export async function checkNextSpeaker()

in packages/core/src/utils/nextSpeakerChecker.ts [61:151]

• 68 lines of code
• 15 McCabe index (conditional complexity)

export async function checkNextSpeaker(
  chat: GeminiChat,
  geminiClient: GeminiClient,
  abortSignal: AbortSignal,
): Promise<NextSpeakerResponse | null> {
  // We need to capture the curated history because there are many moments when the model will return invalid turns
  // that when passed back up to the endpoint will break subsequent calls. An example of this is when the model decides
  // to respond with an empty part collection if you were to send that message back to the server it will respond with
  // a 400 indicating that model part collections MUST have content.
  const curatedHistory = chat.getHistory(/* curated */ true);

  // Ensure there's a model response to analyze
  if (curatedHistory.length === 0) {
    // Cannot determine next speaker if history is empty.
    return null;
  }

  const comprehensiveHistory = chat.getHistory();
  // If comprehensiveHistory is empty, there is no last message to check.
  // This case should ideally be caught by the curatedHistory.length check earlier,
  // but as a safeguard:
  if (comprehensiveHistory.length === 0) {
    return null;
  }
  const lastComprehensiveMessage =
    comprehensiveHistory[comprehensiveHistory.length - 1];

  // If the last message is a user message containing only function_responses,
  // then the model should speak next.
  if (
    lastComprehensiveMessage &&
    isFunctionResponse(lastComprehensiveMessage)
  ) {
    return {
      reasoning:
        'The last message was a function response, so the model should speak next.',
      next_speaker: 'model',
    };
  }

  if (
    lastComprehensiveMessage &&
    lastComprehensiveMessage.role === 'model' &&
    lastComprehensiveMessage.parts &&
    lastComprehensiveMessage.parts.length === 0
  ) {
    lastComprehensiveMessage.parts.push({ text: '' });
    return {
      reasoning:
        'The last message was a filler model message with no content (nothing for user to act on), model should speak next.',
      next_speaker: 'model',
    };
  }

  // Things checked out. Lets proceed to potentially making an LLM request.

  const lastMessage = curatedHistory[curatedHistory.length - 1];
  if (!lastMessage || lastMessage.role !== 'model') {
    // Cannot determine next speaker if the last turn wasn't from the model
    // or if history is empty.
    return null;
  }

  const contents: Content[] = [
    ...curatedHistory,
    { role: 'user', parts: [{ text: CHECK_PROMPT }] },
  ];

  try {
    const parsedResponse = (await geminiClient.generateJson(
      contents,
      RESPONSE_SCHEMA,
      abortSignal,
    )) as unknown as NextSpeakerResponse;

    if (
      parsedResponse &&
      parsedResponse.next_speaker &&
      ['user', 'model'].includes(parsedResponse.next_speaker)
    ) {
      return parsedResponse;
    }
    return null;
  } catch (error) {
    console.warn(
      'Failed to talk to Gemini endpoint when seeing if conversation should continue.',
      error,
    );
    return null;
  }
}