Plugins

Embeds charts, comparison tables, and interactive blocks between answer paragraphs, with locally saved state and revision history.

Renders a dsh-view fence in an assistant reply as cards — text, tables, charts, Mermaid diagrams and sandboxed HTML widgets — with an editable model prompt, a render_view tool and a bundled skill.

Writing council: parallel multi-model drafting, judge consensus & critique synthesis, AI prompt refinement, visual concept illustration, and Markdown file preview.

Adds a General settings row choosing where the Add-workspace directory picker opens: a fixed custom path (typed, pasted, or picked visually) or the last directory you confirmed. Quoted and CJK paths are accepted, and a This PC level reaches other Windows drives.

AIVN's stage engine inside DeepSeek Harness: a workspace is a play, the playwright preset writes Stage DSL, and a Stage tab in the conversation renders it live (backgrounds, sprites, dialog, stop-point choices, line-by-line TTS). dsh-aivn：把 AIVN 的舞台引擎装进 D

MCP visual manager plugin for DeepSeek Harness: inspect installed/enabled MCP servers, add/remove, enable/disable and view live connection status from the web GUI.

插件书架：优化 DSH 官方插件页的搜索、筛选、折叠、置顶、视图与安装信息。Plugin Shelf: visual organization for the native DSH plugins page.

可视化回答：AI 生成一段 HTML，在对话中以沙箱卡片渲染，支持交互按钮；配色自动跟随当前主题。

Visual Git graph, interactive branch management, and commit diff inspector in DeepSeek Harness right sidebar.

Adds an Optimize button to the composer that rewrites a one-line idea into a structured product brief: a positioning sentence, 3–6 key features, visual references and design tokens; it sits beside your original text in a compare dialog where you can accept it into the input, generate another version, or cancel and keep the draft untouched. No settings page and no API keys — it calls the model channel you already configured.

将 Graphify 原版代码知识图谱深度集成至 DeepSeek Harness（DSH），支持项目自动索引、实时增量更新、交互式可视化、扫描范围配置及 AI Agent 图谱查询。Native Graphify integration for DSH Desktop, featuring automatic code knowledge graphs, original interactive visualization, live updates, and Agent tools.

为 DeepSeek Harness 注入递归自化能力优化，以及可视化调整

Adds a draggable lucky-block button to the DeepSeek Harness web UI. Single-click plays zero-cost little performances (popups, a fake blue screen, daily fortune, trivia, cold jokes, music, and a set of visual stunts); a 1.4-second long-press mines the block open and starts a new session to write a random paper, read the news, invent something, or spin a short story. It also appends a "lucky block" choice to the model's multiple-choice questions and rolls a random pick, reversible by saying "rollback". Block appearance and event weights are adjustable in settings.

Training Lens opens a local TensorBoard scalar dashboard with selectable metrics, explicit improvement direction, optional EMA smoothing and Chinese/English UI; requires an existing Python environment with TensorBoard.

Move45clock: a health clock for DeepSeek Harness. A 45-minute work timer (5–120 minutes), 12 guided 12–15 minute seated/standing break plans, a visual plan editor, reminder cards scalable to 200%, night reminders at 21:30/22:00/22:30, and optional action-name voice coaching. Window wake is Windows-only.

In-conversation workflow run timeline for DSH Web: a horizontal rail with phase stations, agent pills, loop arcs and parallel bands replaces the stock workflow tool card and workflow-run chat node. Planned stations render before the run starts via client-side script scanning; status dots and icons follow DSH official primitives.

Previews a workspace OpenWiki in the DSH Web right Sidebar: detects the wiki directory, serves it with the official `openwiki visualize` reader on a loopback port, and embeds it in its own tab, reporting the installed openwiki and DSH versions against configurable floors and checking the registry for its own updates.

Live multi-way tree of the current session's agents in the DeepSeek Harness conversation view and right sidebar, with status, plan progress, tokens, cost (requires dsh-cost-meter), and runtime on every card.

Renders an Agent Teams swimlane canvas above the composer: lead centred with members below, tasks laid out in lanes by longest dependency path, and four SVG connector families drawn as dashed paths (task dependency as a cubic bezier from the upstream card edge to the downstream card edge, lead bus, peer bus, member-to-task tether). Cards are absolutely positioned DOM, connectors are one SVG layer sharing the same geometry constants. Layout constants and path algorithms are ported from cc-haha. Reads the live per-session agentTeam projection (roster, shared tasks, dependency edges, running state) and falls back to the session todo list when the session has no team; team messages are not part of the projection yet, so the communication panel shows an empty state. Body colours come from host theme tokens; the eight member identity colours are the deliberate exception — fixed hues mixed with the theme accent via color-mix, declared as CSS variables because the same values feed an SVG stroke attribute that rejects colour functions. Ships zh/en dictionaries with identical keys.

A floating panel that lights up which HowNet semantic primitives the current answer touches, as a brain-shaped node graph, EEG-style channel traces and a composition card.

Gives the DSH conversation the Visual Studio Code editor chrome: a 14px always-visible scrollbar with a flat, translucent thumb, plus a VS Code-style minimap in the right margin (half-window column, media not painted, hover-only minimapSlider, click/wheel scrolling) and auto-expanded older pages.

Movable radio pill with live visualizer, station search, favourites and self-update check for DSH Web.

Answers a hard question with a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled dependency-free `am` CLI builds the layout, CSS and diagram coordinates. Vendors the upstream answer-me-with-html skill verbatim as a skill-only DSH bundle with no Host code.

Pixel-level screenshot diff for visual regression. Two local PNGs in; a machine-readable first line (`PIXEL_CHANGED=true|false`, greppable as an assertion), then the difference ratio, per-region bounding boxes, maximum channel delta and mean absolute error, plus a self-contained HTML comparison page. An ignore-region list with absolute or fractional coordinates excludes clocks, cursors and other per-render noise. It deliberately does no content recognition: it answers only "did this change", which is the part that can be made deterministic. Entirely local — no model call, no network, no upload.