From a1fdcbc36cb2a71d07842b082f8261782ba7d7d4 Mon Sep 17 00:00:00 2001
From: Wenjie Zhang <xerrors@163.com>
Date: Fri, 24 Oct 2025 00:11:52 +0800
Subject: [PATCH] style: ruff format

---
 Makefile                                |  1 +
 server/routers/chat_router.py           |  6 +-
 server/utils/lifespan.py                |  4 +-
 server/utils/singleton.py               |  4 +-
 src/agents/chatbot/tools.py             |  5 +-
 src/agents/common/base.py               |  4 +-
 src/agents/common/tools.py              | 13 ++--
 src/config/app.py                       | 44 +++++-------
 src/knowledge/base.py                   | 11 ++-
 src/knowledge/graph.py                  |  2 +-
 src/knowledge/implementations/chroma.py | 18 ++---
 src/knowledge/implementations/milvus.py |  6 +-
 src/knowledge/indexing.py               |  3 +-
 src/knowledge/manager.py                | 95 ++++++++++++++-----------
 src/knowledge/utils/kb_utils.py         |  2 +-
 src/storage/conversation/manager.py     |  3 +-
 src/storage/db/manager.py               |  1 +
 17 files changed, 115 insertions(+), 107 deletions(-)

diff --git a/Makefile b/Makefile
index 19cf1dea..60002357 100644
--- a/Makefile
+++ b/Makefile
@@ -27,6 +27,7 @@ lint:
 format:
 	uv run ruff format .
 	uv run ruff check . --fix
+	uv run python -m ruff check --select I src --fix
 
 format_diff:
 	uv run ruff format --diff .
diff --git a/server/routers/chat_router.py b/server/routers/chat_router.py
index e86762fb..9ec98af4 100644
--- a/server/routers/chat_router.py
+++ b/server/routers/chat_router.py
@@ -112,7 +112,8 @@ async def get_agent(current_user: User = Depends(get_required_user)):
             metadata = yaml.safe_load(f)
     return {"agents": agents, "metadata": metadata}
 
-#TODO:[未完成]这个thread_id在前端是直接生成的1234，最好传入thread_id时做校验只允许uuid4
+
+# TODO:[未完成]这个thread_id在前端是直接生成的1234，最好传入thread_id时做校验只允许uuid4
 @chat.post("/agent/{agent_id}")
 async def chat_agent(
     agent_id: str,
@@ -254,7 +255,8 @@ async def chat_agent(
             logger.error(f"Error saving messages from LangGraph state: {e}")
             logger.error(traceback.format_exc())
 
-    #TODO:[功能建议]针对需要人工审批后再执行的工具，可以使用langgraph的interrupt方法中断对话，等待用户输入后再使用command跳转回去
+    # TODO:[功能建议]针对需要人工审批后再执行的工具，
+    # 可以使用langgraph的interrupt方法中断对话，等待用户输入后再使用command跳转回去
     async def stream_messages():
         # 代表服务端已经收到了请求
         yield make_chunk(status="init", meta=meta, msg=HumanMessage(content=query).model_dump())
diff --git a/server/utils/lifespan.py b/server/utils/lifespan.py
index 8215fd75..60e34530 100644
--- a/server/utils/lifespan.py
+++ b/server/utils/lifespan.py
@@ -1,11 +1,11 @@
-import asyncio
 from contextlib import asynccontextmanager
 
 from fastapi import FastAPI
 
 from server.services import tasker
 
-#TODO:[已完成]使用lifespan进行统一生命周期管理
+# TODO:[已完成]使用lifespan进行统一生命周期管理
+
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
diff --git a/server/utils/singleton.py b/server/utils/singleton.py
index 568ed675..0bfccb07 100644
--- a/server/utils/singleton.py
+++ b/server/utils/singleton.py
@@ -1,9 +1,11 @@
 from threading import Lock
 
+
 class SingletonMeta(type):
     """
     This is a thread-safe implementation of Singleton.
     """
+
     _instances = {}
     _lock: Lock = Lock()
 
@@ -12,4 +14,4 @@ class SingletonMeta(type):
             if cls not in cls._instances:
                 instance = super().__call__(*args, **kwargs)
                 cls._instances[cls] = instance
-        return cls._instances[cls]
\ No newline at end of file
+        return cls._instances[cls]
diff --git a/src/agents/chatbot/tools.py b/src/agents/chatbot/tools.py
index 4d6a1593..edfc1b10 100644
--- a/src/agents/chatbot/tools.py
+++ b/src/agents/chatbot/tools.py
@@ -9,8 +9,9 @@ from src.agents.common.tools import get_buildin_tools
 from src.storage.minio import upload_image_to_minio
 from src.utils import logger
 
