Plugins

Requires DeepSeek Harness 0.1.5-rc.1+ (DSH Desktop >= 2.0.7) and dsh-better-sidebar >= 0.19.0 - update both before installing or updating this plugin. Plays local Wallpaper Engine Video/Web wallpapers behind the chat, renders Scene wallpapers as extracted static frames, and adds content-rating/type filters, custom uploads and an iOS-style liquid-glass settings window.

iPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.

Lets a DSH agent drive a local Blender over a direct TCP channel with 15 tools: viewport frames, custom-angle renders, Python execution, headless and job offload, transaction rollback, and a planning layer of 228 ops across 34 families.

MCP Apps Host plugin for DeepSeek Harness: renders interactive HTML cards from MCP _meta.ui in sandboxed iframes, bridges postMessage to MCP tools/call and resources/read

Generates game art from reference images via Seedream image generation and MiniMax image-to-video, assembling eight-direction sprites, sequence frames, and skeleton animations with local green-screen keying.

DSH plugin half of Fish Buddy: relays a separately downloaded Windows desktop whale widget (the .exe from the project's Releases page) to the session you bind; the widget itself does the listening, speaking, live subtitles, sampled frames and in-game chat, and downloads one of its voice-recognition models (228 MB default) on first use.

Whale-maid theme for DSH desktop and Web UI with light and dark palettes, ocean illustrations, hand-drawn frames, and a native Windows companion.

DSH Web UI little whale-maid theme with light and dark palettes, ocean illustrations, hand-drawn frames, decorative assets, and a new built-in Codex-style pet.

Visible agent browser for DSH over CDP, also driving egolite, Tabbit, Chrome, Edge, Brave and Lightpanda backends. Only bcdp_status stays resident (401 chars); the other 33 context-optimized bcdp_* tools unlock per activity batch, so non-browser sessions pay no schema tax (-91.9% measured). Realtime watch panel with direct click/scroll/IME input, element picks quoted into the composer as balanced @"picks/*.json" references, and human-verification notices; non-CDP channels (ego CLI / Tabbit CLI) sync frames by 3s polling. Cross-version support for DSH 0.1.7-rc.1 ~ 0.2.2-rc.1 (exact enumeration of 10 rc).

Twenty-one official HyperFrames by HeyGen skills synced from the official upstream (HTML video authoring, animation, keyframes, audio/music-to-video, CLI, registry, slideshow, talking-head recut, website/product/PR-to-video, Studio timeline conventions and more), plus a bundled-resource health check. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Reads animated GIF and WebP as animations: a pasted one keeps playing in the UI while the model gets a labelled sheet of frames sampled across it, and the read_animation tool samples a file on demand.

Bilibili video analysis: metadata, transcript (ASR fallback via Bijian/sherpa-onnx/whisper.cpp), comments, danmaku, and sharp keyframes with optional local vision descriptions.

Ten video tools (probe/cut/concat/encode/subtitle/extract/gif/frames/adjust/health) on the official subprocess service: probe summaries, batch frame extraction, speed/volume/mute/rotate adjust, shell-free argv, zero runtime dependencies.

Plays Inception Mercury's diffusion (denoising) stream live in the dsh Web UI answer bubble: for routes that support it, the request is re-sent with `diffusing: true` and the real frames are replayed from noise to final text, while only the converged answer reaches the session log. Support is detected per provider/model with a probe that is rejected before any token is generated, a floating per-model toggle turns it on, and attachments, auxiliary calls or unsupported routes fall back to the original adapter. Replaces the assistant-message renderer for all models while enabled.

Content-aware tool-result reducer: 13 reducers cut oversized output by meaning at tools/post-execute (failing tests kept, diff context dropped, JSON and CSV sampled, lint problems grouped by rule, dependency stack frames collapsed, crowded directories counted), with full originals spilled to disk behind a locator.

Controls the Chrome you are already logged into: the model clicks, types, fills in forms, reads pages, takes screenshots and downloads files in your real tabs, including inside same-origin iframes. Runs on macOS, Windows and Linux; needs Chrome 116+ and Node 18+. Works over native messaging and chrome.debugger instead of a listening port. Ships 12 browser_* tools and a cb CLI, dispatches real CDP input events, draws an on-page cursor that also appears in screenshots, and adds a toolbar panel with live status, the controlled tabs and a pause switch. browser_download saves a link, an element's target or a URL with the site's login cookies (following redirects, keeping the server's file name) to the Downloads folder or the session's working directory; cross-origin iframes are named in the snapshot but not entered. The native host and the MV3 extension travel inside this tarball: on first load the plugin copies them into place and writes the native-messaging registration itself, so there is no clone, no install.sh and no python3 - the one step left is adding the extension to Chrome: install DSH Bridge from the Chrome Web Store (https://chromewebstore.google.com/detail/bippcbbbipppmhjkjomgdnjbooecbimo, no Developer mode), or load the bundled unpacked copy at chrome://extensions (the plugin opens that page and puts the folder on the clipboard for you). Until then the tools fail loudly with those steps. On Windows the registration goes into the registry (for Chrome and Edge) and the host talks over a named pipe. A daily CI run on GitHub's macOS, Windows and Linux machines installs the plugin, loads the extension into a real Chrome and reads a page through the browser_* tools.

Drive FigCraft from the agent: create frames, components and auto layout, set fills, strokes and effects, build prototypes, and export PNG, SVG, PDF or code. Exposes both FigCraft's command ids and its own MCP server. Requires the matching ArtCraft app CLI installed locally; it is not bundled.

