What version of Codex CLI is running?
codex-cli 0.114.0
What subscription do you have?
OpenAI Codex / ChatGPT Plus
Which model were you using?
gpt-5.4
What platform is your computer?
Linux 6.18.12-200.fc43.x86_64 x86_64 unknown
What terminal emulator and version are you using (if applicable)?
Bash terminal with proxy configuration
What issue are you seeing?
Stream disconnection errors during code review:
■ stream disconnected before completion: error sending request for url
(https://chatgpt.com/backend-api/codex/responses)
Conversation interrupted - tell the model what to do differently.
The code review process fails repeatedly and returns:
Review was interrupted. Please re-run /review and wait for it to complete.
What steps can reproduce the bug?
- Configure codex CLI with HTTP proxy
- Run
/review command on a project
- Wait for code review to process
- Stream disconnects before completion
What is the expected behavior?
Code review should complete successfully without stream disconnection errors, even when using a proxy.
Additional information
The issue appears to be related to proxy configuration causing stream timeouts or connection drops during long-running API requests. This may affect users behind corporate proxies or in regions requiring proxy access.
What version of Codex CLI is running?
codex-cli 0.114.0
What subscription do you have?
OpenAI Codex / ChatGPT Plus
Which model were you using?
gpt-5.4
What platform is your computer?
Linux 6.18.12-200.fc43.x86_64 x86_64 unknown
What terminal emulator and version are you using (if applicable)?
Bash terminal with proxy configuration
What issue are you seeing?
Stream disconnection errors during code review:
The code review process fails repeatedly and returns:
What steps can reproduce the bug?
/reviewcommand on a projectWhat is the expected behavior?
Code review should complete successfully without stream disconnection errors, even when using a proxy.
Additional information
The issue appears to be related to proxy configuration causing stream timeouts or connection drops during long-running API requests. This may affect users behind corporate proxies or in regions requiring proxy access.