codex

It’s probably not really related, but this bug and the saga of OpenAI trying and failing to fix it for two weeks is not indicative of a functional company: https://github.com/openai/codex/issues/9253 OTOH, if Anthropic did that to Claude Code, there wasn’t a moderately straightforward workaround, and Anthropic didn’t revert it quickly, it might actually be a risk-the-whole-business issue. Nothing makes people jump ship quite like the ship refusing to go anywhere for weeks while the skipper fumbles around and keeps claiming to have fixed the engines. Also, the fact that it’s not major news that most business users cannot log in to the agent CLI for two weeks running is not major news suggests that OpenAI has rather less developer traction than they would like. (Personal users are fine. Users who are running locally on an X11-compatible di

yes [0] > The Rust implementation is now the maintained Codex CLI and serves as the default experience [0] https://github.com/openai/codex/tree/main/codex-rs#whats-new...

Wow, this part where they describe skills sounds quite odd https://github.com/openai/codex/blob/99f47d6e9a3546c14c43af9... Why wouldnt they just expose the files directly? Having the model ask for them as regular files sounds a bit odd

Hmm, this seems promising? https://github.com/openai/codex/pull/9796

This came as a big surprise to me last year. I remember they announced that Codex CLI is opensource, and the codex-rs [0] from TypeScript to Rust, with the entire CLI now open source. This is a big deal and very useful for anyone wanting to learn how coding agents work, especially coming from a major lab like OpenAI. I've also contributed some improvements to their CLI a while ago and have been following their releases and PRs to broaden my knowledge. [0] https://github.com/openai/codex/tree/main/codex-rs

Maybe it's changed, but this is certainly how it was back in November. I would see my context window jump in size, after each user turn (i.e. from 70 to 85% remaining). Built a tool to analyze the requests, and sure enough the reasoning tokens were removed from past responses (but only between user turns). Here are the two relevant PRs [0][1]. When trying to get to the bottom of it, someone from OAI reached out and said this was expected and a limitation of the Responses API (interesting sidenote: Codex uses the Responses API, but passes the full context with every request). This is the relevant part of the docs[2]: > In turn 2, any reasoning items from turn 1 are ignored and removed, since the model does not reuse reasoning items from previous turns. [0]https://github.com/openai/codex/pull/5857 [1]https://github.com/openai/codex/pull/598

The best part about this blog post is that none of it is a surprise – Codex CLI is open source. It's nice to be able to go through the internals without having to reverse engineer it. Their communication is exceptional, too. Eric Traut (of Pyright fame) is all over the issues and PRs. https://github.com/openai/codex

What I really want from Codex is checkpoints ala Copilot. There are a couple of issues [0][1] opened about on GitHub, but it doesn't seem a priority for the team. [0] https://github.com/openai/codex/issues/2788 [1] https://github.com/openai/codex/issues/3585

"At some point I realized that rather than do something else until it finishes, I would constantly check on it to see if it was asking for yet another permission, which felt like it was missing the point of having an agent do stuff" Why don't Claude Code & other AI agents offer an option to make a sound or trigger a system notification whenever they prompt for approval? I've looked into setting this up, and it seems like I'd have to wire up a script that scrapes terminal output for an approval request. Codex has had a feature request open for a while: https://github.com/openai/codex/issues/3052

OpenAI rolled out a shiny new version of codex (the CLI) that finally supports device code authentication, so now it's finally now awkward to use it in headless environments. And they appear to have disabled the old non-headless variant in the mean time. But trying to use it in a workspace says "Please contact your workspace admin to enable device code authentication". It's not obvious that this setting actually exists, and OpenAI's chat support says, and I quote, "The latest updates require device code authentication, which works for personal ChatGPT accounts but does not work for workspace (Business/Enterprise/Edu) users." An actual human at OpenAI closed the relevant issue as "not planned": https://github.com/openai/codex/issues/9253 Did OpenAI really just decide that it doesn't need to be possible to use the codex CLI on a paid work