Plugins

One-click prompt enhancement (5 modes, memory chain, multi-model fallback) plus voice recognition (cloud Qwen3-ASR / offline SenseVoice, auto-stop on silence) for the composer, with one-click DSH service restart.

Design-fidelity QA for text-only models: a `deepseek_vision` tool borrows an eye from any OpenAI-compatible vision route, so the model can judge whether an implementation matches its mock — shipped with the benchmark behind that judgement (four fixtures, 23 injected defects, raw transcripts) and the questioning discipline it depends on.

DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.

Voice AI girlfriend for the Web UI: FunASR mic input, Qwen3-TTS spoken replies, companion animation window, and two-way QQ chat (text/voice/image push) via NapCat.

Dispatch self-contained tasks from DSH to 11 external agent CLIs (Codex, Claude Code, TraeCode, OpenCode, Gemini, Cursor, Kimi, Qwen, Copilot, WorkBuddy, Grok): a host-only bundle registering the conductor_dispatch tool plus an auto-triggered conductor skill.

Forces context compression when running low-context llama.cpp models such as Qwen3.8-27B, improving model efficiency and usage smoothness, together with well-refined compaction prompts.

A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.

Free vision bridge for text-only models: image understanding, OCR, UI and debug analysis via free-tier providers (Qwen3-VL-Flash, Doubao, DeepSeek-OCR) with a settings GUI.

One-click free-model setup for DSH web, built for coding beginners: one-click installer for Windows (install.bat) and macOS/Linux (install.sh, v1.7.0+); four permanently free channels — Zhipu GLM (text + image), SiliconFlow (Qwen3-8B plus 15+ sub-9B models), iFlytek Spark Lite and the OpenRouter free pool, which routes through openrouter/auto and picks from a pool that changes over time; bottom-left setup hint hides once any free model is connected; real-time DeepSeek peak/off-peak pricing reminder; bundled beginner help center.

Scans 20+ AI agents on this machine (Codex, Claude Code, cc-switch, Hermes, opencode, Gemini, Grok, Kimi, CodeBuddy, Trae, OpenClaw, Qoder, WorkBuddy, Zcode, Cursor, Windsurf, Cline, Roo Code, Qwen Code, ...) and one-click syncs, manages and adds their MCP servers and skills into DSH — global or per-workspace.

Multi-model orchestrator: the main brain decomposes complex tasks and dispatches subtasks to GLM / Kimi / Qwen sub-agents by each model's strengths, with per-model token usage.

Unified image generation router for DeepSeek Harness (DSH): auto-discovers image models from any OpenAI-compatible endpoint, provides draw_image and draw_list_sources tools, supports SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more.

LLM adapter plugin for locally deployed Qwen models behind a vLLM OpenAI-compatible endpoint, with per-model multimodal switch, fully configurable reasoning efforts, and a web settings page for editing the deployment from the frontend.

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

Local multi-plan bridge for DeepSeek Harness: use your existing ChatGPT Codex, Claude, ZCode (GLM) and Qwen subscriptions through one loopback proxy, with a settings-page status card and one-click provisioning. No dsh core changes.

ui_mockup 工具 Consumer：研讨阶段生成 UI 线框图/高保真草图，落盘设计稿并提示确认后锁定设计规格；含客户端卡片、图片路由与 i18n

Generates UI wireframes and high-fidelity mockups in DeepSeek Harness with selectable DashScope and Volcengine image providers.

More agent presets for DSH, derived from other coding agents such as Qwen Code and iFlow.

Agent-initiated voice calls: `offer_call` rings the human (接听/拒接/稍后再说); accepted calls synthesize and play locally via CrispASR + Qwen3-TTS (9 speakers, 2 Chinese dialects), rejected calls return the decision to the agent.

Native vision capability extension, using either Zhipu (free) or Qwen-VL (local).

Use ChatGPT Codex, Claude, Grok, Antigravity, Kimi, GLM, Cursor, Kiro, Copilot, Qwen, ERNIE, Spark, JetBrains, Perplexity, Replit, and Cody accounts as DeepSeek Harness LLM providers via OAuth.

Deterministic loop guard: denies a tool call repeated with identical arguments and caps per-agent calls, in code outside the model; incident log lets a parent interrupt a stuck subagent.

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).