完成请求推送，但组装mes还有问题

backend/api/route.py

@@ -1,18 +1,26 @@
 from fastapi import APIRouter
-from .routes import presetsRoute, chatsRoute, worldbooksRoute, apiConfigRoute, charactersRoute
+from .routes import presetsRoute, chatsRoute, worldbooksRoute, apiConfigRoute, charactersRoute, chatWsRoute, tokenUsageRoute, imageGalleryRoute, regexRoute
 from utils.file_utils import get_all_roles_and_chats
 from core.config import settings
 from pathlib import Path
 
 router = APIRouter()
 
-# 注册子路由
+# 注册子路由（HTTP路由）
 router.include_router(presetsRoute.router)
 router.include_router(chatsRoute.router)
 router.include_router(worldbooksRoute.router)
 router.include_router(apiConfigRoute.router)
 router.include_router(charactersRoute.router)
 
+# ✅ 注册新增路由
+router.include_router(tokenUsageRoute.router)
+router.include_router(imageGalleryRoute.router)
+router.include_router(regexRoute.router)
+
+# ✅ 注册 WebSocket 路由（必须在 HTTP 路由之后，避免路径冲突）
+router.include_router(chatWsRoute.router)
+
 
 # 保留原有的其他路由
 @router.get("/tool_bar/get_all_role_and_chat")

backend/api/routes/apiConfigRoute.py

@@ -2,24 +2,28 @@ from fastapi import APIRouter, HTTPException, UploadFile, File
 from pydantic import BaseModel, Field
 from typing import Dict, Optional, List, Any
 import json
-import os
+import sys
 from pathlib import Path
 from core.config import settings
-from cryptography.fernet import Fernet
-import base64
 from services.comfyui_workflow_manager import workflow_manager
 from services.llm_model_service import LLMModelService
 
 router = APIRouter(prefix="/api-config", tags=["API Configuration"])
 
-# 加密密钥（实际项目中应该从环境变量读取）
-ENCRYPTION_KEY = os.getenv('API_ENCRYPTION_KEY', Fernet.generate_key().decode())
-fernet = Fernet(ENCRYPTION_KEY.encode() if isinstance(ENCRYPTION_KEY, str) else ENCRYPTION_KEY)
-
 # 配置文件路径
 CONFIG_DIR = Path(settings.DATA_PATH) / "apiconfig"
 CONFIG_DIR.mkdir(parents=True, exist_ok=True)
 
+# 调试信息：打印配置目录路径
+print(f"[API Config] DATA_PATH: {settings.DATA_PATH}", file=sys.stderr)
+print(f"[API Config] CONFIG_DIR: {CONFIG_DIR}", file=sys.stderr)
+print(f"[API Config] CONFIG_DIR exists: {CONFIG_DIR.exists()}", file=sys.stderr)
+if CONFIG_DIR.exists():
+    config_files = list(CONFIG_DIR.glob("*.json"))
+    print(f"[API Config] Found {len(config_files)} config files", file=sys.stderr)
+    for f in config_files:
+        print(f"  - {f.name}", file=sys.stderr)
+
 
 class ApiConfigItem(BaseModel):
     """单个 API 配置项"""
@@ -50,32 +54,8 @@ class ProfileResponse(BaseModel):
     apis: Dict[str, dict]  # apiKey 字段会被移除或脱敏
 
 
-def encrypt_api_key(api_key: str) -> str:
-    """加密 API Key"""
-    if not api_key:
-        return ""
-    encrypted = fernet.encrypt(api_key.encode())
-    return base64.urlsafe_b64encode(encrypted).decode()
 
 
-def decrypt_api_key(encrypted_key: str) -> str:
-    """解密 API Key（仅在后端内部使用）"""
-    if not encrypted_key:
-        return ""
-    try:
-        decoded = base64.urlsafe_b64decode(encrypted_key.encode())
-        decrypted = fernet.decrypt(decoded)
-        return decrypted.decode()
-    except Exception:
-        return ""
-
-
-def mask_api_key(api_key: str) -> str:
-    """脱敏 API Key（返回给前端）"""
-    if not api_key or len(api_key) < 8:
-        return "****"
-    return api_key[:4] + "****" + api_key[-4:]
-
 
 def load_profile(profile_id: str) -> Optional[dict]:
     """加载配置文件"""
@@ -119,29 +99,28 @@ def get_all_profiles():
 
 @router.get("/profiles/{profile_id}", response_model=ProfileResponse)
 def get_profile(profile_id: str):
-    """获取单个配置文件（API Key 已脱敏）"""
+    """获取单个配置文件（明文存储，不返回 API Key）"""
     profile = load_profile(profile_id)
     if not profile:
         raise HTTPException(status_code=404, detail="配置文件不存在")
     
-    # 脱敏所有 API Key
-    masked_apis = {}
+    # 移除 API Key 字段，不返回给前端
+    safe_apis = {}
     for category, api_config in profile.get("apis", {}).items():
-        masked_config = api_config.copy()
-        if "apiKey" in masked_config and masked_config["apiKey"]:
-            masked_config["apiKey"] = mask_api_key(masked_config["apiKey"])
-        masked_apis[category] = masked_config
+        safe_config = api_config.copy()
+        safe_config.pop("apiKey", None)
+        safe_apis[category] = safe_config
     
     return {
         "id": profile.get("id", profile_id),
         "name": profile.get("name", profile_id),
-        "apis": masked_apis
+        "apis": safe_apis
     }
 
 
 @router.post("/profiles", response_model=ProfileResponse)
 def create_or_update_profile(request: ProfileSaveRequest):
-    """创建或更新配置文件（增量更新）"""
+    """创建或更新配置文件（增量更新，明文存储 API Key）"""
     # 加载现有配置
     existing_profile = load_profile(request.profileId)
     
@@ -150,16 +129,11 @@ def create_or_update_profile(request: ProfileSaveRequest):
         for category, api_config in request.apis.items():
             api_config_dict = api_config.dict(exclude_none=True)
             
-            # 处理 API Key 加密
-            if api_config.apiKey and api_config.apiKey != "****":
-                # 如果是新的明文 key，加密它
-                api_config_dict["apiKey"] = encrypt_api_key(api_config.apiKey)
-            elif api_config.apiKey == "****":
-                # 如果是脱敏的 key，保留原有的加密 key
-                if category in existing_profile.get("apis", {}):
-                    api_config_dict["apiKey"] = existing_profile["apis"][category].get("apiKey", "")
-                else:
-                    api_config_dict.pop("apiKey", None)
+            # 如果前端传入了空的 apiKey，保留原有的 key
+            if api_config.apiKey == "" and category in existing_profile.get("apis", {}):
+                existing_key = existing_profile["apis"][category].get("apiKey", "")
+                if existing_key:
+                    api_config_dict["apiKey"] = existing_key
             
             # 更新配置
             if "apis" not in existing_profile:
@@ -177,28 +151,25 @@ def create_or_update_profile(request: ProfileSaveRequest):
             "apis": {}
         }
         
-        # 添加所有 API 配置
+        # 添加所有 API 配置（明文存储）
         for category, api_config in request.apis.items():
             api_config_dict = api_config.dict(exclude_none=True)
-            if api_config_dict.get("apiKey"):
-                api_config_dict["apiKey"] = encrypt_api_key(api_config_dict["apiKey"])
             profile_data["apis"][category] = api_config_dict
     
     # 保存配置文件
     save_profile(request.profileId, profile_data)
     
-    # 返回脱敏后的数据
-    masked_apis = {}
+    # 返回不包含 API Key 的数据
+    safe_apis = {}
     for category, api_config in profile_data.get("apis", {}).items():
-        masked_config = api_config.copy()
-        if "apiKey" in masked_config and masked_config["apiKey"]:
-            masked_config["apiKey"] = mask_api_key(masked_config["apiKey"])
-        masked_apis[category] = masked_config
+        safe_config = api_config.copy()
+        safe_config.pop("apiKey", None)
+        safe_apis[category] = safe_config
     
     return {
         "id": profile_data.get("id", request.profileId),
         "name": profile_data.get("name", request.profileId),
-        "apis": masked_apis
+        "apis": safe_apis
     }
 
 
@@ -217,13 +188,31 @@ def delete_profile(profile_id: str):
 def test_connection(api_config: ApiConfigItem):
     """测试 API 连接并获取模型列表"""
     try:
+        api_key_to_use = api_config.apiKey or ""
+        
+        # 如果 API Key 为空，尝试从已保存的配置中获取
+        if not api_key_to_use and api_config.category:
+            # 遍历所有配置文件，找到包含该 category 的配置
+            for config_file in CONFIG_DIR.glob("*.json"):
+                try:
+                    with open(config_file, 'r', encoding='utf-8') as f:
+                        profile = json.load(f)
+                    
+                    # 检查是否包含该 category
+                    if api_config.category in profile.get("apis", {}):
+                        api_key_to_use = profile["apis"][api_config.category].get("apiKey", "")
+                        if api_key_to_use:
+                            break
+                except Exception:
+                    continue
+        
         # 检测提供商类型
         provider = LLMModelService.detect_provider(api_config.apiUrl)
         
         # 获取模型列表
         models = LLMModelService.get_models_by_provider(
             provider=provider,
-            api_key=api_config.apiKey or "",
+            api_key=api_key_to_use,
             api_url=api_config.apiUrl
         )
         

