Files
code-review-agent/scripts/review_pr.py
T
2026-06-11 17:48:38 +08:00

616 lines
23 KiB
Python

"""CI orchestrator for code-review-agent.
Fetches a PR diff from Gitea, runs Claude Code to analyze it,
and posts the review back to the Gitea PR.
Usage:
python scripts/review_pr.py \
--target-repo owner/repo \
--pr 42 \
--gitea-url https://gitea.example.com \
--api-token <token>
"""
import argparse
import json
import os
import re
import shlex
import shutil
import subprocess
import sys
import threading
import time
import urllib.error
import urllib.request
from monitor_session import SessionMonitor
MAX_DIFF_CHARS = 200_000 # ~50k words, safe for Claude context
def _find_claude():
"""Resolve the claude CLI binary path.
Checks (in order):
1. CLAUDE_BIN env var (explicit override)
2. ``claude`` on PATH
3. Common install locations (npm global, homebrew, etc.)
Returns the path string, or None.
"""
# 1. Explicit override
env_bin = os.environ.get("CLAUDE_BIN", "")
if env_bin:
if os.path.isfile(env_bin) and os.access(env_bin, os.X_OK):
return env_bin
print(f"WARNING: CLAUDE_BIN={env_bin} is not executable, falling back.",
file=sys.stderr)
# 2. On PATH
path_bin = shutil.which("claude")
if path_bin:
return path_bin
# 3. Common install locations
candidates = [
os.path.expanduser("~/.npm-global/bin/claude"),
"/usr/local/bin/claude",
"/usr/bin/claude",
"/home/linuxbrew/.linuxbrew/bin/claude",
]
# Also try npm global prefix
try:
result = subprocess.run(
["npm", "config", "get", "prefix"],
capture_output=True, text=True, timeout=5,
)
npm_prefix = result.stdout.strip()
if npm_prefix:
candidates.append(os.path.join(npm_prefix, "bin", "claude"))
except Exception:
pass
for candidate in candidates:
if os.path.isfile(candidate) and os.access(candidate, os.X_OK):
return candidate
return None
def _check_claude():
claude_bin = _find_claude()
if not claude_bin:
print(
"ERROR: claude CLI not found. Install Claude Code or set CLAUDE_BIN env var.",
file=sys.stderr,
)
sys.exit(1)
missing = []
for var in ("ANTHROPIC_BASE_URL", "ANTHROPIC_AUTH_TOKEN"):
if not os.environ.get(var):
missing.append(var)
if missing:
print(
f"ERROR: Required env vars not set: {', '.join(missing)}. "
f"Set them in the CI workflow or shell environment.",
file=sys.stderr,
)
sys.exit(1)
return claude_bin
def _api_req(gitea_url, api_token, method, path):
"""Send a Gitea API request, return parsed JSON or raw bytes."""
url = f"{gitea_url}/api/v1/repos{path}"
req = urllib.request.Request(url, method=method)
req.add_header("Authorization", f"token {api_token}")
req.add_header("Content-Type", "application/json")
try:
with urllib.request.urlopen(req) as resp:
raw = resp.read()
if not raw:
return {} if path.endswith("/merge") else None
content_type = resp.headers.get("Content-Type", "")
if "application/json" in content_type:
return json.loads(raw)
return raw # raw bytes for .diff endpoints
except urllib.error.HTTPError as e:
body = e.read().decode(errors="replace")
print(f"API Error {e.code} on {method} {path}: {body}", file=sys.stderr)
sys.exit(1)
def fetch_pr_metadata(gitea_url, api_token, target_repo, pr_num):
"""Fetch PR details: title, description, head SHA."""
pr = _api_req(gitea_url, api_token, "GET", f"/{target_repo}/pulls/{pr_num}")
return {
"number": pr["number"],
"title": pr["title"],
"body": pr.get("body", ""),
"head_sha": pr.get("head", {}).get("sha", ""),
"html_url": pr.get("html_url", ""),
}
def fetch_pr_diff(gitea_url, api_token, target_repo, pr_num):
"""Fetch raw unified diff for a PR."""
raw = _api_req(gitea_url, api_token, "GET", f"/{target_repo}/pulls/{pr_num}.diff")
return raw.decode("utf-8", errors="replace") if isinstance(raw, bytes) else ""
def fetch_pr_files(gitea_url, api_token, target_repo, pr_num):
"""Fetch changed file list with stats."""
