OpenAI 为 Codex 推出可跨设备使用的可复用云端开发环境

OpenAI 为其软件工程 Agent Codex 推出了新能力：通过可复用、可从任何设备访问的云端开发环境，让 Codex 不再局限于开发者的笔记本电脑。

这项更新于周二在 OpenAI DevDay 上宣布，是 Codex 多项更新中的一部分。OpenAI 还发布了焕新的 Codex CLI、新的代码审查体验、用于强化基础设施的工具，以及其他 API 增强功能。

尽管 Codex 此前已可启动云端任务以远程完成工作，但今天的公告表明，OpenAI 正让这些云端环境具备更强的持久性和可配置性，而非将每项云端任务都视为相互隔离的远程沙盒。

正如该公司所述，开发者如今可以在任何所需位置运行 Codex，无论是在电脑上、通过手机远程操作，还是直接在云端运行。OpenAI 表示，可复用开发环境旨在帮助任务更快启动，并为团队提供具有获批设置与权限的共享工作空间。

图片来源： OpenAI

与此同时，Codex CLI 将获得更新，使开发者能够通过语音启动和指挥任务。

新的 /agents 视图旨在让委派工作以及同时跟踪多项任务变得更加容易。其他变化包括改进日常操作，例如编辑提示词、恢复会话和使用 worktrees。OpenAI 还将推出一套“更简洁”的终端用户界面，旨在让较长会话更易于阅读。

图片来源： OpenAI

Codex 还可以接入 ChatGPT 桌面应用中的全新代码审查体验，用户可阅读摘要、查看代码变更，或在向 GitHub pull request 或 GitLab merge request 提交反馈前，询问 Codex 是否存在潜在问题。

自动代码审查功能还允许 Codex 在用户离开电脑期间完成初步审查。

图片来源： OpenAI

在安全方面，OpenAI 正推出一套名为 Codex Security Cloud 的新工具，旨在帮助开发者保护其基础设施。开发者可按需或定期扫描整个 GitHub 仓库，也可以在新提交到来时触发扫描。随后，Codex 将调查发现的问题、去除重复项，并在云端准备修复方案——即使用户当前并未使用系统、笔记本电脑处于关闭状态。

值得注意的是，这套工具包含对 OpenAI 网络安全计划 Daybreak Blue 所提供模型的访问权限，开发者无需单独提交申请。

图片来源： OpenAI

OpenAI 还宣布了多项 API 更新，包括面向实时决策的新 Decisions API。该 API 使用 Luna，针对一组由用户定义的问题给出预先设定的答案。该公司还推出了更新版本的 Agents API，现已支持计算机操作，并支持使用 Amazon 的 Bedrock Managed Agents 构建完全运行在 AWS 上的 OpenAI Agent。

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.

The update, announced at OpenAI’s DevDay 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.

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.

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.

Image Credits: OpenAI

Meanwhile, the Codex CLI is getting an update that allows developers to start and direct tasks using their voice.

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 to read.

Image Credits: OpenAI

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.

Automatic code reviews also let Codex perform an initial review while users step away from their computers.

Image Credits: OpenAI

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.

Notably, the tool set includes access to the models offered through OpenAI’s cybersecurity initiative Daybreak Blue, without requiring developers to submit a separate application.

Image Credits: OpenAI

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.