GCLI2API

https://github.com/su-kaka/gcli2api
Admin
GCLI2API converts GeminiCLI and Antigravity to OpenAI, Gemini, and Claude API compatible interfaces...
Tokens:28,559
Snippets:194
Trust Score:6
Update:6 months ago
Show doc for...
Tokens:
Raw
### Install and Start gcli2api on Linux

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Commands to install and start the service on Linux systems.

```bash
curl -o install.sh "https://raw.githubusercontent.com/su-kaka/gcli2api/refs/heads/master/install.sh" && chmod +x install.sh && ./install.sh
```

```bash
cd gcli2api
bash start.sh
```

--------------------------------

### Install and Start gcli2api on macOS

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Commands to install and start the service on macOS.

```bash
curl -o darwin-install.sh "https://raw.githubusercontent.com/su-kaka/gcli2api/refs/heads/master/darwin-install.sh" && chmod +x darwin-install.sh && ./darwin-install.sh
```

```bash
cd gcli2api
bash start.sh
```

--------------------------------

### Install and Start gcli2api on Windows

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

PowerShell command to install the service on Windows, followed by instructions to start it.

```powershell
iex (iwr "https://raw.githubusercontent.com/su-kaka/gcli2api/refs/heads/master/install.ps1" -UseBasicParsing).Content
```

```text
双击执行 start.bat
```

--------------------------------

### Install and Start gcli2api on Termux

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Commands to download the installation script and start the service in a Termux environment.

```bash
curl -o termux-install.sh "https://raw.githubusercontent.com/su-kaka/gcli2api/refs/heads/master/termux-install.sh" && chmod +x termux-install.sh && ./termux-install.sh
```

```bash
cd gcli2api
bash termux-start.sh
```

--------------------------------

### Docker Setup

Source: https://github.com/su-kaka/gcli2api/blob/master/docs/README_JA.md

Instructions for setting up gcli2api using Docker and Docker Compose.

```APIDOC
## Docker Run Example

### Description
Run gcli2api as a Docker container with MongoDB URI and API password.

### Method
`docker run`

### Endpoint
`ghcr.io/su-kaka/gcli2api:latest`

### Parameters
#### Environment Variables
- **MONGODB_URI** (string) - Required - MongoDB connection string.
- **API_PASSWORD** (string) - Required - Password for API access.
- **PORT** (integer) - Optional - Service port (default: 7861).

### Request Example
```bash
docker run -d --name gcli2api \
  -e MONGODB_URI="mongodb+srv://user:pass@cluster.mongodb.net/gcli2api" \
  -e API_PASSWORD=your_password \
  -p 7861:7861 \
  ghcr.io/su-kaka/gcli2api:latest
```

## Docker Compose Example

### Description
Set up gcli2api and MongoDB using Docker Compose.

### Method
`docker-compose up`

### Endpoint
`docker-compose.yml`

### Request Example
```yaml
version: '3.8'

services:
  mongodb:
    image: mongo:7
    container_name: gcli2api-mongodb
    restart: unless-stopped
    environment:
      MONGO_INITDB_ROOT_USERNAME: admin
      MONGO_INITDB_ROOT_PASSWORD: password123
    volumes:
      - mongodb_data:/data/db
    ports:
      - "27017:27017"

  gcli2api:
    image: ghcr.io/su-kaka/gcli2api:latest
    container_name: gcli2api
    restart: unless-stopped
    depends_on:
      - mongodb
    environment:
      - MONGODB_URI=mongodb://admin:password123@mongodb:27017/admin
      - MONGODB_DATABASE=gcli2api
      - API_PASSWORD=your_api_password
      - PORT=7861
    ports:
      - "7861:7861"

volumes:
  mongodb_data:
```
```

--------------------------------

### Run gcli2api with MongoDB using Docker

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Deploy gcli2api with MongoDB integration using Docker. This example shows a single-instance MongoDB setup and connection to MongoDB Atlas.

```bash
# 单机 MongoDB 部署
docker run -d --name gcli2api \
  -e MONGODB_URI="mongodb://mongodb:27017" \
  -e API_PASSWORD=your_password \
  --network your_network \
  ghcr.io/su-kaka/gcli2api:latest

# 使用 MongoDB Atlas
docker run -d --name gcli2api \
  -e MONGODB_URI="mongodb+srv://user:pass@cluster.mongodb.net/gcli2api" \
  -e API_PASSWORD=your_password \
  -p 7861:7861 \
ghcr.io/su-kaka/gcli2api:latest
```

--------------------------------

### Authentication API - Start Antigravity Mode Auth

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Begin the authentication flow specifically for Antigravity mode.

```bash
curl -X POST "http://127.0.0.1:7861/auth/start" \
  -H "Authorization: Bearer pwd" \
  -H "Content-Type: application/json" \
  -d '{"mode": "antigravity"}'
```

