@mengruo/dsh-vision-toolkit 0.1.4 → 0.1.5

package/README.md

@@ -6,12 +6,6 @@
 
 # DSH Vision Toolkit
 
-<a href="https://trendshift.io/repositories/149708?utm_source=trendshift-badge&amp;utm_medium=badge&amp;utm_campaign=badge-trendshift-149708" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/trendshift/repositories/149708/daily?language=TypeScript" alt="Anionex%2Fdsh-vision-toolkit | Trendshift" width="250" height="55"/></a>
-
-[![Recommended by dshfind](https://img.shields.io/badge/recommended%20by-dshfind-FFD700?style=flat-square)](https://dshfind.com/en/plugins/Anionex/dsh-vision-toolkit)
-[![dshfind score: 94 — highest-rated plugin](https://img.shields.io/badge/dshfind%20score-94%20%7C%20highest--rated%20plugin-5B4CF0?style=flat-square)](https://dshfind.com/en/plugins/Anionex/dsh-vision-toolkit)
-[![agentic leaderboard](https://www.theagenticleaderboard.com/badges/new/dsh-vision-toolkit.svg)](https://www.theagenticleaderboard.com)
-
 [![npm](https://img.shields.io/npm/v/@mengruo/dsh-vision-toolkit?style=flat-square&color=5B4CF0)](https://www.npmjs.com/package/@mengruo/dsh-vision-toolkit)
 [![MIT](https://img.shields.io/badge/license-MIT-0B7285?style=flat-square)](LICENSE)
 [![DSH](https://img.shields.io/badge/DSH-Web%20%2B%20Headless-5B4CF0?style=flat-square)](cordis.patch.yml)
@@ -20,28 +14,23 @@
 
 🚀 Paste an image and ask directly | Install with one command | Broad use cases
 
-[Highlights](#highlights) | [Quick start](#quick-start-three-steps) | [Toolbox](#toolbox) | [Configuration and limits](#configuration-and-limits) | [Troubleshooting](#troubleshooting) | [Community](#development-and-community)
+[Highlights](#highlights) | [Quick start](#quick-start-three-steps) | [Toolbox](#toolbox) | [Configuration and limits](#configuration-and-limits) | [Troubleshooting](#troubleshooting) | [Development](#development)
 
 🌐 **English** | [中文](README.zh.md)
 
 </div>
 
-🏆 This project is the first comprehensive vision-tool plugin in the DeepSeek Harness ecosystem: it was initiated before internal beta and built during the beta with reference to [`agent-vision-toolkit`](https://github.com/Anionex/agent-vision-toolkit).
-
-> **Original work:** The system and division of responsibilities behind these visual tools, together with the `vision-skills` Skill, were personally created and continuously refined by the author through long-term real-world use and repeated iteration.
-
-> If this project helps you or gives you some inspiration, feel free to star 🌟 & fork.
+> **Upstream:** [Anionex/dsh-vision-toolkit](https://github.com/Anionex/dsh-vision-toolkit) — this is a fork of that project.
 
 ## Highlights
 
 - **Paste an image and ask directly.** In DSH Web, pasting an image switches the text-only model to its `(Vision Toolkit)` variant automatically — no manual path copying or model changes. Native thumbnails, session history, and workspace paths stay intact; Web can preview artifacts.
 - **One command to install.** After installation, configure a vision provider in **Settings → Vision Toolkit** and start using the tools.
 - **Not just a caption — the content that matters.** The model does not produce a generic description; it extracts evidence around the current task, such as “Where is the error?” or “Where is the button?”.
+- **More than one provider, with fallback.** Configure multiple vision providers; routes, streaming, and automatic fallback are handled by policy for better availability and stability.
 - **A battle-tested visual-task methodology.** The bundled Skill tells the agent what to look at for different visual tasks, which tool to choose, how to proceed, and how to verify the result.
 
