DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Compaction — DSH Plugin for DeepSeek Harness
← Plugins
C

@agentframe/dsh-compaction

Compaction

AgentFrame compaction backend for DeepSeek Harness: semantic + physical KV compression (28.4x) replacing LLM summarization

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:ljsysfurryACE/dsh-compaction#cd360149d7ee4daa520b2ccb53e448de13c64cbf
READMECompatibilityVersions

Compatibility and provenance

Compaction is published as @agentframe/dsh-compaction and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
github
Registry updated
9/24/2026

Versions

0.1.0stable
9/24/2026

Related plugins

Loading related plugins…

Latest
0.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
any
License
GPL-3.0
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
9/24/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in

Related plugins

More verified plugins in memory-context.

Hindsight Coding Agents@vectorize-io/hindsight-coding-agentsReflect-only Hindsight long-term memory for coding agents (harness-pluggable: opencode, …), with automatic background ingestion (no setup CLI).Memory Plugin@openviking/dsh-memory-pluginOpenViking memory and context bundle for DeepSeek HarnessWeknora@wxg-prc-cpg/dsh-weknoraWeKnora knowledge retrieval tools for DeepSeek Harness (dsh): semantic search, document reading and RAG/agent answers over your own knowledge bases.Archive Manager@michengai/dsh-archive-managerNPM-installable DSH Web plugin for managing archived sessions.

README

dsh-compaction-agentframe

AgentFrame 压缩后端插件 —— 把 DeepSeek Harness 的默认 LLM 摘要压缩替换为 语义 + 物理双轨压缩（28.4x KV 压缩思路）。

为什么替换默认压缩

默认 compaction-basic 用 LLM 摘要（有损总结旧对话），每次压缩都要一次 LLM 调用，且摘要可能丢细节。

AgentFrame 的思路：

  • 语义轨：MemoryDirector 判断哪些 token 值得保留（去闲聊、留关键）
  • 物理轨：吸收式 MLA + INT4 量化（270KB→7.6KB/token，28.4x）
  • 效果：保留关键信息 + 大幅省 token + 不额外调用 LLM

使用

在 profile 的 cordis.patch.yml 中把 compaction-basic 替换为：

- id: compaction-agentframe
  name: '@deepseek-ai/dsh-compaction-agentframe'
  config:
    semantic: true
    retainRatio: 0.2
    physical: true

配置

字段默认说明
semantictrue语义压缩（保留高信息行）
retainRatio0.2压缩后保留比例
physicaltrue物理压缩记账（bytes/token）
bytesPerToken7776INT4 压缩后每 token 字节
autotrue自动压缩

实现

继承 CompactionEngine（compaction seam），实现三个抽象方法：

  • compactIfNeeded — 自动压力触发
  • compactNow — 手动 /compact 命令
  • compactRegion — 指定范围压缩

保持 dsh 的 surface/事件/持久化契约（compaction/start → replace → compaction/end）， 只替换"如何压缩"。

License

GPL-3.0 © Cloud LTE Studio / AgentFrame