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/internal_brain.py

@@ -0,0 +1,37 @@
+"""内部 LLM 大脑:prompt 与 workflow。
+
+二者都用本地维护的 LLMContext + OpenAI 兼容 LLM,支持 cascade 与 realtime。
+workflow 的图编排(切提示/转移工具/node-active)阶段 1 仍内联在 pipeline.py,
+这里只负责提供 LLM 槽位与元数据,行为与改造前完全一致。
+"""
+
+from __future__ import annotations
+
+from models import AssistantConfig
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.frame_processor import FrameProcessor
+
+from services.brains.base import BrainSpec
+
+_CASCADE_AND_REALTIME = frozenset({"pipeline", "realtime"})
+
+
+class InternalBrain:
+    """prompt / workflow 共用。"""
+
+    def __init__(self, brain_type: str):
+        self.spec = BrainSpec(
+            type=brain_type,
+            supported_runtime_modes=_CASCADE_AND_REALTIME,
+            owns_context=True,
+        )
+
+    async def greeting(self, cfg: AssistantConfig) -> str:
+        # 内部类型的开场白由 pipeline.py 现有逻辑(workflow 起始节点 / cfg.greeting)决定,
+        # 该方法仅为满足 Brain 协议,实际不在内部路径上被调用。
+        return cfg.greeting
+
+    def build_llm(self, cfg: AssistantConfig, context: LLMContext) -> FrameProcessor:
+        from services.pipecat.service_factory import create_llm
+
+        return create_llm(cfg)