Плагины

Плагин сообщества DSH: уведомления/мост со Slack (v0.2 поддерживает двунаправленный Socket Mode: входящие + ответы в тредах).

Провайдер LLM для DeepSeek Harness для моделей Codex через управляемый OAuth ChatGPT

Независимое от загрузчика восстановление запуска для DSH Web: обнаруживает вероятно сломанные плагины, временно пропускает их и восстанавливает только изменения, управляемые Boot Guard.

Ползунок уровня рассуждений в стиле Codex, встроенный в выбор модели.

Режим чтения документов для DSH.

Preset-mode badge embedded in the "New Session" button: click to pick the default agent preset for the next session (long names truncate with ellipsis so the label stays readable).

DeepSeek Harness 多模型路由插件：让专业的事情交给专业的 agent——自定义视觉/翻译/语音/子代理等专业 agent 并绑定独立模型，多模态账号一键登录、账号池健康路由与实时用量统计

SSH terminal panel and AI connection manager for DeepSeek Harness: model-driven SSH connections (connect/exec/list/status/disconnect), auto-saved connection records, keep-alive + auto-reconnect, execution mutex, credential-safe auth, and an XShell-style m

Multi-provider account balance display for the DeepSeek Harness Web GUI. Queries real billing APIs (DeepSeek, StepFun, Kimi Coding, OpenRouter, MiniMax, xAI) and shows balance/quota in front of the model selector. Providers without an API-level billing en

Tavily-backed web search for the DeepSeek Harness: rotation-aware tavily_search model tool plus the Tavily Search settings card (keys, usage strategy, usage gauge, on/off switch).

Cherry Studio-style knowledge base system for DeepSeek Harness (DSH): bases, documents, chunking, embeddings (OpenAI-compatible / Ollama / local / lexical fallback), retrieval, model-facing tools, and a browser management panel

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

Multi-pet companion for the dsh web GUI: a registry-driven floating pet that reacts to model activity.

LLM auto-approval for sandbox escalation requests, with presets and a fail-closed fallback.

Literary DSH plugin: one session is one book. Cover-card /new opens one of 19 realms, a prose-only 诸天万界DSH preset keeps the model writing fiction, keyword worldbook entries ground each turn, and /export-story typesets the session into a Markdown novel.

Advertise image paste on text-only DeepSeek routes, describe attachments with a vision sidecar, and leave native vision models untouched.

Gives a text-only model image understanding via a vision-language model, exposed as a `describe_image` tool.

Per-subagent LLM provider/model selection with role templates.

LLM provider that runs the locally installed Claude Code CLI as the model backend, so requests go through an existing Claude subscription instead of a metered API key; native tool calls are bridged over MCP.

Configurable DSH usage statistics: a sidebar text/card widget plus a detail dialog with per-provider and per-model breakdowns, cache-hit rates, token trends, and latency details (TTFT and duration).

Wallpaper Engine local library, background layer, native Scene panel, and desktop-mode controls for the DSH desktop shell.

One-click enter/exit Plan mode for the DSH web input bar, a quick-click shortcut for /plan.

Runs open-mcp-apps inside DSH: every MCP app gets its own sidebar container with a separate workspace, session, and App mode, an agent status strip under the app, and inline app rendering in ordinary chats.

A Claude Code-style reasoning-effort slider for the DSH Web UI: stepless drag, snap-on-release, a WebGL fire trail, and real, working thinking-effort control for any custom third-party model or provider.