Skip to content

✨ feat: hive-lite free-tier triage (non-CLI backends, Family C) - #186

Open
hanthor wants to merge 20 commits into
sync/upstream-v6-dea69b3from
feat/hive-lite-family-c
Open

hanthor wants to merge 20 commits into
sync/upstream-v6-dea69b3from
feat/hive-lite-family-c

Conversation

@hanthor

@hanthor hanthor commented Nov 16, 2026 •

Copy link
Copy Markdown
Member

Fork-first build of hivecommons#18464 (non-CLI backends and a zero-cost CLI-less coordinator), cut to the scope the maintainer accepted.

Stacked on #179 (sync/upstream-v6-dea69b3), so this diff is only the hive-lite work. Merge #179 first, and GitHub retargets this PR to tuna/v6.

Scope per hivecommons#18464 decision

Decision (clubanderson): accepted with scope cuts, targeting v6.

  • Phase 1: the router, executor and tool classes as a default-off, report-only advisory engine over existing Model Gateways, shadow first.
  • Phase 2: a read-only MCP server at ADVISORY.
  • Deferred until phase 1 shows advisory quality over a few weeks: write tools, vendor sessions, chat bridges and serverless stores.
  • Hard rules: vendor agents never write to GitHub (there is no github-mediated mode). All writes stay with the Hive App. Tool-hosted is capped at ISSUES_AND_PRS permanently. Free tiers that train on inputs stay off for private repos by default.

This PR now enforces those rules:

Area State in this PR
pkg/extwork Only tool-hosted exists. github-mediated, MediatedPR and VetMediatedPR are gone. ClampMode never returns a mode above the request, the posture's ceiling or ISSUES_AND_PRS, and a test covers every mode and request.
pkg/hivetool Read tools and terminal markers only. The write side (repo.patch_files, pr.create, RESTWriter, Verifier) is removed, and a test asserts that Definitions is read-only at every agent mode.
cmd/hive-lite Report-only shadow. -post, -fix and -verify are gone, and the GitHub client is GET-only. State is memory-only, so it writes nothing anywhere. It prints the advisory and JSON to stdout.
cmd/hive-mcp Read-only at ADVISORY. -write is gone, every principal is clamped to ADVISORY, and a token entry naming any other mode is refused. Tests assert that no write tool is listed or callable.
pkg/coordstate Open accepts only memory, so both binaries are memory-only. github specs are refused as a GitHub write (each checkpoint would be a commit). d1: specs are refused because serverless stores are deferred. The Contents and D1 driver code stays, marked deferred and unwired.
hive-lite-triage.yml Deleted. Phase 1's report-only engine runs inside the Hive over Model Gateways, not as a public Actions job, and a step summary on a public repo is published output.
pkg/turn/llmrouter trains_on_inputs per provider. WithPrivateRepo skips training providers unless allow_training_providers_for_private opts in. hive-lite sets it from repo visibility, and treats unknown or internal visibility as private.

Contents

The first six commits are cherry-picked (-x) from the upstream PRs, unchanged:

New, fork-only:

  • pkg/hivelite.RunTriage holds the session policies proven in live runs:
    • ioscan-screened issue body pinned in the task message, plus a per-session canary;
    • forced finish phase;
    • grounded implicit completion;
    • canary and ioscan output withholding (a withheld summary is also redacted from the JSON);
    • capacity → retry later;
    • only a report-only admission runs. Anything above ADVISORY is refused.
  • cmd/hive-lite: gateways.yaml (Hive GatewayConfig entries in failover order, as a list or a mapping with gateways: and allow_training_providers_for_private:) and pkg/codeindex search. Exit 75 means no free capacity.
  • pkg/coordstate: a compare-and-swap Store with a memory driver and a merge-on-flush router ledger. pkg/hivelite checkpoints to a configured Store, with the canary stripped. The binaries configure none, because durable stores are deferred.
  • pkg/hivemcp + cmd/hive-mcp: the Family E agent-driven MCP server, read-only.
    • Hashed bearer tokens map to principals at ADVISORY.
    • The client gets an offer, then accepts or declines, and only then receives the brief.
    • Hive executes every read tool with the evidence gate.
    • Claim leases and sessions live in a Store (memory in the binary).
  • llmrouter fix (🐛 llmrouter: sanitise invalid history tool args, fail over on truncated calls hivecommons/hive#18511 upstream): invalid history tool arguments are wrapped, length-truncated tool calls fail over, and max_tokens is configurable.

