judges

List judge evaluation runs

Paginated history of this judge's evaluations, newest first. Optional status_filter narrows to queued, running, completed, or failed states. low_score_only keeps rows whose score is below low_score_threshold_pct of the rubric maximum. Each row links back to the evaluated agent run and includes reasoning text, token usage, and judge token cost.

Required permission: judges.view.

get/v1/projects/{project_id}/judges/{judge_id}/runs

Request

  • Base URL: https://api.connic.co
  • URL: https://api.connic.co/v1/projects/{project_id}/judges/{judge_id}/runs
  • Auth: HTTP bearer

Path parameters

project_idstring uuid required

ID of the project the API key belongs to.

judge_idstring uuid required

Judge ID from GET /judges.

Query parameters

limitinteger

Page size, 1 to 100.

offsetinteger

Number of evaluations to skip.

status_filterJudgeRunStatus[] nullable

Only evaluations in these statuses.

low_score_onlyboolean

Only scored evaluations whose overall score is below low_score_threshold_pct percent of the maximum.

low_score_threshold_pctnumber

Percentage of the maximum score used by low_score_only, 0 to 100.

convert_costs_to'EUR' | 'USD' nullable

Convert token costs to EUR or USD at the daily ECB reference rate of each model call

Response

Successful Response

totalinteger required

Number of evaluations matching the filters.

limitinteger required

Page size used for this response.

offsetinteger required

Number of evaluations skipped.

Changes

No recorded changes to this operation across all 2 revisions of this API.