Enhance AssistantConfig and pipeline for FastGPT integration

- Add new fields in AssistantConfig for FastGPT connection details, including `fastgpt_api_url`, `fastgpt_api_key`, and `fastgpt_app_id`.
- Update the pipeline to utilize the new FastGPT configuration, ensuring proper integration with external services.
- Introduce type handling for different assistant types, including support for realtime modes and external brain management.
- Refactor frontend components to include hints for FastGPT configuration inputs, improving user guidance during setup.

backend/models.py

@@ -19,6 +19,8 @@ class AssistantConfig(BaseModel):
     """运行时配置:前端可见部分(name/prompt/...) + 服务端注入部分(*_api_key/*_base_url)。"""
 
     name: str = "未命名助手"
+    # prompt|workflow|dify|fastgpt|opencode;决定由哪种「大脑」驱动对话
+    type: str = "prompt"
     greeting: str = "您好,我是 AI 视频助手,请问有什么可以帮您?"
     prompt: str = "你是一个有帮助的助手。"
     runtimeMode: RuntimeMode = "pipeline"
@@ -49,6 +51,11 @@ class AssistantConfig(BaseModel):
     # workflow 类型:节点图(nodes/edges)。非 workflow 为空,引擎据此决定是否启用。
     graph: dict = {}
 
+    # 外部托管类型(fastgpt/dify/opencode)的连接信息:context/KB/tools 由对方服务端接管。
+    fastgpt_api_url: str = ""
+    fastgpt_api_key: str = ""
+    fastgpt_app_id: str = ""
+
     # ---- 运行时连接信息(服务端注入,不来自浏览器) ----
     # 为空时,service_factory 会回退到 config.py 的 .env 默认值。
     llm_api_key: str = ""