LLM-free lossless compression engine

Project overview

Instant, near-lossless context compaction for DeepSeek Harness — a drop-in replacement for @deepseek-ai/dsh-compaction-basic that replaces LLM summarization with the deterministic conversation-compiler principle of lllyasviel/VCC.

A region containing a user request, an assistant text + tool call, and its result compiles to:

Every tool call is ONE line: the key argument for whitelisted tools (toolArgTools), name-only for the rest ( jobkill (seq 9 -> result 10)), nothing at all for hideTools rows. Tool results never occupy entries — the -> result N pointer keeps them one recall(type:"result") away. Long user/assistant text is truncated to its budget with ...(truncated from seq N); every elision names the durable event that still holds the full content. Recall: the lossless read-back layer