> ## Documentation Index
> Fetch the complete documentation index at: https://doc.featherhq.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Get an eval run (optionally with embedded evidence)

> Read one eval run. With no ``include`` the response is the shallow
run+scores shape (back-compat); each ``include`` token adds the matching
evidence section. Unknown tokens are ignored. Cross-org/unknown → 404.



## OpenAPI

````yaml /api-reference/openapi.json get /v1/eval-runs/{run_id}
openapi: 3.1.0
info:
  title: Feather API
  description: >-
    Unified customer experience platform API. Manages identity, conversations,
    memory, agents, procedures, policies, model routing, knowledge bases,
    integrations, and runtime execution.
  version: 1.21.0
servers:
  - url: https://api-sandbox.featherhq.com
    description: Sandbox
  - url: http://localhost:8000
    description: Local dev
security: []
paths:
  /v1/eval-runs/{run_id}:
    get:
      tags:
        - evals
        - evals
      summary: Get an eval run (optionally with embedded evidence)
      description: |-
        Read one eval run. With no ``include`` the response is the shallow
        run+scores shape (back-compat); each ``include`` token adds the matching
        evidence section. Unknown tokens are ignored. Cross-org/unknown → 404.
      operationId: getEvalRun
      parameters:
        - name: run_id
          in: path
          required: true
          schema:
            type: string
            format: uuid
            title: Run Id
        - name: include
          in: query
          required: false
          schema:
            anyOf:
              - type: string
              - type: 'null'
            description: 'comma-separated evidence to embed: session,turns,recording'
            title: Include
          description: 'comma-separated evidence to embed: session,turns,recording'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EvalRunDetailResponse'
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Authentication required
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: Resource not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
        - APIKeyHeader: []
components:
  schemas:
    EvalRunDetailResponse:
      properties:
        id:
          type: string
          format: uuid
          title: Id
        organization_id:
          type: string
          format: uuid
          title: Organization Id
        session_id:
          type: string
          format: uuid
          title: Session Id
        evaluator_id:
          type: string
          format: uuid
          title: Evaluator Id
        agent_id:
          anyOf:
            - type: string
              format: uuid
            - type: 'null'
          title: Agent Id
        channel:
          anyOf:
            - type: string
            - type: 'null'
          title: Channel
        status:
          type: string
          title: Status
        started_at:
          anyOf:
            - type: string
              format: date-time
            - type: 'null'
          title: Started At
        finished_at:
          anyOf:
            - type: string
              format: date-time
            - type: 'null'
          title: Finished At
        error_text:
          anyOf:
            - type: string
            - type: 'null'
          title: Error Text
        prompt_snapshot:
          anyOf:
            - type: string
            - type: 'null'
          title: Prompt Snapshot
        threshold_snapshot:
          anyOf:
            - type: number
            - type: 'null'
          title: Threshold Snapshot
        config_snapshot:
          additionalProperties: true
          type: object
          title: Config Snapshot
        severity_snapshot:
          type: string
          title: Severity Snapshot
        format_snapshot:
          type: string
          title: Format Snapshot
        is_critical_snapshot:
          type: boolean
          title: Is Critical Snapshot
          default: false
        created_at:
          type: string
          format: date-time
          title: Created At
        scores:
          items:
            $ref: '#/components/schemas/EvalScoreResponse'
          type: array
          title: Scores
        session:
          anyOf:
            - $ref: '#/components/schemas/ConversationSummary'
            - type: 'null'
        turns:
          anyOf:
            - items:
                $ref: '#/components/schemas/TurnView'
              type: array
            - type: 'null'
          title: Turns
        turns_truncated:
          type: boolean
          title: Turns Truncated
          default: false
        recording:
          anyOf:
            - $ref: '#/components/schemas/RecordingRef'
            - type: 'null'
      type: object
      required:
        - id
        - organization_id
        - session_id
        - evaluator_id
        - status
        - started_at
        - finished_at
        - error_text
        - prompt_snapshot
        - threshold_snapshot
        - severity_snapshot
        - format_snapshot
        - created_at
      title: EvalRunDetailResponse
      description: >-
        ``EvalRunResponse`` superset; extras stay null/[]/false unless
        requested.
    ErrorResponse:
      properties:
        error:
          type: string
          title: Error
        message:
          type: string
          title: Message
      type: object
      required:
        - error
        - message
      title: ErrorResponse
      description: Standard error response returned by all API error handlers.
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    EvalScoreResponse:
      properties:
        id:
          type: string
          format: uuid
          title: Id
        organization_id:
          type: string