backend/api/routes/chatWsRoute.py

@@ -0,0 +1,420 @@
+"""
+聊天 WebSocket 路由
+处理实时对话生成
+"""
+from fastapi import APIRouter, WebSocket, WebSocketDisconnect
+from typing import Dict, Any
+import json
+import asyncio
+
+try:
+    from backend.services.chat_workflow_service import ChatWorkflowService
+    from backend.services.chat_service import ChatService
+    from backend.services.task_queue_manager import task_queue_manager
+    from backend.core.config import settings
+except ImportError:
+    from services.chat_workflow_service import ChatWorkflowService
+    from services.chat_service import ChatService
+    from services.task_queue_manager import task_queue_manager
+    from core.config import settings
+
+router = APIRouter(prefix="/chat", tags=["chat-websocket"])
+
+# 初始化服务
+workflow_service = ChatWorkflowService()
+chat_service = ChatService(settings.DATA_PATH)
+
+# ✅ 全局变量：用于存储需要中断的聊天会话
+interrupt_flags: Dict[str, bool] = {}
+
+
+@router.websocket("/{role_name}/{chat_name}/ws")
+async def websocket_chat_endpoint(
+    websocket: WebSocket,
+    role_name: str,
+    chat_name: str
+):
+    """
+    WebSocket 聊天端点
+    
+    接收前端发送的完整对话请求，调用工作流生成回复，支持流式输出
+    """
+    await websocket.accept()
+    print(f"\n{'='*80}")
+    print(f"[WebSocket] 📡 连接建立: {role_name}/{chat_name}")
+    print(f"{'='*80}\n")
+    
+    chat_id = f"{role_name}/{chat_name}"
+    
+    try:
+        while True:
+            # 1. 接收前端消息
+            data = await websocket.receive_text()
+            request_data = json.loads(data)
+            
+            # ✅ 检查是否是取消任务的请求
+            if request_data.get("type") == "cancel_task":
+                task_id = request_data.get("taskId")
+                print(f"[WebSocket] ❌ 收到取消任务请求: {task_id}")
+                
+                # ✅ 特殊处理：如果是 LLM 生成任务，需要中断当前流式生成
+                if task_id == "current_llm_generation":
+                    print(f"[WebSocket] 🛑 正在终止 LLM 流式生成...")
+                    # TODO: 实现 LLM 生成的中断逻辑
+                    # 目前只能通过关闭连接来终止
+                    
+                    await websocket.send_json({
+                        "type": "task_cancelled",
+                        "taskId": task_id,
+                        "success": True,
+                        "message": "LLM 生成已终止"
+                    })
+                else:
+                    # 取消其他类型的任务（图像生成、动态表格等）
+                    success = await task_queue_manager.cancel_task(task_id)
+                    
+                    await websocket.send_json({
+                        "type": "task_cancelled",
+                        "taskId": task_id,
+                        "success": success
+                    })
+                    print(f"[WebSocket] ✅ 任务取消结果: {success}")
+                continue
+            
+            print(f"\n{'-'*80}")
+            print(f"[WebSocket] 📨 收到请求:")
+            print(f"  - Floor: {request_data.get('floor')}")
+            print(f"  - Role: {request_data.get('currentRole')}")
+            print(f"  - Chat: {request_data.get('currentChat')}")
+            print(f"  - Stream: {request_data.get('stream', False)}")
+            print(f"  - Message Length: {len(request_data.get('mes', ''))}")
+            
+            # ✅ 打印 API 配置信息（隐藏密钥）
+            api_config = request_data.get('apiConfig', {})
+            current_profile = request_data.get('currentProfile', {})
+            profile_id = current_profile.get('id') if isinstance(current_profile, dict) else None
+            
+            print(f"  - Profile ID: {profile_id or 'N/A'}")
+            print(f"  - API URL: {api_config.get('api_url', 'N/A')[:50]}..." if len(api_config.get('api_url', '')) > 50 else f"  - API URL: {api_config.get('api_url', 'N/A')}")
+            print(f"  - Model: {api_config.get('model', 'N/A')}")
+            
+            # ✅ 始终从配置文件中读取 API Key（不信任前端传来的 Key）
+            if profile_id:
+                try:
+                    from .apiConfigRoute import load_profile
+                    
+                    profile = load_profile(profile_id)
+                    if profile:
+                        # 找到 mainLLM 的配置
+                        main_llm_config = profile.get('apis', {}).get('mainLLM', {})
+                        api_key = main_llm_config.get('apiKey', '')
+                        
+                        if api_key:
+                            # 使用明文 API Key
+                            api_config['api_key'] = api_key
+                            request_data['apiConfig'] = api_config
+                            print(f"  - API Key: ✅ 已从配置文件加载")
+                        else:
+                            print(f"  - API Key: ⚠️ 配置文件中未找到 Key")
+                    else:
+                        print(f"  - API Key: ❌ 无法加载配置文件: {profile_id}")
+                except Exception as e:
+                    print(f"  - API Key: ❌ 加载失败: {str(e)}")
+                    import traceback
+                    traceback.print_exc()
+            else:
+                print(f"  - API Key: ⚠️ 未提供 profileId，无法加载")
+            
+            print(f"{'-'*80}\n")
+            
+            # 2. 提取流式输出标志
+            stream_output = request_data.get("stream", False)
+            
+            if stream_output:
+                # === 真正的流式输出模式 ===
+                print(f"[WebSocket] 🌊 进入流式处理模式")
+                await _handle_stream_chat(
+                    websocket, role_name, chat_name, request_data, workflow_service
+                )
+            else:
+                # === 非流式输出模式 ===
+                print(f"[WebSocket] 📦 进入非流式处理模式")
+                result = await workflow_service.process_chat_request(request_data)
+                
+                if result["success"]:
+                    content = result["content"]
+                    
+                    print(f"\n[WebSocket] ✨ 生成成功，内容长度: {len(content)}")
+                    
+                    # ✅ 发送激活的世界书条目信息
+                    active_entries = result.get("activeEntries", [])
+                    print(f"[WebSocket] 📚 发送世界书激活信息: {len(active_entries)} 个条目")
+                    await websocket.send_json({
+                        "type": "worldbook_active",
+                        "entries": active_entries
+                    })
+                    
+                    # ✅ 发送任务ID信息
+                    task_ids = result.get("taskIds", {})
+                    if task_ids.get("imageWorkflow") or task_ids.get("dynamicTable"):
+                        print(f"[WebSocket] 📋 发送任务ID信息: {task_ids}")
+                        await websocket.send_json({
+                            "type": "tasks_created",
+                            "tasks": task_ids
+                        })
+                    
+                    # 一次性发送完整内容
+                    print(f"[WebSocket] 📤 发送完整内容 (chunk)")
+                    await websocket.send_json({
+                        "type": "chunk",
+                        "content": content
+                    })
+                    
+                    print(f"[WebSocket] ✅ 发送完成信号")
+                    await websocket.send_json({
+                        "type": "complete"
+                    })
+                    
+                    # 保存消息
+                    print(f"[WebSocket] 💾 保存消息到文件...")
+                    await _save_messages(role_name, chat_name, request_data, content)
+                    print(f"[WebSocket] ✅ 消息保存完成\n")
+                else:
+                    error_msg = result["error"]
+                    print(f"[WebSocket] ❌ 处理失败: {error_msg}")
+                    await websocket.send_json({
+                        "type": "error",
+                        "message": error_msg
+                    })
+    
+    except WebSocketDisconnect:
+        print(f"\n{'='*80}")
+        print(f"[WebSocket] 🔌 连接断开: {role_name}/{chat_name}")
+        print(f"{'='*80}\n")
+    except Exception as e:
+        print(f"\n{'='*80}")
+        print(f"[WebSocket] ⚠️ 错误: {str(e)}")
+        print(f"{'='*80}\n")
+        import traceback
+        traceback.print_exc()
+        try:
+            await websocket.send_json({
+                "type": "error",
+                "message": f"服务器错误: {str(e)}"
+            })
+        except:
+            pass
+    finally:
+        try:
+            await websocket.close()
+        except:
+            pass
+
+
+async def _handle_stream_chat(
+    websocket: WebSocket,
+    role_name: str,
+    chat_name: str,
+    request_data: Dict[str, Any],
+    workflow_service
+):
+    """
+    处理流式聊天请求
+    
+    Args:
+        websocket: WebSocket 连接
+        role_name: 角色名
+        chat_name: 聊天名
+        request_data: 请求数据
+        workflow_service: 工作流服务实例
+    """
+    try:
+        print(f"[StreamChat] 🚀 开始流式处理")
+        
+        # ✅ 第1步：加载角色卡
+        current_role = request_data.get("currentRole")
+        character_data = request_data.get("characterData")
+        
+        if character_data:
+            try:
+                from backend.models.internal import CharacterCard
+            except ImportError:
+                from models.internal import CharacterCard
+            character = CharacterCard(**character_data)
+        else:
+            from backend.services.character_service import CharacterService
+            character_service = CharacterService()
+            character = character_service.get_character_by_name(current_role)
+        
+        if not character:
+            print(f"[StreamChat] ❌ 错误: 无法加载角色 '{current_role}'")
+            await websocket.send_json({
+                "type": "error",
+                "message": f"角色 '{current_role}' 不存在"
+            })
+            return
+        
+        print(f"[StreamChat] ✅ 已加载角色卡: {character.name}")
+        
+        # ✅ 第2步：激活世界书条目（在LLM调用之前）
+        print(f"[StreamChat] 📚 正在激活世界书条目...")
+        active_entries = await workflow_service._collect_and_activate_worldbooks(
+            request_data,
+            character
+        )
+        
+        # ✅ 发送激活的世界书条目信息（在LLM调用前）
+        if active_entries:
+            print(f"[StreamChat] 📤 发送世界书激活信息: {len(active_entries)} 个条目")
+            await websocket.send_json({
+                "type": "worldbook_active",
+                "entries": active_entries
+            })
+        
+        # ✅ TODO: RAG检索（暂时为空，待实现）
+        rag_results = []
+        if rag_results:
+            print(f"[StreamChat] 🔍 发送 RAG 检索结果: {len(rag_results)} 条")
+            await websocket.send_json({
+                "type": "rag_results",
+                "results": rag_results
+            })
+        
+        # ✅ 第2步：启动并行任务（在LLM调用前创建任务ID）
+        options = request_data.get("options", {})
+        task_ids = {
+            "imageWorkflow": None,
+            "dynamicTable": None
+        }
+        
+        if options.get("imageWorkflow", False):
+            import uuid
+            chat_id = f"{role_name}/{chat_name}"
+            task_ids["imageWorkflow"] = f"img_{uuid.uuid4().hex[:8]}"
+            from backend.services.task_queue_manager import task_queue_manager, TaskType
+            await task_queue_manager.add_task(task_ids["imageWorkflow"], TaskType.IMAGE_WORKFLOW, chat_id)
+        
+        if options.get("dynamicTable", False):
+            import uuid
+            chat_id = f"{role_name}/{chat_name}"
+            task_ids["dynamicTable"] = f"tbl_{uuid.uuid4().hex[:8]}"
+            from backend.services.task_queue_manager import task_queue_manager, TaskType
+            await task_queue_manager.add_task(task_ids["dynamicTable"], TaskType.DYNAMIC_TABLE, chat_id)
+        
+        # ✅ 发送任务ID信息（在LLM调用前）
+        if task_ids.get("imageWorkflow") or task_ids.get("dynamicTable"):
+            print(f"[StreamChat] 📤 发送任务ID信息: {task_ids}")
+            await websocket.send_json({
+                "type": "tasks_created",
+                "tasks": task_ids
+            })
+        
+        # ✅ 第3步：调用LLM流式生成
+        chunk_count = 0
+        result = await workflow_service.process_chat_request_stream(
+            request_data,
+            on_chunk=lambda chunk: asyncio.create_task(
+                _send_chunk_with_log(websocket, chunk, chunk_count)
+            )
+        )
+        
+        if result["success"]:
+            content = result["content"]
+            
+            print(f"\n[StreamChat] ✨ 流式生成成功，总长度: {len(content)}")
+            
+            # 发送完成信号
+            print(f"[StreamChat] ✅ 发送完成信号")
+            await websocket.send_json({
+                "type": "complete"
+            })
+            
+            # 保存消息
+            print(f"[StreamChat] 💾 保存消息到文件...")
+            await _save_messages(role_name, chat_name, request_data, content)
+            print(f"[StreamChat] ✅ 消息保存完成\n")
+        else:
+            error_msg = result["error"]
+            print(f"[StreamChat] ❌ 流式处理失败: {error_msg}")
+            await websocket.send_json({
+                "type": "error",
+                "message": error_msg
+            })
+    
+    except Exception as e:
+        print(f"\n[StreamChat] ⚠️ 错误: {str(e)}")
+        import traceback
+        traceback.print_exc()
+        await websocket.send_json({
+            "type": "error",
+            "message": f"流式处理失败: {str(e)}"
+        })
+
+
+async def _send_chunk_with_log(websocket: WebSocket, chunk: str, chunk_count: list):
+    """
+    发送 chunk 并记录日志
+    
+    Args:
+        websocket: WebSocket 连接
+        chunk: 文本片段
+        chunk_count: 计数器（使用列表以便在闭包中修改）
+    """
+    chunk_count[0] += 1
+    if chunk_count[0] % 10 == 0:  # 每10个chunk记录一次
+        print(f"[StreamChat] 📤 已发送 {chunk_count[0]} 个 chunks")
+    
+    await websocket.send_json({"type": "chunk", "content": chunk})
+
+
+async def _save_messages(
+    role_name: str,
+    chat_name: str,
+    request_data: Dict[str, Any],
+    ai_response: str
+):
+    """
+    保存用户消息和AI回复到聊天文件
+    
+    Args:
+        role_name: 角色名
+        chat_name: 聊天名
+        request_data: 前端发送的请求数据
+        ai_response: AI生成的回复
+    """
+    try:
+        from datetime import datetime
+        
+        # 1. 保存用户消息
+        user_message = {
+            "id": f"msg_{datetime.now().timestamp()}_user",
+            "name": request_data.get("userName", "User"),
+            "is_user": True,
+            "is_system": False,
+            "sendDate": datetime.now().isoformat(),
+            "mes": request_data.get("mes", ""),
+            "chatId": f"{role_name}/{chat_name}",
+            "floor": request_data.get("floor", 0)
+        }
+        
+        chat_service.add_message(role_name, chat_name, user_message)
+        
+        # 2. 保存AI回复
+        ai_message = {
+            "id": f"msg_{datetime.now().timestamp()}_ai",
+            "name": request_data.get("characterName", role_name),
+            "is_user": False,
+            "is_system": False,
+            "sendDate": datetime.now().isoformat(),
+            "mes": ai_response,
+            "chatId": f"{role_name}/{chat_name}",
+            "floor": request_data.get("floor", 0) + 1
+        }
+        
+        chat_service.add_message(role_name, chat_name, ai_message)
+        
+        print(f"[WebSocket] 消息已保存: {role_name}/{chat_name}")
+        
+    except Exception as e:
+        print(f"[WebSocket] 保存消息失败: {e}")
+        # 不抛出异常，避免影响主流程

backend/api/routes/chatsRoute.py

@@ -43,7 +43,7 @@ async def list_role_chats(role_name: str):
 	except Exception as e:
 		raise HTTPException(status_code=500, detail=str(e))
 
-
+ 
 @router.post("/{role_name}", status_code=status.HTTP_201_CREATED)
 async def create_chat(role_name: str, chat_data: dict):
 	"""创建新聊天"""

backend/api/routes/imageGalleryRoute.py

@@ -0,0 +1,140 @@
+"""
+图片画廊路由
+
+提供图片查询、删除等管理接口
+"""
+from fastapi import APIRouter, HTTPException
+from typing import Dict, Any, List, Optional
+import os
+
+try:
+    from backend.services.image_metadata_service import image_metadata_service
+except ImportError:
+    from services.image_metadata_service import image_metadata_service
+
+router = APIRouter(prefix="/image-gallery", tags=["image-gallery"])
+
+
+@router.get("/stats")
+async def get_gallery_stats():
+    """获取画廊统计信息"""
+    return await image_metadata_service.get_gallery_stats()
+
+
+@router.get("/images/{chat_id}")
+async def get_chat_images(
+    chat_id: str,
+    floor: Optional[int] = None
+):
+    """
+    获取指定聊天的图片列表
+    
+    Args:
+        chat_id: 聊天ID (role_name/chat_name)
+        floor: 楼层号（可选）
+    """
+    images = await image_metadata_service.get_images_by_chat(chat_id, floor)
+    return {
+        "chatId": chat_id,
+        "totalImages": len(images),
+        "images": [img.model_dump() for img in images]
+    }
+
+
+@router.get("/images/role/{role_name}")
+async def get_role_images(role_name: str):
+    """获取指定角色的所有图片"""
+    images = await image_metadata_service.get_images_by_role(role_name)
+    return {
+        "roleName": role_name,
+        "totalImages": len(images),
+        "images": [img.model_dump() for img in images]
+    }
+
+
+@router.delete("/images/{chat_id}/{image_id}")
+async def delete_image(chat_id: str, image_id: str):
+    """
+    删除图片（元数据和文件）
+    
+    Args:
+        chat_id: 聊天ID
+        image_id: 图片ID
+    """
+    # 先获取元数据以得到文件路径
+    images = await image_metadata_service.get_images_by_chat(chat_id)
+    target_image = None
+    for img in images:
+        if img.id == image_id:
+            target_image = img
+            break
+    
+    if not target_image:
+        raise HTTPException(status_code=404, detail="图片不存在")
+    
+    # 删除元数据
+    success = await image_metadata_service.delete_image(chat_id, image_id)
+    
+    if not success:
+        raise HTTPException(status_code=500, detail="删除失败")
+    
+    # 删除实际文件
+    try:
+        file_path = image_metadata_service.get_image_full_path(target_image.filepath)
+        if file_path.exists():
+            file_path.unlink()
+    except Exception as e:
+        print(f"[ImageGallery] 删除文件失败: {e}")
+        # 不抛出异常，因为元数据已删除
+    
+    return {"message": "图片已删除"}
+
+
+@router.post("/images/{chat_id}/clear")
+async def clear_chat_images(chat_id: str):
+    """
+    清空指定聊天的所有图片
+    
+    Args:
+        chat_id: 聊天ID
+    """
+    count = await image_metadata_service.clear_chat_images(chat_id)
+    return {
+        "message": f"已清空 {count} 张图片",
+        "deletedCount": count
+    }
+
+
+@router.post("/images/{chat_id}/{image_id}/set-current")
+async def set_current_swipe(chat_id: str, image_id: str):
+    """
+    设置某张图片为当前显示的 swipe
+    
+    Args:
+        chat_id: 聊天ID
+        image_id: 图片ID
+    """
+    success = await image_metadata_service.set_current_swipe(chat_id, image_id)
+    
+    if not success:
+        raise HTTPException(status_code=404, detail="图片不存在")
+    
+    return {"message": "已设置为当前显示"}
+
+
+@router.get("/image/{filepath:path}")
+async def get_image(filepath: str):
+    """
+    获取图片文件
+    
+    Args:
+        filepath: 文件相对路径
+    """
+    from fastapi.responses import FileResponse
+    
+    file_path = image_metadata_service.get_image_full_path(filepath)
+    
+    if not file_path.exists():
+        raise HTTPException(status_code=404, detail="图片文件不存在")
+    
+    return FileResponse(str(file_path))

