dsh-compaction

Manifest valid

Compaction backend replacing LLM summarization with a deterministic semantic extractor (keeps code/paths/commands, drops chatter) plus 28.4x KV-compression accounting.

hasBundlePatch

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
`semantic`	true	语义压缩（保留高信息行）
`retainRatio`	0.2	压缩后保留比例
`physical`	true	物理压缩记账（bytes/token）
`bytesPerToken`	7776	INT4 压缩后每 token 字节
`auto`	true	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

Comments

Loading…

Similar plugins

dsh-compaction-codex

by r-ayin

Codex-style window-swap compaction engine: deterministic pointer-template summaries with zero LLM calls, replacing the default LLM-summary compaction.

Manifest valid

★ 0

MIT

TypeScript

Oct 15, 2026

dsh plugin --profile web add dsh-compaction-codex

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph evict

Memory & ContextManifest valid

★ 15

↓ 1.1k/wk

MIT

TypeScript

Oct 26, 2026

dsh plugin --profile web add dsh-argp

dsh-dcp

by fan56

dsh plugin: deterministic context compression backend — zero LLM calls, reproducible compression

Memory & ContextManifest valid

★ 13

↓ 708/wk

MIT

JavaScript

Oct 18, 2026

dsh plugin --profile web add @aiwayds/dsh-dcp

dsh-quilt-compact

by bvbhu

Compaction-chain backend for the DeepSeek Harness: tiered model-pool summarization with per-model cooldown, overlapping chunking, and session-model fallback.

Terminal & ClientsSessions & MessagesManifest valid

★ 0

MIT

JavaScript

Oct 2, 2026

dsh plugin --profile web add dsh-quilt-compact

dsh-aux-degrade

Stops compaction summaries and session titles from burning their output budget on reasoning, by lowering the thinking level and raising the token floor for auxiliary calls only.

Models & ProvidersManifest valid

★ 0

dsh plugin --profile web add dsh-aux-degrade

dsh-plugin-thread

by zhaoyuntao-wl

Decision-and-goal memory with lineage: explicit commands and a model tool record decisions deterministically, a status card re-anchors them across compaction, a lossless event stream with BM25+jieba r

Development & InfrastructureMemory & ContextManifest valid

★ 2

↓ 208/wk

MIT

TypeScript

Oct 19, 2026

dsh plugin --profile web add dsh-thread