Microsoft Azure Event Hubs Ingress and Egress Throttled Requests Sentinel

id: azure-event-hubs-throttled-requests-sentinel
namespace: company.cloud

inputs:
  - id: subscription_id
    type: STRING
    description: Azure Subscription ID.
  - id: resource_group
    type: STRING
    description: Azure Resource Group containing Event Hubs namespace.
  - id: namespace_name
    type: STRING
    description: Azure Event Hubs Namespace name.
  - id: threshold_throttled_requests
    type: INT
    defaults: 0
    description: "Maximum allowable throttled requests in 5-minute sampling interval
      (default 0)."

tasks:
  - id: check_throttled_requests
    type: io.kestra.plugin.scripts.shell.Commands
    containerImage: mcr.microsoft.com/azure-cli:latest
    commands:
      - |
        az login --service-principal -u "{{ secret('AZURE_CLIENT_ID') }}" -p "{{ secret('AZURE_CLIENT_SECRET') }}" --tenant "{{ secret('AZURE_TENANT_ID') }}" --output none
        az account set --subscription "{{ inputs.subscription_id }}"

        RESOURCE_ID="/subscriptions/{{ inputs.subscription_id }}/resourceGroups/{{ inputs.resource_group }}/providers/Microsoft.EventHub/namespaces/{{ inputs.namespace_name }}"

        az monitor metrics list           --resource "$RESOURCE_ID"           --metric "ThrottledRequests"           --interval PT5M           --output json > /tmp/eventhub_telemetry.json

        THROTTLED=$(jq '[.value[]?.timeseries[]?.data[]?.total // 0] | add // 0' /tmp/eventhub_telemetry.json)
        echo "::set-output name=throttled_count::$THROTTLED::"

  - id: evaluate_throttling
    type: io.kestra.plugin.core.flow.If
    condition: "{{ outputs.check_throttled_requests.vars.throttled_count | int >
      inputs.threshold_throttled_requests }}"
    then:
      - id: notify_streaming_team
        type: io.kestra.plugin.slack.notifications.SlackIncomingWebhook
        url: "{{ secret('SLACK_WEBHOOK') }}"
        payload: |
          {
            "channel": "#cloud-ops",
            "attachments": [
              {
                "color": "danger",
                "title": "🚨 Azure Event Hubs Throttling Alert",
                "text": "Event Hubs Namespace `{{ inputs.namespace_name }}` recorded *{{ outputs.check_throttled_requests.vars.throttled_count }} throttled requests* over the last 5 minutes! Throughput units (TU) or processing units (PU) capacity has been exceeded.",
                "footer": "Kestra Cloud Sentinel • Microsoft Azure"
              }
            ]
          }

errors:
  - id: alert_pipeline_failure
    type: io.kestra.plugin.slack.notifications.SlackIncomingWebhook
    url: "{{ secret('SLACK_WEBHOOK') }}"
    payload: |
      {
        "channel": "#cloud-ops",
        "attachments": [
          {
            "color": "danger",
            "title": "⚠️ Azure Event Hubs Throttled Requests Sentinel Failure",
            "text": "Failed to query Azure Monitor metrics for Event Hubs namespace. Verify Azure Service Principal credentials and permissions.",
            "footer": "Kestra Workflow Failure Sentinel"
          }
        ]
      }

triggers:
  - id: periodic_schedule
    type: io.kestra.plugin.core.trigger.Schedule
    cron: "*/15 * * * *"
    disabled: true
    inputs:
      subscription_id: replace-with-your-subscription-id
      resource_group: replace-with-your-resource-group
      namespace_name: replace-with-your-namespace-name