@mengruo/dsh-vision-toolkit 0.0.1 → 0.1.0

package/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write dsh-vision-toolkit/README.md
-README.md: f38885c9ef8b326808f9a43c8433e9e6a5c929db
-README.zh.md: 06e3133487ea5465a8c81e04a1a98308217c8432
+README.md: bceb6b5dfaa5dcf528704a4e15403de96f145d85
+README.zh.md: 2b45a75b4be7cf991c1c151ef9dcf5344f0ed639

package/README.md

@@ -18,7 +18,7 @@
 
 **A more powerful vision toolkit—give text-only models in DeepSeek Harness eyes: image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks in one toolkit and Skill.**
 
-🚀 Paste an image and ask directly | Install with one command | Built-in free vision | Broad use cases
+🚀 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)
 
@@ -35,8 +35,7 @@
 ## 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.** The built-in free Gemini 3.7 Flash vision service is ready after installation, with no API key required.
-- **Built-in free vision quota.** The shared service works immediately after installation with a quota of **100 images per machine per day**.
+- **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?”.
 - **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.
 
@@ -45,9 +44,7 @@
 This project 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, with a free Gemini 3.7 Flash vision service ready after installation.
-
-> **Install and use it immediately.** The default setup includes a free Gemini 3.7 Flash vision service and requires no API key.
+2. **Native DSH integration:** those capabilities live inside Profiles, sessions, Settings, Artifacts, and the Web UI.
 
 ```sh
 dsh plugin --profile web add @mengruo/dsh-vision-toolkit
@@ -64,8 +61,12 @@ dsh plugin --profile web add @mengruo/dsh-vision-toolkit
 
 <table>
 <tr>
-<td width="220"><a href="https://aihubmix.com/?aff=5wj6sgx8"><img src="assets/logo_aihubmix.png" alt="AIHubMix" height="48"></a></td>
-<td>Thanks to <a href="https://aihubmix.com/?aff=5wj6sgx8">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=5wj6sgx8">AIHubMix entry</a> outside mainland China or the <a href="https://inferera.com/?aff=5wj6sgx8">Inferera entry</a> within mainland China.</td>
+<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>
 
@@ -86,12 +87,12 @@ dsh plugin --profile web add @mengruo/dsh-vision-toolkit
 
 ## Recent updates
 
-- **2026-08-20 · AIHubMix setup guide:** Added a screenshot-based guide for getting an API key through the Inferera entry and using the free Gemini 3.7 Flash vision model; Settings now links directly to this guide.
+- **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 · Free vision upgrade:** Switched the built-in no-key service to Gemini 3.7 Flash and fixed Qwen/Gemini bounding-box coordinate order.
+- **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 · More shared capacity:** Expanded the free service capacity to reduce peak-time `429` responses.
+- **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.
 
 ## Who it is for
@@ -178,7 +179,7 @@ For the full Desktop install, update, and troubleshooting walkthrough, see [Inst
 
 ### 2. Restart and check it
 
-Restart a running Web Profile, then open **Settings → Vision Toolkit**. The free provider is already configured; run **Test vision model** to confirm it is reachable.
+Restart a running Web Profile, then open **Settings → Vision Toolkit**, configure a vision provider, and run **Test vision model** to confirm it is reachable.
 
