alertmanager.yml

global:
  resolve_timeout: 5m
  slack_api_url: '${SLACK_WEBHOOK_URL}'

templates:
  - '/etc/alertmanager/templates/*.tmpl'

route:
  group_by: ['alertname', 'team']
  group_wait: 30s
  group_interval: 5m
  repeat_interval: 4h
  receiver: 'slack-default'
  routes:
    - match:
        severity: critical
      receiver: 'slack-critical'
      continue: true
    - match:
        team: contracts
      receiver: 'slack-contracts'
      continue: true
    - match:
        alertname: ContractPaused
      receiver: 'pagerduty-oncall'

receivers:
  - name: 'slack-default'
    slack_configs:
      - channel: '#trivela-alerts'
        send_resolved: true
        title: '[{{ .Status | toUpper }}] {{ .GroupLabels.alertname }}'
        text: >-
          {{ range .Alerts }} *Alert:* {{ .Annotations.summary }} *Details:* {{
          .Annotations.description }} *Runbook:* {{ .Annotations.runbook_url }} {{ end }}

  - name: 'slack-critical'
    slack_configs:
      - channel: '#trivela-critical'
        send_resolved: true
        title: '🚨 CRITICAL: {{ .GroupLabels.alertname }}'
        text: >-
          {{ range .Alerts }} *Summary:* {{ .Annotations.summary }} *Description:* {{
          .Annotations.description }} *Runbook:* {{ .Annotations.runbook_url }} {{ end }}

  - name: 'slack-contracts'
    slack_configs:
      - channel: '#trivela-contracts'
        send_resolved: true
        title: '📋 Contract Alert: {{ .GroupLabels.alertname }}'
        text: >-
          {{ range .Alerts }} {{ .Annotations.description }} Runbook: {{ .Annotations.runbook_url }}
          {{ end }}

  - name: 'pagerduty-oncall'
    pagerduty_configs:
      - service_key: '${PAGERDUTY_SERVICE_KEY}'
        description: '{{ .GroupLabels.alertname }}: {{ (index .Alerts 0).Annotations.summary }}'

inhibit_rules:
  - source_match:
      alertname: 'BackendDown'
    target_match_re:
      alertname: 'HighBackendErrorRate|BackendProcessRestart'
    equal: ['instance']