deploy: Dockerfile, Compose pro Rolle, LiteLLM, Prometheus/Alertmanager, Canary-Prober, n8n-Workflows

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 00:51:31 +02:00
parent 4cbe313c62
commit cb5a413169
28 changed files with 1731 additions and 9 deletions
@@ -0,0 +1,18 @@
+# Alertmanager → Router-Service (Healer). Kurzes repeat_interval treibt die Eskalationsleiter voran;
+# Cooldowns pro Stufe regelt der Healer selbst.
+route:
+  receiver: knaster-healer
+  group_by: [alertname, slot, instance]
+  group_wait: 30s
+  group_interval: 1m
+  repeat_interval: 5m
+
+receivers:
+  - name: knaster-healer
+    webhook_configs:
+      - url: http://router:8080/v1/healer/alertmanager
+        send_resolved: true
+        http_config:
+          authorization:
+            type: Bearer
+            credentials_file: /etc/alertmanager/router_token