Agents

Steer Agent Work Item

Redirect a RUNNING work item at its next safe step boundary.

Not mid-step - that is what makes steering safe at all. The instruction is picked up when the agent reaches a boundary, so a steer sent during a long tool call lands afterwards rather than corrupting it.

SAFE TO RETRY: client_turn_id is a caller-generated idempotency key, and the same id twice comes back status: "duplicate" rather than queueing a second instruction into a running agent. Check that field before assuming a retry did something.

post/agent/work-items/{work_item_id}/steer

Request

  • Base URL: https://be.graph8.com/api/v1
  • URL: https://be.graph8.com/api/v1/agent/work-items/{work_item_id}/steer
  • Auth: HTTP bearer

Path parameters

work_item_idstring required

Work item id (UUID).

Headers

Authorizationstring nullable
X-Target-Org-Idstring nullable

Request body

client_turn_idstring uuid required

Caller-generated idempotency key. REQUIRED, and the reason steering is safe to retry: the same id twice comes back duplicate rather than queueing a second instruction into a running agent.

instructionstring required

What to do differently. Applied at the next safe step boundary, not mid-step.

Response

Successful Response

dataobject required

Changes

No recorded changes to this operation across all 2 revisions of this API.