Context Reading Strategy Discussion - File Count Impact on Input Tokens

Support Help
1

Hi everyone,

I’d like to ask about how the number of files in Cursor’s workspace affects input token usage:

Specific questions:

  1. Does Cursor automatically determine which files to read, or does it always read all files in the directory? This matters because I’m wondering if I should create a smaller subdirectory specifically for Cursor usage.

  2. Are certain types of data files being read unnecessarily? For example, model checkpoints (.ckpt files) and other binary data files. It seems like I might need to set up proper data isolation.

Any insights on optimizing workspace organization to reduce token consumption would be greatly appreciated!

2

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.