-[`agent-vision-toolkit`](https://github.com/Anionex/agent-vision-toolkit) gives an agent more than image captions: it can read, locate, crop, trace, rebuild, and verify visual work. DSH Vision Toolkit is its native DeepSeek Harness integration, bringing that workflow into Web and Headless Profiles.
-
-This project has two layers:
+This project brings a visual-task working method into DeepSeek Harness. It has two layers:
 
 1. **Visual tools and a Skill:** the agent learns when to inspect, ground, OCR, crop, trace, or compare pixels.
 2. **Native DSH integration:** those capabilities live inside Profiles, sessions, Settings, Artifacts, and the Web UI.
@@ -50,50 +39,16 @@ This project has two layers:
 dsh plugin --profile web add @mengruo/dsh-vision-toolkit
 ```
 
-**Upstream toolkit:** [Anionex/agent-vision-toolkit](https://github.com/Anionex/agent-vision-toolkit) · **Project website:** [agent-vision.anionex.me](https://agent-vision.anionex.me)
-
-## ❤️ Sponsor
-
-> Want to sponsor this project? See [FUNDING.md](FUNDING.md) or email davidyang042@gmail.com.
-
-<details open>
-<summary>Click to collapse</summary>
-
-<table>
-<tr>
-<td width="220" align="center" valign="middle"><a href="https://aihubmix.com/?aff=sinZ"><img src="assets/logo_aihubmix.png" alt="AIHubMix" height="48"></a></td>
-<td valign="middle">Thanks to <a href="https://aihubmix.com/?aff=sinZ">AIHubMix</a> for sponsoring this project! AIHubMix is a stable, high-concurrency AI model API gateway that connects Claude, GPT, Gemini, DeepSeek, and other mainstream models through a single API key, compatible with multiple protocols, with <b>free model options</b> available. To sign up, use the <a href="https://aihubmix.com/?aff=sinZ">AIHubMix entry</a> outside mainland China or the <a href="https://inferera.com/?aff=sinZ">Inferera entry</a> within mainland China.</td>
-</tr>
-<tr>
-<td width="220" align="center" valign="middle"><a href="https://api.ewo.so/register?aff=U6PT7J"><img src="assets/logo_eapi_dark.png" alt="E-API" height="48"></a></td>
-<td valign="middle">Thanks to <a href="https://api.ewo.so/register?aff=U6PT7J">E-API</a> for sponsoring this project! E-API aggregates mainstream AI models behind OpenAI-, Anthropic-, and Codex-compatible APIs, with selected Claude models up to <b>98% below official prices</b> and DeepSeek V4 models about <b>25% below official prices</b>.</td>
-</tr>
-</table>
-
-</details>
-
 **Contents**
 
 - [Highlights](#highlights)
-- [Recent updates](#recent-updates)
 - [Who it is for](#who-it-is-for)
 - [See it in action](#see-it-in-action)
 - [Quick start: three steps](#quick-start-three-steps)
 - [Toolbox](#toolbox)
 - [Configuration and limits](#configuration-and-limits)
 - [Troubleshooting](#troubleshooting)
-- [Donation](#donation)
-- [Development and community](#development-and-community)
-
-## Recent updates
-
-- **2026-08-20 · AIHubMix setup guide:** Added a screenshot-based guide for getting an API key through the Inferera entry and configuring the Gemini 3.7 Flash vision model; Settings now links directly to this guide.
-- **2026-08-19 · Transparent routing by default:** The model selector keeps one entry per model with the original name, and image input (paste, history, `read_image`) works without manually switching to a `(Vision Toolkit)` variant. Disable “Transparent variant routing” in advanced settings → image input to restore the explicit entries.
-- **2026-08-16 · Windows Python:** Added Microsoft Store Python support, fixing first-time isolated-runtime setup failures for affected Windows users.
-- **2026-08-17 · Vision upgrade:** Switched the default model to Gemini 3.7 Flash and fixed Qwen/Gemini bounding-box coordinate order.
-- **2026-08-16 · Image paste:** Text-only routes now switch to a `(Vision Toolkit)` variant and keep a workspace path, fixing blocked pastes and images that could not be reused later.
-- **2026-08-16 · Service stability:** Expanded service capacity to reduce peak-time `429` responses.
-- **2026-08-16 · Real model test:** Added a full image-request test in Settings, fixing the false confidence caused by a successful `/models` request to a model that still cannot process images.
+- [Development](#development)
 
 ## Who it is for
 
@@ -276,6 +231,8 @@ You can also configure a Profile patch:
 
 OpenAI Chat Completions-compatible endpoints and Anthropic Messages are supported. The Web Settings panel exposes the full provider, runtime, timeout, image-limit, and image-input-variant configuration.
 
+Requests are non-streaming by default. For endpoints with weak non-streaming support or that time out on long outputs, set `stream: true` on an individual provider (or enable the "Streaming" toggle in Web Settings) to request the completion over SSE. Streamed responses are accumulated into the full text inside the Python client before returning, so the tool interface and result shape are unchanged.
+
 The advanced **Default save directory** setting can place artifacts, pasted images, and caches below an absolute POSIX shared root such as `/tmp/dsh-vision-toolkit`; the plugin creates a private mode-0700 child for the current user and workspace. Leaving it blank keeps the existing workspace-local `.dsh-vision-toolkit` directory. Configured shared roots are currently rejected on Windows because their ownership and access-control lists cannot yet be verified safely.
 
