Files
Trevin Chow 63f7e4fe30 refactor(ce-code-review): adopt anchored confidence, validation gate, and mode-aware precision
Port the anchored-rubric pattern from ce-doc-review and add three
code-review-specific precision controls inspired by Anthropic's official
code-review plugin.

Changes:
- Replace continuous confidence (0.0-1.0) with integer enum [0,25,50,75,100]
  and behavioral anchors. Threshold: anchor 75 (P0 escape at anchor 50).
- Replace +0.10 cross-reviewer boost with one-anchor promotion
  (50 -> 75, 75 -> 100). Sort by anchor descending.
- Add Stage 5b validation pass: independent validator subagent per surviving
  finding before externalization. Mode-conditional (headless/autofix and
  interactive LFG/File-tickets routing). 15-finding budget cap. No metadata
  field on findings; rejected drops, accepted flows through.
- Add PR-mode skip-condition pre-check (closed/draft/trivial/already-reviewed).
  Single gh pr view probe. Standalone branch and base: modes unaffected.
- Add mode-aware demotion in Stage 5: testing/maintainability P2/P3 advisory
  findings route to testing_gaps/residual_risks in interactive/report-only,
  suppress in headless/autofix.
- Add lint-ignore suppression to false-positive catalog.
- Update 18 persona files from float bands to anchored language, preserving
  per-persona calibration signals.
- Update review-output-template.md to render anchors as integers.
- Contract tests cover all the above plus per-persona anchored-language
  assertions.

Plan: docs/plans/2026-04-21-002-refactor-ce-code-review-precision-and-validation-plan.md
Solutions doc extended: docs/solutions/skill-design/confidence-anchored-scoring-2026-04-21.md

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-21 18:36:19 -07:00
..