-#TODO:[已完成]修改了tool定义的示例，使用更符合langgraph调用的方式
-@tool(name_or_callable="全能计算器",description="可以对给定的2个数字选择进行加减乘除四种计算")
+
+# TODO:[已完成]修改了tool定义的示例，使用更符合langgraph调用的方式
+@tool(name_or_callable="全能计算器", description="可以对给定的2个数字选择进行加减乘除四种计算")
 def calculator(a: float, b: float, operation: str) -> float:
     """
     可以对给定的2个数字选择进行加减乘除四种计算
diff --git a/src/agents/common/base.py b/src/agents/common/base.py
index 7078b0c1..b3d4fd0d 100644
--- a/src/agents/common/base.py
+++ b/src/agents/common/base.py
@@ -1,12 +1,12 @@
 from __future__ import annotations
 
 import os
-from pathlib import Path
 from abc import abstractmethod
+from pathlib import Path
 
-from langgraph.graph.state import CompiledStateGraph
 from langgraph.checkpoint.memory import InMemorySaver
 from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver, aiosqlite
+from langgraph.graph.state import CompiledStateGraph
 
 from src import config as sys_config
 from src.agents.common.context import BaseContext
diff --git a/src/agents/common/tools.py b/src/agents/common/tools.py
index 6fb26cd9..0023d9b8 100644
--- a/src/agents/common/tools.py
+++ b/src/agents/common/tools.py
@@ -11,7 +11,7 @@ from src import config, graph_base, knowledge_base
 from src.utils import logger
 
 
-@tool
+@tool(name_or_callable="查询知识图谱", description="使用这个工具可以查询知识图谱中包含的三元组信息。")
 def query_knowledge_graph(query: Annotated[str, "The keyword to query knowledge graph."]) -> Any:
     """Use this to query knowledge graph, which include some food domain knowledge."""
     try:
@@ -35,7 +35,9 @@ def get_static_tools() -> list:
 
     # 检查是否启用网页搜索
     if config.enable_web_search:
-        static_tools.append(TavilySearch(max_results=10))
+        search = TavilySearch(max_results=10)
+        search.metadata = {"name": "Tavily 网页搜索"}
+        static_tools.append(search)
 
     return static_tools
 
@@ -76,9 +78,6 @@ def get_kb_based_tools() -> list:
 
     for db_id, retrieve_info in retrievers.items():
         try:
-            # 使用改进的工具ID生成策略
-            tool_id = f"query_{db_id[:8]}"
-
             # 构建工具描述
             description = (
                 f"使用 {retrieve_info['name']} 知识库进行检索。\n"
@@ -88,10 +87,12 @@ def get_kb_based_tools() -> list:
             # 使用工厂函数创建检索器包装函数，避免闭包问题
             retriever_wrapper = _create_retriever_wrapper(db_id, retrieve_info)
 
+            safename = retrieve_info["name"].replace(" ", "_")[:20]
+
             # 使用 StructuredTool.from_function 创建异步工具
             tool = StructuredTool.from_function(
                 coroutine=retriever_wrapper,
-                name=tool_id,
+                name=safename,
                 description=description,
                 args_schema=KnowledgeRetrieverModel,
                 metadata=retrieve_info["metadata"] | {"tag": ["knowledgebase"]},
diff --git a/src/config/app.py b/src/config/app.py
index c8ea3b8b..78d0d753 100644
--- a/src/config/app.py
+++ b/src/config/app.py
@@ -13,7 +13,7 @@ from typing import Any
 
 import tomli
 import tomli_w
-from pydantic import BaseModel, Field, field_validator
+from pydantic import BaseModel, Field
 
 from src.config.static.models import (
     DEFAULT_CHAT_MODEL_PROVIDERS,
@@ -172,13 +172,10 @@ class Config(BaseModel):
         self.model_dir = os.environ.get("MODEL_DIR", self.model_dir)
         if self.model_dir:
             if os.path.exists(self.model_dir):
-                logger.debug(
-                    f"Model directory ({self.model_dir}) contains: {os.listdir(self.model_dir)}"
-                )
+                logger.debug(f"Model directory ({self.model_dir}) contains: {os.listdir(self.model_dir)}")
             else:
                 logger.warning(
-                    f"Model directory ({self.model_dir}) does not exist. "
-                    "If not configured, please ignore it."
+                    f"Model directory ({self.model_dir}) does not exist. If not configured, please ignore it."
                 )
 
