Plugin

Full-screen screenshot panel for the DSH composer: marquee selection with rectangle, ellipse, arrow, pen, mosaic and text annotation, then insert into the conversation, copy or save. The selected region can also be recognized offline — PP-OCRv6 through onnxruntime-node, falling back to the built-in Windows OCR engine — and translated into nine languages with the model already configured in DSH. On Windows the marquee covers the whole screen including the taskbar and hides the DSH window first, so the capture is of the real desktop. The panel runs in an Edge or Chrome kiosk window, and falls back to an in-DSH capture flow when no browser can be launched. Note that DSH Desktop denies ordinary browser access by default, so the full-screen panel also needs "Allow opening this Profile in a browser" (compatibility mode) enabled in the profile settings; without it every capture goes through the in-DSH fallback. Windows only (DSH Desktop); the PP-OCRv6 models are downloaded from ModelScope on first recognition.

Hosted PrimeSync AI Studio strategy-research MCP configuration bundle using the official MCP client and mcp-remote OAuth bridge; eligible Studio access required. Experimental: OAuth consent and tool calls are not yet verified end-to-end. Complete manual CLI sign-in on the same computer before starting Harness; otherwise tools may be absent after startup. Targets DSH 0.2.1-rc.2 only; mcp-remote 0.15.2 is downloaded through npx on first launch.

Snipaste-style screenshot for DeepSeek Harness: press F1 (a real Windows global hotkey) to freeze and dim the whole screen, drag a region, then draw red boxes and click-to-type text annotations with wheel-resizable font; the annotated PNG drops into the composer at native resolution. Esc exits. Windows 10/11.

Adds two buttons beside the sidebar toggle at the top-left of the DSH desktop UI, on macOS, Windows and Linux. Reload refreshes only the UI layer while a turn already generating keeps running; restart asks for one confirmation, quits the whole app and reopens it with sessions and workspaces intact. Restart is a POST that must carry a random per-boot token read from the plugin's status route. The plugin makes no network calls, reads no session content and has zero runtime dependencies.

Create, import and manage personality presets with global and per-conversation choices.

Drive local Origin/OriginPro from chat via 27 MCP tools: import .dat/.csv/.txt and CHI workstation .bin files, plot, style, fit, and deliver PNG/TIF/SVG/PDF plus an editable .opju project, with read-back verification on plots, styles and exports. Requires Windows, Origin/OriginPro 2021+ and Python 3.10+, plus `pip install originpro numpy` into the interpreter dsh launches: without the package every tool answers `missing_originpro`, and without an interpreter on PATH no tools register at all.

Real-time per-session token cost for the DeepSeek Harness web GUI, with per-provider pricing and configurable peak/off-peak tariffs

Restores the permission preset a session was last set to when that session is reopened; a session opened for the first time is left untouched. Load it after dsh-experimental-auto-review to restore the auto preset.

Evaluation guard for DSH: workspace-only filesystem, no network/subagents, wall-clock limits, and task installation for meow-ai-arena and benchmark tasks.

New in v0.3.0, import your own TXT three ways - pick files or drag them in, browse folders and click a book, or type a path - while an AI companion rides along in the DSH right sidebar commenting on whatever you just read, on a timer or on demand, in four styles, floating in the corner with a speech bubble. Picked files land as content-hashed copies so re-importing is a no-op and your originals are never touched; folder picks stay zero-copy. Chapters split and render one at a time with adjustable font size and line height; five reading themes; annotations and progress written back to the same files the novel-reader desktop app uses; pick any model provider registered in DSH or your own OpenAI-compatible endpoint, off by default, and when something breaks it names the route and the reason; Chinese and English UI.

DSH onboarding plugin: recommends plugins across eight domains ranked by weighted GitHub stars and npm monthly downloads, installs the recommended set in one click behind a reviewable plan, and exports or imports an environment code recording a profile's plugin list, exact versions and enabled flags.

A global permission watchdog: a hard budget on auto-approved permission requests. At most 10 per rolling 60 seconds, at least 3 seconds apart; anything past either limit is deferred to the human answerer and waits. It never refuses and never changes what is asked -- it only decides who answers and how fast. Installs disabled; enable it with the plugin manager toggle.

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.

Sends an Edge/Windows desktop notification when a tool call waits for approval, the agent asks you to choose an option, or a session finishes a turn, and only while the DSH page is in the background or unfocused; an optional chime covers cases where the browser or Windows suppresses the notification.

Registers native doubao_generate_image and doubao_image_status Agent tools to automate Doubao Web (doubao.com) via Tabbit Browser, automatically extracting watermark-free 2.7K wm0 original images into local files and multimodal chat attachments.

Recursive delegation for dsh agent trees: a preset plus Host limits bound what each subagent may do, subagents work in separate _agents/ workspaces, and the parent decides which results to integrate.

Runs a second agent: hands independent subtasks to a local Codex CLI in parallel (up to three at a time), and asks it to review a design or a plan before the user sees it, returning conclusion, evidence, counterexamples and a verification step. A dispatch missing its timeout or its acceptance check is rejected by the plugin, not by the model remembering to check.

Conversation search, checkpoints, context management, main and side chats, local long-term memory, tasks, and daily planning for DeepSeek Harness.

Agent preset for DeepSeek Harness: the standard tool stack plus four working rules written into the persona prompt — a project keeps at most four documents (intro, decisions, change log, current state and next steps), those documents describe only the current state with no AI edit history or superseded decisions, no git commit or push or pull request until the user explicitly asks, and a careful-coding workflow (restate the goal and done-criteria first, surgical diffs, evidence before claiming success) with plain-language reports.

Companion operations panel for the Kaipu site plugin: round timeline, run status, jump gates and browser entry. Installs and uninstalls on its own; the site plugin stays fully usable without it. Renders the persisted workstation state (no live stream yet).

Adds a writing-plans skill that generates a structured implementation plan document before coding, then executes simple tasks inline or offers an execution choice for complex work.

Eight academic skills bundled for one-command install — publication-ready academic figures designed from real data with visual review, AI-text humanization, paper polishing and rewriting, PubMed citation verification (DOI/PMID reconciliation), Chinese citation and medical-book reference checks, and WeChat medical article structuring. Three skills run fully local, five call external services only when used (NCBI E-utilities, DOI resolvers, publishing platforms), declared per skill. Zero telemetry, no install-time scripts. Skills run local Python 3.8+; the academic-figures skill also needs its pip dependencies installed.

Kill AI Slop for DSH — score a received document on three weighted axes (expression, execution, decision), audit work-slop with a delivery-obligation ledger, and machine-verify every quote against the source. Reads docx, pptx, xlsx, pdf, txt, md, csv, json and html. Zero runtime dependencies, zero network, fully local.

Design-first PowerPoint builder: six pptx_* tools turn a deck.json design draft into an editable .pptx with AI backgrounds, cutout illustrations and decoration pieces, run layout and contrast checks, render slide previews, and review pages with a configurable vision model; chat cards and a settings page in the Web UI. Requires DSH Desktop 0.2.1-rc.2+ (pptx_render uses its bundled LibreOffice Kit) and an Agnes or ModelScope API key for image generation.