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/services/brains/base.py

@@ -0,0 +1,46 @@
+"""「大脑」抽象:把不同助手类型(prompt/workflow/fastgpt/…)在运行时的差异收口。
+
+cascade 管线骨架对所有类型一致(STT → LLM 槽 → TTS),变化的只有:
+  - 谁产出助手文本(LLM 槽里塞什么)——build_llm
+  - 开场白来源(静态 / 外部异步拉取)——greeting
+  - 对话上下文归谁维护——spec.owns_context
+  - 是否支持 realtime——spec.supported_runtime_modes
+
+阶段 1 只抽到「够 fastgpt 用」的程度;workflow 编排仍内联在 pipeline.py,
+待阶段 2 再搬进 WorkflowBrain 收口。
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Protocol, runtime_checkable
+
+from models import AssistantConfig
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.frame_processor import FrameProcessor
+
+
+@dataclass(frozen=True)
+class BrainSpec:
+    """类型元数据。单一来源,供运行时门控与上下文归属决策复用。"""
+
+    type: str
+    supported_runtime_modes: frozenset[str]
+    # True:由本服务维护 LLMContext(prompt/workflow);
+    # False:上下文/知识库/工具由外部服务端接管(fastgpt/dify),本地不写 context。
+    owns_context: bool
+
+
+@runtime_checkable
+class Brain(Protocol):
+    """每通电话 new 一个实例(可持有 chatId / 当前节点等会话状态)。"""
+
+    spec: BrainSpec
+
+    async def greeting(self, cfg: AssistantConfig) -> str:
+        """开场白。内部类型通常直接用 cfg.greeting;外部类型异步拉取后端配置。"""
+        ...
+
+    def build_llm(self, cfg: AssistantConfig, context: LLMContext) -> FrameProcessor:
+        """返回丢进管线 LLM 槽位的帧处理器(标准 LLMService 或外部托管的伪 LLM)。"""
+        ...