deepseek-harness-jev-pre-compaction

A pre-compaction advisor for DeepSeek Harness that runs before the standard compaction backend and uses TypeSafe's Jev to decide which low-value tool results can be safely pruned from the model's visible context, while the original session log stays intact and only the model-facing view is replaced with compact markers.

unverified — sourced from awesomejev.com; description independently written by AionEdge from the repo’s own GitHub metadata and README, not GitHub-API relevance-checked