75d5ca5875
* feat(code-review): add optional fallow structural pre-pass * fix(ci): sync lockfile for fallow optional binaries * fix(test): make fallow integration tests cross-platform * fix(review): require executable fallow binary paths * docs(review): clarify structural findings usage and size guard * fix(fallow): preserve line:0, prefer node_modules/.bin, sync SDK twin (H1, M2, N1 from #3424 review) * fix(workflow): harden fallow pre-pass — exit check, timeout, atomic write, size-guard order (B1, H2-H4, M1, M3 from #3424 review) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(deps): pin fallow floor to ^2.70.0 matching lockfile (H7 from #3424 review) * fix(config): enum-validate fallow.scope/profile + group code_quality.* contiguously (H5, N3 from #3424 review) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs(fallow): label mcp gate reserved, version-pin install, expand context schema (B3, H8, M4, M8, L1 from #3424 review) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * test(fallow): replace source-grep with behavioral tests, expand fixtures, fail-loud tmpdir (B4, H6, L2, L3, M5, M6, N2 from #3424 review) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(workflow): escape closing structural_findings tag in JSON payload (CR #3424 inline finding) --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
1.3 KiB
1.3 KiB
Review Context Profile
Agent output guidance for review mode. Loaded when context: review is set in config.json.
Output Style
- Critical, detail-focused responses that prioritize correctness
- Organize findings by severity: blocking, important, nit
- Reference specific lines and files for every finding
- State what is correct as well as what needs change — confirm the good parts
Focus Areas
- Correctness — logic errors, off-by-ones, missing edge cases
- Security — input validation, injection vectors, secret exposure
- Performance — unnecessary allocations, O(n^2) patterns, missing caching
- Style and consistency — naming, formatting, import order
- Test coverage — untested branches, missing assertions, flaky patterns
- Structural Findings (fallow) — machine-derived cross-module facts injected as
<structural_findings>{ findings: [...], summary: { total, unusedExports, duplicates, circularDependencies } }</structural_findings>. Render in REVIEW.md under## Structural Findings (fallow)as a separate section from narrative findings. Treat as ground truth for cross-module facts; do not re-derive.
Verbosity
Medium. Be thorough on findings but terse in explanation. Each issue should be one to three sentences: what is wrong, why it matters, and how to fix it.