feat(knowledge): 阶段二 向量 RAG 与召回注入

- embeddings.py：OpenAI 兼容 embedding 客户端，未配置时关键词兜底
- chunking.py + knowledge_embeddings 表：Markdown 分块与向量索引（Python 余弦）
- search.py：keyword/vector/hybrid 三种模式，向量不可用自动降级
- 笔记创建/更新自动重建向量索引；新增 /reindex 维护接口
- KnowledgeRagMiddleware：按对话级开关 knowledge_rag_enabled 注入 <knowledge-context>，接入 lead agent 中间件链（默认随 config.knowledge.rag_enabled）
- service.build_rag_context（wiki-query 风格分层召回）
- 笔记版本快照（knowledge_note_versions）+ GET /notes/{id}/versions
- 前端：聊天页「知识库」对话级 RAG 开关 + 类型字段
- 新增 entities/relations 表（阶段四预置）

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

frontend-web/src/pages/ChatPage.tsx

@@ -16,6 +16,7 @@ import {
 } from "@/components/workspace/chats";
 import { ExportTrigger } from "@/components/workspace/export-trigger";
 import { KnowledgeSaveTrigger } from "@/components/workspace/knowledge-save-trigger";
+import { KnowledgeRagToggle } from "@/components/workspace/knowledge-rag-toggle";
 import { InputBox } from "@/components/workspace/input-box";
 import {
   MessageList,
@@ -409,6 +410,7 @@ export default function ChatPage() {
                 enabled={tokenUsageEnabled}
                 messages={thread.messages}
               />
+              <KnowledgeRagToggle threadId={threadId} />
               <ExportTrigger threadId={threadId} />
               <KnowledgeSaveTrigger threadId={threadId} />
               <ArtifactTrigger />