         # 检查模型提供商的环境变量
@@ -195,14 +192,10 @@ class Config(BaseModel):
             self.enable_web_search = True
 
         # 获取可用的模型提供商
-        self.valuable_model_provider = [
-            k for k, v in self.model_provider_status.items() if v
-        ]
+        self.valuable_model_provider = [k for k, v in self.model_provider_status.items() if v]
 
         if not self.valuable_model_provider:
-            raise ValueError(
-                "No model provider available, please check your `.env` file."
-            )
+            raise ValueError("No model provider available, please check your `.env` file.")
 
     def save(self):
         """保存配置到 TOML 文件（仅保存用户修改的字段）"""
@@ -251,15 +244,11 @@ class Config(BaseModel):
         )
 
         # 添加模型信息（转换为字典格式供前端使用）
-        config_dict["model_names"] = {
-            provider: info.model_dump() for provider, info in self.model_names.items()
-        }
+        config_dict["model_names"] = {provider: info.model_dump() for provider, info in self.model_names.items()}
         config_dict["embed_model_names"] = {
             model_id: info.model_dump() for model_id, info in self.embed_model_names.items()
         }
-        config_dict["reranker_names"] = {
-            model_id: info.model_dump() for model_id, info in self.reranker_names.items()
-        }
+        config_dict["reranker_names"] = {model_id: info.model_dump() for model_id, info in self.reranker_names.items()}
 
         # 添加运行时状态信息
         config_dict["model_provider_status"] = self.model_provider_status
@@ -269,10 +258,12 @@ class Config(BaseModel):
         for field_name, field_info in Config.model_fields.items():
             if not field_info.exclude:  # 排除内部字段
                 fields_info[field_name] = {
-                    'des': field_info.description,
-                    'default': field_info.default,
-                    'type': field_info.annotation.__name__ if hasattr(field_info.annotation, '__name__') else str(field_info.annotation),
-                    'exclude': field_info.exclude if hasattr(field_info, 'exclude') else False,
+                    "des": field_info.description,
+                    "default": field_info.default,
+                    "type": field_info.annotation.__name__
+                    if hasattr(field_info.annotation, "__name__")
+                    else str(field_info.annotation),
+                    "exclude": field_info.exclude if hasattr(field_info, "exclude") else False,
                 }
         config_dict["_config_items"] = fields_info
 
@@ -301,14 +292,12 @@ class Config(BaseModel):
 
     def __getitem__(self, key: str) -> Any:
         """支持字典式访问 config[key]"""
-        logger.warning("Using deprecated dict-style access for Config. "
-                       "Please use attribute access instead.")
+        logger.warning("Using deprecated dict-style access for Config. Please use attribute access instead.")
         return getattr(self, key, None)
 
     def __setitem__(self, key: str, value: Any):
         """支持字典式赋值 config[key] = value"""
-        logger.warning("Using deprecated dict-style assignment for Config. "
-                       "Please use attribute access instead.")
+        logger.warning("Using deprecated dict-style assignment for Config. Please use attribute access instead.")
         setattr(self, key, value)
 
     def update(self, other: dict):
@@ -352,8 +341,7 @@ class Config(BaseModel):
             else:
                 # 保存所有 model_names
                 user_config["model_names"] = {
-                    provider: info.model_dump()
-                    for provider, info in self.model_names.items()
+                    provider: info.model_dump() for provider, info in self.model_names.items()
                 }
                 # 记录整个 model_names 字段的修改
                 self._user_modified_fields.add("model_names")
diff --git a/src/knowledge/base.py b/src/knowledge/base.py
index 48fdd49f..cfde47f2 100644
--- a/src/knowledge/base.py
+++ b/src/knowledge/base.py
@@ -1,7 +1,7 @@
 import json
 import os
-import tempfile
 import shutil
+import tempfile
 from abc import ABC, abstractmethod
 from typing import Any
 
