시각 도구 · DeepSeek Harness 플러그인 — 50 페이지

让纯文本模型也能粘贴图片 — 宿主包装 apiProxy.sessions.prompt, 把 image block 转成附件 id 文本标记, 客户端保持原生粘贴

Provider-independent DSH PDF parsing tools powered by MinerU, with session jobs, immutable global results, and safe request coalescing.

AI-powered PDF reader for DeepSeek Harness with annotations, multi-PDF workflows, mixed image-text evidence, and on-demand OCR.

DeepSeek Harness plugin: PDF→Word (.docx) conversion with layout fidelity (fonts/tables/images/borders), OCR scan mode, and optional multimodal LLM verification. Registers the pdf_to_word model tool.

DSH plugin: translate text-based PDFs via DeepSeek or any OpenAI-compatible API, preserving layout, fonts, images and links (editable output PDF, ≤50 pages per task).

DSH plugin: keep text-only models (deepseek-v4-flash / deepseek-v4-pro) as the session default and automatically route image-bearing requests to a configured vision model; also ships the generic file-attachment feature (drag/paste any file as a durable attachment the agent reads by path) as core patches (apply via scripts/patch-core.mjs).

DSH plugin: auto-downscale oversized images (and a portable Agent Skill). Powered by sharp. Install from GitHub — no npm publish.

Hands for your DeepSeek Harness agent — autonomous browser operation with a native permission model. Accessibility-ref page snapshots let a text-only model navigate, act, and test without vision or CSS-selector guessing.

Unified 88api.ai image generation and editing tools for DeepSeek Harness, covering Image2 and Nano Banana models.

dsh-plugin-appshot — a DeepSeek Harness plugin for macOS context screenshot capture.

DeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev

DSH 外观定制：主题色 / 背景色 / 壁纸（渐变·URL·本地图片）/ 面板不透明度 / 磨砂玻璃，设置自动持久化。

Drive a Windows 10 interactive desktop from DeepSeek Harness: window/UI automation, trusted screenshots, offline OCR, and Chrome CDP — as tools, slash commands and skills.

DocumentStudio tools for DeepSeek Harness — bidirectional document conversion (X↔Markdown), templates, PDF merge, and image extraction as model-facing tools.

A session-aware workspace file tree, text and media preview, and Git status panel for DeepSeek Harness.

Image translation for non-multimodal models via GLM-4V-Flash: intercepts images, generates descriptions, injects as text.

DeepSeek Harness plugin: drive the local Grok Build CLI for text, image, and video.

图片转文字输入插件：给无视觉能力的纯文本 LLM（DeepSeek 等）提供图片输入接管。输入框粘贴/拖拽图片后一键转为结构化文字描述；视觉 API 配置在设置页填写，支持任意 OpenAI 兼容视觉模型（qwen-vl / gpt-4o / glm-4v 等）。多模态模型下自动让位，不劫持原生图片通道。

DSH 图片插件，三个工具覆盖三种场景：ask_user_choice 图片/图文混合选择卡（Web GUI 渲染，可放大查看）+ show_images 回复内嵌图片（图文混排）+ save_received_images 盲模型收图存为工作区文件；聊天栏所有图片点击放大，支持滚轮缩放与拖拽平移。来源支持本地路径 / http(s) URL / base64 data URI。零 token 本地渲染，纯插件实现不改核心包。

DSH web plugin: serve workspace image files over a constrained /dsh-image route so agents can embed images inline in conversation.

DeepSeek Harness plugin: image and video generation over the KIE AI API, with polling to completion and a status query

DeepSeek Harness 本地视觉插件：通过 LM Studio 本地视觉模型描述图片/截图，全本地、无云端依赖。提供 vision_describe 工具（Node 原生后端，可选 Python 压缩后端）。

DeepSeek Harness (Cordis) 插件: 给 Agent 直接加上多模态(图/声/视频)能力

NovelAI Diffusion V4.5 Full image generation for DeepSeek Harness: the AI designs NovelAI prompts and generates images via the nai_generate_image tool.