Codex 更新：对话中可切换推理档位且不丢缓存
Why we picked it
用 Codex 写代码的可以升级了：推理强度随用随切还不掉缓存，低档省钱高档干活，CLI 也顺手不少。
OpenAI 的 Codex 现在支持在对话中途切换推理档位（reasoning level），切换时不丢失已有缓存，可在快速任务用低档、复杂任务调高档。CLI 同时加入可复用的提示词预设、内联切换模型和权限、长会话恢复修复。企业侧新增 MCP 登录与 Windows 代理认证支持，dot 调用连接速度也更快。
Original · Vaibhav Srivastav
QoL update for Codex devs:
You can now switch reasoning levels mid-conversation without losing your cache! Use lower reasoning for the quick stuff and dial it up when you need it, without having to rebuild the context.
and some nice CLI updates:
- Reusable prompt presets - Change models and permissions inline - Fixes for resuming long sessions - Enterprise MCP sign-in and Windows proxy auth
Also dot calls connect much faster now too ;)
