Plugins

Attention reminders: frame badge, tab-title count, and a status-colored whale favicon for sessions waiting for input or finished unopened.

DSH plugin: auto-fill metadata (context length, output cap, display name, input modalities) for custom-provider models from the Model Metadata Registry (models.dev).

Fine-grained permission gateway: per-category tool-call review (outside-workspace directories, commands, file read/write, subagents, repeated actions) with global & per-project allow/deny exceptions, quick-tool defaults, custom rules, a bilingual approval modal with inline diff details, custom rejection reasons and a sandbox-upgrade flow.

Continual self-refinement loop: persistent memory, periodic review-and-refine, cross-session shared knowledge, and automatic rollback through a model-callable harness_refine tool.

Desktop notifications for run completion, model questions, and approval requests with per-platform system sounds, zero runtime dependencies.

Virtual product team agent preset: user-led conversation walks you through the full 12-step pipeline from idea to shipped, promoted and operated product, with staged gates and per-stage skills.

Workspace-safe Office tools for agents: create/read Word, create/read/update Excel, and create/read PowerPoint decks with PNG/JPG/GIF image placement.

Voice input for DeepSeek Harness: speak into the microphone and the recognized text is submitted as a normal chat message, via local or browser speech recognition.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

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

Font engine for the Web GUI: system font enumeration, global and per-component font-size tuning with a Spy++-style picker, settings page.

VS Code-style three-column Explorer + Monaco editor plugin for the DeepSeek Harness web GUI

一个可以让ai自动调用VLM(多模态模型)进行视觉分析的dsh插件。A dsh plugin that allows AI to automatically invoke VLMs (multimodal models) for visual analysis.

一个基于DSH-better-sidebar的侧边栏提问tab，实现类codex的侧边提问或claude code的/btw功能

DeepSeek Harness 的跨会话引用(cue)插件

Monitors session state in the DSH web app and sends desktop, browser, and third-party notifications for interactions, completions, and errors.

DeepSeek Harness plugin bundle: graphlint dead-code detection tools for agents (graphlint_query / graphlint_build / graphlint_config + graphlint skill).

Local-first long-term companion plugin suite for DeepSeek Harness

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

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

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/ plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via a memory-IR parse layer that keeps .claude as the source of truth with no writes back. Six installable packages: loader, skills, permissions, agents, hooks, mcp.

Semantic UI sound effects powered by uisfx: task start/success/failure and per-button cues, settings UI with instant preview, 12 sound packs, Host-persisted preferences, and `ctx.uisfx` service for other plugins.

Tavily search with multiple API keys, key rotation and failover, a usage gauge, and a settings card.