ops: add production observability and recovery

2026-07-27 19:06:34 +08:00
parent e69368a2f3
commit b02d18d3b9
33 changed files with 8832 additions and 1 deletions
--- a/infra/monitoring/alertmanager.yml
+++ b/infra/monitoring/alertmanager.yml
@@ -0,0 +1,14 @@
+route:
+  receiver: operations-webhook
+  group_by:
+    - alertname
+    - severity
+  group_wait: 30s
+  group_interval: 5m
+  repeat_interval: 4h
+
+receivers:
+  - name: operations-webhook
+    webhook_configs:
+      - url_file: /run/secrets/alert_webhook_url
+        send_resolved: true