Plugins

Configurable image recognition for text-only DSH models: attached images are preserved through the DSH 0.1.7-rc.2 adapter pipeline, transcribed by an OpenAI-compatible vision model, and passed to the main model as text. Supports selectable OpenAI, Anthropic, Gemini or Azure auth headers and reports a missing API key before sending a request.

Vision bridge for text-only DeepSeek: send images (alone or mixed with text) and a fast tiny vision model describes them behind the scenes — the chat keeps the picture, DeepSeek sees only text. Pure plugin: uninstall restores everything.

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.

Full-screen lightbox for chat images: click any image to open the full-resolution original with zoom (wheel, buttons, shortcuts), drag panning, prev/next paging, filename caption and download, plus keyboard-arrow and touch-swipe navigation. One "image display control" popover next to the composer collapses every image in the conversation into a thumbnail grid whose column count (1-12) is configurable and remembered, or hides them entirely so the space closes up and restores them later; images are styled in place and no node is ever moved or reparented. The host-side display_image tool takes a local path or directory (TIFF/HEIC transcoded, originals still saved on download), a remote URL, or a keyword search over Bing, Huaban and Sogou that samples loadability before picking a source, re-saves images blocked by hotlink protection and drops dead links after a magic-byte check, returning paste-ready Markdown. It also keeps a system-prompt rule that every delivered image must appear in the reply body as  markdown, because collapsed tool rows are invisible to the reader.

Animated and video live wallpaper for the DeepSeek Harness Web GUI — GIF, animated WebP/APNG and static PNG/JPEG images, plus MP4/WebM video backgrounds, with auto format detection, a dim slider, and UI chrome tone matching.

DSH web plugin: replace the DeepSeek Harness branding (tab favicon, sidebar wide logo, collapsed rail icon) with your own images — upload two pictures from the sidebar panel, no manual resizing

Dockable Markdown preview for the DSH Web UI: side-by-side with the conversation, a per-session recently-read .md list, local relative-path images render in place, and clicking an in-chat .md reference previews it instead of launching the system editor; follows the shell light/dark theme.

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.

Routes images to a vision model of your choice - auto-rewrite, explicit tools, or hybrid - so a text-only chat model does not fail a turn that contains a picture.

Chat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local Ollama or cloud): pasted/dropped images become `view_image` path markers before reaching text-only DeepSeek models.

Vision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.

Vision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.

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.

OpenAI-compatible image generation in DSH Desktop chat: generate inline, edit reference images or chain-edit previous results directly (image-to-image) without re-uploading, with storage cleanup.

Composer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only DeepSeek models.

Read books and papers in DSH: a reading toolbar on the official PDF preview that remembers your page and zoom, plus PDF tools for the model (page map, full-text search, page text and images).

DSH text-to-image/image-to-image plugin: compatible with OpenAI-style image generation APIs, with 多米API as the default; standard OpenAI endpoints may require protocol, image-to-image mode and size adjustments; text-to-image and URL reference images do not use COS, while local reference images can be compressed and stored in COS; custom prompt suffixes are supported.

Remote-control DeepSeek Harness from a HarmonyOS phone: list, switch and create sessions; send prompts (the phone follows the host's busy-enter behaviour, queue or steer); stream assistant text, reasoning and tool steps; answer approval requests and questions; view session images as inline thumbnails with on-demand full-size fetch; switch model and reasoning effort; cancel running tasks; receive push notifications. Traffic is end-to-end encrypted (AES-256-GCM with HKDF-SHA256 key derivation) and travels through a dumb-pipe relay that only sees ciphertext; v1.1.3 adds a session-epoch anti-replay handshake and optional native TLS for the relay. The relay can be hosted on the local machine (managed by the plugin) or on a VPS; the phone app and the plugin ship in one repository. 5 Remote methods.

Drive PdfCraft from the agent: read and extract text, render pages to images, rotate, delete, reorder, combine or split pages, and audit faux redactions. Exposes PdfCraft's tool set as both commands and an MCP server. Requires the matching ArtCraft app CLI installed locally; it is not bundled.

Adds Regenerate and Edit and resend to each message you already sent: Regenerate re-answers the same text in one click without going through the composer; Edit and resend retracts that message and everything after it in place — out of the transcript and out of the model context, in the same session with no new branch — then puts its text and images back into the composer, so the edited send rewrites the conversation from that point. Messages carrying files rather than images stay disabled.

Visual reference moodboard for DeepSeek Harness: drag-and-drop images with tags and notes, and pinned style guides the agent reads before it generates or restyles UI.

Personal WeChat and WeCom (企业微信) bridge: QR pairing, one DSH conversation per chat, two-way text/image/video/document/archive transfer, chat commands (/help, /status, /new, /stop, /friends) answered by the bridge itself without spending a model turn, a switch that restricts the bot to 1:1 chats (group messages are dropped silently and counted), remote approval by replying 1 or 2 in the chat, and a two-way WeCom intelligent robot over its long connection (no public URL needed) that also receives and sends images, files and videos.

Prepares a repository README before pushing: scans repo facts, renders banner and process-diagram images (needs Pillow and the Microsoft YaHei font), lints layout and section numbering, then commits and pushes with retry.

Vision relay for text-only models: a configurable GLM-compatible vision endpoint analyzes the images you attach in the background and the original model keeps answering in the same session, leaving your message, image, model and history untouched. Requires applying patches/0001-session-image-admission.patch to a stock DSH install (images are rejected before storage otherwise); the repo ships an apply/restore script.