 The first start prepares an isolated runtime: the plugin prefers a system Python 3.11+; when none is found, it downloads a hash-verified standalone Python (about 35 MB) from the domestic mirror (`dsh-vision-python-bootstrap-1317715800.cos.ap-guangzhou.myqcloud.com`) on first use, falling back to the GitHub release when the mirror is unreachable. The locked runtime dependencies (Pillow, NumPy, vtracer) are installed from the Tencent Cloud PyPI mirror (`mirrors.cloud.tencent.com/pypi/simple`) first and fall back to the official PyPI index. A normal installation does not require an `agent-vision-toolkit` source checkout or a local path setting.
 
@@ -255,37 +256,11 @@ For routes that DSH positively identifies as text-only, the plugin registers a s
 
 ## Configuration and limits
 
-### Built-in free service
-
-The default setup uses:
-
-```text
-Base URL: https://vision.anionex.me/v1
-Model:    gemini-3.7-flash
-API Key:  https://agent-vision.anionex.me (filled automatically)
-```
-
-Requests that still use the previous `qwen/qwen3.6-27b` model name remain compatible and are routed to the Qwen backend.
-
-This is a shared zero-configuration entry point, not an unlimited private endpoint. Request safeguards include:
-
-| Limit | Current value |
-| --- | --- |
-| Daily quota | 100 images per machine per day |
-| Images per request | Up to 5 |
-| Image size | 4 MiB per image |
-| Decoded pixels | 20,000,000 per image |
-| Output | Up to 4,096 tokens per request |
-
-These safeguards prevent unusually large requests from monopolizing memory or request time. When shared capacity is reached, the service returns a readable `429` response with `Retry-After` instead of collapsing into an unexplained model failure.
-
-Existing clients that still send `api_key="free"` remain compatible.
-
-### Bring your own vision model
+### Configure a vision model
 
-For higher quotas, private endpoints, or another model, change the provider in **Settings → Vision Toolkit** and store the API key as a DSH Credential. Settings stores the Credential reference and never reads the saved secret back into the browser.
+Configure the vision provider in **Settings → Vision Toolkit** and store the API key as a DSH Credential. Settings stores the Credential reference and never reads the saved secret back into the browser.
 
-**Step-by-step AIHubMix tutorial:** [Get an AIHubMix API key and use free Gemini 3.7 Flash for vision](docs/aihubmix-gemini-vision.md). It includes screenshots for account/API-key setup, the exact Vision Toolkit settings, free-model selection, and troubleshooting.
+**Step-by-step AIHubMix tutorial:** [Get an AIHubMix API key and configure Gemini 3.7 Flash for vision](docs/aihubmix-gemini-vision.md). It includes screenshots for account/API-key setup, the exact Vision Toolkit settings, model selection, and troubleshooting.
 
 You can also configure a Profile patch:
 
@@ -315,7 +290,7 @@ For advanced setups — overriding `runtime.python`, using `runtime.mode: extern
 | --- | --- |
 | The vision-model test fails with `Vision API returned an incompatible response structure` | The base URL usually needs a path prefix. Local OpenAI-compatible services such as LM Studio and Ollama should be entered as `http://127.0.0.1:1234/v1` (include `/v1`); the plugin appends `/chat/completions`, and a port-only address hits an unknown endpoint and returns this error |
 | Pasting an image still says the model does not support image input | Restart the Web Profile, refresh the page, and confirm the selected route has the `(Vision Toolkit)` suffix. You can also place the image in the session workspace and invoke `/vision-skills` |
-| The free service returns 429 | Wait for the `Retry-After` interval, or switch to your own endpoint when you need stable higher volume |
