Плагины

RSS/Atom subscription management and parsing (rss_list/add/remove/fetch/check), persisted to settings.

Seven video tools (probe/cut/concat/encode/subtitle/extract/gif) on the official subprocess service: shell-free argv, zero runtime dependencies.

Optimize a raw instruction into a professional prompt through the harness llm service — four-section (Role / Task / Context / Format) or a headerless plain-text style. Context-aware by default: the recent conversation is injected as background and may enrich the ## Context section. Long outputs resume from the truncation point with auto-expanded budgets; validated results are cached (identical requests cost zero model calls); a unified call budget bounds worst-case cost. Composer ✨ one-click optimize, undo, cancel and a token-cost hint; prompt_optimize tool (optimize + iterate), auto-optimize hook, auto-detected zh/en role document.

Zotero library tools via the local API (no API key): search items/collections, read metadata and abstracts, list attachments, read full text (parses PDFs on the fly when Zotero cache misses), download PDFs, and manage notes.

Learning Mode agent preset: a coding agent that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style; installable via dsh plugin add (dsh-learning-mode on npm).

Connect dsh to a local Obsidian vault: search, read, write, move, and trash notes through `obsidian_*` tools.

File-based cross-session memory: plain Markdown memory files with automatic retrieval injection, format-compatible with Claude Code's CLAUDE.md and memory files, so migrating is a manual file copy.

Knowledge-base-driven agent preset: wiki long-term memory, a web KB UI, a management page and optional UI polish.

Export sessions to Markdown/JSON for review, replay, and per-session cost summaries.

In-place conversation rewind in the same session window without forking (Claude Code /rewind semantics): a per-message ↶ button cuts the model context back to any user message, with an optional Claude-Code-style file restore from disk-persisted before-backups.

Cross-session agent messaging for DeepSeek Harness with session discovery, offline delivery, delivery receipts, and sender-session navigation.

Codex App Server model provider using a local Codex login, with session reuse, Harness tool bridging, native action traces, and durable generated-image projection.

Use third-party subscription accounts in DeepSeek Harness: chat, image understanding, image generation, and image editing with the models your subscription covers, with available models and reasoning levels synced from your account; currently supports OpenAI/ChatGPT subscriptions, more providers planned.

Two-tier model routing: a strong tier plans, advises and reviews while a cheap tier implements, with plan-mode-aware auto routing, a high-impact escalation guard, failure auto-escalation, and subagent tiering.

Web theme and file workspace plugin with global typography controls, @file mentions, a project file tree, Markdown preview, and a resizable side panel.

A settings-panel skin manager that auto-discovers installed Web UI skins, switches between them in one click, and maintains the profile patch automatically.

OpenCode Go plan usage display for the DSH web GUI: a persistent badge under the composer shows rolling/weekly/monthly usage percents with reset countdowns; click to expand a card; agents can query the balance via the `opencode_go_usage` tool.

Usage tiers and shareable stats cards: 🐟→🐳 ranks by monthly token burn with a locally-computed estimated percentile, precise pricing for 46 models across 6 vendors (including size-tiered Chinese pricing), backfill of pre-install sessions, and old-vs-new comparison across the 2026-08-17 rate change. Local-only, no telemetry.

Highlights parts of speech (nouns green, verbs red, adjectives/adverbs purple) in rendered DSH Web Markdown, with light/dark palettes, toggles, and stream-aware updates.

Session timeline down the left of the conversation: every user message at a glance, current-message tracking, hover preview of the message and its reply, click to jump, collapsible.

Composer expand/collapse toggle for the Web UI: a ⬆/⬇ button in the composer tool row grows the input to a tall 70vh writing view for long drafts.

Телеметрия времени выполнения для DSH без вмешательства: каждая сессия автоматически записывает задачу, уровень модели, инструменты, сбои, длительность и статус в удобочитаемый журнал со статистическим разделом (чистый наблюдатель — без инструментов, без вызовов LLM, без внедрения).

Провайдер веб-поиска на основе Tavily для встроенного инструмента web_search, с карточкой настроек для API-ключа, количества результатов и окна свежести.

Плагин трёхколоночного проводника в стиле VS Code + редактора Monaco для веб-интерфейса DeepSeek Harness