Repository Conventions adversary

review/conventions reviews changed code against the conventions of the repository being changed.

It considers both declared rules—such as contributor guides, AGENTS.md, formatter and linter configuration—and conventions encoded in existing code. An inferred convention requires several consistent examples and is rejected when meaningful counterexamples exist. A second model pass independently verifies every proposed finding.

The package is language-agnostic. It reports only deviations introduced by the change and cites both the changed line and the repository evidence establishing the convention.

SDK source coverage

The SDK dependency follows the published version pinned in package.json. Model review retains evidence-backed findings when repository source coverage is partial, records the limitation, and does not grant a whole-change clean opinion. Provider and output-validation failures are not coverage gaps: they retain failure or model-unavailable reporting and cannot grant a whole-change clean opinion.

Generated dependency lockfiles (package-lock.json, npm-shrinkwrap.json, yarn.lock, pnpm-lock.yaml, and Bun lockfiles) are outside conventions review. Deliberately excluding them does not mark a completed source review as incomplete. Unread or excluded source files still report a limitation.

Bounded model output repair

Model stages use the SDK output-validation loop with at most two final-generation requests (initial output plus one repair), unless a stage already supplies its own bounded validator. Broker and client schema failures provide specific feedback to final generation; gathered evidence and the original deadline are retained. Rejected completion usage is included in returned totals and terminal or interrupted ModelReviewError failures. Unexpected exceptions from custom model implementations propagate unchanged and do not expose SDK usage totals; custom models should report request failures with ModelReviewError. Exhausted validation remains incomplete and cannot grant a whole-change clean opinion.

This release uses SDK 0.1.43, including schema repair and interrupted-repair usage preservation.

Provider transport retries and format corrections have their own existing bounds; the two-attempt limit applies to SDK final-generation requests.

SDK 0.1.43

This release rebuilds with SDK 0.1.43. SDK PR #73 adds a tested neutral fallback to formatOpinionAsync when concern wording validation is exhausted, preserving completed findings and the ship decision. Reviewers that do not call this API retain their existing opinion behavior. Provider and transport failures remain errors. Domain rules and evidence requirements are unchanged.