Improve error logging and add user guidance for issue reporting

- Added fatal log in `login.go` for Cloud AI API enablement check failures, prompting users to report issues.
- Enhanced error logging in `client.go` with warning messages directing users to copy and provide error details when creating issues.

.goreleaser.yml

@@ -14,4 +14,5 @@ archives:
     files:
       - LICENSE
       - README.md
+      - README_CN.md
       - config.yaml

README.md

@@ -1,5 +1,7 @@
 # CLI Proxy API
 
+English | [中文](README_CN.md)
+
 A proxy server that provides an OpenAI/Gemini/Claude compatible API interface for CLI. This allows you to use CLI models with tools and libraries designed for the OpenAI/Gemini/Claude API.
 
 ## Features
@@ -149,10 +151,13 @@ The server uses a YAML configuration file (`config.yaml`) located in the project
 ### Configuration Options
 
 | Parameter                             | Type     | Default            | Description                                                                                  |
-|-------------------------------|----------|--------------------|----------------------------------------------------------------------------------------------|
+|---------------------------------------|----------|--------------------|----------------------------------------------------------------------------------------------|
 | `port`                                | integer  | 8317               | The port number on which the server will listen                                              |
 | `auth-dir`                            | string   | "~/.cli-proxy-api" | Directory where authentication tokens are stored. Supports using `~` for home directory      |
 | `proxy-url`                           | string   | ""                 | Proxy url, support socks5/http/https protocol, example: socks5://user:pass@192.168.1.1:1080/ |
+| `quota-exceeded`                      | object   | {}                 | Configuration for handling quota exceeded                                                    |
+| `quota-exceeded.switch-project`       | boolean  | true               | Whether to automatically switch to another project when a quota is exceeded                  |
+| `quota-exceeded.switch-preview-model` | boolean  | true               | Whether to automatically switch to a preview model when a quota is exceeded                  |
 | `debug`                               | boolean  | false              | Enable debug mode for verbose logging                                                        |
 | `api-keys`                            | string[] | []                 | List of API keys that can be used to authenticate requests                                   |
 | `generative-language-api-key`         | string[] | []                 | List of Generative Language API keys                                                         |
@@ -169,6 +174,14 @@ auth-dir: "~/.cli-proxy-api"
 # Enable debug logging
 debug: false
 
+# Proxy url, support socks5/http/https protocol, example: socks5://user:pass@192.168.1.1:1080/
+proxy-url: ""
+
+# Quota exceeded behavior
+quota-exceeded:
+   switch-project: true # Whether to automatically switch to another project when a quota is exceeded
+   switch-preview-model: true # Whether to automatically switch to a preview model when a quota is exceeded
+
 # API keys for authentication
 api-keys:
   - "your-api-key-1"

