Acceldata Pipeline Failure Investigation

arazzo: 1.0.1
info:
  title: Acceldata Pipeline Failure Investigation
  summary: Find failed pipeline jobs, pull related critical alerts, and acknowledge the first one.
  description: >-
    A pipeline incident flow. The workflow lists failed pipeline jobs in a time
    window, queries the open critical alerts raised during that period, and when
    at least one such alert exists it acknowledges the first one. When no
    critical alerts are open the flow ends. 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: alertsApi
  url: ../openapi/acceldata-alerts-api-openapi.yml
  type: openapi
- name: pipelineJobsApi
  url: ../openapi/acceldata-pipeline-jobs-api-openapi.yml
  type: openapi
workflows:
- workflowId: pipeline-failure-investigation
  summary: Correlate failed pipeline jobs with critical alerts and acknowledge one.
  description: >-
    Lists failed pipeline jobs from a start time, queries open critical alerts
    from that same start time, and branches: when one or more open critical
    alerts exist it acknowledges the first, otherwise it ends.
  inputs:
    type: object
    required:
    - apiKey
    - fromTime
    properties:
      apiKey:
        type: string
        description: Acceldata API key sent in the X-API-Key header.
      fromTime:
        type: string
        description: Start time (ISO 8601) for the failed-job and alert query range.
      acknowledgeComment:
        type: string
        description: Comment recorded when acknowledging the alert.
  steps:
  - stepId: listFailedJobs
    description: >-
      List pipeline jobs that failed since the start time to identify the
      incident window.
    operationId: listPipelineJobs
    parameters:
    - name: X-API-Key
      in: header
      value: $inputs.apiKey
    - name: status
      in: query
      value: failed
    - name: from_time
      in: query
      value: $inputs.fromTime
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      failedJobCount: $response.body#/total
      firstJobId: $response.body#/data/0/id
  - stepId: listCriticalAlerts
    description: >-
      Query open critical alerts raised since the start time to correlate with
      the failed pipeline jobs.
    operationId: listAlerts
    parameters:
    - name: X-API-Key
      in: header
      value: $inputs.apiKey
    - name: status
      in: query
      value: open
    - name: severity
      in: query
      value: critical
    - name: from_time
      in: query
      value: $inputs.fromTime
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      firstAlertId: $response.body#/data/0/id
      alertCount: $response.body#/total
    onSuccess:
    - name: criticalAlertsPresent
      type: goto
      stepId: acknowledgeAlert
      criteria:
      - context: $response.body
        condition: $.data.length > 0
        type: jsonpath
    - name: noCriticalAlerts
      type: end
      criteria:
      - context: $response.body
        condition: $.data.length == 0
        type: jsonpath
  - stepId: acknowledgeAlert
    description: >-
      Acknowledge the first open critical alert to mark the incident as under
      investigation.
    operationId: acknowledgeAlert
    parameters:
    - name: X-API-Key
      in: header
      value: $inputs.apiKey
    - name: id
      in: path
      value: $steps.listCriticalAlerts.outputs.firstAlertId
    requestBody:
      contentType: application/json
      payload:
        comment: $inputs.acknowledgeComment
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      alertId: $response.body#/id
      alertStatus: $response.body#/status
  outputs:
    failedJobCount: $steps.listFailedJobs.outputs.failedJobCount
    criticalAlertCount: $steps.listCriticalAlerts.outputs.alertCount
    acknowledgedAlertId: $steps.acknowledgeAlert.outputs.alertId