apiVersion: rules.alerting.grafana.app/v0alpha1
kind: AlertRule
metadata:
  annotations:
    grafana.app/folder: dotcom
    grafana.com/provenance: ''
  labels:
    grafana.app/folder: dotcom
    grafana.com/group: dotcom-alerts
    grafana.com/group-index: '1'
  name: dotcom-file-do-exceptions
  namespace: stacks-890472
spec:
  annotations:
    description: TLFileDurableObject threw more than 300 uncaught exceptions in the
      last hour. Quiet hours run 1-50; the bursts that followed hibernation being
      enabled on 2026-08-13 run 700-1300. Check the "DO exceptions by namespace"
      panel on the Cloudflare platform metrics dashboard, then Sentry for the
      matching source tag.
    summary: File room durable objects are throwing uncaught exceptions
  execErrState: Error
  expressions:
    A:
      datasourceUID: ffuyblsuemj28b
      model:
        columns:
          - selector: sum.requests
            text: exceptions
            type: number
        format: table
        global_query_id: ''
        parser: backend
        refId: A
        root_selector: data.viewer.accounts[0].durableObjectsInvocationsAdaptiveGroups
        source: url
        type: graphql
        url: https://api.cloudflare.com/client/v4/graphql
        url_options:
          body_content_type: application/json
          body_graphql_query: |-
            query {
              viewer {
                accounts(filter: {accountTag: "c34edc4e76350954b63adebde86d5eb1"}) {
                  durableObjectsInvocationsAdaptiveGroups(limit: 1, filter: {datetime_geq: "${__from:date:iso}", datetime_leq: "${__to:date:iso}", namespaceId: "5864db4344ac4c55bfd94e81dd25a043", status: "scriptThrewException"}) {
                    sum { requests }
                  }
                }
              }
            }
          body_type: graphql
          method: POST
      relativeTimeRange:
        from: 1h0m0s
        to: 0s
    C:
      model:
        conditions:
          - evaluator:
              params:
                - 300
              type: gt
            operator:
              type: and
            query:
              params:
                - C
            reducer:
              params: []
              type: last
            type: query
        datasource:
          type: __expr__
          uid: __expr__
        expression: A
        intervalMs: 1000
        maxDataPoints: 43200
        refId: C
        type: threshold
      queryType: expression
      source: true
  for: 10m0s
  labels:
    service: dotcom
    severity: warning
  # The query filters to scriptThrewException, so a healthy hour returns no rows at
  # all rather than a zero. NoData here means "nothing threw" — alerting on it would
  # invert the rule.
  noDataState: Ok
  notificationSettings:
    receiver: Discord
    type: SimplifiedRouting
  title: File room DO exceptions
  trigger:
    interval: 10m