groups:
- name: alertmanager.rules
  rules:
  - alert: AlertmanagerConfigInconsistent
    annotations:
      message: The configuration of the instances of the Alertmanager cluster `{{$labels.service}}`
        are out of sync.
    expr: |
      count_values("config_hash", alertmanager_config_hash{job="alertmanager-main",namespace="monitoring"}) BY (service) / ON(service) GROUP_LEFT() label_replace(max(prometheus_operator_spec_replicas{job="prometheus-operator",namespace="monitoring",controller="alertmanager"}) by (name, job, namespace, controller), "service", "alertmanager-$1", "name", "(.*)") != 1
    for: 5m
    labels:
      component: alertmanager
      oncall_team: o11y
      severity: critical
      response_class: page
  - alert: AlertmanagerFailedReload
    annotations:
      message: Reloading Alertmanager's configuration has failed for {{ $labels.namespace
        }}/{{ $labels.pod}}.
    expr: |
      alertmanager_config_last_reload_successful{job="alertmanager-main",namespace="monitoring"} == 0
    for: 10m
    labels:
      severity: warning
      component: alertmanager
      oncall_team: o11y
  - alert: AlertmanagerMembersInconsistent
    annotations:
      message: Alertmanager has not found all other members of the cluster.
    expr: |
      alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"}
        != on (service) GROUP_LEFT()
      count by (service) (alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"})
    for: 5m
    labels:
      component: alertmanager
      oncall_team: o11y
      severity: critical
      response_class: page