+| The vision service returns 429 | Wait for the `Retry-After` interval, or switch to your own endpoint when you need stable higher volume |
 | The image exceeds a size or pixel limit | Crop or resize it first; the error identifies whether bytes or decoded pixels caused the rejection |
 | A custom Credential is missing | Enter the API key in **Settings → Vision Toolkit** and confirm the Credential name matches the provider configuration |
 | First-time runtime setup fails | The standalone-Python download needs network and disk access (domestic mirror first, GitHub fallback). Check connectivity or package-cache access, or install Python 3.11+ / configure `runtime.python` in Settings, then retry the model test |

package/README.zh.md

@@ -17,7 +17,7 @@
 
 **更强大的视觉工具箱——给 DeepSeek Harness 里的纯文本模型装上眼睛：图片问答、长图 OCR、前端 UI 还原、GUI 视觉任务，一套视觉工具箱和一个 Skill。**
 
-🚀 粘贴图片，直接提问 ｜ 一行命令安装即用 ｜ 内置免费视觉 ｜ 场景丰富
+🚀 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)
 
@@ -34,8 +34,7 @@
 ## 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。** 安装插件后默认使用内置免费 Gemini 3.7 Flash 视觉服务，不需要申请 API Key。
-- **内置免费视觉模型额度。** 安装后即可直接使用共享服务，每台机器每天有**100 张图**的免费额度。
+- **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。
 - **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。
 
@@ -46,8 +45,6 @@
 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。
 
-> **安装即可使用。** 默认接入内置免费 Gemini 3.7 Flash 视觉服务，不需要申请 API Key。
-
 ```sh
 dsh plugin --profile web add @mengruo/dsh-vision-toolkit
 ```
@@ -63,8 +60,12 @@ dsh plugin --profile web add @mengruo/dsh-vision-toolkit
 
 <table>
 <tr>
-<td width="220"><a href="https://aihubmix.com/?aff=5wj6sgx8"><img src="assets/logo_aihubmix.png" alt="AIHubMix" height="48"></a></td>
-<td>感谢 <a href="https://aihubmix.com/?aff=5wj6sgx8">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=5wj6sgx8">AIHubMix 入口</a>，中国大陆用户请使用 <a href="https://inferera.com/?aff=5wj6sgx8">Inferera 入口</a>。</td>
+<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>
 
@@ -85,12 +86,12 @@ dsh plugin --profile web add @mengruo/dsh-vision-toolkit
 
 ## 最近更新
 
-- **2026-08-20 · AIHubMix 申请教程：** 新增通过 Inferera 入口申请 API Key、使用免费 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。
+- **2026-08-20 · 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 · 免费视觉升级：** 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。
+- **2026-08-17 · 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 · 共享容量：** 扩大免费服务容量，减少高峰期出现 `429` 的情况。
+- **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。
 
 ## 适合谁用
@@ -178,7 +179,7 @@ dsh plugin --profile desktop add @mengruo/dsh-vision-toolkit
 
 ### 2. 重启并确认
 
-重启正在运行的 Web Profile，打开 **设置 → 视觉工具**。默认免费服务已经配置好；你可以直接运行**测试视觉模型**确认连接。
+重启正在运行的 Web Profile，打开 **设置 → 视觉工具**，配置视觉模型，然后运行**测试视觉模型**确认连接。
 
 首次启动会自动准备隔离运行环境：插件优先使用系统已有的 Python 3.11+；如果系统没有，会自动从国内镜像（`dsh-vision-python-bootstrap-1317715800.cos.ap-guangzhou.myqcloud.com`）下载一个带完整性校验的托管 Python（约 35MB，仅首次需要网络），镜像不可用时自动回退到 GitHub 官方发布源。锁定依赖（Pillow、NumPy、vtracer）会优先从腾讯云 PyPI 镜像（`mirrors.cloud.tencent.com/pypi/simple`）安装，镜像不可用时回退到官方 PyPI。普通安装不需要下载 `agent-vision-toolkit` 源码，也不需要设置本地路径。
 
@@ -253,37 +254,11 @@ flowchart LR
 
 ## 配置与限制
 
-### 默认免费服务
-
-默认配置使用：
-
-```text
-Base URL: https://vision.anionex.me/v1
-Model:    gemini-3.7-flash
-API Key:  https://agent-vision.anionex.me（自动填写）
-```
-
-仍然使用旧模型名 `qwen/qwen3.6-27b` 的请求保持兼容，会自动路由到 Qwen 后端。
-
-这是共享的免费入口，不是无限量私有服务。请求保护规则包括：
-
-| 限制 | 当前值 |
-| --- | --- |
-| 每日额度 | 每台机器每天 100 张图 |
-| 单次请求图片数 | 最多 5 张 |
-| 单张图片大小 | 4 MiB |
-| 单张图片像素 | 20,000,000 |
-| 单次输出 | 最多 4,096 tokens |
-
-这些保护规则避免异常大的请求占满内存或请求时间。共享容量用尽时，服务会返回带 `Retry-After` 的明确 `429` 响应，不会只得到一个含糊的“模型失败”。
-
-仍然发送 `api_key="free"` 的旧客户端可以继续使用。
-
-### 使用自己的视觉模型