 When the configured save directory changes, the plugin retains earlier validated roots as read-only input locations. Web Profiles persist that history in the plugin-owned `vision_toolkit_storage` storage-domain sidecar, including when the active Settings provider is read-only, so existing pasted-image paths remain usable after a Profile restart. Custom Profiles should compose `@deepseek-ai/dsh-storage-domain` when they use configured shared storage.
@@ -308,27 +265,11 @@ For advanced setups — overriding `runtime.python`, using `runtime.mode: extern
 
 No. Each inspection sends only the necessary intent and the image to the multimodal model, and context does not accumulate across calls, so the added cost stays small. To reduce it further, a locally deployed small multimodal side model (for example the Gemma 4 or Qwen 3.5/3.6 series) can provide the vision capability.
 
-## Donation
-
-If this project is valuable to you, you are welcome to buy the developer a coffee ☕️
-
-<img width="240" alt="WeChat reward code" src="assets/wechat-reward.png" />
-
-## Development and community
-
-- Read [CONTRIBUTING.md](CONTRIBUTING.md) before contributing.
-- Use [GitHub Issues](https://github.com/mengruoa/dsh-vision-toolkit/issues) for bugs, focused feature requests, and usage questions; see [SUPPORT.md](SUPPORT.md) for channel guidance.
-- Report vulnerabilities privately through [SECURITY.md](SECURITY.md).
-- See [CHANGELOG.md](CHANGELOG.md) for releases and [FUNDING.md](FUNDING.md) for sponsorship details.
-- Visit upstream [agent-vision-toolkit](https://github.com/Anionex/agent-vision-toolkit) for the general toolkit, cross-agent integrations, and visual-task playbooks.
-
-<p align="center">
-  <img src="assets/community-group-qr.png" alt="QR code for the agent-vision-toolkit community group" width="240" />
-</p>
-
-I'm [anionex](https://anionex.me/), an AI-native developer who once ranked **No. 3** on GitHub's global developer trending list, with more than 16k stars across my projects. If you would like to follow my future work, [follow me on GitHub](https://github.com/Anionex).
+## Development
 
-[`agent-vision-toolkit`](https://github.com/Anionex/agent-vision-toolkit) was created by [Anionex](https://anionex.me/). This repository maintains its native DeepSeek Harness integration.
+- Use [GitHub Issues](https://github.com/mengruoa/dsh-vision-toolkit/issues) for bugs, focused feature requests, and usage questions.
+- See [CHANGELOG.md](CHANGELOG.md) for release history.
+- This is a fork of [Anionex/dsh-vision-toolkit](https://github.com/Anionex/dsh-vision-toolkit); when relevant, changes can be contributed back upstream.
 
 ## License
 

package/README.zh.md

@@ -6,12 +6,7 @@
 
 # DSH Vision Toolkit
 
-<a href="https://trendshift.io/repositories/149708?utm_source=trendshift-badge&amp;utm_medium=badge&amp;utm_campaign=badge-trendshift-149708" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/trendshift/repositories/149708/daily?language=TypeScript" alt="Anionex%2Fdsh-vision-toolkit | Trendshift" width="250" height="55"/></a>
-
-[![由 dshfind 推荐](https://img.shields.io/badge/%E7%94%B1%20dshfind-%E6%8E%A8%E8%8D%90-FFD700?style=flat-square)](https://dshfind.com/zh/plugins/Anionex/dsh-vision-toolkit)
-[![dshfind 评分：94——最高分插件](https://img.shields.io/badge/dshfind%20%E8%AF%84%E5%88%86-94%20%7C%20%E6%9C%80%E9%AB%98%E5%88%86%E6%8F%92%E4%BB%B6-5B4CF0?style=flat-square)](https://dshfind.com/zh/plugins/Anionex/dsh-vision-toolkit)
 [![npm](https://img.shields.io/npm/v/@mengruo/dsh-vision-toolkit?style=flat-square&color=5B4CF0)](https://www.npmjs.com/package/@mengruo/dsh-vision-toolkit)
-
 [![MIT](https://img.shields.io/badge/license-MIT-0B7285?style=flat-square)](LICENSE)
 [![DSH](https://img.shields.io/badge/DSH-Web%20%2B%20Headless-5B4CF0?style=flat-square)](cordis.patch.yml)
 
@@ -19,28 +14,23 @@
 
 🚀 粘贴图片，直接提问 ｜ 一行命令安装即用 ｜ 场景丰富
 
-[亮点](#亮点) ｜ [快速开始](#快速开始三步完成) ｜ [工具一览](#工具一览) ｜ [配置与限制](#配置与限制) ｜ [常见问题](#常见问题) ｜ [交流群](#开发与社区)
+[亮点](#亮点) ｜ [快速开始](#快速开始三步完成) ｜ [工具一览](#工具一览) ｜ [配置与限制](#配置与限制) ｜ [常见问题](#常见问题) ｜ [开发](#开发)
 
 🌐 [English](README.md) ｜ **中文**
 
 </div>
 
-🏆 本项目为deepseek harness生态首个综合性视觉工具插件：内测前已立项，并在内测期间参考本人的[`agent-vision-toolkit`](https://github.com/Anionex/agent-vision-toolkit)做出。
-
-> **原创声明：** 这套视觉工具的体系和划分方式，以及 `vision-skills` Skill，均由作者个人原创并持续打磨，相关工具、方法和工作流来自长期的真实使用与反复迭代。
-
-> 如果这个项目对你有帮助，或给了你一些灵感，欢迎 Star 🌟 & Fork。
+> **上游：** [Anionex/dsh-vision-toolkit](https://github.com/Anionex/dsh-vision-toolkit) —— 本仓库是该项目的 fork。
 
 ## 亮点
 
 - **粘贴图片，直接提问。** 在 DSH Web 里粘贴图片，文本模型会自动切换到看图模式变体，不需要手动复制路径或更换模型。图片保留原生缩略图、会话记录和工作区路径；Web 可以预览产物。
 - **一行命令安装即用。** 安装插件后即可在 **设置 → 视觉工具** 中配置视觉模型并开始使用。
 - **不只是看图描述，是获取图中真正需要关注的内容。** 模型不只是生成通用描述，而是围绕“报错在哪里”“按钮在哪”等当前任务提取证据。
+- **多提供商 + 自动回退。** 可配置多个视觉提供商，路由、流式请求与自动回退均由策略处理，提升可用性与稳定性。
 - **一套经过实战验证的视觉任务方法论**：项目提供的skill，会告诉 agent 面对不同视觉任务时应该看什么、选择哪个工具、按什么步骤推进，以及最后如何验证结果。
 
-[`agent-vision-toolkit`](https://github.com/Anionex/agent-vision-toolkit) 的视觉能力不只停留在图片描述：Agent 可以读取、定位、裁剪、描摹、还原和验证视觉内容。DSH Vision Toolkit 是这套工具箱面向 DeepSeek Harness 的原生接入，让它进入 Web 和 Headless Profile。
-
-本项目提供两层能力：
+本项目把一整套视觉任务方法论带进 DeepSeek Harness，提供两层能力：
 
 1. **视觉工具和 Skill**：让 Agent 知道什么时候该看图、定位、OCR、裁剪、描摹或做像素对比。
 2. **DSH 原生接入**：把这些能力放进 Profile、会话、Settings、Artifacts 和 Web 界面。
@@ -49,50 +39,16 @@
 dsh plugin --profile web add @mengruo/dsh-vision-toolkit
 ```
 
