The idea

Tamara demonstrates context compaction driven by Jev decisions. The accompanying fast-jev-compaction project keeps relevant tool calls and results, truncates or drops stale ones, and preserves retained conversation content verbatim.

Inside the decision loop

01 / CONTEXT

Conversation + paired tool results

02 / DECISION

Score which calls and results to keep

03 / ACTION

Rebuild a smaller conversation

What to take from it

Treat compaction as a selection problem when exact filenames, errors and commands matter. Keep recent context pinned and preserve the relationship between each tool call and its result.

KEEP IN MIND

The project documents a fallback when scoring fails or removes too little context. A relevance score does not guarantee that a discarded result will never be needed again. The repository also includes a scripted visual demo that does not call the API.

Follow the original work

This case is an editorial interpretation of a public community demonstration. It has not been reproduced or benchmarked by this publication.

Original post by @tamarajtran