https://t.co/OL0LzGsXKY can now orchestrate subagents with different models & reasoning efforts. e.g: Fable planning and Grok executing. Fable is a genius, Grok is a fast workhorse. ① Simple. 𝙰𝙶𝙴𝙽𝚃𝚂.𝚖𝚍 or your prompt…

Guillermo Rauch 披露 fx.sh 已支持用不同模型和不同推理强度编排子代理,例如让 Fable 负责规划、Grok 负责执行。这意味着多模型分工不再依赖服务端复杂路由,而是由模型自己承担调度。

![ValueError: 'text-generation' is not a valid ModelType` [[2]](https://github.com/langgenius/dify/issues/41294). The root cause is that old rows in tables like `provider_models`, `provider_mode](https://www.chat-gpts.plus/wp-content/uploads/2026/09/41605-8fa5f766-768x403.jpg)
![[Bug v1.15] Frontend cannot receive reply after Manual Intervention Node + Conditional Branch](https://www.chat-gpts.plus/wp-content/uploads/2026/09/38315-37e2660f-768x403.jpg)


![issue: upstream failure mid-stream truncates /api/chat/completions SSE with no error frame or [DONE]](https://www.chat-gpts.plus/wp-content/uploads/2026/09/29628-271ce5fc-768x403.jpg)


