Azure Databricks Restart a Running Cluster and Wait

arazzo: 1.0.1
info:
  title: Azure Databricks Restart a Running Cluster and Wait
  summary: Restart a running cluster and poll until it returns to RUNNING.
  description: >-
    Cycles a running cluster and confirms it comes back healthy. The workflow
    confirms the cluster is RUNNING, issues a restart, then polls the cluster
    get endpoint until the state settles back to RUNNING, branching to a
    failure end if it terminates instead. 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: azureDatabricksApi
  url: ../openapi/azure-databricks-openapi.yml
  type: openapi
workflows:
- workflowId: restart-cluster-and-wait
  summary: Restart a running cluster and wait until it is RUNNING again.
  description: >-
    Verifies the cluster is RUNNING, restarts it, then polls getCluster until
    the state returns to RUNNING, branching to a failure end on TERMINATED.
  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 running cluster to restart.
  steps:
  - stepId: confirmRunning
    description: >-
      Confirm the cluster is currently RUNNING before issuing a restart, since
      restart is only valid for a running cluster.
    operationId: getCluster
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.token
    - name: cluster_id
      in: query
      value: $inputs.clusterId
    successCriteria:
    - condition: $statusCode == 200
    - condition: $response.body#/state == "RUNNING"
    outputs:
      state: $response.body#/state
  - stepId: restartCluster
    description: >-
      Issue the restart. The cluster transitions to RESTARTING and then back to
      RUNNING when the restart completes.
    operationId: restartCluster
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.token
    requestBody:
      contentType: application/json
      payload:
        cluster_id: $inputs.clusterId
    successCriteria:
    - condition: $statusCode == 200
  - stepId: pollCluster
    description: >-
      Retrieve the current cluster state. Repeat until the cluster reports
      RUNNING again; branch to failure if it reports TERMINATED or ERROR.
    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
    onSuccess:
    - name: backToRunning
      type: end
      criteria:
      - context: $response.body
        condition: $.state == "RUNNING"
        type: jsonpath
    - name: failed
      type: goto
      stepId: reportFailure
      criteria:
      - context: $response.body
        condition: $.state == "TERMINATED" || $.state == "ERROR"
        type: jsonpath
    - name: stillRestarting
      type: goto
      stepId: pollCluster
      criteria:
      - context: $response.body
        condition: $.state == "RESTARTING" || $.state == "PENDING"
        type: jsonpath
  - stepId: reportFailure
    description: >-
      Read the cluster once more to capture the termination reason when the
      restart did not return to RUNNING.
    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
      terminationReason: $response.body#/termination_reason
  outputs:
    clusterId: $inputs.clusterId
    finalState: $steps.pollCluster.outputs.state
    failureState: $steps.reportFailure.outputs.state