Managed Deep Agents v0.10 is out today. It adds browser use, so your agent can work on websites that have no API, and async subagents, which run long tasks in the background while your agent keeps talking with you. In this post, we cover why agents need each one and how to turn it on, then the rest of the release.
Managed Deep Agents v0.10 今天发布：新增浏览器使用（agent 能在没 API 的网站上干活）与异步子代理（长任务后台跑，主 agent 继续跟你聊）。这篇讲两者为什么需要、怎么开启，以及版本其余内容。
Give your agent a browser · 给 agent 一台浏览器
Booking travel, canceling a subscription, or filing a claim all happen on sites built for people clicking through pages, and there's often no API an agent can call. While agents can reason through how to complete the task, they can't take action on websites without an API. Fetching the page with curl doesn't get far either, it produces HTML before any JavaScript renders the page and the agent can't click anything. Personal agents like Instinct and Meta's Muse can browse websites to unlock a broader set of use cases, and DataDome saw agentic browser requests jump 4.7x in September alone. Coding agents need a browser too, to check that a change to an app actually renders and works.
订机票、退订阅、理赔都发生在「为人点页面」而建的网站上，往往没有 API 可调。agent 能推理出怎么完成任务，但没 API 就无法在网站上行动；用 curl 抓页面也走不远——拿到的是 JavaScript 渲染之前的 HTML，什么也点不了。Instinct、Meta 的 Muse 这类个人 agent 已靠浏览网站解锁更大的用例集，DataDome 光 9 月一个月就看到 agent 浏览器请求涨了 4.7 倍。coding agent 同样需要浏览器——验证对应用的改动真的渲染且能用。
To turn it on, declare a browser at your project root: # browser.py from managed_deepagents import define_browser; browser = define_browser(scope 设 thread, idle_ttl_seconds 600). Managed Deep Agents runs the browser in its own LangSmith sandbox and adds the following browser tools to your agent automatically. browser_snapshot reads the page's accessibility tree and assigns element IDs. browser_run navigates and interacts, through JavaScript or batches of actions against snapshot IDs. browser_screenshot captures the page, optionally saving the image to the sandbox. browser_handoff gives a person control of the window.
开启方式：项目根声明 browser = define_browser(scope 设 thread, idle_ttl_seconds 600)。浏览器跑在专属的 LangSmith 沙箱里，以下浏览器工具自动加给 agent：**browser_snapshot**（读页面无障碍树并给元素编 ID）、**browser_run**（按快照 ID 导航与交互，支持 JavaScript 或批量动作）、**browser_screenshot**（截屏，可选存图进沙箱）、**browser_handoff**（把窗口交给真人控制）。
By default, each conversation gets its own browser, which is reused across turns and starts with no cookies or logins from other threads. With scope="user", each signed-in person gets one browser whose logins carry across all of their conversations, so the agent only asks them to sign in to a site once.
默认每个会话一个浏览器：跨轮复用，且不带其他线程的 cookie 或登录。scope 设为 user 则每个登录用户一个浏览器，登录跨其全部会话保留——agent 只请用户对每个网站登录一次。
Hand the browser to a person · 把浏览器交给真人
Most browser agents stop at a login wall or a two-factor prompt. With browser_handoff, the agent hands the window to you instead, so your password never ends up in the model's messages or traces. The agent calls browser_handoff(reason) and explains why it needs you. Your agent channels — like Slack and Studio — will show a link to allow users of your agents to hand off browser control natively, which opens a link to interact with the remote browser and a Hand back button. Custom clients can render the handoff artifact themselves. Once you sign in and hand control back, the agent checks the page to see whether the login worked and continues. Handoff returns immediately, so the agent can do other work while it waits. Handoff links expire after 15 minutes. Handoffs let your agent use a webpage for you, without seeing your credentials.
多数浏览器 agent 卡在登录墙或两步验证。browser_handoff 让 agent 改为把窗口交给你——**你的密码永远不会出现在模型的消息或轨迹里**。agent 调 browser_handoff(reason) 并解释为什么需要你；agent 渠道（Slack、Studio）会原生显示交接链接，点开即与远端浏览器交互，还有一个「交还」按钮；自定义客户端可自行渲染交接 artifact。你登录并交还控制权后，agent 检查页面确认登录成功、继续干活。交接调用立即返回，等待期间 agent 可以干别的；交接链接 15 分钟过期。交接让你的 agent 替你使用网页，而看不到你的凭证。
Run subagents in the background · 子代理后台跑
Subagents let an agent hand a focused task to a helper with its own context window. Previously in Managed Deep Agents, subagents ran inline, so the agent called one and waited for its answer. This works for a quick lookup, and still is a supported pattern. But for a long task backed by a synchronous agent, or where multiple agents need to be fanned out, the person talking to the agent waits too, and additional interactions with the orchestrator agent are blocked. With Managed Deep Agents v0.10, you can run subagents asynchronously, without blocking the orchestrator agent, by adding async to a subagent definition: from managed_deepagents import define_deep_agent; agent = define_deep_agent(name="research-assistant", model="openai:gpt-5.5", subagents=[{ "name": "researcher", "description": "Researches a topic in the background.", "system_prompt": "Research the topic…", "async": True }]). A long job can go to a subagent that runs in the background while your agent keeps talking with you. You can ask the agent to check on the job or change its course, and the result comes back to the conversation when the subagent finishes.
子代理让 agent 把聚焦任务交给有独立上下文窗口的帮手。此前 Managed Deep Agents 里子代理是内联跑的：agent 调一个就等一个的答案——快查没问题（仍是受支持的模式），但长任务或需要扇出多个 agent 时，与 agent 对话的人也被晾着、与编排 agent 的其他交互全部阻塞。v0.10 在子代理定义（如 model=openai:gpt-5.5 的 research-assistant 下挂 researcher）里加 async 即可异步运行、不阻塞编排 agent：define_deep_agent 的 subagents 列表里给子代理定义加 async 字段——长任务交给后台子代理，主 agent 继续与你对话；你可以问进度、改方向，子代理完成时结果回到对话。
The rest of the release · 版本其余内容
Thread origins and stopping runs: Replies go back to the Slack thread a request started in, including replies from a scheduled run or from a subagent that finished later. A Stop button in the thread cancels its runs. Also new in this release: runtime.thread and resolveUser, and the removal of connectors.mcp() and other older interfaces.
回复回到请求发起的 Slack 线程——包括定时运行的回复与迟归的子代理；线程内的 Stop 按钮可取消其运行。本版还新增 runtime.thread 与 resolveUser，并移除了 connectors.mcp() 等旧接口。