apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: openclaw-alerts
  namespace: openclaw
  labels:
    release: prometheus-operator
    app.kubernetes.io/name: openclaw
spec:
  groups:
    - name: openclaw.rules
      rules:
        - alert: OpenClawPodNotReady
          expr: kube_pod_status_ready{namespace="openclaw", pod="openclaw-0", condition="true"} == 0
          for: 5m
          labels:
            severity: critical
          annotations:
            summary: "OpenClaw pod openclaw-0 is not ready"
            description: "Pod openclaw-0 in namespace openclaw has been unready for more than 5 minutes. Telegram and background agents may be offline."
        - alert: OpenClawCrashLooping
          expr: increase(kube_pod_container_status_restarts_total{namespace="openclaw", pod="openclaw-0"}[15m]) >= 2
          for: 2m
          labels:
            severity: warning
          annotations:
            summary: "OpenClaw container restart detected"
            description: "Container {{ $labels.container }} in pod openclaw-0 has restarted {{ $value }} times in the last 15 minutes."
        - alert: OpenClawDataVolumeLow
          expr: kubelet_volume_stats_available_bytes{namespace="openclaw", persistentvolumeclaim="openclaw-data"} / kubelet_volume_stats_capacity_bytes{namespace="openclaw", persistentvolumeclaim="openclaw-data"} < 0.15
          for: 15m
          labels:
            severity: warning
          annotations:
            summary: "OpenClaw PVC data volume is low on space"
            description: "PersistentVolumeClaim openclaw-data has less than 15% space available."