/**
 * Visible-answer generation settings shared by consultation and rectification.
 *
 * DeepSeek V4 Flash thinks by default, and those hidden tokens share
 * `max_tokens` with the spoken answer. Consultation and rectification may
 * enable a separate Chinese thinking channel; the spoken answer still uses
 * this visible token budget. Default remains disabled for other callers.
 */
export const AGENT_MAX_OUTPUT_TOKENS = 8192;

type ThinkingMode = "enabled" | "disabled";

export function agentGenerationSettings(
  model?: unknown,
  options: { thinking?: ThinkingMode } = {},
) {
  const thinking = { thinking: { type: (options.thinking ?? "disabled") as ThinkingMode } };
  const providerId = typeof model === "string"
    ? model
    : model && typeof model === "object" && "providerId" in model && typeof model.providerId === "string"
      ? model.providerId
      : undefined;
  const providerOptions: Record<string, typeof thinking> = {
    openai: thinking,
  };
  if (providerId) providerOptions[providerId] = thinking;
  return {
    modelSettings: { maxOutputTokens: AGENT_MAX_OUTPUT_TOKENS },
    providerOptions,
  };
}