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/components/workspace/knowledge-rag-toggle.tsx

@@ -0,0 +1,44 @@
+"use client";
+
+import { Database } from "lucide-react";
+
+import { Button } from "@/components/ui/button";
+import { useThreadSettings } from "@/core/settings";
+import { cn } from "@/lib/utils";
+
+import { Tooltip } from "./tooltip";
+
+/**
+ * Per-conversation toggle for knowledge-base RAG injection (phase 2).
+ *
+ * Writes ``context.knowledge_rag_enabled`` into the thread settings, which the
+ * run forwards as ``runtime.context`` so ``KnowledgeRagMiddleware`` injects
+ * recalled knowledge before each model call for this conversation only.
+ */
+export function KnowledgeRagToggle({ threadId }: { threadId: string }) {
+  const [settings, setSettings] = useThreadSettings(threadId);
+  const enabled = settings.context.knowledge_rag_enabled === true;
+
+  const toggle = () => {
+    setSettings("context", {
+      ...settings.context,
+      knowledge_rag_enabled: !enabled,
+    });
+  };
+
+  return (
+    <Tooltip content={enabled ? "知识库召回：已开启" : "知识库召回：已关闭"}>
+      <Button
+        variant="ghost"
+        onClick={toggle}
+        className={cn(
+          "text-muted-foreground hover:text-foreground",
+          enabled && "text-primary hover:text-primary",
+        )}
+      >
+        <Database />
+        知识库
+      </Button>
+    </Tooltip>
+  );
+}