Earlier live results (before the scope cut)

  • Dry run, Workers AI free tier, 🐛 scanner: stale Dependabot PRs stay stuck (App's @dependabot rebase is refused; NOTICE commit blocks rebase) hivecommons/hive#18441: 13 turns in 68 s, with a grounded advisory and 1 of 1 citations verified. glm-4.7-flash returned HTTP 500 mid-session. The router cooled it down, gpt-oss-120b served 8 turns and glm served the last one. pkg/codeindex hit its 64 MB text budget on the hive repo, so search coverage was partial.
  • MCP: Claude Code (haiku) finished a triage for $0.006 of its own inference, with 4/4 citations verified. Two concurrent clients claimed different issues.
  • The fix-mode, GitHub-state-branch and workflow results from earlier revisions of this PR came from code that this PR has now removed.

Testing

The fork's PR checks run no Go tests (this PR's base is not a release branch), so v2-tests.yml is dispatched on the branch. Following the repo's CLAUDE.md, the suite wasn't run locally. Locally, only gofmt ran, plus a compile and type-check of the changed packages and their tests.

🤖 Generated with Claude Code

hanthor and others added 7 commits November 16, 2026 19:34
…r turn.Runner (hivecommons#18464)

First library slice of RFC hivecommons#18464 (Family C, stateless LLM backends).

- pkg/turn/llmrouter: turn.LLMClient over an ordered list of
  OpenAI-compatible /chat/completions providers. 429 honours
  Retry-After; 5xx/408/transport and 200-with-error bodies fail over;
  401/403 and 404/410 (retired free model) fail over with long
  cooldowns; other 4xx are returned without resending. Cooldowns and
  per-UTC-day request caps live behind a Ledger interface so a
  stateless coordinator can persist them. API keys are referenced by
  env var name only.
- pkg/turn: new ErrInferenceCapacity sentinel. Runner.Step parks the
  session as paused without consuming a turn when the LLM client
  reports it, and resumes on the next served inference. Previously any
  LLM error marked the session failed.

Not wired into any binary or config; default behaviour is unchanged.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
(cherry picked from commit 11fae40)
Signed-off-by: James Reilly <jreilly1821@gmail.com>
…runs (hivecommons#18464)

Converge with the in-flight gateway work instead of a parallel config:
- FromGateway builds a provider from crux/config.GatewayConfig,
  authenticates via crux/inference.ResolveGatewayAuth (key env/file,
  watsonx IAM mint + project header) and POSTs to
  config.LiteLLMChatCompletionsURL, the URL rule the inference
  translator and Test Connection share. Keyless gateways stay keyless.
- HealthHook feeds crux/inferencehealth so free-tier throttling shows in
  the existing gateway-health surface; a served attempt clears it.

Fixes found by running turn.Runner + llmrouter live against Workers AI:
- Tool names: hive-tool/v1 dotted names are mapped to the OpenAI
  function-name alphabet and back. With "issue.read", llama-4-scout
  silently answered in prose; with "issue_read" it called the tool.
- Assistant tool-call messages send content "" not null: Workers AI
  gpt-oss-120b 400s on null.
- A 200 whose content is one repeated character (seen: ~300 '!') is
  malformed and fails over instead of entering the envelope.
- A 429 naming a per-day limit (RPD/TPD/daily) cools the provider down
  until 00:00 UTC rather than 60s; cooldown uses a fresh clock read.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
(cherry picked from commit 56841d4)
Signed-off-by: James Reilly <jreilly1821@gmail.com>
…es, tool_choice (hivecommons#18464)

From live finish-phase runs (only task.complete offered):
- the model still called repo__search_code and then repo.read_file. The
  router built its wire-name map only from the offered tools, so the
  first reached toolapprove unmapped, and the Runner executed the second
  although it was never offered.

