Add issue review

.claude/agents/code-review-agent.md

@@ -10,12 +10,14 @@ description: "Code Review Agent: 通过 Gitea API 获取 PR diff，分析代码
 ## 工作方式
 
 1. 读取提供的 PR diff 文件（路径在 prompt 中）
-2. **（如提供）读取全局影响报告，了解变更的影响范围**
+2. **（如提供）读取关联 Issue 文件，了解原始需求/缺陷描述**
-3. 逐文件分析代码变更
+3. **（如提供）读取全局影响报告，了解变更的影响范围**
-4. **使用搜索工具（Grep）追踪变更函数/类的调用方，验证接口兼容性**
+4. 逐文件分析代码变更
-5. **检查相关测试文件是否覆盖了变更逻辑**
+5. **使用搜索工具（Grep）追踪变更函数/类的调用方，验证接口兼容性**
-6. 识别问题，按严重程度分类
+6. **检查相关测试文件是否覆盖了变更逻辑**
-7. 输出结构化 JSON 供 CI 脚本解析并发布到 Gitea
+7. **对比 Issue 验收条件，验证改动是否完整满足需求**
+8. 识别问题，按严重程度分类
+9. 输出结构化 JSON 供 CI 脚本解析并发布到 Gitea
 
 ## 审查标准
 
@@ -26,6 +28,8 @@ description: "Code Review Agent: 通过 Gitea API 获取 PR diff，分析代码
 - 功能缺陷：明显与 PR 描述不符的实现
 - **接口兼容性破坏：函数签名变更导致已有调用方编译/运行失败**
 - **行为语义变更：返回值、异常、副作用的行为变化影响依赖方**
+- **业务不符：改动未满足关联 Issue 的需求描述**
+- **遗漏场景：Issue 中描述的边界情况或验收条件未被代码覆盖**
 
 ### 中等（建议修复）
 - 错误处理不完整、异常被吞没

scripts/gitea_api.py

@@ -0,0 +1,180 @@
+"""Gitea API helpers for the code-review-agent.
+
+Fetches PR data (metadata, diff, files), linked issues, and posts reviews.
+"""
+
+import json
+import re
+import sys
+import urllib.error
+import urllib.request
+
+
+# ── Low-level helper ────────────────────────────────────────────────────
+
+def _api_req(gitea_url, api_token, method, path, body=None):
+    """Send a Gitea API request, return parsed JSON or raw bytes."""
+    url = f"{gitea_url}/api/v1/repos{path}"
+    data = json.dumps(body).encode("utf-8") if body else None
+    req = urllib.request.Request(url, method=method, data=data)
+    req.add_header("Authorization", f"token {api_token}")
+    if data:
+        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:
+        err_body = e.read().decode(errors="replace")
+        print(f"API Error {e.code} on {method} {path}: {err_body}", file=sys.stderr)
+        sys.exit(1)
+
+
+# ── PR endpoints ────────────────────────────────────────────────────────
+
+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 post_review(gitea_url, api_token, target_repo, pr_num, review):
+    """Post a PR review to Gitea."""
+    comments = review.get("comments", [])
+    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 = {
+        "body": review["body"],
+        "event": review.get("event", "COMMENT"),
+    }
+    if gitea_comments:
+        payload["comments"] = gitea_comments
+
+    _api_req(gitea_url, api_token, "POST",
+             f"/{target_repo}/pulls/{pr_num}/reviews", body=payload)
+    print(f"Review posted to PR #{pr_num}")
+
+
+# ── Issue endpoints ─────────────────────────────────────────────────────
+
+_ISSUE_REF_RE = re.compile(
+    r"(?:fixe?s?|close?s?|resolve?s?|refs?|see)\s+"
+    r"((?:[\w.-]+/[\w.-]+)?#\d+)",
+    re.IGNORECASE,
+)
+_BARE_ISSUE_RE = re.compile(r"(?:^|\s)(#\d+)")
+
+
+def _extract_issue_refs(pr_body):
+    """Extract issue references from PR description.
+
+    Returns list of ``(owner, repo, issue_num)`` tuples.
+    ``owner/repo`` is ``None`` when using shorthand ``#123``.
+    """
+    refs = []
+    for m in _ISSUE_REF_RE.finditer(pr_body):
+        ref = m.group(1)
+        match = re.match(r"(?:([\w.-]+)/([\w.-]+))?#(\d+)", ref)
+        if match:
+            refs.append((match.group(1), match.group(2), int(match.group(3))))
+
+    # Add bare #123 refs not already captured
+    for m in _BARE_ISSUE_RE.finditer(pr_body):
+        num = int(m.group(1)[1:])
+        if not any(r[2] == num for r in refs):
+            refs.append((None, None, num))
+
+    return refs
+
+
+def fetch_issue(gitea_url, api_token, target_repo, issue_num):
+    """Fetch a single issue from Gitea.
+
+    Returns dict with keys: number, title, body, state, labels, html_url.
+    """
+    data = _api_req(gitea_url, api_token, "GET",
+                    f"/{target_repo}/issues/{issue_num}")
+    return {
+        "number": data["number"],
+        "title": data["title"],
+        "body": data.get("body", ""),
+        "state": data.get("state", "open"),
+        "labels": [lb["name"] for lb in data.get("labels", [])],
+        "html_url": data.get("html_url", ""),
+    }
+
+
+def fetch_linked_issues(gitea_url, api_token, target_repo, pr_body):
+    """Extract issue refs from PR body and fetch each issue.
+
+    Returns list of issue dicts (see ``fetch_issue``).
+    """
+    refs = _extract_issue_refs(pr_body)
+    issues = []
+    for owner, repo, num in refs:
+        if owner and repo:
+            repo_path = f"{owner}/{repo}"
+        else:
+            repo_path = target_repo
+        try:
+            issues.append(fetch_issue(gitea_url, api_token, repo_path, num))
+        except SystemExit:
+            # issue fetch failed (404, etc.) — skip and continue
+            print(f"[gitea] Warning: could not fetch issue #{num}, skipping",
+                  file=sys.stderr)
+    return issues
+
+
+def format_issues_markdown(issues):
+    """Format a list of issue dicts as a Markdown string."""
+    if not issues:
+        return ""
+    parts = ["# Linked Issues\n"]
+    for iss in issues:
+        labels = ", ".join(iss["labels"]) if iss["labels"] else "none"
+        parts.append(
+            f"## #{iss['number']}: {iss['title']}\n"
+            f"- **State**: {iss['state']}\n"
+            f"- **Labels**: {labels}\n"
+            f"\n{iss['body']}\n"
+        )
+    return "\n".join(parts)

