TRtraceroot
Offline Eval

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.

get/api/v1/public/evaluation-runs/{run_id}

Request

  • Base URL
    https://app.traceroot.ai
  • URL
    https://app.traceroot.ai/api/v1/public/evaluation-runs/{run_id}
  • Auth
    HTTP bearer

Path parameters

run_idstring required

Query parameters

project_idstring nullable

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.

Response

Successful Response

candidate_versionstring required
completed_atstring nullable
dataset_idstring required
dataset_version_idstring required
environmentstring required
errored_countinteger required
evaluation_idstring required
evaluation_keystring nullable
evaluation_namestring required
evaluation_run_idstring required
failed_countinteger required
not_scored_countinteger required
passed_countinteger required
result_countinteger required
run_numberinteger required
run_pathstring required
run_urlstring required
scored_countinteger nullable required
scorer_error_countinteger nullable required
started_atstring required
status'running' | 'completed' | 'completed_with_errors' | 'failed' | 'incomplete' | 'cancelled' required
task_error_countinteger nullable required

Changes

No recorded changes to this operation across all 1 revision of this API.