Plugins

Computer use through an external USB HID device: name a target in plain language, a vision model locates it in a cropped window screenshot, and a Raspberry Pi Pico 2 moves the real mouse and types on the real keyboard. 7 tools. Windows has window listing, per-window cropping and automatic window raising; macOS needs pyobjc and has neither; Linux is unsupported.

DeepSeek balance and per-session cost in the DSH web composer dock, with official peak/off-peak pricing (peak hours Mon-Fri BJT 9-12 / 14-18, weekends off-peak) and built-in deepseek-v4-flash-vision-exp vision model rates billed at flash price (images billed as tokens, max 384 tokens each).

Turns attached files into versioned evidence: `search_documents` builds a private local index (SQLite FTS5 after a startup capability probe, dependency-free JS fallback otherwise) and returns compact evidence blocks carrying an exact coordinate — PDF page, PPTX slide, text/DOCX line range, or quoted XLSX `Sheet!Range` — which `read_document` expands only while the content version still matches. Contiguous CJK runs are indexed as overlapping bigrams and queried as phrases, so word order is preserved; uploaded raster images take the native vision attachment path instead.

DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.

Per-model vision (image input) toggle for DeepSeek Harness (dsh): list every configured model and flip a switch to enable/disable image support without hand-editing settings.yaml. 为 DeepSeek Harness 提供按模型的「支持图片」开关：无需手改 settings.yaml。

Bridges images into text for DeepSeek Harness: when the session's selected model cannot see images, a configured vision model describes them and the descriptions enter the durable session history as folded context rows — your message stays untouched.

Display companion for dsh-vision-router: keep Auto Vision routing, and put a square picture button on each original model row. Does nothing unless dsh-vision-router is installed.

Vision browser tool: drives real Chrome over CDP with browser-use and reads the page with deepseek-v4-flash-vision-exp, so canvas text, text baked into images and values in rendered charts are readable; returns JSON validated against a caller-supplied schema and reports per-run token cost.

Enhanced vision toolbox: 14 pixel-level vision tools (describe, ground, detect, crop, pixel-diff, OCR, long-screenshot OCR, vectorize, colors, cutout, screenshot, present, materialize, html-screenshot) driven by one OpenAI-compatible endpoint, with clean \[图片: path] bridge markers, content-safety classification and rate-limit auto-retry.

Drag-and-drop file upload for PDF, Word, Excel and images: dropped files are saved to a local directory and referenced by path, no base64 bloat in the chat.

Inline preview for \[图片: path] image bridge markers: after the marker renders, the image shows in chat automatically, keeping long instructions out of the conversation.

Windows computer-use capability for DeepSeek Harness: screenshot → vision model → simulated mouse/keyboard input, with self-evolving knowledge base.

GLM 视觉模型插件：注册 glm-vision 供应商路由（glm-4.6v 系列，image+text 输入声明）并提供 glm_vision 工具，让 DeepSeek 等文本主模型直接调用智谱视觉模型看图。

DeepSeek Harness plugin: a vision worker over Cloudflare Workers AI (@cf/moonshotai/kimi-k2.6) that routes image requests from text-only callers, returns a versioned righthand.vision.v1 envelope, and supports follow-up questions.

ROS2 debugging toolset and robot-state vision analysis for DeepSeek Harness: node/topic/service/action/interface/TF enumeration, whole-graph topology JSON, rosdep checks, approval-gated builds and custom message scaffolding, GUI screenshots and multimodal vision observation, plus headless RViz2 offscreen rendering (low-poly meshes, direct pixel read, GPU passthrough - motion rendering at 30Hz) with parallel VLM realtime analysis.

meow-vision 是 DeepSeek Harness 的一款视觉插件，解决纯文本模型无视觉。另一方面vue页面开发视觉验证不闭环的问题。

Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.

DSH Web 插件：调用智谱 GLM 视觉模型分析图片（analyze_image 工具 + 插件设置卡片）。

Lightweight, route-preserving vision link for DSH: a configured vision model sees while the selected text model stays in control.

Local eyes for text-only models: eyes_render draws text/shapes/Mermaid onto a canvas in the Web GUI, eyes_paste captures pasted images, eyes_ocr reads text via the built-in Windows OCR (offline), and eyes_analyze inspects pixels as structured data — no vision model required.

Lifecycle supervision, evidence-driven audit subagents, safe intervention, and blind acceptance gates for DeepSeek Harness

macOS desktop control for DeepSeek Harness: agent operates non-browser apps (CapCut, Photoshop, WPS, native clients) like a human — 14 tools for mouse, keyboard, scrolling, app activation, windows and screenshots, plus a vision closed-loop (desktop_see for image understanding + desktop_locate for UI element coordinates) that reuses dsh existing vision credentials. GUI-session service starts on demand, no login autostart.

Model-facing accurate_vision tool: precise image spatial reasoning via a vision model

Paste images into DeepSeek Harness chat and have them read by a free local backend (macOS Vision / Tesseract) before the text-only DeepSeek model answers