-**上游工具箱：** [Anionex/agent-vision-toolkit](https://github.com/Anionex/agent-vision-toolkit) · **项目网站：** [agent-vision.anionex.me](https://agent-vision.anionex.me)
-
-## ❤️ 赞助
-
-> 想赞助本项目？详见 [FUNDING.md](FUNDING.md) 或发送邮件到 davidyang042@gmail.com。
-
-<details open>
-<summary>点击折叠</summary>
-
-<table>
-<tr>
-<td width="220" align="center" valign="middle"><a href="https://aihubmix.com/?aff=sinZ"><img src="assets/logo_aihubmix.png" alt="AIHubMix" height="48"></a></td>
-<td valign="middle">感谢 <a href="https://aihubmix.com/?aff=sinZ">AIHubMix</a> 赞助本项目！AIHubMix 是稳定、高并发的 AI 大模型 API 聚合平台，一个 API Key 即可接入 Claude、GPT、Gemini、DeepSeek 等主流模型，兼容多种协议，并提供<b>免费模型选择</b>。注册时，海外用户请使用 <a href="https://aihubmix.com/?aff=sinZ">AIHubMix 入口</a>，中国大陆用户请使用 <a href="https://inferera.com/?aff=sinZ">Inferera 入口</a>。</td>
-</tr>
-<tr>
-<td width="220" align="center" valign="middle"><a href="https://api.ewo.so/register?aff=U6PT7J"><img src="assets/logo_eapi_dark.png" alt="E-API" height="48"></a></td>
-<td valign="middle">感谢 <a href="https://api.ewo.so/register?aff=U6PT7J">E-API</a> 赞助本项目！E-API 聚合主流 AI 模型，兼容 OpenAI、Anthropic 与 Codex 接口；部分 Claude 模型相比官方价<b>最高优惠约 98%</b>，DeepSeek V4 系列<b>优惠约 25%</b>。</td>
-</tr>
-</table>
-
-</details>
-
 **目录**
 
