How does the GitHub Copilot app fetch models from the catalog of a given provider? Is there a way this API could provide the correct values for max prompt tokens, max output tokens and supported reasoning levels? I need to look at docs every time to find the correct values
- How does the GitHub Copilot app fetch models from the catalog of a given provider? Is there a way this API could provide the correct values for max prompt tokens, max output tokens and supported reasoning levels? I need to look at docs every time to find the correct values
@burkeholland this is a big usability issues when using custom BYOK providers. Since the catalog listing works and you can just add models that work, it's easy to forget that you're probably getting incorrect or suboptimal settings for input and output sizes and reasoning levels