A visual map for your sessions: every conversation is a card on an infinite whiteboard — workspaces become frames that fold their overflow into a drawer, card positions are never rearranged, lines between cards carry context (drag one to fork with an injected digest), and each card shows a status lamp for running, waiting, unread or interrupted.

Five tools for reading a video as raw material rather than as something to watch. video_outline maps a whole file as text and draws nothing at all: 4-60 equal windows, each with its cut count, speech share, intensity bar and tags, then the windows worth opening and the exact start/end for the call that follows -- zero image tokens. video_probe returns metadata and a reading plan without decoding frames. video_storyboard turns a window into one contact sheet plus a text index binding every cell to its timecode, cut count and frame time; cells whose text would be illegible at that scale are marked zoom, and dedupe global folds a picture that comes back after a cut. video_zoom re-renders 1-9 cells from a short window at a larger scale. video_read decodes only keyframes, OCRs each screen, and returns an outline plus \[mm:ss] text -- the path for lectures, slide decks and screen recordings, where the words are the content. It also reads a file with sound and no picture as a transcript (subtitle track, then DSH_ASR_CMD, then a transcript file you pass; long audio is cut at 45 s onto silence), composes six changed frames into one sheet when a file has no readable text at all, and can write the result out as SRT, WebVTT or text. Cuts, dissolves and one-frame flashes are found in a single ffmpeg pass; from ten minutes up a file is analysed on its keyframes only, 2.7x faster on a two-hour lecture; and a cell is never shrunk below a fifth of the source, so a 1440p sheet spends the same tokens on fewer, bigger cells. OCR is the engine Windows ships, tesseract with line boxes, or DSH_OCR_CMD. It takes a B station link (bilibili.com/video/BV..., a bare BV id, an av id or a b23.tv short link) wherever it takes a file: up to 300 seconds is read from the CDN in place with nothing written to disk, longer videos are downloaded once and cached within a 4 GB / 24 video budget, play URLs are cached for ten minutes, and a link that is not a single video says what it is. Needs ffmpeg, uses ffprobe when present, and has no other runtime dependencies. It is a wire-compatible reimplementation of SAOS-3624/dsh-video-storyboard: it registers the same video_probe / video_storyboard / video_zoom tool names, so the two cannot be enabled together.

Drive EffectCraft from the agent: build compositions, add layers, set properties and keyframes, evaluate expressions, then render frames or movies. Exposes EffectCraft's command ids and its MCP server. Requires the matching ArtCraft app CLI installed locally; it is not bundled.

Drive DesignCraft from the agent: create pages, place and flow text, arrange frames and master pages, then export PDF. Exposes DesignCraft's command ids and its MCP server. Requires the matching ArtCraft app CLI installed locally; it is not bundled.

Cristiano Ronaldo desktop pet for DeepSeek Harness: a chibi Portugal number 7 mascot in a bottom-right overlay whose animation follows the agent state — dribbling while tools run, thinking during a turn, waiting at approvals, diving on errors — and jumping in a SIU celebration with a host-process sound when a turn completes; it can be dragged, looks at the cursor on hover, dives on a triple click, and a settings panel manages several pets and imports custom spritesheets. It also runs as a borderless, always-on-top native Windows window that keeps living after the browser is closed: hovering shows the current workspace and conversation title, double-clicking opens the Harness page in Edge, and dragging, mouse-wheel resizing and a right-click menu work there too, sharing position, size and behaviour with the web panel. Pet sheets may use any cell resolution and scale preserving aspect ratio (atlas.scaling: smooth | pixelated). v2.2 adds a video route — feed it a clip (green screen or ordinary footage) and its real motion becomes the pet animations, via automatic backdrop sampling, chroma keying with spill suppression, motion-based segment splitting and union-bbox alignment; already-extracted PNG frames work too, with no video decoder installed, and the clip audio can be cut into per-action sounds. Pets can also be published to the community gallery under the DPSL-1.0 sharing declaration, and installed from it in one click. v2.3 adapts it to DSH 0.2 desktop clients — the celebration sound now falls back to spawning PowerShell when the host no longer provides the shell service — and makes a single click play a short, configurable taunt animation (`interactions.clickAnim`).

Android in the sidebar, driven by text instead of screenshots. 30 tools read the real UI tree, tap by text/id/ref, measure animation motion, and mirror the screen into the sidebar where you circle a spot and send it back with one sentence — the host ships the marked-up frame plus the controls inside the circle to the chat. Token cost is the point: a screen check is a 200-600 token text block, not a 1k+ token screenshot, and a warm check costs 100-200 ms of wall clock. Video is raw H.264 straight into WebCodecs — no transcoding — with p50 2 ms host-write to decoded frame over a 26 s run, one decoder, zero dropped frames; it falls back to MSE on its own and ?avc=0 forces the old path. Sound is one switch, off by default and remembered per serial, so the default path pays nothing; when on, audio rides its own socket (48 kHz stereo PCM, measured 22 s / 1047 packets / 0 loss) and closing the window reclaims it too. Nothing runs behind your back: closing the window stops capture at once, the viewer-less host decoder, recorder and device-side server are gone within 3 s, an idle channel is dropped after 90 s, and a request you closed is never reopened by itself. `adb_proc audit` settles who leaked what in one call. Bundled helpers, no extra services; needs adb and ffmpeg on the host, and the adb_ocr tool plus the OCR fallback for empty UI trees are macOS-only.

Performance optimization and smoothness enhancement for DSH Desktop (renderer-side only; host code untouched, no on-disk config): skips offscreen message rendering, stops frames and timers while the window is hidden, lazily loads media, coalesces session-list repaints and pre-warms large session files; shows the measured main-thread saving in settings. A lightweight speed-up for lag, dropped frames, slow large-session opening and background CPU use.