視覚ツール · DeepSeek Harness プラグイン — 47 ページ

Labnana image generation for DeepSeek Harness: text-to-image / image-to-image / precise editing with credits estimation, subscription balance and web settings UI.

公式图片 → LaTeX（pix2tex / LaTeX-OCR）：把教材/截图中的数学公式识别为 LaTeX 代码

DSH 个人工作台：总览 / 看板 / 资料三视图，玻璃拟态视觉，Host 权威持久化。Personal workbench plugin for DSH Web.

LinkDigest for DeepSeek Harness: mounts the remote LinkDigest MCP (https://linkdigest.dev/mcp) via the in-box @deepseek-ai/dsh-mcp-client bridge — turn a Xiaohongshu, Douyin, TikTok, YouTube or X link into text an agent can read.

DSH Web GUI 动态背景插件：静态图 / GIF / MP4 / WebM 背景，低内存自动降级、标签页不可见自动暂停、本地素材目录扫描 + 面板点选即换。参考 dsh-skins 皮肤系统的架构（路由 / 插槽 / 持久化机制），不包含任何皮肤资产。

DeepSeek Harness plugin that turns a local llama.cpp (llama-server) into a first-class model provider: process & router management, model catalog sync with mmproj vision pairing, auto-start on demand, stop-then-load model switching, and a sidebar terminal-output monitor panel.

百炼（DashScope）上的 Kimi LLM 适配器插件：支持 kimi-k3 图片输入、思考链与工具调用

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

DeepSeek Harness (dsh) LLM adapter for Command Code, routing models through the generate endpoint a Go plan can reach — including image input.

Kimi (Moonshot AI) chat-completions adapter for the DeepSeek Harness LLM seam — three routes: kimi-code (Kimi Code subscription), kimi-cn, kimi-global

Per-model reasoning-effort levels and multimodal input settings for custom (llm-pi-ai) providers in the DSH Models settings page. · 为自定义供应商的每个模型配置推理强度档位与多模态输入。

DSH 插件：在 DSH 中提供图像/视频生成工具，基于 OpenAI 兼容 API。模型自动从现有 llm-pi-ai 设置中发现。

DeepSeek Harness LLM adapter plugin for locally deployed Qwen models behind a vLLM OpenAI-compatible endpoint: per-model multimodal switch, fully configurable reasoning efforts, and a web settings page (client plugin) for editing the deployment from the frontend

Task-aware automatic model router (auto route) for the DeepSeek Harness: picks a backend model per request (vision / long-context / default) and falls back across configured models on clean pre-content failures.

Model-facing describe_image + extract_text tools for the DeepSeek Harness web GUI: gives a text-only model reliable image understanding and OCR through an OpenAI-compatible vision endpoint, with critical-inspection prompts, auto-preprocessing, retries, and a persistent answer cache.

DSH plugin: auto-route to a multimodal model when messages contain images, stay on the cheap model otherwise.

A local OCR library and DeepSeek Harness plugin for macOS and Windows.

Preset-scoped multi-Canvas uGUI Workspace with a standalone-only browser designer, extended selectable, scrolling, masking and layout components, stable node IDs, safe gesture undo, image staging, and explicit Unity Prefab generation.

Universal local vision bridge tool for DSH: describe/answer questions about images via any OpenAI-compatible local inference framework (llama.cpp / Ollama / LM Studio / vLLM), vision models auto-detected

DeepSeek Harness 自定义 Logo 插件 — 上传图片替换侧边栏左上角的品牌图标和文字。

Native macOS OCR and Vision tools for DeepSeek Harness

Bridge Apple's on-device Vision framework (macOS) into DeepSeek Harness: OCR, image classification, face detection, and document layout as local dsh tools. No network, no API key, no daemon.

Offline macOS Vision OCR tool for DeepSeek Harness

Microsoft MarkItDown as a DeepSeek Harness tool: convert PDF, Word, Excel, PowerPoint, HTML, CSV, EPUB, or a URL into Markdown the model can read.