Wake a sleeping background response

Interrupts a short sleep tool call on an in-progress background response by providing follow-up input. Wake delivery is polled by the sleeping agent and may take up to one second.

POST /api/v1/llm/responses/{response_id}/wake

Python (SDK)

Python

from mka1 import SDK


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.llm.responses.wake(response_id="resp_sleep123", input="I have more context now; resume immediately.")

    # Handle response
    print(res)

200

{
  "object": "response.sleep_wake",
  "response_id": "resp_sleep123",
  "created_at": "2026-05-01T16:30:00.000Z"
}

Authorizations

Authorization · string · header · required

Gateway auth: send Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, you can also send X-On-Behalf-Of: <external-user-id>.

Headers

X-On-Behalf-Of · string

Optional external end-user identifier forwarded by the API gateway.

Path Parameters

response_id · string · required

The unique identifier of the response, formatted as 'resp_' or 'resp-' followed by alphanumeric characters.

Pattern: ^resp[-_][a-zA-Z0-9]+$

Body

application/json

input · string · required

Required string length: 1 - 20000

Response

200

application/json

The sleeping response was signalled to wake.

object · enum<string> · required

Available options: response.sleep_wake

response_id · string · required

created_at · string<date-time> · required