Skip to main content
Every task has a durable task_id. To refine, expand, or fix results, continue the same task: the agent keeps the plan, the output rows, and the task-local files.
Wait for the continue turn to finish the same way you wait for the first one: poll GET /task/{task_id} until status: "plan" and activity: "idle", or use POST /task/{task_id}/continue/stream and read events until done. See Live messages.

When to continue vs. start fresh

Continue when the user references previous work: “add a column”, “find more”, “narrow to US-only”, “fix the empty fields”. Start a new task only for unrelated work. When you continue, rewrite the user’s request into a clear instruction stating the current goal, not just their raw words.

Execute and stop

  • POST /task/{task_id}/execute pushes an existing task toward producing output from its current plan. Use it after a task has been planned but is sitting idle.
  • POST /task/{task_id}/stop stops a run and returns the task to plan.
Continuing a task keeps the model tier it started with. version is a start-only field.

Human in the loop

Let the agent ask a clarifying question first.

Live messages

Watch each turn as it happens.