--------------------------------

### Start Docker Compose Services

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Command to start the services defined in your docker-compose.yml file in detached mode.

```bash
docker-compose up -d
```

--------------------------------

### Start gcli2api with MongoDB Support

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Run the gcli2api application. It automatically detects and uses the MongoDB configuration if MONGODB_URI is set.

```bash
# 应用会自动检测 MongoDB 配置并使用 MongoDB 存储
python web.py
```

--------------------------------

### Python SDK Integration

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Example of connecting to GCLI2API using the Google GenAI Python SDK for text and image generation.

```python
from io import BytesIO
from PIL import Image
from google.genai import Client
from google.genai.types import HttpOptions
from google.genai import types

# 创建客户端连接到 GCLI2API
client = Client(
    api_key="pwd",
    http_options=HttpOptions(base_url="http://127.0.0.1:7861"),
)

# 文本生成
response = client.models.generate_content(
    model="gemini-2.5-pro",
    contents=["请解释什么是机器学习"],
)
print(response.text)

# 图像生成（Antigravity 模式）
prompt = "画一只可爱的猫咪在阳光下玩耍"

response = client.models.generate_content(
    model="gemini-3.1-flash-image",
    contents=[prompt],
    config=types.GenerateContentConfig(
        image_config=types.ImageConfig(
            aspect_ratio="16:9",  # 横屏比例
        )
    )
)

# 处理响应
for part in response.candidates[0].content.parts:
    if part.text is not None:
        print(part.text)
    elif part.inline_data is not None:
        # 保存生成的图像
        image = Image.open(BytesIO(part.inline_data.data))
        image.save("generated_image.png")
        print("图像已保存到 generated_image.png")
```

--------------------------------

### Authentication API - Start OAuth Flow (GCLI Mode)

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Initiate the OAuth authentication process for GCLI mode, requiring a project ID. Returns an authorization URL and state.

```bash
curl -X POST "http://127.0.0.1:7861/auth/start" \
  -H "Authorization: Bearer pwd" \
  -H "Content-Type: application/json" \
  -d '{
    "project_id": "my-project-id",
    "mode": "geminicli"
  }'
```

--------------------------------

### Docker Deployment with Separate Passwords

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Example of deploying gcli2api using Docker with separate passwords for API and panel access. The PORT environment variable is also specified.

```bash
docker run -d --name gcli2api \
  -e API_PASSWORD=my_api_password \
  -e PANEL_PASSWORD=my_panel_password \
  -e PORT=7861 \
  ghcr.io/su-kaka/gcli2api:latest
```

--------------------------------

### Antigravity Claude Endpoint Request

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

This example demonstrates how to make a request to the Antigravity Claude compatible endpoint. It requires an API key and specifies the Anthropic version.

```bash
curl -X POST "http://127.0.0.1:7861/antigravity/v1/messages" \
  -H "x-api-key: your_api_password" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'
```

--------------------------------

### Thinking Model Response Example

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Example response structure for thinking models, including both the final answer and the reasoning process.

```json
{
  "choices": [{
    "message": {
      "role": "assistant",
      "content": "解: x = -2 或 x = -3",
      "reasoning_content": "让我分析这个二次方程...\n首先，我需要找到两个数..."
    },
    "finish_reason": "stop"
  }]
}
```

--------------------------------

### OpenAI-Compatible API Response Example

Source: https://context7.com/su-kaka/gcli2api/llms.txt

A JSON structure representing the model list response format.

```json
{
  "object": "list",
  "data": [
    {"id": "gemini-2.5-pro", "object": "model", "owned_by": "google"},
    {"id": "gemini-2.5-pro-high", "object": "model", "owned_by": "google"},
    {"id": "gemini-2.5-pro-search", "object": "model", "owned_by": "google"},
    {"id": "gemini-3-pro-preview", "object": "model", "owned_by": "google"}
  ]
}
```

--------------------------------

### Docker Deployment with Common Password

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Example of deploying gcli2api using Docker with a single common password for API and panel access. Ensure the PORT environment variable is set.

```bash
docker run -d --name gcli2api \
  -e PASSWORD=mypassword \
  -e PORT=7861 \
  ghcr.io/su-kaka/gcli2api:latest
```

--------------------------------

### Interact with Gemini Native Endpoints

Source: https://github.com/su-kaka/gcli2api/blob/master/docs/README_JA.md

Examples of using curl to interact with the Gemini-native API using different authentication methods.

```bash
# x-goog-api-keyヘッダーを使用
curl -X POST "http://127.0.0.1:7861/v1/models/gemini-2.5-pro:generateContent" \
  -H "x-goog-api-key: your_api_password" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {"role": "user", "parts": [{"text": "Hello"}]}
    ]
  }'

# URLパラメータを使用
curl -X POST "http://127.0.0.1:7861/v1/models/gemini-2.5-pro:streamGenerateContent?key=your_api_password" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {"role": "user", "parts": [{"text": "Hello"}]}
    ]
  }'
```