 - [亮点](#亮点)
-- [最近更新](#最近更新)
 - [适合谁用](#适合谁用)
 - [实际效果](#实际效果)
 - [快速开始：三步完成](#快速开始三步完成)
 - [工具一览](#工具一览)
 - [配置与限制](#配置与限制)
 - [常见问题](#常见问题)
-- [赞赏](#赞赏)
-- [开发与社区](#开发与社区)
-
-## 最近更新
-
-- **2026-08-20 · AIHubMix 申请教程：** 新增通过 Inferera 入口申请 API Key 并配置 Gemini 3.7 Flash 视觉模型的图文教程，并在视觉工具设置中直接提供入口。
-- **2026-08-19 · 透明变体路由默认开启：** 模型选择器默认只显示每个模型一项并保留原模型名，粘贴图片、历史图片和内置 `read_image` 工具都能直接使用，不再需要手动切换到 `(Vision Toolkit)` 变体；如需恢复显式条目，可在 设置 → 高级设置 → 图片输入 关闭“透明变体路由”。
-- **2026-08-16 · Windows Python：** 支持 Microsoft Store Python，解决 Windows 用户首次创建隔离环境失败的问题。
-- **2026-08-17 · 视觉升级：** 默认模型切换到 Gemini 3.7 Flash，并修复 Qwen/Gemini 检测框坐标顺序错位的问题。
-- **2026-08-16 · 图片粘贴：** 文本模型自动切换到 `(Vision Toolkit)` 变体并保留工作区路径，解决粘贴图片被拦截或后续无法复用的问题。
-- **2026-08-16 · 服务稳定性：** 扩大服务容量，减少高峰期出现 `429` 的情况。
-- **2026-08-16 · 真实模型测试：** Settings 新增完整图片请求测试，解决 `/models` 可访问却不能证明模型真的会看图的问题。
+- [开发](#开发)
 
