dev
84ae9b817e
Adds the unified-review integration that fuses CRG graph context with the ai-code-review scoring methodology and gstack-review fix-first workflow: - scoring.py: objective Layer-2 metrics (sql_risk, exception_coverage, redundancy_rate, high_risk_density, vulnerability_risk) with good/warn/fail grades, plus dedupe_findings (fingerprint merge, multi-source confidence boost, PR quality score) and report data builder - tools/scoring_tools.py + main.py: three new MCP tools (score_review_tool, dedupe_findings_tool, generate_report_tool) - assets/report-template.html: self-contained HTML report template - skills.py + skills/unified-review/: new read-only unified-review skill with language/manual-review/specialist checklists - docs and CHANGELOG updated; tests added (test_scoring, test_report, test_unified_review) and test_skills updated for 5 skills
1.2 KiB
1.2 KiB
Unified Review — Common Mistakes
- Skipping graph context — always run
get_minimal_contextfirst; CRG context is what makes the review token-efficient and blast-radius aware. - Rushing to fix — this skill is READ-ONLY. Present findings, wait for user decision. Never apply fixes, commit, or push.
- Ignoring tier — read
.code-review.yaml.fastskips Layer 2/3;strictrequires per-item confirmation for every blocker/major. - Judging metrics without evidence —
score_review_tooloutputs are heuristics. Cite the evidence, and let the LLM confirm SQL/exception/vuln findings before presenting them as facts. - Missing manual-review modules — payment, order, inventory, permission, distributed-lock, data-migration always require a manual review checklist.
- Forgetting enum completeness reads OUTSIDE the diff — grep sibling values, then read each consumer; in-diff review alone is insufficient.
- Batch-skipping blockers — 🔴 blockers cannot be batch-skipped; each needs an explicit user decision.
- Not producing the report — always call
generate_report_toolat the end and present the text report inline.