智能体
x.com ·
@LangChain(@LangChainAI)
LangGraph 推出带类型响应 schema 的 interrupt 功能
LangChain 转述 Sydney Runkle 的更新：LangGraph 的 interrupt 现支持定义类型化响应 schema，人类回复在传回 agent 前会先经过校验，并可在 UI 中渲染真实响应表单，而非仅提供 JSON 输入框。官方称这是“类型安全的人类介入”，并给出文档链接。
AI推荐理由 LangGraph 新增带类型响应 schema 的 interrupt 功能，属于开发者可直接使用的具体新能力：人类介入时响应在回传 agent 前先做校验，并可在 UI 渲染真实表单而非 JSON 输入框。信息来自官方账号转述并附文档链接，但正文为转推片段，缺少版本号与完整示例，实际效果未验证。
72
正文
.[@sydneyrunkle](https://x.com/sydneyrunkle) on the latest in LangGraph
Sydney Runkle@sydneyrunkle
new in langgraph: interrupts with typed response schemas!
when your agent pauses for a human, you define what a valid response looks like:
1. responses are validated before they're passed back to the agent
2. you can render a real response form in your UI, not just a json entry field
human in the loop, but (type) safe
docs: [docs.langchain.com/oss/python/lan…](https://docs.langchain.com/oss/python/langgraph/interrupts#define-an-interrupt-response-schema)
[Your browser does not support the video tag.](https://video.twimg.com/amplify_video/2105385691027001344/vid/avc1/1920x1080/uD9AE-Y91kXuTcCs.mp4?tag=29)
[🔗 View on Twitter](https://x.com/sydneyrunkle/status/2105386023752790083/video/1)
[🔗 View Quoted Tweet](https://x.com/sydneyrunkle/status/2105386023752790083)
💬0🔄0❤️3👀1334📊1