backend/api/routes/regexRoute.py

@@ -0,0 +1,248 @@
+"""
+正则规则 API 路由
+
+提供正则规则的 CRUD 操作和导入导出功能
+"""
+from fastapi import APIRouter, HTTPException, UploadFile, File
+from pydantic import BaseModel
+from typing import List, Optional
+import json
+import logging
+
+from services.regex_service import regex_service
+from models.regex_rules import RegexRule, RegexRuleset, RegexScope
+from services.system_settings_service import system_settings_service
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/api/regex", tags=["regex"])
+
+
+# ==================== 数据模型 ====================
+
+class RuleUpdateRequest(BaseModel):
+    """规则更新请求"""
+    rule: RegexRule
+    scope: RegexScope
+    name: Optional[str] = None  # 角色卡名称或预设名称（scope 为 CHARACTER/PRESET 时需要）
+
+
+class SystemSettingsUpdate(BaseModel):
+    """系统设置更新请求"""
+    thinkingTagPrefix: Optional[str] = None
+    thinkingTagSuffix: Optional[str] = None
+    currentPresetName: Optional[str] = None
+
+
+# ==================== 规则查询 ====================
+
+@router.get("/rules")
+async def get_rules(
+    character_name: Optional[str] = None,
+    preset_name: Optional[str] = None
+):
+    """
+    获取适用的正则规则列表
+    
+    Args:
+        character_name: 当前角色卡名称（可选）
+        preset_name: 当前预设名称（可选）
+    
+    Returns:
+        规则列表
+    """
+    try:
+        rules = regex_service.get_rules_for_context(character_name, preset_name)
+        return {
+            "success": True,
+            "rules": [rule.dict() for rule in rules],
+            "count": len(rules)
+        }
+    except Exception as e:
+        logger.error(f"获取规则失败: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.get("/rulesets/global")
+async def get_global_rulesets():
+    """获取所有全局规则集"""
+    try:
+        rulesets = list(regex_service.global_rulesets.values())
+        return {
+            "success": True,
+            "rulesets": [rs.dict() for rs in rulesets]
+        }
+    except Exception as e:
+        logger.error(f"获取全局规则集失败: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.get("/rulesets/character/{character_name}")
+async def get_character_ruleset(character_name: str):
+    """获取指定角色卡的规则集"""
+    try:
+        if character_name in regex_service.character_rulesets:
+            ruleset = regex_service.character_rulesets[character_name]
+            return {
+                "success": True,
+                "ruleset": ruleset.dict()
+            }
+        else:
+            return {
+                "success": True,
+                "ruleset": None
+            }
+    except Exception as e:
+        logger.error(f"获取角色规则集失败: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.get("/rulesets/preset/{preset_name}")
+async def get_preset_ruleset(preset_name: str):
+    """获取指定预设的规则集"""
+    try:
+        if preset_name in regex_service.preset_rulesets:
+            ruleset = regex_service.preset_rulesets[preset_name]
+            return {
+                "success": True,
+                "ruleset": ruleset.dict()
+            }
+        else:
+            return {
+                "success": True,
+                "ruleset": None
+            }
+    except Exception as e:
+        logger.error(f"获取预设规则集失败: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+# ==================== 规则管理 ====================
+
+@router.post("/rules")
+async def add_rule(request: RuleUpdateRequest):
+    """添加新规则"""
+    try:
+        regex_service.save_ruleset(
+            RegexRuleset(
+                id=request.rule.id,
+                name=request.rule.scriptName,
+                rules=[request.rule]
+            ),
+            request.scope,
+            request.name
+        )
+        
+        # 重新加载规则
+        regex_service._load_all_rules()
+        
+        return {
+            "success": True,
+            "message": "规则添加成功"
+        }
+    except Exception as e:
+        logger.error(f"添加规则失败: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.delete("/rules/{rule_id}")
+async def delete_rule(rule_id: str):
+    """删除规则（需要指定作用域和名称）"""
+    # TODO: 实现具体的删除逻辑
+    return {
+        "success": False,
+        "message": "暂未实现，请使用规则集级别的删除"
+    }
+
+
+# ==================== 规则导入导出 ====================
+
+@router.post("/import")
+async def import_rules(file: UploadFile = File(...)):
+    """
+    导入正则规则（支持 SillyTavern 格式）
+    
+    可以导入：
+    1. 单个规则文件（JSON 数组）
+    2. 规则集文件（JSON 对象）
+    """
+    try:
+        content = await file.read()
+        data = json.loads(content.decode('utf-8'))
+        
+        # 判断格式并导入
+        if isinstance(data, list):
+            # SillyTavern 格式 - 导入为全局规则
+            ruleset = regex_service._convert_sillytavern_format(data, file.filename.replace('.json', ''))
+            regex_service.save_ruleset(ruleset, RegexScope.GLOBAL)
+        elif isinstance(data, dict):
+            if 'rules' in data:
+                # 规则集格式
+                ruleset = RegexRuleset(**data)
+                regex_service.save_ruleset(ruleset, RegexScope.GLOBAL)
+            else:
+                raise ValueError("未知的文件格式")
+        else:
+            raise ValueError("无效的文件格式")
+        
+        # 重新加载规则
+        regex_service._load_all_rules()
+        
+        return {
+            "success": True,
+            "message": f"成功导入规则集: {ruleset.name}"
+        }
+    except Exception as e:
+        logger.error(f"导入规则失败: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.get("/export/global")
+async def export_global_rules():
+    """导出所有全局规则"""
+    try:
+        all_rulesets = list(regex_service.global_rulesets.values())
+        return {
+            "success": True,
+            "rulesets": [rs.dict() for rs in all_rulesets]
+        }
+    except Exception as e:
+        logger.error(f"导出规则失败: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+# ==================== 系统设置 ====================
+
+@router.get("/settings")
+async def get_system_settings():
+    """获取系统设置"""
+    try:
+        settings = system_settings_service.settings
+        return {
+            "success": True,
+            "settings": settings.dict()
+        }
+    except Exception as e:
+        logger.error(f"获取系统设置失败: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.put("/settings")
+async def update_system_settings(request: SystemSettingsUpdate):
+    """更新系统设置"""
+    try:
+        if request.thinkingTagPrefix is not None or request.thinkingTagSuffix is not None:
+            prefix = request.thinkingTagPrefix or system_settings_service.settings.thinkingTagPrefix
+            suffix = request.thinkingTagSuffix or system_settings_service.settings.thinkingTagSuffix
+            system_settings_service.update_thinking_tags(prefix, suffix)
+        
+        if request.currentPresetName is not None:
+            system_settings_service.update_current_preset(request.currentPresetName)
+        
+        return {
+            "success": True,
+            "message": "系统设置已更新"
+        }
+    except Exception as e:
+        logger.error(f"更新系统设置失败: {e}")
+        raise HTTPException(status_code=500, detail=str(e))

backend/api/routes/tokenUsageRoute.py

@@ -0,0 +1,130 @@
+"""
+Token 使用统计路由
+
+提供 token 使用情况的查询接口
+"""
+from fastapi import APIRouter, HTTPException
+from typing import Dict, Any, List, Optional
+
+try:
+    from backend.services.token_usage_service import token_usage_service
+except ImportError:
+    from services.token_usage_service import token_usage_service
+
+router = APIRouter(prefix="/token-usage", tags=["token-usage"])
+
+
+@router.get("/months")
+async def list_months():
+    """列出所有有数据的月份"""
+    return await token_usage_service.list_months()
+
+
+@router.get("/stats/{year}/{month}")
+async def get_monthly_stats(
+    year: int,
+    month: int,
+    role_name: Optional[str] = None,
+    chat_name: Optional[str] = None
+):
+    """
+    获取指定月份的统计数据
+    
+    Args:
+        year: 年份
+        month: 月份
+        role_name: 角色名称（可选）
+        chat_name: 聊天名称（可选）
+    """
+    if month < 1 or month > 12:
+        raise HTTPException(status_code=400, detail="月份必须在 1-12 之间")
+    
+    try:
+        stats = await token_usage_service.get_stats_by_month(
+            year=year,
+            month=month,
+            role_name=role_name,
+            chat_name=chat_name
+        )
+        return stats
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"获取统计数据失败: {str(e)}")
+
+
+@router.get("/api-urls")
+async def get_api_url_stats():
+    """
+    ✅ 获取按 API URL 分组的统计数据（快速查询）
+    
+    Returns:
+        {
+            "api_url_1": {
+                "totalPromptTokens": 1000,
+                "totalCompletionTokens": 2000,
+                "totalTokens": 3000,
+                "count": 10,
+                "firstUsed": 1234567890,
+                "lastUsed": 1234567899
+            },
+            ...
+        }
+    """
+    try:
+        stats = await token_usage_service.get_api_url_stats()
+        return stats
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"获取 API URL 统计失败: {str(e)}")
+
+
+@router.get("/daily/{year}/{month}")
+async def get_daily_stats(year: int, month: int):
+    """
+    ✅ 获取指定月份的每日统计数据（快速查询）
+    
+    Args:
+        year: 年份
+        month: 月份
+        
+    Returns:
+        {
+            "2024-01-01": {
+                "promptTokens": 1000,
+                "completionTokens": 2000,
+                "totalTokens": 3000,
+                "count": 10
+            },
+            ...
+        }
+    """
+    if month < 1 or month > 12:
+        raise HTTPException(status_code=400, detail="月份必须在 1-12 之间")
+    
+    try:
+        stats = await token_usage_service.get_daily_stats(year, month)
+        return stats
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"获取每日统计失败: {str(e)}")
+
+
+@router.get("/roles/{year}/{month}")
+async def get_available_roles(year: int, month: int):
+    """获取指定月份有数据的角色列表"""
+    if month < 1 or month > 12:
+        raise HTTPException(status_code=400, detail="月份必须在 1-12 之间")
+    
+    roles = await token_usage_service.get_available_roles(year, month)
+    return {"roles": roles}
+
+
+@router.get("/chats/{year}/{month}")
+async def get_available_chats(
+    year: int,
+    month: int,
+    role_name: Optional[str] = None
+):
+    """获取指定月份有数据的聊天列表"""
+    if month < 1 or month > 12:
+        raise HTTPException(status_code=400, detail="月份必须在 1-12 之间")
+    
+    chats = await token_usage_service.get_available_chats(year, month, role_name)
+    return {"chats": chats}

backend/core/config.py

@@ -19,13 +19,6 @@ load_dotenv(PROJECT_ROOT / ".env")
 
 
 class Settings:
-	# --- 主模型配置 ---
-	MAIN_LLM_API_KEY = os.getenv("MAIN_LLM_API_KEY")
-	MAIN_LLM_MODEL = os.getenv("MAIN_LLM_MODEL", "gpt-3.5-turbo")
-	MAIN_LLM_BASE_URL = os.getenv("MAIN_LLM_BASE_URL", "https://api.openai.com/v1")
-	MAIN_LLM_MAX_TOKENS = int(os.getenv("MAIN_LLM_MAX_TOKENS", "4096"))
-	MAIN_LLM_STREAM = os.getenv("MAIN_LLM_STREAM", "true").lower() == "true"
-
 	# --- 路径配置 (核心修改) ---
 
 	# 强制使用计算出的项目根目录，不再依赖 .env 中的 BASE_PATH
@@ -38,7 +31,8 @@ class Settings:
 	STATE_FILE = DATA_PATH / "state.json"
 	SCHEMA_FILE = DATA_PATH / "schema.json"
 	PRESETS_FILE = DATA_PATH / "presets.json"
-	REGEX_FILE = DATA_PATH / "regex_rules.json"
+	REGEX_FILE = DATA_PATH / "regex_rules.json"  # 正则规则文件
+	SYSTEM_SETTINGS_FILE = DATA_PATH / "system_settings.json"  # 系统设置文件
 	VECTORSTORE_PATH = DATA_PATH / "vectorstore"
 
 	# --- 业务数据目录 ---
@@ -49,8 +43,11 @@ class Settings:
 	# 预设目录
 	PRESET_PATH = DATA_PATH / "preset"
 
-	# 聊天记录目录
+	# 聊天记录目录（同时存放角色卡和聊天）
 	CHAT_PATH = DATA_PATH / "chat"
+	
+	# 兼容别名：用于代码中引用
+	CHATS_PATH = CHAT_PATH
 
 	# 临时文件目录
 	TEMP_PATH = DATA_PATH / "temp"
@@ -58,8 +55,8 @@ class Settings:
 	# ComfyUI 工作流目录
 	COMFYUI_WORKFLOWS_PATH = DATA_PATH / "comfyui_workflows"
 	
-	# 角色卡目录
-	CHARACTERS_PATH = DATA_PATH / "characters"
+	# 角色卡目录（已合并到 CHAT_PATH）
+	CHARACTERS_PATH = CHAT_PATH
 	
