Send Conversation Message

Send a follow-up to a (possibly running) conversation. mode=auto queues while running and signals 'started' when idle; mode=queue always enqueues; mode=steer delivers into the running task at its next tool boundary (409 when idle); mode=interrupt stops the task and runs this message as the next turn. A conversation with a live process (an external-harness agent between turns) takes every mode into that process: the answer is steered with steer_target process, never 409, and the process reads it on its next turn.

post/v1/agents/{agent_id}/conversations/{conversation_id}/messages

Request

Base URL
https://api.xpander.ai (the document declares no server; this is the origin it was published from)
Auth
API key in header x-api-key

Path parameters

agent_idstring required

conversation_idstring required

Request body

textstring

filesstring[]

attachmentsobject[]

mode'auto' | 'queue' | 'steer' | 'interrupt' | 'steer_if_running'

How an inbound message to a (possibly running) conversation is handled.

idempotency_keystring nullable

userobject nullable

ui_contextobject nullable

is_noticeboolean

Response

Successful Response

actionstring required

message_idstring nullable

queue_depthinteger

steer_target'none' | 'gateway' | 'child' | 'process'

Where a steer would land right now (run-state / accept responses).

Distinct from GatewaySteerTarget, which records where a steer WAS delivered after the fact (router | child | next_turn).

conversation_idstring nullable

Changes

No recorded changes to this operation across all 4 revisions of this API.