USusesapient
Eval Results

List Eval History

Returns eval result history with limit-and-offset pagination, filtering, and sorting. Runs that ended because of infrastructure failures are excluded.

get/v1/api-performance/custom-evals/history

Request

  • Base URL
    https://api.lightsage.com
  • Auth
    API key in header X-Lightsage-Api-Key

Query parameters

custom_eval_idstring

Filter results to one eval from GET /v1/api-performance/custom-evals. This filter also limits the target and category facet values.

limitinteger

Maximum number of results to return.

offsetinteger

Number of matching results to skip.

searchstring

Case-insensitive substring match on prompt, description, category, target labels, and prompt_sent.

result_filter'all' | 'passed' | 'failed'

Filter returned results by pass or fail status. Facet counts remain based on all results for the selected evals.

target_keystring

Filter by a public target key returned in facets.targets.

category_idstring

Filter by a category ID returned in facets.categories.

sort_by'time' | 'use_case' | 'target' | 'result' | 'score' | 'tool_calls' | 'latency'

Field used to order results. time uses run_at, use_case uses the prompt, target uses the display label, and result uses the pass/fail value.

sort_dir'asc' | 'desc'

Sort results in ascending or descending order.

Response

Successful Response

totalinteger required

Ignores limit and offset.

limitinteger required
offsetinteger required
hide_infra_errorsboolean

Always true on the public API.

Changes

No operation changes recorded.