deepseekplugins

DeepSeek Harness plugin

dsh-compaction-meta

元压缩：模型自己决定何时、如何压缩自己的上下文——列 surface、选区间、以自写文本替换；替换走官方 compaction 事务（检查点、配对平衡、可重建）。Meta-compaction: the model directs its own context compaction through the official compaction seam.

Memory
Jump to install

Source facts

Repository
DViridescent/dsh-compaction-meta
Latest update
Aug 15, 2026
Category
Memory
GitHub stars
0
Format
plugin
Catalog evidence
Upstream dsh.bundle evidence
Evidence path
package.json#dsh.bundle
Checked against
0.1.0-rc.8
Upstream check date
2026-08-20

This evidence comes from the upstream catalog. This site has not installed, run, or security-reviewed the plugin.

Install

Start with a prompt that asks an agent to review the GitHub repository and source. Switch to the command if you want to install it yourself.

Copy this prompt into DSH, Codex, or another agent and ask it to review the GitHub repository and source first.

Do not install or run any commands yet. Read this plugin's GitHub repository, README, and relevant source code. Then answer the questions below clearly and directly so I can decide whether it fits my needs:

1. What is this plugin, and what problem does it solve?
2. Who is it for, and what are its typical use cases?
3. How is it used after installation? Include one minimal example.
4. What known limitations or privacy, security, compatibility, or maintenance risks does it have?
5. Give a clear recommendation: recommend, conditionally recommend, or do not recommend, with reasons.

Distinguish statements documented by the repository, inferences from source code, and unknowns. If evidence is insufficient, say so explicitly. Do not guess or simply repeat the README.

GitHub: https://github.com/DViridescent/dsh-compaction-meta
Plugin: dsh-compaction-meta
Author: DViridescent

Check the source files

Read the README and other files from this plugin directory before installing.

File explorer3 files
README.mdSource · read only

dsh-compaction-meta · 元压缩

> Meta-compaction for DeepSeek Harness：模型自己决定何时、如何压缩自己的上下文。

愿景

我们对未来模型的判断：

  • 上下文不会无限大，模型依旧在有限上下文里工作
  • 短期内做不到动态权重调整：今天告诉它的信息，不会自动变成永久的记忆
  • 模型会获得元认知，能够自我剖析

由这几点推出的方向：

  • 有了元认知，模型可以自己控制自己的上下文。今天大部分 harness（包括 DSH）的做法是越过阈值后被动压缩，模型无法干预
  • 未来的 harness 应该配合模型的元认知：让模型容易地编辑自己的上下文，容易地为自己添加和删除工具

DeepSeek 的下一步是长期学习，DSH 是面向开发者的基座。

这个插件做的是其中一块：把"编辑自己的上下文"变成模型可以直接调用的动作，替换掉阈值触发的被动压缩。

状态

🚧 骨架阶段——尚未实现。实现计划见 src/index.js 顶部注释。

计划中的能力

  • context_list：列出当前上下文（带编号、按 turn/调用折叠、前后缀、token 估算），模型据此定位自己记忆中的区间
  • context_compact：把指定区间替换为模型自写的文本；替换走官方 compaction 事务（检查点标记、工具调用配对平衡、日志可重建）
  • 关闭被动压缩：阈值不再触发，何时压缩由模型决定
  • 配套 skill：教模型何时、如何使用

与官方后端的关系

本包是 compaction seam 的第三个 Provider，与 compaction-basic（被动阈值裁剪）、 compaction-instant 并列，在 preset 的 isolate: { compaction: true } 组中替换 basic 使用。

安装

dsh plugin --profile <name> add dsh-compaction-meta
# 或从 GitHub 安装：
dsh plugin --profile <name> add "github:DViridescent/dsh-compaction-meta"
Back to searchOpen GitHub repository

More related plugins

View category