@@ -144,8 +144,8 @@ class KnowledgeBase(ABC):
             "name": database_name,
             "description": description,
             "kb_type": self.kb_type,
-            "embed_info": embed_info.model_dump() if hasattr(embed_info, 'model_dump') else embed_info,
-            "llm_info": llm_info.model_dump() if hasattr(llm_info, 'model_dump') else llm_info,
+            "embed_info": embed_info.model_dump() if hasattr(embed_info, "model_dump") else embed_info,
+            "llm_info": llm_info.model_dump() if hasattr(llm_info, "model_dump") else llm_info,
             "metadata": kwargs,
             "created_at": utc_isoformat(),
         }
@@ -559,7 +559,7 @@ class KnowledgeBase(ABC):
 
     def _serialize_metadata(self, obj):
         """递归序列化元数据中的 Pydantic 模型"""
-        if hasattr(obj, 'dict'):
+        if hasattr(obj, "dict"):
             return obj.dict()
         elif isinstance(obj, dict):
             return {k: self._serialize_metadata(v) for k, v in obj.items()}
@@ -589,8 +589,7 @@ class KnowledgeBase(ABC):
 
             # 原子性写入（使用临时文件）
             with tempfile.NamedTemporaryFile(
-                mode='w', dir=os.path.dirname(meta_file),
-                prefix='.tmp_', suffix='.json', delete=False
+                mode="w", dir=os.path.dirname(meta_file), prefix=".tmp_", suffix=".json", delete=False
             ) as tmp_file:
                 json.dump(data, tmp_file, ensure_ascii=False, indent=2)
                 temp_path = tmp_file.name
diff --git a/src/knowledge/graph.py b/src/knowledge/graph.py
index b0090b66..53400db4 100644
--- a/src/knowledge/graph.py
+++ b/src/knowledge/graph.py
@@ -299,7 +299,7 @@ class GraphDatabase:
             logger.info(f"Adding entity to {kgdb_name}")
             session.execute_write(_create_graph, triples)
             logger.info(f"Creating vector index for {kgdb_name} with {config.embed_model}")
-            session.execute_write(_create_vector_index, getattr(cur_embed_info, 'dimension', 1024))
+            session.execute_write(_create_vector_index, getattr(cur_embed_info, "dimension", 1024))
 
             # 收集所有需要处理的实体名称，去重
             all_entities = []
diff --git a/src/knowledge/implementations/chroma.py b/src/knowledge/implementations/chroma.py
index 86cede70..976b6060 100644
--- a/src/knowledge/implementations/chroma.py
+++ b/src/knowledge/implementations/chroma.py
@@ -72,11 +72,11 @@ class ChromaKB(KnowledgeBase):
             logger.info(f"Retrieved existing collection: {collection_name}")
 
             # 检查现有集合的配置是否匹配当前的 embed_info
-            expected_model = getattr(embed_info, 'name', None) if embed_info else None
-            if expected_model is None and hasattr(embed_info, 'get'):
-                expected_model = embed_info.get('name')
+            expected_model = getattr(embed_info, "name", None) if embed_info else None
+            if expected_model is None and hasattr(embed_info, "get"):
+                expected_model = embed_info.get("name")
             elif embed_info and isinstance(embed_info, dict):
-                expected_model = embed_info.get('name')
+                expected_model = embed_info.get("name")
             expected_model = expected_model or "default"
             collection_metadata = collection.metadata or {}
             current_model = collection_metadata.get("embedding_model", "unknown")
@@ -93,13 +93,13 @@ class ChromaKB(KnowledgeBase):
 
         except Exception:
             # 创建新集合
-            model_name = getattr(embed_info, 'name', None) if embed_info else None
-            if model_name is None and hasattr(embed_info, 'get'):
-                model_name = embed_info.get('name')
+            model_name = getattr(embed_info, "name", None) if embed_info else None
+            if model_name is None and hasattr(embed_info, "get"):
+                model_name = embed_info.get("name")
             elif embed_info and isinstance(embed_info, dict):
-                model_name = embed_info.get('name')
+                model_name = embed_info.get("name")
 
-            model_name = model_name or 'default'
+            model_name = model_name or "default"
             logger.info(f"Creating new collection with embedding model: {model_name}")
             collection_metadata = {
                 "db_id": db_id,
diff --git a/src/knowledge/implementations/milvus.py b/src/knowledge/implementations/milvus.py
index a843bf80..f999c43a 100644
--- a/src/knowledge/implementations/milvus.py
+++ b/src/knowledge/implementations/milvus.py
@@ -103,7 +103,7 @@ class MilvusKB(KnowledgeBase):
 
