bojansandhaus/jev-lcm-dsh-compaction ↗★ 0
@bojansandhaus/jev-lcm-dsh-compaction
提供基于Jev排序和SQLite的无损上下文压缩管理。 适合需要精细化控制长对话上下文、防止超出模型Token限制的任务。
安装
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bojansandhaus/jev-lcm-dsh-compaction说明文档
阅读完整 README ↗What configuration does the DSH bundle expose?
The bundle schema in src/index.ts currently exposes these DSH-level values:
| Setting | Default | Meaning |
|---|---|---|
databasePath | jev-lcm.sqlite | Local archive path. |
thresholdRatio | 0.8 | Host compaction trigger ratio. |
retainRatio | 0.16 | Host retention ratio. |
maxTokens | 8192 | Engine context budget. |
auto | true | Enable automatic engine behavior. |
jev | host-supplied value | Jev engine configuration passed to the implementation. |
The engine defaults in src/settings.ts include jev_provider: auto, TypeSafe base https://api.typesafe.ai/v1, OpenRouter base https://openrouter.ai/api, TypeSafe path /systemone, OpenRouter model ~typesafe/jev-latest, a 0.15 fallback threshold, a 0.40 threshold cap, a 0.10 minimum keep rate, a 500-sample calibration window, a 50-sample calibration minimum, a three-turn batch window, a 300-candidate batch cap, a 25,000-token state cap, and a 30,000-token request cap. See docs/reference.md for the complete table and validation rules.
Provider environment variables are:
export TYPESAFE_API_KEY='set-through-your-secret-manager'