Plugins

Retransmite las solicitudes de aprobación y preguntas del agente a canales de iMessage / Email / WeChat y las resuelve respondiendo con el número de solicitud (#N 批准 / 拒绝 / 回答).

Mensajería bidireccional de Slack (notify/channels/inbox/reply/health) sobre Socket Mode, sin necesidad de callback público.

Bundles 19 short-video production skills (1 entry point, 1 orchestration, 17 atomic) into the agent skill catalog: Chinese TTS pronunciation fixes, text-to-image and text-to-video, image panning, composition, covers, media verification, data review and four-platform publishing. Ships skills and scripts only, so a runnable pipeline still needs ffmpeg, Python 3 + Pillow, Node.js and playwright installed locally, your own Bilibili biliup credential and WeChat Channels / Douyin / Xiaohongshu login states, and the placeholder values under skills/*/scripts/ filled in with your own. An installer's own skill of the same name keeps precedence.

Comunidades estilo Discord dentro de DSH, con canales, roles y permisos, búsqueda de mensajes y opción de compartir o clonar sesiones.

Añade al lateral de DeepSeek Harness Web un indicador de solo lectura con la versión DSH activa, canales npm latest/next/alpha y etiquetas de compatibilidad, más un comando de actualización solo para copiar.

Drive a local DeepSeek Harness agent from QQ and other IM channels through AstrBot: send tasks with /dsh, continue by quoting or @-mentioning the bot, answer approvals and ask_user_question prompts from chat (in parallel with the DSH web UI), and get results, inline images and file cards back. Ships session / workspace / model / permission commands, /compact and /last recovery, three progress-display modes, and group-shared or per-user session scoping.

Envía tarjetas de aprobación y preguntas de DSH a canales de mensajería instantánea (WeChat primero) y las responde desde el chat, con una consola de sesiones, seguridad por canal y un servicio abierto de push.

Tareas programadas del Agent de DeepSeek Harness con pruebas de extremo a extremo obligatorias, historial de ejecuciones y entrega bidireccional a través de nueve canales de mensajería.

Analista financiero y operativo de compañías de seguros — solvencia, finanzas, inversión, canales de distribución y comparación entre pares con cálculos reales.

Integración del bot oficial de QQ (q.qq.com) para DeepSeek Harness: chatea con el agente completo desde chats privados, grupos y canales — conexión larga WS (latido / reconexión / RESUME), aislamiento de sesión por chat, preset de agente estándar, botones de aprobación en línea con /revoke, comandos de barra, lista blanca a prueba de fallos y credenciales vía el dominio credentials.

Controlador remoto nativo de Discord para DeepSeek Harness: controla sesiones persistentes de agentes de programación desde MD, canales de servidor con mención obligatoria e hilos, con comandos slash, actualizaciones de progreso, aprobaciones, preguntas estructuradas y adjuntos de imagen y texto.

Kit de visión para DeepSeek solo de texto: herramienta `vision` invocable por el modelo, adaptadores contenedores para deepseek/opencode-go (v4 flash/pro), cuota de Antigravity IDE (default, flash/pro) / cualquier VLM compatible con OpenAI / Gemini / canales locales de Ollama, memoria de evidencias con rehidratación por compactación, caché de hash de contenido y un panel de cliente bilingüe.

Peer channels between conversations at the same level: user-granted, symmetric, with durable grants that survive a restart and burst messages merged into one ordered delivery.

Two-level model routing: pick the best model group first, then the best channel within that model; a failure switches channel before switching model. Preference mode pins one model across its channels, a status bar under the composer shows the live model, channel health and the day's token usage, and a speed/intelligence report can be imported as the routing prior. Exposes a model_orchestrator tool and a /route command.

Give the agent a talking face: seven tools that drive a self-hosted Mynah realtime digital human — speak (queued or interrupting), play a gesture clip, interrupt, list live sessions and channels, check health, add text to its knowledge base.

