context-compression 11

Cut token cost without cutting model intelligence — a DeepSeek Harness (dsh) bundle plugin: structure-aware compression + TOON-style lossless encoding first + reversible spill-to-disk + real-time dashboard.

In-process DeepSeek Harness context compression bundle

Context compression tool (context_compact): the agent writes the replacement checkpoint itself and hands it to the host compaction engine, which skips the LLM summarizer call; automatic compaction stays on the official engine.

Generic stateless dialogue compression that mimics human memory — forgetting-curve bounded context for LLM conversations, with a ready-to-use adapter module for DeepSeek Harness (DSH).

OpenRouter Provider List — 填写 OpenRouter 请求使用的提供商列表与量化位数限制，作为 provider.only / provider.order / provider.quantizations 注入；可选地把请求改经 billion-context 压缩代理。配置由插件自持（$DSH_HOME/openrouter-providers.json），不依赖 settings 命名空间注册，因此同时适配 DSH 0.1.5-rc.1 ~ 0.2.1-alpha.1。配

Deterministic, zero-LLM, byte-budget context compaction for DeepSeek Harness, with byte-exact recall of compacted history.

Adaptive Reversible Context (ARC) for DeepSeek Harness — provider-aware, cache-conscious context governance with reversible recovery.

Windowed, reversible context management for DeepSeek Harness; replaces Basic compaction.

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

Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.

Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.