dsh-active-context-pruning

DeepSeek Harness Memory Low risk

Model-authored context pruning for DeepSeek Harness through the official compaction API.

面向 DeepSeek Harness 的模型驱动上下文裁剪插件，通过官方 compaction API 释放上下文空间。

How to install

DeepSeek Harness dsh plugin add github:aerince/dsh-active-context-pruning

About

dsh-active-context-pruning 让 DeepSeek Harness 的模型自己决定哪些历史值得压缩、自己写检查点摘要，再通过官方 ctx.compaction.compactRegion 从下一次请求的表层中隐藏这段历史。这不是官方 @deepseek-ai/dsh-acp；后者指 Agent Client Protocol。本插件只复用 DSH 已有的 compaction 事务，不修改原始 session.events。功能 | 工具 | 作用 | |---|---| | acp_status | 用量、表层 seq 表、检查点 | | acp_compress | 用模型提供的 summary 替换一个表层 seq 范围 | | acp_decompress | 读取被隐藏的原文；不撤销表层替换 | | acp_search | 搜表层和已压缩原文 | /acp 是给人看的状态命令。工具使用 DSH 的表层 seq，不是 OpenCode 的 m00001。官方 dsh-compaction-basic 自动压缩仍可作为兜底。若只想让模型主动压缩，可在 profile 中将其 auto 设为 false。配置与限制解压不能撤销 replace。原文仍在 session.events，只作为工具结果返回。不能压最新 preserveRecen…

GitHub ↗

Recommendation signals

47 Tool quality · Based on stars, downloads, maintenance, security and docs

– User interest · Adjusted by in-site views, install copies and download clicks

47 Overall

0views

0install copies

0download clicks

0outbound clicks

Links

GitHub ↗ Report issue ↗

Basic safety check

Findings: curated 收录但无 npm 包/安装命令
Sources: curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics: cordis, deepseek-harness, dsh-plugin

Related plugins

DeepSeek Harness New

Score97

hindsight

vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents

Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.

☆ 20.0K ↓ 116.9K Memory ↗

MCP ServerClaude Code New

Score93

firecrawl-mcp-server

firecrawl/firecrawl-mcp-server

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

☆ 7.3K ↓ 522.5K Memory ↗

Claude CodeCodex New

Score80

hivemind

activeloopai/hivemind

Hivemind turns your traces into reusable skills across agents

☆ 1.6K ↓ 4.3K Memory ↗