优化：重构 state，分离持久化和临时字段，完善 init_state_node

主要改动：
1. 移除无用字段 system_prompt
2. 重新组织 state，明确标注「持久化字段」和「临时字段」
3. 完善 init_state_node，重置所有临时字段
4. 解决数据残留隐患，确保每轮对话开始时状态干净

backend/app/main_graph/nodes/routing.py

@@ -11,21 +11,97 @@
 from datetime import datetime
 
 from backend.app.core.intent import get_route_by_reasoning, ReasoningAction
-from ...main_graph.state import MainGraphState
+from ...main_graph.state import (
+    MainGraphState,
+    CurrentAction,
+    ReactReasoningState,
+    HybridRouterState,
+    FastPathState
+)
 from backend.app.logger import info
 
 
 # ========== 初始化状态节点 ==========
 def init_state_node(state: MainGraphState) -> MainGraphState:
-    """初始化状态节点：在流程开始时设置初始值"""
+    """
+    初始化状态节点：在流程开始时设置初始值
+    
+    重置策略：
+    - 持久化字段（如 messages、turns_since_last_summary）不重置
+    - 临时字段（如 rag_context、final_result）重置为初始值
+    """
+    # 持久化字段保留原样
+    # - messages
+    # - turns_since_last_summary
+    # - user_id
+    
+    # ========== 重置临时字段 ==========
+    
+    # 主图控制字段
+    state.user_query = ""
+    state.current_action = CurrentAction.NONE
+    state.current_model = ""
+    state.intent_confidence = 0.0
+    
+    # React 推理专用字段
+    state.reasoning_step = 0
+    state.last_action = ""
+    state.reasoning_history = []
+    
+    # RAG 相关字段
+    state.rag_context = ""
+    state.rag_retrieved = False
+    state.rag_docs = []
+    state.rag_confidence = 0.0
+    state.rag_attempts = 0
+    
+    # 联网搜索相关字段
+    state.web_search_results = []
+    
+    # 错误处理字段
+    state.errors = []
+    state.current_error = None
+    state.retry_action = None
+    state.error_message = ""
+    
+    # 子图结果字段
+    state.news_result = None
+    state.dictionary_result = None
+    state.contact_result = None
+    
+    # 执行状态
+    state.current_phase = "initializing"
+    state.final_result = ""
+    state.success = False
+    
+    # 元数据
+    state.start_time = None
+    state.end_time = None
+    
+    # 结构化状态
+    state.react_reasoning = ReactReasoningState()
+    state.hybrid_router = HybridRouterState()
+    state.fast_path = FastPathState()
+    
+    # 统计字段
+    state.llm_calls = 0
+    state.last_token_usage = {}
+    state.last_elapsed_time = 0.0
+    state.memory_context = ""
+    
+    # 向后兼容字段
+    state.debug_info = {}
+    
+    # 设置初始值
     state.current_phase = "initializing"
     state.reasoning_step = 0
     state.start_time = datetime.now().isoformat()
-
+    
+    # 从 messages 中提取 user_query（如果没有的话）
     if not state.user_query and state.messages:
         last_msg = state.messages[-1]
         state.user_query = getattr(last_msg, "content", str(last_msg))
-
+    
     return state
 
 

backend/app/main_graph/state.py

@@ -1,6 +1,10 @@
 """
 主图状态定义 - React 模式增强版
 Main Graph State Definition - React Mode Enhanced
+
+字段分类说明：
+- 持久化字段：跨轮次保留，不重置
+- 临时字段：每轮对话开始时重置
 """
 
 from enum import Enum, auto
@@ -10,7 +14,7 @@ from langgraph.graph import add_messages
 from langchain_core.messages import BaseMessage
 
 
-# ========== 新的类型 ==========
+# ========== 枚举类型 ==========
 class CurrentAction(Enum):
     """主图当前操作类型"""
     NONE = auto()
@@ -43,21 +47,21 @@ class ErrorRecord:
 
 @dataclass
 class ReactReasoningState:
-    """React 推理状态 - 替代 debug_info 中的相关字段"""
+    """React 推理状态"""
     last_reasoning: Optional[Dict[str, Any]] = None
     reasoning_result: Optional[Any] = None  # 实际类型是 ReasoningResult
 
 
 @dataclass
 class HybridRouterState:
-    """混合路由状态 - 替代 debug_info 中的相关字段"""
+    """混合路由状态"""
     decision: Optional[Any] = None  # 实际类型是 HybridRouterResult
     start_time: Optional[str] = None
 
