实时扫描最新社区关于 DeepSeek Harness 发布的插件

DSH plugin: Windows toast notification when an agent turn completes; click the toast to jump back into that session in the Web UI.

DSH web plugin: better-sidebar Turn Review tab — a human gate on the diff of the just-finished agent turn (Approve / Request changes per path with comment). Not a rewind.

DSH web plugin: a right-side workbench panel (file tree / file viewer / git review) with a draggable-width side panel that coexists with the official tool-details panel.

理解任何东西技能包（移植自 Understand-Anything）

Quantum Algorithms Best Practices tool bundle for DeepSeek Harness

Update copilot for DeepSeek Harness: tracks the DSH core, bundle packages, and every profile plugin (npm version + git upstream dual channel), summarizes changelogs for agent-assisted upgrade decisions, and executes plugin updates only after explicit confirmation.

Privacy-minimal heuristic per-turn execution summaries for DeepSeek Harness

Goal-completion verification gate for DeepSeek Harness: intercept update_goal(complete), run workspace verification commands, and only let the goal close when they pass

dsh-vision — a DeepSeek Harness plugin (tool template).

DeepSeek Harness 识图插件：为 Agent 注册 image_analyze 工具，把本地图片或 URL 发送给 OpenAI 兼容视觉模型（默认 OpenRouter google/gemini-3.7-flash）并返回文字分析

Local-first vision for text-only DeepSeek Harness agents: route image understanding to a local OpenAI-compatible vision model, return structured JSON evidence (summary / OCR / layout / semantics / visual / uncertainty).

Vision for text-only DeepSeek Harness agents: delegate image reading to a one-shot subagent on a configurable vision route (MiniMax / Kimi / any OpenAI-compatible provider), keeping image bytes and the vision model's context out of the main session.

vision tool for DeepSeek Harness agents: describe local images via any OpenAI-compatible vision endpoint you configure (no built-in keys, optional multi-model cross-check)

Visual plan mode for DeepSeek Harness: structured plan.json + plan.md, an editable React Flow canvas, comments, plan diff, versioned revisions, and reliable write-back to the agent.

DeepSeek Harness (dsh) bundle plugin: vision_analyze tool lets text-only LLM agents read images via SenseNova VLM, with Schemastery config and single-source credentials

Voice for DeepSeek Harness — give text-only DeepSeek ears and a mouth: browser-native speech input (STT) + read-aloud (TTS), plus Whisper/TTS agent tools.

DeepSeek Harness 语音输入插件:麦克风 → 本地/浏览器识别 → 文本进会话(纯输入,与 agent preset 解耦)

DSH 语音双件套插件：voice_tts（edge-tts 协议零成本微软神经语音合成）/ voice_stt（OpenAI 兼容 ASR 语音转文字）/ voice_list（音色列表），原生 WebSocket + 插件级代理。

VPS Hub for DeepSeek Harness: manage your cloud-server SSH ledger, import hosts from ~/.ssh/config, and let agents discover, test, execute commands on, and transfer files to your servers. Private keys stay local as path references only. Optional Settings-page UI via the dynamic-plugin example.

Use DeepSeek Harness (DSH) directly inside the VS Code sidebar by embedding its web UI. Auto-starts `dsh web`, reuses an existing server, and reopens your most recent session.

%description%

Run DeepSeek Harness sessions from a VS Code sidebar.

Web access for DeepSeek Harness — multi-provider search/fetch on ctx.web, plus GitHub/PDF/YouTube extraction.

DeepSeek Harness (DSH) Web 插件：把聊天 Markdown 中的 ```mermaid 围栏代码块离线渲染为 Mermaid 图表（SVG）。mermaid 运行时随插件内置，不依赖任何在线 CDN。