Codex Cloud - Post Setup Caching isn't working

Resolved 💬 10 comments Opened Nov 13, 2025 by samskiter Closed Mar 29, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What version of Codex is running?

Cloud

What subscription do you have?

ChatGPT Business

Which model were you using?

N/A

What platform is your computer?

N/A

What issue are you seeing?

Every time we run a task (even updating an existing task by asking follow on) we see the FULL setup script (not the maintenance script). We have container caching turned on and are asking questions in well under 12 hours.

This makes a simple change to an existing session take >10 minutes

What steps can reproduce the bug?

Start a task or comment on an existing task.

What is the expected behavior?

Codex should reuse the cached container from the previous run and execute quickly.

Additional information

_No response_

View original on GitHub ↗

10 Comments

samskiter · 8 months ago
github-actions[bot] contributor · 8 months ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

  • #4871

Powered by Codex Action

samskiter · 8 months ago

Nope, that duplicate actually shows others having the same issue

OptiWhisperer · 8 months ago

Yes, I have this issue too and the linked issue #4871 doesn't address it at all. This is so bad that I've abandoned codex cloud - if the base image doesn't have what you need then you have no recourse.

samskiter · 8 months ago

Still very broken @pakrym-oai this must be costing you a fortune?

OptiWhisperer · 8 months ago

This was also reported in the forums almost 3 months ago: https://community.openai.com/t/how-to-properly-utilize-codex-vm-cache/1354885

So I'm guessing that this isn't a priority for OAI.

samskiter · 7 months ago

Codex cloud is currently unusable.

samskiter · 7 months ago

I believe this may be fixed. Anyone else having better results @OptiWhisperer ?

OptiWhisperer · 7 months ago

I see it only partially improved, @samskiter. I did this:

  1. Start task A: environment builds
  2. Followup prompt in task A: environment persists as expected
  3. Start task B: environment persists as expected
  4. Followup prompt in task B: environment got rebuilt again here

So this is still probably unusable for me. I've moved on to running multiple cli instances in an EC2 container.

etraut-openai contributor · 3 months ago

This bug report hasn't received any upvotes or follow-up posts in four months. I think it is likely fixed, so I'm closing. If you're still seeing a similar problem, please let us know.