- turn.Runner denies (before approval, never executes) any call to a tool
  outside AvailableTools when that list is non-empty; the deny is recorded
  as a tool_approval operation and returned to the model with the list of
  available tools. An empty list keeps today's behaviour.
- llmrouter maps names seen in the conversation history back as well.
- llmrouter.WithToolChoice sets OpenAI tool_choice. Measured on Workers
  AI: llama-4-scout and glm-4.7-flash honour "required"; gpt-oss-120b
  ignores it and still reports finish_reason "tool_calls".

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
(cherry picked from commit 63039da)
Signed-off-by: James Reilly <jreilly1821@gmail.com>
…ivecommons#18464)

A plain sliding window (DefaultCompactor{2,20}) dropped the issue itself
in a live Family C run. The model re-read it and repeated identical
searches until max-turns.

DigestCompactor keeps the pinned head (primer + task) and a recent window,
and replaces the dropped middle with one deterministic user message
listing the tool calls already made. The list is carried forward across
compactions, deduplicated and bounded, so no extra model call is needed.
The recent window never starts on a tool result whose tool_calls message
was dropped, because OpenAI-compatible APIs may reject an orphaned tool
message.

Opt-in via WithCompactor. DefaultCompactor is unchanged.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
(cherry picked from commit e314989)
Signed-off-by: James Reilly <jreilly1821@gmail.com>
…ommons#18464)

The tool-host surface proposed in RFC hivecommons#18464 uses dotted names
(issue.read, pr.create, ...). None of toolapprove's heuristics
(pull_request, merge, mcp__github__ prefixes) recognised them, so:
- reads were "side-effectful" and operator-gated at L1-L4 (measured in a
  live turn.Runner session: every file read stalled for approval), and
- pr.create / issue.comment / repo.patch_files were neither GitHub writes
  nor issue/PR operations, so an ADVISORY agent's calls skipped the
  AgentMode capability checks and auto-approved at L5/L6 on a green scan.

Explicit classes fix both before any tool-hosted backend exists. No CLI
backend emits these names, so no current verdict changes (the RFC hivecommons#4000
parity constraint).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
(cherry picked from commit c8e3b18)
Signed-off-by: James Reilly <jreilly1821@gmail.com>
…ommons#18464)

The read side of the tool host from RFC hivecommons#18464: a turn.ToolExecutor for
credential-less backends, pinned to one repository and ref.

- Tools: issue.read, repo.list_files, repo.read_file (<=200 lines per
  call, with a continuation hint), repo.search_code (CodeSearcher; the
  CodeIndexSearcher adapter uses pkg/codeindex, not GitHub code search),
  checks.read, task.complete / task.abort. Write tools are absent and
  return ErrUnknownTool naming what is available.
- Every output is capped at 12k chars with a "narrow the request" hint.
  Paths are confined to the repository. An identical repeated call
  (canonical JSON) is refused with a pointer to the earlier result. A
  failed call can be retried.
- Evidence gate (RequireEvidence): task.complete records which path:line
  citations the session actually served (read ranges and search hits).
  Optionally it refuses a summary with none.
- ParseFenced: ```hive-tool JSON blocks for chat-only bridges and for
  models that write a tool call as prose.
- Definitions/FinishOnly produce tool schemas in the llmrouter convention.

