Get a run
Fetch one run by id. By default this returns core metadata plus terminal output/error fields. Pass ?expand=input,usage,execution,debug to include detailed sub-objects; expand=execution is also where embedded review and expected artifacts appear.
Authorizations
API key issued from Settings → API Keys. Pass as Authorization: Bearer <key>.
Path Parameters
Run id
Query Parameters
Optional sections: input, usage, execution, debug. Terminal runs always include top-level output, files, and error.
Response
Run detail. Expanded sections appear only when requested.
workflow, agent True when the run has reached a terminal status.
Deterministic pseudo-random rank in [0, 1) for this run within the tenant. Use with a sample rate threshold to review a stable subset.
0 <= x <= 1Slim execution metadata always present. Pass expand=execution to replace with full RunExecution (WorkflowRunExecution or AgentRunExecution depending on run type).
- Option 1
- Option 2
- Option 3
Present only when the run is eval-scoped.
Completed runs only.
Completed runs only. Download with GET /api/v1/runs/:id/artifacts/:path.
Terminal failure message. Null when the run succeeded or is still in flight.
expand=input.
expand=usage. Null for old runs without telemetry.
expand=debug.