Plugins

Orquestração de tarefas de desenvolvimento dirigida por configuração para DSH: workflows em grafo (nós de tarefa/porta de entrada/humano) com persistência por estágio, além de um assistente de IA no editor que configura workflows por meio de conversa com validação ao vivo. Passe documentos aos nós como anexos genéricos (sem necessidade de declaração): os arquivos vão para o espaço de trabalho da tarefa e ${inputs.附件} fornece os caminhos absolutos unidos por quebras de linha, para que um nó os analise com seu próprio prompt.

Adiciona um painel de ajuste de tema em Aparência para personalizar a cor de destaque, o fundo, o primeiro plano, o contraste e o gradiente, aplicado ao vivo através de substituições de tokens do tema.

Executa 3 ou 5 candidatos de coding agent em worktrees Git desanexados, valida seus patches com comandos do projeto, classifica apenas os candidatos aprovados e exige aprovação separada antes de aplicar o vencedor.

Adiciona 20 localidades (chinês tradicional HK/TW, japonês, coreano, francês, alemão, espanhol, português, italiano, russo, ucraniano, polonês, neerlandês, turco, árabe, hindi, indonésio, vietnamita, tailandês, sueco) à Web UI do DeepSeek Harness, com traduções cuidadosamente refinadas, fallbacks em tempo de execução e tradução automática dos textos do mercado e de terceiros.

Adiciona uma ferramenta x_search para pesquisa no X/Twitter ao DeepSeek Harness, autenticada por uma conta SuperGrok OAuth separada, de modo que não consome a cota do provedor da sessão.

Geração local de imagem, voz, música e SFX, além de transcrição, com identidade fixada: personagens, animais, objetos e vozes de atores são definidos uma vez e reutilizados em cada chamada posterior; a saída degenerada (imagem quase plana, áudio silencioso) é rejeitada em vez de retornada como sucesso, e uma linha gerada pode ser lida de volta como texto, para que um clone que engoliu seu final se torne visível. Os motores descarregam quando ociosos, e a geração de imagens e a transcrição podem cada uma apontar para uma API no formato OpenAI em vez do backend local Vulkan.

Acompanha no WakaTime as leituras de arquivos, visualizações de imagens e edições de código do DSH, incluindo contagens exatas de linhas adicionadas e removidas pela IA. Mantém o rastreamento de atividade em execução enquanto o DSH responde, agrupa atualizações entre arquivos e coordena limites de relatórios por projeto entre processos DSH paralelos. Instala e atualiza o wakatime-cli automaticamente.

O GPT planeja DAGs de dependência, os workers DeepSeek executam tarefas com paralelismo adaptativo e um revisor GPT opcional audita diffs incrementais de Git e conduz rodadas de reparo.

Port do TaskPlane para DSH: executa ondas ordenadas por dependências em trilhas paralelas de git-worktree, com pacotes de tarefas, revisão entre modelos e recuperação após falhas.

RAG de grafo de conhecimento duplo para notas Markdown com decaimento de memória half-life: grafos de pré-requisitos + similaridade (travessia P/S-Agent), fragmentação por parágrafos, busca híbrida n-gram/embedding e loop explícito de feedback de pesos — plugin nativo Cordis, instalável via npm como @eqman00003/knowlp-rag.

Connects DeepSeek Harness to QQ over OneBot 11/12, Satori, Milky or the official QQ bot API, with a separate session per group or private chat and nine built-in tools: group management, chat history with image understanding, web search, page fetching, reverse image search and image generation. Optional proactive chatter reads recent messages on an interval and decides whether to join in, with the judging and speaking stages able to use different models. Models, proxy and allowlists are configured in the DSH settings page. First run requires an owner (auth.owners): with it empty the plugin drives no sessions at all (deny by default, so installing it does not expose the bot); once set, private chats and groups work immediately, guests only reach the guest tool allowlist while qqbot and qqconfig stay owner-only.

Runtime plugin firewall for sessions started through its launcher (the DSH Desktop app cannot be injected and is not covered): filesystem, network and subprocess calls plugins make are attributed to the plugin that made them and judged against what that plugin declares, so a plugin doing its declared job stays silent and leaving it is recorded. Attribution is best-effort, not a guarantee - uncovered calls fall back to host, never to another plugin. Also adds a pre-install health card (capability surface, red-line combinations, PASS/WARN/BLOCK), boundary judging, opt-in pre-execution blocking with a credential-exfil rule, update diff with a trial install in an isolated child process, SARIF/CSV audit export, and multi-source aggregation. Local-only storage, no telemetry; the optional webhook is off by default.

