@crosery/dsh-drop
Drag and paste files into dsh Web with a unified preview rail; keep native images and add file references only when sending.
73 results
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.
DSH LLM adapter that transcribes native image attachments with Codex Luna before delegating to DeepSeek
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
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
On-demand vision for text-only LLMs in DeepSeek Harness: keep pasted/attached images in the backend, and let the model call view_image to look at them anytime via any OpenAI-compatible vision endpoint — as if the model were natively multimodal.
Extend the DeepSeek Harness (DSH) web chat drag-and-drop to accept every file type: dropping any file in the composer saves it into the current session's workspace so the agent can read and use it.
Let DeepSeek-V4-Pro (text-only) use V4-Flash-Vision-Exp for attached images. Mac/Windows/Linux.
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.
Mobile UI fixes for the DeepSeek Harness web profile: composer attachment upload, a restart row, input-modality switches, a narrow-screen drawer and settings tabs, a full-width model menu, a stuck-request network chip, and a throttled reaction to streaming message storms.
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。
⭐ 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 web plugin: native Windows file picker with attachment rail that injects file paths into the session context at send time
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.
家庭关怀技能 · 走出原生家庭 — 帮助用户觉察原生家庭模式、理解创伤来源、建立安全型关系习惯,在陪伴性对话中获得疗愈。包含 8 个疗愈角色档案,覆盖安全型关系模拟与内在小孩对话。适用于自愈、关系修复、自我觉察等场景。
DeepSeek Harness plugin: drag unsupported files into the composer as workspace path references
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-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.
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
Web UI plugin: send workspace images to the user as chat attachments (show_image tool + chat gallery node)
DSH profile plugin: converts read_image PNG/WebP attachments to opaque sRGB JPEG so LM Studio's openai-completions endpoint accepts them
DSH Web 输入框工具栏图片按钮:点击用系统文件选择器挑图片,不用拖拽。Toolbar button that opens the OS file picker to attach images to the DSH Web composer — no drag-and-drop needed.
Attach files and folders in the DSH composer: clipboard paste, native file/folder picker, @-mention path search; folders are converted to paged Markdown for the agent to read page by page
DeepSeek Harness Web GUI 输入框 📎 选图按钮:通过系统文件选择器添加参考图,绕开拖拽环境问题,复用官方附件管线(缩略图/上限校验/随消息上传)。Image-picker button for the conversation composer.