Plugin

Split-screen workspace for the DeepSeek Harness web GUI - chat with several agents side by side in panes that look and behave exactly like the stock conversation: drag-to-split, live sessions with queued messages and in-pane ask_user/approval cards, per-pane view tabs (Chat/Trajectory/plugin views), a compact TUI composer mode (Alt+T) and pane-focus shortcuts. Requires DSH 0.1.5+.

Custom script manager for DSH: turn verified operations into reusable scripts that run directly via /script or register as agent tools, with parameterized scripts, declared expected outcomes, and execution history.

All-in-one combo patch for STARDUSTLC's 18 DSH plugins: one command injects shared default configs across office, media, DevOps and notification presets; each component installs directly via a one-line add command (flat design, no git subdependencies).

Install and call external Agent CLIs (Codex, Claude Code) from DSH without touching the system install. Each CLI gets its own Provider, model, reasoning effort and permission preset, callable directly or as a native subagent.

Drag documents into the dsh web chat; the agent reads them directly from the local filesystem and the right sidebar lists the outputs and file paths.

Controllo servizi DSH: gestisce ciclo di vita systemd, configurazione e diagnostica tramite `dsh --profile ctl`.

Accedi direttamente al tuo account Cursor all'interno di DeepSeek Harness e utilizza il tuo abbonamento Cursor — nessuna API Key necessaria e nessuna dipendenza da Cursor IDE o Cursor CLI.

Durante i lunghi periodi di riflessione dell'agente, pubblica un messaggio di notizia calda o di promemoria direttamente nel flusso della conversazione.

Compagno di pausa: un mini player fluttuante che trasmette in streaming video Bilibili (player nativo, danmaku, commenti, ricerca) e si mette in pausa quando il tuo agente ha bisogno di te, riprendendo esattamente da dove avevi lasciato.

Cambio skin con un clic per le impostazioni Web DSH: rileva automaticamente i temi installati, ne mantiene esattamente uno attivo alla volta e ritorna all'aspetto ufficiale quando tutti sono disattivati. Le modifiche si applicano istantaneamente e sopravvivono ai riavvii.

Pet da scrivania nativo per DSH che segue l'attività dell'agente, supporta i pacchetti pet di Codex e importa pet approvati direttamente da Petdex senza la sua CLI.

出口管制物项核对（按管制清单、最终用途与许可证核对台账齐备，仅提示差异，不作出定性结论）

Removes sandbox_permissions / justification arguments that cannot widen the call's current sandbox mode, so calls no longer fail with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "danger-full-access" mode'. GPT models tend to fill these optional fields on every call and pick workspace-write, which is narrower than danger-full-access. Runs in tools/pre-execute: compares the requested mode with the mode the session's sandbox policy resolves, and drops the fields when the request is the same or narrower (also drops a lone justification). Also understands the values GPT carries over from Codex's own shell tool: null, empty and use_default are treated as no request, and in a danger-full-access session any value (including require_escalated) is dropped because nothing is wider. Real widening requests, unknown modes and tools that do not advertise DSH's escalation schema are left to DSH core. Never widens permissions. Configurable tool list (default bash, pwsh, write, edit, run_code). Zero dependencies.

Skill browser and switchboard for the DSH web GUI: a sidebar entry lists skills from configurable source directories as cards, clicking a card opens the full SKILL.md, and the per-card switch writes disable-model-invocation and registers or removes that skill in the agent skill catalog, so the model can load exactly the skills that are switched on. It also recognises WorkBuddy expert-team folders and shows avatar, tags, quick prompts and members, registering its lead prompt as a skill when switched on. Source directories are editable in the panel.

Adds Codex-like no-project drafts with per-project draft switching and date-and-topic directories created on first send; requires the native bridge patch for DSH Desktop 0.2.0-rc.2 on Windows.

Export the current session to clean Markdown from a button in the session header, through the native save dialog, with a CLI and an HTTP route over the same renderer; reads session logs directly (formats v0, v3 and v4) and declares no @deepseek-ai peer dependencies.

Extract text from an image or PDF, reading a born-digital text layer directly and falling through to a configured OCR engine for scans.

Aqua glassmorphism theme for the DSH Web UI, adapted to DSH v0.2.x and desktop v0.22.3+: the header, sidebar, composer, stats line and trajectory view become frosted glass panes over a live WebGL fluid board or an image/video wallpaper, with mica and compatibility layouts, adjustable blur, frost, hue and brightness, marine decorations (particle whale, fish, mesh, cursor glow), a one-click reset-to-defaults button, and a master switch whose off state restores the stock UI exactly; adapted from WYH66666666's original (0.1.x) and du-u-uck's 0.1.1-rc.2 port.

Restart button for DSH Desktop placed directly above the sidebar account button.

Relays the ZCode CLI (the client-bundled coding agent) into DeepSeek Harness as a model provider: a resident app-server session injects the Start Plan account and signs each request with the OAuth plan token, so model requests burn ZCode Start Plan / Coding Plan quota directly — real streaming, image input, per-session resume, no API key.

A glass-material appearance for DSH: translucent composer, dialogs, menus and code blocks — one switch in Settings, off restores the stock look exactly.

fal.ai native image generation for DSH: a FAL_KEY settings card that follows DSH's language (zh/en, English default) plus Agent tools (fal_generate_image async / fal_edit_image / fal_get_image_task / fal_list_image_models) that call queue.fal.run directly

Sign in with a ChatGPT account and view Codex subscription usage directly in DSH Web's model settings, with browser or device-code OAuth.

AlphaRSI — three-role self-improvement loop that evolves the training recipe of alpha sequence models. Operator runs walk-forward, Evaluator grades with OOS RankIC, Refiner proposes hyperparameters via TPE Bayesian search; only strictly-better recipes are kept. Offline one-command run, data bundle shipped with sha1 reconciliation, GPU auto-detect. Ships one skill.