Retell Conversation Flow And Response Engine

Operator deploys a custom-llm. Their server URL is https://host/llm-websocket and they set llm_websocket_url to that http(s) URL on the agent.

llm_websocket_url must be a WebSocket URL: prepend wss:// (not https://) and append the /llm-websocket path Retell expects, e.g. wss://host/llm-websocket/{call_id}. Retell opens the socket per call; reject a plain https URL at config time.

The caller has gone silent. Retell sends a reminder_required event (not response_required) to the custom-LLM server.

Treat reminder_required as a nudge after user silence: emit a brief check-in ('Are you still there?') tied to the event's response_id, distinct from a full response_required turn. Do not regenerate the entire prior answer.

Custom-LLM server receives a response_required event carrying the transcript and a response_id. The server begins generating and streaming content.

On response_required, stream RetellResponse frames with the SAME response_id as the inbound event, emitting content incrementally and a final frame with content_complete=true. The response_id ties your output to the turn Retell asked about.