openapi: 3.1.0 info: title: Arthur GenAI Engine Agent Discovery Continuous Eval Test Runs API version: 2.1.688 tags: - name: Continuous Eval Test Runs paths: /api/v1/continuous_evals/{eval_id}/test_runs: post: tags: - Continuous Eval Test Runs summary: Create and start a test run for a continuous eval description: Run a continuous eval against specific traces as a test. Results are stored separately from production annotations. operationId: create_test_run_api_v1_continuous_evals__eval_id__test_runs_post security: - API Key: [] parameters: - name: eval_id in: path required: true schema: type: string format: uuid title: Continuous Eval ID description: The id of the continuous eval to test. description: The id of the continuous eval to test. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateTestRunRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ContinuousEvalTestRunResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' get: tags: - Continuous Eval Test Runs summary: List test runs for a continuous eval description: Get all test runs for a specific continuous eval. operationId: list_test_runs_api_v1_continuous_evals__eval_id__test_runs_get security: - API Key: [] parameters: - name: eval_id in: path required: true schema: type: string format: uuid title: Continuous Eval ID description: The id of the continuous eval. description: The id of the continuous eval. - name: sort in: query required: false schema: $ref: '#/components/schemas/PaginationSortMethod' description: Sort the results (asc/desc) default: desc description: Sort the results (asc/desc) - name: page_size in: query required: false schema: type: integer description: Page size. Default is 10. Must be greater than 0 and less than 5000. default: 10 title: Page Size description: Page size. Default is 10. Must be greater than 0 and less than 5000. - name: page in: query required: false schema: type: integer description: Page number default: 0 title: Page description: Page number responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ListContinuousEvalTestRunsResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/continuous_evals/test_runs/{test_run_id}: get: tags: - Continuous Eval Test Runs summary: Get a test run by id description: Get the status and counters for a specific test run. Use this endpoint for polling progress. operationId: get_test_run_api_v1_continuous_evals_test_runs__test_run_id__get security: - API Key: [] parameters: - name: test_run_id in: path required: true schema: type: string format: uuid title: Test Run ID description: The id of the test run. description: The id of the test run. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ContinuousEvalTestRunResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' delete: tags: - Continuous Eval Test Runs summary: Delete a test run description: Delete a test run and all its associated annotation results. operationId: delete_test_run_api_v1_continuous_evals_test_runs__test_run_id__delete security: - API Key: [] parameters: - name: test_run_id in: path required: true schema: type: string format: uuid title: Test Run ID description: The id of the test run to delete. description: The id of the test run to delete. responses: '204': description: Test run deleted. '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/continuous_evals/test_runs/{test_run_id}/results: get: tags: - Continuous Eval Test Runs summary: Get individual test case results for a test run description: Get the per-trace results of a test run, including scores, reasons, and input variables. operationId: get_test_run_results_api_v1_continuous_evals_test_runs__test_run_id__results_get security: - API Key: [] parameters: - name: test_run_id in: path required: true schema: type: string format: uuid title: Test Run ID description: The id of the test run. description: The id of the test run. - name: sort in: query required: false schema: $ref: '#/components/schemas/PaginationSortMethod' description: Sort the results (asc/desc) default: desc description: Sort the results (asc/desc) - name: page_size in: query required: false schema: type: integer description: Page size. Default is 10. Must be greater than 0 and less than 5000. default: 10 title: Page Size description: Page size. Default is 10. Must be greater than 0 and less than 5000. - name: page in: query required: false schema: type: integer description: Page number default: 0 title: Page description: Page number responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ListAgenticAnnotationsResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: AgenticAnnotationType: type: string enum: - human - continuous_eval title: AgenticAnnotationType ContinuousEvalTestRunResponse: properties: id: type: string format: uuid title: Id description: ID of the test run. continuous_eval_id: type: string format: uuid title: Continuous Eval Id description: ID of the continuous eval being tested. task_id: type: string title: Task Id description: ID of the parent