Sometimes if you use a custom model you'll get this error:

Access to fetch at 'https://myCustomLLM.com' from origin 'vscode-file://vscode-app' has been blocked by CORS policy: 
    Response to preflight request doesn't pass access control check: 
    No 'Access-Control-Allow-Origin' header is present on the requested resource. 

The only reason this error happens is because our origin header is being set to vscode-file://vscode-app inside of VSCode, which I guess conflicts with many servers' https://* CORS rule. I think we can solve this problem by simply deleting our Origin header every time we call sendLLMMessage.

My asks for Void contributors:

• Confirm that deleting the Origin header will work
• Find a way to delete the Origin header only when we call sendLLMMessage
  • make a new service for it?
  • some other electron-app hack?