attach-plus
DSH web-ui plugin: '/' glyph on the composer command-menu button plus a '+' attach button with separated image/document/other uploads.
303 results
DSH web-ui plugin: '/' glyph on the composer command-menu button plus a '+' attach button with separated image/document/other uploads.
DeepSeek Harness web plugin — upload files and folders straight into the conversation (no workspace copy needed): images attach as real image blocks, text content is written into the composer, folders land under ~/.dsh/uploads by directory structure
Skill picker for the DeepSeek Harness web UI (dsh web): choose a skill from the composer tool row like the model selector, inserting the /skill reference into the draft.
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.
Selection toolbar for the DSH web UI: quote (expandable markers in the composer), temp chat (in-page context-free panel), web ask (chat.deepseek.com popup with ?q= prefill)
Save and switch model and reasoning-effort presets in the DeepSeek Harness composer.
dsh auto-vision bridge: paste an image into a text-only model's composer and a configured multimodal model transcribes it as text, automatically.
DSH web plugin: speak into the composer — macOS native speech-to-text (Apple Speech framework) via a bundled Swift helper
Add an upload-image button beside the composer plus button. Picks local images and feeds them through the conversation draft-image drop path (DataTransfer + synthetic drop event), so describe-image rewrites the send into an image reference.
SenseVoiceSmall-powered local speech-to-text for the DSH Desktop input box: click the mic beside the composer, speak, and the recognized draft (with language/emotion tags) is written into the input.
Voice (speech-to-text) input for the DSH Web composer via the browser Web Speech API — tap the mic, speak, the transcript fills the input box. Zero server, zero API keys, nothing leaves the machine. · DSH Web 语音输入:点麦克风说话,识别文字回填输入框(Chrome/Edge,无需 API key)。
Add selected DSH assistant text to the composer as a structured reference.
Model and reasoning-effort switcher: composer seat with an Off/Max effort slider over session.models / session.selectModel
DeepSeek Harness 插件:Host 半区向系统提示词注入规则,要求 LLM 把需要用户决策的内容用 <!-- dsh-todo:start -->…<!-- dsh-todo:end --> 成对标记包裹(渲染不可见);Client 半区仅对标记块在输入框上方显示带复选框的表格增强 UI,支持单行/整体编辑与「直接发送」「填入对话框」「关闭」,任意操作完成后关闭。
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.
粘贴「路径:行号 + 代码」到 DSH 输入框时自动折叠为紧凑引用,发送时把代码快照以独立上下文消息内联给模型。
Voice input plugin for DeepSeek Harness web: a mic button in the composer that recognizes speech (Web Speech API) and fills the draft, with optional auto-send.
DeepSeek Harness (DSH) web plugin: read PDF / Word .docx / PPT .pptx / plain-text & code files straight into the composer via upload or drag-and-drop
Arrow-key input history for the DeepSeek Harness Web GUI: press Up/Down in the chat composer to recall previously sent messages, with a floating history dropdown.
Vision recognition plugin for DeepSeek Harness: paste images into the composer, recognize them via GLM-4V on the host side, and inject the result into the conversation.
Local JSON / URL / Base64 / timestamp / UUID toolbox in the dsh web composer
DSH profile bundle: @-mention files and directories of the current session's workspace in the composer — prioritized fuzzy search, arrow-key/Tab completion, plain-text mentions that can be copied or edited, per-workspace indexing with LRU cache, and durable settings.
DeepSeek Harness Web overlay: hide chrome, dock the composer, filter transcript kinds, and drive sidebar/details occupancy
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.