Plugin

Automazione di JLCEDA Professional (EasyEDA Pro): dà all'harness IA le "mani" per lavorare sulla canvas di progettazione — un insieme di azioni tipizzate per schemi/PCB, unificate in tre interfacce: CLI, Agent Skill e stdio MCP. Porta avanti il motto di JLCEDA: "non puntare al profitto dalla vendita di schede, ma avere come missione la formazione di ingegneri cinesi".

Applica branding OpenQuantum, metadati del browser e asset PWA all'interfaccia web nativa di DeepSeek Harness.

Revisione offline degli schemi per EasyEDA Pro, esposta a dsh come quattro strumenti: report di controllo una tantum, scheletri di architettura, un controllo di installazione e un ponte verso l'editor live che privilegia azioni in sola lettura, il tutto guidato dalla CLI locale boardwise.

Animaletto desktop viola e bianco che si aggancia al bordo dello schermo e mostra in tempo reale temperature di CPU, RAM, GPU e NVMe con informazioni 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.

Strumenti human-in-the-loop (`human_task` / `human_task_ready_check`): mettono in pausa l'agente finché l'utente non compie un'azione reale o riporta un'osservazione (operazione GUI, test di gioco, verifica visiva, controlli hardware), vincolati dal consenso della sessione e da un controllo di presenza AFK, restituendo un risultato JSON strutturato tramite una finestra di dialogo web per l'attività.

Raggruppa segnali da arXiv, laboratori di prima parte, artefatti ufficiali, produttori hardware e X con consenso in bundle di prove versionati, e vincola la riproduzione a livello di affermazione a comandi, artefatti, metriche e verificatori.

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.