Vision tools · DeepSeek Harness plugins — Page 60

dsh-zcode cli反代：把 DSH 的模型请求经 ZCode 客户端 app-server 转接到 ZCode Start Plan 额度（GLM 系列，真流式、图片输入、会话复用），注册成 DSH 可直接选用的模型提供方。原 zcode2api 网关已移除，需要请用原版 liu5269/zcode2api。

Zhipu BigModel capabilities for the DeepSeek Harness in one plugin: web_search_prime search provider, webReader fetch provider (server-side rendered), and GLM-4.6V vision (vision_analyze tool + pasted-image pre-step hook), all behind one ZAI_API_KEY

PaddleOCR-VL-first visual model adapter for Codex and DeepSeek Harness

Turn receipts and invoices into ledger-ready expense rows without invention: every field (date, merchant, amount, currency, tax) traces to the source image, unclear fields are flagged not guessed, currency and tax treatment are stated, and the batch ends with a reconciliation of count and total against the sources.

Inline image preview for DeepSeek Harness: display local image files (PNG/JPG/WebP/GIF) directly inside the chat — fence language `img` + `img_serve` tool. Click to open full size, captions, multi-image grids.

家纺工厂管家：单据识别 / 语音报工 / 数据查询的 DSH 工具包（通用 extract 引擎 + nl2sql 三道闸）

ModLens-style vision bridge for DeepSeek Harness: deepseek-v4-pro as the brain, deepseek-v4-flash-vision-exp as the eyes.

Turn every idea into an image or video with Kling AI. In DeepSeek Harness, use natural language for text-to-image, image-to-image, text-to-video, image-to-video, reference-image creation, task tracking, and result previews.

DSH desktop plugin: Orca-style embedded browser and Design Mode (screenshot, inspect, insert into chat).

DSH 插件:接管 DeepSeek 官方 provider 路由并补 image 输入模态声明,让图片消息通过 apiproxy 准入预检(实际图片由 image-bridge 等插件在 agent/pre-step 转成文字)

dsh 插件：给文本模型补一双眼睛 + 给多模态模型补一对观察 UI 渲染的眼睛 —— 设置弹窗选视觉模型 + meow_vision 工具 + meow_preview 组件截图工具

DeepSeek Harness (DSH) native plugin: the describe_image tool, a vision bridge (image -> mimo-v2.5 -> text description) over the ctx.fs / ctx.credentials seams

MinerU document parsing plugin for DSH (DeepSeek Harness): dual-mode cloud parsing (free Agent API / Standard API with token, auto-routing), agent tools and a browser panel with drag-drop upload.

全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据。

DeepSeek Harness plugin: drag images into the composer and get a file path back, so text-only models can read them via the read tool.

OMX 风格工作流技能集（oh-my-deepseek-harness）：移植自 oh-my-codex（MIT）的 deep-interview / ralplan / ralph / plan / autopilot / team / code-review 等技能，全部重写为 DeepSeek Harness 原生机制（goal / workflow / ralph / subagent / ask_user_question 工具），不含视觉技能。

Oh My DSH — tiered model routing for DeepSeek Harness: think/build tiers, an automatic vision tier for images, and image generation through an ordinary chat model (e.g. gpt-5.6-luna on opencode-go), all configured from an 'oh my dsh' settings tab. Works in the Web (Desktop) surface and in the terminal (TUI).

Pasting non-image files into the web composer inserts their paths as @file references (host-side clipboard reading).

Let your AI agent see and operate a real Android phone — vision + UI-tree fusion over adb, for any MCP client

Playwright browser automation tools for DSH: open pages, click, type, fill, extract, screenshot.

Sage GUI Toolkit — Windows desktop control tools (screen layout / annotated screenshot / click / type / key / scroll / wait / window / UIA structured query) via PowerShell + SendInput + UIAutomation, DPI-aware and multi-monitor safe

便签 (sticky notes) client plugin for the dsh webui: floating, resizable post-it notes with markdown text and image notes, per-conversation binding, archived in browser localStorage.

泰山识图 Taishan Vision - 让 DeepSeek Harness 纯文本模型也能识图:GLM 视觉识别 + 所选模型推理(静态插件包,重启永久生效;由鲸晴 JingQing v1.1.8 魔改)

taxue 画师：图片/视频提示词反推、审计优化与多供应商生图的一体化 DSH 工具链。