feat(chat): 基于 RAG 的笔记内容 AI 问答功能

实现类似 Google NotebookLM 的效果：笔记生成后自动向量化，
用户可针对笔记内容进行 LLM 问答。

### 后端
- 新增 VectorStoreManager（ChromaDB），按标题/转录分块建立向量索引
- 新增 chat_service.py RAG 问答：检索相关片段 → 构建 prompt → 调用 LLM
- 新增 /chat/index, /chat/ask, /chat/status API 端点
- 笔记生成完成后自动建立向量索引

### 前端
- 使用 @ant-design/x Bubble.List + Sender 组件构建聊天面板
- 新增 chatStore（Zustand + persist）持久化聊天记录
- MarkdownViewer 右侧嵌入 ChatPanel，通过"AI 问答"按钮切换
- 首次打开自动检查/触发索引，支持重新索引

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

BillNote_frontend/src/store/chatStore/index.ts

@@ -0,0 +1,43 @@
+import { create } from 'zustand'
+import { persist } from 'zustand/middleware'
+import type { ChatSource } from '@/services/chat'
+
+export interface ChatMessage {
+  role: 'user' | 'assistant'
+  content: string
+  sources?: ChatSource[]
+}
+
+interface ChatState {
+  chatHistory: Record<string, ChatMessage[]>
+  addMessage: (taskId: string, msg: ChatMessage) => void
+  clearChat: (taskId: string) => void
+  getMessages: (taskId: string) => ChatMessage[]
+}
+
+export const useChatStore = create<ChatState>()(
+  persist(
+    (set, get) => ({
+      chatHistory: {},
+
+      addMessage: (taskId, msg) =>
+        set(state => ({
+          chatHistory: {
+            ...state.chatHistory,
+            [taskId]: [...(state.chatHistory[taskId] || []), msg],
+          },
+        })),
+
+      clearChat: (taskId) =>
+        set(state => {
+          const { [taskId]: _, ...rest } = state.chatHistory
+          return { chatHistory: rest }
+        }),
+
+      getMessages: (taskId) => get().chatHistory[taskId] || [],
+    }),
+    {
+      name: 'bilinote-chat-storage',
+    },
+  ),
+)