Plugins

Recolhimento com um clique de todas as seções expandidas (linhas de Think, cartões de ferramentas), com pílula de contagem ao vivo e atalho personalizável

Adds subscription OAuth and provider Plan API-key logins through Pi adapters, using a DSH-owned credential store.

DeepSeek Harness plugin: Claude Code-style prompt history, double-Esc picker, selection quote/copy & right-click paste | DeepSeek Harness 插件：Claude Code 风格上下键历史回溯、双击 Esc 历史搜索、选中文本引用/自动复制与鼠标右键直接粘贴

商汤日日新（SenseNova）多 Key 轮换池 — 填入多把 Key 即可零配置接入 DeepSeek Harness，遇 429 限流自动切换下一把 Key。

DSH Web 成本与余额指示器：峰谷时段徽标 + 本会话/本轮 token 费用 + DeepSeek Key 余额 + 悬停自定义配色（RGB 轮盘，可整体或单个调色）——合并 dsh-peak-indicator 与 dsh-balance-indicator

Targeted Windows input from WSL: invoke a UI Automation element by name, or send keys, clicks and mouse wheel to a chosen window.

Read-only Windows registry access from WSL, restricted to an allowlist of key prefixes; list a key's values or its child keys.

Windows desktop automation for dsh: 14 tools that enumerate apps and windows, capture window screenshots that still work when the window is covered by other windows, read the accessibility tree, and perform real input — click, type text (CJK included), press key combinations, scroll and drag. Loads the official computer-use runtime (@oai/sky) already installed on the machine, discovering it by enumerating vendor directories, so vendor upgrades that change hash directories do not break it.

Ollama Cloud provider for DeepSeek Harness that configures the route on install, publishes each model's own thinking levels for the composer effort control, and shows account usage with an API-key field in the Models page and sidebar.

Zero-token DuckDuckGo search provider for the DeepSeek Harness (DSH) web seam — local headless browser, no API key, no model billing

只填 Key 的服务商预设：50 家渠道为 DSH 一键写入官方 llm-pi-ai 路由与凭据（插件），并可写入腾讯 WorkBuddy、OpenCode（Key 走其 auth.json）与 cc-switch 的配置（CLI）；核心为纯 JS，可被更多应用的外壳复用。

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.

A live crypto ticker card in the DeepSeek Harness sidebar footer, above the balance and Settings, showing BTC, ETH, SOL and JUP prices, 24-hour change and 24-point sparklines, with a pulse on each price tick, zero dependencies and no API key.

Configuration UI for the official OpenViking memory plugin: connection and user-key setup, local connection diagnostics, a per-session memory toggle in the composer, memory isolation that keeps recall inside the current topic, and recall tuning for score threshold, injected item count, query expansion and excluded URIs.

Shared browser panel for DeepSeek Harness via Better Sidebar, with local Chromium, human and agent mouse and keyboard control, page snapshots, screenshots, and per-chat persistent profiles.

SMS forwarding webhook for DeepSeek Harness. Phone apps (SMS Forwarder, Tasker, or any HTTP POST) push messages to a local HTTP endpoint; the plugin stores them as JSONL and exposes sms_recent / sms_search tools so the agent can read SMS verification codes during tasks. Auto-extracts the first 4-8 digit OTP from each message, supports keyword filtering, and works over LAN or Tailscale.

TypeSafe Jev (modelo de decisão System One) para o DeepSeek Harness, de ponta a ponta: jev_decision (choice/score/noul, paralelo, respostas tipadas + confiança), um cartão em Settings > Plugins para a API key e chaves de liga/desliga, visualizações inline de ferramenta mostrando cada decisão na conversa (resposta, confiança, latência, custo), um auto-guard (checagens determinísticas + de risco/loop do Jev), um dashboard local /jev e um benchmark de verificação online (96,3% em 27 perguntas rotuladas, mediana ~283 ms no jev-latest, 2026-09-21). Honesto por design: só API real, sem fallback simulado.

Skill that fact-checks a claim against the open web rather than model memory: it splits the claim into independently checkable fact points, routes each point to the primary-source ladder for its domain (policy, academic, medical, financial, disaster and accidents, food safety, science, education, sports, entertainment, judicial, and more), searches domestic and international ecosystems in parallel, fetches primary pages, grades sources by type, re-searches with debunking keywords, and reports conclusion-first with a full URL and citation position behind every statement, keeping unverified and undecidable points separate from confirmed ones. Three factual judgements can be routed to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not; a model verdict can only lower a confidence tier.

Registers a keyless search provider for the built-in web_search tool so it works without an API key, failing over between the documented no-key tiers of Tavily and Firecrawl; a TAVILY_API_KEY or FIRECRAWL_API_KEY is picked up automatically when present. Two Bing scrape backends are included but off by default.

Cota do plano Command Code na barra lateral do DSH, acima de Configurações: janelas de 5 horas, semanal e mensal como percentuais usados com contagem regressiva de reset, um comando /quota e uma CLI sem dependências. A chave é lida da sua própria rota de provedor, então não precisa de configuração nem de outro plugin.

Pre-execution safety valve for DSH that judges with TypeSafe Jev: it hooks tools/pre-execute and decides every bash/pwsh call by first applying offline static rules, then by asking the Jev model — the System One model from TypeSafe, which returns a structured decision instead of prose — one yes-no question ("will this command irreversibly delete or overwrite real data?"), turning the answer into allow, revise, block or escalate; revise hands the model a safer rewrite, escalate offers a one-shot human token; exhausted credit or a missing API key degrades loudly instead of failing silent, and a missing key is requested in the conversation itself (`guard key set`, read from stdin); every verdict is appended to a shared audit log and the text people read is bilingual zh-CN/en.

Automatically highlights key points, definitions, warnings, and questions in completed assistant answers using one separate model call.

Mobile-first Web UI quality-of-life pack for the DeepSeek Harness: a Chrome-style active-session tab bar, full-screen sidebar swipe open/close, overlay sidebar, collapsed-sidebar recents, keyboard-suppressing session switching, viewport/IME keyboard adaptation, touch feedback, code/table inner scrolling, hidden permission dropdown, a full-screen settings rewrite with tab memory, and a compositor-driven status pulse, no-touch-drag long-press protection — 14 features, each independently toggleable from the Settings QoL section with instant effect, persisted per browser in localStorage; pure client-side CSS/JS, mobile rules locked to viewports of 768px and below so desktop stays untouched.

Literature search for DeepSeek Harness: pubmed_search, pubmed_paper and pubmed_related over the official NCBI E-utilities (including elink related-article ranking), plus scholar_search and scholar_cite (MLA/APA/Chicago/Harvard/Vancouver/BibTeX via SerpApi). Both backends return one paper shape, and a settings card configures the API keys, the Scholar backend and the rate/result limits.