Plugin

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.

System-level desktop notifications: turn-completion and workflow-end banners, plus a modal alert when an approval is needed (macOS osascript / Linux notify-send).

Desktop notifications and tones when a task finishes, waits for approval, or errors — native on macOS, Windows and Linux with zero runtime dependencies.

Esporta eventi DSH di solo metadati — turno, modello, strumento, approvazione, nuovo tentativo ed errore — verso Tuning Engines per tracce governate, valutazione delle policy, analisi dei costi e revisione delle Work Session, con una coda di ripetizione su disco.

Injects allowlisted GitHub Actions and GitLab CI run metadata into agent context without reading logs, credentials, or provider APIs.

Git and GitHub panel for the DSH web profile: stage/unstage/discard/diff, branches, commit, push/pull/sync, log, file browser, workflow board, and GitHub OAuth with PR creation.

Event-sourced cross-session work ledger: register, track and settle tasks with full audit history, kanban export, and a board digest injected into every model turn.

Disk-persisted execution planning for DSH: milestone/step state machines, dependency gating, an audit event stream, and a deterministic completion gate via dsh tools, CLI, or skill.

Main-brain orchestration preset: delegation-first persona, root-session execution gate, and portable AI-LAW rule skill.

DSH project scaffold preset: strict 5-phase init runbook, engineering standards and six runnable starter templates (node-ts / react-vite / python / go / spring-boot / monorepo).

Pubblica un documento HTML come link condivisibile che si apre con un tocco e appare come scheda nelle app di chat; pubblica, aggiorna ed esporta in PNG/PDF/Word.

Real-time duplex voice over Volcengine streaming ASR/TTS: agent reply narration, barge-in, wake word, live captions, 30 Chinese voices and a reply-first acknowledgment; builds in the DSH monorepo.

Give text-only models vision: a describe_image tool that delegates images to a vision model from your dsh model list over the harness's own LLM runtime.

Lets a text-only DeepSeek agent read images in the same session by delegating to a vision-capable subagent, with send-time image-to-path conversion.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a locally running Unsloth Desktop (Unsloth Studio) server through unsloth_run and unsloth_vision tools; pure HTTP client, never spawns or owns processes.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a local KoboldCpp (llama.cpp) server through koboldcpp_run and koboldcpp_vision tools, with on-demand server lifecycle management.

OCR locale per le immagini allegate tramite il motore integrato di Windows (Windows.Media.Ocr): al modello viene inviato solo il testo riconosciuto, mai i byte dell'immagine; il passthrough della visione è opzionale (opt-in).

OCR locale per le immagini allegate tramite Tesseract: solo il testo riconosciuto viene inviato al modello, mai i byte dell'immagine; il passthrough vision è opzionale.

Give your text-only model eyes - chat image attachments are auto-described via a vision model (default prompt), with iterative re-parsing through model-generated prompts when details are missing; system/custom model modes + GUI config panel, key-safe secret handling, and a small host patch for DSH 0.1.0-rc.6 (see repo README).

Two-tier image reading for text-only models: fast local OCR (RapidOCR, offline) first, vision-model fallback (modlens).

Transparent image guard for text-only routes: paste images without the 400 session deadlock, plus a vision_analyze tool for OCR/PDF/docx/pptx/video.

Image-to-text input for the Web UI: paste or drag an image and it is transcribed into structured text and sent, giving text-only LLMs image-input takeover (OpenAI-compatible vision API).

Give DSH text-only models vision: an image/OCR/document recognition skill (race pool → custom channels → local) plus an idempotent host patch so image messages reach the model.

Real-browser automation for dsh via an MCP server (Playwright core): navigate, click, fill, type, screenshot, and act on accessibility snapshots with numbered references - all 22 web_* tools re-exposed to the harness over stdio.