Adaptive multi-model AI roundtable. Runs up to 4 AI models (configurable) in 2 debate rounds with cross-critique and formal consensus scoring. Requires a configured Anthropic provider (Claude Opus recommended). Optionally adds GPT-5.3 Codex (OpenAI), Grok 4, and Gemini 3.1 Pro via Blockrun proxy. Works with Claude-only fallback if optional providers are unavailable. Writes results to local filesystem. Debate panel agents are persistent thread sessions; meta-panel and synthesis agents are one-shot.

自适应多模型AI圆桌会议。可同时运行最多四个AI模型（可配置），进行两轮辩论，支持交叉评审与正式共识评分。需配置Anthropic提供方（推荐使用Claude Opus）。可选通过Blockrun代理添加GPT-5.3 Codex（OpenAI）、Grok 4和Gemini 3.1 Pro。若可选提供方不可用，则回退至仅使用Claude的模式。结果写入本地文件系统。辩论面板代理为持久线程会话；元面板与综合代理为一次性执行。