ArthurAI Continuous Evals API

openapi: 3.1.0
info:
  title: Arthur GenAI Engine Agent Discovery Continuous Evals API
  version: 2.1.688
tags:
- name: Continuous Evals
paths:
  /api/v1/continuous_evals/{eval_id}:
    get:
      tags:
      - Continuous Evals
      summary: Get a continuous eval by id
      description: Get a continuous eval by id
      operationId: get_continuous_eval_by_id_api_v1_continuous_evals__eval_id__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 to retrieve.
        description: The id of the continuous eval to retrieve.
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ContinuousEvalResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    patch:
      tags:
      - Continuous Evals
      summary: Update a continuous eval
      description: Update a continuous eval
      operationId: update_continuous_eval_api_v1_continuous_evals__eval_id__patch
      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 update.
        description: The id of the continuous eval to update.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/UpdateContinuousEvalRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ContinuousEvalResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    delete:
      tags:
      - Continuous Evals
      summary: Delete a continuous eval
      description: Delete a continuous eval
      operationId: delete_continuous_eval_api_v1_continuous_evals__eval_id__delete
      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 delete.
        description: The id of the continuous eval to delete.
      responses:
        '204':
          description: Continuous eval deleted.
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/tasks/{task_id}/continuous_evals:
    get:
      tags:
      - Continuous Evals
      summary: Get all continuous evals for a specific task
      description: Get all continuous evals for a specific task
      operationId: list_continuous_evals_api_v1_tasks__task_id__continuous_evals_get
      security:
      - API Key: []
      parameters:
      - name: task_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Task Id
      - 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
      - name: name
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Name of the continuous eval to filter on.
          title: Name
        description: Name of the continuous eval to filter on.
      - name: llm_eval_name
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Name of the llm eval to filter on
          title: Llm Eval Name
        description: Name of the llm eval to filter on
      - name: created_after
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Inclusive start date for prompt creation in ISO8601 string format. Use local time (not UTC).
          title: Created After
        description: Inclusive start date for prompt creation in ISO8601 string format. Use local time (not UTC).
      - name: created_before
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Exclusive end date for prompt creation in ISO8601 string format. Use local time (not UTC).
          title: Created Before
        description: Exclusive end date for prompt creation in ISO8601 string format. Use local time (not UTC).
      - name: enabled
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Whether the continuous eval is enabled.
          title: Enabled
        description: Whether the continuous eval is enabled.
      - name: continuous_eval_ids
        in: query
        required: false
        schema:
          anyOf:
          - type: array
            items:
              type: string
          - type: 'null'
          description: List of continuous eval IDs to filter on.
          title: Continuous Eval Ids
        description: List of continuous eval IDs to filter on.
      - name: llm_eval_name_exact
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Exact LLM eval name to filter on (case-sensitive exact match).
          title: Llm Eval Name Exact
        description: Exact LLM eval name to filter on (case-sensitive exact match).
      - name: llm_eval_version
        in: query
        required: false
        schema:
          anyOf:
          - type: integer
          - type: 'null'
          description: LLM eval version to filter on.
          title: Llm Eval Version
        description: LLM eval version to filter on.
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListContinuousEvalsResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    post:
      tags:
      - Continuous Evals
      summary: Create a continuous eval
      description: Create a continuous eval
      operationId: create_continuous_eval_api_v1_tasks__task_id__continuous_evals_post
      security:
      - API Key: []
      parameters:
      - name: task_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Task Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ContinuousEvalCreateRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ContinuousEvalResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/tasks/{task_id}/continuous_evals/results:
    get:
      tags:
      - Continuous Evals
      summary: Get all continuous eval run results for a specific task
      description: Get all continuous eval run results for a specific task
      operationId: list_continuous_eval_run_results_api_v1_tasks__task_id__continuous_evals_results_get
      security:
      - API Key: []
      parameters:
      - name: task_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Task Id
      - 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
      - name: ids
        in: query
        required: false
        schema:
          anyOf:
          - type: array
            items:
              type: string
          - type: 'null'
          description: List of agentic annotation IDs to filter on.
          title: Ids
        description: List of agentic annotation IDs to filter on.
