Steer a live task with mid-run user input
Inject a user message into an actively running (or resuming) task. The current tool/LLM step finishes, then every live agent loop on this stream sees a real user message at its next LLM step.
Send stream_id from the live SSE you are watching. The API will
not retarget the steer onto a newer run of the same chat.
This does not abort in-flight tools. Do not PATCH working memory
(user_runtime_input) for composer text — use this endpoint while
the stream is live.
Authorizations
JWT authentication token
Path Parameters
Task ID
Body
Composer text to inject into the live run
1 - 32000Idempotency key and mastra_messages id. Reuse the same id on retries so a duplicate POST cannot mint a new signal. Go mints one when omitted.
v1 only supports steer (inject at the next LLM step)
steer Live SSE stream this composer send was typed against. When set, the API returns 409 if that stream is no longer live — including when a newer run on the same chat has started. Prevents a retried steer (e.g. "stop") from attaching to the next turn. Send the stream_id from the live SSE metadata.
Optional target for one live subagent invocation. This is the
subagent stream srid, which is also the parent trigger toolCallId.
When omitted, the steer is broadcast to the parent and all
subagents on the live stream.
1 - 512
