Плагины

Курирование вывода инструментов на этапе приёма: сохраняет строки ошибок и предупреждений плюс начало и конец, а полный текст выгружает на диск с указателем, который модель может прочитать; охватывает все текстовые инструменты, а небольшие результаты проходят без изменений.

Запускает биоинформатические анализы OmicVerse/OmicOS в постоянном ядре Python, с поиском по каталогу возможностей, инспекцией ядра и вкладкой аккаунта.

Урезанный порт Headroom: сжимает вывод инструментов, срезая до 20% контекста, не затрагивая кэш контекста модели и производительность агента.

Панель квоты API DeepSeek, свёрнутая в ручку у левого края веб-интерфейса: по клику раскрываются баланс, официальный расход за сегодня (с токеном платформы) и стоимость текущей беседы; форк dsh-deepseek-quota.

Навык структурированного код-ревью для DeepSeek Harness — баги, безопасность, производительность, стиль

Поддержка кроссплатформенной песочницы Microsoft.

Инструменты для чтения информации об устройстве Windows: по одному инструменту агента на каждую категорию Win32-устройств (время, система, CPU, память, диск, GPU, сеть, батарея, процессы, USB, аудио, принтеры) через WMI/CIM и коллекторы Node os.

Гигиена текста как плагин dsh: очистка ненадёжного текста, поиск невидимых символов, очистка форматирования LLM и экранирование CSV-инъекций формул.

DeepSeek Harness document-routing tools: sniff a file's real format and a PDF's page layout, then extract with the right pipeline — layout-aware Markdown for multi-column papers, MarkItDown for everything else, images for scans.

Session management for DSH: archive/restore, batch & conditional delete, AI auto-rename, interrupted-session auto-resume, workspace grouping, undo last message, repair damaged session logs (seq-gap/EIO/dual-format), value analysis and full-text search — plus plan/closing template injection (system prompt + context).

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.

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.

Geological 3D modeling and 3D seismic processing workflow skill: SEG-Y volume parsing, CGCS2000 coordinate unification, fault representative line and exploration boundary shapefile output, and multi-mine 3D geology platform building.

Adds a UI effects page to Settings that switches off DSH Web animations and transitions, loading and progress animations, backdrop blur, smooth scrolling, hover title scroll, shadows, gradients and JS motion one category at a time, to cut browser rendering cost.

Shared infrastructure for data assetization plugins: business rules loader, file format adapter, report generator, path validator, audit logger Also known as @deepseek-ai/dsh-data-asset-shared.

Shows the DeepSeek account balance as a row in the sidebar footer with a refresh button, and opens a popover with the balance card, daily token and estimated-cost charts over a 7/30-day window, a per-model table, and a link to the platform usage page. The balance comes from the official /user/balance endpoint; usage is aggregated from local DSH session logs and priced with the published peak/off-peak rate card in CNY, so it is labelled an estimate and its scope is stated on the panel.

Shows token and CNY cost per turn and per session in the harness's own statistics form, a whole-account bill over 1/7/30-day windows with cost-per-unit-of-work trends, and an advisor that re-measures its own suggestions after you adopt them.

A full-page console panel opened from the sidebar, with eight tabs: an overview; a session list read from the sessions service (title, directory, running state, updated time, with filters); installed bundles and Loader entries from pluginInventory and pluginManager, with per-bundle enable switches; a plugin market listing public topic:dsh-plugin repositories from the GitHub search API; a model and provider editor that writes the llm-pi-ai settings namespace through remote.settings.mutate (switch a session model, add or edit providers and their model lists, and store API keys via remote.credentials, merging over the stored profile so fields the form does not expose survive an edit); MCP and skills tabs; and a usage tab that reads the host's loopback /api/dsh-usage/overview document. Services are declared through ctx.inject, so a deployment that omits one mounts without the console rather than crashing.

Audits a DSH profile for capabilities nothing consumes: inventories the declared composition rows, counts how often each registered tool and skill is actually called in the session logs, separates calls that were made from calls that returned a result, and reports the ones with no observed consumer. Ships a skill that fixes the evidence-chain format for completion claims.

Consistency guard for long-form writing: scans conversation prose for character, timeline and numeric setting conflicts across chapters, then jumps straight to the conflicting message.

Scaffold DSH local bundles in the dph format from any workspace and keep a pitfall experience library to steer later development.

Declare any number of LLM providers, each with its own endpoint, credential and per-model parameters (reasoning-effort vocabulary, image input, retry policy), across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats, configured from a settings page.

dsh-TUI /term: open a system terminal in a workspace folder — blank opens the working-directory root, a fragment fuzzy-matches folders (unlimited candidates, managed picker), with ordered per-platform launcher chains for Windows / macOS / Linux (incl. WSL

Lenovo device diagnostics and service assistant for DeepSeek Harness, including battery health, Windows device, performance, storage, Wi-Fi, app diagnostics and safe actions.