latestOpenAPI 3.1.12026-08-2227401.1 MB

2fe02c07eb49

Evals

Creates an eval run.

post/experimental/eval-runs-v2

Headers

Authorizationstring

Request body

workspaceNamestring required
scenariosobject required

Per-scenario tarballs and fixtures, keyed by scenario path

evalRunFixturesobject
skipForcedContextActivationboolean
skipScoringboolean
agentstring
modelstring
scorerAgentstring
scorerModelstring
runsinteger
skipSolvedboolean
runQualityCheckboolean
labelstring

Response

Default Response