 	# 图片资源目录
 	IMAGES_PATH = DATA_PATH / "images"
@@ -78,6 +75,10 @@ class Settings:
 		]
 		for directory in directories:
 			directory.mkdir(parents=True, exist_ok=True)
+		
+		# 确保核心数据文件的父目录存在
+		for file_path in [self.STATE_FILE, self.SCHEMA_FILE, self.PRESETS_FILE, self.REGEX_FILE, self.SYSTEM_SETTINGS_FILE]:
+			file_path.parent.mkdir(parents=True, exist_ok=True)
 
 
 settings = Settings()

backend/models/internal.py

@@ -141,7 +141,14 @@ class CharacterCard(BaseModel):
     outputSchema: Optional[List[OutputSchemaField]] = Field(None, description="输出 schema 定义 (结构化输出)")
     avatarPath: Optional[str] = Field(None, description="角色头像路径")
     alternate_greetings: Optional[List[str]] = Field(None, description="替代问候语数组")
-    tags: Optional[List[str]] = Field(None, description="标签数组")
+    
+    # TODO: 拓展提示词设置（插件/拓展系统预留接口）
+    # - tableMaintenancePrompt: 用于指导 AI 维护动态表格（RPG状态、任务追踪等）
+    # - imageGenerationPrompt: 用于指导 AI 生成图片描述提示词
+    # 当前状态：字段已定义，默认值为 None，等待插件系统实现
+    tableMaintenancePrompt: Optional[str] = Field(None, description="动态表格维护提示词 - 指导 AI 如何更新表格数据")
+    imageGenerationPrompt: Optional[str] = Field(None, description="生图提示词模板 - 指导 AI 如何生成图片描述")
+    
     createdAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="创建时间戳")
     updatedAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="最后更新时间戳")
     lastChatAt: Optional[int] = Field(None, description="最后聊天时间戳")
@@ -300,3 +307,84 @@ class ChatRAGConfig(BaseModel):
     indexConfig: Optional[Dict[str, Any]] = Field(None, description="索引配置")
     createdAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="创建时间戳")
     updatedAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="最后更新时间戳")
+
+
+# ==================== Token 统计 ====================
+
+class TokenUsageStatus(str, Enum):
+    """Token 使用状态"""
+    COMPLETED = 'completed'    # 成功完成
+    INTERRUPTED = 'interrupted'  # 被用户中断
+    FAILED = 'failed'          # 请求失败（API错误等）
+
+
+class TokenUsageRecord(BaseModel):
+    """
+    Token 使用记录
+    
+    记录每次 LLM 调用的 token 使用情况，支持按时间、角色、聊天维度统计
+    """
+    id: str = Field(..., description="记录唯一标识符 (UUID)")
+    chatId: str = Field(..., description="聊天ID (role_name/chat_name)")
+    roleName: str = Field(..., description="角色名称")
+    chatName: str = Field(..., description="聊天名称")
+    messageId: Optional[str] = Field(None, description="关联的消息ID")
+    floor: Optional[int] = Field(None, description="楼层号")
+    
+    # Token 统计
+    promptTokens: int = Field(0, description="输入 token 数")
+    completionTokens: int = Field(0, description="输出 token 数")
+    totalTokens: int = Field(0, description="总 token 数")
+    
+    # 状态信息
+    status: TokenUsageStatus = Field(TokenUsageStatus.COMPLETED, description="请求状态")
+    errorMessage: Optional[str] = Field(None, description="错误信息（如果失败）")
+    
+    # 时间信息
+    timestamp: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="请求时间戳")
+    duration: Optional[float] = Field(None, description="请求耗时（秒）")
+    
+    # API 信息
+    model: Optional[str] = Field(None, description="使用的模型")
+    apiProvider: Optional[str] = Field(None, description="API 提供商")
+    apiUrl: Optional[str] = Field(None, description="API URL地址")
+
+
+# ==================== 图片元数据 ====================
+
+class ImageMetadata(BaseModel):
+    """
+    图片元数据
+    
+    记录生成的图片信息，绑定到角色/聊天的特定楼层
+    """
+    id: str = Field(..., description="图片唯一标识符 (UUID)")
+    chatId: str = Field(..., description="聊天ID (role_name/chat_name)")
+    roleName: str = Field(..., description="角色名称")
+    chatName: str = Field(..., description="聊天名称")
+    floor: int = Field(..., description="楼层号")
+    
+    # 图片信息
+    filename: str = Field(..., description="文件名")
+    filepath: str = Field(..., description="文件相对路径")
+    width: Optional[int] = Field(None, description="图片宽度")
+    height: Optional[int] = Field(None, description="图片高度")
+    fileSize: Optional[int] = Field(None, description="文件大小（字节）")
+    
+    # Swipe 支持
+    swipeIndex: int = Field(0, description="Swipe 索引（同一楼层多张图片）")
+    isCurrentSwipe: bool = Field(True, description="是否为当前显示的 swipe")
+    
+    # 生成信息
+    prompt: Optional[str] = Field(None, description="生成使用的提示词")
+    negativePrompt: Optional[str] = Field(None, description="负面提示词")
+    seed: Optional[int] = Field(None, description="随机种子")
+    model: Optional[str] = Field(None, description="使用的模型/checkpoint")
+    workflowName: Optional[str] = Field(None, description="使用的工作流名称")
+    
+    # 任务信息
+    taskId: Optional[str] = Field(None, description="关联的任务ID")
+    generationTime: Optional[float] = Field(None, description="生成耗时（秒）")
+    
+    # 时间信息
+    createdAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="创建时间戳")

backend/models/regex_rules.py

@@ -0,0 +1,164 @@
+"""
+正则替换规则模型
+
+兼容 SillyTavern 的正则系统，支持全局、角色卡、预设三种作用域。
+"""
+from enum import Enum
+from typing import List, Optional, Dict, Any
+from pydantic import BaseModel, Field
+from datetime import datetime
+
+
+class RegexPlacement(int, Enum):
+    """
+    正则应用位置（对应 SillyTavern 的 placement 数组）
+    
+    0: System Prompt - 系统提示词
+    1: User Input - 用户输入
+    2: AI Output - AI 输出
+    3: Quick Reply - 快捷回复
+    4: World Info - 世界书信息
+    5: Reasoning/Thinking - 推理/思考内容
+    """
+    SYSTEM_PROMPT = 0
+    USER_INPUT = 1
+    AI_OUTPUT = 2
+    QUICK_REPLY = 3
+    WORLD_INFO = 4
+    REASONING = 5
+
+
+class RegexScope(str, Enum):
+    """
+    正则规则作用域
+    
+    - GLOBAL: 全局生效，对所有聊天应用
+    - CHARACTER: 绑定到特定角色卡
+    - PRESET: 绑定到特定预设
+    """
+    GLOBAL = 'global'
+    CHARACTER = 'character'
+    PRESET = 'preset'
+
+
+class SubstituteMode(int, Enum):
+    """
+    替换模式
+    
+    对应 SillyTavern 的 substituteRegex 字段
+    """
+    REPLACE_ALL = 0        # 替换所有匹配
+    REPLACE_FIRST = 1      # 仅替换首次匹配
+    REPLACE_CAPTURED = 2   # 替换捕获组
+
+
+class RegexRule(BaseModel):
+    """
+    单条正则替换规则
+    
+    完全兼容 SillyTavern 的正则规则格式
+    """
+    id: str = Field(..., description="规则唯一标识符 (UUID)")
+    scriptName: str = Field(..., description="脚本名称（用于显示）")
+    
+    # 核心正则配置
+    findRegex: str = Field(..., description="查找正则表达式（如：/<thinking>[\\s\\S]*?<\\/thinking>/gi）")
+    replaceString: str = Field("", description="替换字符串（支持捕获组引用 $1, $2 等）")
+    trimStrings: List[str] = Field(default_factory=list, description="要额外修剪的字符串数组")
+    
+    # 应用位置（关键！对应 SillyTavern 的 placement 数组）
+    placement: List[RegexPlacement] = Field(
+        default_factory=lambda: [RegexPlacement.AI_OUTPUT],
+        description="应用位置数组：0=系统提示词, 1=用户输入, 2=AI输出, 3=快捷回复, 4=世界书, 5=推理内容"
+    )
+    
+    # 替换模式
+    substituteRegex: SubstituteMode = Field(
+        SubstituteMode.REPLACE_ALL, 
+        description="替换模式：0=全部，1=首次，2=捕获组"
+    )
+    
+    # 作用范围控制
+    markdownOnly: bool = Field(False, description="是否仅应用于 Markdown 渲染后的内容")
+    promptOnly: bool = Field(False, description="是否仅应用于发送给 LLM 的提示词")
+    runOnEdit: bool = Field(True, description="用户编辑消息时是否重新应用")
+    
+    # 消息深度控制
+    minDepth: int = Field(0, ge=0, description="最小消息深度（从最新消息开始计数）")
+    maxDepth: Optional[int] = Field(None, ge=0, description="最大消息深度（None 表示无限制）")
+    
+    # 作用域配置
+    scope: RegexScope = Field(RegexScope.GLOBAL, description="规则作用域")
+    characterName: Optional[str] = Field(None, description="绑定的角色卡名称（scope=CHARACTER 时使用）")
+    presetName: Optional[str] = Field(None, description="绑定的预设名称（scope=PRESET 时使用）")
+    
+    # 启用状态
+    disabled: bool = Field(False, description="是否禁用此规则（与 enabled 相反，为了兼容 ST）")
+    
+    # 执行顺序
+    order: int = Field(0, description="执行顺序（数值越小越先执行）")
+    
+    # 元数据
+    createdAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="创建时间戳")
+    updatedAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="最后更新时间戳")
+    description: Optional[str] = Field(None, description="规则描述（可选）")
+
+
+class RegexRuleset(BaseModel):
+    """
+    正则规则集
+    
+    一组正则规则的集合，可以整体导入/导出，兼容 SillyTavern 格式
+    """
+    id: str = Field(..., description="规则集唯一标识符 (UUID)")
+    name: str = Field(..., description="规则集名称")
+    description: Optional[str] = Field(None, description="规则集描述")
+    
+    rules: List[RegexRule] = Field(default_factory=list, description="规则列表")
+    
+    # 元数据
+    createdAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="创建时间戳")
+    updatedAt: int = Field(default_factory=lambda: int(datetime.now().timestamp()), description="最后更新时间戳")
+    version: int = Field(1, description="版本号（用于数据迁移）")
+    
+    # SillyTavern 兼容性标记
+    isSillyTavernFormat: bool = Field(False, description="是否为 SillyTavern 导入格式")
+
+
+# ==================== 使用示例 ====================
+
+if __name__ == '__main__':
+    import json
+    
+    # 创建一条规则
+    rule = RegexRule(
+        id="example-hide-thinking-001",
+        scriptName="隐藏思考标签",
+        findRegex=r"<thinking>[\s\S]*?<\/thinking>",
+        replaceString="",
+        trimStrings=[],
+        placement=[RegexPlacement.AI_OUTPUT],
+        substituteRegex=SubstituteMode.REPLACE_ALL,
+        markdownOnly=False,
+        promptOnly=False,
+        runOnEdit=True,
+        minDepth=0,
+        maxDepth=None,
+        scope=RegexScope.GLOBAL,
+        characterName=None,
+        presetName=None,
+        disabled=False,
+        order=1,
+        description="隐藏 AI 回复中的 <thinking> 标签及其内容"
+    )
+    
+    # 创建规则集
+    ruleset = RegexRuleset(
+        id="ruleset-001",
+        name="默认正则规则集",
+        description="包含常用的文本处理规则",
+        rules=[rule]
+    )
+    
+    # 导出为 JSON（兼容 SillyTavern）
+    print(json.dumps(ruleset.dict(), indent=2, ensure_ascii=False))

backend/models/system_settings.py

@@ -0,0 +1,49 @@
+"""
+系统设置模型
+
+包含全局配置，如思考标签前后缀等。
+"""
+from typing import Optional
+from pydantic import BaseModel, Field
+from datetime import datetime
+
+
+class SystemSettings(BaseModel):
+    """
+    系统全局设置
+    
+    持久化存储到 data/system_settings.json
+    """
+    
+    # ==================== 思考标签配置 ====================
+    thinkingTagPrefix: str = Field(
+        "<thinking>",
+        description="思考标签前缀（默认：<thinking>）"
+    )
+    thinkingTagSuffix: str = Field(
+        "</thinking>",
+        description="思考标签后缀（默认：</thinking>）"
+    )
+    
+    # ==================== 当前选中的预设 ====================
+    currentPresetName: Optional[str] = Field(
+        None,
+        description="当前选中的预设名称（用于确定全局正则的作用域）"
+    )
+    
+    # ==================== 元数据 ====================
+    updatedAt: int = Field(
+        default_factory=lambda: int(datetime.now().timestamp()),
+        description="最后更新时间戳"
+    )
+    version: int = Field(1, description="版本号")
+
+
+# ==================== 默认设置 ====================
+
+DEFAULT_SYSTEM_SETTINGS = SystemSettings()
+
+
+if __name__ == '__main__':
+    import json
+    print(json.dumps(DEFAULT_SYSTEM_SETTINGS.dict(), indent=2, ensure_ascii=False))

backend/services/character_service.py

@@ -177,8 +177,8 @@ class CharacterService:
         更新角色卡
         
         Args:
-            name: 角色名
-            updates: 更新的字段
+            name: 角色名（旧名称，用于定位文件夹）
+            updates: 更新的字段（可以包含 name 字段来重命名）
         
         Returns:
             更新后的 CharacterCard 对象
@@ -193,6 +193,29 @@ class CharacterService:
         with open(char_file, 'r', encoding='utf-8') as f:
             existing_data = json.load(f)
         
+        # 检查是否需要重命名
+        new_name = updates.get('name')
+        needs_rename = new_name and new_name != name
+        
+        if needs_rename:
+            # 验证新名称是否合法
+            if not new_name or new_name.strip() == '':
+                raise ValueError("角色名不能为空")
+            
+            # 检查新名称是否已存在
+            new_folder = self.characters_dir / new_name
+            if new_folder.exists():
+                raise FileExistsError(f"角色 '{new_name}' 已存在")
+            
+            # 重命名文件夹
+            try:
+                import shutil
+                shutil.move(str(char_folder), str(new_folder))
+                char_folder = new_folder
+                char_file = char_folder / "character.json"
+            except Exception as e:
+                raise RuntimeError(f"重命名文件夹失败: {str(e)}")
+        
         # 合并更新
         existing_data.update(updates)
         existing_data['updatedAt'] = int(datetime.now().timestamp())

backend/services/chat_service.py

@@ -57,7 +57,7 @@ class ChatService:
                 logger.error(f"处理角色目录 {role_dir.name} 时出错: {str(e)}")
                 continue
         
