플러그인

DeepSeek Harness용 LLM 없이 동작하는 무손실* 압축 엔진입니다.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

Deterministic context compaction: prunes conversation atoms in reference-graph topological order with no LLM calls during compaction, and keeps pruned atoms recallable by marker.

Pure-incremental directive-driven compaction for DeepSeek Harness: /compact-directive <requirement> summarizes the session middle per your requirement, /trim-directive <requirement> trims the whole conversation per your requirement