compact error
Resolved 💬 9 comments Opened Apr 24, 2026 by JosephCooperHC Closed Jun 29, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor)
responded on this thread — see the highlighted reply below.
What version of the Codex App are you using (From “About Codex” dialog)?
26.422.21637 (2056)
What subscription do you have?
plus
What platform is your computer?
macos
What issue are you seeing?
compact error
Error running remote compact task: unexpected status 408 Request Timeout: {"detail":"Request body read timed out"}, url: https://chatgpt.com/backend-api/codex/responses/compact, cf-ray: 9f160e3d0e883231-SIN, request id: d2cc4ded-29a1-412d-9183-3d95b33f2f24
What steps can reproduce the bug?
Uploaded thread: 019d9707-441f-7002-a67e-7f95f097d26a
What is the expected behavior?
_No response_
Additional information
_No response_
9 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
0.125 is still the same, failing over and over again. For such a high-frequency, recurring issue, it has been reported for so long and has severely affected the user experience—basically making it impossible to carry out long-running tasks. Yet there still hasn’t been an urgent fix. This should be prioritized as one of the most critical issues to be fixed immediately.
@etraut-openai How's the fix going? This bug has been bothering me for a long time. Right now, I can only continue my work by reading the old session content in a new session prompt, which is terrible.And every failure consumes my token.
Also seeing this on Codex Desktop for macOS.
Thread ID:
019e0390-d329-74c3-b8ab-13a32d339c9bCodex App:
26.429.61741 (2429)Error:
This is still happening today (2026-05-07).
This bug has been bothering me for a long time. Could you please help me fix it as soon as possible?
still happening
+1
@tibo-openai Is anyone currently addressing this issue? It's been bothering me every time I use Codex for work.
Thanks for reporting this problem. Until recently, Codex used a separate endpoint and server-side logic for compaction. We recently switched to a more robust approach where the compaction logic is moved locally using the same endpoint as normal turns. This eliminates "remote compaction" errors and increases the stability and reliability of compaction operations. If you see further problems with compaction, please use
/feedbackand open a new bug report.