Skip to main content
POST
Append a system message to a live conversation’s LLM context while the call is in progress. The posted content is added as exactly one message:
It is not spoken, and it is not a user turn. Use this from your server with an API key, not from browser code. For the workflow, see Updating Conversation Context. On failure the body includes error and error_code. See Error responses. Required headers:
  • Authorization: Bearer <YOUR_AKAPULU_API_KEY>
  • Content-Type: application/json
Required request fields:
  • content: non-empty string, at most 16,000 characters
Optional request fields:
  • run_llm: boolean, default false
    • false: append the system message only. The assistant sees it on the next LLM run (typically the next user turn).
    • true: append the system message and immediately run the LLM so the assistant can reply.
The session id in the path must be owned by the API key. Live conversations from connect and Testing Mode sessions both work. Example request:

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

conversation_session_id
string<uuid>
required

Conversation session ID from connect, or X-Akapulu-Conversation-Session-Id on an HTTP tool POST.

Body

application/json
content
string
required

Text appended to the live LLM context as a system message. Not spoken and not treated as a user turn.

Required string length: 1 - 16000
run_llm
boolean
default:false

If false (default), only append the system message. If true, also trigger an assistant reply that can see the new context.

Response

System message queued for the live session

conversation_session_id
string<uuid>
required

Session that received the system message.

run_llm
boolean
required

Echo of the request run_llm value.