hardes11/dsh-squeeze-command ↗★ 0
dsh-squeeze-command
Manual budget-targeted context compression for DeepSeek Harness: the conversation model picks ranges, a cheap flash-tier route writes the checkpoint summaries.
AI 分析
核心用途是通过智能压缩历史对话来降低长文本的 Token 成本。适合长对话、重度上下文消耗场景，希望通过摘要技术节省 API 费用的用户。
インストール
検証済み bundle がないか、互換性チェックに失敗しています。先にリポジトリの説明を読んでください。 README 全文を読む ↗
ドキュメント
README 全文を読む ↗Configuration
| Field | Default | Meaning |
|---|---|---|
contextBudgetTokens | — (required for bare /squeeze) | target for bare invocation |
summarizerProvider | — (required) | provider key for the summary route |
summarizerModel | — (required) | model id for the summary route |
summarizerReasoningEffort | null | effort pin for summarizer calls; pin e.g. low only if the route's effort map declares it |
summarizerConcurrency | 5 | max parallel summarizer calls |
maxSpanInputTokens | 30000 | per-span summarizer input cap |
maxSummaryTokens | 2048 | per-summary output cap |
minSpanTokens | 200 | span floor worth a checkpoint |
maxSnapSteps | 5 | balanced-edge snap budget |
Invalid values (zero, negative, non-integer) fail at plugin load with a named-field error, not at squeeze time.
The summarizer route should be a cheap, fast model — a flash-tier model is the sweet spot: dense summarization is not reasoning-heavy work, and spans run in parallel. The plugin is provider-neutral; any route registered in your DSH settings works.