> ## Documentation Index
> Fetch the complete documentation index at: https://docs.calibrate.artpark.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Get test case result

> Get the full result of one test case in a run



## OpenAPI

````yaml /api-reference/openapi.json get /agent-tests/run/{task_id}/results/{test_uuid}
openapi: 3.1.0
info:
  title: Calibrate Public API
  version: 0.1.0
  description: Programmatic API for CI/automation. Pass your key in the `X-API-Key` header.
servers:
  - url: https://api.calibrate.artpark.ai
    description: Production
security: []
paths:
  /agent-tests/run/{task_id}/results/{test_uuid}:
    get:
      tags:
        - agent-tests
      summary: Get test case result
      description: Get the full result of one test case in a run
      operationId: >-
        get_agent_test_case_result_agent_tests_run__task_id__results__test_uuid__get
      parameters:
        - name: task_id
          in: path
          required: true
          schema:
            type: string
            description: Test run or benchmark the case was run in
            examples:
              - a3b2c1d0-e5f4-3210-abcd-ef1234567890
            title: Task Id
          description: Test run or benchmark the case was run in
        - name: test_uuid
          in: path
          required: true
          schema:
            type: string
            description: The test whose result to read, as `test_uuid` on the case
            examples:
              - b1c2d3e4-f5a6-7890-bcde-f12345678901
            title: Test Uuid
          description: The test whose result to read, as `test_uuid` on the case
        - name: model
          in: query
          required: false
          schema:
            anyOf:
              - type: string
              - type: 'null'
            description: >-
              Which model's answer to read. Required for a benchmark, which runs
              every test once per model
            examples:
              - openai/gpt-4.1
            title: Model
          description: >-
            Which model's answer to read. Required for a benchmark, which runs
            every test once per model
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TestCaseResult'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
        - ApiKeyAuth: []
components:
  schemas:
    TestCaseResult:
      properties:
        test_case_id:
          anyOf:
            - type: string
            - type: 'null'
          title: Test Case Id
          description: ID of the test case within the run
        name:
          anyOf:
            - type: string
            - type: 'null'
          title: Name
          description: Name of the test
        test_uuid:
          anyOf:
            - type: string
            - type: 'null'
          title: Test Uuid
          description: >-
            ID of the test this case ran, which is what you pass to read the
            case on its own
          examples:
            - b1c2d3e4-f5a6-7890-bcde-f12345678901
        test_type:
          anyOf:
            - type: string
              enum:
                - response
                - tool_call
                - conversation
                - general
            - type: 'null'
          title: Test Type
          description: >-
            What the test asks of the agent, which decides how a reader draws
            the case
        passed:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Passed
          description: Whether the case passed
        reasoning:
          anyOf:
            - type: string
            - type: 'null'
          title: Reasoning
          description: The judge's reasoning, or the tool-call diff for a tool-call test
        output:
          anyOf:
            - $ref: '#/components/schemas/TestOutput'
            - type: 'null'
          description: The agent's output for this case
        test_case:
          anyOf:
            - additionalProperties: true
              type: object
            - type: 'null'
          description: The test case definition that was run
        inputs:
          anyOf:
            - additionalProperties: true
              type: object
            - type: 'null'
          description: >-
            Extra request fields sent to the agent for this case, the agent's
            `default_inputs` with this case's overrides applied
        judge_results:
          anyOf:
            - items:
                $ref: '#/components/schemas/JudgeResult'
              type: array
            - type: 'null'
          title: Judge Results
          description: One verdict for each evaluator
        latency_ms:
          anyOf:
            - type: number
            - type: 'null'
          title: Latency Ms
          description: How long the agent took to respond, in milliseconds
        cost:
          anyOf:
            - type: number
            - type: 'null'
          title: Cost
          description: Cost of this case (USD)
        unanswered:
          type: boolean
          title: Unanswered
          description: >-
            Whether this case produced no answer because the agent or the judge
            could not be reached, in which case `reasoning` carries the error
            and `passed` is not a verdict on the agent
          default: false
        not_run:
          type: boolean
          title: Not Run
          description: >-
            Whether this case never started, because a user stopped the run
            first. It is counted neither as passed nor as failed
          default: false
      type: object
      title: TestCaseResult
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    TestOutput:
      properties:
        response:
          anyOf:
            - type: string
            - type: 'null'
          title: Response
          description: The reply the agent generated
        tool_calls:
          anyOf:
            - items:
                $ref: '#/components/schemas/ToolCallOutput'
              type: array
            - type: 'null'
          title: Tool Calls
          description: Tool calls the agent generated
      type: object
      title: TestOutput
    JudgeResult:
      properties:
        evaluator_uuid:
          anyOf:
            - type: string
              maxLength: 36
              minLength: 36
            - type: 'null'
          title: Evaluator Uuid
          description: ID of the evaluator that produced this verdict
        reasoning:
          anyOf:
            - type: string
            - type: 'null'
          title: Reasoning
          description: The judge's rationale for this verdict
        match:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Match
          description: Pass/fail verdict, set for binary evaluators
        score:
          anyOf:
            - type: number
            - type: 'null'
          title: Score
          description: Numeric score, set for rating evaluators
        value_name:
          anyOf:
            - type: string
            - type: 'null'
          title: Value Name
          description: Readable label for the verdict, taken from the run's rubric
        variable_values:
          anyOf:
            - additionalProperties: true
              type: object
            - type: 'null'
          description: >-
            Values filled into the evaluator prompt's `{{variable}}`
            placeholders for this test case, keyed by variable name
          examples:
            - criteria: Is the reply correct and helpful?
      type: object
      title: JudgeResult
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
              - type: string
              - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError
    ToolCallOutput:
      properties:
        tool:
          type: string
          title: Tool
          description: Name of the tool the agent called
        arguments:
          anyOf:
            - additionalProperties: true
              type: object
            - type: 'null'
          description: Arguments the agent passed to the tool
          examples:
            - city: Paris
        output:
          anyOf:
            - {}
            - type: 'null'
          title: Output
          description: >-
            Tool execution result, when the agent ran the tool and returned its
            result
      type: object
      required:
        - tool
      title: ToolCallOutput
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-API-Key
      description: API key for authentication

````