You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
What version of the Codex App are you using (From “About Codex” dialog)?
26.515.10909
What subscription do you have?
Plus
What platform is your computer?
Microsoft Windows NT 10.0.26100.0 x64 (Windows 11 Pro)
What issue are you seeing?
So, after the latest update of Codex App it started asking me to configure agent Sandbox and the problem is: every time I click set up it succeeds... but after a few seconds it asls me to do it again and again and again.. I work on a local drive.
And than it asks you to do it again and again and again...
What is the expected behavior?
The Codex App always will tell you that it configured agent sandbox successfully but then it will ask you to click set it up again. And There it is... The infinite loop has started...
Additional information
Here are the additional logs that might help you solve this issue:
Hey! Noticed you are dealing with agent loops/token bleeding here.
I was facing the exact same issue with infinite reasoning loops burning API credits, so I built a lightweight algorithmic handbrake in Python to stop it.
It audits the execution and automatically freezes the agent if it hits the same error 3 times in a row. It might save you some headaches and API costs while you debug the core issue.
The issue was resolved only after deleting all Codex user-level residual files under %USERPROFILE%\.codex and then reinstalling Codex. This suggests the App may be stuck on corrupted/stale user-level sandbox/app state even though the sandbox setup binary reports success.
Suggested improvement
Please consider adding a UI action like “Reset local Codex state / Reset Agent Sandbox state” that safely clears stale sandbox/app state without requiring users to manually delete %USERPROFILE%\.codex and lose sessions/configuration.
The newer Windows reproduction makes this look less like a one-off installer failure and more like a missing failure-state contract around sandbox setup.
A useful diagnostic would be to persist one setup attempt record with:
sandbox version before/after
update stage reached
failure fingerprint
whether anything changed since the prior attempt
explicit retry_allowed and halt_reason
If the fingerprint and environment state are unchanged, Retry should stop re-running the same path and surface the captured record. That would also make reports from different Windows machines much easier to compare.
Activity
github-actions commentedon May 17, 2026
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
callejoab commentedon May 18, 2026
You can still run Codex via PowerShell and ask Codex to fix the problem form there.
callejoab commentedon May 18, 2026
Codex Desktop was stuck at "Set up Agent sandbox to continue" for all projects.
Root cause appears to be a version mismatch:
C:\Users\calle\AppData\Local\OpenAI\Codex\bin
The Windows sandbox itself worked from CLI:
codex sandbox windows cmd.exe /c "chcp 65001 > nul && dir /b"
After replacing the stale user-local bin files with the newer files from the installed Desktop package resources folder, Desktop was able to continue.
gedeon1972-svg commentedon Jun 3, 2026
Hey! Noticed you are dealing with agent loops/token bleeding here.
I was facing the exact same issue with infinite reasoning loops burning API credits, so I built a lightweight algorithmic handbrake in Python to stop it.
It audits the execution and automatically freezes the agent if it hits the same error 3 times in a row. It might save you some headaches and API costs while you debug the core issue.
You can drop it in your workflow: https://github.com/gedeon1972-svg/loop-guardian-skill
Hope it helps you save some tokens! Let me know if it works for your use cas
Keesan12 commentedon Jun 5, 2026
kllin8154-arch commentedon Jun 12, 2026
I’m reporting a reproduced Windows Codex App sandbox setup/update loop that appears closely related to this issue.
Summary
Codex App repeatedly shows the banner/error:
However, the Windows sandbox setup log indicates that the sandbox setup itself completed successfully.
Environment
v0.139.0D:\Java-p\developer-workbenchRelevant symptoms
%USERPROFILE%\.codex\.sandbox%USERPROFILE%\.codex\.sandbox-bin%USERPROFILE%\.codex\.tmp%USERPROFILE%\.codex\tmp.sandboxand.sandbox-bin, but.sandbox-binwas empty.code=3221225477Failed to create shell snapshot for powershell: Shell snapshot not supported yet for PowerShell%USERPROFILE%\.codexstate remained.Sandbox log excerpt
setup_marker.json
{ "version": 5, "offline_username": "CodexSandboxOffline", "online_username": "CodexSandboxOnline", "created_at": "2026-06-12T06:41:52.827710+00:00", "proxy_ports": [], "allow_local_binding": false, "read_roots": [], "write_roots": [] }Result / workaround
The issue was resolved only after deleting all Codex user-level residual files under
%USERPROFILE%\.codexand then reinstalling Codex. This suggests the App may be stuck on corrupted/stale user-level sandbox/app state even though the sandbox setup binary reports success.Suggested improvement
Please consider adding a UI action like “Reset local Codex state / Reset Agent Sandbox state” that safely clears stale sandbox/app state without requiring users to manually delete
%USERPROFILE%\.codexand lose sessions/configuration.Keesan12 commentedon Jul 16, 2026
The newer Windows reproduction makes this look less like a one-off installer failure and more like a missing failure-state contract around sandbox setup.
A useful diagnostic would be to persist one setup attempt record with:
retry_allowedandhalt_reasonIf the fingerprint and environment state are unchanged, Retry should stop re-running the same path and surface the captured record. That would also make reports from different Windows machines much easier to compare.