      - name: continuous_eval_ids
        in: query
        required: false
        schema:
          anyOf:
          - type: array
            items:
              type: string
          - type: 'null'
          description: List of continuous eval IDs to filter on.
          title: Continuous Eval Ids
        description: List of continuous eval IDs to filter on.
      - name: eval_name
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Name of the continuous eval to filter on.
          title: Eval Name
        description: Name of the continuous eval to filter on.
      - name: trace_ids
        in: query
        required: false
        schema:
          anyOf:
          - type: array
            items:
              type: string
          - type: 'null'
          description: List of trace IDs to filter on.
          title: Trace Ids
        description: List of trace IDs to filter on.
      - name: annotation_score
        in: query
        required: false
        schema:
          anyOf:
          - type: integer
          - type: 'null'
          description: Annotation score to filter on.
          title: Annotation Score
        description: Annotation score to filter on.
      - name: run_status
        in: query
        required: false
        schema:
          anyOf:
          - $ref: '#/components/schemas/ContinuousEvalRunStatus'
          - type: 'null'
          description: Run status to filter on.
          title: Run Status
        description: Run status to filter on.
      - name: created_after
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Inclusive start date for prompt creation in ISO8601 string format. Use local time (not UTC).
          title: Created After
        description: Inclusive start date for prompt creation in ISO8601 string format. Use local time (not UTC).
      - name: created_before
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Exclusive end date for prompt creation in ISO8601 string format. Use local time (not UTC).
          title: Created Before
        description: Exclusive end date for prompt creation in ISO8601 string format. Use local time (not UTC).
      - name: continuous_eval_enabled
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Whether the continuous eval is enabled.
          title: Continuous Eval Enabled
        description: Whether the continuous eval is enabled.
      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'
  /api/v1/tasks/{task_id}/continuous_evals/transforms/{transform_id}/llm_evals/{eval_name}/versions/{eval_version}/variables:
    get:
      tags:
      - Continuous Evals
      summary: Get all variables and mappings for a continuous eval
      description: Get all variables and mappings for a continuous eval
      operationId: get_continuous_eval_variables_and_mappings_api_v1_tasks__task_id__continuous_evals_transforms__transform_id__llm_evals__eval_name__versions__eval_version__variables_get
      security:
      - API Key: []
      parameters:
      - name: transform_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Transform ID
          description: The id of the transform to get the continuous eval variables and mappings for.
        description: The id of the transform to get the continuous eval variables and mappings for.
      - name: eval_name
        in: path
        required: true
        schema:
          type: string
          title: Eval Name
      - name: eval_version
        in: path
        required: true
        schema:
          type: string
          title: Eval Version
          description: The version of the eval to get the continuous eval variables and mappings for.
        description: The version of the eval to get the continuous eval variables and mappings for.
      - name: task_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Task Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ContinuousEvalVariableMappingResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/continuous_evals/results/{run_id}/rerun:
    post:
      tags:
      - Continuous Evals
      summary: Rerun a failed continuous eval
      description: Rerun a failed continuous eval
      operationId: rerun_continuous_eval_api_v1_continuous_evals_results__run_id__rerun_post
      security:
      - API Key: []
      parameters:
      - name: run_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Run ID
          description: The id of the continuous eval run to rerun.
        description: The id of the continuous eval run to rerun.
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ContinuousEvalRerunResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/tasks/{task_id}/continuous_evals/analytics/daily:
    get:
      tags:
      - Continuous Evals
      summary: Get daily aggregated analytics for agentic annotations
      description: Returns daily counts of passed/failed/error/skipped annotations and total cost per day
      operationId: get_daily_annotation_analytics_api_v1_tasks__task_id__continuous_evals_analytics_daily_get
      security:
      - API Key: []
      parameters:
      - name: task_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Task Id
      - name: start_time
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          description: Start time (inclusive). Defaults to 30 days ago.
          title: Start Time
        description: Start time (inclusive). Defaults to 30 days ago.
