feat: add unified-review workflow (scoring tools + skill)

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
This commit is contained in:
dev
2026-08-05 13:31:55 +08:00
parent 82b7c6dc9e
commit 84ae9b817e
32 changed files with 2229 additions and 19 deletions
+17 -10
View File
@@ -27,6 +27,8 @@
│ │ ├── Communities: list, get, architecture │ │
│ │ ├── Analysis: detect_changes, refactor, │ │
│ │ │ apply_refactor, hotspots, gaps │ │
│ │ ├── Scoring: score_review, dedupe_ │ │
│ │ │ findings, generate_report │ │
│ │ ├── Wiki: generate, get_page │ │
│ │ └── Multi-repo: list_repos, cross_search │ │
│ └────────────────┬───────────────────────────┘ │
@@ -34,16 +36,21 @@
┌───────────┼───────────────┐
▼ ▼ ▼
┌─────────┐ ┌─────────┐ ┌─────────────┐
│ Parser │ │ Graph │ │ Incremental │
│ │ │ Store │ │ Engine │
└────┬────┘ └────┬────┘ └──────┬──────┘
│ │ │
▼ ▼ ▼
Tree-sitter SQLite DB git/svn diff
grammars (.code-review- subprocess
graph/
graph.db)
┌─────────┐ ┌─────────┐ ┌─────────────┐
│ Parser │ │ Graph │ │ Incremental │
│ │ │ Store │ │ Engine │
└────┬────┘ └────┬────┘ └──────┬──────┘
│ │ │
▼ ▼ ▼
Tree-sitter SQLite DB git/svn diff
grammars (.code-review- subprocess
graph/
graph.db)
Scoring module (code_review_graph/scoring.py) sits on top of the
GraphStore and reads changed files + git history to compute the
objective review metrics consumed by the unified-review skill and the
score_review / dedupe_findings / generate_report MCP tools.
```
## Data Flow