Automatic Compact Recurring Error

Resolved 💬 5 comments Opened Apr 24, 2026 by diginfobiz 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?

Pro 200$

What platform is your computer?

MacOS

What issue are you seeing?

When the conversation try to automatically compact the context, it shows an error and it blocks the work. It says: Error running remote compact task: stream disconnected before completion: error sending request for url (https://chatgpt.com/backend-api/codex/responses/compact)

What steps can reproduce the bug?

The automatic compact of each conversation always stop and shows this error: Error running remote compact task: stream disconnected before completion: error sending request for url (https://chatgpt.com/backend-api/codex/responses/compact)

What is the expected behavior?

To properly compact and work.

Additional information

019db22a-b11f-7f51-a0e8-219c2eb5f3db

View original on GitHub ↗

5 Comments

github-actions[bot] contributor · 4 months ago

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

  • #18450
  • #19255
  • #18838

Powered by Codex Action

uujx · 4 months ago

same!

MikeK184 · 4 months ago

same here, happens for some reason when it tries to compact around 5% left

presidenzo · 3 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).

etraut-openai contributor · 1 month 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.