The context cannot be automatically compressed and an error is prompted: Error running remote compact task: stream disconnected before completion: error sending request for url (https://chatgpt.com/backend-api/codex/responses/compact)

Resolved 💬 3 comments Opened Jun 3, 2026 by yixuanoba 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)?

new

What subscription do you have?

pro

What platform is your computer?

_No response_

What issue are you seeing?

The context cannot be automatically compressed and an error is prompted: 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 context cannot be automatically compressed and an error is prompted: 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?

_No response_

Additional information

_No response_

View original on GitHub ↗

3 Comments

github-actions[bot] contributor · 2 months ago

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

  • #25678
  • #25493
  • #24920

Powered by Codex Action

ybsun0215 · 2 months ago

Why does this issue persist? Hasn't anyone noticed it? Even in version 138, Compact is still broken.

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.