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

# GetEvalRunAPI mirrors erdo_get_eval_run.




## OpenAPI

````yaml /api/openapi.json get /v1/evals/runs/{runID}
openapi: 3.0.0
info:
  title: Erdo API
  description: >-
    Erdo's REST API: query and write datasets, run agents, manage threads,
    integrations, pages, evals, workstreams, and experiments. Authenticate with
    a Bearer API key (erdo_api_...) or scoped token (erdo_token_...).
  version: '2026-07-25'
servers:
  - url: https://api.erdo.ai
    description: Production
security:
  - bearerAuth: []
paths:
  /v1/evals/runs/{runID}:
    get:
      summary: |
        GetEvalRunAPI mirrors erdo_get_eval_run.
      operationId: GET:mcp.GetEvalRunAPI
      parameters:
        - allowEmptyValue: true
          explode: false
          in: path
          name: runID
          required: true
          schema:
            type: string
          style: simple
      responses:
        '200':
          content:
            application/json:
              schema:
                properties:
                  cases:
                    items:
                      $ref: '#/components/schemas/types.EvalCase'
                    type: array
                  results:
                    items:
                      $ref: '#/components/schemas/types.EvalCaseResult'
                    type: array
                  run:
                    $ref: '#/components/schemas/types.EvalRun'
                type: object
          description: Success response
        default:
          $ref: '#/components/responses/APIError'
components:
  schemas:
    types.EvalCase:
      properties:
        context:
          type: object
        created_at:
          format: date-time
          type: string
        evaluators:
          items:
            $ref: '#/components/schemas/types.Evaluator'
          type: array
        id:
          format: uuid
          type: string
        input:
          type: string
        name:
          type: string
        rubric:
          items:
            $ref: '#/components/schemas/types.RubricCriterion'
          type: array
        suite_id:
          format: uuid
          type: string
        tags:
          items:
            type: string
          type: array
        updated_at:
          format: date-time
          type: string
      title: |
        Case is one prompt + rubric the judge scores against.
      type: object
    types.EvalCaseResult:
      properties:
        agent_error:
          type: string
        agent_output:
          type: string
        agent_run_id:
          format: uuid
          type: string
        artifact_id:
          format: uuid
          type: string
        case_id:
          format: uuid
          type: string
        cost_millicents:
          format: int64
          type: integer
        created_at:
          format: date-time
          type: string
        duration_ms:
          format: int32
          maximum: 2147483647
          minimum: -2147483648
          type: integer
        eval_run_id:
          format: uuid
          type: string
        id:
          format: uuid
          type: string
        judge_criteria_scores:
          items:
            $ref: '#/components/schemas/types.JudgeCriterionScore'
          type: array
        judge_reasoning:
          type: string
        passed:
          type: boolean
        score:
          type: number
        thread_id:
          format: uuid
          type: string
        tokens_used:
          format: int32
          maximum: 2147483647
          minimum: -2147483648
          type: integer
      title: |
        CaseResult is the outcome of one case within one eval run.
      type: object
    types.EvalRun:
      properties:
        agent_model:
          type: string
        avg_score:
          type: number
        commit_sha:
          type: string
        completed_at:
          format: date-time
          type: string
        created_by_user_id:
          format: uuid
          type: string
        id:
          format: uuid
          type: string
        organization_id:
          format: uuid
          type: string
        passed_cases:
          format: int32
          maximum: 2147483647
          minimum: -2147483648
          type: integer
        started_at:
          format: date-time
          type: string
        status:
          type: string
        suite_id:
          format: uuid
          type: string
        thread_id:
          format: uuid
          type: string
        total_cases:
          format: int32
          maximum: 2147483647
          minimum: -2147483648
          type: integer
        total_cost_millicents:
          format: int64
          type: integer
        total_duration_ms:
          format: int64
          type: integer
        triggered_by:
          type: string
      title: |
        Run is one execution of a suite.
      type: object
    types.Evaluator:
      description: >
        llm\_rubric evaluator (from the case rubric); set evaluators explicitly
        to mix cheap deterministic checks with LLM judging.

          - "llm\_rubric": an LLM scores the agent output (or the rendered page when the suite has evaluate\_artifact) against Rubric.
          - "script": a JS function \`evaluate(ctx)\` run via jsexec returns {score:0-5, passed:bool, reasoning:string}. ctx = {input, output, artifact, data\_store}. No LLM tokens — use it to assert on output/artifact/persisted data deterministically.
      properties:
        rubric:
          items:
            $ref: '#/components/schemas/types.RubricCriterion'
          type: array
        script:
          type: string
        type:
          type: string
        weight:
          type: number
      title: |
        Evaluator is one scoring step for a case. Cases default to a single
      type: object
    types.RubricCriterion:
      description: |
        0-5 per criterion; the final score is a weight-normalised average.
      properties:
        criterion:
          type: string
        weight:
          type: number
      title: >
        RubricCriterion is one scoring dimension for an eval case. The judge
        scores
      type: object
    types.JudgeCriterionScore:
      properties:
        criterion:
          type: string
        reasoning:
          type: string
        score:
          type: number
        weight:
          type: number
      title: |
        JudgeCriterionScore is what the judge returns per criterion.
      type: object
  responses:
    APIError:
      content:
        application/json:
          schema:
            externalDocs:
              url: https://pkg.go.dev/encore.dev/beta/errs#Error
            properties:
              code:
                description: Error code
                example: not_found
                externalDocs:
                  url: https://pkg.go.dev/encore.dev/beta/errs#ErrCode
                type: string
              details:
                description: Error details
                type: object
              message:
                description: Error message
                type: string
            title: APIError
            type: object
      description: Error response
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: An Erdo API key (erdo_api_...) or scoped token (erdo_token_...).

````