-        return {"chat": [{"role_name": role, **chat} for role, chats in result.items() for chat in chats]}
+        return result
     
     def _get_chat_summary(self, role_name: str, chat_name: str) -> Optional[Dict]:
         """
@@ -197,7 +197,8 @@ class ChatService:
         tags = []
         
         try:
-            character_file = Path("data/characters") / role_name / "character.json"
+            from backend.core.config import settings
+            character_file = settings.CHARACTERS_PATH / role_name / "character.json"
             if character_file.exists():
                 with open(character_file, 'r', encoding='utf-8') as f:
                     character_data = json.load(f)

backend/services/image_metadata_service.py

@@ -0,0 +1,346 @@
+"""
+图片元数据服务
+
+负责管理生成图片的元数据，支持绑定到角色/聊天的特定楼层
+数据持久化到 data/image_metadata 目录
+"""
+import json
+import uuid
+from pathlib import Path
+from typing import List, Dict, Optional, Any
+from datetime import datetime
+
+try:
+    from backend.models.internal import ImageMetadata
+    from backend.core.config import settings
+except ImportError:
+    from models.internal import ImageMetadata
+    from core.config import settings
+
+
+class ImageMetadataService:
+    """
+    图片元数据服务
+    
+    功能：
+    - 记录生成图片的元数据
+    - 按角色/聊天/楼层组织
+    - 支持 swipe（同一楼层多张图片）
+    - 提供画廊查询接口
+    """
+    
+    def __init__(self):
+        self.metadata_dir = settings.DATA_PATH / "image_metadata"
+        self.metadata_dir.mkdir(parents=True, exist_ok=True)
+        
+        # 图片存储目录
+        self.images_dir = settings.DATA_PATH / "images"
+        self.images_dir.mkdir(parents=True, exist_ok=True)
+    
+    def _get_chat_metadata_file(self, chat_id: str) -> Path:
+        """获取指定聊天的元数据文件路径"""
+        # chat_id 格式: role_name/chat_name
+        parts = chat_id.split("/")
+        if len(parts) == 2:
+            role_name, chat_name = parts
+            role_dir = self.metadata_dir / role_name
+            role_dir.mkdir(parents=True, exist_ok=True)
+            return role_dir / f"{chat_name}.json"
+        else:
+            #  fallback
+            return self.metadata_dir / f"{chat_id.replace('/', '_')}.json"
+    
+    def _load_chat_metadata(self, chat_id: str) -> List[ImageMetadata]:
+        """加载指定聊天的所有图片元数据"""
+        file_path = self._get_chat_metadata_file(chat_id)
+        
+        if not file_path.exists():
+            return []
+        
+        try:
+            with open(file_path, 'r', encoding='utf-8') as f:
+                data = json.load(f)
+                return [ImageMetadata(**item) for item in data]
+        except Exception as e:
+            print(f"[ImageMetadata] 加载元数据失败: {e}")
+            return []
+    
+    def _save_chat_metadata(self, chat_id: str, metadata_list: List[ImageMetadata]):
+        """保存聊天的所有图片元数据"""
+        file_path = self._get_chat_metadata_file(chat_id)
+        
+        try:
+            data = [m.model_dump() for m in metadata_list]
+            with open(file_path, 'w', encoding='utf-8') as f:
+                json.dump(data, f, ensure_ascii=False, indent=2)
+        except Exception as e:
+            print(f"[ImageMetadata] 保存元数据失败: {e}")
+    
+    async def add_image(
+        self,
+        chat_id: str,
+        role_name: str,
+        chat_name: str,
+        floor: int,
+        filename: str,
+        filepath: str,
+        prompt: Optional[str] = None,
+        negative_prompt: Optional[str] = None,
+        seed: Optional[int] = None,
+        model: Optional[str] = None,
+        workflow_name: Optional[str] = None,
+        task_id: Optional[str] = None,
+        generation_time: Optional[float] = None,
+        width: Optional[int] = None,
+        height: Optional[int] = None,
+        file_size: Optional[int] = None
+    ) -> ImageMetadata:
+        """
+        添加图片元数据
+        
+        Args:
+            chat_id: 聊天ID
+            role_name: 角色名称
+            chat_name: 聊天名称
+            floor: 楼层号
+            filename: 文件名
+            filepath: 文件相对路径
+            prompt: 提示词
+            negative_prompt: 负面提示词
+            seed: 随机种子
+            model: 使用的模型
+            workflow_name: 工作流名称
+            task_id: 任务ID
+            generation_time: 生成耗时
+            width: 图片宽度
+            height: 图片高度
+            file_size: 文件大小
+            
+        Returns:
+            ImageMetadata: 创建的元数据
+        """
+        metadata_list = self._load_chat_metadata(chat_id)
+        
+        # 计算 swipe_index
+        same_floor_images = [m for m in metadata_list if m.floor == floor]
+        swipe_index = len(same_floor_images)
+        
+        # 如果这是该楼层的第一张图片，将其他图片的 isCurrentSwipe 设为 False
+        if swipe_index == 0:
+            for m in metadata_list:
+                if m.floor == floor:
+                    m.isCurrentSwipe = False
+        
+        metadata = ImageMetadata(
+            id=str(uuid.uuid4()),
+            chatId=chat_id,
+            roleName=role_name,
+            chatName=chat_name,
+            floor=floor,
+            filename=filename,
+            filepath=filepath,
+            prompt=prompt,
+            negativePrompt=negative_prompt,
+            seed=seed,
+            model=model,
+            workflowName=workflow_name,
+            taskId=task_id,
+            generationTime=generation_time,
+            width=width,
+            height=height,
+            fileSize=file_size,
+            swipeIndex=swipe_index,
+            isCurrentSwipe=True
+        )
+        
+        metadata_list.append(metadata)
+        self._save_chat_metadata(chat_id, metadata_list)
+        
+        return metadata
+    
+    async def get_images_by_chat(
+        self,
+        chat_id: str,
+        floor: Optional[int] = None
+    ) -> List[ImageMetadata]:
+        """
+        获取指定聊天的图片列表
+        
+        Args:
+            chat_id: 聊天ID
+            floor: 楼层号（可选，用于过滤）
+            
+        Returns:
+            图片元数据列表
+        """
+        metadata_list = self._load_chat_metadata(chat_id)
+        
+        if floor is not None:
+            metadata_list = [m for m in metadata_list if m.floor == floor]
+        
+        # 按楼层和 swipe_index 排序
+        metadata_list.sort(key=lambda m: (m.floor, m.swipeIndex))
+        
+        return metadata_list
+    
+    async def get_images_by_role(self, role_name: str) -> List[ImageMetadata]:
+        """获取指定角色的所有图片"""
+        all_images = []
+        
+        role_dir = self.metadata_dir / role_name
+        if not role_dir.exists():
+            return []
+        
+        for chat_file in role_dir.glob("*.json"):
+            chat_name = chat_file.stem
+            chat_id = f"{role_name}/{chat_name}"
+            images = self._load_chat_metadata(chat_id)
+            all_images.extend(images)
+        
+        # 按创建时间排序
+        all_images.sort(key=lambda m: m.createdAt, reverse=True)
+        
+        return all_images
+    
+    async def delete_image(self, chat_id: str, image_id: str) -> bool:
+        """
+        删除图片元数据（不删除实际文件）
+        
+        Args:
+            chat_id: 聊天ID
+            image_id: 图片ID
+            
+        Returns:
+            bool: 是否成功删除
+        """
+        metadata_list = self._load_chat_metadata(chat_id)
+        
+        # 找到要删除的图片
+        target_image = None
+        for m in metadata_list:
+            if m.id == image_id:
+                target_image = m
+                break
+        
+        if not target_image:
+            return False
+        
+        floor = target_image.floor
+        swipe_index = target_image.swipeIndex
+        
+        # 删除该图片
+        metadata_list = [m for m in metadata_list if m.id != image_id]
+        
+        # 重新调整同一楼层其他图片的 swipe_index
+        same_floor_images = [m for m in metadata_list if m.floor == floor]
+        same_floor_images.sort(key=lambda m: m.swipeIndex)
+        
+        for idx, m in enumerate(same_floor_images):
+            m.swipeIndex = idx
+            m.isCurrentSwipe = (idx == 0)  # 第一个为当前显示
+        
+        self._save_chat_metadata(chat_id, metadata_list)
+        return True
+    
+    async def clear_chat_images(self, chat_id: str) -> int:
+        """
+        清空指定聊天的所有图片元数据
+        
+        Args:
+            chat_id: 聊天ID
+            
+        Returns:
+            int: 删除的图片数量
+        """
+        metadata_list = self._load_chat_metadata(chat_id)
+        count = len(metadata_list)
+        
+        # 清空元数据文件
+        file_path = self._get_chat_metadata_file(chat_id)
+        if file_path.exists():
+            file_path.unlink()
+        
+        return count
+    
+    async def set_current_swipe(self, chat_id: str, image_id: str) -> bool:
+        """
+        设置某张图片为当前显示的 swipe
+        
+        Args:
+            chat_id: 聊天ID
+            image_id: 图片ID
+            
+        Returns:
+            bool: 是否成功设置
+        """
+        metadata_list = self._load_chat_metadata(chat_id)
+        
+        target_image = None
+        for m in metadata_list:
+            if m.id == image_id:
+                target_image = m
+                break
+        
+        if not target_image:
+            return False
+        
+        floor = target_image.floor
+        
+        # 将同一楼层的所有图片设为非当前
+        for m in metadata_list:
+            if m.floor == floor:
+                m.isCurrentSwipe = False
+        
+        # 设置目标图片为当前
+        target_image.isCurrentSwipe = True
+        
+        self._save_chat_metadata(chat_id, metadata_list)
+        return True
+    
+    async def get_gallery_stats(self) -> Dict[str, Any]:
+        """
+        获取画廊统计信息
+        
+        Returns:
+            统计信息字典
+        """
+        stats = {
+            "totalImages": 0,
+            "byRole": {},
+            "byChat": {}
+        }
+        
+        if not self.metadata_dir.exists():
+            return stats
+        
+        for role_dir in self.metadata_dir.iterdir():
+            if not role_dir.is_dir():
+                continue
+            
+            role_name = role_dir.name
+            role_count = 0
+            
+            for chat_file in role_dir.glob("*.json"):
+                chat_name = chat_file.stem
+                chat_id = f"{role_name}/{chat_name}"
+                images = self._load_chat_metadata(chat_id)
+                
+                chat_count = len(images)
+                role_count += chat_count
+                stats["totalImages"] += chat_count
+                
+                if chat_count > 0:
+                    stats["byChat"][chat_id] = chat_count
+            
+            if role_count > 0:
+                stats["byRole"][role_name] = role_count
+        
+        return stats
+    
+    def get_image_full_path(self, filepath: str) -> Path:
+        """获取图片的完整路径"""
+        return self.images_dir / filepath
+
+
+# 全局实例
+image_metadata_service = ImageMetadataService()

backend/services/llm_model_service.py

@@ -27,18 +27,35 @@ class LLMModelService:
             if not base_url:
                 base_url = "https://api.openai.com/v1"
             
-            # 确保 base_url 以 /v1 结尾
-            if not base_url.endswith('/v1'):
-                base_url = base_url.rstrip('/') + '/v1'
+            # 规范化 base_url：确保有协议前缀
+            base_url = base_url.strip()
+            if not base_url.startswith(('http://', 'https://')):
+                base_url = 'https://' + base_url
             
-            response = requests.get(
-                f"{base_url}/models",
-                headers={
-                    "Authorization": f"Bearer {api_key}",
-                    "Content-Type": "application/json"
-                },
-                timeout=10
-            )
+            # 移除末尾的斜杠和常见 endpoint 路径
+            base_url = base_url.rstrip('/')
+            # 移除可能已经存在的 endpoint 路径
+            for endpoint in ['/chat/completions', '/completions', '/embeddings', '/models']:
+                if base_url.endswith(endpoint):
+                    base_url = base_url[:-len(endpoint)]
+                    break
+            
+            # 调用 models API
+            try:
+                response = requests.get(
+                    f"{base_url}/models",
+                    headers={
+                        "Authorization": f"Bearer {api_key}",
+                        "Content-Type": "application/json"
+                    },
+                    timeout=10
+                )
+            except requests.exceptions.InvalidSchema as e:
+                raise Exception(f"URL 格式错误: {base_url}/models - 请确保 URL 以 http:// 或 https:// 开头")
+            except requests.exceptions.ConnectionError as e:
+                raise Exception(f"无法连接到 API: {base_url}/models - 请检查网络连接和 API 地址")
+            except requests.exceptions.Timeout as e:
+                raise Exception(f"请求超时: {base_url}/models - 请检查网络连接")
             
             if response.status_code != 200:
                 raise Exception(f"HTTP {response.status_code}: {response.text}")
@@ -46,14 +63,8 @@ class LLMModelService:
             data = response.json()
             models = [model['id'] for model in data.get('data', [])]
             
-            # 过滤出聊天模型（可选）
-            chat_models = [
-                m for m in models 
-                if any(keyword in m.lower() for keyword in ['gpt', 'chat'])
-            ]
-            
-            # 如果没有找到聊天模型，返回所有模型
-            return chat_models if chat_models else models
+            # 返回所有模型，不做过滤
+            return models
             
         except Exception as e:
             raise Exception(f"获取 OpenAI 模型列表失败: {str(e)}")
@@ -132,6 +143,9 @@ class LLMModelService:
             return 'anthropic'
         elif 'ollama' in api_url_lower or 'localhost:11434' in api_url_lower or '127.0.0.1:11434' in api_url_lower:
             return 'ollama'
+        elif 'bigmodel' in api_url_lower or 'glm' in api_url_lower:
+            # 智谱AI GLM - 兼容 OpenAI API
+            return 'openai'
         elif 'siliconflow' in api_url_lower or 'silicon.cloud' in api_url_lower:
             # SiliconFlow 等兼容 OpenAI API 的服务
             return 'openai'

