initial

scripts/review_pr.py

@@ -0,0 +1,400 @@
+"""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 shutil
+import subprocess
+import sys
+import tempfile
+import urllib.error
+import urllib.request
+
+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 build_prompt(meta, files, diff_path):
+    """Build the prompt string for Claude."""
+    files_summary = format_files_summary(files)
+    total_additions = sum(f["additions"] for f in files)
+    total_deletions = sum(f["deletions"] for f in files)
+
+    return (
+        f"You are reviewing 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"
+        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."
+    )
+
+
+def run_claude(claude_bin, agent_path, project_root, prompt):
+    """Run claude -p with the agent definition, return stdout."""
+    cmd = [
+        claude_bin, "-p",
+        "--agent", agent_path,
+        "--permission-mode", "acceptEdits",
+        prompt,
+    ]
+    print(f"[review_pr] Running: {' '.join(cmd[:4])} ...", file=sys.stderr)
+    proc = subprocess.Popen(
+        cmd,
+        cwd=project_root,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        text=True,
+        encoding="utf-8",
+    )
+    stdout_lines = []
+    for line in proc.stdout:
+        line = line.rstrip("\n")
+        stdout_lines.append(line)
+        if line:
+            print(f"[claude] {line}", file=sys.stderr)
+
+    proc.wait(timeout=600)
+    # Drain remaining stderr
+    stderr_output = proc.stderr.read()
+    if stderr_output:
+        print(stderr_output, file=sys.stderr)
+
+    if proc.returncode != 0:
+        print(f"Claude exited with code {proc.returncode}", file=sys.stderr)
+        sys.exit(1)
+    return "\n".join(stdout_lines)
+
+
+def extract_json_from_output(stdout):
+    """Extract the JSON block from Claude's output."""
+    # Try ```json ... ``` block first
+    match = re.search(r"```json\s*([\s\S]*?)\s*```", stdout)
+    if match:
+        return json.loads(match.group(1))
+
+    # Try bare JSON object
+    match = re.search(r'\{[\s\S]*"event"[\s\S]*\}', stdout)
+    if match:
+        return json.loads(match.group(0))
+
+    print("ERROR: Could not find JSON in Claude output:", file=sys.stderr)
+    print(stdout[:2000], file=sys.stderr)
+    sys.exit(1)
+
+
+def validate_review(review):
+    """Validate the review JSON structure."""
+    if not isinstance(review, dict):
+        print("ERROR: review is not a JSON object", 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("ERROR: review.body is required and must be a string", 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")
+    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)
+
+    # ── 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 to temp file ───────────────────────────────────────
+    tmp = tempfile.NamedTemporaryFile(
+        mode="w", suffix=".diff", prefix=f"pr{args.pr}_",
+        delete=False, encoding="utf-8",
+    )
+    tmp.write(diff_text)
+    tmp.close()
+    diff_path = tmp.name
+    print(f"  Diff saved to: {diff_path}")
+
+    try:
+        # ── 5. Build prompt & run Claude ─────────────────────────────────
+        prompt = build_prompt(meta, files, diff_path)
+        print("[review_pr] Invoking Claude for analysis...")
+        stdout = run_claude(claude_bin, agent_path, project_root, prompt)
+
+        # ── 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:
+        # Clean up temp file
+        if os.path.exists(diff_path):
+            os.unlink(diff_path)
+
+
+if __name__ == "__main__":
+    main()