files = _api_req(gitea_url, api_token, "GET", f"/{target_repo}/pulls/{pr_num}/files")
result = []
for f in files:
result.append({
"filename": f["filename"],
"status": f["status"],
"additions": f.get("additions", 0),
"deletions": f.get("deletions", 0),
})
return result
def format_files_summary(files):
"""Build a one-line-per-file summary for the Claude prompt."""
lines = []
for f in files:
lines.append(
f" {f['status']:7} {f['filename']} "
f"(+{f['additions']} -{f['deletions']})"
)
return "\n".join(lines)
def _extract_symbols(diff_text):
"""Extract changed function/class/method names from a unified diff."""
symbols = set()
# Match lines added by the PR: "+def name" or "+class name"
for m in re.finditer(r'^\+ *(?:async\s+)?def\s+(\w+)', diff_text, re.MULTILINE):
symbols.add(m.group(1))
for m in re.finditer(r'^\+ *class\s+(\w+)', diff_text, re.MULTILINE):
symbols.add(m.group(1))
return sorted(symbols)
def _build_impact_report(repo_dir, changed_files, symbols):
"""Generate an impact-analysis report for the changed code.
Uses ``git grep`` in *repo_dir* to find:
- files that import the changed modules
- call-sites of changed functions / classes
- related test files
"""
changed_modules = set()
for f in changed_files:
if f.endswith(".py"):
# Convert path like "skills/utils/LLM.py" → "skills.utils.LLM"
mod = f.replace("/", ".").replace(".py", "")
changed_modules.add(mod)
lines = ["# Global Impact Report\n"]
# ── Importers ──
if changed_modules:
lines.append("## Importers (files that import changed modules)\n")
for mod in sorted(changed_modules):
try:
result = subprocess.run(
["git", "grep", "-l", f"from {mod} import|import {mod}"],
cwd=repo_dir, capture_output=True, text=True, timeout=30,
)
found = [l.strip() for l in result.stdout.splitlines() if l.strip()]
# Exclude the changed file itself
found = [f for f in found if f not in changed_files]
if found:
lines.append(f"- `{mod}` — used by: {', '.join(f'`{f}`' for f in found[:10])}")
if len(found) > 10:
lines.append(f" *(and {len(found) - 10} more)*")
else:
lines.append(f"- `{mod}` — no external importers found")
except Exception:
pass
lines.append("")
# ── Callers ──
if symbols:
lines.append("## Callers (files that reference changed symbols)\n")
for sym in sorted(symbols):
try:
result = subprocess.run(
["git", "grep", "-l", f"\\b{sym}\\b"],
cwd=repo_dir, capture_output=True, text=True, timeout=30,
)
found = [l.strip() for l in result.stdout.splitlines() if l.strip()]
# Exclude the changed file itself
found = [f for f in found if f not in changed_files]
if found:
lines.append(f"- `{sym}()` — referenced in: {', '.join(f'`{f}`' for f in found[:10])}")
if len(found) > 10:
lines.append(f" *(and {len(found) - 10} more)*")
else:
lines.append(f"- `{sym}()` — no external callers found")
except Exception:
pass
lines.append("")
# ── Related tests ──
if changed_modules:
lines.append("## Related test files\n")
for mod in sorted(changed_modules):
# Try common test naming patterns
parts = mod.split(".")
test_patterns = [
f"test_{parts[-1]}.py",
f"{parts[-1]}_test.py",
]
for pat in test_patterns:
try:
result = subprocess.run(
["find", ".", "-name", pat, "-not", "-path", "*/.git/*"],
cwd=repo_dir, capture_output=True, text=True, timeout=15,
)
found = [l.strip() for l in result.stdout.splitlines() if l.strip()]
if found:
lines.append(f"- {', '.join(f'`{f}`' for f in found)}")
else:
lines.append(f"- `{mod}` — no test files found (pattern `{pat}`)")
except Exception:
pass
break # Only try first matching pattern
lines.append("")
if len(lines) == 2: # Only title + one blank line
lines.append("*(No importers, callers, or related tests found.)*\n")
return "\n".join(lines)
def _strip_frontmatter(md_text):
"""Remove YAML frontmatter (``--- ... ---``) from markdown text."""
