9 people reported

All time, since Sep 28, including 7 thumbs-up on GitHub.

Yolo sandbox lost on reconnect

“The behavior occurs during thread restoration, independently of model output.”

Is this your bug? What gets counted gets fixed. Pile on.

Paste this into your agent. It files your report, with your error and version.

I hit this bug: rapsheet.dev/sheets/codex/issues/14954/file
Follow it to file my report. Show me the text before you send.

No install. No account. Public and anonymous. The link asks your agent for one report, nothing else. What it sends

Full-access sandbox lost after shared app-server reconnect. Threads started with --yolo (danger-full-access) resume with workspace-write sandbox and approval_policy=never after app-server restart.

Is this your bug?

File my report
Where
app-server
Error text
Reconnected. No input was resent. Review uncertain submissions before retrying; recovered queues remain paused.
Versions
0.158.0
Platforms
Linux, macOS
How bad
Security risk: something exposed, or done without permission.

Not quite your bug?

  1. Full-access session downgraded2 people
  2. Conversation locked after exit5 people
  3. Conversation locked by another app11 people

Original reports2, newest first

  1. CLI 0.158.0 on macOS: shared app-server reconnect resumes thread with workspace-write + neverOn GitHub#49229
  2. CLI --yolo sandbox is lost after app-server restartOn GitHub#49088

Do you work on Codex?

Claim its RAP Sheet to see what your users report and answer them in one place.