概览
dsh-context-extract
源码级技术说明Context extraction and compression for DeepSeek Harness: one context_extract tool that turns long raw documents (financial reports, contracts, ledgers) into dense structured Markdown plus JSON — key metrics, tables, numbered clauses, entities and cross-check alerts — so a downstream pipeline spends far fewer tokens on the same facts.收起技术说明
Context extraction and compression for DeepSeek Harness: one context_extract tool that turns long raw documents (financial reports, contracts, ledgers) into dense structured Markdown plus JSON — key metrics, tables, numbered clauses, entities and cross-check alerts — so a downstream pipeline spends far fewer tokens on the same facts.
README / ZH
插件文档
目录摘要
Context extraction and compression for DeepSeek Harness: one context_extract tool that turns long raw documents (financial reports, contracts, ledgers) into dense structured Markdown plus JSON — key metrics, tables, numbered clauses, entities and cross-check alerts — so a downstream pipeline spends far fewer tokens on the same facts.
dsh.pub 核对固定版本的组合包契约、运行时事实与分发语义；完整 README 请查看源仓库。
在 GitHub 阅读完整 READMELIMITATIONS
已知限制
- 关键指标依赖中文行标签（资产总计、负债合计、货币资金……）；非中文模板退化为台账/文本。 - 公式单元格若没有缓存值，按空处理（报告里会标注；需要精确值先用 LibreOffice 重算）。 - 条款切分是结构性切分，不生成语义摘要——「条款号 + 核心义务/权利」的一句话说由 agent 按系统提示完成。 - PDF 不支持，需先转换。