Rate limiting: Copilot Models are silently changed leading to less reliable results #192797
Replies: 1 comment
-
|
💬 Your Product Feedback Has Been Submitted 🎉 Thank you for taking the time to share your insights with us! Your feedback is invaluable as we build a better GitHub experience for all our users. Here's what you can expect moving forward ⏩
Where to look to see what's shipping 👀
What you can do in the meantime 💻
As a member of the GitHub community, your participation is essential. While we can't promise that every suggestion will be implemented, we want to emphasize that your feedback is instrumental in guiding our decisions and priorities. Thank you once again for your contribution to making GitHub even better! We're grateful for your ongoing support and collaboration in shaping the future of our platform. ⭐ |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
🏷️ Discussion Type
Bug
💬 Feature/Topic Area
Copilot in GitHub
Body
I have been trying to work around the P1 Rate limiting Incident. I found that choosing different models would allow the AI to respond without being impacted by the rate limiting bug.
However, I noticed the results were strange and not at all of the quality I would expect. I then noticed the following in the logs:
[Conversations Warning] [CopilotClient] Failed to resolve Copilot model for response: 'gpt-5.4-2026-03-05'. Error: Microsoft.VisualStudio.Copilot.Diagnostics.Exceptions.CopilotApiException: The requested model is not supported.
at Microsoft.VisualStudio.Copilot.Diagnostics.DiagnosticExceptionHelper.ThrowCopilotApiException(String errorContent, HttpResponseMessage response) in D:\dbs\el\ddvsm\src\Copilot\src\Copilot.Core\Diagnostics\DiagnosticExceptionHelper.cs:line 224
at Microsoft.VisualStudio.Conversations.CopilotClient.CopilotAPIClient.GetModelAsync(String id, String userCopilotSku, CancellationToken cancellationToken) in D:\dbs\el\ddvsm\src\Copilot\src\CopilotClient\CopilotAPIClient.cs:line 1424
at Microsoft.VisualStudio.Conversations.CopilotClient.CopilotAPIClient.ResolveResponseModelAsync(String responseModelName, CopilotModel requestModel, CancellationToken cancellationToken) in D:\dbs\el\ddvsm\src\Copilot\src\CopilotClient\CopilotAPIClient.cs:line 281
What this means is that a much less capable model is automatically chosen for the job. The result is garbage and you are left scratching your head wondering why. (Yes, of course you are still being charged for the activity, but the wasted effort is far more expensive)
Beta Was this translation helpful? Give feedback.
All reactions