 ## 适合谁用
 
@@ -274,6 +230,8 @@ flowchart LR
 
 支持 OpenAI Chat Completions 兼容端点和 Anthropic Messages。Web Settings 页面还可以调整超时、图片限制、并发、运行时和图片输入变体。
 
+默认使用非流式请求。对非流式支持不佳、长输出容易连接超时的端点，可为单个 provider 设置 `stream: true`（或在 Web Settings 中打开「流式请求」开关）改用以 SSE 流式方式请求补全；流式响应会在 Python 客户端内聚合成完整文本后返回，工具接口与结果结构不变。
+
 高级设置中的 **默认保存目录** 可以把产物、粘贴图片和缓存放到 `/tmp/dsh-vision-toolkit` 等 POSIX 绝对共享根目录下；插件会为当前用户和工作区创建权限为 0700 的私有子目录。留空时继续使用工作区内原有的 `.dsh-vision-toolkit` 目录。Windows 目前会拒绝配置共享根目录，因为插件尚不能安全校验其所有权和访问控制列表。
 
 配置的保存目录变更后，插件会把之前验证过的根目录保留为只读输入位置。Web Profile 会把这段历史保存在插件自有的 `vision_toolkit_storage` storage-domain sidecar 中；即使当前 Settings 提供方只读，Profile 重启后原有粘贴图片路径仍可继续使用。使用配置共享存储的自定义 Profile 应组合 `@deepseek-ai/dsh-storage-domain`。
@@ -306,27 +264,11 @@ flowchart LR
 
 不会。每次检查只把必要的意图和图片发给多模态模型，调用之间不会累积上下文，因此额外成本很小。想进一步降低成本，可以用本地部署的小型多模态侧模型（例如 Gemma 4 或 Qwen 3.5/3.6 系列）提供视觉能力。
 
-## 赞赏
-
-如果本项目对你有价值，欢迎请开发者喝杯咖啡☕️
-
-<img width="240" alt="微信收款码" src="assets/wechat-reward.png" />
-
-## 开发与社区
-
-- 贡献前请阅读 [CONTRIBUTING.md](CONTRIBUTING.md)。
-- Bug、功能建议和使用问题请提交到 [GitHub Issues](https://github.com/mengruoa/dsh-vision-toolkit/issues)；渠道说明见 [SUPPORT.md](SUPPORT.md)。
-- 安全漏洞请按 [SECURITY.md](SECURITY.md) 私下报告。
-- 版本变化见 [CHANGELOG.md](CHANGELOG.md)，赞助说明见 [FUNDING.md](FUNDING.md)。
-- 通用视觉工具、跨 Agent 接入和视觉任务方法论请访问上游 [agent-vision-toolkit](https://github.com/Anionex/agent-vision-toolkit)。
-
-<p align="center">
-  <img src="assets/community-group-qr.png" alt="agent-vision-toolkit 项目交流群二维码" width="240" />
-</p>
-
-我是 [anionex](https://anionex.me/)，一位 AI 原生开发者，曾位列 GitHub 全球开发者趋势榜第 **3** 名，项目累计超过 16k stars。想了解我后续的工作，欢迎在 [GitHub](https://github.com/Anionex) 关注我。
+## 开发
 
-[`agent-vision-toolkit`](https://github.com/Anionex/agent-vision-toolkit) 由 [Anionex](https://anionex.me/) 创建。本仓库维护它面向 DeepSeek Harness 的原生集成。
+- Bug、功能建议和使用问题请提交到 [GitHub Issues](https://github.com/mengruoa/dsh-vision-toolkit/issues)。
+- 版本变化见 [CHANGELOG.md](CHANGELOG.md)。
+- 本仓库是 [Anionex/dsh-vision-toolkit](https://github.com/Anionex/dsh-vision-toolkit) 的 fork；如有合适的改动欢迎回馈给上游。
 
 ## 许可证