Skip to main content

How to use billion-context-dsh

Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.

This article is auto-derived from indexed fields (wiki / faq / compatibility_json), not freshly AI-generated.

This article is derived from the plugin's already-indexed fields (wiki / faq / compatibility_json / readme), not freshly generated by AI. Source field is noted at the end of each section.

Quick start

Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.

— source: plugins.ai_summary

Install & verify

dsh plugin --profile web add billion-context-dsh

Run the command above in your DSH Web Profile. Then enable the plugin in the plugin list.

— source: plugins.install

Key points

  • 模型驱动 —— 摘要由模型自己书写，没有第二次 LLM 摘要调用
  • 只建议、不强令 —— 自动策略只 nudge（提醒），是否压缩、何时压缩由模型决定
  • 持久且可恢复 —— 压缩范围成为 checkpoint 节点，原文保留在 append-only 会话日志中；decompress 可恢复，search_context 可在块内查找
  • 长任务稳得住 —— 每一步都接着前面的成果走，关键结论持续可用、不断叠加，超长任务更容易跑完
  • 上下文始终精简 —— 每次请求都只用少量、精炼的上下文，只保留关键信息；不做大段统一压缩，细节不随之衰失，token 消耗自然更低

— source: plugin_wiki.readme_en (fallback readme_raw)

Compatibility

  • DSH: 0.1.0-rc.6+
  • Node: >=20

— source: plugin_wiki.compatibility_json

Pitfalls

Review the upstream repo before installing. This guide is auto-derived from indexed fields and may lag the latest release. If anything contradicts the official docs, treat the upstream source as authoritative.

— source: general rule