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
- Does installation/onboarding make sense?
- Does the app identify an actual Codex interruption, rather than an unrelated error?
- Does it point to the correct session instead of an older or unrelated task?
- 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?
Top comments (2)
Your last question is the right one, so here's my list, from the other side of the same problem…
I build cairn, a work harness for coding agents (github.com/eventually-consistent-code-org/cairn2), and its walk-away mode runs whole phases unattended inside Claude Code, so usage limits in the middle of the night are a thing I've had to think about. The platform does the waiting there, and the one lesson from building the part around it is this: the resume isn't the dangerous step, the gap is. Same session, same host, no guessing is a good bar, and it's the wrong unit. The question I'd want answered before trusting an unattended continuation is "what is this session allowed to do that it wasn't already doing when it stopped?" and the answer has to be nothing. A resumed run in cairn never widens scope, never pushes, never touches anything the original approval didn't cover, and if the run was frozen for refusals it never resumes under its own id at all. "Refuse if there are newer instructions" is one instance of that rule, and the rule is cheaper to test than the instances.
Second thing: three interruptions that look the same in the UI are three different animals, and the record has to say which. Limit hit and will reset, limit hit but the Mac slept through the reset and it's now waiting for a human, and limit hit too many times so automatic continue stopped. cairn writes each as its own row with the time it was observed, and never calls a wake-time row the reset time, because the platform doesn't say when it fired. Your Oct 14 note about resuming and then hitting model capacity is a fourth. If "inspect what resumed" in 0.3.2 shows the kind and the observed time per cycle, that's most of what I'd read in the morning. The wait length per cycle and the cycle count per task are the other two numbers, because once you can see them you start subtracting them from "how long did this take."
Third, and this is the one I'd want before the demo video: for each guardrail, the one forced failure that makes it refuse, written down. An unrelated Codex error that must not count as an interruption. A session file from an older task that must not be pinned. A message you typed after the pause that must stop the continuation. An approval prompt sitting open. Four refusals you made happen on purpose, with the line the app printed, is what I'd trust more than a successful resume, which is the easy case and exercises the least code. Your own honest line about the real test, preserved but didn't resume, is already that shape.
The honest trade in your direction: cairn deliberately builds nothing outside the session. Keeping the Mac awake and relaunching a host are the OS's and the vendor's job, and our 3.0 work is about reaching the web and desktop app surfaces, not a menubar watcher. So you're building the piece we chose not to, and I'd rather it exist than not…
One question. What does Continua actually read to decide "this is a usage limit and this is the session": a file Codex Desktop writes, the window text, or something the app exposes? That's the claim everything else rests on, and it's the one that moves when Codex ships a release.
Hey Spidy, I read your post about the free Mac beta for Codex interruptions. I'm a solo founder too and stuck on the same problem with my own tool, so I'm curious: who's the one kind of person you'd most want using it right now?