Adds a Forget action to every session row menu, confirmed by a second click in the menu, that removes the session from the sidebar and from disk: running work is stopped, workspace, archive and pin records are detached through official channels, the log directory and projection-cache entries are deleted, and a revive guard re-deletes anything a late write or a lingering handle recreates; memories, attachments and other sessions are left alone.

Tidy the model list of DeepSeek Harness: hide any model from the selector, rename models and channels while keeping the provider billing rate, and arrange both with arrows. Search, per-provider batch toggles, back to top, one-click restore. Display only — no provider configuration is rewritten.

Personal coding assistant that schedules, follows up on and verifies local Codex or Claude Code tasks from DSH, with WeChat, WeCom and Feishu remote channels.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

Three independent language channels for model output — tool-call descriptions (every tool-call card title, including run_code in PTC-style presets), thinking, and replies — each set to follow the web GUI language, force a specific language, or turn off (default: only descriptions, following the GUI). One global runtime-context prompt directive on the host; the client half reports the GUI language; a Settings plugin card switches the modes.

Channel-grouped session view injected into the sidebar — Workspace/Channels tabs with live-running dots, archived grouping, orphan tagging, built purely on official extension surfaces and serving as the RFC-0001 reference implementation.

Conecta nueve canales de IM y una AI Office pública a un DeepSeek Harness local. Compatible con Feishu, WeChat, DingTalk, WeChat Empresarial, QQ, Slack, Telegram, Discord, WhatsApp y AI Office. Bifurcación de @xmanrui/dsh-im — corrección de medios HTML en Feishu (privado/personalizado).

Union IM bridge for DSH — an independent implementation uniting the capability sets of community peer plugins (xmanrui/dsh-im, MichengAI/dsh-im-connect). Drive your agent session from 15 channel adapters across 12 platforms (including email; WeCom/DingTalk/QQ each contribute two: bot + self-built app or notify tier) — WeChat (official iLink QR bind), Feishu/Lark (long-connection + streaming cards; the voice tier requires system ffmpeg), Telegram, Discord, WeCom intelligent bot & self-built app (signed callback), DingTalk (stream + AI Card and custom-robot notify), QQ official bot (plus notify tier), Slack (Socket Mode), WhatsApp (Baileys QR pairing; the dependency ships as an optionalDependency of the plugin package), Matrix, iMessage (macOS only), Email (IMAP/SMTP thread routing). The cross-version narrow waist auto-adapts settings gen1/gen2/gen3 across hosts 0.1.2-rc.1→0.2.1-rc.2 (12-tag enum; rc.2 verified by a real desktop-profile install with double read-back) using capability probing only, never version branches. In chat: a 25-command panel, tool-approval and question loops answered in the originating chat (deny-by-default, initiator-only, 5-min expiry), image/file input gated on host model metadata, deliverable file return, a delivery log with bounded retry (uncertain is never re-sent), proactive delivery and fragment composition. It also splits the native sidebar into self-owned Tasks / Channels tabs (standing down entirely when another plugin already owns the slot), registers an `im-concise` agent preset plus reply sanitisation that keeps GenUI fences and raw HTML out of text-only chats, renders `svg` fences to PNG images, guards model choice with an allowlist, and mirrors each turn's final answer to notify channels via `/relay` (addressed by account ID or alias, never guessed on ambiguity). Secrets are one-way into the vault and never echoed back. npm: `dsh-im-union`.

Plain-language trust dashboard for the dsh trust family: aggregates the nine channels (injection interception, write denials, egress blocks, custody-chain verification, tool-surface and prompt drift, leftover scans, forgotten compaction constraints, profile composition) into one right-sidebar panel with a single status light and event cards that translate engine jargon into sentences a non-security user can act on; the read and egress engines run from the package's own npm dependencies so those channels work even without the sibling plugins, and absent plugins simply show as not installed.