--------------------------------

### Claude API Format with System Parameter (JSON)

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Example JSON payload for the Claude API format endpoint, including the system parameter for setting assistant behavior. Supports standard Claude parameters.

```json
{
  "model": "gemini-2.5-pro",
  "max_tokens": 1024,
  "system": "You are a helpful assistant",
  "messages": [
    {"role": "user", "content": "Hello"}
  ]
}
```

--------------------------------

### Run gcli2api with Separate Passwords on Docker Mac

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Configure gcli2api on Docker Mac with separate API and panel passwords. This example includes port mapping and volume mounting for persistent data.

```bash
docker run -d \
--name gcli2api \
-p 7861:7861 \
-p 8080:8080 \
-e API_PASSWORD=api_pwd \
-e PANEL_PASSWORD=panel_pwd \
-e PORT=7861 \
-v $(pwd)/data/creds:/app/creds \
ghcr.io/su-kaka/gcli2api:latest
```

--------------------------------

### Configure MongoDB URI for gcli2api

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Set the MONGODB_URI environment variable to connect gcli2api to a MongoDB instance. Examples include local, Atlas, and authenticated connections.

```bash
# 本地 MongoDB
export MONGODB_URI="mongodb://localhost:27017"

# MongoDB Atlas 云服务
export MONGODB_URI="mongodb+srv://username:password@cluster.mongodb.net"

# 带认证的 MongoDB
export MONGODB_URI="mongodb://admin:password@localhost:27017/admin"

# 可选：自定义数据库名称（默认: gcli2api）
export MONGODB_DATABASE="my_gcli_db"
```

--------------------------------

### Credentials API - Get Status List

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Query the status of credentials, supporting pagination, filtering by status, and specifying the mode (GCLI or Antigravity).

```bash
curl -X GET "http://127.0.0.1:7861/creds/status?mode=geminicli&offset=0&limit=50&status_filter=enabled" \
  -H "Authorization: Bearer pwd"
```

--------------------------------

### Antigravity OpenAI Format Request (cURL)

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Example cURL request for the Antigravity endpoint using OpenAI format. Authentication is via the Authorization: Bearer header. Supports streaming.

```bash
curl -X POST "http://127.0.0.1:7861/antigravity/v1/chat/completions" \
  -H "Authorization: Bearer your_api_password" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5",
    "messages": [
      {"role": "user", "content": "Hello"}
    ],
    "stream": true
  }'
```

--------------------------------

### Gemini Native Generate Content Request (cURL)

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Example cURL request for generating content using the Gemini native endpoint with x-goog-api-key authentication. Ensure the Content-Type is set to application/json.

```bash
curl -X POST "http://127.0.0.1:7861/v1/models/gemini-2.5-pro:generateContent" \
  -H "x-goog-api-key: your_api_password" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {"role": "user", "parts": [{"text": "Hello"}]}
    ]
  }'
```

--------------------------------

### Gemini API Request Body Example

Source: https://github.com/su-kaka/gcli2api/blob/master/src/api/Response_example.txt

Example of a request body for the Gemini API, specifying the model and content for the request. This structure is used for both streaming and non-streaming calls.

```json
{
  "model": "gemini-2.5-flash",
  "request": {
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "Hello, tell me a joke in one sentence."
          }
        ]
      }
    ]
  }
}
```

--------------------------------

### Gemini API Streaming Response Chunk Example

Source: https://github.com/su-kaka/gcli2api/blob/master/src/api/Response_example.txt

An example of a single chunk received from a streaming Gemini API response. It includes metadata and the actual text content from the model.

```json
{
    "response": {
        "candidates": [
            {
                "content": {
                    "role": "model",     
                    "parts": [
                        {
                            "text": "Why did the scarecrow win an award? Because he was outstanding in his field."
                        }
                    ]
                },
                "finishReason": "STOP"   
            }
        ],
        "usageMetadata": {
            "promptTokenCount": 10,      
            "candidatesTokenCount": 17,  
            "totalTokenCount": 51,       
            "trafficType": "PROVISIONED_THROUGHPUT",
            "promptTokensDetails": [     
                {
                    "modality": "TEXT",  
                    "tokenCount": 10     
                }
            ],
            "candidatesTokensDetails": [ 
                {
                    "modality": "TEXT",  
                    "tokenCount": 17     
                }
            ],
            "thoughtsTokenCount": 24     
        },
        "modelVersion": "gemini-2.5-flash",
        "createTime": "2026-01-10T01:55:29.168589Z",
        "responseId": "kbFhaY2lCr-ZseMPqMiDmAU"
    },
    "traceId": "55650653afd3c738"        
}
```

