OpenAI 为其软件工程智能体 Codex 推出了新功能，使其不再局限于开发者的笔记本电脑，而是通过可复用的云开发环境，让用户能从任何设备访问。
OpenAI introduced new capabilities for its software engineering agent Codex, making it more useful beyond a developer’s laptop with reusable cloud development environments that can be accessed from any device.
该更新于周二的 OpenAI Dev Day 上发布，是 Codex 众多更新之一。OpenAI 还宣布了焕新的 Codex CLI、全新的代码审查体验、基础设施加固工具以及其他 API 增强功能。
The update, announced at OpenAI’s Dev Day on Tuesday, is one of several for Codex. OpenAI also announced a refreshed Codex CLI, a new code review experience, tools to harden infrastructure, and other API enhancements.
虽然 Codex 此前已能启动云任务以远程工作，但今天的公告显示，OpenAI 正让这些云环境更持久、更可配置，而不再将每个云任务视为孤立的远程沙箱。
While Codex could already spin up cloud tasks to do work remotely, today’s announcement shows that OpenAI is making those cloud environments more persistent and configurable, rather than treating each cloud task as an isolated remote sandbox.
正如公司所解释，开发者现在能在任何需要的地方运行 Codex，无论是电脑上、手机远程操作，还是在云端。OpenAI 表示，可复用的开发环境旨在帮助任务更快启动，并为团队提供一个具有经批准设置和权限的共享工作空间。
As the company explains, developers will now be able to run Codex wherever they need it, whether that’s on a computer, remotely from a phone, or in the cloud. The reusable development environments are designed to help tasks start more quickly and give teams a shared workspace with approved settings and permissions, OpenAI said.
同时，Codex CLI 获得更新，允许开发者使用语音启动和指导任务。
Meanwhile, the Codex CLI is getting an update that allows developers to start and direct tasks using their voice.
新的 /agents 视图旨在让委派工作和同时追踪多个任务变得更容易。其他改进包括日常任务的优化，如编辑提示词、恢复会话和使用工作树。OpenAI 还推出了“更简洁”的终端用户界面，旨在让长时间会话更轻松。Codex 还可被引入 ChatGPT 桌面应用中的新代码审查体验，用户可在其中阅读摘要、探索代码变更，或在 GitHub 拉取请求或 GitLab 合并请求上分享反馈前，向 Codex 询问潜在问题。
A new /agents view is meant to make it easier to delegate work and track multiple tasks at the same time. Other changes include improvements to everyday tasks such as editing prompts, resuming sessions, and using worktrees. OpenAI is also rolling out a “cleaner” terminal user interface designed to make longer sessions easier Codex can also be pulled into a new code review experience within the ChatGPT desktop app, where users can read summaries, explore code changes, or ask Codex about potential issues before sharing feedback on GitHub pull requests or GitLab merge requests.
自动代码审查还能让 Codex 在用户离开电脑时执行初步审查。
Automatic code reviews also let Codex perform an initial review while users step away from their computers.
在安全方面，OpenAI正在推出一套名为 Codex Security Cloud 的新工具，旨在帮助开发者保护他们的基础设施。开发者可以按需或定期使用这些工具来扫描整个 GitHub 仓库，或者在新的代码提交时自动进行扫描。Codex 会分析扫描结果、删除重复的漏洞信息，并在云端准备相应的修复方案——即使开发者当前不在线、笔记本电脑处于关闭状态，这些功能依然可以正常运行。
On the security side, OpenAI is rolling out a new set of tools called Codex Security Cloud, designed to help developers secure their infrastructure. Developers can use the tools to scan entire GitHub repositories on demand or on a regular schedule, as well as whenever new commits arrive. Codex will then investigate findings, remove duplicates, and prepare fixes in the cloud — even when the user isn’t active and their laptop is closed.
值得注意的是，这套工具集允许开发者直接使用 OpenAI 的网络安全项目 Daybreak Blue 提供的模型，而无需另行提交申请。
Notably, the toolset includes access to the models offered through OpenAI’s cybersecurity initiative Daybreak Blue without requiring developers to submit a separate application.
此外，OpenAI 还宣布了对多个 API 的更新，其中包括一个新的“Decisions API”，用于实现实时决策功能。该 API 利用 Luna 技术来回答用户预先定义的问题（这些问题都配有预设的答案）。同时，OpenAI 还更新了“Agents API”的版本，使其支持计算机的使用，并允许开发者利用 Amazon 的 Bedrock Managed Agents 来构建完全运行在 AWS 上的 OpenAI 代理程序。
OpenAI also announced several API updates, including a new Decisions API for real-time decision-making. The API uses Luna to answer a set of user-defined questions with predefined answers. The company also introduced an updated a version of the Agents API that now supports computer use and the ability to use Amazon’s Bedrock Managed Agents to build OpenAI agents that run entirely on AWS.