      - name: end_time
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          description: End time (exclusive). Defaults to now.
          title: End Time
        description: End time (exclusive). Defaults to now.
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AgenticAnnotationAnalyticsResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    AgenticAnnotationType:
      type: string
      enum:
      - human
      - continuous_eval
      title: AgenticAnnotationType
    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
    ListContinuousEvalsResponse:
      properties:
        evals:
          items:
            $ref: '#/components/schemas/ContinuousEvalResponse'
          type: array
          title: Evals
          description: List of continuous evals.
        count:
          type: integer
          title: Count
          description: Total number of evals
      type: object
      required:
      - evals
      - count
      title: ListContinuousEvalsResponse
    DailyAgenticAnnotationStats:
      properties:
        date:
          type: string
          title: Date
          description: Date in YYYY-MM-DD format
        passed_count:
          type: integer
          title: Passed Count
          description: Count of annotations with score=1
        failed_count:
          type: integer
          title: Failed Count
          description: Count of annotations with score=0
        error_count:
          type: integer
          title: Error Count
          description: Count of annotations with run_status='error'
        skipped_count:
          type: integer
          title: Skipped Count
          description: Count of annotations with run_status='skipped'
        total_cost:
          type: number
          title: Total Cost
          description: Total cost for the day
        total_count:
          type: integer
          title: Total Count
          description: Total annotations for the day
      type: object
      required:
      - date
      - passed_count
      - failed_count
      - error_count
      - skipped_count
      - total_cost
      - total_count
      title: DailyAgenticAnnotationStats
      description: Statistics for a single day of agentic annotations.
    ContinuousEvalTransformVariableMappingResponse:
      properties:
        transform_variable:
          type: string
          title: Transform Variable
          description: Name of the transform variable.
        eval_variable:
          type: string
          title: Eval Variable
          description: Name of the eval variable.
      type: object
      required:
      - transform_variable
      - eval_variable
      title: ContinuousEvalTransformVariableMappingResponse
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    UpdateContinuousEvalRequest:
      properties:
        name:
          anyOf:
          - type: string
          - type: 'null'
          title: Name
          description: Name of the continuous eval
        description:
          anyOf:
          - type: string
          - type: 'null'
          title: Description
          description: Description of the continuous eval
        llm_eval_name:
          anyOf:
          - type: string
          - type: 'null'
          title: Llm Eval Name
          description: Name of the llm eval to create the continuous eval for
        llm_eval_version:
          anyOf:
          - type: string
          - type: integer
          - type: 'null'
          title: Llm Eval Version
          description: Version of the llm eval to create the continuous eval for. Can be 'latest', a version number (e.g. '1', '2', etc.), an ISO datetime string (e.g. '2025-01-01T00:00:00'), or a tag.
        transform_id:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Transform Id
          description: ID of the transform to create the continuous eval for
        transform_version_id:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Transform Version Id
          description: ID of the transform version to pin. When set, the continuous eval will always execute using this version's configuration snapshot.
        transform_variable_mapping:
          anyOf:
          - items:
              $ref: '#/components/schemas/ContinuousEvalTransformVariableMappingRequest'
            type: array
          - type: 'null'
          title: Transform Variable Mapping
          description: Mapping of transform variables to eval variables.
        enabled:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Enabled
          description: Whether to enable or disable a continuous eval.
      type: object
      title: UpdateContinuousEvalRequest
      description: Request schema for creating a continuous eval
    ContinuousEvalVariableMappingResponse:
      properties:
        matching_variables:
          items:
            type: string
          type: array
          title: Matching Variables
          description: List of matching variables.
        transform_variables:
          items:
            type: string
          type: array
          title: Transform Variables
          description: List of transform variables.
        eval_variables:
          items:
            type: string
          type: array
          title: Eval Variables
          description: List of eval variables.
      type: object
      required:
      - matching_variables
      - transform_variables
      - eval_variables
      title: ContinuousEvalVariableMappingResponse
    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
    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
    EvalType:
      type: string
      enum:
      - llm_eval
      - ml_eval
      title: EvalType
    PaginationSortMethod:
      type: string
      enum:
      - asc
      - desc
      title: PaginationSortMethod
    ContinuousEvalResponse:
      properties:
        id:
          type: string
          format: uuid
          title: Id
          description: ID of the transform.
