DSH Plugin HubDSH 插件市场
linkingoscar/dsh-attachment-formats 预览 preview

linkingoscar/dsh-attachment-formats

Plugin插件 Native原生 ⭐ 4 Apache-2.0 Vision & Media视觉与多媒体Docs & Writing文档与写作

用于DeepSeek Harness Web GUI的Codex风格附件格式：PDF文本层提取、Office文本提取、扫描PDF的OCR、长文档溢出加索引卡片、图片转PNG。

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

This is a native Cordis plugin built exclusively for the DeepSeek Harness (DSH) web interface, designed to expand the number of supported attachment formats DSH can process. You can install it in one line with the command dsh plugin --profile web add github:linkingoscar/dsh-attachment-formats, or via the npm alias once it is published. It does not require any changes to DSH’s core packages, instead it reuses DSH’s native image draft rail, upload limits, history rendering, and model request pipeline. It supports extracting text from dozens of common file types including PDF, DOCX, XLSX, PPTX, EPUB, TIFF, and more. Scanned PDFs get OCR processing that only accepts results with a confidence score of 45 or higher.

When you drag or paste text-based attachments into the DSH composer, this plugin does not stuff the content directly into your input box. Instead, it creates an individually removable document card above the composer that shows the file name, character count, and content label. When you send your request, the plugin merges all card content into your message automatically, adding provenance markers for each attachment to keep track of sources. Any content longer than 80,000 characters is spilled into the session workspace as an index card, so no content is ever silently truncated before sending. This plugin is ideal for users that regularly work with long documents, scanned papers, or multiple office files.

This plugin is released under the open-source Apache 2.0 license, and all conversion results are content-addressed and cached for reuse across multiple sends. Conversion results are automatically cached for 7 days before being cleaned up, and cached results are invalidated only if you switch OCR or extraction engines. Legacy .doc, .xls, and .ppt files require LibreOffice headless to convert, while RTF files require pandoc available on your system PATH. Scanned PDF OCR supports both local tesseract.js and optional cloud backends including Baidu, DeepSeek Vision, Aliyun, Tencent, Azure, and Volcengine. Unconverted formats like iWork files, archives, and audio-video are passed directly to DSH’s native upload process.

这是一个专为DeepSeek Harness（DSH）网页版开发的原生插件，可通过一行命令dsh plugin --profile web add github:linkingoscar/dsh-attachment-formats完成安装。插件扩展了DSH编辑器支持的附件格式，无需修改DSH核心代码，复用原生的图片草稿栏、上传限制、历史渲染和模型请求流程。它支持PDF、各类Office文档、EPUB、TIFF等数十种常见格式的文本提取处理。

对于拖入或选择的文本类附件，插件不会将内容直接塞入输入框，而是在编辑器上方生成可单独删除的文档卡片，保留原输入提示干净。发送请求时，插件会自动将卡片内容合并到消息中，带来源标记，超过80k字符的长文档会自动存入会话工作区，生成索引卡片，不会出现内容静默截断的问题。这个插件适合需要处理大量文档、扫描件的科研人员、文案工作者日常使用。

插件采用Apache-2.0开源许可，扫描PDF默认使用tesseract.js做本地OCR，也支持调用百度、阿里、腾讯、DeepSeek等云厂商的OCR视觉大模型能力。旧版doc/xls/ppt需要LibreOffice headless支持，rtf需要pandoc，iWork和音视频归档文件不做转换，直接走原生上传流程。缓存默认存在DSH_HOME目录，7天自动清理，提取结果可跨会话复用。

View on GitHub在 GitHub 查看

Recommended强烈推荐 Send to your DSH发给你的 DSH 安装 
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-attachment-formats（linkingoscar/dsh-attachment-formats）
仓库：https://github.com/linkingoscar/dsh-attachment-formats
本站详情页：https://www.yhbd.top/plugins/linkingoscar-dsh-attachment-formats/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 Apache-2.0 · ⭐ 4 · 最近提交 2026-09-30 · 主语言 JavaScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 4 stars - very few users, little community feedback星标只有 4，几乎没人在用，遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装 

dsh plugin --profile web add dsh-attachment-formats

把 linkingoscar/dsh-attachment-formats 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

32.4 KB · 缓存于 2026-09-30 22:11:22 · 32.4 KB

dsh-attachment-formats — DeepSeek Harness Attachment Expansion (dsh-plugin, Codex-style)

license version harness dsh-plugin GitHub

English | 中文

DeepSeek Harness plugin (dsh-plugin) for the Web GUI — dsh plugin add one-liner. Makes the composer accept PDF, Office (docx/xlsx/pptx), TIFF, epub/odt/rtf, long-document text and scanned-PDF OCR, Codex-style. Keywords: dsh, deepseek-harness, cordis, pdf-extraction, tesseract, deepseek-vision, files-api.

A DeepSeek Harness web plugin (dsh-plugin, Cordis) that makes the composer accept many more attachment formats, Codex-style. Zero core-package changes: a pure plugin that reuses the harness-native image draft rail, upload limits, history rendering and model request pipeline.

# one-liner (GitHub)
dsh plugin --profile web add github:linkingoscar/dsh-attachment-formats
# alias (npm, when published)
dsh plugin --profile web add dsh-attachment-formats

dsh-attachment-formats — paperclip, document chips and index card (Playwright mock, dsh 0.1.1-rc.2)

Paperclip button · drag & drop / paste · official per-session injection · index-card never silently truncated — captured via Playwright against a local mock of the composer.

Supported formats

File Handling Destination
PNG / JPEG / WebP / GIF native pipeline (plugin not involved) image draft rail (native)
PDF (with text layer) text-layer extraction (≤40 pages via the pymupdf4llm high-fidelity engine; larger/unavailable falls back to pdfjs) full text on a document card (merged on send); over-limit → workspace spill + index card
PDF (scanned / no text layer) tesseract.js OCR (accepted only at confidence ≥45), falls back to page images OCR success → text channel; failure → image draft rail (vision models only)
Word (.docx) / Excel (.xlsx) / PPT (.pptx) text extraction — docx via mammoth HTML → turndown, tables kept as Markdown pipe tables document card (merged on send); over-limit → spill + index card
Legacy .doc / .xls / .ppt LibreOffice headless → docx/xlsx/pptx → standard Office pipeline (needs soffice; clear error when absent) document card (merged on send)
epub / odt / rtf pandoc → Markdown (probe on PATH); epub/odt fall back to jszip+turndown without pandoc; rtf requires pandoc document card (merged on send)
TIFF (.tiff/.tif) sharp (libvips) → PNG pages (multi-page, ≤20) native image draft rail
txt / md / json / code read in the browser (UTF-8, GB18030 fallback) document card (merged on send); over-limit → spill + index card
BMP / ICO / AVIF / SVG etc. browser decode → canvas → PNG native image draft rail
iWork / audio-video / archives no conversion; passed to native upload native file attachment (dsh 0.1.3+)

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 linkingoscar/dsh-attachment-formats 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev nomicore 下一个 Next dsh-team-rooms →