Langgraph条件边实现报错：AIMessage不可下标访问修复方案

错误原因 #

调用llm.invoke()后返回的是AIMessage实例，而非包含messages键的字典，因此使用response["messages"]会触发"对象不可下标访问"的TypeError。

修复步骤 #

• 直接通过response.content获取模型返回的文本内容，而非尝试以字典方式访问messages字段。
• 可选：优化系统提示，强制模型仅返回指定关键词（language_info或development_tasks），减少后续判断的干扰。

修改后的query_decision_func代码 #

def query_decision_func(state):
    user_query = [msg for msg in state["messages"] if isinstance(msg, HumanMessage)][-1].content

    system_message = """
    You are an AI assistant that decides whether the query is about software development tasks or a specific question about a programming language.
    Based on the context of the user's query, determine whether it is about:
    - A specific programming language (e.g., "When was Java released?")
    - A software development task (e.g., writing code, designing architecture, etc.)
    
    Provide your decision on how the query should be processed.
    YOU MUST ONLY RETURN ONE OF THE FOLLOWING EXACT STRINGS:
    "language_info" or "development_tasks"
    """
    
    # Get the model's response to the query and system message
    response = llm.invoke([SystemMessage(content=system_message)] + [HumanMessage(content=user_query)])
    
    # Analyze the response from the model
    model_decision = response.content.strip().lower()
    
    # Based on the model's decision, route to the appropriate node
    if model_decision == "language_info":
        return "language_info"
    elif model_decision == "development_tasks":
        return "analyst"
    else:
        # Default case: route to development tasks if unsure
        return "analyst"

内容的提问来源于stack exchange，提问作者xxjmpxx__