Плагины

Управление откатом для последнего завершённого сообщения диалога

Превращает последний завершённый ход сеанса DSH в вертикальное видео-резюме, которым можно поделиться: редактируемая раскадровка из пяти сцен, маскирование приватных данных на хосте, необязательная AI-обработка и TTS-озвучивание, экспорт MP4/WebM с PNG-обложкой.

Регистрирует навык Inspiration Deck Workshop для DSH: локальные статические HTML-презентационные колоды (6 шаблонов колод, более 25 макетов, 23 темы и витрина анимаций) с CLI для проверки и экспорта в PNG/PDF и дымовыми тестами, без рантайм-зависимостей.

Плагин предметной области разработки на Rust для DeepSeek Harness (dsh): пирамида верификации fmt→clippy→build+test→miri+audit(+semver) как инструменты для модели + управление на уровне графа (anti-Goodhart: 8 правил, включая плотность #[allow] / удалённые тесты, blind-spot через Cargo.toml и pub

Плагин достижений и геймификации: разблокирует значки за ходы, вызовы инструментов, сессии, ежедневные серии и поведение при кодировании (правки/чтения/тесты), со стеной значков, всплывающими уведомлениями о разблокировке и SDK ctx.achievements.

Значок в заголовке беседы с версией DeepSeek Harness: проверяет последний релиз в npm и предлагает обновление.

Независимое браузерное приемочное тестирование результатов агента: на вход JSON-спецификация, на выходе вердикт из реального Chromium.

Сканер первоначальной настройки репозитория только для чтения (инструмент repo_setup_scan): определяет stack/тесты/документы/git/db и рекомендует плагины, MCP-серверы и файлы гигиены.

Автоматическая генерация модульных тестов: команда /testgen и инструмент generate_tests, которые создают, запускают и исправляют тесты до прохождения (LLM + офлайн-генераторы шаблонов; vitest/jest/mocha/node:test).

On-screen test-progress HUD for DSH — a click-through panel drawn over the app under test, showing each step's expectation vs actual and whether the waiting human may take back the mouse and keyboard. Ships a universal prebuilt binary (arm64 + x86_64), so no Xcode Command Line Tools are needed; the panel itself requires macOS 14+.

Five tools that build, test and run the Inimerse engine, and drive its Verse layers over the server's line protocol. Needs a local Inimerse checkout built with CMake; point the bundle's repoRoot at it (the shipped default is the author's path).

Asset governance console for self-hosted AI infrastructure. Registers MCP servers, skills, agents and AI apps in one ledger with a lifecycle state machine, per-tool RBAC permission points, department x agent x skill cost attribution, dependency topology and an append-only audit trail. Ships 27 plugin packages, 354 REST routes and 83 MCP tools; selftest runs 1486 end-to-end assertions. Not a hosted service, no cloud contract.

Learning Mode toggle in the input toolbar: injects a teaching prompt into the current session so the assistant introduces a topic, teaches it, tests it, and corrects mistakes, rendering graded quizzes through GenUI. Requires the GenUI plugin (@changfenhuang/dsh-genui); without it the teaching text still works but quizzes, sliders and charts degrade to plain text.

Predicts your next message after each completed turn and shows it as ghost text in the composer: press → to accept, or keep typing and finish it word by word with Ctrl+→, Esc to dismiss. The prediction model follows the session by default or can be picked in the settings card, which also has an on/off switch and a speed test.

An easter-egg brake-pedal self-test. A draggable pill in the DSH web UI runs six full-force braking stomps; the bracket snaps at a pseudo-random stomp between the second and the sixth, or the run passes entirely, and then a fictional notice appears. The pedal force is derived and labelled as such, while the session figures it derives from are read from the real session log. It never intercepts, delays or takes over the real stop action.

Network explorer for kids: my identity, DNS lookup, a traceroute trip, speed test and who is home on the LAN.

Enforces a check-fix-recheck loop when a task is wrapping up: it auto-runs your tests/lint/audit, blocks any round that still has unfixed problems, and only calls the task done after three consecutive clean full checks, then notifies the user.

Backs up DeepSeek Harness sessions, plugin config and workspace memory to Nutstore (Jianguoyun) over WebDAV, with incremental upload, connection test and one-click restore on a new machine.

Tracks this turn cost under the input box, today tokens and spend in the sidebar with peak and idle pricing, and pins the latest question to the top of the conversation.

AI-agent-driven automated testing platform for DeepSeek Harness (dsh): Markdown case library, bug reports, per-project serial queue, development board and built-in load testing.

Read-only work report rebuilt from local session logs: tools used and how often, commands run, files read and written, whether tests passed, failures and their causes, token usage, and whether the task finished.

Browser automation for DSH: the agent fills in forms, scrapes lists and works across tabs in real pages, using the logins you already have. It drives its own visible window on your desktop — minimise it and it keeps working without stealing focus — and a sign-in, CAPTCHA or native dialog stops the run and hands the page back to you: it never confirms on your behalf. Login state persists (own profile plus session-cookie re-injection). 23 Playwright tools (20 always on, 3 gated and off by default), with a URL allowlist, dialog suspension and a CDP method allowlist that are mechanism-level and pinned by tests.

Zero-token DuckDuckGo search provider for the DeepSeek Harness (DSH) web seam — local headless browser, no API key, no model billing