Codex CLI轻量级 AI 编程智能体 ：openai又放大招了
Codex CLI是轻量级 AI 编程智能体，基于自然语言指令帮助开发者高效生成代码、执行文件操作和进行版本控制。
源码：https://github.com/openai/codex
安装
只要有npm就可以安装：
# npm install codex
sudo npm install -g @openai/codex设置环境变量OPENAI_API_KEY
Next, set your OpenAI API key as an environment variable:
export OPENAI_API_KEY="your-api-key-here"
Note: This command sets the key only for your current terminal session. You can add the
exportline to your shell's configuration file (e.g.,~/.zshrc) but we recommend setting for the session. Tip: You can also place your API key into a.envfile at the root of your project:OPENAI_API_KEY=your-api-key-hereThe CLI will automatically load variables from
.env(viadotenv/config).
然后直接运行codex即可：
Run interactively:
codex
Or, run with a prompt as input (and optionally in Full Auto mode):
或者是直接跟上prompt：
codex "explain this codebase to me"
codex --approval-mode full-auto "create the fanciest todo-list app"
skywalk@fb:~ $ OPENAI_API_KEY=hello
skywalk@fb:~ $ OPENAI_URL_BASE=http://192.168.1.5:1337/v1
OPENAI_URL_BASE=http://192.168.1.5:1337/v1 OPENAI_API_KEY=hello codex
╭──────────────────────────────────────────────────────────────╮
│ ● OpenAI Codex (research preview) v0.1.2504251709 │
╰──────────────────────────────────────────────────────────────╯
╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│Warning! It can be dangerous to run a coding agent outside of a git repo in case there are changes that you want to │
│revert. Do you want to continue? │
│ │
│/home/skywalk │
│ │
│y/N │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
配置
vi ~/.codex/config.json
写配置：
{"model": "o4-mini","provider": "openai","providers": {"openai": {"name": "OpenAI","baseURL": "http://192.168.1.5:1337/v1","envKey": "OPENAI_API_KEY"},
}
}
启动
OPENAI_API_KEY=hello codex总结：
codex并没有调试通，后来是安装了codex的国内个人升级版：codexy，倒是调试成功了，具体见：codexy一个在终端中运行的轻量级编码助手（OpenAI Codex CLI Python 版本）-CSDN博客
总之，因为openai本身的问题，导致codex的调试极难，最终放弃，还是改投codexy
调试
一直打印横向字符串
一直没调试好....
咨询：Which models are supported?
Any model available with Responses API. The default is o4-mini, but pass --model gpt-4.1 or set model: gpt-4.1 in your config file to override.
Sorry, you have been blocked
You are unable to access openai.com
大约就是用openai的大部分模型都可以。
修改了model gpt-4o，但是没改过来
model: o4-mini │
│ ↳ provider: openai │
│ ↳ approval: suggest
后来在命令行里带了模型，终于改过来了。codex "explain this codebase to me" --model deepseek-v3
还是报超时，就好像.codex/config.json文件没有起作用一样
里面的baseurl没起作用，在命令行里带上：
codex "explain this codebase to me" --model deepseek-v3 --baseURL "http://192.168.1.5:1337/v1"
还是报错超时：
system
⚠️ Network error while contacting OpenAI. Please check your connection and try again.
所以一直没有调通
在WSL Ubuntu22环境下报错SyntaxError: Unexpected token '?'
codex
SyntaxError: Unexpected token '?'
at Loader.moduleStrategy (internal/modules/esm/translators.js:133:18)
at async link (internal/modules/esm/module_job.js:42:21)
AI说：升级 Node.js 是最直接的解决方案。
不明白啥原因