        name:
          type: string
          title: Name
          description: Name of the continuous eval.
        description:
          anyOf:
          - type: string
          - type: 'null'
          title: Description
          description: Description of the continuous eval.
        task_id:
          type: string
          title: Task Id
          description: ID of the parent task.
        eval_type:
          $ref: '#/components/schemas/EvalType'
          description: 'Type of evaluator: ''llm_eval'' or ''ml_eval''.'
          default: llm_eval
        llm_eval_name:
          anyOf:
          - type: string
          - type: 'null'
          title: Llm Eval Name
          description: Name of the eval.
        llm_eval_version:
          anyOf:
          - type: integer
          - type: 'null'
          title: Llm Eval Version
          description: Version of the eval.
        transform_id:
          type: string
          format: uuid
          title: Transform Id
          description: ID of the transform.
        transform_version_id:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Transform Version Id
          description: ID of the pinned transform version. When set, the continuous eval will always execute using this version's configuration snapshot.
        transform_variable_mapping:
          items:
            $ref: '#/components/schemas/ContinuousEvalTransformVariableMappingResponse'
          type: array
          title: Transform Variable Mapping
          description: Mapping of transform variables to eval variables.
        enabled:
          type: boolean
          title: Enabled
          description: Whether the continuous eval is enabled.
          default: true
        created_at:
          type: string
          format: date-time
          title: Created At
          description: Timestamp representing the time the transform was added to the llm eval.
        updated_at:
          type: string
          format: date-time
          title: Updated At
          description: Timestamp representing the time the continuous eval was last updated.
      type: object
      required:
      - id
      - name
      - task_id
      - transform_id
      - created_at
      - updated_at
      title: ContinuousEvalResponse
    AgenticAnnotationAnalyticsResponse:
      properties:
        stats:
          items:
            $ref: '#/components/schemas/DailyAgenticAnnotationStats'
          type: array
          title: Stats
          description: Daily statistics ordered by date descending
        count:
          type: integer
          title: Count
          description: Number of days with data
      type: object
      required:
      - stats
      - count
      title: AgenticAnnotationAnalyticsResponse
      description: Response containing daily aggregated statistics.
    ContinuousEvalCreateRequest:
      properties:
        name:
          type: string
          title: Name
          description: Name of the continuous eval
        description:
          anyOf:
          - type: string
          - type: 'null'
          title: Description
          description: Description of the continuous eval
        eval_type:
          type: string
          enum:
          - llm_eval
          - ml_eval
          title: Eval Type
          description: 'Type of evaluator: ''llm_eval'' or ''ml_eval''.'
          default: llm_eval
        llm_eval_name:
          type: string
          title: Llm Eval Name
          description: Name of the eval to create the continuous eval for
        llm_eval_version:
          anyOf:
          - type: string
          - type: integer
          - type: 'null'
          title: Llm Eval Version
          description: Version of the eval. Can be 'latest', a version number, an ISO datetime string, or a tag.
        transform_id:
          type: string
          format: uuid
          title: Transform Id
          description: ID of the transform to create the continuous eval for
        transform_version_id:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Transform Version Id
          description: ID of the transform version to pin. When set, the continuous eval will always execute using this version's configuration snapshot.
        transform_variable_mapping:
          items:
            $ref: '#/components/schemas/ContinuousEvalTransformVariableMappingRequest'
          type: array
          title: Transform Variable Mapping
          description: Mapping of transform variables to eval variables.
        enabled:
          type: boolean
          title: Enabled
          description: Whether to enable or disable a continuous eval. Defaults to True.
          default: true
      type: object
      required:
      - name
      - llm_eval_name
      - transform_id
      - transform_variable_mapping
      title: ContinuousEvalCreateRequest
      description: Request schema for creating a continuous eval
    ListAgent

# --- truncated at 32 KB (33 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/arthurai/refs/heads/main/openapi/arthurai-continuous-evals-api-openapi.yml