                 # 检查嵌入模型是否匹配
                 description = collection.description
-                expected_model = getattr(embed_info, 'name', 'default') if embed_info else "default"
+                expected_model = getattr(embed_info, "name", "default") if embed_info else "default"
 
                 if expected_model not in description:
                     logger.warning(f"Collection {collection_name} model mismatch, recreating...")
@@ -116,8 +116,8 @@ class MilvusKB(KnowledgeBase):
 
         except Exception:
             # 创建新集合
-            embedding_dim = getattr(embed_info, 'dimension', 1024) if embed_info else 1024
-            model_name = getattr(embed_info, 'name', 'default') if embed_info else "default"
+            embedding_dim = getattr(embed_info, "dimension", 1024) if embed_info else 1024
+            model_name = getattr(embed_info, "name", "default") if embed_info else "default"
 
             # 定义集合Schema
             fields = [
diff --git a/src/knowledge/indexing.py b/src/knowledge/indexing.py
index 750dd0d0..e2c6ce9f 100644
--- a/src/knowledge/indexing.py
+++ b/src/knowledge/indexing.py
@@ -2,7 +2,6 @@ import asyncio
 import os
 from pathlib import Path
 
-from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_community.document_loaders import (
     CSVLoader,
     JSONLoader,
@@ -12,10 +11,10 @@ from langchain_community.document_loaders import (
     UnstructuredMarkdownLoader,
     UnstructuredWordDocumentLoader,
 )
+from langchain_text_splitters import RecursiveCharacterTextSplitter
 
 from src.utils import logger
 
-
 SUPPORTED_FILE_EXTENSIONS: tuple[str, ...] = (
     ".txt",
     ".md",
diff --git a/src/knowledge/manager.py b/src/knowledge/manager.py
index 9ddd496d..de8569fb 100644
--- a/src/knowledge/manager.py
+++ b/src/knowledge/manager.py
@@ -104,16 +104,11 @@ class KnowledgeBaseManager:
                 shutil.copy2(meta_file, backup_file)
 
             # 准备数据
-            data = {
-                "databases": self.global_databases_meta,
-                "updated_at": utc_isoformat(),
-                "version": "2.0"
-            }
+            data = {"databases": self.global_databases_meta, "updated_at": utc_isoformat(), "version": "2.0"}
 
             # 原子性写入（使用临时文件）
             with tempfile.NamedTemporaryFile(
-                mode='w', dir=os.path.dirname(meta_file),
-                prefix='.tmp_', suffix='.json', delete=False
+                mode="w", dir=os.path.dirname(meta_file), prefix=".tmp_", suffix=".json", delete=False
             ) as tmp_file:
                 json.dump(data, tmp_file, ensure_ascii=False, indent=2)
                 temp_path = tmp_file.name
@@ -520,7 +515,7 @@ class KnowledgeBaseManager:
             "chroma": {"missing_collections": [], "missing_files": []},
             "milvus": {"missing_collections": [], "missing_files": []},
             "total_missing_collections": 0,
-            "total_missing_files": 0
+            "total_missing_files": 0,
         }
 
         logger.info("开始检测向量数据库与元数据的一致性...")
@@ -573,10 +568,7 @@ class KnowledgeBaseManager:
                 if not collection_name.startswith("kb_"):
                     continue
 
-                collection_info = {
-                    "collection_name": collection_name,
-                    "detected_at": utc_isoformat()
-                }
+                collection_info = {"collection_name": collection_name, "detected_at": utc_isoformat()}
 
                 # 尝试获取集合的基本信息
                 try:
@@ -588,7 +580,10 @@ class KnowledgeBaseManager:
                     collection_info["count"] = "unknown"
 
                 inconsistencies["missing_collections"].append(collection_info)
-                logger.warning(f"发现 ChromaDB 中存在但 metadata 中缺失的集合: {collection_name} (文档数: {collection_info['count']})")
+                logger.warning(
+                    f"发现 ChromaDB 中存在但 metadata 中缺失的集合: {collection_name} "
+                    f"(文档数: {collection_info['count']})"
+                )
 
             # 检查文件级别的不一致（针对已知的数据库）
             for db_id in metadata_collection_names:
@@ -597,18 +592,23 @@ class KnowledgeBaseManager:
                     actual_count = collection.count()
 
