I released a free Mac beta for Codex interruptions. I need people to break it.

I'm building Continua because I got tired of leaving a Codex task running and coming back to find that it had stopped hours earlier.

I now have a free experimental macOS beta, and I'm looking for developers who use Codex Desktop on Mac and are willing to test it.

The aim is narrow: keep track of a task interrupted by a genuine usage limit, wait until usage is available again, then attempt to continue the same task only if the original session and environment can be verified. It doesn't bypass quota or approve commands on your behalf.

Where it stands

• The beta is available for macOS 13+ (Apple silicon and Intel).
• In a real usage-limit test, the app safely preserved the interruption but did not successfully resume when usage returned.
• I've patched the retry logic, but a fresh, fully unattended interruption → reset → continuation cycle still needs validation.
• The build is unsigned and not Apple-notarized. Check the installation instructions before installing.

So I'm not looking for nice reviews. I'd rather hear what doesn't work.

What I'd love tested

1. Does installation/onboarding make sense?
2. Does the app identify an actual Codex interruption, rather than an unrelated error?
3. Does it point to the correct session instead of an older or unrelated task?
4. Does it refuse to continue if Codex is waiting for approval, or if you've sent newer instructions?

Try the free beta · Installation guide · Feedback and bug reports

I'm building Continua independently; it isn't an official OpenAI product. If you're using Codex on macOS, what would you need to see before trusting unattended continuation?