Start TaskAgent Eval Run
Create a TaskAgent eval run and enqueue background execution. Callers are responsible for understanding candidate run side effects, external tool or integration mutations, and quota usage before starting an eval.
Authentication
AuthorizationBearer
Bearer token authentication using JWT tokens from Ory Kratos/Hydra
Path parameters
org_id
The organization ID
project_id
The project ID
task_agent_id
The task agent ID
Request
This endpoint expects an object.
candidate_revision_id
eval_set_id
task_agent_run_ids
last_n
judge_model_id
Response
Successful Response
id
task_agent_id
project_id
candidate_revision_id
status
Status of a TaskAgent eval run.
pass_count
fail_count
error_count
created
modified
task_agent_run_ids
pass_rate
eval_set_id
started_at
completed_at
last_activity_at
error_message
created_by_user_id
Errors
400
Bad Request Error
403
Forbidden Error
404
Not Found Error
422
Unprocessable Entity Error
503
Service Unavailable Error
