Nice! This looks like it would pair really well with something like RLM[0] which requires "symbolic" representation of the prompt and output during recursion[1]

0. https://mack.work/blog/recursive-language-models

1. https://x.com/lateinteraction/status/2011250721681773013

This is a really interesting direction we have been exploring too! Our approach is basically to create a file containing the prompt for each turn within the virtual filesystem. The results seem promising so far