OpenAI Codex 0.144.0 发布
英文标题:OpenAI Codex 0.144.0
OpenAI Codex 0.144.0 版本发布,带来多项新功能:使用量重置积分现可显示类型与过期时间并允许选择兑换;新增 writes 应用审批模式,可声明只读动作并需为写入操作确认;MCP 工具无需实验性选项即可交互式认证,应用主机支持运行时认证和登录重定向。此版本修复了 Intel macOS 崩溃、Windows 沙箱文件删除、终端控制序列损坏、认证过期等问题,并优化了大型仓库中 /review 分支选择器性能。这些改进增强了开发者对资源消耗和安全性的控制,提升了多智能体场景下的使用体验。
打开原文相关 12.1 · 机会 3
1.1 KB
1.5 KB
1.7 KB
21.9 KB
1.8 KB
1.7 KB
1.6 KB
1.5 KB
1.4 KB
1.6 KB
1.3 KB
1.7 KB
1.8 KB
1.3 KB
2.3 KB
1.5 KB
1.4 KB
1.5 KB
1.5 KB
1.5 KB
中文
新功能
- 使用量限制重置积分现在会显示其类型和过期时间,并可让您选择要兑换的积分。 (#30488)
- 新增
writes应用审批模式,允许在提示写入的同时执行已声明的只读操作。 (#30482) - MCP 工具现在无需实验性 opt-in 即可交互式请求认证。 (#28772)
- 应用服务器主机可在运行时提供 Codex 认证,并将成功登录重定向到托管页面。 (#28745, #31274)
- 全局 pnunen 安装现在可被检测到,以便诊断和更新使用正确的包管理器。 (#31503)
- 选择 Ultra 推理时,现在会警告高多智能体并发可能快速增加用量。 (#31621)
错误修复
- 恢复的 ChatGPT 线程在压缩引用已退役模型时,可通过重试当前选定的模型来恢复。 (#30319)
- 修复了 Intel macOS 发布二进制文件中的 Code Mode 崩溃问题。 (#30953)
- Windows 沙箱会话现在可以删除可写根目录中的文件并访问受管的主运行时。 (#31138, #31574)
- 粘贴的终端控制序列不会破坏 TUI 渲染或恢复的对话历史记录。 (#31494)
- 长时间运行的应用会话现在会刷新托管
codex_apps连接器的过期认证。 (#31486) - 响应 WebSocket 在尊重系统代理和自定义证书颁发机构的同时继续使用低延迟传输。 (#31441, #31622)
文档
- 设备代码登录警告现在解释如何识别和阻止网络钓鱼尝试。 (#31648)
杂项
- 通过在每个根目录下解析一次命名空间,减少了远程执行器上插件技能加载时间。 (#31348)
- 使
/review分支选择器在大型仓库中更快更可靠。 (#31464) - 通过提供更清晰的说明和聚焦的工具集改进了自动审查行为。 (#31480)
- 使 Amazon Bedrock 模型名称能清楚标识其 GPT-5.6 系列和变体。 (#31636)
变更日志
English / 原文
New Features
- Usage-limit reset credits now show their type and expiration, and let you choose which credit to redeem. (#30488)
- Added a
writesapp-approval mode that allows declared read-only actions while prompting for writes. (#30482) - MCP tools can now request authentication interactively without an experimental opt-in. (#28772)
- App-server hosts can provide Codex authentication at runtime and redirect successful logins to a hosted page. (#28745, #31274)
- Global pnunen installs are now detected so diagnostics and updates use the correct package manager. (#31503)
- Selecting Ultra reasoning now warns when high multi-agent concurrency could increase usage quickly. (#31621)
Bug Fixes
- Resumed ChatGPT threads recover when compaction references a retired model by retrying with the currently selected model. (#30319)
- Fixed Code Mode crashes in Intel macOS release binaries. (#30953)
- Windows sandbox sessions can delete files in writable roots and access the managed primary runtime. (#31138, #31574)
- Pasted terminal control sequences can no longer corrupt TUI rendering or resumed conversation history. (#31494)
- Long-running app sessions now refresh expired authentication for the hosted
codex_appsconnector. (#31486) - Responses WebSockets continue using the low-latency transport while respecting system proxies and custom certificate authorities. (#31441, #31622)
Documentation
- Device-code login warnings now explain how to recognize and stop phishing attempts. (#31648)
Chores
- Reduced plugin skill-loading time on remote executors by resolving namespaces once per root. (#31348)
- Made the
/reviewbranch picker faster and more reliable in large repositories. (#31464) - Improved automatic review behavior with clearer instructions and a focused tool set. (#31480)
- Made Amazon Bedrock model names clearly identify their GPT-5.6 family and variant. (#31636)
Changelog
Full Changelog: rust-v0.143.0...rust-v0.144.0