if md_text.startswith("---\n"):
end = md_text.find("---\n", 4)
if end != -1:
return md_text[end + 4:].lstrip("\n")
return md_text
def build_prompt(meta, files, diff_path, agent_md, impact_report_path=None):
"""Build the prompt string for Claude, embedding the agent definition."""
files_summary = format_files_summary(files)
total_additions = sum(f["additions"] for f in files)
total_deletions = sum(f["deletions"] for f in files)
prompt = (
f"{_strip_frontmatter(agent_md)}\n\n"
f"---\n\n"
f"PR #{meta['number']} in repository.\n\n"
f"PR Title: {meta['title']}\n"
f"PR Description:\n{meta.get('body', '(no description)')}\n\n"
f"Changed Files ({len(files)} files, +{total_additions} -{total_deletions}):\n"
f"{files_summary}\n\n"
f"The complete diff has been saved to: {diff_path}\n"
f"Read that file to see every line changed.\n\n"
)
if impact_report_path:
prompt += (
f"A global impact report has been saved to: {impact_report_path}\n"
f"Read that file to see which files import, call, or test the changed code.\n"
f"You have access to the target repository. Use Grep and Glob tools to "
f"trace callers, check interface compatibility, and verify that the "
f"changes do not break existing dependents.\n\n"
)
else:
prompt += (
f"Note: no global impact report is available (--repo-dir not provided). "
f"Review the diff in isolation.\n\n"
)
prompt += (
f"Analyze the diff thoroughly. Focus on: security, correctness, "
f"error handling, performance, and code quality — in that order.\n\n"
f"Output your review as a single JSON object inside a ```json code block. "
f"Do NOT output anything else."
)
return prompt
def run_claude(claude_bin, project_root, prompt, extra_dir=None, prompt_file=None):
"""Run claude -p, return stdout. Prompt is fed via ``< file`` redirect."""
cmd = [claude_bin, "-p", "--permission-mode", "bypassPermissions"]
if extra_dir:
cmd += ["--add-dir", extra_dir]
# Write prompt to temp file, then feed via shell redirect to avoid arg-too-long
if not prompt_file:
prompt_file = os.path.join(project_root, ".reviews", "_prompt.txt")
os.makedirs(os.path.dirname(prompt_file), exist_ok=True)
with open(prompt_file, "w", encoding="utf-8") as f:
f.write(prompt)
shell_cmd = f"{shlex.join(cmd)} < {shlex.quote(prompt_file)}"
print(f"[review_pr] Command: {shell_cmd}", file=sys.stderr)
proc = subprocess.Popen(
shell_cmd,
cwd=project_root,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
text=True,
encoding="utf-8",
shell=True,
)
def _stream(pipe, prefix, dest_lines):
for line in pipe:
line = line.rstrip("\n")
dest_lines.append(line)
if line.strip():
print(f"[{prefix}] {line}", file=sys.stderr)
stdout_lines = []
stderr_lines = []
heartbeat_stop = threading.Event()
def _heartbeat(start):
while not heartbeat_stop.is_set():
heartbeat_stop.wait(30)
if not heartbeat_stop.is_set():
elapsed = int(time.time() - start)
print(f"[review_pr] ... still running ({elapsed}s elapsed)", file=sys.stderr)
t_beat = threading.Thread(target=_heartbeat, args=(time.time(),))
t_beat.start()
t_out = threading.Thread(target=_stream, args=(proc.stdout, "claude", stdout_lines))
t_err = threading.Thread(target=_stream, args=(proc.stderr, "claude:stderr", stderr_lines))
t_out.start()
t_err.start()
t_out.join(timeout=600)
heartbeat_stop.set()
t_err.join(timeout=10)
t_beat.join(timeout=5)
proc.wait(timeout=10)
if proc.returncode != 0:
print(f"Claude exited with code {proc.returncode}", file=sys.stderr)
if stderr_lines:
print("\n".join(stderr_lines[-50:]), file=sys.stderr)
sys.exit(1)
return "\n".join(stdout_lines)
def extract_json_from_output(stdout):
"""Extract the review JSON from Claude's output."""
