    "target": "com.amazonaws.comprehend#ListOfDescriptiveMentionIndices",
+                    "traits": {
+                        "smithy.api#documentation": "<p>One or more index into the Mentions array that provides the best name for the entity group.</p>"
+                    }
+                },
+                "Mentions": {
+                    "target": "com.amazonaws.comprehend#ListOfMentions",
+                    "traits": {
+                        "smithy.api#documentation": "<p>An array of mentions of the entity in the document. The array represents a co-reference group.\n      See <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-targeted-sentiment.html#how-targeted-sentiment-values\">\n        Co-reference group</a> for an example. </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Information about one of the entities found by targeted sentiment analysis.</p>\n         <p>For more information about targeted sentiment, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-targeted-sentiment.html\">Targeted sentiment</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#TargetedSentimentEntityType": {
+            "type": "enum",
+            "members": {
+                "PERSON": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PERSON"
+                    }
+                },
+                "LOCATION": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "LOCATION"
+                    }
+                },
+                "ORGANIZATION": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ORGANIZATION"
+                    }
+                },
+                "FACILITY": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "FACILITY"
+                    }
+                },
+                "BRAND": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "BRAND"
+                    }
+                },
+                "COMMERCIAL_ITEM": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "COMMERCIAL_ITEM"
+                    }
+                },
+                "MOVIE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "MOVIE"
+                    }
+                },
+                "MUSIC": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "MUSIC"
+                    }
+                },
+                "BOOK": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "BOOK"
+                    }
+                },
+                "SOFTWARE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "SOFTWARE"
+                    }
+                },
+                "GAME": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "GAME"
+                    }
+                },
+                "PERSONAL_TITLE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PERSONAL_TITLE"
+                    }
+                },
+                "EVENT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "EVENT"
+                    }
+                },
+                "DATE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "DATE"
+                    }
+                },
+                "QUANTITY": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "QUANTITY"
+                    }
+                },
+                "ATTRIBUTE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "ATTRIBUTE"
+                    }
+                },
+                "OTHER": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "OTHER"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#TargetedSentimentMention": {
+            "type": "structure",
+            "members": {
+                "Score": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Model confidence that the entity is relevant. Value range is zero to one, where one is highest confidence.</p>"
+                    }
+                },
+                "GroupScore": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The confidence that all the entities mentioned in the group relate to the same entity.</p>"
+                    }
+                },
+                "Text": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The text in the document that identifies the entity.</p>"
+                    }
+                },
+                "Type": {
+                    "target": "com.amazonaws.comprehend#TargetedSentimentEntityType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The type of the entity. Amazon Comprehend supports a variety of <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-targeted-sentiment.html#how-targeted-sentiment-entities\">entity types</a>.</p>"
+                    }
+                },
+                "MentionSentiment": {
+                    "target": "com.amazonaws.comprehend#MentionSentiment",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Contains the sentiment and sentiment score for the mention.</p>"
+                    }
+                },
+                "BeginOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The offset into the document text where the mention begins.</p>"
+                    }
+                },
+                "EndOffset": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The offset into the document text where the mention ends.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Information about one mention of an entity. The mention information includes the location of the mention\n      in the text and the sentiment of the mention.</p>\n         <p>For more information about targeted sentiment, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/how-targeted-sentiment.html\">Targeted sentiment</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#TaskConfig": {
+            "type": "structure",
+            "members": {
+                "LanguageCode": {
+                    "target": "com.amazonaws.comprehend#LanguageCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Language code for the language that the model supports.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DocumentClassificationConfig": {
+                    "target": "com.amazonaws.comprehend#DocumentClassificationConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Configuration required for a document classification model.</p>"
+                    }
+                },
+                "EntityRecognitionConfig": {
