Плагины

Используйте свой телефон как периферийный пульт DSH: отправляйте сообщения (набранные или продиктованные с клавиатуры телефона), отвечайте на запросы да/нет и выбора, просматривайте сообщения и переключайте сессии на экране в стиле Game Boy, сопряжение через LAN QR или встроенный туннель Cloudflare.

Конфигурации запуска в стиле IDE для DSH: сохраняйте промпты LLM и команды shell как переиспользуемые конфигурации запуска (глобальные или для каждого workspace), запускайте их из заголовка сессии или со страницы новой сессии и управляйте ими через инструмент task_run_config, с записями, требующими подтверждения.

Анализирует изображения из диалогов с помощью мод-специфичных промптов (caption, UI, document, grounding, topology и т.д.) и внедряет структурированные доказательства с примитивами координат (боксы, точки, ссылки) в виде текста, с кэшированием на уровне сессии для повторного использования при replay и compaction.

Drive a DSH instance from another device: a host plugin opens a token-authenticated TCP port that a single-file Python CLI drives - listing and creating sessions, sending prompts with images, streaming replies, and switching models, permissions and workspaces.

Google-AI-Studio-style turn controls for DeepSeek Harness, in one install: edit a prompt and re-run it, re-run a reply in place, delete a turn from the model context, and render sent prompts as Markdown. Self-contained: the plugin list shows this one row;

Adds a human-facing TypeSafe Jev second-opinion card to DSH multiple-choice prompts, showing recommendations, probability distributions, confidence, raw JSON, and one-click adoption.

Forwards an unattended DeepSeek Harness run's tool-call approvals and ask_user_question prompts to Feishu cards on your phone. The desktop GUI answers first — a card is only sent after `delaySeconds` (120 by default) with no answer there — and a phone approval grants `allowed-once`, so no authority accumulates on the phone. One outbound WebSocket long connection to Feishu: no public IP, domain, tunnel or relay.

Drive a local DeepSeek Harness agent from QQ and other IM channels through AstrBot: send tasks with /dsh, continue by quoting or @-mentioning the bot, answer approvals and ask_user_question prompts from chat (in parallel with the DSH web UI), and get results, inline images and file cards back. Ships session / workspace / model / permission commands, /compact and /last recovery, three progress-display modes, and group-shared or per-user session scoping.

Arrow-key input history for DSH 0.1.2-alpha.1: press ↑ in an empty composer to recall this session's prompts, ↓ to go forward, Esc to restore the draft.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

Matches prompts to installed skills for automatic activation, applies skill-declared lifecycle hooks and tool policies, and manages GitHub-hosted skills from Settings or the skill_manager tool.

Делегирование планировщик/исполнитель с именованными ролями: сильный планировщик управляет, одноразовые субагенты-исполнители (маршруты и промпты для каждой роли) выполняют. Роль по умолчанию плюс переопределение для каждого делегирования, глобальный регулятор усилия рассуждения в чипе поля ввода и страница настроек для управления ролями.

Добавляет рельс навигации по сообщениям в стиле Codex для быстрого поиска более ранних промптов в длинных беседах веб-интерфейса DeepSeek Harness.

Улучшение поля ввода веб-композера: восстанавливает отправленные промпты между сессиями с помощью ArrowUp/ArrowDown, ищет их с помощью Ctrl+R, восстанавливает богатые черновики и открывает закреплённую беседу /btw или /side.

Плагин DeepSeek Harness, превращающий git-синхронизацию anywhere-claude-mem в узел DSH: получает межмашинную память при старте сессии и отправляет новые промпты/наблюдения по мере их появления в воркере claude-mem

Нативные уведомления ОС для запросов подтверждения и вопросов/планов: во всплывающем уведомлении указано рабочее пространство, клик переходит к нему, двуязычно (zh-CN/zh-TW/en), со звуковым сигналом.

DSH plugin: keep your own prompts in Settings and switch them on per chat

Watches Feishu (Lark) conversations with your own user identity and forwards new messages as prompts into a chosen DeepSeek Harness session: per-monitor sender filters, @bot-mention bypass and keyword allow/block lists, auto-created pinned target sessions, and cursor-based polling that re-reads messages after a failed delivery.

DSH prompt library and reusable snippets plugin: save, edit, delete, and append prompt templates, workflow instructions, and reusable text from a button beside the composer without sending.

Conversation outline panel for the DSH web surface: user questions as root nodes (index, time, tool count and text volume per turn) with the Markdown headings of assistant replies hanging beneath them, plus level slider, search scope, bookmarks, copy and export as Markdown, section jump, keyboard navigation, a right-edge density rail and per-session reading-position memory. Read-only UI: it never touches prompts, tool results or provider traffic, and writes nothing outside its own localStorage keys.

Prompt scene picker for DSH: choose a scene from a dropdown and it opens a new session with the prompt already filled in (with {variable} placeholders), so you only tweak and send.

Maintains stable emoji session titles in DeepSeek Harness after user prompts without adding naming messages.

Replacement session-title provider that compresses oversized or code-heavy first prompts before calling the model (in the tested DSH version the built-in provider rejects inputs above 4096 bytes without a model call) and waits for a real task instead of titling a greeting. Titles use the session’s own provider and model by default and manual titles are protected; title rules cover a character cap, an optional date affix, style, language and exclusion words, plus a per-session lock. Also re-titles stored sessions in bulk, with a progress overlay that keeps running after Settings is closed.

Prompt history navigation for DeepSeek Harness (dsh) web: browse previously submitted prompts in the conversation composer with the Up/Down arrow keys, shell-style.