Plugins

Mais predefinições de agentes para DSH, derivadas de outros agentes de programação, como Qwen Code e iFlow.

Chamadas de voz iniciadas pelo agente: `offer_call` faz o humano tocar (接听/拒接/稍后再说); as chamadas aceitas são sintetizadas e reproduzidas localmente com CrispASR + Qwen3-TTS (9 vozes, 2 dialetos chineses), e as rejeitadas devolvem a decisão ao agente.

Extensão nativa de capacidade de visão, usando Zhipu (grátis) ou 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.

Balance badge that follows the active model provider: official readings for DeepSeek, Qwen Token Plan and Aliyun BSS, plus Moonshot and OpenRouter endpoints not yet key-verified.

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).

Consent-bound one-turn voice preview for DSH Web with a credential-free local synthetic demo, optional Qwen Audio, exact Session isolation, and explicit transcript-to-draft handoff without automatic submission.

DeepSeek Harness vision plugin: 8 analysis modes (describe, OCR, chart data, UI review, object detection, compare, code-gen, debug), any OpenAI- or Anthropic-compatible vision API, with a built-in free vision model and automatic rate-limit failover.

Plugin out-of-tree para DeepSeek Harness: dá olhos a um modelo de codificação somente texto roteando imagens para uma rota Qwen-VL (DashScope) via ctx.llm e retornando texto.

Ferramenta image_describe (识图) voltada ao modelo sobre a API compatível com OpenAI do DashScope (qwen3.7-flash), além de uma ponte de colagem: em sessões somente texto, imagens coladas se convertem automaticamente em caminhos de arquivo no envio e são renderizadas de volta na transcrição, para nunca esbarrarem na admissão de imagens. Traga sua própria DASHSCOPE_API_KEY; endpoint/modelo/orçamentos configuráveis, cliente HTTP à prova de redirecionamento e funciona em todos os agent presets.

Visão sob demanda para modelos DeepSeek somente texto: envie imagens e o modelo chama uma ferramenta view_image apoiada em qualquer endpoint de visão compatível com OpenAI (Qwen/DashScope por padrão).

Plugin do DeepSeek Harness: alternância de modo de raciocínio por requisição (enable_thinking) para modelos da família Qwen3 em endpoints compatíveis com OpenAI

Pacote de plugins do DeepSeek Harness: ferramentas qwen_vision (compreensão de imagens via Qwen-VL) e qwen_generate (texto para imagem via Qwen-Image) para modelos somente de texto

ModelTester — model detection & attribution panel for the DeepSeek Harness web chat. Ranks vendor families (DeepSeek / Anthropic / OpenAI / Google / Qwen / GLM / Kimi / MiniMax / MiMo / LongCat / InternLM / Step / Yi / Llama / Mistral / Nemotron / Grok /

Adds a button beside the composer and a global hotkey palette (default mod+shift+k) that hand one-off questions to a web chat instead of into the harness context: the draft is lifted out of the composer, copied to the clipboard and opened in the templated URL. Ships target-site presets (DeepSeek, Kimi, Qwen, 豆包, 腾讯元宝, GLM, Gemini), a local question history that can be re-opened, copied, or inserted back into the composer, and a settings tab for site, URL template, hotkey, clipboard and history.

OAuth sign-in for 9 subscription LLM providers (Claude, Codex, Grok, Antigravity, OpenRouter, Agnes AI, Qwen, Spark, ERNIE) with zero-config login and usage dashboards.

Voice input plugin (dual-face): mic button beside the composer send action, live recording bubble streaming PCM to a local Qwen3-ASR python service managed by the host, plus an ASR environment settings page (clone runtime/model repos, create venv, run ser

ServerChan3 (Server酱) push notifications when a turn finishes — title, model, project directory, git branch, status and a reply excerpt, with subagent filtering and fire-and-forget delivery.

Qwen Token Plan CN Responses provider for DeepSeek Harness via the OpenAI Responses API, with Qwen server-side tools, DSH local function tools, text/reasoning/tool-call multi-turn history, persisted image attachments, and a per-release official model catalog snapshot.

OAuth sign-in for 9 subscription LLM providers (Claude, Codex, Grok, Antigravity, OpenRouter, Agnes AI, Qwen, Spark, ERNIE) with zero-config login and usage dashboards.

DeepSeek Harness adapter for Qwen Token Plan CN with Responses tools, GLM Chat routing, and a versioned official catalog

Model-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.

明眸 VisionBridge - Ponte visual própria: quando um modelo cego recebe imagens, chama automaticamente um modelo visual para reconhecê-las e devolve o texto reconhecido ao modelo principal; transparente, configurável e sem perdas ao atualizar.