From c6754d02331880c564f3ec514d764baae28d36cf Mon Sep 17 00:00:00 2001 From: host Date: Mon, 26 Oct 2026 11:01:52 +0800 Subject: [PATCH] monitor.sh: worker check accepts autoscaler (static worker retired) Since the autoscaler takeover (static codex-cloud-worker stopped at 2026-10-26 07:02:55, disabled by design), the monitor's worker check (systemctl is-active codex-cloud-worker) has failed every 5 minutes while the real workers were healthy (health worker_ok kept passing, GET /workers shows live autoscale-1 + host-1). A monitor that always fails masks real failures. Fix: pass if either codex-autoscaler or codex-cloud-worker is active, covering both deployment modes; the health check still covers worker heartbeat freshness. --- deploy/monitor.sh | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/deploy/monitor.sh b/deploy/monitor.sh index 68b1a5d..595406f 100755 --- a/deploy/monitor.sh +++ b/deploy/monitor.sh @@ -7,7 +7,10 @@ # # 检查项（全部不需要密码、不读 env 文件）： # server：systemctl is-active codex-cloud-server 为 active -# worker：systemctl is-active codex-cloud-worker 为 active +# worker：codex-autoscaler 或 codex-cloud-worker 任一为 active +# （autoscaler 接管后静态 worker 故意停用，只查静态会误报： +# 2026-10-26 07:02:55 静态 worker 停用后每 5 分钟 worker fail， +# 实际 worker 正常、health 的 worker_ok 也一直 pass） # health：curl health，要求 ok=true、backend=postgres、db_ok=true、 # worker_ok=true（worker 心跳 180 秒内，见 server.py） # postgres：pg_isready -h 127.0.0.1 -p 5432（只测就绪，不连库查数据， @@ -43,7 +46,8 @@ check_server() { } check_worker() { - if systemctl is-active codex-cloud-worker >/dev/null 2>&1; then + if systemctl is-active codex-autoscaler >/dev/null 2>&1 \ + || systemctl is-active codex-cloud-worker >/dev/null 2>&1; then echo pass else echo fail