+                    "target": "com.amazonaws.comprehend#EntityRecognitionConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Configuration required for an entity recognition model.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Configuration about the model associated with a flywheel.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#TextSegment": {
+            "type": "structure",
+            "members": {
+                "Text": {
+                    "target": "com.amazonaws.comprehend#CustomerInputString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The text content.</p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>One of the of text strings. Each string has a size limit of 1KB.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#TextSizeLimitExceededException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The size of the input text exceeds the limit. Use a smaller document.</p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 400
+            }
+        },
+        "com.amazonaws.comprehend#Timestamp": {
+            "type": "timestamp"
+        },
+        "com.amazonaws.comprehend#TooManyRequestsException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The number of requests exceeds the limit. Resubmit your request later.</p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 429
+            }
+        },
+        "com.amazonaws.comprehend#TooManyTagKeysException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The request contains more tag keys than can be associated with a resource (50 tag keys per\n      resource).</p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 400
+            }
+        },
+        "com.amazonaws.comprehend#TooManyTagsException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The request contains more tags than can be associated with a resource (50 tags per\n      resource). The maximum number of tags includes both existing tags and those included in your\n      current request. </p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 400
+            }
+        },
+        "com.amazonaws.comprehend#TopicsDetectionJobFilter": {
+            "type": "structure",
+            "members": {
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p></p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of topic detection jobs based on job status. Returns only jobs with\n      the specified status.</p>"
+                    }
+                },
+                "SubmitTimeBefore": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Only returns jobs submitted before the specified time. Jobs are returned in descending order,\n      newest to oldest.</p>"
+                    }
+                },
+                "SubmitTimeAfter": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Filters the list of jobs based on the time that the job was submitted for processing.\n      Only returns jobs submitted after the specified time. Jobs are returned in ascending order,\n      oldest to newest.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information for filtering topic detection jobs. For more information, see\n        .</p>"
+            }
+        },
+        "com.amazonaws.comprehend#TopicsDetectionJobProperties": {
+            "type": "structure",
+            "members": {
+                "JobId": {
+                    "target": "com.amazonaws.comprehend#JobId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The identifier assigned to the topic detection job.</p>"
+                    }
+                },
+                "JobArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the topics detection job. It is a unique, fully\n      qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The\n      format of the ARN is as follows:</p>\n         <p>\n            <code>arn:<partition>:comprehend:<region>:<account-id>:topics-detection-job/<job-id></code>\n         </p>\n         <p>The following is an example job ARN:</p>\n         <p>\n            <code>arn:aws:comprehend:us-west-2:111122223333:topics-detection-job/1234abcd12ab34cd56ef1234567890ab</code>\n         </p>"
+                    }
+                },
+                "JobName": {
+                    "target": "com.amazonaws.comprehend#JobName",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name of the topic detection job.</p>"
+                    }
+                },
+                "JobStatus": {
+                    "target": "com.amazonaws.comprehend#JobStatus",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The current status of the topic detection job. If the status is <code>Failed</code>,\n      the reason for the failure is shown in the <code>Message</code> field.</p>"
+                    }
+                },
+                "Message": {
+                    "target": "com.amazonaws.comprehend#AnyLengthString",
+                    "traits": {
+                        "smithy.api#documentation": "<p>A description for the status of a job.</p>"
+                    }
+                },
+                "SubmitTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the topic detection job was submitted for processing.</p>"
+                    }
+                },
+                "EndTime": {
+                    "target": "com.amazonaws.comprehend#Timestamp",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The time that the topic detection job was completed.</p>"
+                    }
+                },
+                "InputDataConfig": {
+                    "target": "com.amazonaws.comprehend#InputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The input data configuration supplied when you created the topic detection\n      job.</p>"
+                    }
+                },
+                "OutputDataConfig": {
+                    "target": "com.amazonaws.comprehend#OutputDataConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The output data configuration supplied when you created the topic detection\n      job.</p>"
+                    }
+                },
+                "NumberOfTopics": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The number of topics to detect supplied when you created the topic detection job. The\n      default is 10. </p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend read access to your job data. </p>"