--------------------------------

### Gemini API Non-Streaming Response Content Example

Source: https://github.com/su-kaka/gcli2api/blob/master/src/api/Response_example.txt

Example of the content part of a non-streaming Gemini API response. This shows the structure of the model's generated text within the response.

```json
{
  "response": {
    "candidates": [
      {
        "content": {
          "role": "model",
          "parts": [
            {

```

--------------------------------

### Configure MongoDB Connection Strings

Source: https://github.com/su-kaka/gcli2api/blob/master/docs/README_JA.md

Set environment variables to optimize MongoDB connections, including pooling, replica sets, and read preferences.

```bash
# コネクションプールとタイムアウト設定
export MONGODB_URI="mongodb://localhost:27017?maxPoolSize=10&serverSelectionTimeoutMS=5000"

# レプリカセット設定
export MONGODB_URI="mongodb://host1:27017,host2:27017,host3:27017/gcli2api?replicaSet=myReplicaSet"

# リード・ライト分離設定
export MONGODB_URI="mongodb://localhost:27017/gcli2api?readPreference=secondaryPreferred"
```

--------------------------------

### Environment Variables

Source: https://github.com/su-kaka/gcli2api/blob/master/docs/README_JA.md

Configuration options available via environment variables.

```APIDOC
## Environment Variables

### Basic Settings
- **PORT**: Service port (default: 7861)
- **HOST**: Server listen address (default: 0.0.0.0)

### Password Settings
- **API_PASSWORD**: Password for chat API access (overrides PASSWORD if set).
- **PANEL_PASSWORD**: Password for control panel access (overrides PASSWORD if set).
- **PASSWORD**: Common password, overrides API_PASSWORD and PANEL_PASSWORD if set (default: pwd).

### Performance and Stability
- **RETRY_429_ENABLED**: Enable automatic retries for 429 errors (default: true).
- **RETRY_429_MAX_RETRIES**: Maximum number of retries for 429 errors (default: 3).
- **RETRY_429_INTERVAL**: Retry interval for 429 errors in seconds (default: 1.0).
- **ANTI_TRUNCATION_MAX_ATTEMPTS**: Maximum retry attempts for anti-truncation (default: 3).

### Network and Proxy Settings
- **PROXY**: HTTP/HTTPS proxy address (format: `http://host:port`).
- **OAUTH_PROXY_URL**: OAuth authentication proxy endpoint.
- **GOOGLEAPIS_PROXY_URL**: Google APIs proxy endpoint.
- **METADATA_SERVICE_URL**: Metadata service proxy endpoint.

### Automation Settings
- **AUTO_BAN**: Enable automatic credential banning (default: true).
- **AUTO_LOAD_ENV_CREDS**: Automatically load credentials from environment variables on startup (default: false).

### Compatibility Settings
- **COMPATIBILITY_MODE**: Enable compatibility mode, converting system messages to user messages (default: false).

### Log Settings
- **LOG_LEVEL**: Log level (DEBUG/INFO/WARNING/ERROR, default: INFO).
- **LOG_FILE**: Log file path (default: log.txt).

### Storage Settings
#### SQLite Settings (Default)
- No configuration needed; uses local SQLite database automatically.
- Database file is created in the project directory.

#### MongoDB Settings (Optional Cloud Storage)
- **MONGODB_URI**: MongoDB connection string (enables MongoDB mode when set).
- **MONGODB_DATABASE**: MongoDB database name (default: gcli2api).
```

--------------------------------

### Run gcli2api with Password Configurations

Source: https://github.com/su-kaka/gcli2api/blob/master/docs/README_JA.md

Deploy the container using either a common password or specific API and panel passwords.

```bash
# 共通パスワードを使用
docker run -d --name gcli2api \
  -e PASSWORD=mypassword \
  -e PORT=7861 \
  ghcr.io/su-kaka/gcli2api:latest

# 個別パスワードを使用
docker run -d --name gcli2api \
  -e API_PASSWORD=my_api_password \
  -e PANEL_PASSWORD=my_panel_password \
  -e PORT=7861 \
  ghcr.io/su-kaka/gcli2api:latest
```

--------------------------------

### Authentication API - Complete Auth from Callback URL

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Finalize authentication using a full callback URL, including code and state parameters.

```bash
curl -X POST "http://127.0.0.1:7861/auth/callback-url" \
  -H "Authorization: Bearer pwd" \
  -H "Content-Type: application/json" \
  -d '{
    "callback_url": "http://localhost:8080/callback?code=xxx&state=yyy",
    "mode": "geminicli"
  }'
```

--------------------------------

### Docker Deployment Commands

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Various Docker run commands and a Docker Compose configuration for deploying GCLI2API.

```bash
# 基础部署（使用通用密码）
docker run -d --name gcli2api \
  --network host \
  -e PASSWORD=pwd \
  -e PORT=7861 \
  -v $(pwd)/data/creds:/app/creds \
  ghcr.io/su-kaka/gcli2api:latest

# 使用分离密码（API 和面板分开）
docker run -d --name gcli2api \
  --network host \
  -e API_PASSWORD=api_pwd \
  -e PANEL_PASSWORD=panel_pwd \
  -e PORT=7861 \
  -v $(pwd)/data/creds:/app/creds \
  ghcr.io/su-kaka/gcli2api:latest

# macOS 部署（端口映射模式）
docker run -d --name gcli2api \
  -p 7861:7861 \
  -p 8080:8080 \
  -e PASSWORD=pwd \
  -e PORT=7861 \
  -v "$(pwd)/data/creds":/app/creds \
  ghcr.io/su-kaka/gcli2api:latest

# 使用 MongoDB 存储
docker run -d --name gcli2api \
  -e MONGODB_URI="mongodb://admin:password@mongodb:27017/admin" \
  -e MONGODB_DATABASE="gcli2api" \
  -e API_PASSWORD=your_password \
  -p 7861:7861 \
  ghcr.io/su-kaka/gcli2api:latest

# Docker Compose 完整配置
cat > docker-compose.yml << 'EOF'
version: '3.8'

services:
  mongodb:
    image: mongo:7
    container_name: gcli2api-mongodb
    restart: unless-stopped
    environment:
      MONGO_INITDB_ROOT_USERNAME: admin
      MONGO_INITDB_ROOT_PASSWORD: password123
    volumes:
      - mongodb_data:/data/db
    ports:
      - "27017:27017"

  gcli2api:
    image: ghcr.io/su-kaka/gcli2api:latest
    container_name: gcli2api
    restart: unless-stopped
    depends_on:
      - mongodb
    environment:
      - MONGODB_URI=mongodb://admin:password123@mongodb:27017/admin
      - MONGODB_DATABASE=gcli2api
      - API_PASSWORD=your_api_password
      - PORT=7861
    ports:
      - "7861:7861"

volumes:
  mongodb_data:
EOF

docker-compose up -d
```

--------------------------------

### Configuration Management API

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Endpoints for retrieving and updating system configurations with hot-reload support.

```bash
curl -X GET "http://127.0.0.1:7861/config/get" \
  -H "Authorization: Bearer pwd"
```

```bash
curl -X POST "http://127.0.0.1:7861/config/save" \
  -H "Authorization: Bearer pwd" \
  -H "Content-Type: application/json" \
  -d '{
    "config": {
      "retry_429_enabled": true,
      "retry_429_max_retries": 5,
      "retry_429_interval": 1.5,
      "anti_truncation_max_attempts": 5,
      "compatibility_mode_enabled": false,
      "return_thoughts_to_frontend": true,
      "keepalive_url": "https://example.com/keepalive",
      "keepalive_interval": 300
    }
  }'
```

