Plugins

Unofficial Zhipu Qingyan (chatglm.cn) web provider — run DeepSeek Harness on web-app credits with a login token, streaming and prompt-bridged tool calls included.

Native DeepSeek Harness plugin: feeds every prompt into the local agent-feedback-loop capture pipeline and injects compiled recurrence rules back as context.

Connect Notion from the GUI with OAuth 2.0 + PKCE — official Notion MCP, no integration token.

Bidi-safe RTL rendering for mixed Arabic and English text, a full Arabic interface pack (3,307 strings) registered through the DSH locale service, and three thmanyah cuts — Sans for the interface, Serif Text for reading, Serif Display for headings — placed behind whatever font the app itself is set to.

In-terminal plugin manager for dsh-tui: list installed plugins and bundles, and install, remove, enable or disable them without leaving the TUI.

Adds a Download button to DSH Web GUI delivery cards, so files delivered with present save straight from the browser.

让 DeepSeek Harness 以 WSL 子系统作为会话的执行环境：shell、文件读写与命令执行均在子系统内完成，目录选择器与 GUI 终端同样定位到子系统路径，并通过子系统内的 bubblewrap 对命令进行沙箱隔离

Prompt library stored in the plugin config, with a Settings page and a composer picker: the ticked prompts are injected into every model step of that session, and a subagent inherits the selection of its nearest ancestor session.

One-tap connect Agnes language, image and video models into DSH (off by default), with image recognition and thinking level filled in automatically. After signing in to the Agnes console (re-login uses AGNES_PASSWORD), you can see the quota windows (5-hour requests, weekly requests, daily images, video), account-wide cumulative usage, and a usage pill beside the input box. AgnesCode desktop models can be connected too (Windows only), re-reading the desktop app login when the token expires, with rate-limit hits backing off on their own.

Image and video wallpapers for the DSH web workspace: auto-detected GIF/APNG/animated WebP/PNG/JPEG/MP4/WebM backgrounds with blur, brightness and dimming, tint-following UI, per-component transparency, and one-click preset wallpapers.

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Image generation with a sidebar gallery page and three agent tools (paint_image, paint_images, edit_painting); preset providers include ModelScope, Google Gemini, OpenAI, SiliconFlow, Volcengine Seedream, Alibaba DashScope, xAI and Zhipu, plus any OpenAI-compatible endpoint, each with its own proxy setting.

Windows desktop control exposed as native DSH tools - whole-screen and single-window capture (the window one goes through PrintWindow, so a covered window still captures), click, drag, typing, keyboard shortcuts, scrolling, window management, pixel and window polling, and UIA queries that can invoke a control or read its value instead of clicking coordinates. 13 tools over a PowerShell 7 child process; no MCP server, no resident process, no API key.

Windows 2000 desktop skin for the DSH Web GUI: metric-accurate grey chrome, two-tone gradient title bars, 1px bevels, square corners, 16px scrollbars, and the pixel font it renders with served by its own host route.

Niubash-only shell executor and Bash-dialect teaching for DeepSeek Harness (dsh 0.2.0-rc.2, and the 0.1.7-rc.x line it shares its shell seam with): every ctx.shell execution runs as `niu -c`, PowerShell/cmd/WSL/nu handoffs are refused, PowerShell habits a

DeepSeek Harness 输入框的下一句建议：助手回复完，空输入框里出现一句灰色建议，按 Tab 填入。Prompt suggestions for the DSH composer.

Real-time disaster alerts for DeepSeek Harness: Japan earthquakes (P2PQuake) and JMA EEW, tsunami and weather telegrams, global earthquakes (EMSC/USGS) and NOAA tsunamis, mainland China earthquakes (CENC via Wolfx) plus nmc.cn rainstorm and geological-hazard warnings, and US/Canadian NWS and ECCC flood, rainfall and storm-surge warnings — matched against your watch regions and thresholds.

Counts completed compactions per session in a floating window and warns only after repeated compactions plus extra token spend or high context occupancy, with all three thresholds adjustable in Settings.

OpenBKN business knowledge-network context for DeepSeek Harness

Host-level proactive wake-ups for DeepSeek Harness: let the model schedule its own alarms (once / interval / cron with random jitter), wake cold sessions on time, gate model-initiated follow-ups with quiet hours and a daily budget, and reclaim silent wake

DSV4.1 reasoning support with multimodal context and bounded artifact acceptance for DeepSeek Harness

Model attribution panel for the dsh web chat — local, zero-network structural fingerprinting (template token leaks, glitch canaries, tokenizer usage-vector matching) that scores which of 29 AI vendors a session's responses most resemble, with a per-claim evidence ledger and a 12-probe active battery.

Web search provider with switchable engines, several usable without an API key (Bing, DuckDuckGo, SearXNG and others) and a fallback order between them; adds multi_search, platform_search, image_search with an in-chat image wall, page_images and save_images, plus a settings page for engines, keys and per-engine proxy.

Connects the Xiaozhi voice assistant to DSH Web over MCP: DSH is the tool provider, weaving 35 DSH Web endpoints into 16 voice-friendly tools for workspaces, sessions, chat, models, settings and files — outbound WebSocket to the Xiaozhi MCP access point by default (no public IP or port forwarding needed), several devices bound at once, plus a DSH settings page with live status.