Each rule comes from a measured failure in live turn.Runner runs on Workers
AI (hivecommons#18464 comment): GitHub search loops, re-reads, ungrounded two-turn
"triage", and runs that never finished.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
(cherry picked from commit da52100)
Signed-off-by: James Reilly <jreilly1821@gmail.com>
…mons#18464)

Fork-first build of RFC hivecommons#18464's Family C on top of the upstream PR slices
(llmrouter hivecommons#18465, toolapprove classes hivecommons#18467, hivetool hivecommons#18472):

- pkg/hivelite.RunTriage drives one session:
  - ioscan-screened issue body pinned in the task message, plus a
    per-session canary;
  - DigestCompactor;
  - forced-finish phase that offers only terminal tools (tool_choice
    "required" where honoured);
  - finish-phase prose accepted only through the same evidence gate;
  - canary echo or an ioscan output block withholds the result;
  - ErrInferenceCapacity propagates so a later pass can retry.
- cmd/hive-lite: gateways.yaml (Hive GatewayConfig entries in failover
  order, plus model and daily_cap) and pkg/codeindex search over a
  checkout. Dry-run by default; -post upserts one marked advisory comment.
  Exit 75 means no free capacity now.
- .github/workflows/hive-lite-triage.yml: workflow_dispatch on a free
  hosted runner.

Live run (Workers AI free tier, hivecommons#18441, dry run): 13
turns, 68s, a grounded advisory with 1 of 1 citations verified. glm-4.7-flash
returned HTTP 500 mid-session; the router cooled it down, gpt-oss-120b
served 8 turns, and glm served the final one.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
@tuna-reef-hive

tuna-reef-hive Bot commented Nov 16, 2026 •

Copy link
Copy Markdown
408110d

ℹ️ Sentinel notice — informational; author is trusted (owner), merge is not blocked

Hive flagged this PR (author @hanthor, head 408110def720) because it matches behaviors that can override security controls, escalate privileges or damage the codebase. This is a heuristic, not an accusation — a maintainer should confirm the change is intended before it merges.

  • sensitive_path — changes 1 sensitive path(s) (Touches a sensitive path (OWNERS, workflows, policies, hive config, security docs, …))
    • .github/workflows/hive-lite-triage.yml
  • permission_escalation — widens workflow permissions or uses pull_request_target (Widens GitHub Actions permissions or switches to pull_request_target)
    • .github/workflows/hive-lite-triage.yml
  • ci_gate_weakening — CI configuration is deleted, softened or has gate checks removed (Disables or softens CI gates (continue-on-error, || true, removed checks))
    • .github/workflows/hive-lite-triage.yml

Hive did not add the sentinel-alert label because this author is trusted. The finding remains recorded for audit and the dashboard Security tab; set sentinel.trusted_authors_block: true to require the blocking label for trusted authors too.

@tuna-reef-hive

tuna-reef-hive Bot commented Nov 16, 2026 •

Copy link
Copy Markdown

Hive status — updated in place; edits do not notify. Full history is in the Activity Monitor.

@hanthor this PR is held at stage/071-needs-author and the hive will not merge it yet.

Failing checks:

  • check-failure

Next: the hive does not push to your branch. Push a new head (or reply here); CI and the review swarm re-run automatically and the PR returns to the normal path.

hanthor and others added 4 commits November 16, 2026 19:57
… branches

- A 400 whose body shows the provider failed to parse the model's own
  tool-call generation (Workers AI code 3030: glm-4.7-flash emitted
  "<tool_call>…" its server parser rejected as json_invalid, seen live in
  a hive-lite fix session) is a malformed generation, not a bad request:
  it now fails over with the short cooldown. Plain 400s still do not.
- Coverage for the package was 86.3%, below the 90% gate. This adds tests
  for key-file and Auth resolution with extra headers, transport-error
  failover, context cancellation, ledger errors, a cooldown that never
  shortens, parseResponse/normalizeArguments edge cases, rejected request
  bodies, CapacityError text, keyless FromGateway, and a truncated 200 body.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
(cherry picked from commit 0ce5f50)
Signed-off-by: James Reilly <jreilly1821@gmail.com>
…r failures

Package coverage was 84.9%, below the 90% gate.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
(cherry picked from commit e69be78)
Signed-off-by: James Reilly <jreilly1821@gmail.com>
…eate

The write half of RFC hivecommons#18464 ModeToolHosted (fork-first;
gated upstream). The model holds no credential; Hive applies its patches
to an executor-pinned work branch via the Git Data API and opens a DRAFT PR.

