The
tasks functions are currently in BETA. The API may change without notice. A one-time warning is emitted on first use.List Tasks
Create a Task
Tasks run LLM-as-judge evaluators over project spans (online monitoring) or dataset examples (offline batch evaluation). Exactly one ofproject or dataset must be provided.
Project-scoped task (continuous monitoring)
Dataset-scoped task (batch evaluation)
Create an Evaluation Task
Ergonomic helper for creatingTEMPLATE_EVALUATION or CODE_EVALUATION tasks. Equivalent to createTask but rejects unsupported types up-front.
Create a Run Experiment Task
Ergonomic helper for creatingRUN_EXPERIMENT tasks. The server drives all LLM calls using the AI integration specified in runConfiguration. Resolves aiIntegration by name (use ai_integration_id directly when calling createTask).
Get a Task
Update a Task
Delete a Task
Trigger a Task Run
List Task Runs
Get a Task Run
Wait for a Task Run
Poll until the run reaches a terminal status (COMPLETED, FAILED, or CANCELLED).
Cancel a Task Run
Only valid for runs with statusPENDING or RUNNING.