Instead of minimap/navigating symbols, you have AI "folding" where you abstract code into a map or code graph that has a dynamic zoom feature for granularity. This is useful for the user, but also as context for the assistant as a smart "codebase summary" (see how aider does a static version)
Possibly better than fold because you aren't folding on symbols but on other possibly more abstract/ useful things like functionality.
If applicable, add mockups / screenshots to help present your vision of the feature
Check for existing issues
Describe the feature
Instead of minimap/navigating symbols, you have AI "folding" where you abstract code into a map or code graph that has a dynamic zoom feature for granularity. This is useful for the user, but also as context for the assistant as a smart "codebase summary" (see how aider does a static version)
Possibly better than fold because you aren't folding on symbols but on other possibly more abstract/ useful things like functionality.
If applicable, add mockups / screenshots to help present your vision of the feature
No response