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt\n      data on the storage volume attached to the ML compute instance(s) that process the analysis\n      job. The VolumeKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Configuration parameters for a private Virtual Private Cloud (VPC) containing the\n      resources you are using for your topic detection job. For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Provides information about a topic detection job.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#TopicsDetectionJobPropertiesList": {
+            "type": "list",
+            "member": {
+                "target": "com.amazonaws.comprehend#TopicsDetectionJobProperties"
+            }
+        },
+        "com.amazonaws.comprehend#ToxicContent": {
+            "type": "structure",
+            "members": {
+                "Name": {
+                    "target": "com.amazonaws.comprehend#ToxicContentType",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The name of the toxic content type.</p>"
+                    }
+                },
+                "Score": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p> \n      Model confidence in the detected content type. Value range is zero to one, where one is highest confidence.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Toxic content analysis result for one string. For more information about toxicity detection, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/toxicity-detection.html\">Toxicity detection</a> in the <i>Amazon Comprehend Developer Guide</i>\n         </p>"
+            }
+        },
+        "com.amazonaws.comprehend#ToxicContentType": {
+            "type": "enum",
+            "members": {
+                "GRAPHIC": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "GRAPHIC"
+                    }
+                },
+                "HARASSMENT_OR_ABUSE": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "HARASSMENT_OR_ABUSE"
+                    }
+                },
+                "HATE_SPEECH": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "HATE_SPEECH"
+                    }
+                },
+                "INSULT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "INSULT"
+                    }
+                },
+                "PROFANITY": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "PROFANITY"
+                    }
+                },
+                "SEXUAL": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "SEXUAL"
+                    }
+                },
+                "VIOLENCE_OR_THREAT": {
+                    "target": "smithy.api#Unit",
+                    "traits": {
+                        "smithy.api#enumValue": "VIOLENCE_OR_THREAT"
+                    }
+                }
+            }
+        },
+        "com.amazonaws.comprehend#ToxicLabels": {
+            "type": "structure",
+            "members": {
+                "Labels": {
+                    "target": "com.amazonaws.comprehend#ListOfToxicContent",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Array of toxic content types identified in the string.</p>"
+                    }
+                },
+                "Toxicity": {
+                    "target": "com.amazonaws.comprehend#Float",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Overall toxicity score for the string. Value range is zero to one, where one is the highest confidence.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Toxicity analysis result for one string. For more information about toxicity detection, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/toxicity-detection.html\">Toxicity detection</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#UnsupportedLanguageException": {
+            "type": "structure",
+            "members": {
+                "Message": {
+                    "target": "com.amazonaws.comprehend#String"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Amazon Comprehend can't process the language of the input text. For a list of supported languages,\n      <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/supported-languages.html\">Supported languages</a> in the Comprehend Developer Guide.\n    </p>",
+                "smithy.api#error": "client",
+                "smithy.api#httpError": 400
+            }
+        },
+        "com.amazonaws.comprehend#UntagResource": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#UntagResourceRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#UntagResourceResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#ConcurrentModificationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyTagKeysException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Removes a specific tag associated with an Amazon Comprehend resource. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#UntagResourceRequest": {
+            "type": "structure",
+            "members": {
+                "ResourceArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p> The Amazon Resource Name (ARN) of the given Amazon Comprehend resource from which you\n      want to remove the tags. </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "TagKeys": {
+                    "target": "com.amazonaws.comprehend#TagKeyList",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The initial part of a key-value pair that forms a tag being removed from a given resource.\n      For example, a tag with \"Sales\" as the key might be added to a resource to indicate its use by\n      the sales department. Keys must be unique and cannot be duplicated for a particular resource.\n    </p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#UntagResourceResponse": {
+            "type": "structure",
+            "members": {},
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#UpdateDataSecurityConfig": {
+            "type": "structure",
+            "members": {