Guards, each enforced in the executor independently of toolapprove:
- the mode must be push-capable (ISSUES_AND_PRS+); Writer and WorkBranch
  must be set;
- pushbroker.DefaultProtectedPaths are refused (.github/workflows/, OWNERS,
  policies/ ...), and paths are confined to the repository;
- search/replace must match exactly once;
- a whole-file content write that drops more than 30% of an existing file's
  lines is refused (live: a free model "fixed" a one-line bug by rewriting
  the file and deleted an unrelated function);
- an optional Verifier runs before every commit, and its report goes back
  to the model on failure;
- any argument carrying the session canary is refused; size limit 256 KiB;
- one draft PR per session;
- closing keywords in the PR body become "Refs #N";
- Hive appends its own verification record (or a warning that none ran),
  so the model's prose claims are distinguishable from checks that ran;
- reads follow the work-branch head once it exists (live: a resumed
  session read the base and kept re-patching).

Comparer/RESTWriter.Compare render the branch diff for resumed sessions.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
- hivelite.Config.Fix/Writer/WorkBranch/Verifier. In fix mode the session
  runs as ISSUES_AND_PRS at ACMM >= 5, the finish phase still offers
  repo.patch_files and pr.create (live: a session diagnosed the bug
  exactly and could not patch), and a resumed session's task message pins
  the work branch's existing diff (live: it otherwise redid the fix).
- cmd/hive-lite: -fix (refuses while a hive-lite draft is open for the
  issue) and -verify '<cmd>', which runs in a scratch copy of -checkout
  with credential variables scrubbed. Model-authored code executes there,
  so use an ephemeral runner.

Live (Workers AI free tier, private sandbox hanthor/hive-lite-sandbox#1):
- first attempt without guards: a broken draft (deleted Page(), a failing
  test), closed and recorded;
- with guards: a verified one-line fix (ceiling division), and draft PR #4
  in 4 turns of a resumed session. It closes no issue and was gofmt-, vet-
  and test-clean.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
Adds the two non-CLI admission modes from RFC hivecommons#18464 §2.
A declaration-only mode is refused by the binding unless the adapter
lists it via PostureDeclarer, so existing adapters keep refusing them.
ClampMode caps the tool host's agent mode at the posture ceiling
(tool-hosted: ISSUES_AND_PRS; everything else: ADVISORY). VetMediatedPR
is the outside-contributor bar for vendor-written PRs: green checks, no
protected paths, an approval by someone other than the author or a Hive
identity. hive-lite fix mode now runs as a tool-hosted admission and is
refused under report-only or github-mediated.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
@hanthor
hanthor added this pull request to stack #187 November 16, 2026 21:18
hanthor and others added 8 commits November 16, 2026 21:21
…ed calls

Live (Workers AI gpt-oss-120b, 2026-11-16): a task.complete call was cut
off mid-string by the output limit. The executor refused it, but the
router resent those bytes as history, and Workers AI rejected every later
request with HTTP 400 code 3030 "Unterminated string" (the column was
where the summary value began). Invalid arguments are now wrapped as
{"invalid_arguments": "<raw>"} when resent; a tool call with invalid
arguments and finish_reason length is malformed (fail over) since the
same request would be cut off again; Provider.MaxTokens sets max_tokens.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
pkg/coordstate is the small Store from RFC hivecommons#18464 §7:
compare-and-swap per key, a memory driver and a GitHub Contents API
driver whose Version is the blob sha (PUT with a stale sha is a 409, the
only per-file CAS GitHub offers). It bootstraps an orphan state branch.
The router Ledger loads once and merges on flush (same-day counts add,
later cooldown wins) so overlapping passes neither lose nor double spend.

hive-lite checkpoints the envelope plus executor memory (evidence spans,
duplicate fingerprints, write-side state) on every exit and resumes an
unfinished checkpoint of the same admission mode. The canary never
reaches the store: the system prompt is emptied and rebuilt with a fresh
canary on resume, and any echo is replaced before writing. A save
conflict is reported, never overwritten.