scripts/review_pr.py

@@ -21,9 +21,8 @@ import subprocess
 import sys
 import threading
 import time
-import urllib.error
-import urllib.request
 
+import gitea_api
 from monitor_session import SessionMonitor
 
 MAX_DIFF_CHARS = 200_000  # ~50k words, safe for Claude context
@@ -101,60 +100,6 @@ def _check_claude():
     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 = []
@@ -279,7 +224,8 @@ def _strip_frontmatter(md_text):
     return md_text
 
 
-def build_prompt(meta, files, diff_path, agent_md, impact_report_path=None):
+def build_prompt(meta, files, diff_path, agent_md, impact_report_path=None,
+                 issue_context_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)
@@ -297,6 +243,13 @@ def build_prompt(meta, files, diff_path, agent_md, impact_report_path=None):
         f"Read that file to see every line changed.\n\n"
     )
 
+    if issue_context_path:
+        prompt += (
+            f"Linked issue(s) saved to: {issue_context_path}\n"
+            f"Read that file to see the original requirements / bug report.\n"
+            f"Verify that the code changes address the issue requirements completely.\n\n"
+        )
+
     if impact_report_path:
         prompt += (
             f"A global impact report has been saved to: {impact_report_path}\n"
@@ -312,8 +265,9 @@ def build_prompt(meta, files, diff_path, agent_md, impact_report_path=None):
         )
 
     prompt += (
-        f"Analyze the diff thoroughly. Focus on: security, correctness, "
+        f"Analyze the diff thoroughly. Focus on: business correctness (vs linked "
-        f"error handling, performance, and code quality — in that order.\n\n"
+        f"issues), security, correctness, error handling, performance, "
+        f"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."
     )
@@ -447,45 +401,6 @@ def validate_review(review):
     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"
@@ -517,12 +432,17 @@ def main():
 
     # ── 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)
+    meta = gitea_api.fetch_pr_metadata(args.gitea_url, args.api_token, args.target_repo, args.pr)
     print(f"  Title: {meta['title']}")
 
+    # ── 1b. Fetch linked issues ───────────────────────────────────────────
+    issues = gitea_api.fetch_linked_issues(
+        args.gitea_url, args.api_token, args.target_repo, meta.get("body", ""))
+    print(f"  {len(issues)} linked issue(s) found")
+
     # ── 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)
+    files = gitea_api.fetch_pr_files(args.gitea_url, args.api_token, args.target_repo, args.pr)
     print(f"  {len(files)} file(s) changed")
 
     if not files:
@@ -531,7 +451,7 @@ def main():
 
     # ── 3. Fetch diff ────────────────────────────────────────────────────
     print("[review_pr] Fetching diff...")
-    diff_text = fetch_pr_diff(args.gitea_url, args.api_token, args.target_repo, args.pr)
+    diff_text = gitea_api.fetch_pr_diff(args.gitea_url, args.api_token, args.target_repo, args.pr)
 
     if not diff_text.strip():
         print("Empty diff — skipping review.")
@@ -575,11 +495,21 @@ def main():
     else:
         print("[review_pr] No --repo-dir provided — skipping global impact analysis")
 
+    # ── 4c. Write linked issues to file ──────────────────────────────────
+    issue_context_path = None
+    if issues:
+        issue_md = gitea_api.format_issues_markdown(issues)
+        issue_context_path = os.path.join(diff_dir, f"{prefix}_issue.md")
+        with open(issue_context_path, "w", encoding="utf-8") as f:
+            f.write(issue_md)
+        print(f"  Issues saved to: {issue_context_path}")
+
     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)
+        prompt = build_prompt(meta, files, diff_path, agent_md,
+                             impact_report_path, issue_context_path)
         print("[review_pr] Invoking Claude for analysis...")
 
         mon = SessionMonitor(project_root)
@@ -596,7 +526,7 @@ def main():
 
         # ── 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)
+        gitea_api.post_review(args.gitea_url, args.api_token, args.target_repo, args.pr, review)
 
         print("[review_pr] Done.")
     finally:
@@ -609,6 +539,8 @@ def main():
             os.unlink(prompt_file)
         if impact_report_path and os.path.exists(impact_report_path):
             os.unlink(impact_report_path)
+        if issue_context_path and os.path.exists(issue_context_path):
+            os.unlink(issue_context_path)
 
 
 if __name__ == "__main__":