Plugins

Desktop notifications for run completion, model questions, and approval requests with per-platform system sounds, zero runtime dependencies.

DeepSeek account balance and current-session spend estimate in a top-bar chip and settings card, with pause-aware auto-refresh, an editable official price table, a `deepseek_balance` model tool, and a bilingual UI.

Session cost estimate in a status bar at the bottom of the conversation (per-model token pricing, CNY) plus the live DeepSeek account balance via the official balance API.

Provider-tabbed model picker for the dsh web composer: left provider column and right model list, both independently scrollable, with cross-provider search.

Fully customizable keyboard shortcuts for the Web UI: 34 pre-registered features (sessions, views, clipboard, models, silent permission cycling, settings), one-click recording to bind your own, and a shortcut cheatsheet with built-in diagnostics.

Adds searchable filtering to the model selector by provider, model name, and model ID; spaces act as wildcards.

DSH 插件:直接复用 Codex CLI 本地登录订阅凭证,在 DeepSeek Harness 中使用 ChatGPT 订阅模型,无需 API Key | DSH plugin: reuse your Codex CLI local subscription login to use ChatGPT subscription models in DeepSeek Harness, no API key required

Two-level model circuit breaker with failover: trip a model or a whole provider after repeated request failures and route the next request to a configured fallback.

Activity heatmap in the DSH Web sidebar: GitHub-style grid of daily commits, token usage, and estimated spend, with a today stats line for all-session token totals, cache hit rate, and per-model auto-priced cost.

GitHub-style activity heatmap in the sidebar, one cell per day over 30/90/365-day ranges, with token usage and estimated cost per model and editable per-model prices.

Six-layer local memory for dsh: captures turns, stages them through an L2 buffer into DL3 summaries via a staging model, injects a stable memory block each turn and replaces chat history with placeholders. Ships five memory tools and a config page.

SAO (Sword Art Online) theme for DeepSeek Harness: a Link Start startup animation rendered ahead of the app shell, with Kirito/Asuna voice lines, plus theme and surface colours, liquid or frosted glass, per-component transparency, nine built-in or uploaded wallpapers, and a model-intensity slider.

Deep PTC mode is an open-source agent preset for DeepSeek Harness that keeps the built-in PTC tool surface and replaces the persona with a working contract: a DeepSeek identity and unlimited-token-budget instruction so the model does not skip reads, commands or checks to save tokens; planning by estimated size (internal up to 5 minutes, shown without approval up to 20, approval required beyond); and asking about unclear intent instead of guessing. Waiting is limited in code by wrapping the official shell, job and question tools: foreground commands move to background jobs after 30 s (configurable), a steered user message ends the current wait so the model reads it, foreground pauses over 5 s and long timers in run_code are refused, and questions run in timed mode. The mode derives its preset from the official PTC declaration shipped by the installed Harness and inherits upstream composition changes, so an official PTC update — including removed or renamed modules — does not break existing sessions. A settings card selects the preset executor — Automatic, WSL Bash, Windows PowerShell, native Zsh or native Bash.

Breeze TTS client for DeepSeek Harness: connects to your own Breeze TTS server to read replies aloud and manage voice cloning (the server and its model must be deployed separately; hardware requirements are on the server side), with an optional cross-machine mode. Merges @dsh-external/dsh-plugin-local-ai-tts (abbccdd/dsh-localtts) and dsh-breeze-voices, carries code from 1624318455/dsh-plugin-tts, and must not be installed alongside the two upstream plugins it merges.

Local-first achievement collection for DeepSeek Harness. Normal use earns 67 stamped badges across 7 series, completes 9 voyage chapters holding 36 ocean collectibles, unlocks a configurable ASCII aquarium and exports a five-badge voyage card as PNG or offline HTML. No check-ins, no model calls, no chat uploads.

Control the Chrome browser you are already using: open new tabs or reuse your logged-in tabs, so the model can read pages, click, fill inputs, drag page elements, scroll, take screenshots, open tabs in groups and close the tabs it opened, inspect console and network logs, and debug the browser. Requires Chrome 120 or newer; install the extension from the Chrome Web Store and pair it with an 8-digit code.

Connects the free ZCode plan to the model picker: a multi-account pool with rotation, per-account rate-limit and quota display, and bigmodel/zai device login.

DSH 提供商与模型高级管理台：设置页独立导航「提供商配置」，管理提供商（地址/协议/Key 凭据）与模型（增删改/拉取/批量删除/识图声明/推理档位/拖动排序/连通测试），直写 llm-pi-ai 命名空间热生效。自包含：模板组件已内联，无外部依赖。

Publishes the running DSH host as a Model Context Protocol endpoint, so other harnesses such as Claude Code, Cursor, Codex or another DSH can start and continue sessions, read transcripts, wait on or cancel turns, and answer pending approvals; every call is attributed to its caller, and owner-scoped sessions keep callers apart.

Fortune-telling toolkit: bazi, ziwei doushu, meihua yijing, liuyao (six-line coin oracle with najia), almanac, chenggu bone-weight, zodiac, date selection, qimen dunjia, fengshui, name scoring, compatibility, numerology, a life K-line chart, tarot and xiaoliuren — 16 tools whose ganzhi, stars, hexagrams and bone weights are all computed by deterministic local engines, with the model only interpreting results. Supports solar and lunar dates with leap months, China DST and true solar time correction, plus a ten-page read-only side panel.

Replaces the Windows pwsh executor row so the model-facing pwsh tool runs PowerShell 7, with a shell_router tool for status, diagnosis, and per-user portable installation.

Registers Epic's Unreal Engine skills (unreal-mcp, create-toolset, unreal-skill), injects Unreal project context, and connects the editor's ModelContextProtocol server with a port form on the Plugins page.

Union web search for DSH (consolidated successor of DDDMUC/dsh-free-search, which it credits): 28 engines across three tiers — keyless free (Bing/DuckDuckGo/AnySearch/SearXNG multi-instance union, plus Exa/Tavily/Keenable/Firecrawl/Parallel keyless modes), paid-with-key (Zhihu/Perplexity/Serply/DeepSeek official/You.com/Baidu/Kimi/Aliyun/Doubao/Zhipu/Bocha/Metaso), and model built-in search (OpenAI/Gemini/Claude/Grok, explicit opt-in only) — with auto smart routing, per-engine enable/disable & fallback priority, parallel top-3 merge, multi_search, failure-aware fallback, a toggle to block the system built-in search, time filtering, platform search, web_fetch and a web settings UI. Experimental free advance_fetch: whole-page GFM-Markdown or CSS-selector/fields structured extraction with no API key and no per-call billing; fetch identity configurable (custom User-Agent, Referer, per-domain cookies attached only on domain match, never leaked across cross-domain redirects). Hosts 0.1.0-rc.2 through 0.2.1-rc.2 (17-tag exact engines.dsh enum; the rc.2 search-provider takeover goes through volatile config pinning after capability probing, never version branches). Paid engines need your own API keys (optional; free engines work keyless). npm: @drscrewdriver/dsh-union-search and bare dsh-union-search.