+                "ModelKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the KMS key that Amazon Comprehend uses to encrypt\n      trained custom models. The ModelKmsKeyId can be either of the following formats:</p>\n         <ul>\n            <li>\n               <p>KMS Key ID: <code>\"1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n            <li>\n               <p>Amazon Resource Name (ARN) of a KMS Key:\n            <code>\"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\"</code>\n               </p>\n            </li>\n         </ul>"
+                    }
+                },
+                "VolumeKmsKeyId": {
+                    "target": "com.amazonaws.comprehend#KmsKeyId",
+                    "traits": {
+                        "smithy.api#documentation": "<p>ID for the KMS key that Amazon Comprehend uses to encrypt the volume.</p>"
+                    }
+                },
+                "VpcConfig": {
+                    "target": "com.amazonaws.comprehend#VpcConfig"
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>Data security configuration.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#UpdateEndpoint": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#UpdateEndpointRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#UpdateEndpointResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceInUseException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceLimitExceededException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceUnavailableException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Updates information about the specified endpoint.\n      For information about endpoints, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/manage-endpoints.html\">Managing endpoints</a>.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#UpdateEndpointRequest": {
+            "type": "structure",
+            "members": {
+                "EndpointArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendEndpointArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the endpoint being updated.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "DesiredModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The ARN of the new model to use when updating an existing endpoint.</p>"
+                    }
+                },
+                "DesiredInferenceUnits": {
+                    "target": "com.amazonaws.comprehend#InferenceUnitsInteger",
+                    "traits": {
+                        "smithy.api#documentation": "<p> The desired number of inference units to be used by the model using this endpoint.\n      \n      Each inference unit represents of a throughput of 100 characters per second.</p>"
+                    }
+                },
+                "DesiredDataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Data access role ARN to use in case the new model is encrypted with a customer CMK.</p>"
+                    }
+                },
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#UpdateEndpointResponse": {
+            "type": "structure",
+            "members": {
+                "DesiredModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the new model.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#UpdateFlywheel": {
+            "type": "operation",
+            "input": {
+                "target": "com.amazonaws.comprehend#UpdateFlywheelRequest"
+            },
+            "output": {
+                "target": "com.amazonaws.comprehend#UpdateFlywheelResponse"
+            },
+            "errors": [
+                {
+                    "target": "com.amazonaws.comprehend#InternalServerException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#InvalidRequestException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#KmsKeyValidationException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#ResourceNotFoundException"
+                },
+                {
+                    "target": "com.amazonaws.comprehend#TooManyRequestsException"
+                }
+            ],
+            "traits": {
+                "smithy.api#documentation": "<p>Update the configuration information for an existing flywheel.</p>"
+            }
+        },
+        "com.amazonaws.comprehend#UpdateFlywheelRequest": {
+            "type": "structure",
+            "members": {
+                "FlywheelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendFlywheelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the flywheel to update.</p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "ActiveModelArn": {
+                    "target": "com.amazonaws.comprehend#ComprehendModelArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Number (ARN) of the active model version.</p>"
+                    }
+                },
+                "DataAccessRoleArn": {
+                    "target": "com.amazonaws.comprehend#IamRoleArn",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The Amazon Resource Name (ARN) of the IAM role that\n      grants Amazon Comprehend permission to access the flywheel data.</p>"
+                    }
+                },
+                "DataSecurityConfig": {
+                    "target": "com.amazonaws.comprehend#UpdateDataSecurityConfig",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Flywheel data security configuration.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#input": {}
+            }
+        },
+        "com.amazonaws.comprehend#UpdateFlywheelResponse": {
+            "type": "structure",
+            "members": {
+                "FlywheelProperties": {
+                    "target": "com.amazonaws.comprehend#FlywheelProperties",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The flywheel properties.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#output": {}
+            }
+        },
+        "com.amazonaws.comprehend#VersionName": {
+            "type": "string",
+            "traits": {
+                "smithy.api#length": {
+                    "min": 0,
+                    "max": 63
+                },
+                "smithy.api#pattern": "^[a-zA-Z0-9](-*[a-zA-Z0-9])*$"
+            }
+        },
+        "com.amazonaws.comprehend#VpcConfig": {
+            "type": "structure",
+            "members": {
+                "SecurityGroupIds": {