Live on a private sandbox: pass 1 paused at a daily cap of 3 (exit 75);
pass 2 was refused by the persisted ledger; pass 3 resumed at turn 3;
pass 4 resumed at turn 11 and completed with 3/3 citations verified
against code read in earlier passes.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
A remote MCP server (Streamable HTTP, POST-only, JSON responses, the
same shape as the dashboard's public knowledge endpoint) through which
an MCP-capable agent spends its own inference on Hive work, per RFC
hivecommons#18464 §3a. Hive holds no model credential and the
client holds no GitHub credential; every tool call is executed by
hivetool.Executor under a tool-hosted admission (ClampMode: never merge;
no Writer means no write tools).

- Bearer tokens are stored hashed and map to a principal and mode.
- hive_next_task offers issue number and title only; hive_accept_task
  delivers the ioscan-screened brief; hive_decline_task skips.
- Sessions (executor evidence and duplicate memory) and per-issue claim
  leases live in a coordstate.Store under CAS, so the handler is
  stateless; a lapsed claim taken by someone else ends the old session.
- Per-principal call budget; sessions bound to the opening principal.

Live: Claude Code (haiku) connected over MCP and triaged a sandbox issue
in 9 turns for $0.006 of its own inference, 4/4 citations verified. Two
concurrent clients on a GitHub state branch claimed different issues and
both completed (5/5, 4/4 verified). That run exposed that the Contents
API answers 409 for a concurrent write to a DIFFERENT file on the same
branch; ContentsStore now re-reads the key and retries when its version
still matches, so only a real change is ErrConflict.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
The malformed answer in the first half of the test cools provider a
down, so the second half was served by b.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
…trip

Acquire returns three values; v2-tests on the branch caught the
assignment mismatch. Adds a State JSON round-trip test (duplicates,
evidence, write-side fields, outcome) for hivetool coverage.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
D1Store keeps each key as a row (key, value, version) and uses the D1
HTTP query API, so it works from a CI runner as well as a Worker. Create
is INSERT ... ON CONFLICT DO NOTHING, update is UPDATE ... WHERE
version = ?, and the changed-row count decides success or ErrConflict:
a real per-row CAS with no branch-wide serialisation and no history.
Table creation is retried until it succeeds rather than memoised.

coordstate.Open parses github, github:owner/name@branch and
d1:<account>/<database>; hive-lite and hive-mcp use it for -state.

Live (free D1, replication off): CAS semantics hold; 20 concurrent
increments of one key end at exactly 20 (10.7 s wall, hot-key
contention); two overlapping ledger flushes merge to the exact sum;
~0.86 s per get+put from this host vs ~1.0 s for the Contents driver.
Two concurrent Claude Code clients on hive-mcp with -state d1 claimed
different issues and both completed: 4 rows, ~32 row writes, versus 52
commits on a state branch for the same run on the Contents driver.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
… no GitHub writes

Aligns the fork's hive-lite work with the maintainer decision on RFC
hivecommons#18464 (issuecomment-6938430548): phase 1 is a
default-off, report-only shadow advisory engine; phase 2 is a read-only
MCP server at ADVISORY. Vendor agents never write to GitHub, all writes
stay with the Hive App, and tool-hosted is capped at ISSUES_AND_PRS.

