Purchased Dedicated Server: CLIProxyAPI streaming interrupted prematurely

Resolved

?夏伟FREE5/6/2026

My service is CLIProxyAPI, which provides an OpenAI-compatible streaming API. When I use the codex terminal to call image2 for image generation, it throws an error during long-running tasks: stream disconnected before completion: An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID 2b09a05f-403c-4dfb-9e3b-bb18f47b55b1 in your message.

2 Replies

BCBohan ChenEMPLOYEE5/6/2026

Hello, I have fixed this for you.

Root Cause: The default HTTP ReadTimeout/WriteTimeout for the ingress-controller on your dedicated server is 10 minutes (600 seconds). Any request exceeding 10 minutes (including long streaming responses, such as image2 generation) is actively terminated by the ingress, which is why codex was seeing stream disconnected before completion. This is independent of the timeout settings in your backend service; it is being blocked at the ingress layer.

Fix Applied: I have updated the SERVER_TIMEOUT for your server's ingress to 24h, allowing long streaming requests to run for up to 24 hours without being terminated. Verification:

Using custom server timeout: 24h0m0s

You should now be able to run image2 generation requests without them being interrupted. Please try again and confirm.

AAnonymous5/10/2026

This post has been inactive for a while. We will be closing it in 2 days if there is no new activity.

This issue has been marked as resolved

New replies are disabled for resolved issues.

Forum

2 Replies