Asking it to do it on the whole thing, then parsing the output and checking that the AST still matches?
1. It asks the LLM to write a description of what the variable does
2. It asks for a good variable name based on the description from 1.
3. It uses a custom Babel plugin to do a scope-aware rename
This way the LLM only decides the name, but the actual renaming is done with traditional and reliable tools.
Based on it, I went and read the readme. The readme was also excellent, and answered every question I had. Great job, thank you, I'll be trying this.