Plugins

Automatización de JLCEDA Professional (EasyEDA Pro): le da al harness de IA las "manos" para trabajar en el lienzo de diseño — un conjunto de acciones tipadas de esquemático/PCB, unificadas en tres interfaces: CLI, Agent Skill y stdio MCP. Continúa el lema de JLCEDA: "no busca lucrar con la venta de placas, sino que tiene como misión formar ingenieros chinos".

Aplica la marca OpenQuantum, metadatos del navegador y assets PWA a la interfaz web nativa de DeepSeek Harness.

Revisión offline de esquemáticos para EasyEDA Pro, expuesta a dsh como cuatro herramientas: informes de comprobación puntual, esqueletos de arquitectura, un diagnóstico de instalación y un puente al editor en vivo que prioriza acciones de solo lectura, todo impulsado por la CLI local boardwise.

Mascota de escritorio morada y blanca que se acopla al borde de la pantalla y muestra en tiempo real temperaturas de CPU, RAM, GPU y NVMe, con información del hardware.

DSH hardware sandbox plugin: assemble a 3D scene of ESP32 / BME280 / PIR / LED components with protocol- and voltage-checked port wiring, run real Python project code in the loop against simulated I2C/GPIO hardware with fault injection, let networked device simulators report over HTTP to a real backend (validated end-to-end against a live seat-reservation system), observe a real device read-only and map its state onto the scene, and add support for new boards through data-driven pin definitions. Ships 16 hw_* agent tools plus a bundled SKILL.md.

Deep-sea whale-blue reskin for the DSH Web GUI: 14 theme tokens in light and dark, five whale-tail-maid placements, a clock and weather card, and a collapsible hardware readout (CPU, memory, GPU, per-drive temperatures via HWiNFO). No backdrop image is bundled; drop your own in. MIT code, MIT character art.

Clusters arXiv, first-party lab, official artifact, hardware-vendor, and opt-in X signals into versioned release evidence bundles, then gates claim-level reproduction on commands, artifacts, metrics, and verifiers.

Herramientas de humano en el bucle (`human_task` / `human_task_ready_check`): pausan el agente hasta que el usuario realice una acción en el mundo real o devuelva una observación (operación de GUI, prueba de juego, verificación visual, comprobaciones de hardware), sujetas al consentimiento de la sesión y a una comprobación de presencia AFK, devolviendo un resultado JSON estructurado a través de un diálogo de tarea web.

Agrupa señales de arXiv, laboratorios de primera parte, artefactos oficiales, fabricantes de hardware y X con consentimiento en paquetes de evidencia de versión, y condiciona la reproducción a nivel de afirmación a comandos, artefactos, métricas y verificadores.

macOS only: holds a PreventUserIdleSystemSleep assertion (caffeinate -i -w <host pid>) while any DSH session runs, and releases it when the last one stops, so a long turn is not cut off by idle sleep. The display may still turn off. It keeps holding through the maintenance phase, where Agent.status reports idle and a long manual /compact runs, via the compaction/start and compaction/end events. It reconciles against ctx.agents.list() every 60s, so a session already running when the plugin is hot-reloaded is picked up at once instead of at the next turn boundary. A failed hold retries with exponential backoff capped at 60s and never gives up; release escalates from SIGTERM to SIGKILL after 2s, and -w lets caffeinate exit by itself if the host dies. No browser half — configured through the profile patch. 51 tests, including two that read pmset -g assertions on real hardware.

Remote operations for the DSH Web app: manages SSH servers, collects hardware and process metrics, inspects logs with a read-only AI pass, and deploys a Git repo over SSH using git pull --ff-only plus a health check. Credentials are AES-256-GCM encrypted. Linux and macOS hosts; no Windows support.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.