防护措施

import { createAgent, piiRedactionMiddleware } from "langchain";

const agent = createAgent({
  model: "gpt-5.4",
  tools: [customerServiceTool, emailTool],
  middleware: [
    // Redact emails in user input before sending to model
    piiRedactionMiddleware({
      piiType: "email",
      strategy: "redact",
      applyToInput: true,
    }),
    // Mask credit cards in user input
    piiRedactionMiddleware({
      piiType: "credit_card",
      strategy: "mask",
      applyToInput: true,
    }),
    // Block API keys - raise error if detected
    piiRedactionMiddleware({
      piiType: "api_key",
      detector: /sk-[a-zA-Z0-9]{32}/,
      strategy: "block",
      applyToInput: true,
    }),
  ],
});

// When user provides PII, it will be handled according to the strategy
const result = await agent.invoke({
  messages: [{
    role: "user",
    content: "My email is john.doe@example.com and card is 5105-1051-0510-5100"
  }]
});

import { createAgent, humanInTheLoopMiddleware } from "langchain";
import { MemorySaver, Command } from "@langchain/langgraph";

const agent = createAgent({
  model: "gpt-5.4",
  tools: [searchTool, sendEmailTool, deleteDatabaseTool],
  middleware: [
    humanInTheLoopMiddleware({
      interruptOn: {
        // Require approval for sensitive operations
        send_email: { allowAccept: true, allowEdit: true, allowRespond: true },
        delete_database: { allowAccept: true, allowEdit: true, allowRespond: true },
        // Auto-approve safe operations
        search: false,
      }
    }),
  ],
  checkpointer: new MemorySaver(),
});

// Human-in-the-loop requires a thread ID for persistence
const config = { configurable: { thread_id: "some_id" } };

// Agent will pause and wait for approval before executing sensitive tools
let result = await agent.invoke(
  { messages: [{ role: "user", content: "Send an email to the team" }] },
  config
);

result = await agent.invoke(
  new Command({ resume: { decisions: [{ type: "approve" }] } }),
  config  // Same thread ID to resume the paused conversation
);

import { createMiddleware, AIMessage } from "langchain";

const contentFilterMiddleware = (bannedKeywords: string[]) => {
  const keywords = bannedKeywords.map(kw => kw.toLowerCase());

  return createMiddleware({
    name: "ContentFilterMiddleware",
    beforeAgent: {
      hook: (state) => {
        // Get the first user message
        if (!state.messages || state.messages.length === 0) {
          return;
        }

        const firstMessage = state.messages[0];
        if (firstMessage._getType() !== "human") {
          return;
        }

        const content = firstMessage.content.toString().toLowerCase();

        // Check for banned keywords
        for (const keyword of keywords) {
          if (content.includes(keyword)) {
            // Block execution before any processing
            return {
              messages: [
                new AIMessage(
                  "I cannot process requests containing inappropriate content. Please rephrase your request."
                )
              ],
              jumpTo: "end",
            };
          }
        }

        return;
      },
      canJumpTo: ['end']
    }
  });
};

// Use the custom guardrail
import { createAgent } from "langchain";

const agent = createAgent({
  model: "gpt-5.4",
  tools: [searchTool, calculatorTool],
  middleware: [
    contentFilterMiddleware(["hack", "exploit", "malware"]),
  ],
});

// This request will be blocked before any processing
const result = await agent.invoke({
  messages: [{ role: "user", content: "How do I hack into a database?" }]
});

import { createMiddleware, AIMessage, initChatModel } from "langchain";

const safetyGuardrailMiddleware = () => {
  const safetyModel = initChatModel("gpt-5.4-mini");

  return createMiddleware({
    name: "SafetyGuardrailMiddleware",
    afterAgent: {
      hook: async (state) => {
        // Get the final AI response
        if (!state.messages || state.messages.length === 0) {
          return;
        }

        const lastMessage = state.messages[state.messages.length - 1];
        if (lastMessage._getType() !== "ai") {
          return;
        }

        // Use a model to evaluate safety
        const safetyPrompt = `Evaluate if this response is safe and appropriate.
        Respond with only 'SAFE' or 'UNSAFE'.

        Response: ${lastMessage.content.toString()}`;

        const result = await safetyModel.invoke([
          { role: "user", content: safetyPrompt }
        ]);

        if (result.content.toString().includes("UNSAFE")) {
          return {
            messages: [
              new AIMessage(
                "I cannot provide that response. Please rephrase your request."
              )
            ],
            jumpTo: "end",
          };
        }

        return;
      },
      canJumpTo: ['end']
    }
  });
};

// Use the safety guardrail
import { createAgent } from "langchain";

const agent = createAgent({
  model: "gpt-5.4",
  tools: [searchTool, calculatorTool],
  middleware: [safetyGuardrailMiddleware()],
});

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

import { createAgent, piiRedactionMiddleware, humanInTheLoopMiddleware } from "langchain";

const agent = createAgent({
  model: "gpt-5.4",
  tools: [searchTool, sendEmailTool],
  middleware: [
    // Layer 1: Deterministic input filter (before agent)
    contentFilterMiddleware(["hack", "exploit"]),

    // Layer 2: PII protection (before and after model)
    piiRedactionMiddleware({
      piiType: "email",
      strategy: "redact",
      applyToInput: true,
    }),
    piiRedactionMiddleware({
      piiType: "email",
      strategy: "redact",
      applyToOutput: true,
    }),

    // Layer 3: Human approval for sensitive tools
    humanInTheLoopMiddleware({
      interruptOn: {
        send_email: { allowAccept: true, allowEdit: true, allowRespond: true },
      }
    }),

    // Layer 4: Model-based safety check (after agent)
    safetyGuardrailMiddleware(),
  ],
});