Connector only, it renders nothing itself: subscribes to DeepSeek Harness session events and folds them into a 12-phase work state (planning / thinking / executing-tool / streaming / waiting-input / voice / awaiting-approval / complete / error / paused / idle / heartbeat), then POSTs each phase to a desktop-pet backend at http://127.0.0.1:8000/api/plugin/dsh/ingest. It holds no window. No API key or token is needed. Requires the Mao Live2D pet application to be separately installed and running (that is a Windows Electron app with its own PowerShell 7 / Python 3.10+ / Node 18+ prerequisites); without it this plugin has nothing to push to.

Android development toolchain inside DeepSeek Harness: 23 android_* tools that find the SDK, create and manage AVDs, start and stop emulators, scaffold a Kotlin/Compose project, build and run it with Gradle, then install, launch, screenshot, tail logcat and drive the UI. A settings page holds the SDK, emulator, API-level, build and output parameters.

A long-form Chinese novel workbench inside DeepSeek Harness: read, edit and annotate the manuscript in place; AI reports problems with ready-to-adopt revision drafts, and the text changes only when you accept. A ledger for characters, facts and foreshadowing plus a world map keep a long novel consistent, and AI can continue, expand or rewrite chapters.

Runs a Douyin subagent that browses videos and reads comments in valley hours and reports back, with dy_* tools for publishing and replying (comments sent from the already-logged-in page with its own request signature, no IM ticket), a daily quota timer, and a settings panel under Settings → Douyin: master switch, auto mode, valley windows, rounds per day and report depth. Windows-oriented; needs the separate douyin-mcp binary (yunsur/douyin-mcp releases, path set via dy_config mcpExe) and an Edge/Chromium login; replying needs a logged-in browser on a CDP port; publishing needs extra credentials most accounts lack.

Continues work across coding agents inside DeepSeek Harness: six sessionflow_* tools query a local session index built by sessionFlow to find past work, show where the current project left off, and hand the goal, files and open items to the next agent. Requires the separate sessionFlow core, installed from its GitHub repo. Everything stays local — no cloud, no telemetry.

Model-linked AI personas and desktop pet for DSH, with shared world lore, separate editable memories, task animations, usage statistics, optional AI diaries and idle-time diary consolidation. The native pet window is Windows x64 only; sleep consolidation spends tokens in the background. Before installing or updating, close the visible desktop pet and notification bubble by choosing Close All (全部关闭) in the context menu; otherwise, files in use may cause installation to fail.

Requires the ZCode CLI installed and signed in. Relays the ZCode CLI agent into DeepSeek Harness as a model provider. A resident app-server session streams each turn, and the model catalogue is read from the CLI at runtime, so context windows, image support and provider routes follow the installed CLI and account. Stable 0.5.1 declares DSH compatibility through engines.dsh; ZCode CLI 3.16.3 is the documented reference version. Tool permission requests are denied by default; unknown approval or permission methods are always denied, and full-auto requires an explicit opt-in. DSH approval UI does not mediate this separately spawned app-server process, and the policy is not an OS sandbox.

Model settings panel for DeepSeek Harness: set the default model for new sessions, plus separate provider/model/reasoning-effort overrides for subagents and goal rounds, with live reload.

Separate font slots for content, code and terminal text, plus an interface font, an interface-size stepper and an inline-code size stepper, with line-height and letter-spacing controls. Typography only — it never touches colour.

Shows JeV-selected task plans, progress updates and stage summaries in DSH chat, with native translation or lightweight summaries. Requires a JeV key; the Jev service is called externally and may bill. and hierarchical serial/parallel task flows.

Predicts your next message after each turn and shows it as gray ghost text in the composer: Tab takes the whole line, Alt+Right takes one word at a time, Enter takes it and sends, Esc dismisses, and Alt+R asks the model again without repeating the old one. Typing a few characters completes from prompts already sent in the session, Up in an empty composer recalls the last one, and a plugin-page form sets the provider, model, reasoning effort, per-key toggles and generation limits.

A no-limit Texas holdem table where you are the only human. Eight seats: you plus seven LLM agents written on AI-founder personas (Altman, Dario Amodei, Musk, Liang Wenfeng, Jensen Huang, Lei Jun, Zhang Yiming). Each agent bets through the currently selected host model and falls back to its own heuristic style when no model is available; every agent only ever sees its own hole cards, because the prompt is built from that seat alone. A hand ends by revealing the winner hole cards, with a flip animation replayed on every community card, and a rail keeps a live action-and-table-talk timeline. LAN mode (off by default, single-machine play is unaffected) lets another install on the same network join this very table: the host shows a six-digit room code, UDP broadcast discovers nearby tables, and a joiner randomly takes over one bot seat, with the seat handed back to its character on leave or after twenty seconds of silence. The room code is never put on the wire and every snapshot is generated for one viewer seat, so nobody, not even the host, can read another player hole cards. Fork of BubblePtr/dsh-holdem (MIT), credited in the README and in the UI.