Плагины

Адаптивная маршрутизация моделей: классификация сложности каждого запроса с автоматическим выбором провайдера.

Полноценные инструменты Git для модели: status / diff / log / commit / branch с проверкой сообщений и путей — без прямых вызовов git через shell.

Переопределение модели, провайдера, персоны и toolFilter для каждого вызова при делегировании субагентам, со ссылками @preset: и составными идентификаторами provider/model.

Drive Origin scientific plotting from DeepSeek Harness AI chat via MCP: write data, plot line/scatter/column, export PNG/SVG.

Detached-broker supervision of long-running services (dev servers, watchers, mock APIs) that survive turns, sessions and DSH restarts, with a Service sidebar tab (registered via better-sidebar's extension API) and service_start/stop/restart/list/logs model tools.

WeChat iLink ClawBot bridge: official Tencent iLink protocol, Web UI settings (QR login / model / preset / permissions / session management with delete), 24h auto-renewal pushes a fresh QR before expiry, zero downtime.

Per-file-type multimodal chains: preset processing models per wildcard convert image/video/audio files into prompt tokens before they reach the text-only session model, with per-preset fallback chains and a Multimodal settings page.

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.

Composable working, reasoning, quality, and human-reviewed self-evolution controls for DeepSeek Harness Web.

Composable working, reasoning, and quality controls for DeepSeek Harness Web.

Self-learning habit engine for the DeepSeek Harness — detects user-correction signals, judges habits with a low-cost model on threshold, settles candidates behind a two-level human gate

DSH Web GUI 模型能力配置：在「设置 → 模型」的模型目录编辑器内，为每个已配置的模型直接设置是否支持图像与思考等级（reasoning efforts），写入 llm-pi-ai 设置命名空间。

DeepSeek Harness plugin: a `deepseek-vision` route that declares image input and transcribes pasted images via the free Zhipu GLM vision models before delegating to the DeepSeek adapter.

Choose reasoning effort for additional models in DeepSeek Harness, with Off and five standard levels.

Route DeepSeek Harness model API requests through a local HTTP proxy, with local-port probing and a settings section.

Cost governance for DeepSeek Harness: aggregated token/cost metering per model, session and day, session/daily/monthly budget caps with threshold alerts (desktop notification + webhook) and alert/block/degrade over-limit policies, built-in carbon footprin

Cline free models provider for dsh: scan the Cline model catalog dynamically and serve the :free models through the harness LLM seam

Put a dsh (DeepSeek Harness) workspace on ANY machine. Two modes in one plugin: (1) fleet — enroll an off-site machine behind NAT into your dph via a one-time token + reverse tunnel to your own relay VPS, so it appears as a dsh-ssh host; (2) execution wor

dsh plugin: register codex-web-search-mcp (model-independent OpenAI Codex / Grok web search & deep research MCP server) as a native dsh MCP tool set (mcp__codex-web-search__*).

Switch between Chat and Agent without leaving your DeepSeek Harness session.

DeepSeek Harness out-of-tree plugin: give a text-only coding model eyes by routing images to a Qwen-VL (DashScope) route through ctx.llm and returning text.

DeepSeek Harness plugin: let text-only models receive pasted images, and analyze them with a built-in OpenAI-compatible vision tool

DSH web plugin: a real-pricing usage-cost line beside the official token stats — per-model cost breakdown with a verified price table. / DSH 费用统计行：在官方 Token 用量行旁按模型显示真实费用（按模型分别标注，价格均来自官方定价页）。

Native Windows Computer Use tools for DeepSeek Harness.