Removed:
- extwork: the github-mediated posture (ModeGitHubMediated, MediatedPR,
  VetMediatedPR, ErrMediatedPR) and its tests. ClampMode now also caps at
  ToolHostedCeiling and treats an out-of-range request as ADVISORY.
- hivetool: the whole write side (repo.patch_files, pr.create, Writer,
  RESTWriter, Verifier, Comparer, work-branch reads) and the write fields
  of the executor snapshot. Definitions offers read tools at every mode.
- hive-lite: -post, -fix and -verify (verify.go). The GitHub client is
  GET-only. hivelite.Config has no Fix/Writer/WorkBranch/Verifier, and
  any admission above ADVISORY is refused. Checkpoint shape bumped to v2
  so a v1 fix-mode checkpoint never resumes.
- hive-mcp: -write and Config.Writer/Verifier. Every principal is clamped
  to ADVISORY, and token entries naming any other mode are refused.
- coordstate.Open no longer selects the GitHub Contents driver (each
  checkpoint is a commit, so a GitHub write); the driver stays in code,
  marked unused and deferred. Binaries take memory (default) or d1:.
- hive-lite-triage.yml: contents/issues read, no post input, no
  -state github; optional D1 state via the HIVE_LITE_STATE secret.

Added:
- llmrouter: Provider.TrainsOnInputs (trains_on_inputs) with
  WithPrivateRepo and WithAllowTrainingProvidersForPrivate. A private
  router skips training providers, and New fails with
  ErrOnlyTrainingProviders when none would be left. hive-lite sets it from
  the repository's visibility (unknown or internal counts as private) and
  reads allow_training_providers_for_private from gateways.yaml (mapping
  form) or a flag.
- Tests: ClampMode never raises over every mode and request; no
  github-mediated admission; Definitions read-only at every mode; hive-lite
  offers read tools only and refuses tool-hosted; hive-mcp lists and
  resolves no write tool for any principal and clamps a stored session;
  Open refuses github specs; router privacy cases.

A withheld advisory's summary is also redacted from hive-lite's JSON
output, since that output now lands in a step summary.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>
Owner decisions on the two open items from the hivecommons#18464 scope cut:

- coordstate.Open now refuses d1: specs too, because serverless stores
  are deferred per hivecommons#18464. Only "" and "memory" are
  accepted, so hive-lite and hive-mcp are memory-only. The D1 driver code
  stays, with a doc comment marking it deferred and unwired. Open loses
  its Cloudflare token argument, and both binaries drop cfToken.
- .github/workflows/hive-lite-triage.yml is deleted. Phase 1's
  report-only engine runs inside the Hive over Model Gateways, not as a
  public Actions job, and a step summary on a public repo is published
  output. The changelog fragments no longer mention the workflow, D1
  state or the HIVE_LITE_STATE secret.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: James Reilly <jreilly1821@gmail.com>

@tuna-reef-hive tuna-reef-hive Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Decision needed: @hanthor should decide whether the policy changes in src/pkg/extwork (admission.go, binding.go, posture.go) and src/crux/toolapprove/classify.go may land as part of this 8k-line hive-lite PR, given that it is stacked on #179 and two checks are red.

I did not review the full diff: it is 8,226 added lines across 55 files, too much to read honestly in one pass, so this is routing, not a code review.

What I can state from the PR metadata:

  • Base is sync/upstream-v6-dea69b3, not main. The body says it is stacked on #179 and GitHub retargets it once that merges.
  • overlap and release-lines-in-sync are failing on this head. The failed-log tail I could fetch contained only checkout cleanup, so I do not know why they fail; the runs date from 2026-11-17.
  • It changes trust-adjacent code: src/pkg/extwork/admission.go, binding.go, new posture.go, and src/crux/toolapprove/classify.go. The body describes these as enforcing hard rules (no GitHub-mediated mode, ClampMode capped at ISSUES_AND_PRS, read-only hivetool). I did not verify those claims against the code.
  • Positive: it ships tests alongside the new packages (e.g. src/pkg/extwork/posture_test.go, src/pkg/hivetool/hivetool_test.go) and a changelog.d/ fragment per feature.

Suggestion: a maintainer familiar with the extwork/toolapprove policy should review those four files specifically, after #179 lands and the two checks are green.

— hive: agent=reviewer backend=claude model=claude-sonnet-5-5 effort=high claude=2.1.322

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant