Unisson agent-evals API

The agent-evals API from Unisson — 5 operation(s) for agent-evals.

OpenAPI Specification

unisson-agent-evals-api-openapi.yml Raw ↑
openapi: 3.1.0
info:
  title: Unisson agent-evals API
  version: 1.0.0
tags:
- name: agent-evals
paths:
  /api/v1/agents/{agent_id}/test-cases:
    get:
      tags:
      - agent-evals
      summary: List Test Cases
      operationId: list_test_cases_api_v1_agents__agent_id__test_cases_get
      security:
      - HTTPBearer: []
      parameters:
      - name: agent_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Agent Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/TestCaseResponse'
                title: Response List Test Cases Api V1 Agents  Agent Id  Test Cases Get
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    post:
      tags:
      - agent-evals
      summary: Create Test Case
      operationId: create_test_case_api_v1_agents__agent_id__test_cases_post
      security:
      - HTTPBearer: []
      parameters:
      - name: agent_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Agent Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TestCaseCreate'
      responses:
        '201':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TestCaseResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/agents/{agent_id}/test-cases/{case_id}:
    patch:
      tags:
      - agent-evals
      summary: Update Test Case
      operationId: update_test_case_api_v1_agents__agent_id__test_cases__case_id__patch
      security:
      - HTTPBearer: []
      parameters:
      - name: agent_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Agent Id
      - name: case_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Case Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TestCaseUpdate'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TestCaseResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    delete:
      tags:
      - agent-evals
      summary: Delete Test Case
      operationId: delete_test_case_api_v1_agents__agent_id__test_cases__case_id__delete
      security:
      - HTTPBearer: []
      parameters:
      - name: agent_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Agent Id
      - name: case_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Case Id
      responses:
        '204':
          description: Successful Response
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/agents/{agent_id}/eval-runs:
    post:
      tags:
      - agent-evals
      summary: Create Eval Run
      operationId: create_eval_run_api_v1_agents__agent_id__eval_runs_post
      security:
      - HTTPBearer: []
      parameters:
      - name: agent_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Agent Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateEvalRunRequest'
      responses:
        '201':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EvalRunResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    get:
      tags:
      - agent-evals
      summary: List Eval Runs
      operationId: list_eval_runs_api_v1_agents__agent_id__eval_runs_get
      security:
      - HTTPBearer: []
      parameters:
      - name: agent_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Agent Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/EvalRunResponse'
                title: Response List Eval Runs Api V1 Agents  Agent Id  Eval Runs Get
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/agents/{agent_id}/eval-runs/{run_id}/cancel:
    post:
      tags:
      - agent-evals
      summary: Cancel Eval Run
      operationId: cancel_eval_run_api_v1_agents__agent_id__eval_runs__run_id__cancel_post
      security:
      - HTTPBearer: []
      parameters:
      - name: agent_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Agent Id
      - name: run_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Run Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EvalRunResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/agents/{agent_id}/eval-runs/{run_id}:
    get:
      tags:
      - agent-evals
      summary: Get Eval Run
      operationId: get_eval_run_api_v1_agents__agent_id__eval_runs__run_id__get
      security:
      - HTTPBearer: []
      parameters:
      - name: agent_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Agent Id
      - name: run_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Run Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EvalRunDetailResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    EvalRunDetailResponse:
      properties:
        id:
          type: string
          format: uuid
          title: Id
        agent_id:
          type: string
          format: uuid
          title: Agent Id
        instruction_version_id:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Instruction Version Id
        trigger_source:
          type: string
          title: Trigger Source
        execution_mode:
          type: string
          title: Execution Mode
        status:
          type: string
          title: Status
        summary:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Summary
        error:
          anyOf:
          - type: string
          - type: 'null'
          title: Error
        created_at:
          type: string
          format: date-time
          title: Created At
        completed_at:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Completed At
        results:
          items:
            $ref: '#/components/schemas/EvalCaseResultResponse'
          type: array
          title: Results
          default: []
      type: object
      required:
      - id
      - agent_id
      - trigger_source
      - execution_mode
      - status
      - created_at
      title: EvalRunDetailResponse
    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
    TestCaseCreate:
      properties:
        name:
          type: string
          maxLength: 255
          title: Name
        input_message:
          type: string
          title: Input Message
        criteria:
          items:
            $ref: '#/components/schemas/EvalCriterion'
          type: array
          title: Criteria
          default: []
      type: object
      required:
      - name
      - input_message
      title: TestCaseCreate
    EvalCriterion:
      properties:
        id:
          type: string
          title: Id
        kind:
          type: string
          title: Kind
        text:
          type: string
          title: Text
      type: object
      required:
      - id
      - kind
      - text
      title: EvalCriterion
    CreateEvalRunRequest:
      properties:
        execution_mode:
          type: string
          title: Execution Mode
          default: sandboxed
      type: object
      title: CreateEvalRunRequest
    TestCaseUpdate:
      properties:
        name:
          anyOf:
          - type: string
            maxLength: 255
          - type: 'null'
          title: Name
        input_message:
          anyOf:
          - type: string
          - type: 'null'
          title: Input Message
        criteria:
          anyOf:
          - items:
              $ref: '#/components/schemas/EvalCriterion'
            type: array
          - type: 'null'
          title: Criteria
        is_enabled:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Is Enabled
      type: object
      title: TestCaseUpdate
    TestCaseResponse:
      properties:
        id:
          type: string
          format: uuid
          title: Id
        agent_id:
          type: string
          format: uuid
          title: Agent Id
        name:
          type: string
          title: Name
        input_message:
          type: string
          title: Input Message
        criteria:
          items:
            additionalProperties: true
            type: object
          type: array
          title: Criteria
          default: []
        is_enabled:
          type: boolean
          title: Is Enabled
        created_at:
          type: string
          format: date-time
          title: Created At
      type: object
      required:
      - id
      - agent_id
      - name
      - input_message
      - is_enabled
      - created_at
      title: TestCaseResponse
    EvalCaseResultResponse:
      properties:
        id:
          type: string
          format: uuid
          title: Id
        test_case_id:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Test Case Id
        case_name:
          type: string
          title: Case Name
        input_message:
          type: string
          title: Input Message
        conversation_id:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Conversation Id
        verdict:
          anyOf:
          - type: string
          - type: 'null'
          title: Verdict
        score:
          anyOf:
          - type: number
          - type: 'null'
          title: Score
        criteria_results:
          anyOf:
          - items:
              additionalProperties: true
              type: object
            type: array
          - type: 'null'
          title: Criteria Results
        tool_calls:
          anyOf:
          - items:
              additionalProperties: true
              type: object
            type: array
          - type: 'null'
          title: Tool Calls
        judge_reasoning:
          anyOf:
          - type: string
          - type: 'null'
          title: Judge Reasoning
        status:
          type: string
          title: Status
        error:
          anyOf:
          - type: string
          - type: 'null'
          title: Error
      type: object
      required:
      - id
      - case_name
      - input_message
      - status
      title: EvalCaseResultResponse
    EvalRunResponse:
      properties:
        id:
          type: string
          format: uuid
          title: Id
        agent_id:
          type: string
          format: uuid
          title: Agent Id
        instruction_version_id:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Instruction Version Id
        trigger_source:
          type: string
          title: Trigger Source
        execution_mode:
          type: string
          title: Execution Mode
        status:
          type: string
          title: Status
        summary:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Summary
        error:
          anyOf:
          - type: string
          - type: 'null'
          title: Error
        created_at:
          type: string
          format: date-time
          title: Created At
        completed_at:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Completed At
      type: object
      required:
      - id
      - agent_id
      - trigger_source
      - execution_mode
      - status
      - created_at
      title: EvalRunResponse
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
  securitySchemes:
    HTTPBearer:
      type: http
      scheme: bearer