backend/services/regex_service.py

@@ -0,0 +1,332 @@
+"""
+正则规则服务（重构版 - 文件夹结构）
+
+负责加载、管理和应用正则替换规则。
+使用文件夹结构组织规则，兼容 SillyTavern 格式。
+
+文件结构：
+data/regex/
+├── global/              # 全局规则
+│   └── default.json
+├── characters/          # 角色卡绑定规则
+│   └── {characterName}.json
+└── presets/             # 预设绑定规则
+    └── {presetName}.json
+"""
+import re
+import json
+import logging
+from pathlib import Path
+from typing import List, Optional, Dict
+from uuid import uuid4
+
+from core.config import settings
+from models.regex_rules import RegexRule, RegexRuleset, RegexScope, RegexPlacement, SubstituteMode
+from services.system_settings_service import system_settings_service
+
+logger = logging.getLogger(__name__)
+
+
+class RegexService:
+    """
+    正则替换规则服务（文件夹结构版）
+    """
+    
+    def __init__(self):
+        self.regex_base_path = settings.DATA_PATH / "regex"
+        self.global_path = self.regex_base_path / "global"
+        self.characters_path = self.regex_base_path / "characters"
+        self.presets_path = self.regex_base_path / "presets"
+        
+        # 内存缓存
+        self.global_rulesets: Dict[str, RegexRuleset] = {}
+        self.character_rulesets: Dict[str, RegexRuleset] = {}  # key: characterName
+        self.preset_rulesets: Dict[str, RegexRuleset] = {}     # key: presetName
+        
+        self._ensure_directories()
+        self._load_all_rules()
+    
+    def _ensure_directories(self):
+        """确保目录结构存在"""
+        for path in [self.regex_base_path, self.global_path, self.characters_path, self.presets_path]:
+            path.mkdir(parents=True, exist_ok=True)
+    
+    def _load_all_rules(self):
+        """加载所有规则"""
+        self._load_global_rules()
+        self._load_character_rules()
+        self._load_preset_rules()
+    
+    def _load_global_rules(self):
+        """加载全局规则"""
+        if not self.global_path.exists():
+            return
+        
+        for json_file in self.global_path.glob("*.json"):
+            try:
+                with open(json_file, 'r', encoding='utf-8') as f:
+                    data = json.load(f)
+                
+                if isinstance(data, list):
+                    # SillyTavern 格式
+                    ruleset = self._convert_sillytavern_format(data, json_file.stem)
+                elif isinstance(data, dict) and 'rules' in data:
+                    # 我们的规则集格式
+                    ruleset = RegexRuleset(**data)
+                else:
+                    logger.warning(f"未知的规则文件格式: {json_file}")
+                    continue
+                
+                self.global_rulesets[ruleset.id] = ruleset
+                logger.info(f"加载全局规则集: {ruleset.name} ({len(ruleset.rules)} 条规则)")
+            except Exception as e:
+                logger.error(f"加载全局规则失败 {json_file}: {e}")
+    
+    def _load_character_rules(self):
+        """加载角色卡绑定规则"""
+        if not self.characters_path.exists():
+            return
+        
+        for json_file in self.characters_path.glob("*.json"):
+            try:
+                character_name = json_file.stem
+                with open(json_file, 'r', encoding='utf-8') as f:
+                    data = json.load(f)
+                
+                if isinstance(data, list):
+                    ruleset = self._convert_sillytavern_format(data, character_name, RegexScope.CHARACTER)
+                elif isinstance(data, dict) and 'rules' in data:
+                    ruleset = RegexRuleset(**data)
+                else:
+                    continue
+                
+                # 确保所有规则的 scope 正确
+                for rule in ruleset.rules:
+                    rule.scope = RegexScope.CHARACTER
+                    rule.characterName = character_name
+                
+                self.character_rulesets[character_name] = ruleset
+                logger.info(f"加载角色规则: {character_name} ({len(ruleset.rules)} 条规则)")
+            except Exception as e:
+                logger.error(f"加载角色规则失败 {json_file}: {e}")
+    
+    def _load_preset_rules(self):
+        """加载预设绑定规则"""
+        if not self.presets_path.exists():
+            return
+        
+        for json_file in self.presets_path.glob("*.json"):
+            try:
+                preset_name = json_file.stem
+                with open(json_file, 'r', encoding='utf-8') as f:
+                    data = json.load(f)
+                
+                if isinstance(data, list):
+                    ruleset = self._convert_sillytavern_format(data, preset_name, RegexScope.PRESET)
+                elif isinstance(data, dict) and 'rules' in data:
+                    ruleset = RegexRuleset(**data)
+                else:
+                    continue
+                
+                # 确保所有规则的 scope 正确
+                for rule in ruleset.rules:
+                    rule.scope = RegexScope.PRESET
+                    rule.presetName = preset_name
+                
+                self.preset_rulesets[preset_name] = ruleset
+                logger.info(f"加载预设规则: {preset_name} ({len(ruleset.rules)} 条规则)")
+            except Exception as e:
+                logger.error(f"加载预设规则失败 {json_file}: {e}")
+    
+    def _convert_sillytavern_format(
+        self, 
+        st_rules: List[dict], 
+        name: str,
+        scope: RegexScope = RegexScope.GLOBAL
+    ) -> RegexRuleset:
+        """将 SillyTavern 格式转换为内部格式"""
+        rules = []
+        for idx, st_rule in enumerate(st_rules):
+            find_regex = st_rule.get('findRegex', '')
+            pattern, flags = self._parse_st_regex(find_regex)
+            
+            # 解析 placement（默认为 AI_OUTPUT）
+            placement_data = st_rule.get('placement', [2])
+            placement = [RegexPlacement(p) for p in placement_data]
+            
+            rule = RegexRule(
+                id=str(uuid4()),
+                scriptName=st_rule.get('scriptName', f"{name} 规则 {idx + 1}"),
+                findRegex=pattern,
+                replaceString=st_rule.get('replaceString', ''),
+                trimStrings=st_rule.get('trimStrings', []),
+                placement=placement,
+                substituteRegex=SubstituteMode(st_rule.get('substituteRegex', 0)),
+                markdownOnly=st_rule.get('markdownOnly', False),
+                promptOnly=st_rule.get('promptOnly', False),
+                runOnEdit=st_rule.get('runOnEdit', True),
+                minDepth=st_rule.get('minDepth', 0),
+                maxDepth=st_rule.get('maxDepth'),
+                scope=scope,
+                characterName=name if scope == RegexScope.CHARACTER else None,
+                presetName=name if scope == RegexScope.PRESET else None,
+                disabled=st_rule.get('disabled', False),
+                order=idx
+            )
+            rules.append(rule)
+        
+        ruleset = RegexRuleset(
+            id=str(uuid4()),
+            name=f"{name} 规则集",
+            description=f"从 SillyTavern 导入的规则",
+            rules=rules,
+            isSillyTavernFormat=True
+        )
+        
+        return ruleset
+    
+    def _parse_st_regex(self, st_regex: str) -> tuple[str, str]:
+        """解析 SillyTavern 的正则表达式格式 /pattern/flags"""
+        if st_regex.startswith('/') and st_regex.count('/') >= 2:
+            parts = st_regex.split('/')
+            pattern = '/'.join(parts[1:-1])
+            flags = parts[-1] if len(parts) > 2 else ''
+            return pattern, flags
+        else:
+            return st_regex, ''
+    
+    def apply_rules_by_placement(
+        self,
+        text: str,
+        placement: int,
+        character_name: Optional[str] = None,
+        preset_name: Optional[str] = None,
+        message_depth: int = 0
+    ) -> str:
+        """
+        根据 placement 应用正则规则
+        
+        Args:
+            text: 要处理的文本
+            placement: 应用位置（0-5）
+            character_name: 当前角色卡名称
+            preset_name: 当前预设名称
+            message_depth: 消息深度
+        
+        Returns:
+            处理后的文本
+        """
+        rules = self.get_rules_for_context(character_name, preset_name)
+        
+        result = text
+        for rule in rules:
+            # 检查此规则是否适用于当前 placement
+            if placement not in [p.value for p in rule.placement]:
+                continue
+            
+            # 检查消息深度限制
+            if message_depth < rule.minDepth:
+                continue
+            if rule.maxDepth is not None and message_depth > rule.maxDepth:
+                continue
+            
+            # 应用规则
+            result = self._apply_single_rule(result, rule)
+        
+        return result
+    
+    def _apply_single_rule(self, text: str, rule: RegexRule) -> str:
+        """应用单条正则规则"""
+        try:
+            flags = 0
+            if 'i' in rule.findRegex:
+                flags |= re.IGNORECASE
+            if 'm' in rule.findRegex:
+                flags |= re.MULTILINE
+            if 's' in rule.findRegex:
+                flags |= re.DOTALL
+            
+            pattern = rule.findRegex.replace('i', '').replace('m', '').replace('s', '')
+            
+            if rule.substituteRegex == SubstituteMode.REPLACE_FIRST:
+                result = re.sub(pattern, rule.replaceString, text, count=1, flags=flags)
+            else:
+                result = re.sub(pattern, rule.replaceString, text, flags=flags)
+            
+            for trim_str in rule.trimStrings:
+                result = result.replace(trim_str, '')
+            
+            return result
+        except re.error as e:
+            logger.error(f"正则表达式错误 [{rule.scriptName}]: {e}")
+            return text
+    
+    def get_rules_for_context(
+        self,
+        character_name: Optional[str] = None,
+        preset_name: Optional[str] = None
+    ) -> List[RegexRule]:
+        """
+        根据上下文获取适用的规则列表
+        
+        优先级：全局规则 + 角色规则 + 预设规则
+        """
+        applicable_rules = []
+        
+        # 1. 加载全局规则
+        for ruleset in self.global_rulesets.values():
+            for rule in ruleset.rules:
+                if not rule.disabled:
+                    applicable_rules.append(rule)
+        
+        # 2. 加载角色卡规则
+        if character_name and character_name in self.character_rulesets:
+            ruleset = self.character_rulesets[character_name]
+            for rule in ruleset.rules:
+                if not rule.disabled:
+                    applicable_rules.append(rule)
+        
+        # 3. 加载预设规则
+        if preset_name and preset_name in self.preset_rulesets:
+            ruleset = self.preset_rulesets[preset_name]
+            for rule in ruleset.rules:
+                if not rule.disabled:
+                    applicable_rules.append(rule)
+        
+        # 按 order 排序
+        applicable_rules.sort(key=lambda r: r.order)
+        
+        return applicable_rules
+    
+    def save_ruleset(self, ruleset: RegexRuleset, scope: RegexScope, name: Optional[str] = None):
+        """保存规则集到文件"""
+        if scope == RegexScope.GLOBAL:
+            file_path = self.global_path / f"{ruleset.id}.json"
+        elif scope == RegexScope.CHARACTER:
+            file_path = self.characters_path / f"{name or 'unknown'}.json"
+        elif scope == RegexScope.PRESET:
+            file_path = self.presets_path / f"{name or 'unknown'}.json"
+        else:
+            raise ValueError(f"未知的作用域: {scope}")
+        
+        with open(file_path, 'w', encoding='utf-8') as f:
+            json.dump(ruleset.dict(), f, ensure_ascii=False, indent=2)
+        
+        logger.info(f"保存规则集到: {file_path}")
+    
+    def delete_ruleset(self, scope: RegexScope, name: str):
+        """删除规则集"""
+        if scope == RegexScope.CHARACTER:
+            file_path = self.characters_path / f"{name}.json"
+        elif scope == RegexScope.PRESET:
+            file_path = self.presets_path / f"{name}.json"
+        else:
+            raise ValueError(f"不能删除全局规则集")
+        
+        if file_path.exists():
+            file_path.unlink()
+            logger.info(f"删除规则集: {file_path}")
+
+
+# 全局实例
+regex_service = RegexService()

backend/services/system_settings_service.py

@@ -0,0 +1,95 @@
+"""
+系统设置服务
+
+负责加载、保存和管理全局系统设置。
+"""
+import json
+import logging
+from pathlib import Path
+from typing import Optional
+
+from core.config import settings
+from models.system_settings import SystemSettings, DEFAULT_SYSTEM_SETTINGS
+
+logger = logging.getLogger(__name__)
+
+
+class SystemSettingsService:
+    """
+    系统设置服务
+    
+    提供设置的加载、保存和访问功能
+    """
+    
+    def __init__(self):
+        self.settings_file = settings.SYSTEM_SETTINGS_FILE
+        self._settings: Optional[SystemSettings] = None
+        self._load_settings()
+    
+    def _load_settings(self):
+        """从文件加载系统设置"""
+        if self.settings_file.exists():
+            try:
+                with open(self.settings_file, 'r', encoding='utf-8') as f:
+                    data = json.load(f)
+                
+                self._settings = SystemSettings(**data)
+                logger.info(f"加载系统设置成功")
+            except Exception as e:
+                logger.error(f"加载系统设置失败: {e}")
+                self._settings = DEFAULT_SYSTEM_SETTINGS.copy()
+        else:
+            logger.info("系统设置文件不存在，使用默认设置")
+            self._settings = DEFAULT_SYSTEM_SETTINGS.copy()
+            self._save_settings()
+    
+    def _save_settings(self):
+        """保存系统设置到文件"""
+        try:
+            # 确保父目录存在
+            self.settings_file.parent.mkdir(parents=True, exist_ok=True)
+            
+            # 写入文件
+            with open(self.settings_file, 'w', encoding='utf-8') as f:
+                json.dump(self._settings.dict(), f, ensure_ascii=False, indent=2)
+            
+            logger.info(f"系统设置已保存到 {self.settings_file}")
+        except Exception as e:
+            logger.error(f"保存系统设置失败: {e}")
+    
+    @property
+    def settings(self) -> SystemSettings:
+        """获取当前系统设置"""
+        return self._settings
+    
+    def update_thinking_tags(self, prefix: str, suffix: str):
+        """更新思考标签配置"""
+        self._settings.thinkingTagPrefix = prefix
+        self._settings.thinkingTagSuffix = suffix
+        self._settings.updatedAt = int(__import__('time').time())
+        self._save_settings()
+        logger.info(f"思考标签已更新: {prefix} ... {suffix}")
+    
+    def update_current_preset(self, preset_name: Optional[str]):
+        """更新当前选中的预设名称"""
+        self._settings.currentPresetName = preset_name
+        self._settings.updatedAt = int(__import__('time').time())
+        self._save_settings()
+        logger.info(f"当前预设已更新: {preset_name}")
+    
+    def get_thinking_tag_pattern(self) -> str:
+        """获取思考标签的正则表达式模式"""
+        prefix = self._settings.thinkingTagPrefix
+        suffix = self._settings.thinkingTagSuffix
+        
+        # 转义特殊字符
+        import re
+        escaped_prefix = re.escape(prefix)
+        escaped_suffix = re.escape(suffix)
+        
+        # 返回匹配思考内容的正则模式
+        return f"{escaped_prefix}[\\s\\S]*?{escaped_suffix}"
+
+
+# 全局实例
+system_settings_service = SystemSettingsService()

