Microsoft Purview Trace Data Asset Lineage

arazzo: 1.0.1
info:
  title: Microsoft Purview Trace Data Asset Lineage
  summary: Search for an asset, read its entity, then walk its lineage graph with pagination.
  description: >-
    Discovers a data asset by keyword and traces its lineage in the Purview
    Atlas catalog. The workflow searches the catalog, takes the top hit's GUID,
    reads the full entity, fetches its lineage in the requested direction, and
    branches: when the lineage graph reports more children than the first page
    returned it pulls the next page, otherwise it ends. Every step spells out
    its request inline — including the inline OAuth2 bearer token — so the flow
    can be read and executed without opening the underlying OpenAPI
    description.
  version: 1.0.0
  x-realizes-capability-ids:
  - BC-610.10
  x-capability-derivation:
    method: 'deterministic join: sourceDescriptions -> per-tag OpenAPI -> tag/capability edge. No classification at this step.'
    min_confidence: 0.7
    sources:
    - capability_id: BC-610.10
      capability_name: Data Governance Management
      spec: microsoft-purview-entity-api-openapi.yml
      confidence: 0.7
    model: Turbo EA Capabilities by Vincent Verdet — Turbo EA, https://github.com/vincentmakes/turbo-ea-capabilities, CC BY 4.0
sourceDescriptions:
- name: discoveryApi
  url: ../openapi/microsoft-purview-discovery-api-openapi.yml
  type: openapi
- name: entityApi
  url: ../openapi/microsoft-purview-entity-api-openapi.yml
  type: openapi
- name: lineageApi
  url: ../openapi/microsoft-purview-lineage-api-openapi.yml
  type: openapi
workflows:
- workflowId: trace-asset-lineage
  summary: Find an asset by keyword and walk its lineage graph.
  description: >-
    Runs a discovery search, resolves the top result's GUID, reads the entity,
    retrieves its lineage, and paginates to the next lineage page when the graph
    indicates additional related entities.
  inputs:
    type: object
    required:
    - authorization
    - keywords
    properties:
      authorization:
        type: string
        description: The OAuth2 bearer token value, e.g. "Bearer eyJ0...".
      keywords:
        type: string
        description: The search keywords used to find the data asset.
      direction:
        type: string
        description: Lineage direction to traverse (INPUT, OUTPUT, or BOTH).
        default: BOTH
      depth:
        type: integer
        description: The number of hops of lineage to retrieve.
        default: 3
  steps:
  - stepId: search
    description: Search the catalog for assets matching the supplied keywords.
    operationId: searchQuery
    parameters:
    - name: Authorization
      in: header
      value: $inputs.authorization
    requestBody:
      contentType: application/json
      payload:
        keywords: $inputs.keywords
        limit: 10
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      topAssetId: $response.body#/value/0/id
  - stepId: getEntity
    description: Read the full entity definition for the top search hit.
    operationId: getEntityByGuid
    parameters:
    - name: Authorization
      in: header
      value: $inputs.authorization
    - name: guid
      in: path
      value: $steps.search.outputs.topAssetId
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      entityGuid: $response.body#/entity/guid
  - stepId: getLineage
    description: Retrieve the lineage graph for the entity in the requested direction.
    operationId: getLineageByGuid
    parameters:
    - name: Authorization
      in: header
      value: $inputs.authorization
    - name: guid
      in: path
      value: $steps.getEntity.outputs.entityGuid
    - name: direction
      in: query
      value: $inputs.direction
    - name: depth
      in: query
      value: $inputs.depth
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      childrenCount: $response.body#/childrenCount
      relations: $response.body#/relations
    onSuccess:
    - name: morePages
      type: goto
      stepId: getLineageNext
      criteria:
      - context: $response.body
        condition: $.childrenCount > 0
        type: jsonpath
    - name: done
      type: end
      criteria:
      - context: $response.body
        condition: $.childrenCount == 0
        type: jsonpath
  - stepId: getLineageNext
    description: Pull the next page of lineage when the graph reports additional children.
    operationId: getLineageNextPage
    parameters:
    - name: Authorization
      in: header
      value: $inputs.authorization
    - name: guid
      in: path
      value: $steps.getEntity.outputs.entityGuid
    - name: direction
      in: query
      value: $inputs.direction
    - name: offset
      in: query
      value: 0
    - name: limit
      in: query
      value: 100
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      nextRelations: $response.body#/relations
  outputs:
    entityGuid: $steps.getEntity.outputs.entityGuid
    relations: $steps.getLineage.outputs.relations
    nextRelations: $steps.getLineageNext.outputs.nextRelations