+                    "target": "com.amazonaws.comprehend#SecurityGroupIds",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The ID number for a security group on an instance of your private VPC. Security groups on\n      your VPC function serve as a virtual firewall to control inbound and outbound traffic and\n      provides security for the resources that you’ll be accessing on the VPC. This ID number is\n      preceded by \"sg-\", for instance: \"sg-03b388029b0a285ea\". For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/VPC_SecurityGroups.html\">Security\n        Groups for your VPC</a>. </p>",
+                        "smithy.api#required": {}
+                    }
+                },
+                "Subnets": {
+                    "target": "com.amazonaws.comprehend#Subnets",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The ID for each subnet being used in your private VPC. This subnet is a subset of the a\n      range of IPv4 addresses used by the VPC and is specific to a given availability zone in the\n      VPC’s Region. This ID number is preceded by \"subnet-\", for instance:\n      \"subnet-04ccf456919e69055\". For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/VPC_Subnets.html\">VPCs and\n        Subnets</a>. </p>",
+                        "smithy.api#required": {}
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p> Configuration parameters for an optional private Virtual Private Cloud (VPC) containing\n      the resources you are using for the job. For more information, see <a href=\"https://docs.aws.amazon.com/vpc/latest/userguide/what-is-amazon-vpc.html\">Amazon\n        VPC</a>. </p>"
+            }
+        },
+        "com.amazonaws.comprehend#WarningsListItem": {
+            "type": "structure",
+            "members": {
+                "Page": {
+                    "target": "com.amazonaws.comprehend#Integer",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Page number in the input document.</p>"
+                    }
+                },
+                "WarnCode": {
+                    "target": "com.amazonaws.comprehend#PageBasedWarningCode",
+                    "traits": {
+                        "smithy.api#documentation": "<p>The type of warning.</p>"
+                    }
+                },
+                "WarnMessage": {
+                    "target": "com.amazonaws.comprehend#String",
+                    "traits": {
+                        "smithy.api#documentation": "<p>Text message associated with the warning.</p>"
+                    }
+                }
+            },
+            "traits": {
+                "smithy.api#documentation": "<p>The system identified one of the following warnings while processing the input document:</p>\n         <ul>\n            <li>\n               <p>The document to classify is plain text, but the classifier is a native document model.</p>\n            </li>\n            <li>\n               <p>The document to classify is semi-structured, but the classifier is a plain-text model.</p>\n            </li>\n         </ul>"
+            }
+        }
+    }
+}
diff --git a/tests/compatibility/conftest.py b/tests/compatibility/conftest.py
index 434a3687..389d6311 100644
--- a/tests/compatibility/conftest.py
+++ b/tests/compatibility/conftest.py
@@ -149,6 +149,17 @@ def _make_client(service_name):
     )
 
 
+@pytest.fixture
+def service_client(devcloud_server):
+    """Boto3 client factory for any service, by name.
+
+    Every named fixture below wraps this same call. Writing one more of them per
+    service is the only step of adding a service that scales with the size of
+    the fleet, so a new service gets a test through this factory instead.
+    """
+    return _make_client
+
+
 # --- Existing service fixtures ---
 
 
diff --git a/tests/compatibility/test_service_smoke.py b/tests/compatibility/test_service_smoke.py
new file mode 100644
index 00000000..c1303f95
--- /dev/null
+++ b/tests/compatibility/test_service_smoke.py
@@ -0,0 +1,61 @@
+"""Smoke coverage for services served by the generic CRUD engine.
+
+A scaffolded service is registered and routed the moment it is generated, which
+is not the same as being served: it answers an operation only if its provider
+hands the operation to the CRUD engine. This test is the difference between the
+two. It fails for a service that is routed but returns an error for every
+operation — the state every scaffolded service was in before the provider
+template opted into the engine.
+
+Adding a service means adding its name below, not writing a fixture.
+"""
+
+import pytest
+from botocore import xform_name
+from botocore.exceptions import ClientError
+
+# Services whose coverage comes from the generic CRUD engine rather than a
+# hand-written provider. The engine only serves the awsJson1_0 / awsJson1_1
+# protocols, which carry the operation name in X-Amz-Target; a rest-json,
+# query, or rest-xml service cannot be listed here and be served.
+ENGINE_SERVED_SERVICES = [
+    "comprehend",
+]
+
+
+def _parameterless_read_op(client):
+    """Return the first List*/Describe* operation that needs no input.
+
+    Picking the operation from the service model rather than hardcoding one per
+    service is what keeps this test from growing a branch per service.
+    """
+    model = client.meta.service_model
+    for name in sorted(model.operation_names):
+        if not name.startswith(("List", "Describe")):
+            continue
+        shape = model.operation_model(name).input_shape
+        if shape is None or not shape.required_members:
+            return name
+    return None
+
+
+@pytest.mark.parametrize("service", ENGINE_SERVED_SERVICES)
+def test_service_serves_at_least_one_operation(service_client, service):
+    client = service_client(service)
+
+    op = _parameterless_read_op(client)
+    assert op is not None, (
+        f"{service} declares no parameterless List*/Describe* operation, "
+        "so this test cannot establish that it serves anything"
+    )
+
+    try:
+        response = getattr(client, xform_name(op))()
+    except ClientError as exc:
+        pytest.fail(
+            f"{service}.{op} is routed but not served: {exc.response['Error']}. "
+            "The provider is most likely not returning plugin.ErrUnhandledOp, "
+            "so the request never reaches the CRUD engine."
+        )
+
+    assert response["ResponseMetadata"]["HTTPStatusCode"] == 200