onSamplingRequest method

void onSamplingRequest(Future<CreateMessageResult> handler(CreateMessageRequest request))

Register a handler for server-initiated sampling/createMessage requests. The driver app (Claude Desktop / Claude Code / a vibe-style IDE) fulfils the prompt with its own LLM and returns the spec CreateMessageResult (role, content, model, optional stopReason).

Calling this advertises the sampling client capability during the next initialize handshake.

Implementation

void onSamplingRequest(
  Future<CreateMessageResult> Function(CreateMessageRequest request) handler,
) {
  _requestHandlers['sampling/createMessage'] = (params) async {
    final req = CreateMessageRequest.fromJson(params);
    final result = await handler(req);
    return result.toJson();
  };
}