Plugins

Model capability editor: edit each model reasoning-effort levels and image-input (multimodal) declarations inline in the official model page, written back to settings.yaml as a whole group, with a floating entry as fallback when the anchor breaks.

Point-and-shoot screenshot capture: a system floating window turns a new screenshot (or copied image) into an Obsidian note with comments and key-point marking, instant OCR through the host DSH multimodal model (no extra API key needed, Tongyi Qianwen as fallback), a duplicate-screen guard, per-day merging, and an optional evening AI organization pass.

Structured vision evidence (OCR/layout/semantics) plus a USB camera capture tool for a "shoot-look-adjust" debug loop; backends: Ollama, DeepSeek, Xiaomi.

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

Multi-agent collaboration suite: user-configured specialist roster, persistent on-demand dispatch (team_call/team_message/team_status/team_close), clone instances, star-topology relay, model comparison and a multimodal vision bridge.

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.

Vision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.

Vision toolkit for text-only DeepSeek: model-invokable `vision` tool, wrapper adapters for deepseek/opencode-go (v4 flash/pro), Antigravity IDE quota (default, flash/pro) / any OpenAI-compatible VLM / Gemini / local Ollama channels, evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Qwen media tools: multimodal video and audio understanding, text-to-speech with preset voices, and scene audio generation, through Alibaba Cloud DashScope.

Decision 3.0 multimodal decision models for DeepSeek Harness: calibrated-probability tools, a Settings page and a probability-bar card

Give your DeepSeek Harness agent an addressable visual memory: revisit any image, inspect any region, and read exact pixels.

DocChain knowledge base, document conversion and knowledge-graph toolkit — filename, content and metadata search, locate-by-doc_id/name with content reading, topic listing, bulk document upload, document-to-Markdown conversion, image-similarity search, per-document image descriptions saved to a sidecar markdown (flowcharts and architecture diagrams are turned into PlantUML sketches, other images into text descriptions; the original image is replaced by a clickable link), a deep-research workflow, and a knowledge-graph layer (ontology inspection, read-only Cypher, ontology/entity/relation writes). Every script-backed capability also ships as a native DSH tool executed in-process: doc search, content search, filename search, topic info, metadata search, upload, image search, image describe, doc2markdown, plus kg schema / kg cypher / kg upsert node / kg upsert relation / kg delete node / kg delete relation. All graph operations go through the DocChain API, so no Neo4j password is needed. The configuration page keeps several docchain environments (each with its own address and credential), switches between them in one click, and pre-selects topics per environment. Needs a docchain service URL and API key (except doc2markdown); image descriptions additionally need an OpenAI-compatible multimodal endpoint (defaults to an internal gateway model, configurable).

Add MiniMax image understanding, image generation, speech synthesis, and transcription tools to DeepSeek Harness.

DeepSeek Harness plugin: Bilibili keyword video search, video metadata, subtitle transcripts, direct play URLs, and multimodal frame viewing (bilibili_search / bilibili_video / bilibili_subtitles / bilibili_playurl / bilibili_frames). Anonymous by default

Transparent multimodal routing for text-only models: every image in every model call is fully transcribed (verbatim OCR, data, uncertainty zones, injection-hardened) by your own multimodal understander, with focused re-look via vision_relook and automatic retry on image-related failures. No bundled endpoints, no borrowed logins.

DeepSeek Harness vision plugin: 8 analysis modes (describe, OCR, chart data, UI review, object detection, compare, code-gen, debug), any OpenAI- or Anthropic-compatible vision API, with a built-in free vision model and automatic rate-limit failover.

DeepSeek Harness plugin: direct multimodal image transfer declarations + per-session image clearing (surface replace), with a settings page and composer controls.

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.

Multimodal plugin for DeepSeek Harness: understand images and generate images through configurable OpenAI-compatible or DashScope endpoints.

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.

`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.

Vision for any DSH route: paste images in the Web composer with intent-aware auto-analysis, delegate workspace image reads to a Kimi/MiniMax vision subagent, and materialize pasted originals for editing.

Auto-discovery vision bridge for text-only DeepSeek Harness agents: automatically finds an image-capable model from your configured providers and returns picture descriptions as plain text via a vision tool.

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).