task. status: $ref: '#/components/schemas/TestRunStatus' description: Status of the test run. total_count: type: integer title: Total Count description: Total number of traces in the test run. completed_count: type: integer title: Completed Count description: Number of completed test cases. passed_count: type: integer title: Passed Count description: Number of test cases that passed. failed_count: type: integer title: Failed Count description: Number of test cases that failed. error_count: type: integer title: Error Count description: Number of test cases that errored. skipped_count: type: integer title: Skipped Count description: Number of test cases that were skipped. created_at: type: string format: date-time title: Created At description: When the test run was created. updated_at: type: string format: date-time title: Updated At description: When the test run was last updated. type: object required: - id - continuous_eval_id - task_id - status - total_count - completed_count - passed_count - failed_count - error_count - skipped_count - created_at - updated_at title: ContinuousEvalTestRunResponse ContinuousEvalRunStatus: type: string enum: - pending - passed - running - failed - skipped - error title: ContinuousEvalRunStatus 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 AgenticAnnotationResponse: properties: id: type: string title: Id description: ID of the annotation annotation_type: $ref: '#/components/schemas/AgenticAnnotationType' description: Type of annotation trace_id: type: string title: Trace Id description: ID of the trace this annotation belongs to continuous_eval_id: anyOf: - type: string - type: 'null' title: Continuous Eval Id description: ID of the continuous eval this annotation belongs to continuous_eval_name: anyOf: - type: string - type: 'null' title: Continuous Eval Name description: Name of the continuous eval this annotation belongs to eval_type: anyOf: - $ref: '#/components/schemas/EvalType' - type: 'null' description: 'Type of eval: ''llm_eval'' or ''ml_eval''' eval_name: anyOf: - type: string - type: 'null' title: Eval Name description: Name of the eval the continuous eval used when scoring eval_version: anyOf: - type: integer - type: 'null' title: Eval Version description: Version of the eval the continuous eval used when scoring annotation_score: anyOf: - type: integer - type: 'null' title: Annotation Score description: Binary score for a positive or negative annotation. annotation_description: anyOf: - type: string - type: 'null' title: Annotation Description description: Description of the annotation. input_variables: anyOf: - items: $ref: '#/components/schemas/VariableTemplateValue' type: array - type: 'null' title: Input Variables description: Input variables for the continuous eval run_status: anyOf: - $ref: '#/components/schemas/ContinuousEvalRunStatus' - type: 'null' description: Status of the continuous eval run cost: anyOf: - type: number - type: 'null' title: Cost description: Cost of the continuous eval run created_at: type: string format: date-time title: Created At description: Time the annotation was created updated_at: type: string format: date-time title: Updated At description: Time the annotation was last updated type: object required: - id - annotation_type - trace_id - created_at - updated_at title: AgenticAnnotationResponse ListContinuousEvalTestRunsResponse: properties: test_runs: items: $ref: '#/components/schemas/ContinuousEvalTestRunResponse' type: array title: Test Runs description: List of test runs. count: type: integer title: Count description: Total number of test runs. type: object required: - test_runs - count title: ListContinuousEvalTestRunsResponse ListAgenticAnnotationsResponse: properties: annotations: items: $ref: '#/components/schemas/AgenticAnnotationResponse' type: array title: Annotations description: List of annotations count: type: integer title: Count description: Total number of annotations type: object required: - annotations - count title: ListAgenticAnnotationsResponse VariableTemplateValue: properties: name: type: string title: Name description: Name of the variable value: type: string title: Value description: Value of the variable type: object required: - name - value title: VariableTemplateValue HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError EvalType: type: string enum: - llm_eval - ml_eval title: EvalType CreateTestRunRequest: properties: trace_ids: items: type: string type: array maxItems: 50 minItems: 1 title: Trace Ids description: List of trace IDs to test the continuous eval against type: object required: - trace_ids title: CreateTestRunRequest description: Request schema for creating a continuous eval test run PaginationSortMethod: type: string enum: - asc - desc title: PaginationSortMethod TestRunStatus: type: string enum: - running - completed - partial_failure - error title: TestRunStatus securitySchemes: API Key: type: http description: Bearer token authentication with an API key scheme: bearer