--------------------------------

### Configuration Management API

Source: https://context7.com/su-kaka/gcli2api/llms.txt

APIs for retrieving and saving system configurations. Supports hot-swapping of some configuration items, with environment variables taking precedence over database configurations.

```APIDOC
## GET /config/get

### Description
Retrieves the current system configuration.

### Method
GET

### Endpoint
/config/get

### Request Example
```bash
curl -X GET "http://127.0.0.1:7861/config/get" \
  -H "Authorization: Bearer pwd"
```

### Response
#### Success Response (200)
- **config** (object) - The current configuration settings.
  - **host** (string) - The host address.
  - **port** (integer) - The port number.
  - **api_password** (string) - API password.
  - **panel_password** (string) - Panel password.
  - **auto_ban_enabled** (boolean) - Whether auto-ban is enabled.
  - **retry_429_enabled** (boolean) - Whether retrying 429 errors is enabled.
  - **retry_429_max_retries** (integer) - Maximum retries for 429 errors.
  - **retry_429_interval** (number) - Interval for retrying 429 errors.
  - **anti_truncation_max_attempts** (integer) - Maximum attempts for anti-truncation.
  - **compatibility_mode_enabled** (boolean) - Whether compatibility mode is enabled.
  - **return_thoughts_to_frontend** (boolean) - Whether to return thoughts to the frontend.
  - **keepalive_url** (string) - URL for keep-alive checks.
  - **keepalive_interval** (integer) - Interval for keep-alive checks.
- **env_locked** (array of strings) - Configuration items locked by environment variables.

#### Response Example
```json
{
  "config": {
    "host": "0.0.0.0",
    "port": 7861,
    "api_password": "pwd",
    "panel_password": "pwd",
    "auto_ban_enabled": true,
    "retry_429_enabled": true,
    "retry_429_max_retries": 5,
    "retry_429_interval": 1.0,
    "anti_truncation_max_attempts": 3,
    "compatibility_mode_enabled": false,
    "return_thoughts_to_frontend": true,
    "keepalive_url": "",
    "keepalive_interval": 60
  },
  "env_locked": ["PORT", "PASSWORD"]
}
```
```

```APIDOC
## POST /config/save

### Description
Saves the system configuration.

### Method
POST

### Endpoint
/config/save

### Parameters
#### Request Body
- **config** (object) - Required - The configuration object to save. Can include fields like:
  - **retry_429_enabled** (boolean)
  - **retry_429_max_retries** (integer)
  - **retry_429_interval** (number)
  - **anti_truncation_max_attempts** (integer)
  - **compatibility_mode_enabled** (boolean)
  - **return_thoughts_to_frontend** (boolean)
  - **keepalive_url** (string)
  - **keepalive_interval** (integer)

### Request Example
```bash
curl -X POST "http://127.0.0.1:7861/config/save" \
  -H "Authorization: Bearer pwd" \
  -H "Content-Type: application/json" \
  -d '{
    "config": {
      "retry_429_enabled": true,
      "retry_429_max_retries": 5,
      "retry_429_interval": 1.5,
      "anti_truncation_max_attempts": 5,
      "compatibility_mode_enabled": false,
      "return_thoughts_to_frontend": true,
      "keepalive_url": "https://example.com/keepalive",
      "keepalive_interval": 300
    }
  }'
```

### Response
#### Success Response (200)
- **message** (string) - Confirmation message.
- **saved_config** (object) - The configuration that was saved.

#### Response Example
```json
{"message": "配置保存成功", "saved_config": {...}}
```
```

--------------------------------

### Enable Compatibility Mode

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Set this environment variable to enable compatibility mode, which converts system messages to user messages for better compatibility with certain clients.

```bash
# 启用兼容性模式
export COMPATIBILITY_MODE=true
```

--------------------------------

### Run gcli2api with Separate Passwords (Docker)

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Deploy gcli2api with distinct passwords for API and panel access. This enhances security for production environments. Mount the data directory for credential storage.

```bash
docker run -d --name gcli2api --network host -e API_PASSWORD=api_pwd -e PANEL_PASSWORD=panel_pwd -e PORT=7861 -v $(pwd)/data/creds:/app/creds ghcr.io/su-kaka/gcli2api:latest
```

--------------------------------

### Authentication API - User Login

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Authenticate users by providing a password. Returns a token upon successful login.

```bash
curl -X POST "http://127.0.0.1:7861/auth/login" \
  -H "Content-Type: application/json" \
  -d '{"password": "pwd"}'
```

--------------------------------

### Claude API Format Request (cURL)

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Example cURL request for interacting with the Claude API format endpoint. Supports x-api-key or Authorization: Bearer header for authentication. Specify the anthropic-version header.

```bash
curl -X POST "http://127.0.0.1:7861/v1/messages" \
  -H "x-api-key: your_api_password" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-pro",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello, Claude!"}
    ]
  }'
```

--------------------------------

### Deploy gcli2api with Docker Compose

Source: https://github.com/su-kaka/gcli2api/blob/master/docs/README_JA.md

Orchestrate gcli2api and a local MongoDB instance using Docker Compose.

```yaml
version: '3.8'

services:
  mongodb:
    image: mongo:7
    container_name: gcli2api-mongodb
    restart: unless-stopped
    environment:
      MONGO_INITDB_ROOT_USERNAME: admin
      MONGO_INITDB_ROOT_PASSWORD: password123
    volumes:
      - mongodb_data:/data/db
    ports:
      - "27017:27017"

  gcli2api:
    image: ghcr.io/su-kaka/gcli2api:latest
    container_name: gcli2api
    restart: unless-stopped
    depends_on:
      - mongodb
    environment:
      - MONGODB_URI=mongodb://admin:password123@mongodb:27017/admin
      - MONGODB_DATABASE=gcli2api
      - API_PASSWORD=your_api_password
      - PORT=7861
    ports:
      - "7861:7861"

volumes:
  mongodb_data:
```

--------------------------------

### Antigravity API - OpenAI Format

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Use this endpoint to interact with Antigravity services using the OpenAI API format. Supports streaming responses.

```bash
curl -X POST "http://127.0.0.1:7861/antigravity/v1/chat/completions" \
  -H "Authorization: Bearer pwd" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5",
    "messages": [
      {"role": "user", "content": "Hello"}
    ],
    "stream": true
  }'
```

