fix(runtime): classify repeated adjudicated-revision validation failures (#293) - #295
Merged
Merged
Conversation
…res (#293) - Introduce ProviderFailureStage and RunFailureStage distinguishing transport-parsing, response-schema-validation, artifact-schema-validation, and factual-invariant-rejection - Propagate failureStage across ProviderAdapterError, RunError, and AuthorRetryFeedback without exposing private values or text - Provide deterministic carrier tests covering all 4 failure stages and valid 10-finding reproduction - Extract invalidAuthorProposalError to author-output.ts, lowering local.ts hotspot line count
akoita
deleted the
codex/issue-293-adjudicated-revision-classification
branch
September 3, 2026 23:08
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #293
Summary of Changes
Failure-Stage Classification:
ProviderFailureStageandRunFailureStagedistinguishing four content-free failure stages:transport-parsingresponse-schema-validationartifact-schema-validationfactual-invariant-rejectionfailureStageacrossProviderAdapterError,RunError, andAuthorRetryFeedback.completeCvProposalIssues:"missing_evidence","unsupported_claim","factual_invariant_violation".Sanitized Deterministic Coverage:
packages/application/src/adjudicated-revision-validation.test.tsreproducing the confirmed 10-finding carrier shape (2 accepts, 2 rejects, 6 nuances, 2 accepted effect overrides).awaiting-approval.Hotspot Lineage:
proposalDiagnosticsandinvalidAuthorProposalErrorfrompackages/application/src/local.tstopackages/application/src/author-output.ts.local.tsline count from 4,059 to 4,019 lines and lowered its architecture hotspot limit accordingly inscripts/architecture-hotspots.mjs.Quality Gates:
pnpm format,pnpm lint,pnpm typecheck,pnpm test(1,275 unit tests + 54 release tests), andpnpm validatepass 100% cleanly.