README_CN.md

@@ -0,0 +1,254 @@
+# CLI 代理 API
+
+[English](README.md) | 中文
+
+一个为 CLI 提供 OpenAI/Gemini/Claude 兼容 API 接口的代理服务器。这让您可以摆脱终端界面的束缚，将 Gemini 的强大能力以 API 的形式轻松接入到任何您喜爱的客户端或应用中。
+
+## 功能特性
+
+- 为 CLI 模型提供 OpenAI/Gemini/Claude 兼容的 API 端点
+- 支持流式和非流式响应
+- 函数调用/工具支持
+- 多模态输入支持（文本和图像）
+- 多账户支持与负载均衡
+- 简单的 CLI 身份验证流程
+- 支持 Gemini AIStudio API 密钥
+- 支持 Gemini CLI 多账户轮询
+
+## 安装
+
+### 前置要求
+
+- Go 1.24 或更高版本
+- 有权访问 CLI 模型的 Google 账户
+
+### 从源码构建
+
+1. 克隆仓库：
+   ```bash
+   git clone https://github.com/luispater/CLIProxyAPI.git
+   cd CLIProxyAPI
+   ```
+
+2. 构建应用程序：
+   ```bash
+   go build -o cli-proxy-api ./cmd/server
+   ```
+
+## 使用方法
+
+### 身份验证
+
+在使用 API 之前，您需要使用 Google 账户进行身份验证：
+
+```bash
+./cli-proxy-api --login
+```
+
+如果您是旧版 gemini code 用户，可能需要指定项目 ID：
+
+```bash
+./cli-proxy-api --login --project_id <your_project_id>
+```
+
+### 启动服务器
+
+身份验证完成后，启动服务器：
+
+```bash
+./cli-proxy-api
+```
+
+默认情况下，服务器在端口 8317 上运行。
+
+### API 端点
+
+#### 列出模型
+
+```
+GET http://localhost:8317/v1/models
+```
+
+#### 聊天补全
+
+```
+POST http://localhost:8317/v1/chat/completions
+```
+
+请求体示例：
+
+```json
+{
+  "model": "gemini-2.5-pro",
+  "messages": [
+    {
+      "role": "user",
+      "content": "你好，你好吗？"
+    }
+  ],
+  "stream": true
+}
+```
+
+### 与 OpenAI 库一起使用
+
+您可以通过将基础 URL 设置为本地服务器来将此代理与任何 OpenAI 兼容的库一起使用：
+
+#### Python（使用 OpenAI 库）
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="dummy",  # 不使用但必需
+    base_url="http://localhost:8317/v1"
+)
+
+response = client.chat.completions.create(
+    model="gemini-2.5-pro",
+    messages=[
+        {"role": "user", "content": "你好，你好吗？"}
+    ]
+)
+
+print(response.choices[0].message.content)
+```
+
+#### JavaScript/TypeScript
+
+```javascript
+import OpenAI from 'openai';
+
+const openai = new OpenAI({
+  apiKey: 'dummy', // 不使用但必需
+  baseURL: 'http://localhost:8317/v1',
+});
+
+const response = await openai.chat.completions.create({
+  model: 'gemini-2.5-pro',
+  messages: [
+    { role: 'user', content: '你好，你好吗？' }
+  ],
+});
+
+console.log(response.choices[0].message.content);
+```
+
+## 支持的模型
+
+- gemini-2.5-pro
+- gemini-2.5-flash
+- 并且自动切换到之前的预览版本
+
+## 配置
+
+服务器默认使用位于项目根目录的 YAML 配置文件（`config.yaml`）。您可以使用 `--config` 标志指定不同的配置文件路径：
+
+```bash
+./cli-proxy --config /path/to/your/config.yaml
+```
+
+### 配置选项
+
+| 参数                                    | 类型       | 默认值                | 描述                                                                     |
+|---------------------------------------|----------|--------------------|------------------------------------------------------------------------|
+| `port`                                | integer  | 8317               | 服务器监听的端口号                                                              |
+| `auth-dir`                            | string   | "~/.cli-proxy-api" | 存储身份验证令牌的目录。支持使用 `~` 表示主目录                                             |
+| `proxy-url`                           | string   | ""                 | 代理 URL，支持 socks5/http/https 协议，示例：socks5://user:pass@192.168.1.1:1080/ |
+| `quota-exceeded`                      | object   | {}                 | 处理配额超限的配置                                                              |
+| `quota-exceeded.switch-project`       | boolean  | true               | 当配额超限时是否自动切换到另一个项目                                                     |
+| `quota-exceeded.switch-preview-model` | boolean  | true               | 当配额超限时是否自动切换到预览模型                                                      |
+| `debug`                               | boolean  | false              | 启用调试模式以进行详细日志记录                                                        |
+| `api-keys`                            | string[] | []                 | 可用于验证请求的 API 密钥列表                                                      |
+| `generative-language-api-key`         | string[] | []                 | 生成式语言 API 密钥列表                                                         |
+
+### 配置文件示例
+
+```yaml
+# 服务器端口
+port: 8317
+
+# 身份验证目录（支持 ~ 表示主目录）
+auth-dir: "~/.cli-proxy-api"
+
+# 启用调试日志
+debug: false
+
+# 代理 URL，支持 socks5/http/https 协议，示例：socks5://user:pass@192.168.1.1:1080/
+proxy-url: ""
+
+# 配额超限行为
+quota-exceeded:
+   switch-project: true # 当配额超限时是否自动切换到另一个项目
+   switch-preview-model: true # 当配额超限时是否自动切换到预览模型
+
+# 用于本地身份验证的 API 密钥
+api-keys:
+  - "your-api-key-1"
+  - "your-api-key-2"
+
+# AIStduio Gemini API 的 API 密钥
+generative-language-api-key:
+  - "AIzaSy...01"
+  - "AIzaSy...02"
+  - "AIzaSy...03"
+  - "AIzaSy...04"
+```
+
+### 身份验证目录
+
+`auth-dir` 参数指定身份验证令牌的存储位置。当您运行登录命令时，应用程序将在此目录中创建包含 Google 账户身份验证令牌的 JSON 文件。多个账户可用于轮询。
+
+### API 密钥
+
+`api-keys` 参数允许您定义可用于验证对代理服务器请求的 API 密钥列表。在向 API 发出请求时，您可以在 `Authorization` 标头中包含其中一个密钥：
+
+```
+Authorization: Bearer your-api-key-1
+```
+
+### 官方生成式语言 API
+
+`generative-language-api-key` 参数允许您定义可用于验证对官方 AIStudio Gemini API 请求的 API 密钥列表。
+
+## Gemini CLI 多账户负载均衡
+
+启动 CLI 代理 API 服务器，然后将 `CODE_ASSIST_ENDPOINT` 环境变量设置为 CLI 代理 API 服务器的 URL。
+
+```bash
+export CODE_ASSIST_ENDPOINT="http://127.0.0.1:8317"
+```
+
+服务器将中继 `loadCodeAssist`、`onboardUser` 和 `countTokens` 请求。并自动在多个账户之间轮询文本生成请求。
+
+> [!NOTE]  
+> 此功能仅允许本地访问，因为找不到一个可以验证请求的方法。   
+> 所以只能强制只有 `127.0.0.1` 可以访问。
+
+## 使用 Docker 运行
+
+运行以下命令进行登录：
+
+```bash
+docker run --rm -p 8085:8085 -v /path/to/your/config.yaml:/CLIProxyAPI/config.yaml -v /path/to/your/auth-dir:/root/.cli-proxy-api eceasy/cli-proxy-api:latest /CLIProxyAPI/CLIProxyAPI --login
+```
+
+运行以下命令启动服务器：
+
+```bash
+docker run --rm -p 8317:8317 -v /path/to/your/config.yaml:/CLIProxyAPI/config.yaml -v /path/to/your/auth-dir:/root/.cli-proxy-api eceasy/cli-proxy-api:latest
+```
+
+## 贡献
+
+欢迎贡献！请随时提交 Pull Request。
+
+1. Fork 仓库
+2. 创建您的功能分支（`git checkout -b feature/amazing-feature`）
+3. 提交您的更改（`git commit -m 'Add some amazing feature'`）
+4. 推送到分支（`git push origin feature/amazing-feature`）
+5. 打开 Pull Request
+
+## 许可证
+
+此项目根据 MIT 许可证授权 - 有关详细信息，请参阅 [LICENSE](LICENSE) 文件。

