You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- Source parity state: V41 opens prompt-program parity over V40 exhaustive testing, V38 inference correctness, and V39 commercial Reading readiness; source-side prompt and PromptPart rewrites are blocked until catalogue, benchmark, interpolation, registry, callsite, and return-type surfaces are specified and checked
13
13
- Notes companion: `BITCODE_SPEC_V41_NOTES.md`
14
14
- Delta companion: `BITCODE_SPEC_V41_DELTA.md`
@@ -116,6 +116,8 @@ Gate 2 also preserves V41 scope and prepares draft V42 only as forward roadmap t
116
116
117
117
Gate 3 must prove the composition chain from phase and pipeline context through PTRR agents, PTRR steps, FailsafeGenerationSequence, and ThricifiedGeneration final prompt resolution.
@@ -449,6 +451,7 @@ Generation must fail closed when artifact freshness, source-safety, benchmark co
449
451
450
452
V41 Gate 1 validates with `pnpm run check:v41-gate1`, `node scripts/check-bitcode-spec-family.mjs --version V41 --mode draft --current-target V40`, `node scripts/check-bitcode-canon-posture-drift.mjs --active-canon V40 --draft-target V41`, and `node scripts/check-bitcode-canonical-inputs.mjs --current-target V40`.
451
453
V41 Gate 2 validates with `pnpm run generate:v41-prompt-inventory`, `pnpm run check:v41-prompt-inventory`, `pnpm run check:v41-gate2`, and `node --test --test-force-exit packages/protocol/test/v41-promptpart-prompt-inventory.test.js`.
454
+
V41 Gate 3 validates with `pnpm run generate:v41-registry-interpolation-contracts`, `pnpm run check:v41-registry-interpolation-contracts`, `pnpm run check:v41-gate3`, and `node --test --test-force-exit packages/protocol/test/v41-registry-interpolation-contracts.test.js`.
452
455
Later gates add focused generator, checker, package, benchmark, and workflow commands.
- Source parity state: V41 source parity begins at specification and workflow posture; prompt rewrites are explicitly deferred until catalogue and benchmark gates close
- Source parity state: V41 source parity now includes prompt inventory plus registry/interpolation contracts; prompt rewrites are explicitly deferred until catalogue, contract, and benchmark gates close
12
12
- Scope: V41 draft delta for Prompt and PromptPart excellence over promoted V40
13
13
14
14
## Why V41 exists
@@ -39,6 +39,8 @@ It also records V42 as the subsequent MVP experience version for shortest-path D
39
39
### Gate 3: Registry Composition And Interpolation Contracts
40
40
41
41
Prove registry composition, prompt context interpolation, execution ancestry, tool prompt injection, and parsed return type bindings.
42
+
Gate 3 is package-backed by `buildV41RegistryInterpolationContracts`, emits `.bitcode/v41-registry-interpolation-contracts.json`, and currently covers 12 source-safe contract rows with 65 passing source predicates across Prompt registry totality, PromptPart interpolation, PTRR agent/step composition, FailsafeGenerationSequence context handling, ThricifiedGeneration final prompt resolution, execution ancestry overlays, tool doc-code prompt injection, Reading parser targets, Finding Fits search contracts, and AssetPack synthesis/finishing parser targets.
43
+
It preserves V42 as subsequent reliable MVP experience planning while keeping V41 focused on prompt-program correctness.
- Source parity state: V41 notes track prompt-program planning, catalogue, benchmark, rewrite, telemetry, and promotion parity over active V40
13
13
- Draft target posture: V41 Gate 1 creates the full SPEC, DELTA, NOTES, and PARITY family.
14
14
- Scope: Prompt and PromptPart excellence over the promoted V40 exhaustive testing base.
@@ -29,8 +29,16 @@ This is an inventory and admission artifact, not a rewrite artifact.
29
29
30
30
V42 is re-roadmapped as the MVP experience version after V41.
31
31
Its focus is shortest-path Depositing, shortest-path Reading, and a strong AI-reading dominant demonstration where any deposit source can contribute proprietary or otherwise non-public training, prompt, context, or evaluation material to an AssetPack that measurably improves an AI system beyond public-data-only performance.
32
+
Depositing must minimize the path to admitting source material and later receiving BTC compensation when the deposit participates in a synthesized AssetPack.
33
+
Reading must minimize the path from Read Request to synthesized Need review/resynthesis, Finding Fits, source-safe AssetPack preview, BTD/BTC purchase and settlement, and repository delivery.
32
34
V42 must keep depositor compensation, reader purchase, BTD/AssetPack rights, and repository delivery visible in the shortest path without widening V41 beyond Prompt and PromptPart excellence.
33
35
36
+
## Gate 3 registry and interpolation contract note
37
+
38
+
Gate 3 makes the prompt registry call chain source-checkable before prompt rewrites.
39
+
The package-backed contract currently emits 12 rows and 65 source predicates for Prompt registry totality, TemplatedPromptPart interpolation, PTRR agent and step prompt composition, FailsafeGenerationSequence context handling, ThricifiedGeneration final prompt resolution, execution ancestry overlays, tool doc-code prompt injection, Reading parser targets, Finding Fits search and embedding contracts, AssetPack synthesis and finishing parser targets, and Gate 2 inventory binding.
40
+
The artifact records ids, source paths, hashes, predicate verdicts, parser target ids, interpolation key ids, and ancestry frame ids only; it does not serialize raw prompt text, provider responses, private context, credentials, or unpaid AssetPack source.
It may not serialize raw prompt text, raw provider responses, protected source, private context, credentials, settlement-private payloads, or unpaid AssetPack source.
72
+
It closes prompt rewrites' precondition that prompt composition and interpolation contracts are observable before semantic PromptPart or Prompt rewrite work proceeds.
73
+
70
74
## V41 completion condition
71
75
72
76
V41 closes when prompt-program quality is fully specified, implemented, benchmarked, source-safe, tested, documented, generated, workflow-checked, and promotion-ready across Reading, Conversation, tool-definition, and interface inference surfaces.
0 commit comments