Miglioramenti UI

Updates and plugin management for the DeepSeek Harness desktop app: a sidebar entry beside Settings and a Settings section, driven by the app's native bridge.

Windows 2000 skin for the DSH Web GUI: metric-accurate grey chrome, two-tone gradient title bars, 1px bevels, square corners and a 16px scrollbar. 给 DSH Web GUI 换上 Windows 2000 经典外观。

A browser that lives inside the DSH host: every session gets its own tab, the AI drives it with lazily published browser_embedded_* tools, and a human watches or takes over that same tab in an on-demand right-Sidebar tab — no GUI, no external browser, log

DSH global Markdown notes with workspace binding: sidebar Notes & bookmarks panel, host tools + file fallback. / DSH 全局 Markdown 笔记:侧栏面板,宿主工具 + 文件回退。

Coding-learn floating panel: edits and runs Python/JavaScript/TypeScript/PowerShell with exit code and timing, grades JSON course lessons with progress export, keeps Markdown notes and snippet library, and sends code plus a question into the current conversation for the main model to answer.

DSH Web GUI 数据库管理面板：侧边栏入口 + 独立面板，统一管理 SQLite / MySQL / Redis（数据源配置、实时连接池、SQL 浏览器、Redis 键浏览器），并提供受审批保护的 agent 工具。 | Database management panel for the DeepSeek Harness Web GUI: a sidebar entry and a dedicated panel managing SQLite / MySQL / Redis (source co

Standalone DeepSeek Harness plugin: preview .drawio (mxGraph XML) diagrams in the Web Sidebar

Zero-token on-demand translation for the DeepSeek Harness web GUI: hover a block to translate it in place, drag-select text for a popup or in-place translation. Never auto-translates the page.

DeepSeek Harness 备份与恢复插件：在 Web UI 设置里新增「备份与恢复」页，把全部工作区、完整对话（会话文件字节级复制）、附件、设置与 dsh-mnemon 记忆数据导出为一个 ZIP 备份包，并可预检后合并 / 覆盖导入。会话内容全程不解包不改写，任何 dsh 会话格式代际（v0–v3+）都可携带，harness 升级后可正常导入，dsh-mnemon 上下文注入恢复后与原本一致。

DeepSeek Harness plugin: gives the native right-sidebar file tree six things — an @ file reference button (@文件 / @file, @文件夹 / @folder) on every row, a modification-time and a size column, sortable rows, a whole-workspace quick search & locate (with revea

Uses a configurable system-prompt section to request a chosen reasoning language (Simplified Chinese by default), and expands thinking rows by default while preserving rows the user manually collapses.

ModelTester — model detection & attribution panel for the DeepSeek Harness web chat. Ranks vendor families (DeepSeek / Anthropic / OpenAI / Google / Qwen / GLM / Kimi / MiniMax / MiMo / LongCat / InternLM / Step / Yi / Llama / Mistral / Nemotron / Grok /

Read-only side branch in the right sidebar: quote text to ask follow-ups without polluting the model context of the main session; every follow-up rebuilds the branch from the latest settled turns of the main session, and writes are refused at the tool-execution layer so the prompt prefix stays cacheable.

Composer attach button for DSH Web: multi-file picks become inline draft capsules, files are stored under the workspace uploads root with an auto-extracted UTF-8 .txt sidecar (txt/docx/xlsx/pptx/zip/odt, zero dependencies), and sent messages carry only the file name — never a raw path.

Jev (TypeSafe System One) gives the human a second opinion, not the agent. When DSH's model asks you a multiple-choice question, dsh-jev-advisor builds a structured Jev request and floats the recommendation, probability spread and confidence beside the op

Third-party DeepSeek Harness brand plugin: whale mark plus a minimal 'deepseek' wordmark for the Web client sidebar.

Turn chat logs into a panel list maintained by a resident agent. Includes a zero npm-dependency core and an optional WeChat/QQ ingestion pipeline. Installs as a DSH profile bundle.

A theme gallery for DeepSeek Harness (DSH): JSON-defined skins with full-screen coverage and sidebar scenery, a 15-swatch palette-picker card, a pet-widget card (7 registry-driven pets playing by the chat input), a mood-greeting card (a scrolling greeting

Unified @ mentions in the DeepSeek Harness web composer: five built-in categories (file, folder, skill, past chat, plugin) plus a data-source seam any plugin can register through, references to absolute paths outside the workspace, and a candidate menu that can be scoped by a folder named earlier in the draft and pages with PageUp/PageDown instead of hiding rows.

Legal knowledge-base workbench: hybrid keyword/statistical/vector retrieval over local statute .doc/.docx corpora, faceted filtering, charge-name and civil-cause trees, a document editor, and four AI tools (citation check, contract review, AI analysis, AI drafting).

Legal training workbench: three-pane academic UI that reads the "Minglü" (lawagent preset) learning profile (case dossiers, flashcards, wrong-answer book, notes) and sends instructions into a Minglü session with one click.

A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.

Pins workspaces holding a running session to the top of the sidebar session list, and draws the running session row with an accent frame and tinted title, plus a short settle animation when a session stops running. Colours come from the active theme's own tokens, with the running accent taken from the token the status dot paints ongoing with.

Paper library and reading workbench: arXiv search, a local plain-file library (metadata / PDF / extracted full text), and three-level reading notes (overview / understanding / critique) kept as markdown beside the PDFs; seven model tools plus a web panel.