Azure Databricks Resize a Running Cluster and Wait

arazzo: 1.0.1
info:
  title: Azure Databricks Resize a Running Cluster and Wait
  summary: Edit a running cluster's worker count and poll until it is RUNNING.
  description: >-
    Scales a running cluster up or down by editing its configuration. The
    workflow reads the cluster to capture the configuration required by the
    edit endpoint, applies the new worker count, then polls the cluster get
    endpoint until the resize completes and the state is RUNNING again. 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: resize-running-cluster
  summary: Resize a running cluster's worker count and wait for it to settle.
  description: >-
    Reads the current cluster config, edits it with a new num_workers value,
    then polls getCluster until the state returns to RUNNING.
  inputs:
    type: object
    required:
    - token
    - clusterId
    - numWorkers
    properties:
      token:
        type: string
        description: Databricks personal access token for the Authorization header.
      clusterId:
        type: string
        description: The id of the running cluster to resize.
      numWorkers:
        type: integer
        description: The new number of worker nodes to scale the cluster to.
  steps:
  - stepId: readCluster
    description: >-
      Read the cluster to capture the cluster_name, spark_version, and
      node_type_id required as part of the edit request body.
    operationId: getCluster
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.token
    - name: cluster_id
      in: query
      value: $inputs.clusterId
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      clusterName: $response.body#/cluster_name
      sparkVersion: $response.body#/spark_version
      nodeTypeId: $response.body#/node_type_id
  - stepId: editCluster
    description: >-
      Edit the cluster with the new worker count. A running cluster is
      restarted with the new configuration applied.
    operationId: editCluster
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.token
    requestBody:
      contentType: application/json
      payload:
        cluster_id: $inputs.clusterId
        cluster_name: $steps.readCluster.outputs.clusterName
        spark_version: $steps.readCluster.outputs.sparkVersion
        node_type_id: $steps.readCluster.outputs.nodeTypeId
        num_workers: $inputs.numWorkers
    successCriteria:
    - condition: $statusCode == 200
  - stepId: pollCluster
    description: >-
      Retrieve the current cluster state. Repeat until the cluster is RUNNING
      again after the resize; branch to failure if it terminates.
    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
      numWorkers: $response.body#/num_workers
    onSuccess:
    - name: resized
      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: stillResizing
      type: goto
      stepId: pollCluster
      criteria:
      - context: $response.body
        condition: $.state == "RESIZING" || $.state == "RESTARTING" || $.state == "PENDING"
        type: jsonpath
  - stepId: reportFailure
    description: >-
      Read the cluster once more to capture the termination reason when the
      resize 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
    finalWorkers: $steps.pollCluster.outputs.numWorkers