Plugins

Multi-account Google Gemini provider: picks the account with the most remaining quota, fails over on 429 with exponential cooldown, probes disabled accounts in the background, and ships a Chinese/English settings page.

Brings the models included in the Xiaomi MiMo desktop app (free during beta) into DeepSeek Harness, with zero configuration in the DSH conversation window.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

Peak/off-peak billing clock with a provider-neutral account readout (DeepSeek balance, subscription plan windows, relay credits), per-turn spend measured from the provider's own counter, and a /hist token-history scene split per provider for dsh-tui

Tavily-backed search provider for the DeepSeek Harness web capability seam (ctx.web) — replaces the official web search with multi-key balance-aware rotation, manageable from the DSH web settings (Plugins → Plugin configuration).

Ultra-lightweight Moli (Rust headless browser) web-fetch provider for DeepSeek Harness: renders complex SPAs, micro-frontends, and dynamic pages with ~60MB memory.

LLM provider adapter that routes model calls through any ACP (Agent Client Protocol) server — Claude Code, Codex, Gemini CLI, Devin and more — with a registry browser, per-server settings UI, lazy authentication, and dynamic model discovery.

Adds a settings page for declaring per-model reasoning efforts and vision support on pi-ai provider routes.

Volcengine Ark Coding Plan LLM provider for DeepSeek Harness: provider-scoped PDF and image input, with Responses API streaming support.

Generates UI wireframes and high-fidelity mockups in DeepSeek Harness with selectable DashScope and Volcengine image providers.

Cost panel for DeepSeek Harness: meters every request from session events, prices it against a built-in catalog of 136 models across 16 providers, and shows the current model, account balance, session, today and month spend plus a monthly budget bar next to the composer. Bilingual zh/en.

Doubao Search (Volcengine 豆包搜索) web search provider for the DeepSeek Harness — swaps the active web_search backend to the standalone Doubao Search API with its own key and billing (500 free searches per month), and ships a dedicated settings card that stores the key via the credentials service.

Configures provider and model reasoning-effort mappings for DeepSeek Harness, with a grouped model picker and composer slider.

DeepSeek Harness plugin: provider sign-in, model catalog, and selection routing over a loopback-only /model-hub channel

Modellix integration for DSH: schema-driven image, video and audio generation in a split Design workspace, a live LLM model catalog, and native web search and fetch providers through one API key.

Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.

dsh web 的 Token 用量热力图：固定近 26 周（周日起始对齐）按天着色、GitHub 风格、深色/浅色自适应；今日/本周/本月/累计四个总量 chip 点击即把明细表锁定到对应时段，可再点选单日；明细按 provider/model 拆分（输入/输出/缓存读/缓存写/占比）。数据全部来自本机会话日志，增量聚合 + 磁盘缓存。

Inspect, measure, search, and compare the exact provider-neutral context assembled by DeepSeek Harness.

Aggregated web-search provider for the built-in web_search tool: one prioritized queue over nine providers (AnySearch, TinyFish, Tavily, Brave, Exa, Firecrawl, Jina, SerpApi, Serper), with multi-key rotation per provider, ordered fallback on failed attempts, and a live settings card.

AI-native music player plugin for DeepSeek Harness: aggregates NetEase Cloud Music, QQ Music and KuGou search with cross-provider playback fallback, renders word-by-word karaoke lyrics synced live over USB HID to HALO PIXELBAR speakers, and exposes search, playback, queue, alarm and speaker control as model tools.

Adds OpenAI Codex (ChatGPT) as a selectable DSH provider via the local Codex App Server.

Tavily Search API as a web search provider (settings toggle with DeepSeek fallback, keyless search) plus a Tavily MCP bridge: keyless search and extract tools, crawl and map with an API key.

Multi-backend web_search provider (Exa + Firecrawl) for the built-in web_search tool, with automatic failover, per-backend 429 cooldowns, and key-free anonymous access.

LongCat-2.0 LLM adapter: 1M context, binary thinking mode, tool calling, and streaming over the OpenAI-compatible endpoint.