优化查询代码，优化工具代码

backend/app/tools/__init__.py

@@ -2,124 +2,17 @@
 Agent Tools - 所有工具统一定义
 """
 
-from langchain_core.tools import tool
-from backend.app.logger import info
-
-# ========== RAG ==========
-
-_rag_pipeline = None
-
-
-def _get_rag_pipeline():
-    global _rag_pipeline
-    if _rag_pipeline is None:
-        from backend.app.rag.pipeline import RAGPipeline
-        _rag_pipeline = RAGPipeline(
-            num_queries=3,
-            rerank_top_n=5,
-            use_rerank=True,
-            return_parent_docs=True,
-        )
-    return _rag_pipeline
-
-
-@tool
-async def rag_search(query: str) -> str:
-    """
-    检索知识库获取相关信息
-
-    Returns:
-        包含检索结果和置信度的结构化回复，格式：
-        - 内容：检索到的相关信息
-        - 置信度评估：基于向量相似度、重排分数、LLM判断的综合评分
-    """
-    info(f"[Tool] rag_search: {query[:30]}...")
-    try:
-        pipeline = _get_rag_pipeline()
-        # 使用带置信度的检索
-        result = await pipeline.aretrieve_with_confidence(query, original_query=query)
-
-        if not result.content:
-            return "【RAG检索结果】\n未在知识库中找到相关内容。\n置信度：0.0\n建议：可尝试联网搜索获取信息。"
-
-        # 构建包含置信度的回复
-        confidence_desc = "高"
-        if result.confidence < 0.4:
-            confidence_desc = "低"
-        elif result.confidence < 0.6:
-            confidence_desc = "中"
-
-        response = f"""【RAG检索结果】
-{result.content}
-
-【置信度评估】
-- 综合置信度：{result.confidence:.2f}（{confidence_desc}）
-- 向量相似度：{result.scores['embedding']:.2f}
-- 重排分数：{result.scores['rerank']:.2f}
-- LLM评估：{result.scores['llm']:.2f}
-
-{'✅ 检索结果可信，可直接使用' if result.is_useful else '⚠️ 检索结果置信度较低，可能需要联网搜索补充'}"""
-
-        info(f"[Tool] rag_search 完成: confidence={result.confidence:.3f}, is_useful={result.is_useful}")
-        return response
-
-    except Exception as e:
-        info(f"[Tool] rag_search 失败: {e}")
-        return f"【RAG检索失败】\n错误：{str(e)}\n建议：请稍后重试或使用联网搜索"
-
-
-# ========== 联网搜索 ==========
-
-@tool
-def web_search(query: str) -> str:
-    """联网搜索获取最新信息"""
-    info(f"[Tool] web_search: {query[:30]}...")
-    try:
-        from backend.app.core.web_search import web_search as search_fn
-        return search_fn(query, max_results=5)
-    except Exception as e:
-        info(f"[Tool] web_search 失败: {e}")
-        return f"联网搜索失败: {str(e)}"
-
-
-# ========== 子图工具 ==========
-
-async def _call_subgraph(builder_fn, state_cls, query: str) -> str:
-    """通用子图调用"""
-    try:
-        graph = builder_fn().compile()
-        state = state_cls(user_query=query)
-        result = await graph.ainvoke(state)
-        return result.get("final_result", "执行完成")
-    except Exception as e:
-        info(f"[Tool] 子图调用失败: {e}")
-        return f"执行失败: {str(e)}"
-
-
-@tool
-async def contact_lookup(query: str) -> str:
-    """查询通讯录"""
-    from backend.app.subgraphs.contact.graph import build_contact_subgraph
-    from backend.app.subgraphs.contact.state import ContactState
-    return await _call_subgraph(build_contact_subgraph, ContactState, query)
-
-
-@tool
-async def dictionary_lookup(word: str) -> str:
-    """查询词典/翻译"""
-    from backend.app.subgraphs.dictionary.graph import build_dictionary_subgraph
-    from backend.app.subgraphs.dictionary.state import DictionaryState
-    return await _call_subgraph(build_dictionary_subgraph, DictionaryState, word)
-
-
-@tool
-async def news_analysis(topic: str) -> str:
-    """分析新闻热点"""
-    from backend.app.subgraphs.news_analysis.graph import build_news_analysis_subgraph
-    from backend.app.subgraphs.news_analysis.state import NewsAnalysisState
-    return await _call_subgraph(build_news_analysis_subgraph, NewsAnalysisState, topic)
-
-
-# ========== 导出 ==========
+from .rag import rag_search
+from .web_search import web_search
+from .subgraph import contact_lookup, dictionary_lookup, news_analysis
 
 ALL_TOOLS = [rag_search, web_search, contact_lookup, dictionary_lookup, news_analysis]
+
+__all__ = [
+    "rag_search",
+    "web_search",
+    "contact_lookup",
+    "dictionary_lookup",
+    "news_analysis",
+    "ALL_TOOLS",
+]