Plugins

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.

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.

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

DIT.ai provider bundle for DeepSeek Harness: installs 29 OpenAI Chat Completions models and 10 Anthropic Messages models from one DIT_API_KEY, with protocol-specific thinking configuration.

Terminal-style AI-lab idle game where you hoard compute, train and upgrade models, publish papers, and prestige from neural nets to ASI.

Chat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local Ollama or cloud): pasted/dropped images become `view_image` path markers before reaching text-only DeepSeek models.

`describe_image` tool: a vision bridge that sends images to mimo-v2.5 through the opencode Zen API (credential `OPENCODE_GO_API_KEY`, free route first with paid fallback) and returns text descriptions for text-only models, with native passthrough and ImageMagick transcoding of SVG/TIFF/HEIC formats.

On-demand vision for text-only DeepSeek models: upload images, and the model calls a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).

Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, GUI automation, through layered evidence memory and cache.

Reuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool drives the local deepseek-vision-cli browser automation (manual login helper, deep-think enabled, auto-closes browser) and returns image descriptions as text.

Auto-fills reasoning-effort levels, context windows, output limits and image modality for models from unofficial (custom) providers, with data from models.dev.

Automatic provider failover on rate limits or quota exhaustion: switch between providers with configurable per-provider models, a cooldown, and a permanent last-entry fallback.

Composer cost chip: prices the current session DeepSeek API spend message-by-message with the official pricing table (incl. the 2026-08-17 peak/off-peak policy); hover for the breakdown, today (DSH) total and account balance. DeepSeek models only.

DeepSeek Harness plugin: per-request thinking-mode switch (enable_thinking) for Qwen3-family models on OpenAI-compatible endpoints

DeepSeek Harness plugin bundle: qwen_vision (Qwen-VL image understanding) and qwen_generate (Qwen-Image text-to-image) tools for text-only models

Plug-in vision for text-only DeepSeek Harness (dsh) models: a `vision` tool with built-in cheap/free VLM presets, multi-image batch analysis, paste-to-hint image admission, and a web settings page with hot-reload.

A session recap plugin for DeepSeek Harness with /recap, automatic idle summaries, and configurable models.

fal.ai native image generation for DSH: a FAL_KEY settings card that follows DSH's language (zh/en, English default) plus Agent tools (fal_generate_image async / fal_edit_image / fal_get_image_task / fal_list_image_models) that call queue.fal.run directly

SenseNova connect family bundle for the Harness Web UI: Token Plan credit panel (per-pool quota windows, per-model consumption, self-renewing console token) plus optional provider registration that brings SenseNova models into DSH conversation, with host-

Cut LLM costs: route routine tasks to cheap subagent models (DeepSeek Harness plugin)

Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.

Connects the Xiaozhi voice assistant to DSH Web over MCP: DSH is the tool provider, weaving 35 DSH Web endpoints into 16 voice-friendly tools for workspaces, sessions, chat, models, settings and files — outbound WebSocket to the Xiaozhi MCP access point by default (no public IP or port forwarding needed), several devices bound at once, plus a DSH settings page with live status.

Free OpenCode Zen models in DeepSeek Harness through native HTTP requests. No OpenCode installation, login, API key, server, container, or LiteLLM is required.