> ## Documentation Index > Fetch the complete documentation index at: https://traceroot.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Read an evaluation run's summary > Read a run's own summary: status, result counts, and per-score and per-metric means over the run's results. Typed rather than left to the catch-all so it appears in the published OpenAPI: an endpoint a CLI is expected to call must be in the contract the CLI generates from. Summary only, so the response is bounded by scorer count rather than case count. Comparing two runs is not part of this read. It is a different question with its own trust rules, and an optional parameter here would be too easily confused with the baseline a run stores at registration. ## OpenAPI ````yaml /api-reference/openapi.json get /api/v1/public/evaluation-runs/{run_id} openapi: 3.1.0 info: title: TraceRoot Public API version: 0.1.0 servers: - description: TraceRoot Cloud url: https://app.traceroot.ai - description: Self-hosted url: '{baseUrl}' variables: baseUrl: default: http://localhost:8000 description: Your TraceRoot backend URL security: [] paths: /api/v1/public/evaluation-runs/{run_id}: get: tags: - Offline Eval summary: Read an evaluation run's summary description: >- Read a run's own summary: status, result counts, and per-score and per-metric means over the run's results. Typed rather than left to the catch-all so it appears in the published OpenAPI: an endpoint a CLI is expected to call must be in the contract the CLI generates from. Summary only, so the response is bounded by scorer count rather than case count. Comparing two runs is not part of this read. It is a different question with its own trust rules, and an optional parameter here would be too easily confused with the baseline a run stores at registration. operationId: read_run parameters: - in: path name: run_id required: true schema: title: Run Id type: string - description: >- Target project for the request. Required when authenticating with a user session token (a user credential is only meaningful scoped to a project); for an API key it is optional and, if given, must match the key's project. in: query name: project_id required: false schema: anyOf: - type: string - type: 'null' description: >- Target project for the request. Required when authenticating with a user session token (a user credential is only meaningful scoped to a project); for an API key it is optional and, if given, must match the key's project. title: Project Id responses: '200': content: application/json: schema: $ref: '#/components/schemas/ReadRunResponse' description: Successful Response '400': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Invalid request '401': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Authentication failed '403': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: >- No access to this project, or the run is outside the plan's retention window '404': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Not found '422': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Validation error '429': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Rate limit exceeded '503': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Authentication service unavailable security: - BearerAuth: [] components: schemas: ReadRunResponse: description: >- A run's SUMMARY — deliberately no per-case rows, so the payload is bounded by scorer count rather than case count and needs no truncation flag. properties: candidate_version: title: Candidate Version type: string completed_at: anyOf: - type: string - type: 'null' title: Completed At dataset_id: title: Dataset Id type: string dataset_version_id: title: Dataset Version Id type: string environment: title: Environment type: string errored_count: maximum: 9007199254740991 minimum: 0 title: Errored Count type: integer evaluation_id: title: Evaluation Id type: string evaluation_key: anyOf: - type: string - type: 'null' title: Evaluation Key evaluation_name: title: Evaluation Name type: string evaluation_run_id: title: Evaluation Run Id type: string failed_count: maximum: 9007199254740991 minimum: 0 title: Failed Count type: integer metrics: items: $ref: '#/components/schemas/RunMetricItem' title: Metrics type: array not_scored_count: maximum: 9007199254740991 minimum: 0 title: Not Scored Count type: integer passed_count: maximum: 9007199254740991 minimum: 0 title: Passed Count type: integer result_count: maximum: 9007199254740991 minimum: 0 title: Result Count type: integer run_number: title: Run Number type: integer run_path: title: Run Path type: string run_url: title: Run Url type: string scored_count: anyOf: - maximum: 9007199254740991 minimum: 0 type: integer - type: 'null' title: Scored Count scorer_error_count: anyOf: - maximum: 9007199254740991 minimum: 0 type: integer - type: 'null' title: Scorer Error Count scores: items: $ref: '#/components/schemas/RunMetricItem' title: Scores type: array started_at: title: Started At type: string status: enum: - running - completed - completed_with_errors - failed - incomplete - cancelled title: Status type: string task_error_count: anyOf: - maximum: 9007199254740991 minimum: 0 type: integer - type: 'null' title: Task Error Count required: - evaluation_run_id - evaluation_id - evaluation_name - run_number - candidate_version - environment - status - started_at - dataset_id - dataset_version_id - run_path - run_url - result_count - scored_count - task_error_count - scorer_error_count - passed_count - failed_count - errored_count - not_scored_count title: ReadRunResponse type: object ErrorResponse: description: >- The canonical public error envelope (matches the gateway's normalized shape). properties: detail: title: Detail type: string required: - detail title: ErrorResponse type: object RunMetricItem: description: >- One score or one derived metric. Identical shape for both: they differ in PROVENANCE (a scorer reported it vs the platform derived it from the trace), not in structure, and a client renders them the same way. ``value`` is the run's own mean over ``observed_count`` results, and null rather than 0 when nothing was observed — "no data" and "measured zero" are different facts and must stay distinguishable. properties: direction: enum: - higher_is_better - lower_is_better - none title: Direction type: string name: title: Name type: string observed_count: description: How many results reported a usable value for this score or metric. maximum: 9007199254740991 minimum: 0 title: Observed Count type: integer unit: anyOf: - enum: - $ - tok - ms - count type: string - type: 'null' title: Unit value: anyOf: - type: number - type: 'null' description: >- The run's own mean over observed_count results. Null when nothing was observed, and always for a categorical score or one that stored labels and numbers together. title: Value value_type: description: >- The scorer's declared kind, else the kind it stored. Every derived metric is numeric. enum: - numeric - boolean - categorical title: Value Type type: string required: - name - direction - value_type - observed_count title: RunMetricItem type: object securitySchemes: BearerAuth: scheme: bearer type: http ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.