+### 配置视觉模型
 
-如果你需要更高额度、私有端点或其他模型，可以在 **设置 → 视觉工具** 中修改提供方，并把 API Key 保存为 DSH Credential。Settings 只保存 Credential 引用，不会回显密钥。
+在 **设置 → 视觉工具** 中配置视觉模型提供方，并把 API Key 保存为 DSH Credential。Settings 只保存 Credential 引用，不会回显密钥。
 
-**AIHubMix 图文教程：** [申请 AIHubMix API Key，并用免费 Gemini 3.7 Flash 识图](docs/aihubmix-gemini-vision.zh.md)。教程包含账号与 API Key 获取截图、Vision Toolkit 的准确配置、免费模型选择和常见问题排查。
+**AIHubMix 图文教程：** [申请 AIHubMix API Key 并配置 Gemini 3.7 Flash 识图](docs/aihubmix-gemini-vision.zh.md)。教程包含账号与 API Key 获取截图、Vision Toolkit 的准确配置、模型选择和常见问题排查。
 
 也可以在 Profile patch 中配置：
 
@@ -313,7 +288,7 @@ API Key:  https://agent-vision.anionex.me（自动填写）
 | --- | --- |
 | 视觉模型测试失败：`Vision API returned an incompatible response structure` | 通常是 API 地址少了路径前缀。LM Studio、Ollama 等本地 OpenAI 兼容服务需填写 `http://127.0.0.1:1234/v1`（带 `/v1`），插件会在其后拼接 `/chat/completions`；只填端口号会命中服务的未知端点并返回该错误 |
 | 粘贴图片后仍提示模型不支持图片 | 重启 Web Profile 并刷新页面，确认当前模型已切换到带 `(Vision Toolkit)` 的变体；也可以把图片先放进会话工作区，再调用 `/vision-skills` |
-| 免费服务提示 429 | 按错误中的 `Retry-After` 等待后重试；如果需要稳定高额度，切换到自己的视觉端点 |
+| 视觉服务提示 429 | 按错误中的 `Retry-After` 等待后重试；如果需要稳定高额度，切换到自己的视觉端点 |
 | 图片过大或像素超限 | 先裁剪或缩放图片；错误会明确显示是字节还是像素限制 |
 | 自定义 Credential 缺失 | 在 **设置 → 视觉工具** 填写 API Key，并确认 Credential 名称与配置一致 |
 | 首次运行时准备失败 | 自动下载托管 Python 需要网络和磁盘权限（默认先走国内镜像，失败时回退 GitHub）；失败时检查网络或包缓存，也可以安装 Python 3.11+ 或在 Settings 中配置 `runtime.python`，然后重新测试 |

package/docs/aihubmix-gemini-vision.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write dsh-vision-toolkit/docs/aihubmix-gemini-vision.md
-aihubmix-gemini-vision.md: c2958163461843045fc4547e56fbaae78d1b9f72
-aihubmix-gemini-vision.zh.md: dd2ba9246bb921f4986cacfd28e31aaeec4903e3
+aihubmix-gemini-vision.md: acaab7aec126dd50b99c2950e0e37139d00be8e0
+aihubmix-gemini-vision.zh.md: 769370728d9b734b9947c9223045ac00f045f3a2

package/docs/aihubmix-gemini-vision.md

@@ -12,7 +12,7 @@ This tutorial completes three tasks:
 
 ## 1. Open the signup entry and register
 
-Open the [Inferera signup entry](https://inferera.com/?aff=5wj6sgx8), which redirects to AIHubMix, then select **Sign up** in the upper-right corner or **Get API Key** on the page.
+Open the [Inferera signup entry](https://inferera.com/?aff=sinZ), which redirects to AIHubMix, then select **Sign up** in the upper-right corner or **Get API Key** on the page.
 
 This URL includes the project's referral parameter. You can instead open [Inferera](https://inferera.com/) directly if you prefer not to use a referral link.
 
@@ -132,7 +132,7 @@ The same provider can be stored in a Profile patch. Keep the key value in DSH Cr
 
 ## Official resources
 
-- [Inferera signup entry](https://inferera.com/?aff=5wj6sgx8)
+- [Inferera signup entry](https://inferera.com/?aff=sinZ)
 - [AIHubMix API Keys](https://console.aihubmix.com/token)
 - [AIHubMix documentation](https://docs.aihubmix.com/en)
 - [Gemini 3.7 Flash (free) model page](https://aihubmix.com/model/gemini-3.7-flash-free)

package/docs/aihubmix-gemini-vision.zh.md

@@ -12,7 +12,7 @@
 
 ## 1. 打开申请入口并注册
 
-打开 [Inferera 国内申请入口](https://inferera.com/?aff=5wj6sgx8)，页面会跳转到 AIHubMix；点击右上角 **注册**，也可以点击页面中的 **立即体验**。
+打开 [Inferera 国内申请入口](https://inferera.com/?aff=sinZ)，页面会跳转到 AIHubMix；点击右上角 **注册**，也可以点击页面中的 **立即体验**。
 
 这个入口带有本项目的推荐参数；如果不想使用推荐链接，也可以直接访问 [Inferera](https://inferera.com/)。
 
@@ -132,7 +132,7 @@ gemini-3.7-flash-free
 
 ## 官方资料
 
-- [Inferera 国内申请入口](https://inferera.com/?aff=5wj6sgx8)
+- [Inferera 国内申请入口](https://inferera.com/?aff=sinZ)
 - [AIHubMix API Keys](https://console.aihubmix.com/token)
 - [AIHubMix 中文文档](https://docs.aihubmix.com/cn)
 - [Gemini 3.7 Flash (free) 模型页](https://aihubmix.com/model/gemini-3.7-flash-free)