Plugins

DSH web-GUI pet runtime that renders any Codex spritesheet-atlas pet (v1/v2) as a draggable overlay: drag/wave/jump, v2 mouse-tracking eyes that follow the active mouse, live agent-status poses, progress bubbles, and an in-GUI atlas importer; ships one original CC BY-NC demo pet (nastya), and user pets live in ~/.dsh/pets.

Multi-pet companion for the dsh web GUI: a registry-driven floating pet that reacts to model activity.

Native tavern management panel for DeepSeek Harness: multiple character cards, multiple worldbooks, switchable presets.

Password + TOTP two-factor authentication gateway for the dsh web UI: every HTTP request and WebSocket upgrade is refused until login, with per-source lockout, global rate limits and one-time backup codes.

Vets third-party plugins before you trust them: static scan for malicious patterns (exfiltration, credential access, obfuscation, persistence) and over-privileged path use, transitive-dependency coverage, official-package hash baseline for supply-chain tamper detection, and an optional plugin-tool call gate.

Fine-grained permission gateway: per-category tool-call review (outside-workspace directories, commands, file read/write, subagents, repeated actions) with global & per-project allow/deny exceptions, quick-tool defaults, custom rules, a bilingual approval modal with inline diff details, custom rejection reasons and a sandbox-upgrade flow.

Agent security guardrail: intercepts and audits every tool call, requiring human confirmation on sensitive operations.

Settings -> Plugins switchboard: every loaded plugin card shows its package description and runtime phase, with fuzzy search and start/stop toggles that never rewrite config files.

One-click restart button for the DSH Web UI: a sidebar footer button that restarts the dsh web process with a single click and persists across the restart it triggers.

Connects dsh to Weixin, with arbitrary file sending support.

Desktop notifications for run completion, model questions, and approval requests with per-platform system sounds, zero runtime dependencies.

Feishu (Lark) bridge for DeepSeek Harness: one-command install, streaming progress cards with a tool panel, ask/approval button cards, attachments, and proactive feishu_send pushes.

Official Remotion skill ported to DSH: programmatic video with React (animation/audio/captions/3D/charts/fonts, 38 rule files).

Adds a summonable domain-expert roster that runs as subagents while the parent session keeps the task and final answer.

CloakBrowser-powered native browser tools with per-agent isolated sessions, bounded snapshots, ref-based interaction, screenshots, and safe routing.

Zero-dependency browser control: drive a real headless Edge/Chrome over CDP with 8 `pilot_*` tools (navigate/click/type/keys/eval/screenshot) plus a live draggable cockpit panel in the Web GUI - text-first snapshots for text-only models, no Playwright, no API key.

One-click backup, export, import and migration of a whole DSH config: settings, plugins, MCP, skills and workspaces. Secrets are excluded by default and, if you opt in, are AES-256-GCM encrypted rather than written in the clear; imports preview first and auto-backup with rollback, profiles hold multiple setups, and remote sync pushes portable config through a private Git repo with secrets excluded.

Optimize a raw instruction into a professional prompt through the harness llm service — four-section (Role / Task / Context / Format) or a headerless plain-text style. Situation-aware (1.3.0+): the instruction and conversation are parsed into role / task / goal profiles, so the role stays on-task and goals/constraints are preserved (goal-alignment retry, per-session goal carry-over); roles follow an identity + capability + behavior formula with per-task-type writing tips (1.3.3-1.3.5). Context-aware by default; long outputs resume with auto-expanded budgets; validated results are cached (identical requests cost zero model calls); stream early-stop and an optional fast profile cut latency (1.3.6). Composer ✨ one-click optimize / undo / cancel with a token-cost hint; prompt_optimize tool (optimize + iterate), auto-optimize hook, auto-detected zh/en role document.

Zotero library tools via the local API (no API key): search items/collections, read metadata and abstracts, list attachments, read full text (parses PDFs on the fly when Zotero cache misses), download PDFs, and manage notes.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

In-place conversation rewind in the same session window without forking (Claude Code /rewind semantics): a per-message ↶ button cuts the model context back to any user message, with an optional Claude-Code-style file restore from disk-persisted before-backups.

Use third-party subscription accounts in DeepSeek Harness: chat, image understanding, image generation, and image editing with the models your subscription covers, with available models and reasoning levels synced from your account; currently supports OpenAI/ChatGPT subscriptions, more providers planned.

LLM provider that runs the locally installed Claude Code CLI as the model backend, so requests go through an existing Claude subscription instead of a metered API key; native tool calls are bridged over MCP.