feat(prometheus): add alerting rules and alertmanager config

prometheus-stack/k8s/traefik-alerts.yaml

@@ -0,0 +1,60 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: traefik
+  namespace: prometheus
+  labels:
+    release: prometheus-stack
+spec:
+  groups:
+    - name: traefik
+      rules:
+        - alert: TraefikDown
+          expr: absent(up{job="traefik"})
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Traefik metrics are unavailable"
+            description: "Prometheus has no Traefik target."
+
+        - alert: TraefikConfigReloadFailed
+          expr: traefik_config_last_reload_success == 0
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Traefik configuration reload failed"
+            description: "Traefik failed to apply its last configuration reload. Check Traefik logs and the dynamic config sources."
+
+        - alert: TraefikServiceHigh5xxRate
+          expr: |
+            sum(rate(traefik_service_requests_total{code=~"5.."}[5m])) by (service)
+              / sum(rate(traefik_service_requests_total[5m])) by (service) * 100 > 5
+              and sum(rate(traefik_service_requests_total[5m])) by (service) > 0
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "High 5xx error rate for service {{ $labels.service }}"
+            description: "Service {{ $labels.service }} is returning 5xx errors for more than 5% of requests over the last 5 minutes (current: {{ $value | humanizePercentage }})."
+
+        - alert: TraefikServiceHighLatency
+          expr: |
+            histogram_quantile(0.95,
+              sum(rate(traefik_service_request_duration_seconds_bucket[5m])) by (le, service)) > 2
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "High latency for service {{ $labels.service }}"
+            description: "P95 latency of {{ $labels.service }} exceeded 2 seconds over the last 5 minutes (current: {{ $value | humanizeDuration }})."
+
+        - alert: TraefikCertExpiringSoon
+          expr: min(traefik_tls_certs_not_after) - time() < 14 * 24 * 60 * 60
+          for: 10m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Traefik TLS certificate expires soon"
+            description: "A TLS certificate managed by Traefik expires in less than 14 days (in {{ $value | humanizeDuration }})."