Plugins

Caddy forward_auth administrator login for DeepSeek Harness Web, with Argon2id passwords, revocable sessions, bilingual UI, and a native sidebar sign-out action.

Rules, commands & skills manager for dsh: /rules slash command, settings panel with visual rule editing (add/edit/disable/delete, free-zone support), user-defined custom commands with {input} arguments, skill management, and automatic backup & one-click restore of AGENTS.md.

Run Stata through DeepSeek Harness: the native Stata AI Skill service auto-starts with DSH (macOS/Windows binaries bundled), so you can run regressions, do-files and econometrics workflows with no manual setup.

Dockable Markdown preview for the DSH Web UI: side-by-side with the conversation, a per-session recently-read .md list, local relative-path images render in place, and clicking an in-chat .md reference previews it instead of launching the system editor; follows the shell light/dark theme.

Native image attachments for text-only DeepSeek in the Web GUI: pasted or dropped images appear as thumbnails in the session, and before dispatch the host reads them with the free Zhipu GLM-4V-Flash vision API (glm-4v-flash fallback chain) and substitutes the description, so DeepSeek answers about the image while the original is kept in history.

Registers Baidu, Doubao, Tavily, and Exa backends into ctx.web so official web_search can use them, and routes web_fetch through Tavily Extract or Exa Contents when that backend is active.

Exact-profile control of your real logged-in Chrome browser: an MCP server plus MV3 extension and authenticated localhost bridge for tabs, locators, file injection, media export, and durable scroll capture, with no debug profile or remote-debugging port.

Reference verification for DeepSeek Harness (参考文献真实性检查器): the reference_checker model tool checks a paper's bibliography (.pdf/.bib/.tex/.txt or pasted text) against Crossref, OpenAlex and arXiv, reports found / partial / not_found / error per entry, and emits corrected citations in the input's style (APA, GB/T 7714, IEEE, Vancouver, MLA, Chicago, Harvard, ACS, BibTeX).

Deterministic AST code graph and architecture intelligence tool for call hierarchies, blast radius, circular dependencies, domain slices, and full-stack API contracts.

A DeepSeek Harness plugin that interviews the user about a project, generates a project timeline / Gantt chart, and exports it as Word or Excel.

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

Query local log files with Chinese natural-language time expressions (e.g. "yesterday afternoon", "3 hours ago") — precise time range, matched lines, ERROR/WARN/INFO level stats, fully offline.

Repair DeepSeek Harness sessions that refuse to load, with a sidebar Session surgeon overlay and dry-run repair.

Per-model proxy routing for LLM requests: selected models go through a proxy (Clash etc.) while the rest stay direct, with automatic retry on transport errors, 429 and 5xx, configured live from the settings page.

Wallpaper Engine integration for the dsh web GUI: scan the local WE library (Steam workshop 431960 + local projects) and use its wallpapers as the page background — image/video/web rendered natively, scene wallpapers as softened static previews — with a wallpaper-design panel (opacity, scope, blur, vignette, fps, parallax, carousel, theme linkage) and agent tools wallpaper_scan/list/set/config.

Analyze usage across models, providers, workspaces, and time ranges — including custom start/end dates over the full retained history — with live cache-hit visibility and separate model and provider breakdowns. Includes a 53-week GitHub-style heatmap, usage streaks, cache-efficiency trends, DeepSeek account balance, workspace aliases, CSV export, and a durable ledger that preserves successfully flushed usage after session deletion and rebuilds incrementally — unchanged sessions are reused straight from the ledger and only newly appended events are folded. Token accounting is explicit: input is fresh (cache read/write and reasoning are separate buckets) and zero-usage replays never overwrite recorded usage. Chinese uses local time, English uses UTC; API access is loopback-only.

Adds a "用量" section to the DSH Settings page that shows your MiniMax Token Plan usage (5h and weekly windows with reset countdowns), per-model breakdown, and video bonus credits; fetches `/v1/token_plan/remains` via a trusted plugin that holds the API key, auto-hides when no key is configured. MIT.

Lets you choose which items appear in the DeepSeek Harness settings left nav.

⭐ Drag-and-drop uploads of any file or whole folders, anywhere in the window; remote-safe — bytes go straight into the session workspace on the server, so a DSH deployed on a remote machine works exactly like localhost.

Windows computer use for DeepSeek Harness: an MCP stdio server over a PowerShell UIA backend exposing 22 desktop tools (UIA tree, screenshots, typed input, OCR, window management, failsafe).

Drive Origin scientific plotting from DeepSeek Harness AI chat via MCP: write data, plot line/scatter/column, export PNG/SVG.

Composer-dock balance/usage readout for DeepSeek, Kimi Coding, OpenCode Go, Zhipu, MiniMax, OpenRouter and OpenAI Codex — provider-based, 2s polling, 5min cache.

World-model research toolkit: inspect frames, name 3D / pixel / latent routes, score pred vs GT, and RSI skills / wm.yaml.

GEO brand audit skill bundle: AI-search visibility, recommendations, citations, competitor presence and content-gap diagnosis across 17+ AI engines (ChatGPT/Perplexity/Claude/豆包/DeepSeek/Kimi/文心一言).