songoao25/dsh-auto-compact ↗★ 3
dsh-auto-compact
Enhanced auto-compaction defaults for DeepSeek Harness agent presets
AI 分析
当估算的上下文占用达到设定比例时，自动触发历史会话压缩，并保留最新比例的对话。适合需要频繁进行长对话、防止超出模型上下文窗口限制的用户。
インストール
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:songoao25/dsh-auto-compactドキュメント
README 全文を読む ↗Configuration
All values live in scripts/inject.mjs (the CONFIG_BLOCK). Edit them before running ./install.sh if you want different thresholds. Preview with:
node scripts/inject.mjs --dry-run
| Key | Default | Meaning |
|---|---|---|
thresholdRatio | 0.75 | Trigger compaction when estimated usage reaches this fraction of the model context window |
retainRatio | 0.20 | Keep the most recent fraction of the window verbatim |
modelPolicies | – | Per provider/model overrides |