Plugins

Preset workbench for editing per-agent personas, system prompt sections and tool descriptions, selecting tools and skills, previewing request context, and importing or exporting JSON/YAML configurations.

A community plugin marketplace for DeepSeek Harness, built to the official plugin spec — browse, search and install 4000+ human-curated community plugins without leaving the app. · DeepSeek Harness 社区插件市场（遵循官方开发规范）：4000+ 人工精选社区插件，每日更新。

Read official DSH docs in the Plugins page; Creator mode searches docs and checks plugin npm metadata with native tools.

One-stop visual management of DSH Skills & MCP: on-demand MCP loading, in-session hot reload, SKILL & MCP descriptions viewable in the plugin.

Desktop pet drawn from the official whale outline, for both the desktop app and the web UI: SVG animations and facial expressions follow agent state (thinking, working, done, error, waiting for confirmation), and it can follow other running sessions with a count badge; poke it, drag it, shake it dizzy, squash it against a screen edge, or rub the cursor over its head for a headpat; 7 palettes, 4 sizes, synthesized sounds, light/dark theme sync, and a playable web preview.

Use a ChatGPT/Codex subscription in DeepSeek Harness with GPT models, image generation, web search, subscription quota reporting, model and feature controls, and browser or device-code OAuth sign-in.

Bilibili video analysis: metadata, transcript (ASR fallback via Bijian/sherpa-onnx/whisper.cpp), comments, danmaku, and sharp keyframes with optional local vision descriptions.

Three Zhihu tools for DSH — in-site search, Zhihu's global web index with domain and date filters, and Zhida answers — with a native settings card and source-cited results.

Cache-stable progressive tool discovery: a fixed tool_search and tool_dispatch surface on every request, in-memory catalog search, nested dispatch through the Harness pipeline, and a byte-stable native tool list across discovery.

Adds a generate_image tool backed by the FAL queue, any OpenAI-compatible images API, or a ChatGPT/Grok subscription, and shows the result inline in the conversation.

Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM / LM Studio / self-hosted) can try reasoning — the card writes llm-pi-ai capabilities, the adapter drives the wire (compat.thinkingFormat), and this plugin auto-maintains the takeover list.

Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件（场景感知抽帧 + VLM + 可选语音转录）

Usage tiers and shareable stats cards: 🐟→🐳 ranks by monthly token burn with a locally-computed estimated percentile, precise pricing for 46 models across 6 vendors (including size-tiered Chinese pricing), backfill of pre-install sessions, and old-vs-new comparison across the 2026-08-17 rate change. Local-only, no telemetry.

Signs in to a ChatGPT account over OAuth and serves that plan's models as a DeepSeek Harness provider route, calling api.openai.com/v1/responses with the account's plan scope rather than the Codex backend.

QQ channel for dsh via OneBot 11 (NapCat and friends): reverse or forward WebSocket, DM and group chats, image and voice transcription, t2i text-image cards, merged forwards, and a settings page.

A novel-writing workbench for DeepSeek Harness: you tap thumbs-up or thumbs-down on candidate passages, and the model distils them into a short preference profile that carries into later drafting calls while the manuscript stays out of the drafting context. Adds a chapter board, per-chapter writing packs, annotation-scoped revision that rewrites only the annotated paragraph and verifies the rest byte-for-byte, a project ledger, and local pacing checks.

Fetches any http/https page and returns title, description, main text, heading outline and links, with stats (char/word counts, reading time, language) and top keywords; can download content images to the session workspace for vision analysis and dispatch them to registered analyzers via the scrape.imageAnalyzer service.

Select browser elements directly during Vibe Coding and send structured visual feedback to the DeepSeek Harness Agent.

Android GUI Agent with ADB screenshots, compact UI hierarchy grounding, verified iterative actions, approvals, and a Mobile Web view.

OpenCode Go subscription usage (rolling/weekly/monthly windows with reset countdowns) in the composer dock, with a built-in credential editor.

Domain-identity layer for long-running agent sessions — declaration-first domain addressing, a session factory, four-level pause, and model dispatch for coordinating multiple top-level sessions.

Unofficial upstream bundle for DeepSeek Harness. CodeBuddy gateway with a runtime-synced model catalogue, per-model reasoning efforts, web search/fetch, image generation and a streaming credential bridge, plus TraeWork CN and Qoder CN subscription channels via local translation gateways and a key-type OpenAI-compatible provider registry, all managed from an accordion settings card.

Plugin coordination layer: plugins declare their capabilities, commands route to the owning plugin without a model call, tool schemas load on demand to cut prompt tokens, run history consolidates into long-term memory while idle, and failures are classified before any retry.