backend/services/task_queue_manager.py

@@ -0,0 +1,161 @@
+"""
+任务队列管理器
+管理并行任务（生图、动态表格维护等）的状态和生命周期
+"""
+import asyncio
+from typing import Dict, List, Optional
+from enum import Enum
+from datetime import datetime
+
+
+class TaskStatus(Enum):
+    """任务状态枚举"""
+    PENDING = "pending"      # 等待中
+    RUNNING = "running"      # 进行中
+    COMPLETED = "completed"  # 已完成
+    FAILED = "failed"        # 失败
+    CANCELLED = "cancelled"  # 已取消
+
+
+class TaskType(Enum):
+    """任务类型枚举"""
+    IMAGE_WORKFLOW = "image_workflow"
+    DYNAMIC_TABLE = "dynamic_table"
+
+
+class TaskItem:
+    """任务项"""
+    
+    def __init__(self, task_id: str, task_type: TaskType, chat_id: str):
+        self.task_id = task_id
+        self.task_type = task_type
+        self.chat_id = chat_id
+        self.status = TaskStatus.PENDING
+        self.created_at = datetime.now()
+        self.started_at = None
+        self.completed_at = None
+        self.error = None
+        self.metadata = {}  # 用于存储提示词、修改内容等
+        
+    def to_dict(self):
+        """转换为字典格式（前端友好）"""
+        return {
+            "taskId": self.task_id,
+            "taskType": self.task_type.value,
+            "chatId": self.chat_id,
+            "status": self.status.value,
+            "createdAt": self.created_at.isoformat(),
+            "startedAt": self.started_at.isoformat() if self.started_at else None,
+            "completedAt": self.completed_at.isoformat() if self.completed_at else None,
+            "error": self.error,
+            "metadata": self.metadata
+        }
+
+
+class TaskQueueManager:
+    """
+    全局任务队列管理器
+    
+    功能：
+    - 管理所有并行任务的生命周期
+    - 支持按聊天ID查询任务
+    - 支持取消任务
+    - 自动清理已完成的任务
+    """
+    
+    def __init__(self):
+        self.tasks: Dict[str, TaskItem] = {}
+        self.chat_tasks: Dict[str, List[str]] = {}  # chat_id -> [task_ids]
+        self._lock = asyncio.Lock()
+        
+    async def add_task(self, task_id: str, task_type: TaskType, chat_id: str) -> TaskItem:
+        """添加任务到队列"""
+        async with self._lock:
+            task = TaskItem(task_id, task_type, chat_id)
+            self.tasks[task_id] = task
+            
+            if chat_id not in self.chat_tasks:
+                self.chat_tasks[chat_id] = []
+            self.chat_tasks[chat_id].append(task_id)
+            
+            return task
+    
+    async def start_task(self, task_id: str):
+        """标记任务开始执行"""
+        async with self._lock:
+            if task_id in self.tasks:
+                self.tasks[task_id].status = TaskStatus.RUNNING
+                self.tasks[task_id].started_at = datetime.now()
+    
+    async def complete_task(self, task_id: str, metadata: dict = None):
+        """标记任务完成"""
+        async with self._lock:
+            if task_id in self.tasks:
+                self.tasks[task_id].status = TaskStatus.COMPLETED
+                self.tasks[task_id].completed_at = datetime.now()
+                if metadata:
+                    self.tasks[task_id].metadata.update(metadata)
+    
+    async def fail_task(self, task_id: str, error: str):
+        """标记任务失败"""
+        async with self._lock:
+            if task_id in self.tasks:
+                self.tasks[task_id].status = TaskStatus.FAILED
+                self.tasks[task_id].completed_at = datetime.now()
+                self.tasks[task_id].error = error
+    
+    async def cancel_task(self, task_id: str) -> bool:
+        """
+        取消任务
+        
+        Returns:
+            bool: 是否成功取消
+        """
+        async with self._lock:
+            if task_id in self.tasks:
+                task = self.tasks[task_id]
+                if task.status in [TaskStatus.PENDING, TaskStatus.RUNNING]:
+                    task.status = TaskStatus.CANCELLED
+                    task.completed_at = datetime.now()
+                    return True
+        return False
+    
+    async def get_chat_tasks(self, chat_id: str, include_completed: bool = False) -> List[dict]:
+        """
+        获取某个聊天的所有任务
+        
+        Args:
+            chat_id: 聊天ID
+            include_completed: 是否包含已完成的任务
+            
+        Returns:
+            List[dict]: 任务列表
+        """
+        async with self._lock:
+            task_ids = self.chat_tasks.get(chat_id, [])
+            tasks = []
+            for task_id in task_ids:
+                if task_id in self.tasks:
+                    task = self.tasks[task_id]
+                    # 根据参数决定是否包含已完成的任务
+                    if include_completed or task.status in [TaskStatus.PENDING, TaskStatus.RUNNING]:
+                        tasks.append(task.to_dict())
+            return tasks
+    
+    async def cleanup_completed_tasks(self, chat_id: str):
+        """清理已完成的任务"""
+        async with self._lock:
+            if chat_id in self.chat_tasks:
+                task_ids = self.chat_tasks[chat_id]
+                completed_ids = [
+                    tid for tid in task_ids 
+                    if tid in self.tasks and 
+                    self.tasks[tid].status in [TaskStatus.COMPLETED, TaskStatus.FAILED, TaskStatus.CANCELLED]
+                ]
+                for tid in completed_ids:
+                    del self.tasks[tid]
+                    self.chat_tasks[chat_id].remove(tid)
+
+
+# 全局实例
+task_queue_manager = TaskQueueManager()

backend/services/token_usage_service.py

@@ -0,0 +1,427 @@
+"""
+Token 使用统计服务
+
+负责记录、查询和分析 LLM 调用的 token 使用情况
+数据持久化到 data/token_usage 目录，按月份组织
+采用双层存储：
+1. JSONL 文件 - 详细记录（按月存储）
+2. 索引文件 - 快速聚合统计（按 API URL、日期等维度）
+"""
+import json
+import uuid
+from pathlib import Path
+from typing import List, Dict, Optional, Any
+from datetime import datetime
+from collections import defaultdict
+
+try:
+    from backend.models.internal import TokenUsageRecord, TokenUsageStatus
+    from backend.core.config import settings
+except ImportError:
+    from models.internal import TokenUsageRecord, TokenUsageStatus
+    from core.config import settings
+
+
+class TokenUsageService:
+    """
+    Token 使用统计服务
+    
+    功能：
+    - 记录每次 LLM 调用的 token 使用情况
+    - 按月份、日期、角色、聊天、API URL 维度统计
+    - 支持中断和失败标记
+    - 数据持久化到文件系统（JSONL + 索引）
+    """
+    
+    def __init__(self):
+        self.token_usage_dir = settings.DATA_PATH / "token_usage"
+        self.token_usage_dir.mkdir(parents=True, exist_ok=True)
+        
+        # ✅ 索引文件目录 - 用于快速聚合查询
+        self.index_dir = self.token_usage_dir / "indexes"
+        self.index_dir.mkdir(parents=True, exist_ok=True)
+    
+    def _get_month_file(self, year: int, month: int) -> Path:
+        """获取指定月份的统计文件路径"""
+        month_dir = self.token_usage_dir / f"{year}"
+        month_dir.mkdir(parents=True, exist_ok=True)
+        return month_dir / f"{month:02d}.jsonl"
+    
+    def _load_month_records(self, year: int, month: int) -> List[TokenUsageRecord]:
+        """加载指定月份的所有记录"""
+        file_path = self._get_month_file(year, month)
+        
+        if not file_path.exists():
+            return []
+        
+        records = []
+        try:
+            with open(file_path, 'r', encoding='utf-8') as f:
+                for line in f:
+                    if line.strip():
+                        data = json.loads(line)
+                        records.append(TokenUsageRecord(**data))
+        except Exception as e:
+            print(f"[TokenUsage] 加载记录失败: {e}")
+        
+        return records
+    
+    def _save_record(self, record: TokenUsageRecord):
+        """保存单条记录到对应的月份文件"""
+        dt = datetime.fromtimestamp(record.timestamp)
+        file_path = self._get_month_file(dt.year, dt.month)
+        
+        try:
+            with open(file_path, 'a', encoding='utf-8') as f:
+                f.write(json.dumps(record.model_dump(), ensure_ascii=False) + '\n')
+            
+            # ✅ 同时更新索引文件（用于快速查询）
+            self._update_indexes(record)
+        except Exception as e:
+            print(f"[TokenUsage] 保存记录失败: {e}")
+    
+    def _update_indexes(self, record: TokenUsageRecord):
+        """
+        更新索引文件 - 实现高效的按维度聚合查询
+        
+        索引结构：
+        - indexes/api_urls.json - 按 API URL 聚合
+        - indexes/daily/{year}-{month}.json - 按日聚合
+        """
+        dt = datetime.fromtimestamp(record.timestamp)
+        
+        # 1. 更新 API URL 索引
+        if record.apiUrl:
+            api_url_index = self.index_dir / "api_urls.json"
+            self._update_api_url_index(api_url_index, record)
+        
+        # 2. 更新每日索引
+        daily_index = self.index_dir / "daily" / f"{dt.year}-{dt.month:02d}.json"
+        daily_index.parent.mkdir(parents=True, exist_ok=True)
+        self._update_daily_index(daily_index, record)
+    
+    def _update_api_url_index(self, index_file: Path, record: TokenUsageRecord):
+        """更新 API URL 索引文件"""
+        index_data = {}
+        
+        # 加载现有索引
+        if index_file.exists():
+            try:
+                with open(index_file, 'r', encoding='utf-8') as f:
+                    index_data = json.load(f)
+            except:
+                index_data = {}
+        
+        # 更新统计
+        api_url = record.apiUrl
+        if api_url not in index_data:
+            index_data[api_url] = {
+                "totalPromptTokens": 0,
+                "totalCompletionTokens": 0,
+                "totalTokens": 0,
+                "count": 0,
+                "firstUsed": record.timestamp,
+                "lastUsed": record.timestamp
+            }
+        
+        stats = index_data[api_url]
+        stats["totalPromptTokens"] += record.promptTokens
+        stats["totalCompletionTokens"] += record.completionTokens
+        stats["totalTokens"] += record.totalTokens
+        stats["count"] += 1
+        stats["lastUsed"] = max(stats["lastUsed"], record.timestamp)
+        stats["firstUsed"] = min(stats["firstUsed"], record.timestamp)
+        
+        # 保存索引
+        with open(index_file, 'w', encoding='utf-8') as f:
+            json.dump(index_data, f, ensure_ascii=False, indent=2)
+    
+    def _update_daily_index(self, index_file: Path, record: TokenUsageRecord):
+        """更新每日索引文件"""
+        dt = datetime.fromtimestamp(record.timestamp)
+        day_key = f"{dt.year}-{dt.month:02d}-{dt.day:02d}"
+        
+        index_data = {}
+        
+        # 加载现有索引
+        if index_file.exists():
+            try:
+                with open(index_file, 'r', encoding='utf-8') as f:
+                    index_data = json.load(f)
+            except:
+                index_data = {}
+        
+        # 更新统计
+        if day_key not in index_data:
+            index_data[day_key] = {
+                "promptTokens": 0,
+                "completionTokens": 0,
+                "totalTokens": 0,
+                "count": 0
+            }
+        
+        stats = index_data[day_key]
+        stats["promptTokens"] += record.promptTokens
+        stats["completionTokens"] += record.completionTokens
+        stats["totalTokens"] += record.totalTokens
+        stats["count"] += 1
+        
+        # 保存索引
+        with open(index_file, 'w', encoding='utf-8') as f:
+            json.dump(index_data, f, ensure_ascii=False, indent=2)
+    
+    async def record_usage(
+        self,
+        chat_id: str,
+        role_name: str,
+        chat_name: str,
+        prompt_tokens: int,
+        completion_tokens: int,
+        total_tokens: int,
+        status: TokenUsageStatus = TokenUsageStatus.COMPLETED,
+        message_id: Optional[str] = None,
+        floor: Optional[int] = None,
+        error_message: Optional[str] = None,
+        duration: Optional[float] = None,
+        model: Optional[str] = None,
+        api_provider: Optional[str] = None,
+        api_url: Optional[str] = None
+    ) -> TokenUsageRecord:
+        """
+        记录一次 LLM 调用的 token 使用情况
+        
+        Args:
+            chat_id: 聊天ID
+            role_name: 角色名称
+            chat_name: 聊天名称
+            prompt_tokens: 输入 token 数
+            completion_tokens: 输出 token 数
+            total_tokens: 总 token 数
+            status: 请求状态
+            message_id: 关联的消息ID
+            floor: 楼层号
+            error_message: 错误信息
+            duration: 请求耗时
+            model: 使用的模型
+            api_provider: API 提供商
+            api_url: API URL地址
+            
+        Returns:
+            TokenUsageRecord: 创建的记录
+        """
+        record = TokenUsageRecord(
+            id=str(uuid.uuid4()),
+            chatId=chat_id,
+            roleName=role_name,
+            chatName=chat_name,
+            messageId=message_id,
+            floor=floor,
+            promptTokens=prompt_tokens,
+            completionTokens=completion_tokens,
+            totalTokens=total_tokens,
+            status=status,
+            errorMessage=error_message,
+            duration=duration,
+            model=model,
+            apiProvider=api_provider,
+            apiUrl=api_url
+        )
+        
+        self._save_record(record)
+        return record
+    
+    async def get_stats_by_month(
+        self,
+        year: int,
+        month: int,
+        role_name: Optional[str] = None,
+        chat_name: Optional[str] = None
+    ) -> Dict[str, Any]:
+        """
+        获取指定月份的统计数据
+        
+        Args:
+            year: 年份
+            month: 月份
+            role_name: 角色名称（可选，用于过滤）
+            chat_name: 聊天名称（可选，用于过滤）
+            
+        Returns:
+            统计数据字典
+        """
+        records = self._load_month_records(year, month)
+        
+        # 过滤
+        if role_name:
+            records = [r for r in records if r.roleName == role_name]
+        if chat_name:
+            records = [r for r in records if r.chatName == chat_name]
+        
+        # 统计
+        total_prompt = sum(r.promptTokens for r in records)
+        total_completion = sum(r.completionTokens for r in records)
+        total_tokens = sum(r.totalTokens for r in records)
+        
+        completed_count = sum(1 for r in records if r.status == TokenUsageStatus.COMPLETED)
+        interrupted_count = sum(1 for r in records if r.status == TokenUsageStatus.INTERRUPTED)
+        failed_count = sum(1 for r in records if r.status == TokenUsageStatus.FAILED)
+        
+        # 按日期分组
+        daily_stats = defaultdict(lambda: {
+            "promptTokens": 0,
+            "completionTokens": 0,
+            "totalTokens": 0,
+            "count": 0
+        })
+        
+        for r in records:
+            dt = datetime.fromtimestamp(r.timestamp)
+            day_key = f"{dt.year}-{dt.month:02d}-{dt.day:02d}"
+            daily_stats[day_key]["promptTokens"] += r.promptTokens
+            daily_stats[day_key]["completionTokens"] += r.completionTokens
+            daily_stats[day_key]["totalTokens"] += r.totalTokens
+            daily_stats[day_key]["count"] += 1
+        
+        # 按角色分组
+        role_stats = defaultdict(lambda: {
+            "promptTokens": 0,
+            "completionTokens": 0,
+            "totalTokens": 0,
+            "count": 0
+        })
+        
+        for r in records:
+            role_stats[r.roleName]["promptTokens"] += r.promptTokens
+            role_stats[r.roleName]["completionTokens"] += r.completionTokens
+            role_stats[r.roleName]["totalTokens"] += r.totalTokens
+            role_stats[r.roleName]["count"] += 1
+        
+        # 按聊天分组
+        chat_stats = defaultdict(lambda: {
+            "promptTokens": 0,
+            "completionTokens": 0,
+            "totalTokens": 0,
+            "count": 0
+        })
+        
+        for r in records:
+            chat_key = f"{r.roleName}/{r.chatName}"
+            chat_stats[chat_key]["promptTokens"] += r.promptTokens
+            chat_stats[chat_key]["completionTokens"] += r.completionTokens
+            chat_stats[chat_key]["totalTokens"] += r.totalTokens
+            chat_stats[chat_key]["count"] += 1
+        
+        # ✅ 按 API URL 分组
+        api_url_stats = defaultdict(lambda: {
+            "promptTokens": 0,
+            "completionTokens": 0,
+            "totalTokens": 0,
+            "count": 0
+        })
+        
+        for r in records:
+            if r.apiUrl:
+                api_url_stats[r.apiUrl]["promptTokens"] += r.promptTokens
+                api_url_stats[r.apiUrl]["completionTokens"] += r.completionTokens
+                api_url_stats[r.apiUrl]["totalTokens"] += r.totalTokens
+                api_url_stats[r.apiUrl]["count"] += 1
+        
+        return {
+            "year": year,
+            "month": month,
+            "totalRecords": len(records),
+            "totalPromptTokens": total_prompt,
+            "totalCompletionTokens": total_completion,
+            "totalTokens": total_tokens,
+            "completedCount": completed_count,
+            "interruptedCount": interrupted_count,
+            "failedCount": failed_count,
+            "dailyStats": dict(daily_stats),
+            "roleStats": dict(role_stats),
+            "chatStats": dict(chat_stats),
+            "apiUrlStats": dict(api_url_stats),  # ✅ 新增
+            "records": [r.model_dump() for r in records[:100]]  # 最近100条记录
+        }
+    
+    async def list_months(self) -> List[Dict[str, int]]:
+        """列出所有有数据的月份"""
+        months = []
+        
+        if not self.token_usage_dir.exists():
+            return months
+        
+        for year_dir in sorted(self.token_usage_dir.iterdir()):
+            if year_dir.is_dir() and year_dir.name.isdigit():
+                year = int(year_dir.name)
+                for month_file in sorted(year_dir.glob("*.jsonl")):
+                    month = int(month_file.stem)
+                    months.append({"year": year, "month": month})
+        
+        return months
+    
+    async def get_api_url_stats(self) -> Dict[str, Any]:
+        """
+        ✅ 获取按 API URL 分组的统计数据（从索引文件快速读取）
+        
+        Returns:
+            {api_url: {totalPromptTokens, totalCompletionTokens, totalTokens, count, firstUsed, lastUsed}}
+        """
+        api_url_index = self.index_dir / "api_urls.json"
+        
+        if not api_url_index.exists():
+            return {}
+        
+        try:
+            with open(api_url_index, 'r', encoding='utf-8') as f:
+                return json.load(f)
+        except Exception as e:
+            print(f"[TokenUsage] 读取 API URL 索引失败: {e}")
+            return {}
+    
+    async def get_daily_stats(self, year: int, month: int) -> Dict[str, Any]:
+        """
+        ✅ 获取指定月份的每日统计数据（从索引文件快速读取）
+        
+        Args:
+            year: 年份
+            month: 月份
+            
+        Returns:
+            {day_key: {promptTokens, completionTokens, totalTokens, count}}
+        """
+        daily_index = self.index_dir / "daily" / f"{year}-{month:02d}.json"
+        
+        if not daily_index.exists():
+            return {}
+        
+        try:
+            with open(daily_index, 'r', encoding='utf-8') as f:
+                return json.load(f)
+        except Exception as e:
+            print(f"[TokenUsage] 读取每日索引失败: {e}")
+            return {}
+    
+    async def get_available_roles(self, year: int, month: int) -> List[str]:
+        """获取指定月份有数据的角色列表"""
+        records = self._load_month_records(year, month)
+        roles = set(r.roleName for r in records)
+        return sorted(list(roles))
+    
+    async def get_available_chats(
+        self,
+        year: int,
+        month: int,
+        role_name: Optional[str] = None
+    ) -> List[str]:
+        """获取指定月份有数据的聊天列表"""
+        records = self._load_month_records(year, month)
+        
+        if role_name:
+            records = [r for r in records if r.roleName == role_name]
+        
+        chats = set(f"{r.roleName}/{r.chatName}" for r in records)
+        return sorted(list(chats))
+
+
+# 全局实例
+token_usage_service = TokenUsageService()

