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
@@ -1,6 +1,6 @@
|
||||
"""MCP tool definitions for the Code Review Graph server.
|
||||
|
||||
Exposes 27 tools:
|
||||
Exposes 31 tools:
|
||||
1. build_or_update_graph - full or incremental build
|
||||
2. get_impact_radius - blast radius from changed files
|
||||
3. query_graph - predefined graph queries
|
||||
@@ -29,6 +29,9 @@ Exposes 27 tools:
|
||||
26. get_surprising_connections - find unexpected architectural coupling
|
||||
27. get_suggested_questions - auto-generated review questions from graph analysis
|
||||
28. traverse_graph - BFS/DFS traversal from best-matching node
|
||||
29. score_review - objective Layer-2 review metrics for changed files
|
||||
30. dedupe_findings - fingerprint dedup + confidence merge for findings
|
||||
31. generate_report - render the standalone HTML code review report
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -103,6 +106,13 @@ from .review import (
|
||||
get_review_context,
|
||||
)
|
||||
|
||||
# -- scoring (unified-review) ------------------------------------------------
|
||||
from .scoring_tools import (
|
||||
dedupe_findings_func,
|
||||
generate_report_func,
|
||||
score_review_func,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
# _common
|
||||
"_BUILTIN_CALL_NAMES",
|
||||
@@ -143,6 +153,10 @@ __all__ = [
|
||||
"detect_changes_func",
|
||||
"get_affected_flows_func",
|
||||
"get_review_context",
|
||||
# scoring (unified-review)
|
||||
"score_review_func",
|
||||
"dedupe_findings_func",
|
||||
"generate_report_func",
|
||||
# analysis_tools
|
||||
"get_bridge_nodes_func",
|
||||
"get_hub_nodes_func",
|
||||
|
||||
@@ -115,8 +115,8 @@ def get_docs_section(
|
||||
|
||||
Args:
|
||||
section_name: Exact section name. One of: usage, review-delta,
|
||||
review-pr, commands, legal, watch, embeddings,
|
||||
languages, troubleshooting.
|
||||
review-pr, unified-review, score-review, commands,
|
||||
legal, watch, embeddings, languages, troubleshooting.
|
||||
repo_root: Repository root path. Auto-detected from current
|
||||
directory if omitted.
|
||||
|
||||
@@ -177,8 +177,9 @@ def get_docs_section(
|
||||
}
|
||||
|
||||
available = [
|
||||
"usage", "review-delta", "review-pr", "commands",
|
||||
"legal", "watch", "embeddings", "languages", "troubleshooting",
|
||||
"usage", "review-delta", "review-pr", "unified-review",
|
||||
"score-review", "commands", "legal", "watch", "embeddings",
|
||||
"languages", "troubleshooting",
|
||||
]
|
||||
return {
|
||||
"status": "not_found",
|
||||
|
||||
@@ -0,0 +1,269 @@
|
||||
"""MCP tool wrappers for the unified-review scoring workflow.
|
||||
|
||||
Wraps :mod:`code_review_graph.scoring` (score_review / dedupe_findings /
|
||||
build_report_data) into the three MCP tools consumed by the
|
||||
``unified-review`` skill:
|
||||
|
||||
* ``score_review_tool`` - objective Layer-2 metrics for changed files
|
||||
* ``dedupe_findings_tool`` - fingerprint dedup + confidence merge
|
||||
* ``generate_report_tool`` - render ``code-review-report.html``
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from ..incremental import get_changed_files, get_staged_and_unstaged
|
||||
from ..scoring import build_report_data, dedupe_findings, score_review
|
||||
from ._common import _get_store, _error_response
|
||||
|
||||
try:
|
||||
from importlib.resources import files as _pkg_files # Python 3.9+
|
||||
|
||||
_HAS_IMPORTLIB_RESOURCES = True
|
||||
except ImportError: # pragma: no cover
|
||||
_HAS_IMPORTLIB_RESOURCES = False
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tool: score_review
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def score_review_func(
|
||||
changed_files: list[str] | None = None,
|
||||
base: str = "HEAD~1",
|
||||
include_churn: bool = True,
|
||||
repo_root: str | None = None,
|
||||
detail_level: str = "standard",
|
||||
) -> dict[str, Any]:
|
||||
"""Compute objective Layer-2 review metrics for changed files.
|
||||
|
||||
Runs the git-history / graph risk factors plus the heuristic metrics
|
||||
(SQL risk, exception coverage, redundancy, high-risk density,
|
||||
vulnerability). LLM-judged metrics are listed in ``llm_judged`` so the
|
||||
calling agent knows what still needs judgement.
|
||||
|
||||
Args:
|
||||
changed_files: Files to score (auto-detected from git diff if
|
||||
omitted).
