Multi-agent debate council — spawns 3 specialized sub-agents in parallel (Scholar, Engineer, Muse) for Round 1, then optional Round 2 cross-examination to challenge assumptions and strengthen the final synthesis. Configurable models and templates per role.

多智能体辩论委员会——并行生成三个专业子智能体（学者、工程师、灵感者）进行第一轮讨论，随后可选第二轮交叉质询以挑战假设并强化最终综合结论。支持为每个角色配置不同的模型和模板。