                     # 获取 metadata 中记录的文件数量
-                    metadata_files_count = sum(1 for file_info in chroma_kb.files_meta.values()
-                                            if file_info.get("database_id") == db_id)
+                    metadata_files_count = sum(
+                        1 for file_info in chroma_kb.files_meta.values() if file_info.get("database_id") == db_id
+                    )
 
                     # 如果向量数据库中有数据但 metadata 中没有文件记录，可能存在文件缺失
                     if actual_count > 0 and metadata_files_count == 0:
-                        inconsistencies["missing_files"].append({
-                            "database_id": db_id,
-                            "vector_count": actual_count,
-                            "metadata_files_count": metadata_files_count,
-                            "detected_at": utc_isoformat()
-                        })
-                        logger.warning(f"发现数据库 {db_id} 在 ChromaDB 中有 {actual_count} 条向量数据，但 metadata 中没有文件记录")
+                        inconsistencies["missing_files"].append(
+                            {
+                                "database_id": db_id,
+                                "vector_count": actual_count,
+                                "metadata_files_count": metadata_files_count,
+                                "detected_at": utc_isoformat(),
+                            }
+                        )
+                        logger.warning(
+                            f"发现数据库 {db_id} 在 ChromaDB 中有 {actual_count} 条向量数据，但 metadata 中没有文件记录"
+                        )
 
                 except Exception as e:
                     logger.debug(f"检查数据库 {db_id} 的文件一致性时出错: {e}")
@@ -640,14 +640,12 @@ class KnowledgeBaseManager:
                 if not collection_name.startswith("kb_"):
                     continue
 
-                collection_info = {
-                    "collection_name": collection_name,
-                    "detected_at": utc_isoformat()
-                }
+                collection_info = {"collection_name": collection_name, "detected_at": utc_isoformat()}
 
                 # 尝试获取集合的基本信息
                 try:
                     from pymilvus import Collection
+
                     collection = Collection(name=collection_name, using=milvus_kb.connection_alias)
                     collection_info["count"] = collection.num_entities
                     collection_info["description"] = collection.description
@@ -656,30 +654,39 @@ class KnowledgeBaseManager:
                     collection_info["count"] = "unknown"
 
                 inconsistencies["missing_collections"].append(collection_info)
-                logger.warning(f"发现 Milvus 中存在但 metadata 中缺失的集合: {collection_name} (实体数: {collection_info['count']})")
-
+                logger.warning(
+                    f"发现 Milvus 中存在但 metadata 中缺失的集合: {collection_name} "
+                    f"(实体数: {collection_info['count']})"
+                )
 
             # 检查文件级别的不一致（针对已知的数据库）
             for db_id in metadata_collection_names:
                 try:
                     if utility.has_collection(db_id, using=milvus_kb.connection_alias):
                         from pymilvus import Collection
+
                         collection = Collection(name=db_id, using=milvus_kb.connection_alias)
                         actual_count = collection.num_entities
 
                         # 获取 metadata 中记录的文件数量
-                        metadata_files_count = sum(1 for file_info in milvus_kb.files_meta.values()
-                                                if file_info.get("database_id") == db_id)
+                        metadata_files_count = sum(
+                            1 for file_info in milvus_kb.files_meta.values() if file_info.get("database_id") == db_id
+                        )
 
                         # 如果向量数据库中有数据但 metadata 中没有文件记录，可能存在文件缺失
                         if actual_count > 0 and metadata_files_count == 0:
-                            inconsistencies["missing_files"].append({
-                                "database_id": db_id,
-                                "vector_count": actual_count,
-                                "metadata_files_count": metadata_files_count,
-                                "detected_at": utc_isoformat()
-                            })
-                            logger.warning(f"发现数据库 {db_id} 在 Milvus 中有 {actual_count} 条向量数据，但 metadata 中没有文件记录")
+                            inconsistencies["missing_files"].append(
+                                {
+                                    "database_id": db_id,
+                                    "vector_count": actual_count,
+                                    "metadata_files_count": metadata_files_count,
+                                    "detected_at": utc_isoformat(),
+                                }
+                            )
+                            logger.warning(
+                                f"发现数据库 {db_id} 在 Milvus 中有 {actual_count} 条向量数据，"
+                                "但 metadata 中没有文件记录"
+                            )
 
