init

agents/base_agent.py

@@ -1,76 +1,6 @@
-from typing import Any, Dict, List, Optional
-from langchain_core.messages import BaseMessage, HumanMessage
-from langchain_openai import ChatOpenAI
-from langgraph.graph import StateGraph, END
-from config import Config
+"""兼容导出：请优先使用 agent 包"""
 
+from agent.graph import BaseAgent
+from agent.state import AgentState
 
-class AgentState:
-    """State definition for the agent workflow"""
-    messages: List[BaseMessage]
-    current_step: str
-    context: Dict[str, Any]
-    
-    def __init__(self, messages: List[BaseMessage] = None, current_step: str = "start", context: Dict[str, Any] = None):
-        self.messages = messages or []
-        self.current_step = current_step
-        self.context = context or {}
-
-
-class BaseAgent:
-    """Base agent class with common functionality"""
-    
-    def __init__(self, model_name: str = Config.DEFAULT_MODEL):
-        self.model = ChatOpenAI(
-            model=model_name,
-            api_key=Config.OPENAI_API_KEY,
-            temperature=0.1,
-            max_retries=Config.MAX_RETRIES,
-            timeout=Config.TIMEOUT
-        )
-        self.graph = self._build_graph()
-    
-    def _build_graph(self) -> StateGraph:
-        """Build the state graph for the agent"""
-        workflow = StateGraph(AgentState)
-        
-        # Add nodes and edges
-        workflow.add_node("process_input", self._process_input)
-        workflow.add_node("generate_response", self._generate_response)
-        
-        # Define edges
-        workflow.add_edge("process_input", "generate_response")
-        workflow.add_edge("generate_response", END)
-        
-        # Set entry point
-        workflow.set_entry_point("process_input")
-        
-        return workflow.compile()
-    
-    def _process_input(self, state: AgentState) -> AgentState:
-        """Process user input"""
-        # This is a base implementation - subclasses should override
-        state.current_step = "processed"
-        return state
-    
-    def _generate_response(self, state: AgentState) -> AgentState:
-        """Generate response using the LLM"""
-        if state.messages:
-            response = self.model.invoke(state.messages)
-            state.messages.append(response)
-        return state
-    
-    def run(self, user_input: str, **kwargs) -> Dict[str, Any]:
-        """Run the agent with user input"""
-        initial_state = AgentState(
-            messages=[HumanMessage(content=user_input)],
-            context=kwargs
-        )
-        
-        result = self.graph.invoke(initial_state)
-        
-        return {
-            "messages": result.messages,
-            "context": result.context,
-            "final_step": result.current_step
-        }
+__all__ = ["BaseAgent", "AgentState"]