Plugins

Um plugin de bancada científica reprodutível para o DeepSeek Harness: células conduzidas pelo agente, figuras inline com feedback/nova execução, proveniência via manifesto e snapshots de ambiente

Observabilidade Langfuse para o DeepSeek Harness: exporta logs de sessão como traces OpenTelemetry (convenções semânticas GenAI) para o endpoint OTLP do Langfuse

Geração estável e editável de PPTX para agentes de IA — entrada em IR semântica, saída em DrawingML nativo

Adiciona ferramentas de status, diff, log, commit, branch e checkpoint opcional do Git, todas condicionadas a aprovação

Toques de conclusão por workspace, além de sons de atenção para eventos de aprovação, pergunta, revisão de plano, objetivo bloqueado e falha de tarefa, com sintetizador embutido, voz (TTS) e áudio personalizado

Verifica skills e configurações MCP em busca de injeção de prompt, homóglifos, Unicode oculto, comandos de shell perigosos e vazamento de credenciais

Operações de dispositivo e bancada ADB para o DSH: descoberta de dispositivos, logcat estruturado (streaming em segundo plano), instalação de apk, pull/push de arquivos e snapshots de desempenho via dumpsys

DeepSeek Harness plugin: panel hotkeys for every interaction panel — Enter presses the confirm (primary) button, Esc presses the cancel button (approval, question/choice, plan review; Claude Code habits).

Voice input (Web Speech API) and read-aloud (speechSynthesis) for the DeepSeek Harness web GUI — DSH 语音输入 + 回复朗读套件

DSH plugin: password gate for remote (non-loopback) /api access (passwordless by default), unblock the loopback-pinned privileged endpoints, restore everything on uninstall, and give the local 127.0.0.1 user the native OS folder picker for workspace selec

Multimodal plugin for DeepSeek Harness: understand images and generate images through configurable OpenAI-compatible or DashScope endpoints.

生物信息学「许愿式分析」插件：BioPython 全功能覆盖（任意代码执行器 bio_python + 14 个领域 skill）+ 高频语义化工具 + 零依赖自举 Python 环境（uv + venv + biopython 自动下载到插件私有目录）。用户下载安装即可许愿式分析。

Adds the DeepSeek Harness homepage background to dsh web: WebGL fluid light, dot-line grid and a digital point-cloud whale, with dark and light palettes.

Turns a stated need into a plugin choice: an agent skill that queries a catalog of the whole `dsh-plugin` topic (2600+ repos, recrawled every 6 hours, Chinese descriptions from Workers AI) through a ranked search API, then hands back the matching `dsh plugin add` command.

Pre-install supply-chain poison scanner for DSH plugins: AST (JS-X-Ray) + deobfuscation + regex heuristics, exits non-zero on findings for CI gating.

Exposes bounded Prometheus metrics for DSH sessions, agents, LLM calls, tools, approvals, subagents, and jobs, with a Grafana dashboard and a loopback-only endpoint by default.

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.

Free voice closed loop for the Web UI: browser SpeechRecognition mic input with live interim results plus read-aloud speaker buttons and auto-read for assistant replies, zero configuration and no API key.

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.

Speech-to-text voice input for the web UI: a mic button in the composer transcribes speech into the draft via the browser Web Speech API (zero-config) or an OpenAI-compatible Whisper API (OpenAI / Groq), with a selectable model and language in Settings.

Model-facing image_describe (识图) tool over the DashScope OpenAI-compatible API (qwen3.7-flash), plus a paste bridge: on text-only sessions, pasted images auto-convert to file paths at send time and render back in the transcript, so they never trip image admission. Bring your own DASHSCOPE_API_KEY; endpoint/model/budgets configurable, redirect-proof HTTP client, works in every agent preset.

Agent-callable vision tool that describes local images via any OpenAI-compatible vision endpoint you configure, with an optional multi-model cross-check and no built-in keys.

On-demand vision for text-only DeepSeek models: upload images, and the model calls a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).