          format: uuid
          title: Organization Id
        eval_run_id:
          type: string
          format: uuid
          title: Eval Run Id
        value:
          anyOf:
            - type: number
            - type: 'null'
          title: Value
        raw_value:
          anyOf:
            - type: number
            - type: 'null'
          title: Raw Value
        label:
          anyOf:
            - type: string
            - type: 'null'
          title: Label
        passed:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Passed
        confidence:
          anyOf:
            - type: number
            - type: 'null'
          title: Confidence
        rationale:
          anyOf:
            - type: string
            - type: 'null'
          title: Rationale
        severity:
          anyOf:
            - type: string
            - type: 'null'
          title: Severity
        blocking:
          type: boolean
          title: Blocking
        evidence_observation_ids:
          items:
            type: string
          type: array
          title: Evidence Observation Ids
        created_at:
          type: string
          format: date-time
          title: Created At
      type: object
      required:
        - id
        - organization_id
        - eval_run_id
        - value
        - raw_value
        - label
        - passed
        - confidence
        - rationale
        - severity
        - blocking
        - created_at
      title: EvalScoreResponse
    ConversationSummary:
      properties:
        id:
          type: string
          format: uuid
          title: Id
        channel:
          type: string
          title: Channel
        session_type:
          type: string
          title: Session Type
        status:
          type: string
          title: Status
        assistant_id:
          anyOf:
            - type: string
              format: uuid
            - type: 'null'
          title: Assistant Id
        assistant_revision_id:
          anyOf:
            - type: string
              format: uuid
            - type: 'null'
          title: Assistant Revision Id
        subject:
          anyOf:
            - type: string
            - type: 'null'
          title: Subject
        created_at:
          type: string
          format: date-time
          title: Created At
        last_activity_at:
          anyOf:
            - type: string
              format: date-time
            - type: 'null'
          title: Last Activity At
      type: object
      required:
        - id
        - channel
        - session_type
        - status
        - assistant_id
        - assistant_revision_id
        - subject
        - created_at
        - last_activity_at
      title: ConversationSummary
      description: Projection of the parent ``Conversation`` for the eval-run detail view.
    TurnView:
      properties:
        id:
          type: string
          format: uuid
          title: Id
        seq:
          type: integer
          title: Seq
        role:
          type: string
          title: Role
        content:
          anyOf:
            - type: string
            - type: 'null'
          title: Content
        tool_calls:
          anyOf:
            - items:
                additionalProperties: true
                type: object
              type: array
            - additionalProperties: true
              type: object
            - type: 'null'
          title: Tool Calls
        tool_call_id:
          anyOf:
            - type: string
            - type: 'null'
          title: Tool Call Id
        authored_by:
          type: string
          title: Authored By
        created_at:
          type: string
          format: date-time
          title: Created At
      type: object
      required:
        - id
        - seq
        - role
        - content
        - tool_calls
        - tool_call_id
        - authored_by
        - created_at
      title: TurnView
      description: >-
        Projection of one ``ConvMessage`` transcript row.


        Omits the TOASTed ``citations`` / ``rag_traces`` columns (deferred by

        ``SessionService.get_turns``) so no lazy-load fires. ``tool_calls`` is
        the

        persisted OpenAI-style array (a ``list``) — see
        ``ConvMessage.tool_calls``

        and ``conversation.message_adapter``; the column's ``Mapped[dict]`` hint
        is

        misleading, the value on the wire is a list. The type also admits
        ``dict``

        defensively so a single malformed legacy row can't 500 the whole detail

        response on validation.
    RecordingRef:
      properties:
        id:
          type: string
          format: uuid
          title: Id
        kind:
          type: string
          title: Kind
        status:
          type: string
          title: Status
        duration_ms:
          anyOf:
            - type: integer
            - type: 'null'
          title: Duration Ms
        manifest_key:
          type: string
          title: Manifest Key
        started_at:
          type: string
          format: date-time
          title: Started At
        finalized_at:
          anyOf:
            - type: string
              format: date-time
            - type: 'null'
          title: Finalized At
      type: object
      required:
        - id
        - kind
        - status
        - duration_ms
        - manifest_key
        - started_at
        - finalized_at
      title: RecordingRef
      description: >-
        Metadata-only projection of a voice ``Recording`` (no presigned
        URL/bytes).
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
              - type: string
              - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      in: header
      name: x-api-key

````