Question

A developer on a GitHub Copilot Business plan has the 'suggestions matching public code' policy set to block. While typing, they notice that some suggestions appear instantly while others seem to take slightly longer or never appear at all. A teammate asks where in the code-suggestion lifecycle the public-code matching check actually happens. Which statement most accurately describes this behavior?

Accepted Answer

The GitHub Copilot proxy applies the public-code matching filter as a post-processing step on the model output before returning suggestions to the client.

Answer

The IDE client compares each suggestion against a locally cached index of public repositories before displaying it.

Answer

The large language model itself is fine-tuned to never generate code that matches public repositories, so no filtering is needed.

Answer

The matching check runs asynchronously after a suggestion is accepted and rewrites the accepted code if a match is found.