Repeated stream disconnection
Resolved 💬 7 comments Opened Jan 24, 2026 by peter-olom Closed Jan 24, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor)
responded on this thread — see the highlighted reply below.
What version of Codex is running?
codex-cli 0.89.0
What subscription do you have?
Plus (exceeded my limit so using credits right now)
Which model were you using?
gpt-5.2-codex
What platform is your computer?
Darwin 25.2.0 arm64 arm
What terminal emulator and version are you using (if applicable)?
Ghostty
What issue are you seeing?
Repeated stream disconnected before completion: error sending request for url (https://chatgpt.com/backend-api/codex/responses), codex is unusable right now for me.
What steps can reproduce the bug?
Uploaded thread: 019bf1c5-02b6-7bf2-918c-985e2bdb8fb3
What is the expected behavior?
_No response_
Additional information
_No response_
7 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
Thanks for the bug report. I've looked at your logs, and this looks like a normal connectivity issue. Codex isn't able to access the server endpoint.
Double check your network connectivity and network configuration — especially if you're using any proxies, VPNs, or firewalls.
Has this worked for you in the past on this machine and network? I don't think this is a client issue, but you could try downgrading to an older version of the CLI to confirm.
@etraut-openai I'm experiencing the same issue - sporadic over the last few days and then consistently starting last night. It's definitely not a change in home networking configuration.
Edit: to make my response more helpful :) - It's always the 1/5, 2/5, 3/5 ... every 23-25 seconds or so, until it times out entirely at about 2:35-2:40.
Point in favor of it being completely on my side: when I switch from my home wifi to my iphone hotspot, codex cli works again.
Point against: I've made zero changes to my home networking config and have been working with Pro from this networking setup for weeks now without experiencing the error behavior, and I'm seeing elevated reports from others about this exact thing. For me it started when I was on 0.87, and I tried upgrading to 0.89 which did not resolve the issue.
threadId: 019b5ddf-cdda-7f01-9440-d48507a63a91
I’ve been having the same problem for a few hours now using the VS Code extension.
After about twelve hours, it just started working again for me.
Thanks for the bug reports. We saw elevated errors in one of our clusters. We've rerouted traffic, so things should be back to normal now. We'll continue to monitor over the next few hours.
Also running into this issue tonight. Unable to use Codex.