src/api/toolchain_routes.py

@@ -557,19 +557,51 @@ async def _handle_pr_closed(payload: Dict[str, Any]) -> None:
 
         if needs_restart:
             post_deploy_cmds = target.get("post_deploy", [])
+            pm2_name = target.get("pm2_name", "")
             for cmd in post_deploy_cmds:
                 logger.info("Auto-deploy: executing post_deploy: %s", cmd)
-                deploy_proc = await asyncio.create_subprocess_exec(
-                    "sh", "-c", cmd,
-                    stdout=asyncio.subprocess.PIPE,
-                    stderr=asyncio.subprocess.PIPE,
-                )
-                _, deploy_err = await asyncio.wait_for(deploy_proc.communicate(), timeout=30)
 
-                if deploy_proc.returncode != 0:
-                    logger.error("Auto-deploy: post_deploy failed: %s", deploy_err.decode())
-                    _send_deploy_failure_mail(repo, pr_number, pr_title, f"post_deploy 失败 ({cmd}): {deploy_err.decode()}")
-                    break
+                # M2: 检测当前进程是否会被此命令杀掉（而非脆弱的字符串匹配）
+                # 通过 PM2 环境变量判断：pm2 启动的进程有 PM2_HOME
+                self_restart = False
+                if pm2_name and os.environ.get("PM2_HOME") and "pm2 restart" in cmd:
+                    # 检查命令是否包含当前进程名
+                    import re
+                    if re.search(rf'pm2\s+restart\s+{re.escape(pm2_name)}', cmd):
+                        self_restart = True
+
+                if self_restart:
+                    # M1: 用 asyncio.sleep 延迟而非 nohup，保留子进程输出和错误检测
+                    # 先 sleep 让 handler 正常返回，再启动 restart 命令
+                    # restart 的子进程会在父进程死后被 pm2 新进程接管
+                    logger.info("Auto-deploy: self-restart detected, deferring 2s: %s", cmd)
+                    await asyncio.sleep(2)
+                    deploy_proc = await asyncio.create_subprocess_exec(
+                        "sh", "-c", cmd,
+                        stdout=asyncio.subprocess.PIPE,
+                        stderr=asyncio.subprocess.PIPE,
+                    )
+                    # restart 会杀掉当前进程，communicate 可能不会完成
+                    # 但我们至少尝试读取输出
+                    try:
+                        _, deploy_err = await asyncio.wait_for(
+                            deploy_proc.communicate(), timeout=10)
+                    except (asyncio.TimeoutError, ProcessLookupError):
+                        # 预期行为：进程被 pm2 restart 杀掉
+                        logger.info("Auto-deploy: process killed by self-restart (expected)")
+                        break
+                else:
+                    deploy_proc = await asyncio.create_subprocess_exec(
+                        "sh", "-c", cmd,
+                        stdout=asyncio.subprocess.PIPE,
+                        stderr=asyncio.subprocess.PIPE,
+                    )
+                    _, deploy_err = await asyncio.wait_for(deploy_proc.communicate(), timeout=30)
+
+                    if deploy_proc.returncode != 0:
+                        logger.error("Auto-deploy: post_deploy failed: %s", deploy_err.decode())
+                        _send_deploy_failure_mail(repo, pr_number, pr_title, f"post_deploy 失败 ({cmd}): {deploy_err.decode()}")
+                        break
             else:
                 logger.info("Auto-deploy: all post_deploy commands succeeded (files: %s)", ", ".join(file_list[:5]))
         else: