📝 Refresh agent usage

README.md

@@ -44,7 +44,7 @@
 
 ## Prerequisites
 
-Before you begin, an account on [Google Cloud Platform](https://console.cloud.google.com/) is required to create a **Project** and enable these APIs for this project, in `APIs & Services -> Enable APIs and services -> + ENABLE APIS AND SERVICES`
+Before you begin, an account on [Google Cloud Platform](https://console.cloud.google.com/) is required to create a **Project** and enable these APIs for this project, in `APIs & Services -> Enable APIs and services -> + ENABLE APIS AND SERVICES`:
 
 - [YouTube Data API v3(Required)](https://console.cloud.google.com/apis/api/youtubeanalytics.googleapis.com/overview)
 - [YouTube Analytics API(Optional)](https://console.cloud.google.com/apis/api/youtubeanalytics.googleapis.com/overview)
@@ -159,20 +159,20 @@ Verify the integrity and provenance of `yutu` using its associated cryptographic
 
 ## Agent
 
-`yutu` provides an agent mode to automate YouTube workflows. Currently, the agent mode is in the experimental stage, only supports Google's Gemini models with the following environment variables set:
+`yutu` provides an agent mode to automate YouTube workflows. Currently, the agent mode is in the experimental stage under active development, only supports Google's Gemini models with the following environment variables set:
 
 ```shell
-❯ export GEMINI_MODEL=gemini-3-pro-preview
-❯ export GEMINI_API_KEY=your_gemini_api_key
+❯ export YUTU_AGENT_MODEL=gemini-3-pro-preview
+❯ export YUTU_LLM_API_KEY=your_gemini_api_key
 // Optional settings
 ❯ export GOOGLE_GEMINI_BASE_URL=https://generativelanguage.googleapis.com/
 ❯ export YUTU_AGENT_INSTRUCTION=Your custom instruction here
 ```
 
-Then run the following command to start the agent:
+Then run the following command for detail usage:
+
 ```
-❯ yutu agent console        // interactive console mode
-❯ yutu agent web api webui  // webui mode for debugging
+❯ yutu agent --help
 ```
 
 ## MCP Server

README_zh.md

@@ -44,7 +44,7 @@
 
 ## 前提条件
 
-开始之前，您需要在 [Google Cloud Platform](https://console.cloud.google.com/) 上创建一个账户来创建**项目**，并为该项目启用以下 API，位置在 `APIs & Services -> Enable APIs and services -> + ENABLE APIS AND SERVICES`
+开始之前，您需要在 [Google Cloud Platform](https://console.cloud.google.com/) 上创建一个账户来新建**项目**，并为该项目启用以下 API，位置在 `APIs & Services -> Enable APIs and services -> + ENABLE APIS AND SERVICES`:
 
 - [YouTube Data API v3（必需）](https://console.cloud.google.com/apis/api/youtubeanalytics.googleapis.com/overview)
 - [YouTube Analytics API（可选）](https://console.cloud.google.com/apis/api/youtubeanalytics.googleapis.com/overview)
@@ -157,6 +157,24 @@ yutu 有两个可用的 action，一个是通用 action，另一个专用于上
 ❯ gh attestation verify $(where.exe yutu.exe) --repo eat-pray-ai/yutu
 ```
 
+## Agent
+
+`yutu` 提供了一种 Agent 模式来自动化 YouTube 工作流程。目前，Agent 模式仍处于实验阶段且正在积极开发中，仅支持 Google 的 Gemini 模型，需设置以下环境变量：
+
+```shell
+❯ export YUTU_AGENT_MODEL=gemini-3-pro-preview
+❯ export YUTU_LLM_API_KEY=your_gemini_api_key
+// 可选设置
+❯ export GOOGLE_GEMINI_BASE_URL=https://generativelanguage.googleapis.com/
+❯ export YUTU_AGENT_INSTRUCTION=Your custom instruction here
+```
+
+然后运行以下命令查看详细用法：
+
+```
+❯ yutu agent --help
+```
+
 ## MCP 服务器
 
 [![在 VS Code 中安装](https://img.shields.io/badge/VS_Code-Install_Server-0098FF?style=for-the-badge&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=yutu&config=%7B%22type%22%3A%20%22stdio%22%2C%22command%22%3A%20%22yutu%22%2C%22args%22%3A%20%5B%22mcp%22%5D%2C%22env%22%3A%20%7B%22YUTU_CREDENTIAL%22%3A%20%22%2Fabsolute%2Fpath%2Fto%2Fclient_secret.json%22%2C%22YUTU_CACHE_TOKEN%22%3A%20%22%2Fabsolute%2Fpath%2Fto%2Fyoutube.token.json%22%7D%7D)

docs/CONTRIBUTING.md

@@ -95,6 +95,7 @@ bazel-bin/yutu_
     -c "eat-pray-ai & OpenWaygate" \
     -f LICENSE \
     -s=only \
+    -y $(date +%Y) \
     -ignore "**/*.yml" \
     -ignore "**/*.yaml" \
     -ignore "**/*.bazel" .