atulpurohit/antigravity-awesome-skills/alerting-config

groups:
  - name: slo.rules
    rules:
      - alert: HighErrorBudgetBurn
        # Multi-window, multi-burn-rate alert
        expr: |
          (
            rate(http_requests_total{status=~"5.."}[1h]) /
            rate(http_requests_total[1h]) > 0.14
          ) and (
            rate(http_requests_total{status=~"5.."}[5m]) /
            rate(http_requests_total[5m]) > 0.14
          )
        for: 2m
        labels:
          severity: critical
          team: backend
        annotations:
          summary: "Error rate {{ $value | humanizePercentage }} - burning error budget fast"
          runbook: "https://wiki/runbooks/high-error-rate"
 
      - alert: HighP99Latency
        expr: histogram_quantile(0.99, rate(http_duration_seconds_bucket[5m])) > 1.0
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "P99 latency is {{ $value | humanizeDuration }}"

route:
  group_by: [alertname, service]
  group_wait: 30s
  group_interval: 5m
  repeat_interval: 12h
  receiver: slack-default
  routes:
    - matchers: [severity=critical]
      receiver: pagerduty-critical
      continue: true
    - matchers: [severity=warning]
      receiver: slack-warnings
 
receivers:
  - name: pagerduty-critical
    pagerduty_configs:
      - service_key: $PAGERDUTY_KEY
  - name: slack-warnings
    slack_configs:
      - channel: '#alerts-warnings'