--------------------------------

### Antigravity Gemini Format Non-Streaming Request (cURL)

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Example cURL request for the Antigravity endpoint using Gemini format for non-streaming content generation. Supports x-goog-api-key or URL parameter key authentication.

```bash
curl -X POST "http://127.0.0.1:7861/antigravity/v1/models/claude-sonnet-4-5:generateContent" \
  -H "x-goog-api-key: your_api_password" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {"role": "user", "parts": [{"text": "Hello"}]}
    ],
    "generationConfig": {
      "temperature": 0.7
    }
  }'
```

--------------------------------

### Authentication API - Handle OAuth Callback

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Process the callback from an OAuth provider for GCLI mode authentication.

```bash
curl -X POST "http://127.0.0.1:7861/auth/callback" \
  -H "Authorization: Bearer pwd" \
  -H "Content-Type: application/json" \
  -d '{
    "project_id": "my-project-id",
    "mode": "geminicli"
  }'
```

--------------------------------

### Gemini Native Stream Generate Content Request (cURL)

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Example cURL request for streaming content generation using the Gemini native endpoint with URL parameter key authentication. Ensure the Content-Type is set to application/json.

```bash
curl -X POST "http://127.0.0.1:7861/v1/models/gemini-2.5-pro:streamGenerateContent?key=your_api_password" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {"role": "user", "parts": [{"text": "Hello"}]}
    ]
  }'
```

--------------------------------

### Antigravity API - Gemini Format

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Interact with Antigravity services using the Gemini API format. Allows configuration of generation parameters like temperature.

```bash
curl -X POST "http://127.0.0.1:7861/antigravity/v1/models/gemini-2.5-flash:generateContent" \
  -H "x-goog-api-key: pwd" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {"role": "user", "parts": [{"text": "Hello"}]}
    ],
    "generationConfig": {"temperature": 0.7}
  }'
```

--------------------------------

### Docker Compose Configuration for gcli2api

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

A sample docker-compose.yml file to deploy gcli2api. It supports both universal and separate password configurations and includes a healthcheck.

```yaml
version: '3.8'

services:
  gcli2api:
    image: ghcr.io/su-kaka/gcli2api:latest
    container_name: gcli2api
    restart: unless-stopped
    network_mode: host
    environment:
      # 使用通用密码（推荐用于简单部署）
      - PASSWORD=pwd
      - PORT=7861
      # 或使用分离密码（推荐用于生产环境）
      # - API_PASSWORD=your_api_password
      # - PANEL_PASSWORD=your_panel_password
    volumes:
      - ./data/creds:/app/creds
    healthcheck:
      test: ["CMD-SHELL", "python -c \"import sys, urllib.request, os; port = os.environ.get('PORT', '7861'); req = urllib.request.Request(f'http://localhost:{port}/v1/models', headers={'Authorization': 'Bearer ' + os.environ.get('PASSWORD', 'pwd')}); sys.exit(0 if urllib.request.urlopen(req, timeout=5).getcode() == 200 else 1)\"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s
```

--------------------------------

### Antigravity API - Chat Completions (OpenAI Format)

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Accesses Google Antigravity services using the OpenAI format for chat completions. Supports Claude and Gemini models and image generation.

```APIDOC
## POST /antigravity/v1/chat/completions

### Description
Sends a chat completion request to the Antigravity API using OpenAI format. Supports various models and streaming.

### Method
POST

### Endpoint
`/antigravity/v1/chat/completions`

### Request Body
- **model** (string) - Required - The model to use for generation (e.g., "claude-sonnet-4-5", "gemini-3.1-flash-image-4k-16x9").
- **messages** (array) - Required - An array of message objects representing the conversation history.
  - **role** (string) - Required - The role of the message sender (e.g., "user", "assistant").
  - **content** (string) - Required - The content of the message.
- **stream** (boolean) - Optional - Whether to stream the response.

### Request Example
```json
{
  "model": "claude-sonnet-4-5",
  "messages": [
    {"role": "user", "content": "Hello"}
  ],
  "stream": true
}
```

### Response
#### Success Response (200)
- **id** (string) - The ID of the response.
- **type** (string) - The type of the response.
- **role** (string) - The role of the sender (e.g., "assistant").
- **content** (array) - The content of the message, potentially with different types.
  - **type** (string) - The type of content (e.g., "text").
  - **text** (string) - The text content.
- **model** (string) - The model used for the response.
- **stop_reason** (string) - The reason the generation stopped.
- **usage** (object) - Token usage information.
  - **input_tokens** (integer) - Number of input tokens.
  - **output_tokens** (integer) - Number of output tokens.

#### Response Example
```json
{
  "id": "msg_xxx",
  "type": "message",
  "role": "assistant",
  "content": [{"type": "text", "text": "你好！很高兴见到你..."}],
  "model": "gemini-2.5-pro",
  "stop_reason": "end_turn",
  "usage": {"input_tokens": 10, "output_tokens": 50}
}
```
```

