Error running remote compact task

Resolved 💬 6 comments Opened Apr 25, 2026 by fanfanfan1997525 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?

codex-cli 0.125.0

What subscription do you have?

gpt-pro

Which model were you using?

gpt-5.5

What platform is your computer?

Microsoft Windows NT 10.0.26100.0 x64

What terminal emulator and version are you using (if applicable)?

Windows Terminal PowerShell

What issue are you seeing?

■ Error running remote compact task: stream disconnected before completion: error sending request for url
(https://chatgpt.com/backend-api/codex/responses/compact)
happens per 10 min. I must change model to gpt-5.3 to finish /compact, then switch to gpt-5.5 for continuing

What steps can reproduce the bug?

Perhaps the context length of GPT-5.5 is far shorter than that of GPT-5.3?

What is the expected behavior?

_No response_

Additional information

_No response_

View original on GitHub ↗

6 Comments

github-actions[bot] contributor · 2 months ago

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

#19538
#19441
#18450
#19486

Powered by Codex Action

presidenzo · 2 months ago

Also seeing this on Codex Desktop for macOS.

Thread ID: 019e0390-d329-74c3-b8ab-13a32d339c9b
Codex App: 26.429.61741 (2429)
Error:

Error running remote compact task: stream disconnected before completion: error sending request for url (https://chatgpt.com/backend-api/codex/responses/compact)

This is still happening today (2026-05-07).

yvette-carlisle · 2 months ago

Same here. 05/07

session id: 40b07eeb-6604-4cfd-bc05-1345b3ea27c6

---

I couldn't continue in the original chat, but the fork feature saved the day. I just forked it into a new chat and picked up where I left off.

yvette-carlisle · 2 months ago

Okay, I know. Turn off remote_compaction_v2

sher-l · 2 months ago

same situation‌ 20260509

etraut-openai contributor · 21 days ago

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 /feedback and open a new bug report.