 
 @dataclass
 class FastPathState:
-    """快速路径状态 - 替代 debug_info 中的相关字段"""
+    """快速路径状态"""
     chitchat_success: bool = False
     rag_success: bool = False
     tool_success: bool = False
@@ -68,70 +72,77 @@ class FastPathState:
 @dataclass
 class MainGraphState:
     """
-    - 旧代码的 MessagesState 兼容性字段
+    主图状态定义
-    - React 推理控制字段
-    - 循环和错误处理
-    - 子图结果占位
-    - 用户信息
-    """
-    # ========== 旧 MessagesState 兼容性字段 ==========
-    messages: Annotated[Sequence[BaseMessage], add_messages] = field(default_factory=list)
-    llm_calls: int = 0
-    memory_context: str = ""
-    system_prompt: str = ""
-    turns_since_last_summary: int = 0  # 新增：来自旧状态
-    last_token_usage: Dict[str, Any] = field(default_factory=dict)  # 新增：来自旧状态
-    last_elapsed_time: float = 0.0  # 新增：来自旧状态
     
-    # ========== 主图控制字段 ==========
+    字段分类：
+    - 持久化字段：跨轮次保留，不重置
+    - 临时字段：每轮对话开始时重置
+    """
+    
+    # ==================================================
+    # 持久化字段（每轮保留）
+    # ==================================================
+    
+    messages: Annotated[Sequence[BaseMessage], add_messages] = field(default_factory=list)
+    turns_since_last_summary: int = 0  # 距离上次总结的轮数
+    user_id: str = ""
+    
+    # ==================================================
+    # 临时字段（每轮重置）
+    # ==================================================
+    
+    # 主图控制字段
     user_query: str = ""
     current_action: CurrentAction = CurrentAction.NONE
-    current_model: str = ""  # 新增：本次请求使用的模型
+    current_model: str = ""  # 本次请求使用的模型
     intent_confidence: float = 0.0
     
-    # ========== React 推理专用字段 ==========
+    # React 推理专用字段
     reasoning_step: int = 0
-    max_steps: int = 10  # 从 40 改到 10，避免过长循环
+    max_steps: int = 10  # 避免过长循环
     last_action: str = ""
     reasoning_history: List[Dict[str, Any]] = field(default_factory=list)
     
-    # ========== RAG 相关字段 ==========
+    # RAG 相关字段
     rag_context: str = ""
     rag_retrieved: bool = False
     rag_docs: List[Dict[str, Any]] = field(default_factory=list)
     rag_confidence: float = 0.0  # RAG 检索置信度 (0.0-1.0)
     rag_attempts: int = 0  # RAG 检索次数统计
     
-    # ========== 联网搜索相关字段 ==========
+    # 联网搜索相关字段
     web_search_results: List[str] = field(default_factory=list)
     
-    # ========== 错误处理字段 ==========
+    # 错误处理字段
     errors: List[ErrorRecord] = field(default_factory=list)
     current_error: Optional[ErrorRecord] = None
     retry_action: Optional[str] = None
+    error_message: str = ""
     
-    # ========== 子图结果占位 ==========
+    # 子图结果字段
     news_result: Optional[Dict[str, Any]] = None
     dictionary_result: Optional[Dict[str, Any]] = None
     contact_result: Optional[Dict[str, Any]] = None
     
-    # ========== 用户信息 ==========
+    # 执行状态
-    user_id: str = ""
-    
-    # ========== 执行状态 ==========
     current_phase: str = "init"
-    error_message: str = ""
     final_result: str = ""
     success: bool = False
     
-    # ========== 元数据 ==========
+    # 元数据
     start_time: Optional[str] = None
     end_time: Optional[str] = None
     
-    # ========== 结构化状态（替代黑盒 debug_info）==========
+    # 结构化状态
     react_reasoning: ReactReasoningState = field(default_factory=ReactReasoningState)
     hybrid_router: HybridRouterState = field(default_factory=HybridRouterState)
     fast_path: FastPathState = field(default_factory=FastPathState)
     
-    # ========== 向后兼容 ==========
+    # 统计字段（用于反馈）
+    llm_calls: int = 0
+    last_token_usage: Dict[str, Any] = field(default_factory=dict)
+    last_elapsed_time: float = 0.0
+    memory_context: str = ""  # 记忆检索结果
+    
+    # 向后兼容（保留但不推荐使用）
     debug_info: Dict[str, Any] = field(default_factory=dict)