Plugins

Cherry Studio-style paste: multi-line/indented/fenced text or code pasted into the DSH Web composer collapses into a bordered, collapsible, language-tagged card and is restored as a fenced code block on send.

Native-feel DSH attachments: official PNG/JPEG/WebP/GIF thumbs plus 64px cards for other files via drag, paste, or paperclip; non-images land in .dsh-uploads and sent cards sit on the user bubble.

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

Advertise image paste on text-only DeepSeek routes, describe attachments with a vision sidecar, and leave native vision models untouched.

Full vision-capability bundle for DeepSeek Harness: a vision_understand tool (OpenAI-compatible vision APIs, free Zhipu GLM-4V-Flash by default) plus paste/drag-and-drop/button entry points for image recognition.

Auto-saves large pasted text as an attachment file in the DeepSeek Harness web input box; with dsh-better-sidebar installed, the paste pill opens the file in the sidebar editor and saves it back.

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

Sticky-notes board for DeepSeek Harness: a sidebar entry opens a Markdown note panel with auto-save, colors, image paste and task-list rendering.

AI 输入框粘贴大段文本自动缩略为 [Paste #N +M lines] 小序号标签(编号不可改);👁 点击预览全文(点外关闭)、✎ 编辑名称、↺ 恢复纯原文;无删除按钮,删输入框标签文本即消失;发送时自动展开原文并加固定方括号纯标识块分隔(编号与输入框一致);slash 命令参数展开不加装饰;代理可用 myds_read_captured 工具按编号读取标签对应文本。

Paste non-image files or folders into the chat composer as native @path references, or drag them in as absolute paths, instead of the images-only error.

TikTok-style video feed in a floating sidebar window: swipe local or SMB-NAS folders, or paste online video URLs (yt-dlp, bilibili/YouTube, cookies.txt login state); the window auto-fits the video aspect ratio, with fullscreen, drag-resize, Range streaming and an agent video-queue endpoint.

Native image attachments for text-only DeepSeek in the Web GUI: pasted or dropped images appear as thumbnails in the session, and before dispatch the host reads them with the free Zhipu GLM-4V-Flash vision API (glm-4v-flash fallback chain) and substitutes the description, so DeepSeek answers about the image while the original is kept in history.

Session-scoped @file/@folder mentions in the composer with Git-aware indexing, drag-drop and paste managed uploads, and validated path markers.

Turn raw data (CSV / pasted table / SQL results / DuckDB) into a structured Markdown report with business conclusions, metrics and charts.

Registers a `deepseek-vision` provider route: the Web GUI accepts pasted images and transcribes them to text via the free Zhipu GLM vision API before delegating to the DeepSeek adapter.

Drag or paste files into the Web composer with one image-and-file preview rail; native PNG/JPEG/WebP/GIF keep the image attachment path, while other files reuse a matching local path or stream to Host staging and become @ references only at send time. Includes browser media/PDF and bounded text previews; Office and archives show identity cards, and unsent file entries are page-local.

MCP marketplace and management panel in the Web sidebar: one-click official templates (Apifox public/private, Apipost, MasterGo, Pixso), paste raw mcpServers JSON, and enable, edit or delete your services with hot reload.

Attach tables and documents (xlsx, csv, pdf, zip…) to the DSH composer via paste or drag-and-drop: files are saved into the session workspace and an @reference is inserted.

Drag-and-drop / paste / upload files and images; on non-multimodal models images are auto-described by a configured VLM.

Like Codex/Claude Code: drag any file or folder (no format limit) onto the DSH web page and its real absolute path is inserted into the composer instantly — no typing paths by hand. Workspace-first smart lookup, size checks, same-name picker, batch and clipboard paste support, Windows/macOS.

Composer code-quote collapse for the DSH Web UI: pasting a `path:line` header followed by code folds the input into one compact inline quote token (Ctrl+Z reverses it), and at send time the `agent/pre-step` hook injects the full pasted snapshot to the model as a separate context message.

Listen to Xiaoyuzhou (小宇宙) podcasts in the DSH web UI: paste a share link to play anonymously (host proxies the audio with Range/seek), or log in via QR code to sync subscriptions, keyword-search shows/episodes, page full episode lists, and unlock purchased paywalled episodes; a `podcast_play` tool lets the agent play by link, podcast pid, or episode eid.

Inline image previews in chat for pasted images bridged by dsh-tool-vision on text-only models (click to zoom, old messages get previews too).

A drag-and-drop file plugin for DeepSeek Harness to easily attach files and paste paths into the chat.