HongMing-Huang/dsh-file-upload 预览 preview

HongMing-Huang/dsh-file-upload

DeepSeek Harness(dsh)文件消息插件:Claude风格的拖放/回形针上传、内容嗅探、通过微软MarkItDown将文档转换为Markdown(内置JS回退)、文本内联,以及供智能体使用的read_document工具。

Project Overview项目介绍

This is a native DSH plugin that adds file upload and document handling capabilities to the DeepSeek Harness web client. It is built exclusively for DSH and follows the DSH plugin packaging specification, with a valid bundle manifest included in the repository. To install the plugin, users run the official DSH CLI command dsh plugin --profile web add dsh-file-upload then restart the DSH web client, and the entire process takes less than a minute for most users. The plugin works out of the box with sensible default configurations, so no manual setup is required after installation.

Typical usage starts with either clicking the paperclip button in the message composer toolbar or dragging files and folders anywhere over the DSH window. Small text files under 8KB are inlined directly into the composer, while larger documents are added as color-coded attachment cards that display the file name and size. These attachments can be removed easily before sending the message, and users can also type @ in the composer to pick an existing uploaded file to insert as a reference. Agents use the built-in read_document tool to fetch file content converted to Markdown on demand, with support for paging through large documents via offset and limit parameters.

The plugin is released under the open-source MIT license, and all document parsing runs locally offline with no external network calls required for core conversion. It includes multiple security features such as loopback-only uploads, sanitized file names, session-isolated storage, sha256 content deduplication, bounded concurrency, and TTL-based cleanup of old uploads. All configuration options come with sensible defaults that work for most use cases, but users can optionally tune parameters like maximum file size, allowed file extensions, and cache size to match their specific workflow needs.

这是一款专为 DeepSeek Harness (DSH) 开发的原生文件上传插件,为 DSH 带来了 Claude/Codex 风格的文件上传能力。它支持多种上传方式,包括文件和文件夹拖拽上传、回形针选择器上传、粘贴附加,同时支持多文件上传。插件内置 MarkItDown 引擎,可将 20 余种格式的文档转换为 Markdown,支持 Codex 风格的 @相对路径引用,还能为纯文本模型自动生成图片描述。

插件遵循零配置理念,安装后即可直接使用,无需额外下载 Python 或其他后端依赖,所有默认配置都经过优化。用户可点击编辑器工具栏的回形针按钮上传文件,也可直接拖拽文件到窗口完成上传,小文件会直接内联到编辑器,大文档会以附件卡片形式展示。代理会通过内置的 read_document 工具按需读取文档内容,并支持分页读取。

插件遵循 MIT 许可开源,所有文档解析都在本地完成,无需额外网络调用,安全层面做了多重防护:仅支持环回上传、文件名消毒、会话隔离存储、内容去重、并发限制和过期清理。所有配置项都有合理默认值,用户也可自定义上传大小限制、文件允许列表、缓存大小等参数,安装可通过 DSH 官方 CLI 命令完成。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 note1 项提示
  • 24 stars - an early-stage project星标 24,属于早期项目
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-file-upload

把 HongMing-Huang/dsh-file-upload 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

dsh-file-upload

File-message plugin for DeepSeek Harness (dsh). Claude/Codex-style uploads — drag-and-drop (files and folders), paperclip picker, paste-to-attach, multi-file support; content sniffing; fully bundled document → Markdown conversion (MarkItDown engine, 20+ formats, image OCR); Codex-style @relative/path references; automatic image explanations for text-only models; and a read_document tool for agents.

npm CI license Awesome DSH Plugin

English | 中文

Zero-config, install-and-use. Every feature works out of the box with sensible defaults — no Python, no downloads, no picking backends. Image explanations auto-discover a vision endpoint (local Ollama → OpenAI-compatible key from the dsh credentials seam).

Features

  • Upload — composer paperclip button plus a global drag-and-drop overlay ("release to attach"), multi-file support.
  • Attachment cards — color-coded type badges (PDF red / DOC blue / XLS green / TXT gray / ZIP purple / JSON gold) with name and size; removable.
  • Codex-style file references — uploaded files appear in the message as @relative/path references (like OpenAI Codex), never as raw content dumped into the composer; the agent reads the file with read_document (converted to Markdown on demand).
  • Codex-style @ mentions — type @ in the composer to pick any uploaded file by its relative path; the reference inserts as a mention.
  • Document → Markdown, fully bundled — the MarkItDown engine ships inside the plugin (Microsoft MarkItDown TypeScript port, markitdown-node): PDF / DOCX / PPTX / XLSX / HTML / CSV / JSON / XML / RSS / Atom / ZIP / Jupyter / image OCR / audio transcription. No Python, no downloads, no setup.
  • Image explanation for text-only models — upload an image and the plugin automatically generates a description ("讲解图片") through a vision discovery chain, so the DeepSeek API (text-only) can reason about the image: explicit visionEndpoint → local Ollama with a VL model (e.g. DeepSeek-VL2, zero-config) → OpenAI-compatible endpoint with a dsh-credentials key. Multimodal routes / vision bridges keep the official read_image path.
  • read_document tool for agents — line-numbered paging (offset/limit), byte-budgeted LRU cache (invalidated on file change), size pre-checks, reads through ctx.fs (inherits sandbox and fs-observation policy).
  • Security — loopback-only uploads, sanitized file names, session-isolated storage (.dsh-uploads/<sessionId>), sha256 content dedup, bounded concurrency, TTL sweep.

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 →

← 上一个 Prev dsh-pack-plugin 下一个 Next dsh-advisor →