latestOpenAPI 3.1.0raw.githubusercontent.com2026-08-16142191531.5 KB

f338eb09898f

Evals

Request insights for an eval run

Spends. Runs a model over the finished run and draws on the same shared insightsPerDay ledger as swarm and user-testing insights.

202: scheduled, not done. Poll the run detail's insights envelope rather than re-requesting — the envelope's status distinguishes pending from not_requested, which a second POST would not.

post/projects/{projectId}/eval-runs/{runId}/insights

Request body

forceboolean

Regenerate even when insights already exist. SPENDS AGAIN. Must be a real boolean — "false" is rejected rather than read as consent.

Response

Scheduled.

runIdstring required

projectIdstring required

status'pending' required