v1.16.0

# English

## v1.16.0

### Highlights

#### Jev 1.4 support: faster, lower-cost visual E2E testing

Midscene now supports Jev 1.4, continuing our focus on visual understanding to drive UI automation. With this integration, developers can experience faster, lower-cost E2E testing. See the [Jev configuration guide](https://midscenejs.com/model-common-config#jev) for setup instructions and the current experimental limitations.

In the tile-matching game test shown in the demo below, 28 model calls were made, with model inference averaging **393.57 ms (approximately 0.39 seconds) per call**. Each call averaged **5,025 input tokens** and **67 output tokens**, at a model cost of approximately **$0.000211 per call**. This is calculated at $0.042 per million input tokens, with output tokens free of charge.


https://github.com/user-attachments/assets/22d6b274-dea5-4c5f-b71b-bb092eb5c931



### Changes

**Full Changelog**: https://github.com/web-infra-dev/midscene/compare/v1.15.6...v1.16.0

# 中文

## v1.16.0

### 亮点

#### 接入 Jev 1.4：更快、更低成本的视觉 E2E 测试

Midscene 现已接入 Jev 1.4，继续沿着视觉理解的道路推进 UI 自动化。通过此次接入，开发者可以体验更快、更低成本的 E2E 测试。接入步骤和当前的实验性限制详见 [Jev 配置指南](https://midscenejs.com/zh/model-common-config#jev)。

在下方 Demo 的连连看游戏测试中，共进行了 28 次模型调用，平均每次模型推理耗时 **393.57 ms（约 0.39 秒）**。平均每次输入 **5,025 Token**、输出 **67 Token**，模型调用费用约 **$0.000211/次**。费用按输入 $0.042 / 百万 Token 计算，输出免费。

<video src="https://lf3-static.bytednsdoc.com/obj/eden-cn/luljzkpt/ljhwZthlaukjlkulzlp/showcases/jev/tile-matching-jev.mp4" controls></video>

### 完整变更

**Full Changelog**: https://github.com/web-infra-dev/midscene/compare/v1.15.6...v1.16.0