match = re.search(r"```json\s*([\s\S]*)\s*```", stdout)
if not match:
print("ERROR: No ```json block found in Claude output.", file=sys.stderr)
print(stdout[-3000:], file=sys.stderr)
sys.exit(1)
try:
obj = json.loads(match.group(1))
except json.JSONDecodeError as e:
print(f"ERROR: Invalid JSON in Claude output: {e}", file=sys.stderr)
print(match.group(1)[:2000], file=sys.stderr)
sys.exit(1)
# Unwrap {review: {...}} envelope if present
if isinstance(obj, dict) and "review" in obj and isinstance(obj["review"], dict):
obj = obj["review"]
if not isinstance(obj, dict) or "body" not in obj:
print(f"ERROR: JSON missing required 'body' field. "
f"Keys: {list(obj.keys()) if isinstance(obj, dict) else type(obj).__name__}",
file=sys.stderr)
sys.exit(1)
return obj
def validate_review(review):
"""Validate the review JSON structure."""
if not isinstance(review, dict):
print(f"ERROR: review is not a JSON object, got {type(review).__name__}", file=sys.stderr)
print(f"Raw: {json.dumps(review, ensure_ascii=False)[:2000]}", file=sys.stderr)
sys.exit(1)
event = review.get("event", "")
if event not in ("APPROVED", "REQUEST_CHANGES", "COMMENT", ""):
print(f"ERROR: invalid event '{event}'", file=sys.stderr)
sys.exit(1)
body = review.get("body", "")
if not body or not isinstance(body, str):
print(f"ERROR: review.body is required and must be a string.", file=sys.stderr)
print(f"Got type: {type(body).__name__}, value: {json.dumps(body, ensure_ascii=False)[:500]}", file=sys.stderr)
print(f"Full review keys: {list(review.keys())}", file=sys.stderr)
sys.exit(1)
comments = review.get("comments", [])
if not isinstance(comments, list):
print("ERROR: review.comments must be an array", file=sys.stderr)
sys.exit(1)
for i, c in enumerate(comments):
if not isinstance(c, dict):
print(f"ERROR: comment[{i}] is not an object", file=sys.stderr)
sys.exit(1)
if "path" not in c or "body" not in c:
print(f"ERROR: comment[{i}] missing 'path' or 'body'", file=sys.stderr)
sys.exit(1)
return True
def post_review(gitea_url, api_token, target_repo, pr_num, review):
"""Post a PR review to Gitea."""
payload = {
"body": review["body"],
"event": review.get("event", "COMMENT"),
}
comments = review.get("comments", [])
if comments:
# Translate {line} -> {new_line} for Gitea API
gitea_comments = []
for c in comments:
gc = {
"path": c["path"],
"body": c["body"],
}
if c.get("line"):
gc["new_line"] = c["line"]
if c.get("old_line"):
gc["old_line"] = c["old_line"]
gitea_comments.append(gc)
payload["comments"] = gitea_comments
body = json.dumps(payload).encode("utf-8")
url = f"{gitea_url}/api/v1/repos/{target_repo}/pulls/{pr_num}/reviews"
req = urllib.request.Request(url, data=body, method="POST")
req.add_header("Authorization", f"token {api_token}")
req.add_header("Content-Type", "application/json")
try:
with urllib.request.urlopen(req) as resp:
result = json.loads(resp.read())
print(f"Review posted: {result.get('html_url', result.get('url', 'unknown'))}")
return result
except urllib.error.HTTPError as e:
err_body = e.read().decode(errors="replace")
print(f"Failed to post review: {e.code} - {err_body}", file=sys.stderr)
sys.exit(1)
def main():
parser = argparse.ArgumentParser(
description="Code Review Agent — fetch PR, analyze with Claude, post review"
)
parser.add_argument("--target-repo", required=True,
help="Target repository path (e.g. owner/repo)")
parser.add_argument("--pr", type=int, required=True,
help="PR number to review")
parser.add_argument("--gitea-url", required=True,
help="Gitea instance URL")
parser.add_argument("--api-token", required=True,
help="Gitea API token with read:repository + write:repository")
parser.add_argument("--repo-dir", default=None,
help="Path to local clone of the target repo (enables global impact analysis)")
args = parser.parse_args()
claude_bin = _check_claude()
project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
agent_path = os.path.join(project_root, ".claude", "agents", "code-review-agent.md")
if not os.path.exists(agent_path):
print(f"ERROR: agent definition not found at {agent_path}", file=sys.stderr)
sys.exit(1)
with open(agent_path, "r", encoding="utf-8") as f:
agent_md = f.read()
print(f"[review_pr] Loaded agent definition ({len(agent_md)} chars)")
# ── 1. Fetch PR metadata ─────────────────────────────────────────────
print(f"[review_pr] Fetching PR #{args.pr} metadata from {args.target_repo}...")
