72 results
DeepSeek Harness plugin: a folder-picker button next to the native paperclip. Flattened files enter the host 0.1.3+ native attachment pipeline (official draft rail, background upload, progress, model handle line); plus the read_document tool (text/PDF/DOCX/XLSX) the built-in read tool rejects as binary.
DeepSeek brain + automatic image transcription for DeepSeek Harness: a deepseek-vision provider route that transcribes attached images to text before delegating to the text-only DeepSeek adapter. Official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), any OpenAI-compatible VLM or local Ollama as alternatives, never hangs.
Bring any file into the conversation — stashed to the workspace and referenced by path; zero type rejection
Drop or paste images, PDFs, office docs, zips, videos and audio into the DSH composer as workspace file paths instead of model attachments — lets a text-only model agent read them via vision tools.
⭐ 支持拖拽上传文件/文件夹到 DSH 窗口任意位置；支持远程上传，字节直传服务器会话工作区——部署在服务器上的 DSH 也能像本地一样拖了就发。
dsh plugin: recognize attached images with the built-in Windows OCR engine (Windows.Media.Ocr) and send only the recognized text to the model. Text models never receive image bytes; vision passthrough is opt-in.
Display images read by the read_image tool inside the DeepSeek Harness Web GUI: a dedicated Read image row with a default-expanded message-style image card (PS-style transparency checkerboard), merged read-N-images rows with side-by-side frames for multi-image requests, and an in-page full-resolution lightbox (zoom buttons, mouse wheel, 1:1 original size). 在 Web GUI 对话流中展示 read_image 读到的图片：默认展开的消息图片卡（透明棋盘格）+ 多图合并并排行（读取了 N 张图片）+ 页面内全精度放大层。
dsh plugin: recognize attached images with the built-in Windows OCR engine (Windows.Media.Ocr) and send only the recognized text to the model. Text models never receive image bytes; vision passthrough is opt-in.
A universal path-backed attachment dock for DeepSeek Harness.
Playwright-powered browser capability for DeepSeek Harness: accessibility-snapshot interaction with stable element refs, session-scoped browser sessions, screenshots as attachments.
dsh plugin: recognize attached images locally with Tesseract OCR and send only the recognized text to the model. Text models never receive image bytes; vision passthrough is opt-in.
DeepSeek Harness (dsh) web plugin — Codex-style attachment expansion: PDF text-layer (pymupdf4llm/pdfjs), Office (docx/xlsx/pptx) to Markdown, TIFF/epub/odt/rtf, long-document spill to index cards, scanned-PDF OCR (tesseract.js + 8 cloud providers inc. DeepSeek Vision), and browser image to PNG. dsh-plugin for the DeepSeek Harness Web GUI.
Drag-and-drop file and folder attachments for the DeepSeek Harness Web UI
Upload arbitrary local files from the DeepSeek Harness Web composer, attach them to prompts, and manage stored uploads in Settings.
chat.deepseek.com-style attachments for DeepSeek Harness: official upload icon, DS-style file cards (240x64, 16px radius), drag-drop, text extraction (PDF/DOCX/XLSX/TXT) injected into the message
让纯文本主模型（DeepSeek V4 等）也能接收图片附件：抹除纯文本路由的模态声明放行 0.1.1 准入门禁，图片投影为携带完整 attachmentId 的占位文本，由主模型委托视觉子代理经 read_image 读取。
Host-only Obsidian integration for DeepSeek Harness: 25 on-demand vault, knowledge, attachment, link, editor, and command tools with an authenticated local IPC companion.
Selection quoting for the dsh web GUI: a toolbar over selected assistant text that attaches the selection to the composer as a removable quote banner, prepended to the outgoing message at send
DSH ERNIE-Image-Turbo text-to-image plugin: generate images via Baidu AI Studio, save them as durable session attachments, plus a settings card and a generation gallery panel
Obsidian-style [[wikilink]] mentions for the DeepSeek Harness web GUI: type [[ in the composer to fuzzy-search note titles and attach their contents to the prompt
Let DSH text-only-model conversations accept dragged/pasted images: save them into the session workspace and insert the file path as text, bypassing the webui attachment channel that otherwise rejects image parts.
dsh bundle: attach any file type in dsh web — text-likes inline, binaries as workspace path references, rasters via the built-in pipeline
DeepSeek vision bridge for the dsh web GUI: route image attachments to a vision model (pi-ai / llama.cpp Qwen3-VL) and continue the conversation with the text description on a text-only LLM (DeepSeek)
DeepSeek Harness upload UX plugin: unified file import — drag & drop / paste / picker for ANY file type into the session workspace, with a Hermes-style attachment rail