Function complete

server/src/utils/llm.ts:92–135

(options: CompleteOptions)

 * });
 */
export async function complete(options: CompleteOptions): Promise<LLMResult> {
  const {
    prompt,
    system,
    maxTokens = 100,
    model = 'fast',
    operationName = 'llm-complete',
  } = options;

  const modelId = ModelConfig[model];
  const startTime = Date.now();

  const response = await withRetry(
    async () => {
      return getClient().messages.create({
        model: modelId,
        max_tokens: maxTokens,
        ...(system && { system }),
        messages: [{ role: 'user', content: prompt }],
      });
    },
    { maxRetries: 3, initialDelayMs: 1000 },
    operationName
  );

  const latencyMs = Date.now() - startTime;

  if (!response.content || response.content.length === 0) {
    throw new Error('Empty response from LLM');
  }
  const content = response.content[0];

  if (content.type !== 'text') {
    throw new Error('Unexpected response type from LLM');
  }

  return {
    text: content.text.trim(),
    model: modelId,
    inputTokens: response.usage?.input_tokens,
    outputTokens: response.usage?.output_tokens,
    latencyMs,
  };
}

/**
 * Options for yes/no classification