Plugins

Remote access & authentication for DeepSeek Harness web UI: account/password login gate, MFA (TOTP), signed session cookies, role-based access, in-browser directory picker, account management settings, fully localized in English and Chinese.

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.

Health checks for DSH plugins: manifest/patch/entry/build/pack/install verification, model-callable plugin_check, profile host-shadowing + BOM detection, environment diagnostics, and poison preflight.

Browse, enable, disable, and manage Agent Skills from Claude Code, Codex, OpenCode, Gemini, and custom directories in the DSH settings panel.

Continual self-refinement loop: persistent memory, periodic review-and-refine, cross-session shared knowledge, and automatic rollback through a model-callable harness_refine tool.

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.

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.

Bridge DSH agent sessions, tool calls, and approvals to the CodeIsland macOS notch panel over a Unix socket, with in-panel allow/deny.

Publish articles to CSDN / Juejin / CNBlog directly from the session, no external server.

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

Virtual product team agent preset: user-led conversation walks you through the full 12-step pipeline from idea to shipped, promoted and operated product, with staged gates and per-stage skills.

The DSH plugin-development knowledge base as an on-demand agent skill: official constraints, task workflows, API reference and community gotchas, installed with the bundle so the agent can look things up while building a plugin.

Workspace-safe Office tools for agents: create/read Word, create/read/update Excel, and create/read PowerPoint decks with PNG/JPG/GIF image placement.

Voice input for DeepSeek Harness: speak into the microphone and the recognized text is submitted as a normal chat message, via local or browser speech recognition.

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

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.

RSS/Atom subscription management and parsing (rss_list/add/remove/fetch/check), persisted to settings.

Seven video tools (probe/cut/concat/encode/subtitle/extract/gif) on the official subprocess service: shell-free argv, zero runtime dependencies.

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. Context-aware by default: the recent conversation is injected as background and may enrich the ## Context section. Long outputs resume from the truncation point with auto-expanded budgets; validated results are cached (identical requests cost zero model calls); a unified call budget bounds worst-case cost. Composer ✨ one-click optimize, undo, cancel and 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.

Learning Mode agent preset: a coding agent that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style; installable via dsh plugin add (dsh-learning-mode on npm).