|
||||
base: Git ref to diff against (default: HEAD~1).
|
||||
include_churn: Include git-churn risk factors (default: True).
|
||||
repo_root: Repository root. Auto-detected if omitted.
|
||||
detail_level: Output detail level. ``minimal`` returns only grades
|
||||
and values; ``standard`` includes evidence.
|
||||
"""
|
||||
store, root = _get_store(repo_root)
|
||||
try:
|
||||
if changed_files is None:
|
||||
changed_files = get_changed_files(root, base)
|
||||
if not changed_files:
|
||||
changed_files = get_staged_and_unstaged(root)
|
||||
if not changed_files:
|
||||
return {
|
||||
"status": "ok",
|
||||
"summary": "No changed files detected. Nothing to score.",
|
||||
"metrics": {},
|
||||
"objective_grade": "good",
|
||||
}
|
||||
|
||||
result = score_review(
|
||||
store,
|
||||
root,
|
||||
changed_files,
|
||||
include_churn=include_churn,
|
||||
)
|
||||
|
||||
if detail_level == "minimal":
|
||||
return {
|
||||
"status": "ok",
|
||||
"summary": result["summary"],
|
||||
"objective_grade": result["objective_grade"],
|
||||
"metrics": {
|
||||
name: {"value": m["value"], "grade": m["grade"]}
|
||||
for name, m in result["metrics"].items()
|
||||
},
|
||||
"llm_judged": result["llm_judged"],
|
||||
}
|
||||
|
||||
result["changed_files"] = changed_files
|
||||
result["next_tool_suggestions"] = [
|
||||
"dedupe_findings -- merge specialist findings",
|
||||
"detect_changes -- risk-scored impact analysis",
|
||||
"generate_report -- export HTML report",
|
||||
]
|
||||
return result
|
||||
except Exception as exc:
|
||||
return _error_response(str(exc))
|
||||
finally:
|
||||
store.close()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tool: dedupe_findings
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def dedupe_findings_func(
|
||||
findings: list[dict[str, Any]],
|
||||
suppress_prior: list[dict[str, Any]] | None = None,
|
||||
repo_root: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Merge review findings by fingerprint and boost multi-source confidence.
|
||||
|
||||
Mirrors the gstack-review "collect and merge" step: findings with the
|
||||
same ``path:line:category`` fingerprint are merged (highest confidence
|
||||
wins); findings confirmed by more than one source get confidence +1
|
||||
(cap 10). Confidence gates route low-confidence findings to the
|
||||
appendix or suppress them, and a PR quality score is computed as
|
||||
``max(0, 10 - (critical*2 + informational*0.5))``.
|
||||
|
||||
Args:
|
||||
findings: Raw finding dicts with ``path``, ``category``,
|
||||
``severity``, ``confidence`` and optional ``source``/``line``.
|
||||
suppress_prior: Previously user-skipped findings (from a prior
|
||||
review-log) to suppress when their file has not changed.
|
||||
repo_root: Repository root (used to resolve changed files when
|
||||
suppressing prior findings).
|
||||
"""
|
||||
try:
|
||||
suppressed_prior_list: list[dict[str, Any]] = []
|
||||
if suppress_prior:
|
||||
for f in suppress_prior:
|
||||
suppressed_prior_list.append(f)
|
||||
result = dedupe_findings(findings, suppressed_prior_list)
|
||||
result["next_tool_suggestions"] = [
|
||||
"generate_report -- export HTML report",
|
||||
"detect_changes -- risk-scored impact analysis",
|
||||
]
|
||||
return result
|
||||
except Exception as exc:
|
||||
return _error_response(str(exc))
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tool: generate_report
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def _load_report_template() -> str:
|
||||
"""Load ``report-template.html`` from the installed package assets.
|
||||
|
||||
Falls back to the bundled template string when the asset cannot be
|
||||
loaded, so the tool never fails solely because the package data is
|
||||
missing.
|
||||
"""
|
||||
if _HAS_IMPORTLIB_RESOURCES:
|
||||
try:
|
||||
data = _pkg_files("code_review_graph").joinpath(
|
||||
"assets/report-template.html"
|
||||
).read_text(encoding="utf-8")
|
||||
if data:
|
||||
return data
|
||||
except (FileNotFoundError, OSError):
