DeepSeek Harness attachment extension
linkingoscar/dsh-attachment-formats · skills
Codex-style attachment formats for the DeepSeek Harness Web GUI: PDF text-layer extraction, Office text extraction, scanned-PDF OCR, long-document spill + index cards, image-to-PNG.
★ 5GitHub stars
1Forks
2026-09-06Last updated
JavaScriptLanguage
Apache-2.0License
Key features
- each card has a send buttonsend documents even without typing anything
- doc.md — PDF text layer assembled per page (leading markers), Office-extracted text, long text as-is (long JSON is prettified to doc.json)
- PDF text engineauto (default) → the venv's pymupdf4llm for ≤40 pages (high-fidelity tables/headings)
- DOCX tablesmammoth HTML → turndown + GFM plugin — tables survive as Markdown pipe tables (replaces the old cell-by-cell reading order).
- pressing Enter / the native send button merges the cards first, then submits
Requirements
- OCR (tesseract.js) quality is limited on low-resolution scans and complex tables
- insufficient confidence falls back to page images with an explicit note — garbled text is never injected.
Install command
dsh plugin --profile web add github:linkingoscar/dsh-attachment-formats