feat: (Draft) File summary for large files

[caseymcc]

I have been working with some large json files recently which don't fit the context window so I added the ability to split the file up in chunks and summarize it all into a single file with a caching system. Curious if this is something I should finish fleshing out and if so any direction you all might add.

Currently if the file is > 200K it is sent to the SummaryCache,

• chunks the file while trying to keep the splits between code/format blocks
• runs all the chunks through the llm (might get costly) and summarizes the chunks while trying to hold on to any hierarchical info
• combines the summarizes using the llm (recursively if they dont fit the tokens)
• stores the file time, content size and summary in the cache to be loaded if it exists or generated if it does not or the file has changed.