|
||||
pass
|
||||
return _FALLBACK_TEMPLATE
|
||||
|
||||
|
||||
# Minimal self-contained template (used if the asset file is unavailable).
|
||||
_FALLBACK_TEMPLATE = """<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<title>Code Review Report</title>
|
||||
<style>
|
||||
body{font-family:-apple-system,Segoe UI,Roboto,Helvetica,Arial,sans-serif;
|
||||
margin:2rem auto;max-width:900px;color:#1f2328;line-height:1.5}
|
||||
h1{font-size:1.5rem} .verdict{font-weight:700}
|
||||
.pass{color:#1a7f37}.fail{color:#cf222e}
|
||||
table{border-collapse:collapse;width:100%;margin:1rem 0}
|
||||
th,td{border:1px solid #d0d7de;padding:.4rem .6rem;text-align:left;font-size:.9rem}
|
||||
th{background:#f6f8fa}
|
||||
.good{color:#1a7f37}.warn{color:#bf8700}.fail{color:#cf222e}.na{color:#57606a}
|
||||
.issue{margin:.5rem 0;padding:.6rem;border-radius:6px;background:#f6f8fa}
|
||||
.tag{font-weight:700;margin-right:.4rem}
|
||||
.location{color:#57606a;font-size:.85rem}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<div id="report"></div>
|
||||
<script>
|
||||
const data = {{REPORT_DATA}};
|
||||
const el = document.getElementById("report");
|
||||
let html = `<h1>Code Review Report</h1>
|
||||
<p><span class="verdict ${data.verdictClass || "fail"}">${data.verdict || "NO VERDICT"}</span>
|
||||
· Tier: ${data.tier || "standard"} · Scope: ${data.scope || "change-level"}</p>`;
|
||||
if (data.files) html += `<p><b>Files:</b> ${data.files}</p>`;
|
||||
if (data.summary) html += `<p>${data.summary}</p>`;
|
||||
html += `<h2>Objective Metrics</h2><table><tr><th>Metric</th><th>Value</th><th>Grade</th></tr>`;
|
||||
for (const [k, m] of Object.entries(data.metrics || {})) {
|
||||
html += `<tr><td>${k}</td><td>${m.value ?? "N/A"}</td>
|
||||
<td class="${m.grade || "na"}">${m.grade || "N/A"}</td></tr>`;
|
||||
}
|
||||
html += `</table>`;
|
||||
html += `<h2>Issues (${(data.issues || []).length})</h2>`;
|
||||
for (const i of data.issues || []) {
|
||||
html += `<div class="issue"><span class="tag ${i.severity}">${i.severity}</span>
|
||||
<span>${i.message || ""}</span>
|
||||
<div class="location">${i.location || ""}</div></div>`;
|
||||
}
|
||||
if (data.llm_judged && data.llm_judged.length) {
|
||||
html += `<p><b>LLM-judged:</b> ${data.llm_judged.join(", ")}</p>`;
|
||||
}
|
||||
el.innerHTML = html;
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
"""
|
||||
|
||||
|
||||
def generate_report_func(
|
||||
review_data: dict[str, Any],
|
||||
output_path: str | None = None,
|
||||
repo_root: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Generate a self-contained HTML code review report.
|
||||
|
||||
Injects ``review_data`` (the output of ``score_review_tool`` plus
|
||||
``dedupe_findings_tool`` results and free-form verdict/tier/scope) into
|
||||
the bundled ``report-template.html`` as ``{{REPORT_DATA}}`` and writes
|
||||
the standalone file (default ``repo_root/code-review-report.html``).
|
||||
|
||||
Args:
|
||||
review_data: Review data dict (metrics, findings, verdict, tier,
|
||||
scope, files, baseline, timestamp, manual_review).
|
||||
output_path: Output file path. Defaults to
|
||||
``<repo_root>/code-review-report.html``.
|
||||
repo_root: Repository root. Auto-detected if omitted.
|
||||
"""
|
||||
store, root = _get_store(repo_root)
|
||||
try:
|
||||
data = build_report_data(review_data)
|
||||
data["summary"] = review_data.get("summary", "")
|
||||
|
||||
template = _load_report_template()
|
||||
rendered = template.replace(
|
||||
"{{REPORT_DATA}}", json.dumps(data, ensure_ascii=False)
|
||||
)
|
||||
|
||||
if output_path:
|
||||
out = Path(output_path)
|
||||
if not out.is_absolute():
|
||||
out = root / out
|
||||
else:
|
||||
out = root / "code-review-report.html"
|
||||
|
||||
out.parent.mkdir(parents=True, exist_ok=True)
|
||||
out.write_text(rendered, encoding="utf-8")
|
||||
return {
|
||||
"status": "ok",
|
||||
"summary": f"Report written to {out}",
|
||||
"output_path": str(out),
|
||||
"report_size_bytes": len(rendered),
|
||||
}
|
||||
except Exception as exc:
|
||||
return _error_response(str(exc))
|
||||
finally:
|
||||
store.close()
|
||||
Reference in New Issue
Block a user