Plugins

Windows desktop control through UI Automation, window screenshots and mouse/keyboard input, with per-session app consent and action approvals.

Windows Computer Use for DeepSeek Harness with 21 tools and verified targeting: controls are addressed through their UI Automation identity and patterns, and numbered marks are checked against the live window before input, so a stale target is refused instead of clicked. A known sequence runs in one computer_batch call, one model round trip; incremental observations, compact receipts (normally no more than about 6 KiB extra) bounded handoff waits (HANDOFF_WAIT_TIMEOUT/HANDOFF_HELD_TIMEOUT as continuations) and the desktop-block cycle boundary plus a deterministic 100 s owner-scoped leave backstop and the host-debug settings client keep context small and prevent a stuck handoff from waiting out the tool deadline. Human handoff, approval modes, a model-visible stop brake and prebuilt native workers.

OpenCode Go subscription models as a DeepSeek Harness provider: re-resolves the live gateway catalog every few minutes, auto-adapts models the built-in table has not seen, and covers streaming, tool calls, image input and subscription usage. A maintained fork of dsh-opencode-go: a clash with the upstream package over the llm-opencode-go settings namespace makes it withdraw quietly instead of failing the whole plugin tree, and an already-claimed opencode-go route makes it serve on opencode-go-plus.

Model Capability Manager for DSH Web: thinking levels, context window, output caps, input modalities, gateway compat presets, EN/中文 UI.

Shows coding-plan usage and balance for 5 AI providers (MiniMax, DeepSeek, Kimi, OpenRouter, Zhipu) beside the composer input, switching with the selected model and reusing API keys configured in DSH model settings.

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).

Composer mic for the Web UI: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.

All-in-one bundle for DSH: the native Windows desktop window (WebView2), DeepEye vision (GLM-4V-Flash), and voice input (mic button) in a single install.

Auto-saves large pasted text as an attachment file in the DeepSeek Harness web input box; with dsh-better-sidebar installed, the paste pill opens the file in the sidebar editor and saves it back.

One-click enter/exit Plan mode for the DSH web input bar, a quick-click shortcut for /plan.

Composer expand/collapse toggle for the Web UI: a ⬆/⬇ button in the composer tool row grows the input to a tall 70vh writing view for long drafts.

Attention reminders: frame badge, tab-title count, and a status-colored whale favicon for sessions waiting for input or finished unopened.

Usage statistics: a usage and reference-cost panel for DeepSeek Harness with today, 7-day, 30-day, all-time and custom ranges aggregated by hour or day; a model filter and a per-model breakdown of requests, input and output tokens, cache, reference cost and share; a model-share card showing the top four models by total tokens with the rest grouped as others; a reference price list generated from opencode Zen and DeepSeek's published rates, with DeepSeek models billed by Beijing weekday peak/off-peak windows and Chinese public holidays; a pricing-match dialog to point an unmatched model at a reference model or type per-million rates by hand; reference cost switchable between ¥ and $ at a fixed 1 USD = 7 CNY; and a yearly heatmap drawn only with theme variables, with no third-party chart library.

Chinese metaphysics (xuanxue) divination panel and agent tool with nineteen systems: eight chart systems (BaZi, Zi Wei Dou Shu, LiuYao, MeiHua, Da Liu Ren, Qi Men Dun Jia, compatibility charts, Tarot) plus eleven quick references (almanac, solar–lunar conversion, date selection, bone-weight fortune, Xiao Liu Ren, horoscope, numerology, life-curve, feng shui, name analysis, an MBTI-style 16-type questionnaire), with ask-driven, report-style interpretation. BaZi adds exact dayun handover dates, annual suiyun hints, "passing-through" (通关), three-book classical cross-reference, four-mausoleum (杂气) month pattern selection and daily "human element" (人元司权); Zi Wei adds 34 patterns, eleven switchable school variants (including an opt-in full 61-star minor-star table that ships the placement verses alongside the chart), chained flying transformations and three-way-four-corner composite flights; LiuYao adds yongshen strength, whole-hexagram per-line strength, hidden-spirit release conditions and response-time clues (应期), while LiuYao and MeiHua quote the received Zhouyi text in full (64 hexagram statements, 384 line statements plus 用九/用六, cross-checked across three editions with variant readings in brackets); feng shui covers eight-mansion and Xuan Kong flying stars; name analysis ships a 1,062-character library with five-grid (五格) numerology and phonetics checks; tarot ships a card-by-card library for all 78 cards (Rider-Waite-Smith base: English name, card-image description, core meaning and astrological correspondence, cross-checked against three published sources — court cards deliberately carry no zodiac because two published mappings conflict, and the chart says so). A classical-source library now backs the readings: 464 indexed citations from 66 classical works, with 584 verifiable quotations including all 120 Qiongtong Baojian pattern extracts; every quote is checked as a literal substring against a 341-page offline source snapshot, variant readings are kept side by side rather than harmonised, modern editorial notes are kept separate from the classical text, and the quotations with their plain-language glosses live only in a standalone citation index page instead of the browser chunks. Every result can carry a reproducible shadow-chart ID (same normalized inputs → same ID; version bumps auto-diff chart fields) plus optional step-by-step deduction traces (rule, inputs, result and source per layer). The browser client ships as a small first-screen entry plus per-tab engine chunks loaded on demand (first-screen gzip ≈ 90KB), while the offline page stays a single file. The DSH panel and the offline page share the same grouped first screen (ask / read a person / pick a date) with recent-used entries and narrow-width folding; charts open with a plain-language conclusion, one-click copy of an ask-ready prompt and saved birth charts, and an unknown birth hour falls back to a three-pillar chart instead of silently assuming midnight. All computed locally; networking is off by default. The npm package also ships an offline single-file page (命理排盘.html): double-click to open, every tab included, no server and no network needed.

Thinking levels, image input and image generation for third-party models in the official Models page; multiple keys per provider routed by model, automatic failover between keys on failure, per-route custom request headers, and balance display.

AX-first macOS computer use for DeepSeek Harness: accessibility snapshots with stable refs, background input, Unicode typing, menus, apps, set-of-mark screenshots, on-device OCR, verified actions, and optional Jev (TypeSafe System One) semantic guards — 1

Fills missing context window, max tokens, thinking levels, and image input on custom DSH models from models.dev, and lists unmatched models for manual edits.

Vault button beside the DSH composer: save keys, servers, phone numbers, addresses and URLs, auto-collected from conversations, password-protected with WebDAV backup; click to insert, Ctrl+click to send.

Windows-only computer use for DeepSeek Harness: captures the virtual screen and drives mouse & keyboard through 9 tools built on PowerShell and Win32 SendInput; pairs with picturereader so text-only models can complete the screenshot-analyze-act-verify loop fully locally.

Cost dashboard for DeepSeek Harness: aggregates model input/output/cache tokens across all local sessions, prices them with a builtin table (including DeepSeek peak/off-peak), and shows daily trends plus per-model and per-session tables.

Mic button in the composer tool row: Web Speech API speech-to-text (Chrome/Edge), language switching, and optional auto-send, zero dependencies.

MiniMax-powered multimodal plugin: real-time voice call mode (streaming conversation, floating dock UI), voice mode and mic voice input, plus image/video/music/speech generation and vision inspection tools.

Take over the system input shortcuts for the chat input box and configure behavior independently for each shortcut.

Embeds chat.deepseek.com in a DSH desktop panel and moves text both ways round by round: pick any round of the web conversation and copy it, or send it as a user message into a session of a chosen workspace; and fill any answer of the current agent session back into the web input box without sending it. The embed reuses the web session, so it spends no API quota, and asks for a web login once per app start.