From d82d29fd7997d701678c81adbecd165cf7a2a68c Mon Sep 17 00:00:00 2001
From: cfdaily <cfdaily@gitee.com>
Date: Fri, 12 Jun 2026 15:05:06 +0800
Subject: [PATCH] fix(auto-deploy): prevent self-kill when pm2 restart runs
 inside webhook handler

post_deploy commands that restart the current process (pm2 restart {pm2_name})
now use nohup+sleep to defer execution, allowing the webhook handler to
return normally before the restart happens.

Fix by jiangwei-infra, synced from install dir.
---
 src/api/toolchain_routes.py | 36 +++++++++++++++++++++++++-----------
 1 file changed, 25 insertions(+), 11 deletions(-)

diff --git a/src/api/toolchain_routes.py b/src/api/toolchain_routes.py
index 1c266c8..9f62b57 100644
--- a/src/api/toolchain_routes.py
+++ b/src/api/toolchain_routes.py
@@ -557,21 +557,35 @@ 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
+                # 如果命令会 restart 当前进程（自己杀自己），用延迟执行
+                # 避免当前 webhook handler 被杀导致部署失败
+                if pm2_name and f"pm2 restart {pm2_name}" in cmd:
+                    actual_cmd = f"nohup sh -c 'sleep 2 && {cmd}' > /dev/null 2>&1 &"
+                    deploy_proc = await asyncio.create_subprocess_exec(
+                        "sh", "-c", actual_cmd,
+                        stdout=asyncio.subprocess.PIPE,
+                        stderr=asyncio.subprocess.PIPE,
+                    )
+                    # 不等待：nohup 后台执行，立即返回
+                    logger.info("Auto-deploy: self-restart deferred (nohup): %s", cmd)
+                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]))
+                logger.info("Auto-deploy: all post_deploy commands scheduled/succeeded (files: %s)", ", ".join(file_list[:5]))
         else:
             logger.info("Auto-deploy: docs-only change for %s, skip post_deploy", repo)