[FEATURE]: Detect and notify when OpenAI routes to different models #9053

Open
opened 2026-02-16 18:11:31 -05:00 by yindo · 1 comment
Owner

Originally created by @fhdggervvtcusg on GitHub (Feb 11, 2026).

Originally assigned to: @thdxr on GitHub.

Feature hasn't been suggested before.

  • I have verified this feature I'm about to request hasn't been suggested before.

Describe the enhancement you want to request

OpenAI is silently routing requests from GPT-5.3-Codex to GPT-5.2 when their systems detect potential "cyber activities" (source). This affects legitimate users doing security research or development work.

Request:

OpenCode should detect when requests are routed to a different model and notify users with a clear warning. This could include:
Monitoring API responses for routing indicators
Displaying a warning message when detected
Providing a link to chatgpt.com/cyber for regaining access

Benefits:
Users understand why performance suddenly degrades
Reduces time debugging issues caused by silent model downgrades
Users can take action to regain proper access when misclassified

Context:
A recent incident affected ~9% of users. OpenAI plans to add notifications eventually, but detection at the OpenCode level provides immediate protection.

Originally created by @fhdggervvtcusg on GitHub (Feb 11, 2026). Originally assigned to: @thdxr on GitHub. ### Feature hasn't been suggested before. - [x] I have verified this feature I'm about to request hasn't been suggested before. ### Describe the enhancement you want to request OpenAI is silently routing requests from GPT-5.3-Codex to GPT-5.2 when their systems detect potential "cyber activities" ([source](https://github.com/openai/codex/issues/11189)). This affects legitimate users doing security research or development work. Request: OpenCode should detect when requests are routed to a different model and notify users with a clear warning. This could include: Monitoring API responses for routing indicators Displaying a warning message when detected Providing a link to chatgpt.com/cyber for regaining access Benefits: Users understand why performance suddenly degrades Reduces time debugging issues caused by silent model downgrades Users can take action to regain proper access when misclassified Context: A recent incident affected ~9% of users. OpenAI plans to add notifications eventually, but detection at the OpenCode level provides immediate protection.
yindo added the discussion label 2026-02-16 18:11:31 -05:00
Author
Owner

@github-actions[bot] commented on GitHub (Feb 11, 2026):

This issue might be related to existing work. Please check:

  • #7602: [FEATURE]: Native Model Fallback / Failover Support - while this addresses broader model fallback/routing concerns, it may be worth coordinating with this discussion about comprehensive model routing solutions.
@github-actions[bot] commented on GitHub (Feb 11, 2026): This issue might be related to existing work. Please check: - #7602: [FEATURE]: Native Model Fallback / Failover Support - while this addresses broader model fallback/routing concerns, it may be worth coordinating with this discussion about comprehensive model routing solutions.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#9053