89 results
Web compatibility layer for the DeepSeek Harness UI: polyfills crypto.randomUUID on non-secure contexts (plain-http LAN access) so the official conversation UI no longer crashes when attaching images, and surfaces the context status in Settings
Let DeepSeek-V4-Pro (text-only) use V4-Flash-Vision-Exp for attached images. Mac/Windows/Linux.
DSH-native vision bridge for text-only models with native image attachments, multi-image evidence batching, and session-scoped validated Evidence caching.
DeepSeek Harness plugin that turns silent tool failures into loud ones: a tools/post-execute policy that matches warning signatures in successful tool output and blocks the result or attaches a notice
WeChat-style screenshot for the DeepSeek Harness composer: capture the screen (optionally hiding the DSH window), select a region, and attach the cropped image to the message as a file-card.
DragView：为 DeepSeek Harness 提供拖拽文件、Codex 风格附件卡片、安全文件预览与系统打开能力
Image routing for text-only models in DeepSeek Harness: a global analyze_image tool (Kimi vision) plus automatic rewriting of pasted images into attachment references when the active model cannot see images.
文件附件：拖拽/粘贴/上传文件（支持多文件）；图片与文档统一落盘到 .dsh-file-attachment 并以 @绝对路径 引用发送（文本模型可正常使用）；输入框内联显示图片缩略图预览与文件条目，聊天区图片同样渲染为可点击放大的缩略图、文件保持芯片样式；非多模态模型下图片自动调用可配置 VLM 识别生成中文描述回填草稿；文档/代码/配置文件可上传类型可在设置页配置；支持 PC 与移动端浏览器
Attach local files to the conversation context: a composer chip adds files whose content is injected into the model context (agent/pre-step), with a removable ✕ chips strip above the input.
Drag and paste files into dsh Web with a unified preview rail; keep native images and add file references only when sending.
DSH vision bridge (DSH >= 0.1.2-rc.1): when the selected chat model is text-only, attached images are described by a local Ollama VL model (qwen3-vl:8b) with keep_alive VRAM cooling. Install-time patch of dsh-api-session-controller prompt admission + runtime status companion.
Paste or drag non-image files (xlsx/csv/pdf/zip…) into the DSH web composer: files are saved into the session workspace and an @reference is inserted.
Screenshot/file paste board for the DSH Web GUI: paste, drag or browse to save files locally, show reference chips above the input, and auto-append file paths when sending a message.
DSH 文件收发桥：📎 附件按钮上传（图片原生预览条/文件链接）+ send_files 工具下发 + /dsh-files 静态服务 + 反引号路径一键调起侧边栏 explorer。
Inline previews for the images an agent already produced in DeepSeek Harness: read_image attachments and local paths in any format (HEIC/TIFF/PSD/SVG/BMP/ICO/TGA/PNM/JP2 …), rendered through the official gallery and lightbox.
DeepSeek Harness plugin: drag unsupported files into the composer as workspace path references
⭐ 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。
Two-way Codex↔DSH bridge: skills from ~/.codex/skills, session import with workspace attach, live MCP mirroring of mcp_servers, and a Codex-side reverse MCP installer.
dsh web plugin: native Windows file picker with attachment rail that injects file paths into the session context at send time
dsh-plugin for DeepSeek Harness (DSH) web UI: drop or paste any local file/folder anywhere on the page as attachments (images, any files, whole folders) or locate real filesystem paths — one toggle, two modes.
附件自动降级：DSH 图片准入（单边 ≤2000px / ≤3.5MB / ≤4000万像素）超限图片不再拒绝，用 sharp 自动缩小/重编码后入库，用户上传手机原图不再踩线。
DSH 图片插件，三个工具覆盖三种场景：ask_user_choice 图片/图文混合选择卡（Web GUI 渲染，可放大查看）+ show_images 回复内嵌图片（图文混排）+ save_received_images 盲模型收图存为工作区文件；聊天栏所有图片点击放大，支持滚轮缩放与拖拽平移。来源支持本地路径 / http(s) URL / base64 data URI。零 token 本地渲染，纯插件实现不改核心包。
Composer add-assets plate for the DeepSeek Harness Web Client: an options menu on the composer's + button (files, folders, slash commands) and a Claude Code-style draft attachment preview
DSH profile plugin: converts read_image PNG/WebP attachments to opaque sRGB JPEG so LM Studio's openai-completions endpoint accepts them