feat: Add support for Gemini Web via cookie authentication

README.md

@@ -16,6 +16,7 @@ The first Chinese provider has now been added: [Qwen Code](https://github.com/Qw
 - OpenAI Codex support (GPT models) via OAuth login
 - Claude Code support via OAuth login
 - Qwen Code support via OAuth login
+- Gemini Web support via cookie-based login
 - Streaming and non-streaming responses
 - Function calling/tools support
 - Multimodal input support (text and images)
@@ -76,6 +77,13 @@ You can authenticate for Gemini, OpenAI, and/or Claude. All can coexist in the s
 
   Options: add `--no-browser` to print the login URL instead of opening a browser. The local OAuth callback uses port `8085`.
 
+- Gemini Web (via Cookies):
+  This method authenticates by simulating a browser, using cookies obtained from the Gemini website.
+  ```bash
+  ./cli-proxy-api --gemini-web-auth
+  ```
+  You will be prompted to enter your `__Secure-1PSID` and `__Secure-1PSIDTS` values. Please retrieve these cookies from your browser's developer tools.
+
 - OpenAI (Codex/GPT via OAuth):
   ```bash
   ./cli-proxy-api --codex-login
@@ -277,6 +285,12 @@ The server uses a YAML configuration file (`config.yaml`) located in the project
 | `openai-compatibility.*.models`         | object[] | []                 | The actual model name.                                                                                                                                                                    |
 | `openai-compatibility.*.models.*.name`  | string   | ""                 | The models supported by the provider.                                                                                                                                                     |
 | `openai-compatibility.*.models.*.alias` | string   | ""                 | The alias used in the API.                                                                                                                                                                |
+| `gemini-web`                            | object   | {}                 | Configuration specific to the Gemini Web client.                                                                                                                                          |
+| `gemini-web.context`                    | boolean  | true               | Enables conversation context reuse for continuous dialogue.                                                                                                                               |
+| `gemini-web.code-mode`                  | boolean  | false              | Enables code mode for optimized responses in coding-related tasks.                                                                                                                        |
+| `gemini-web.max-chars-per-request`      | integer  | 1,000,000          | The maximum number of characters to send to Gemini Web in a single request.                                                                                                               |
+| `gemini-web.disable-continuation-hint`  | boolean  | false              | Disables the continuation hint for split prompts.                                                                                                                                         |
+| `gemini-web.token-refresh-seconds`      | integer  | 540                | The interval in seconds for background cookie auto-refresh.                                                                                                                               |
 
 ### Example Configuration File
 
@@ -312,6 +326,13 @@ 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
 
+# Gemini Web client configuration
+gemini-web:
+  context: true # Enable conversation context reuse
+  code-mode: false # Enable code mode
+  max-chars-per-request: 1000000 # Max characters per request
+  token-refresh-seconds: 540 # Cookie refresh interval in seconds
+
 # API keys for authentication
 api-keys:
   - "your-api-key-1"
@@ -491,6 +512,12 @@ Run the following command to login (Gemini OAuth on port 8085):
 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
 ```
 
+Run the following command to login (Gemini Web Cookies):
+
+```bash
+docker run -it --rm -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 --gemini-web-auth
+```
+
 Run the following command to login (OpenAI OAuth on port 1455):
 
 ```bash
@@ -555,6 +582,10 @@ docker run --rm -p 8317:8317 -v /path/to/your/config.yaml:/CLIProxyAPI/config.ya
     ```bash
     docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI -no-browser --login
     ```
+    - **Gemini Web**:
+    ```bash
+    docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI --gemini-web-auth
+    ```
     - **OpenAI (Codex)**:
     ```bash
     docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI -no-browser --codex-login

README_CN.md

@@ -36,6 +36,7 @@
 - 新增 OpenAI Codex（GPT 系列）支持（OAuth 登录）
 - 新增 Claude Code 支持（OAuth 登录）
 - 新增 Qwen Code 支持（OAuth 登录）
+- 新增 Gemini Web 支持（通过 Cookie 登录）
 - 支持流式与非流式响应
 - 函数调用/工具支持
 - 多模态输入（文本、图片）
@@ -89,6 +90,13 @@
 
   选项：加上 `--no-browser` 可打印登录地址而不自动打开浏览器。本地 OAuth 回调端口为 `8085`。
 
+- Gemini Web (通过 Cookie):
+  此方法通过模拟浏览器行为，使用从 Gemini 网站获取的 Cookie 进行身份验证。
+  ```bash
+  ./cli-proxy-api --gemini-web-auth
+  ```
+  程序将提示您输入 `__Secure-1PSID` 和 `__Secure-1PSIDTS` 的值。请从您的浏览器开发者工具中获取这些 Cookie。
+
 - OpenAI（Codex/GPT，OAuth）：
   ```bash
   ./cli-proxy-api --codex-login
@@ -289,6 +297,12 @@ console.log(await claudeResponse.json());
 | `openai-compatibility.*.models`         | object[] | []                 | 实际的模型名称。                                                            |
 | `openai-compatibility.*.models.*.name`  | string   | ""                 | 提供商支持的模型。                                                           |
 | `openai-compatibility.*.models.*.alias` | string   | ""                 | 在API中使用的别名。                                                         |
+| `gemini-web`                            | object   | {}                 | Gemini Web 客户端的特定配置。                                                 |
+| `gemini-web.context`                    | boolean  | true               | 是否启用会话上下文重用，以实现连续对话。                                        |
+| `gemini-web.code-mode`                  | boolean  | false              | 是否启用代码模式，优化代码相关任务的响应。                                      |
+| `gemini-web.max-chars-per-request`      | integer  | 1,000,000          | 单次请求发送给 Gemini Web 的最大字符数。                                        |
+| `gemini-web.disable-continuation-hint`  | boolean  | false              | 当提示被拆分时，是否禁用连续提示的暗示。                                        |
+| `gemini-web.token-refresh-seconds`      | integer  | 540                | 后台 Cookie 自动刷新的间隔（秒）。                                            |
 
 ### 配置文件示例
 
@@ -324,6 +338,13 @@ 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
 
+# Gemini Web 客户端配置
+gemini-web:
+  context: true # 启用会话上下文重用
+  code-mode: false # 启用代码模式
+  max-chars-per-request: 1000000 # 单次请求最大字符数
+  token-refresh-seconds: 540 # Cookie 刷新间隔（秒）
+
 # 用于本地身份验证的 API 密钥
 api-keys:
   - "your-api-key-1"
@@ -499,6 +520,12 @@ auth.json:
 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
 ```
 
+运行以下命令进行登录（Gemini Web Cookie）：
+
+```bash
+docker run -it --rm -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 --gemini-web-auth
+```
+
 运行以下命令进行登录（OpenAI OAuth，端口 1455）：
 
 ```bash
@@ -564,6 +591,10 @@ docker run --rm -p 8317:8317 -v /path/to/your/config.yaml:/CLIProxyAPI/config.ya
     ```bash
     docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI -no-browser --login
     ```
+    - **Gemini Web**:
+    ```bash
+    docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI --gemini-web-auth
+    ```
     - **OpenAI (Codex)**:
     ```bash
     docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI -no-browser --codex-login