apiVersion: 1

groups:
  - orgId: 1
    name: trails.cool alerts
    folder: trails.cool
    interval: 1m
    rules:
      - uid: disk-usage-high
        title: Disk usage > 80%
        condition: C
        data:
          - refId: A
            relativeTimeRange: { from: 600, to: 0 }
            datasourceUid: prometheus
            model:
              expr: (1 - node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) * 100
              intervalMs: 60000
              maxDataPoints: 43200
          - refId: C
            relativeTimeRange: { from: 600, to: 0 }
            datasourceUid: __expr__
            model:
              type: threshold
              conditions:
                - evaluator: { params: [80], type: gt }
                  reducer: { type: last }
        for: 15m
        annotations:
          summary: "Disk usage is above 80%"

      - uid: app-health-failing
        title: App health check failing
        condition: C
        data:
          - refId: A
            relativeTimeRange: { from: 300, to: 0 }
            datasourceUid: prometheus
            model:
              expr: up{job=~"journal|planner"} == 0
              intervalMs: 15000
              maxDataPoints: 43200
          - refId: C
            relativeTimeRange: { from: 300, to: 0 }
            datasourceUid: __expr__
            model:
              type: threshold
              conditions:
                - evaluator: { params: [0], type: gt }
                  reducer: { type: last }
        for: 2m
        annotations:
          summary: "{{ $labels.job }} is down"

      - uid: error-rate-high
        title: Error rate > 5%
        condition: C
        data:
          - refId: A
            relativeTimeRange: { from: 600, to: 0 }
            datasourceUid: prometheus
            model:
              expr: sum(rate(http_request_duration_seconds_count{status=~"5.."}[5m])) / sum(rate(http_request_duration_seconds_count[5m])) * 100
              intervalMs: 60000
              maxDataPoints: 43200
          - refId: C
            relativeTimeRange: { from: 600, to: 0 }
            datasourceUid: __expr__
            model:
              type: threshold
              conditions:
                - evaluator: { params: [5], type: gt }
                  reducer: { type: last }
        for: 5m
        annotations:
          summary: "Error rate is above 5%"

contactPoints:
  - orgId: 1
    name: email
    receivers:
      - uid: email-default
        type: email
        settings:
          addresses: admin@trails.cool

policies:
  - orgId: 1
    receiver: email