meta = fetch_pr_metadata(args.gitea_url, args.api_token, args.target_repo, args.pr)
print(f" Title: {meta['title']}")
# ── 2. Fetch changed files ───────────────────────────────────────────
print("[review_pr] Fetching changed files...")
files = fetch_pr_files(args.gitea_url, args.api_token, args.target_repo, args.pr)
print(f" {len(files)} file(s) changed")
if not files:
print("No files changed — skipping review.")
return
# ── 3. Fetch diff ────────────────────────────────────────────────────
print("[review_pr] Fetching diff...")
diff_text = fetch_pr_diff(args.gitea_url, args.api_token, args.target_repo, args.pr)
if not diff_text.strip():
print("Empty diff — skipping review.")
return
if len(diff_text) > MAX_DIFF_CHARS:
print(
f"Warning: diff is {len(diff_text)} chars "
f"(>{MAX_DIFF_CHARS}). Review may be incomplete.",
file=sys.stderr,
)
diff_text = diff_text[:MAX_DIFF_CHARS]
print(f" Diff: {len(diff_text)} chars, ~{diff_text.count(chr(10))} lines")
# ── 4. Write diff inside project_root so claude CLI can read it ─────
repo_slug = args.target_repo.replace("/", "_")
prefix = f"{repo_slug}_pr{args.pr}"
diff_dir = os.path.join(project_root, ".reviews")
os.makedirs(diff_dir, exist_ok=True)
diff_path = os.path.join(diff_dir, f"{prefix}.diff")
with open(diff_path, "w", encoding="utf-8") as f:
f.write(diff_text)
print(f" Diff saved to: {diff_path}")
# ── 4b. Build impact report (if repo-dir provided) ──────────────────
impact_report_path = None
repo_dir = args.repo_dir
if repo_dir:
if not os.path.isdir(repo_dir):
print(f"ERROR: --repo-dir is not a directory: {repo_dir}", file=sys.stderr)
sys.exit(1)
changed_file_names = [f["filename"] for f in files]
symbols = _extract_symbols(diff_text)
print(f"[review_pr] Extracted {len(symbols)} changed symbol(s): {', '.join(symbols) if symbols else '(none)'}")
report = _build_impact_report(repo_dir, changed_file_names, symbols)
impact_report_path = os.path.join(diff_dir, f"{prefix}_impact.md")
with open(impact_report_path, "w", encoding="utf-8") as f:
f.write(report)
print(f" Impact report saved to: {impact_report_path}")
else:
print("[review_pr] No --repo-dir provided — skipping global impact analysis")
mon = None
prompt_file = os.path.join(diff_dir, f"{prefix}_prompt.txt")
try:
# ── 5. Build prompt & run Claude ─────────────────────────────────
prompt = build_prompt(meta, files, diff_path, agent_md, impact_report_path)
print("[review_pr] Invoking Claude for analysis...")
mon = SessionMonitor(project_root)
mon.start()
stdout = run_claude(claude_bin, project_root, prompt, extra_dir=repo_dir, prompt_file=prompt_file)
mon.stop()
# ── 6. Parse Claude output ───────────────────────────────────────
review = extract_json_from_output(stdout)
validate_review(review)
print(f" Review event: {review.get('event', 'COMMENT')}")
print(f" Body length: {len(review['body'])} chars")
print(f" Inline comments: {len(review.get('comments', []))}")
# ── 7. Post review to Gitea ──────────────────────────────────────
print("[review_pr] Posting review to Gitea...")
post_review(args.gitea_url, args.api_token, args.target_repo, args.pr, review)
print("[review_pr] Done.")
finally:
if mon:
mon.stop()
# Clean up temp files
if os.path.exists(diff_path):
os.unlink(diff_path)
if os.path.exists(prompt_file):
os.unlink(prompt_file)
if impact_report_path and os.path.exists(impact_report_path):
os.unlink(impact_report_path)
if __name__ == "__main__":
main()