Plugins

Sidebar usage dashboard: DeepSeek balance and today's cost, project file explorer, Git diff & history, built-in terminal, and one-click Harness updates.

An Excalidraw prototyping tab for dsh-better-sidebar with structured product clarification, conflict-aware human and Agent board updates, and prototype-guided frontend generation.

DeepSeek Harness plugin that locks the web chat composer Enter-send. Toggle with a lock button or Ctrl+Alt+L to prevent accidental sends while typing or editing long prompts; unlock to send. IME-safe and per-session.

Settings -> Plugins switchboard: every loaded plugin card shows its package description and runtime phase, with fuzzy search and start/stop toggles that never rewrite config files.

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.

A corner HUD for DeepSeek Harness that shows your session's token pressure, per-model cost, and daily/monthly usage at a glance, with an editable budget and balance that tracks spending for you. 右下角常驻的 Token 仪表盘：实时看会话压力、按模型估算花费。预算和余额点一下就能改，每天每月用了多少都有记录。

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.

Sidebar panel for Agnes image and video generation that also ships a node canvas and a short-drama mode. Canvas nodes are chained by extracting the previous shot's tail frame with ffmpeg and submitting it as the next shot's first frame; short-drama mode turns an imported script into storyboard shots. Generation and polling run in the Host process, so tasks survive a page reload or a closed panel, and results plus an 80-entry history are stored on disk.

Control plane for the harness's own Agent Teams: members are ordinary independent sessions created through the same seam the GUI uses, each with its own model, so they open and continue like any other conversation while a sidecar roster and task board coordinate them. Task entries carry a definition of done, a member's completion is submitted and waits for the Lead's review, and availability tells idle apart from awaiting-review or a failed last turn. With delegationEngine=auto it uses independent sessions, continuable subagents, or the kernel roster depending on what the composition provides.

Windows desktop control through UI Automation, window screenshots and mouse/keyboard input, with per-session app consent and action approvals.

Study workbench for exam prep and research: three-column task board with tags and filters, a spaced-repetition queue (simplified SM-2) that keeps finished cards coming back, a heatmap lit by actual focused minutes, weekly reports, per-day review notes, a pomodoro timer that survives panel switches, and Markdown export/import for Obsidian. Installable via dsh plugin add (dsh-study-desk on npm).

Bridges the CursorTouch/Windows-MCP desktop automation server into DSH through the official MCP client bridge, registering its screenshot, UI tree snapshot, mouse and keyboard input, clipboard, process and registry tools as mcp__windows__* tools for the model, and adds a windows_mcp_doctor diagnostic tool. Computer Use is off by default and is switched on from the plugin panel.

Turns a local Obsidian vault into a dedicated RAG chat panel: a sidebar page with the note browser, the retrieval-augmented chat and the cited source side by side, answering from fully local BM25 plus CJK-bigram retrieval over your notes and streaming through the DSH model channel, with clickable \[n] citations and mtime-based incremental indexing.

DeepSeek Harness × Feishu/Lark bridge: chat, cards, approvals, task board, goals and schedules in Feishu — plus fully local (offline) voice transcription with a play bar in the Web GUI.

Usage dashboard: offline-scans session logs to chart daily/weekly/monthly tokens, estimated costs, model/tool/skill/command leaderboards, output speed, working hours and quality metrics; gridstack+ECharts cards are drag-and-drop composable, with custom formulas and AI arrangement (prompt round-trip import).

Huawei HarmonyOS assistant-today (负一屏) task-completion push for DeepSeek Harness: hiboard_push / hiboard_verify tools post Markdown task results to the phone card feed, wire-compatible with the OpenClaw today-task skill, with the authCode managed from the dsh settings panel.

A dsh-better-sidebar tab that renders a session brief — a todo board read from the `todos` projection plus a deliverables section listing the files written this turn — and hides the official todo panel above the composer while it is mounted.

Registers the fight-scene-director skill for designing AI-video fight scenes, ported from the Codex skill of the same name. Emits structured Chinese prompts for Seedance 2.0/2.5 and MiniMax H3, plus trajectory-map and initial-position image prompts.

Go (weiqi) review coach: parses SGF records, backfills winrate and score analysis with a bundled KataGo engine, explains the costly moves in the chat, and writes the commentary back into an SGF copy; a web panel shows the board with problem moves, AI choices and variations.

Cron job board: schedules local scripts or dsh session tasks (fresh or pinned sessions) by cron expression, with centralized environment-variable management, run logs, and concurrency and timeout control.

One-handed, keyboard-free input for the composer: press and hold the mouse on the input box, speak, release — the text lands in the draft, and sliding up cancels without leaving a half sentence behind. No mic button to aim at and no shortcut to remember; the hand never has to leave the input area, which is the point when the other hand is busy. Recognition runs fully offline (SenseVoice via sherpa-onnx, no API key, audio never leaves the machine).

Enhanced model selector for the DSH composer with searchable provider groups, keyboard and accessibility support, and an inline reasoning-effort slider.