Threads freeze and errors for 2 days already Error running remote compact task: timeout waiting for child process to exit
Resolved 💬 5 comments Opened Apr 15, 2026 by seeb1337 Closed Jun 29, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor)
responded on this thread — see the highlighted reply below.
What version of Codex CLI is running?
0.120.0 && 0.121.0-alpha12
What subscription do you have?
Pro
Which model were you using?
gpt5-.4
What platform is your computer?
Linux 6.17.0-20-generic x86_64 x86_64
What terminal emulator and version are you using (if applicable)?
Ghostty & t3code
What issue are you seeing?
Once thread is about to compact for its first time it gets errored. Can't run /compact, /feedback its stuck with an errors.
<img width="1124" height="236" alt="Image" src="https://github.com/user-attachments/assets/9e71db9e-b4dd-4c09-94e9-d48c04f4fd23" />
What steps can reproduce the bug?
Fill the context up to where its about to compact
What is the expected behavior?
It is supposted to compact but its being stuck and frozen...
<img width="1360" height="305" alt="Image" src="https://github.com/user-attachments/assets/9c2bdc74-394e-4cbd-9070-c841201da065" />
Additional information
_No response_
5 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
Not even able to run /feedback
<img width="908" height="202" alt="Image" src="https://github.com/user-attachments/assets/3e6ba92e-db1b-4afa-8833-42fd4dfd6cfb" />
When changed model to 5.3 codex it compacted the conversation succesfully, back to 5.4 and it continues. It happens for me everytime it tries to compact the conversation.
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).
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.