守护机制

from typing import Any

from langchain.agents.middleware import AgentMiddleware, AgentState, hook_config
from langgraph.runtime import Runtime

class ContentFilterMiddleware(AgentMiddleware):
    """确定性守护机制：阻止包含禁用关键词的请求。"""

    def __init__(self, banned_keywords: list[str]):
        super().__init__()
        self.banned_keywords = [kw.lower() for kw in banned_keywords]

    @hook_config(can_jump_to=["end"])
    def before_agent(self, state: AgentState, runtime: Runtime) -> dict[str, Any] | None:
        # 获取第一条用户消息
        if not state["messages"]:
            return None

        first_message = state["messages"][0]
        if first_message.type != "human":
            return None

        content = first_message.content.lower()

        # 检查禁用关键词
        for keyword in self.banned_keywords:
            if keyword in content:
                # 在任何处理前阻止执行
                return {
                    "messages": [{
                        "role": "assistant",
                        "content": "I cannot process requests containing inappropriate content. Please rephrase your request."
                    }],
                    "jump_to": "end"
                }

        return None

# 使用自定义守护机制
from langchain.agents import create_agent

agent = create_agent(
    model="gpt-4.1",
    tools=[search_tool, calculator_tool],
    middleware=[
        ContentFilterMiddleware(
            banned_keywords=["hack", "exploit", "malware"]
        ),
    ],
)

# 此请求将在任何处理前被阻止
result = agent.invoke({
    "messages": [{"role": "user", "content": "How do I hack into a database?"}]
})

from langchain.agents.middleware import AgentMiddleware, AgentState, hook_config
from langgraph.runtime import Runtime
from langchain.messages import AIMessage
from langchain.chat_models import init_chat_model
from typing import Any

class SafetyGuardrailMiddleware(AgentMiddleware):
    """基于模型的守护机制：使用 LLM 评估响应安全性。"""

    def __init__(self):
        super().__init__()
        self.safety_model = init_chat_model("gpt-4.1-mini")

    @hook_config(can_jump_to=["end"])
    def after_agent(self, state: AgentState, runtime: Runtime) -> dict[str, Any] | None:
        # 获取最终的 AI 响应
        if not state["messages"]:
            return None

        last_message = state["messages"][-1]
        if not isinstance(last_message, AIMessage):
            return None

        # 使用模型评估安全性
        safety_prompt = f"""评估此响应是否安全且适当。
        仅回复 'SAFE' 或 'UNSAFE'。

        响应：{last_message.content}"""

        result = self.safety_model.invoke([{"role": "user", "content": safety_prompt}])

        if "UNSAFE" in result.content:
            last_message.content = "I cannot provide that response. Please rephrase your request."

        return None

# 使用安全守护机制
from langchain.agents import create_agent

agent = create_agent(
    model="gpt-4.1",
    tools=[search_tool, calculator_tool],
    middleware=[SafetyGuardrailMiddleware()],
)

result = agent.invoke({
    "messages": [{"role": "user", "content": "How do I make explosives?"}]
})