refactor(k8s): consolidate to infra/+apps/ single-source tree, dedicated per-app CNPG (authentik-db/temporal-db), wire monitoring-config, forgejo→cicd ns, drop orphan/stale (data-schemas, ollama, story-crater, sqs/argocd, key-rotation)

2026-08-18 15:08:03 -07:00
parent 54fa540b33
commit 41f5b05395
241 changed files with 467 additions and 10416 deletions
@@ -0,0 +1,33 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: authentik-rules
+  namespace: iam
+spec:
+  groups:
+    - name: authentik.rules
+      interval: 15s
+      rules:
+        - alert: AuthentikHighErrorRate
+          expr: |
+            (
+              sum(rate(authentik_http_requests_total{status=~"5.."}[5m]))
+              /
+              sum(rate(authentik_http_requests_total[5m]))
+            ) > 0.05
+          for: 10m
+          labels:
+            severity: warning
+          annotations:
+            summary: "High error rate on Authentik"
+            description: "5xx error rate exceeded 5% of total requests for 10 minutes. Value: {{ $value | humanizePercentage }}"
+
+        - alert: AuthentikOutpostDown
+          expr: |
+            authentik_outpost_total_up == 0
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Authentik outpost is down"
+            description: "Outpost {{ $labels.outpost_name }} (type: {{ $labels.outpost_type }}) has been offline for 5 minutes"