Azure Databricks Cluster Health Diagnostics

arazzo: 1.0.1
info:
  title: Azure Databricks Cluster Health Diagnostics
  summary: Read a cluster's state then pull its recent events for diagnosis.
  description: >-
    Gathers diagnostic context for a single cluster. The workflow reads the
    cluster to capture its current state and termination reason, then retrieves
    the most recent cluster events filtered to the failure and lifecycle event
    types so an operator can understand why the cluster is in its current
    state. Every step spells out its request inline so the flow can be read and
    executed without opening the underlying OpenAPI description.
  version: 1.0.0
sourceDescriptions:
- name: clustersApi
  url: ../openapi/microsoft-azure-databricks-clusters-api-openapi.yml
  type: openapi
workflows:
- workflowId: cluster-health-diagnostics
  summary: Inspect a cluster's state and recent events for diagnosis.
  description: >-
    Reads the cluster state, then lists its recent events to surface lifecycle
    and failure activity.
  inputs:
    type: object
    required:
    - token
    - clusterId
    properties:
      token:
        type: string
        description: Databricks personal access token for the Authorization header.
      clusterId:
        type: string
        description: The id of the cluster to diagnose.
      eventLimit:
        type: integer
        description: Maximum number of events to return (max 50).
        default: 50
  steps:
  - stepId: readCluster
    description: >-
      Read the cluster to capture its current state, state message, and any
      termination reason.
    operationId: getCluster
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.token
    - name: cluster_id
      in: query
      value: $inputs.clusterId
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      state: $response.body#/state
      stateMessage: $response.body#/state_message
      terminationReason: $response.body#/termination_reason
  - stepId: listEvents
    description: >-
      Retrieve the most recent cluster events in descending order, filtered to
      key lifecycle and failure event types.
    operationId: listClusterEvents
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.token
    requestBody:
      contentType: application/json
      payload:
        cluster_id: $inputs.clusterId
        order: DESC
        limit: $inputs.eventLimit
        event_types:
        - TERMINATING
        - DRIVER_NOT_RESPONDING
        - DRIVER_UNAVAILABLE
        - SPARK_EXCEPTION
        - NODES_LOST
        - RUNNING
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      events: $response.body#/events
      totalCount: $response.body#/total_count
  outputs:
    clusterState: $steps.readCluster.outputs.state
    terminationReason: $steps.readCluster.outputs.terminationReason
    events: $steps.listEvents.outputs.events
    eventCount: $steps.listEvents.outputs.totalCount