--------------------------------

### Antigravity API - Image Generation

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Use the OpenAI format endpoint for image generation with Antigravity, specifying image-capable models.

```bash
curl -X POST "http://127.0.0.1:7861/antigravity/v1/chat/completions" \
  -H "Authorization: Bearer pwd" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image-4k-16x9",
    "messages": [{"role": "user", "content": "画一只可爱的猫"}]
  }'
```

--------------------------------

### Special Model Feature - Pseudo-Streaming Mode

Source: https://context7.com/su-kaka/gcli2api/llms.txt

Utilize a pseudo-streaming mode for compatibility scenarios by using models with the '-假流式' suffix. This mode still requires 'stream: true'.

```bash
curl -X POST "http://127.0.0.1:7861/v1/chat/completions" \
  -H "Authorization: Bearer pwd" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-pro-假流式",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'
```

--------------------------------

### Advanced MongoDB Connection Options

Source: https://github.com/su-kaka/gcli2api/blob/master/README.md

Configure advanced MongoDB connection parameters via the MONGODB_URI, such as connection pooling, timeouts, replica sets, and read preferences.

```bash
# 连接池和超时配置
export MONGODB_URI="mongodb://localhost:27017?maxPoolSize=10&serverSelectionTimeoutMS=5000"

# 副本集配置
export MONGODB_URI="mongodb://host1:27017,host2:27017,host3:27017/gcli2api?replicaSet=myReplicaSet"

# 读写分离配置
export MONGODB_URI="mongodb://localhost:27017/gcli2api?readPreference=secondaryPreferred"
```

--------------------------------

### Deploy gcli2api with MongoDB Atlas

Source: https://github.com/su-kaka/gcli2api/blob/master/docs/README_JA.md

Run the gcli2api container using a MongoDB Atlas connection string.

```bash
docker run -d --name gcli2api \
  -e MONGODB_URI="mongodb+srv://user:pass@cluster.mongodb.net/gcli2api" \
  -e API_PASSWORD=your_password \
  -p 7861:7861 \
  ghcr.io/su-kaka/gcli2api:latest
```

--------------------------------

### Environment Variable Configuration

Source: https://context7.com/su-kaka/gcli2api/llms.txt

A comprehensive list of environment variables for configuring GCLI2API server, security, performance, and storage.

```bash
# 服务器基础配置
export PORT=7861              # 服务端口（默认：7861）
export HOST=0.0.0.0           # 监听地址（默认：0.0.0.0）
export WORKERS=1              # Worker 数量（默认：1）

# 密码配置
export PASSWORD=pwd           # 通用密码（默认：pwd）
export API_PASSWORD=api_pwd   # API 访问密码（覆盖 PASSWORD）
export PANEL_PASSWORD=panel_pwd  # 控制面板密码（覆盖 PASSWORD）

# 性能和稳定性配置
export RETRY_429_ENABLED=true        # 启用 429 错误自动重试（默认：true）
export RETRY_429_MAX_RETRIES=5       # 429 错误最大重试次数（默认：5）
export RETRY_429_INTERVAL=1.0        # 429 错误重试间隔秒数（默认：1.0）
export ANTI_TRUNCATION_MAX_ATTEMPTS=3  # 抗截断最大重试次数（默认：3）

# 自动封禁配置
export AUTO_BAN=true                 # 启用凭证自动封禁（默认：true）
export AUTO_BAN_ERROR_CODES=403      # 触发封禁的错误码（逗号分隔）

# 兼容性配置
export COMPATIBILITY_MODE=false      # 兼容性模式（默认：false）
export RETURN_THOUGHTS_TO_FRONTEND=true  # 返回思维链（默认：true）

# 网络代理配置
export PROXY=http://proxy:8080       # HTTP/HTTPS 代理
export OAUTH_PROXY_URL=https://oauth2.googleapis.com  # OAuth 代理
export GOOGLEAPIS_PROXY_URL=https://www.googleapis.com  # Google APIs 代理

# 存储配置
export MONGODB_URI=mongodb://localhost:27017  # MongoDB 连接（可选）
export MONGODB_DATABASE=gcli2api     # MongoDB 数据库名（默认：gcli2api）

# 日志配置
export LOG_LEVEL=INFO                # 日志级别（DEBUG/INFO/WARNING/ERROR）
export LOG_FILE=log.txt              # 日志文件路径

# 保活配置
export KEEPALIVE_URL=                # 保活 URL（留空禁用）
export KEEPALIVE_INTERVAL=60         # 保活间隔秒数（默认：60）
```
Tokens:
Raw