internal/api/claude-code-handlers.go

@@ -78,62 +78,16 @@ func (h *APIHandlers) ClaudeMessages(c *gin.Context) {
 	// This loop implements a sophisticated load balancing and failover mechanism
 outLoop:
 	for {
-		// Thread-safe client index rotation to distribute load evenly
-		// This ensures fair usage across all available clients
-		mutex.Lock()
-		startIndex := lastUsedClientIndex
-		currentIndex := (startIndex + 1) % len(h.cliClients)
-		lastUsedClientIndex = currentIndex
-		mutex.Unlock()
-
-		// Build a list of available clients, starting from the next client in rotation
-		// This implements round-robin load balancing while filtering out quota-exceeded clients
-		reorderedClients := make([]*client.Client, 0)
-		for i := 0; i < len(h.cliClients); i++ {
-			cliClient = h.cliClients[(startIndex+1+i)%len(h.cliClients)]
-
-			// Skip clients that have exceeded their quota for the requested model
-			if cliClient.IsModelQuotaExceeded(modelName) {
-				// Log different messages based on authentication method (API key vs account)
-				if cliClient.GetGenerativeLanguageAPIKey() == "" {
-					log.Debugf("Model %s is quota exceeded for account %s, project id: %s", modelName, cliClient.GetEmail(), cliClient.GetProjectID())
-				} else {
-					log.Debugf("Model %s is quota exceeded for generative language API Key: %s", modelName, cliClient.GetGenerativeLanguageAPIKey())
-				}
-
-				cliClient = nil
-				continue
-			}
-			reorderedClients = append(reorderedClients, cliClient)
-		}
-
-		// If all clients have exceeded quota, return a 429 Too Many Requests error
-		if len(reorderedClients) == 0 {
-			c.Status(429)
-			_, _ = fmt.Fprint(c.Writer, fmt.Sprintf(`{"error":{"code":429,"message":"All the models of '%s' are quota exceeded","status":"RESOURCE_EXHAUSTED"}}`, modelName))
+		var errorResponse *client.ErrorMessage
+		cliClient, errorResponse = h.getClient(modelName)
+		if errorResponse != nil {
+			c.Status(errorResponse.StatusCode)
+			_, _ = fmt.Fprint(c.Writer, errorResponse.Error)
 			flusher.Flush()
 			cliCancel()
 			return
 		}
 
-		// Attempt to acquire a lock on an available client using non-blocking TryLock
-		// This prevents blocking when a client is busy with another request
-		locked := false
-		for i := 0; i < len(reorderedClients); i++ {
-			cliClient = reorderedClients[i]
-			if cliClient.RequestMutex.TryLock() {
-				locked = true
-				break
-			}
-		}
-
-		// If no client is immediately available, fall back to blocking on the first client
-		// This ensures the request will eventually be processed
-		if !locked {
-			cliClient = h.cliClients[0]
-			cliClient.RequestMutex.Lock()
-		}
-
 		// Determine the authentication method being used by the selected client
 		// This affects how responses are formatted and logged
 		isGlAPIKey := false

internal/api/handlers.go

@@ -86,6 +86,10 @@ func (h *APIHandlers) Models(c *gin.Context) {
 }
 
 func (h *APIHandlers) getClient(modelName string) (*client.Client, *client.ErrorMessage) {
+	if len(h.cliClients) == 0 {
+		return nil, &client.ErrorMessage{StatusCode: 500, Error: fmt.Errorf("no clients available")}
+	}
+
 	var cliClient *client.Client
 
 	// Lock the mutex to update the last used client index

internal/auth/auth.go

@@ -168,11 +168,12 @@ func getTokenFromWeb(ctx context.Context, config *oauth2.Config) (*oauth2.Token,
 	codeChan := make(chan string)
 	errChan := make(chan error)
 
-	// Create a new HTTP server.
-	server := &http.Server{Addr: "localhost:8085"}
+	// Create a new HTTP server with its own multiplexer.
+	mux := http.NewServeMux()
+	server := &http.Server{Addr: ":8085", Handler: mux}
 	config.RedirectURL = "http://localhost:8085/oauth2callback"
 
-	http.HandleFunc("/oauth2callback", func(w http.ResponseWriter, r *http.Request) {
+	mux.HandleFunc("/oauth2callback", func(w http.ResponseWriter, r *http.Request) {
 		if err := r.URL.Query().Get("error"); err != "" {
 			_, _ = fmt.Fprintf(w, "Authentication failed: %s", err)
 			errChan <- fmt.Errorf("authentication failed via callback: %s", err)

internal/client/client.go

@@ -771,6 +771,7 @@ func (c *Client) CheckCloudAPIIsEnabled() (bool, error) {
 					)
 				}
 			}
+			log.Warnf("\n\nPlease copy this message and create an issue.\n\n%s\n\n", errJson)
 			return false, nil
 		}
 		return false, err.Error

internal/cmd/login.go

@@ -73,6 +73,7 @@ func DoLogin(cfg *config.Config, projectID string) {
 		// If the check fails (returns false), the CheckCloudAPIIsEnabled function
 		// will have already printed instructions, so we can just exit.
 		if !isChecked {
+			log.Fatal("Failed to check if Cloud AI API is enabled. If you encounter an error message, please create an issue.")
 			return
 		}
 	}