backend/utils/llm_client.py

@@ -4,9 +4,12 @@ LLM 客户端工具
 提供统一的 LLM 接口,支持多种模型提供商。
 使用 LangChain 的 ChatModel 抽象,简化不同厂商 API 的调用。
 """
-from typing import Optional
+from typing import Optional, List, Dict, Any, AsyncGenerator
 from langchain_core.language_models.chat_models import BaseChatModel
+from langchain_core.messages import BaseMessage, HumanMessage, SystemMessage, AIMessage
+from langchain_core.callbacks import AsyncCallbackHandler
 from core.config import settings
+import time
 
 
 def get_llm(
@@ -86,3 +89,249 @@ def get_creative_llm(provider: str = "openai") -> BaseChatModel:
 def get_streaming_llm(provider: str = "openai") -> BaseChatModel:
     """获取支持流式输出的 LLM"""
     return get_llm(provider, streaming=True)
+
+
+class TokenUsageCallbackHandler(AsyncCallbackHandler):
+    """
+    Token 使用回调处理器
+    
+    用于捕获 LLM 调用的 token 使用情况
+    """
+    def __init__(self):
+        self.prompt_tokens = 0
+        self.completion_tokens = 0
+        self.total_tokens = 0
+        self.response_content = ""
+    
+    async def on_llm_start(self, serialized: Dict[str, Any], prompts: List[str] = None, **kwargs):
+        """LLM 开始时的回调"""
+        pass
+    
+    async def on_llm_end(self, response, **kwargs):
+        """LLM 结束时的回调，获取 token 统计"""
+        try:
+            # 从 response 中提取 token 信息
+            if hasattr(response, 'llm_output') and response.llm_output:
+                token_usage = response.llm_output.get('token_usage', {})
+                self.prompt_tokens = token_usage.get('prompt_tokens', 0)
+                self.completion_tokens = token_usage.get('completion_tokens', 0)
+                self.total_tokens = token_usage.get('total_tokens', 0)
+        except Exception as e:
+            print(f"[TokenUsageCallback] 提取 token 信息失败: {e}")
+    
+    async def on_llm_new_token(self, token: str, **kwargs):
+        """每个新 token 的回调（流式输出）"""
+        self.response_content += token
+
+
+class LLMClient:
+    """
+    LLM 客户端封装类
+    
+    提供统一的异步接口，支持自定义API配置、流式输出和 token 统计
+    """
+    
+    async def chat_completion(
+        self,
+        messages: List[BaseMessage],
+        api_url: str,
+        api_key: str,
+        model: str = "gpt-3.5-turbo",
+        temperature: float = 1.0,
+        max_tokens: int = 500,
+        request_timeout: int = 60,
+        stream: bool = False,
+        **kwargs
+    ) -> Dict[str, Any]:
+        """
+        调用 LLM API 生成回复
+        
+        Args:
+            messages: LangChain 消息列表
+            api_url: API 地址
+            api_key: API 密钥
+            model: 模型名称
+            temperature: 温度参数
+            max_tokens: 最大 token 数
+            request_timeout: 请求超时时间（秒）
+            stream: 是否启用流式输出
+            **kwargs: 其他参数
+            
+        Returns:
+            OpenAI 格式的响应字典，包含 token 使用信息
+        """
+        try:
+            from langchain_openai import ChatOpenAI
+            
+            # 创建回调处理器
+            callback_handler = TokenUsageCallbackHandler()
+            
+            # 创建自定义的 ChatOpenAI 实例
+            llm = ChatOpenAI(
+                model=model,
+                temperature=temperature,
+                api_key=api_key,
+                base_url=api_url if api_url else None,
+                max_tokens=max_tokens,
+                streaming=stream,
+                callbacks=[callback_handler],
+                request_timeout=request_timeout,  # ✅ 设置超时时间
+                **kwargs
+            )
+            
+            start_time = time.time()
+            
+            if stream:
+                # 流式模式
+                full_content = ""
+                async for chunk in llm.astream(messages):
+                    if hasattr(chunk, 'content'):
+                        full_content += chunk.content
+                
+                duration = time.time() - start_time
+                
+                return {
+                    "choices": [
+                        {
+                            "message": {
+                                "role": "assistant",
+                                "content": full_content
+                            }
+                        }
+                    ],
+                    "usage": {
+                        "prompt_tokens": callback_handler.prompt_tokens,
+                        "completion_tokens": callback_handler.completion_tokens,
+                        "total_tokens": callback_handler.total_tokens
+                    },
+                    "duration": duration
+                }
+            else:
+                # 非流式模式
+                response = await llm.ainvoke(messages)
+                duration = time.time() - start_time
+                
+                return {
+                    "choices": [
+                        {
+                            "message": {
+                                "role": "assistant",
+                                "content": response.content
+                            }
+                        }
+                    ],
+                    "usage": {
+                        "prompt_tokens": callback_handler.prompt_tokens,
+                        "completion_tokens": callback_handler.completion_tokens,
+                        "total_tokens": callback_handler.total_tokens
+                    },
+                    "duration": duration
+                }
+            
+        except Exception as e:
+            print(f"[LLMClient] 调用失败: {e}")
+            raise
+    
+    async def stream_chat(
+        self,
+        messages: List[BaseMessage],
+        api_url: str,
+        api_key: str,
+        model: str = "gpt-3.5-turbo",
+        temperature: float = 1.0,
+        max_tokens: int = 500,
+        request_timeout: int = 60,
+        **kwargs
+    ) -> AsyncGenerator[Dict[str, Any], None]:
+        """
+        流式调用 LLM API
+        
+        Args:
+            messages: LangChain 消息列表
+            api_url: API 地址
+            api_key: API 密钥
+            model: 模型名称
+            temperature: 温度参数
+            max_tokens: 最大 token 数
+            request_timeout: 请求超时时间（秒）
+            **kwargs: 其他参数
+            
+        Yields:
+            包含 token 片段的字典
+        """
+        try:
+            from langchain_openai import ChatOpenAI
+            
+            print(f"\n[LLMClient] 🔧 创建 ChatOpenAI 实例")
+            print(f"  - Model: {model}")
+            print(f"  - API URL: {api_url[:50]}..." if len(api_url) > 50 else f"  - API URL: {api_url}")
+            print(f"  - Temperature: {temperature}")
+            print(f"  - Max Tokens: {max_tokens}")
+            print(f"  - Request Timeout: {request_timeout}s")
+            
+            # 创建回调处理器
+            callback_handler = TokenUsageCallbackHandler()
+            
+            # 创建自定义的 ChatOpenAI 实例
+            llm = ChatOpenAI(
+                model=model,
+                temperature=temperature,
+                api_key=api_key,
+                base_url=api_url if api_url else None,
+                max_tokens=max_tokens,
+                streaming=True,
+                callbacks=[callback_handler],
+                request_timeout=request_timeout,  # ✅ 设置超时时间
+                **kwargs
+            )
+            
+            start_time = time.time()
+            
+            print(f"[LLMClient] 🚀 开始流式请求...")
+            print(f"  - Messages 数量: {len(messages)}")
+            if messages:
+                first_msg_role = getattr(messages[0], 'role', 'unknown')
+                first_msg_preview = str(getattr(messages[0], 'content', ''))[:50]
+                print(f"  - 第一条消息: [{first_msg_role}] {first_msg_preview}...")
+            
+            chunk_count = 0
+            # 流式输出
+            async for chunk in llm.astream(messages):
+                if hasattr(chunk, 'content') and chunk.content:
+                    chunk_count += 1
+                    
+                    # 第一个 chunk 时记录
+                    if chunk_count == 1:
+                        first_chunk_time = time.time()
+                        print(f"[LLMClient] ✨ 收到第一个 chunk (耗时: {first_chunk_time - start_time:.2f}s)")
+                    
+                    yield {
+                        "type": "chunk",
+                        "content": chunk.content
+                    }
+            
+            duration = time.time() - start_time
+            
+            print(f"[LLMClient] ✅ 流式请求完成")
+            print(f"  - 总 Chunks: {chunk_count}")
+            print(f"  - 耗时: {duration:.2f}秒")
+            print(f"  - Prompt Tokens: {callback_handler.prompt_tokens}")
+            print(f"  - Completion Tokens: {callback_handler.completion_tokens}")
+            print(f"  - Total Tokens: {callback_handler.total_tokens}\n")
+            
+            # 最后发送 token 使用信息
+            yield {
+                "type": "usage",
+                "usage": {
+                    "prompt_tokens": callback_handler.prompt_tokens,
+                    "completion_tokens": callback_handler.completion_tokens,
+                    "total_tokens": callback_handler.total_tokens
+                },
+                "duration": duration
+            }
+            
+        except Exception as e:
+            print(f"\n[LLMClient] ❌ 流式调用失败: {e}")
+            import traceback
+            traceback.print_exc()
+            raise