dsh-headroom
Automatic context compression for DeepSeek Harness: compresses tool outputs before they reach the model and keeps every lossy compression reversible via CCR retrieval tools.
面向 DeepSeek Harness 的自动上下文压缩插件：在工具输出进入模型前压缩，并通过 CCR 检索工具保持所有有损压缩可逆。
How to install
dsh plugin add github:giter00/dsh-headroom About
dsh-headroom 适配 **DeepSeek Harness (dsh)** 的上下文自动压缩插件，思路参考 Headroom。 工具输出在进入模型之前先被压缩：JSON、搜索、日志、表格与长文本各自走专用压缩器； 所有**有损压缩**都会把原文存入本地 CCR store，并在压缩结果里注入一个短 marker， 模型需要精确原文时调用 headroom_retrieve(id=…) 即可逐字节取回。 text tool body settles │ ▼ tools/post-execute ← dsh-headroom 在此压缩 │ ▼ tool/result 进入 session log / 模型历史（压缩后内容 + CCR marker） │ ▼ 模型需要原文时调用 headroom_retrieve(id=…) 特性 **自动压缩工具输出**：挂载 tools/post-execute，在工具结果物化之前替换文本内容。 **内容路由，专用压缩器**： | 内容类型 | 压缩策略 | |----------|----------| | JSON 数组/对象 | SmartCrusher 风格透视：_keys + _rows + _common，长单元格截断 | | grep/ripgrep 结果 | 按文件折叠：file (N matches) + line[:co…
Recommendation signals
Meta
- License
- Apache-2.0
- Language
- JavaScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-08-18
- Created
- 2026-08-16
Links
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
- deepseek-harness-plugin, dsh-plugin, dsh-plugins
Related plugins
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.
hivemind
activeloopai/hivemind
Hivemind turns your traces into reusable skills across agents
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.
mcp-notion-server
suekou/mcp-notion-server
A Model Context Protocol server for connecting Notion to MCP-compatible clients