                 except Exception as e:
                     logger.debug(f"检查数据库 {db_id} 的文件一致性时出错: {e}")
@@ -706,25 +713,31 @@ class KnowledgeBaseManager:
         chroma_missing = inconsistencies["chroma"]["missing_collections"]
         chroma_files_missing = inconsistencies["chroma"]["missing_files"]
         if chroma_missing or chroma_files_missing:
-            logger.warning(f"ChromaDB 不一致情况：")
+            logger.warning("ChromaDB 不一致情况：")
             logger.warning(f"  缺失集合数量: {len(chroma_missing)}")
             for collection_info in chroma_missing:
                 logger.warning(f"    - 集合: {collection_info['collection_name']}, 向量数: {collection_info['count']}")
             logger.warning(f"  缺失文件记录数量: {len(chroma_files_missing)}")
             for file_info in chroma_files_missing:
-                logger.warning(f"    - 数据库: {file_info['database_id']}, 向量数: {file_info['vector_count']}, 元数据文件数: {file_info['metadata_files_count']}")
+                logger.warning(
+                    f"    - 数据库: {file_info['database_id']}, 向量数: {file_info['vector_count']}, "
+                    f"元数据文件数: {file_info['metadata_files_count']}"
+                )
 
         # Milvus 不一致情况
         milvus_missing = inconsistencies["milvus"]["missing_collections"]
         milvus_files_missing = inconsistencies["milvus"]["missing_files"]
         if milvus_missing or milvus_files_missing:
-            logger.warning(f"Milvus 不一致情况：")
+            logger.warning("Milvus 不一致情况：")
             logger.warning(f"  缺失集合数量: {len(milvus_missing)}")
             for collection_info in milvus_missing:
                 logger.warning(f"    - 集合: {collection_info['collection_name']}, 实体数: {collection_info['count']}")
             logger.warning(f"  缺失文件记录数量: {len(milvus_files_missing)}")
             for file_info in milvus_files_missing:
-                logger.warning(f"    - 数据库: {file_info['database_id']}, 向量数: {file_info['vector_count']}, 元数据文件数: {file_info['metadata_files_count']}")
+                logger.warning(
+                    f"    - 数据库: {file_info['database_id']}, 向量数: {file_info['vector_count']}, "
+                    f"元数据文件数: {file_info['metadata_files_count']}"
+                )
 
         logger.warning("=" * 80)
         logger.warning(f"总计：缺失集合 {total_missing_collections} 个，缺失文件记录 {total_missing_files} 个")
diff --git a/src/knowledge/utils/kb_utils.py b/src/knowledge/utils/kb_utils.py
index 4ff04916..e14c6106 100644
--- a/src/knowledge/utils/kb_utils.py
+++ b/src/knowledge/utils/kb_utils.py
@@ -211,7 +211,7 @@ def get_embedding_config(embed_info: dict) -> dict:
     try:
         if embed_info:
             # 处理 embed_info 可能是字典或 EmbedModelInfo 对象的情况
-            if hasattr(embed_info, 'name'):
+            if hasattr(embed_info, "name"):
                 # EmbedModelInfo 对象
                 config_dict["model"] = embed_info.name
                 config_dict["api_key"] = os.getenv(embed_info.api_key, embed_info.api_key)
diff --git a/src/storage/conversation/manager.py b/src/storage/conversation/manager.py
index 890c390c..2d590619 100644
--- a/src/storage/conversation/manager.py
+++ b/src/storage/conversation/manager.py
@@ -12,7 +12,8 @@ from src.storage.db.models import Conversation, ConversationStats, Message, Tool
 from src.utils import logger
 from src.utils.datetime_utils import utc_now
 
-#TODO:[未完成]待修改为异步版本
+# TODO:[未完成]待修改为异步版本
+
 
 class ConversationManager:
     """Manager for conversation storage operations"""
diff --git a/src/storage/db/manager.py b/src/storage/db/manager.py
index 0f06d4aa..b301540c 100644
--- a/src/storage/db/manager.py
+++ b/src/storage/db/manager.py
@@ -22,6 +22,7 @@ except ImportError:
 # TODO:[优化建议]需要将数据库修改为异步的aiosqlite或者异步mysql，缓存使用Redis存储
 # TODO:[已完成]为DBManager添加单例模式
 
+
 class DBManager(metaclass=SingletonMeta):
     """数据库管理器 - 只提供基础的数据库连接和会话管理"""