{bug} Vertex Auth Support (#1302)

Co-authored-by: Tommaso Sciortino <sciortino@gmail.com>
This commit is contained in:
matt korwel 2025-06-22 17:30:58 -07:00 committed by GitHub
parent d8ecbde9bd
commit da128e725d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 62 additions and 68 deletions

110
README.md
View File

@ -42,36 +42,15 @@ Or ask it to perform a task using its tools:
> List files in the current directory.
```
## API Key Setup
## Authentication Setup
The Gemini CLI requires you to authenticate with Google's AI services. You'll need to configure **one** of the following authentication methods:
The Gemini CLI requires you to authenticate with Google's AI services. On initial startup you'll need to configure **one** of the following authentication methods:
1. **Gemini Code Assist:**
1. **Login with Google (Gemini Code Assist):**
- To enable this mode you only need set the GEMINI_CODE_ASSIST environment variable to true.
- You can temporarily set the environment variable in your current shell session using the following command:
```bash
export GEMINI_CODE_ASSIST="true"
```
- For repeated use, you can add the environment variable to your `.env` file (located in the project directory or user home directory) or your shell's configuration file (like `~/.bashrc`, `~/.zshrc`, or `~/.profile`). For example, the following command adds the environment variable to a `~/.bashrc` file:
```bash
echo 'export GEMINI_CODE_ASSIST="true"' >> ~/.bashrc
source ~/.bashrc
```
- There are two types of Google Accounts you can use with Gemini CLI:
- **Personal Google Account**: This is the standard, free account you use for services like Gmail, Google Photos, and Google Drive for personal use (e.g. your-name@gmail.com).
- **Google Workspace Account**: This is a paid service for businesses and organizations that provides a suite of productivity tools, including a custom email domain (e.g. your-name@your-company.com), enhanced security features, and administrative controls. These accounts are often managed by an employer or school.
- Google Workspace Account must configure a Google Cloud Project Id to use. You can temporarily set the environment variable in your current shell session using the following command:
```bash
export GOOGLE_CLOUD_PROJECT_ID="YOUR_PROJECT_ID"
```
- For repeated use, you can add the environment variable to your `.env` file (located in the project directory or user home directory) or your shell's configuration file (like `~/.bashrc`, `~/.zshrc`, or `~/.profile`). For example, the following command adds the environment variable to a `~/.bashrc` file:
```bash
echo 'export GOOGLE_CLOUD_PROJECT_ID="YOUR_PROJECT_ID"' >> ~/.bashrc
source ~/.bashrc
```
- During start up, Gemini CLI will direct you to a webpage for authentication. Once authenticated, your credentials will be cached locally so the web login can be skipped on subsequent runs. Cached credentials last about 20 hours before expiring.
- Note that the the web login must be done in a browser that can communicate with the machine Gemini Cli is being run from. (Specifically, the browser will be redirected to a localhost url that Gemini CLI will be listening on).
- Use this option to log in with the standard, free account you use for services like Gmail, Google Photos, and Google Drive for personal use (e.g. your-name@gmail.com).
- During initial startup, Gemini CLI will direct you to a webpage for authentication. Once authenticated, your credentials will be cached locally so the web login can be skipped on subsequent runs.
- Note that the web login must be done in a browser that can communicate with the machine Gemini CLI is being run from. (Specifically, the browser will be redirected to a localhost url that Gemini CLI will be listening on).
2. **Gemini API key:**
@ -87,43 +66,56 @@ The Gemini CLI requires you to authenticate with Google's AI services. You'll ne
source ~/.bashrc
```
3. **Google API Key (Vertex AI Express Mode):**
3. **Login with Google Work**
- You can use a general Google Cloud API key if it has been enabled for the Gemini API or Vertex AI.
- Set the `GOOGLE_API_KEY` and `GOOGLE_GENAI_USE_VERTEXAI` environment variables. In the following methods, replace `YOUR_GEMINI_API_KEY` with your Google Cloud API key:
- You can temporarily set these environment variables in your current shell session using the following commands:
```bash
export GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY"
export GOOGLE_GENAI_USE_VERTEXAI=true
```
- For repeated use, you can add the environment variables to your `.env` file (located in the project directory or user home directory) or your shell's configuration file (like `~/.bashrc`, `~/.zshrc`, or `~/.profile`). For example, the following commands adds the environment variables to a `~/.bashrc` file:
```bash
echo 'export GEMINI_API_KEY="YOUR_GEMINI_API_KEY"' >> ~/.bashrc
echo 'export GOOGLE_GENAI_USE_VERTEXAI=true' >> ~/.bashrc
source ~/.bashrc
```
4. **Vertex AI (Project and Location):**
- Ensure you have a Google Cloud project and have enabled the Vertex AI API.
- Set up Application Default Credentials (ADC), using the following command:
- Use this option to log in with the **Google Workspace Accounts**. This is a paid service for businesses and organizations that provides a suite of productivity tools, including a custom email domain (e.g. your-name@your-company.com), enhanced security features, and administrative controls. These accounts are often managed by an employer or school.
- Google Workspace Account must configure a Google Cloud Project Id to use. You can temporarily set the environment variable in your current shell session using the following command:
```bash
gcloud auth application-default login
export GOOGLE_CLOUD_PROJECT_ID="YOUR_PROJECT_ID"
```
For more information, see [Set up Application Default Credentials for Google Cloud](https://cloud.google.com/docs/authentication/provide-credentials-adc).
- Set the `GOOGLE_CLOUD_PROJECT`, `GOOGLE_CLOUD_LOCATION`, and `GOOGLE_GENAI_USE_VERTEXAI` environment variables. In the following methods, replace `YOUR_PROJECT_ID` and `YOUR_PROJECT_LOCATION` with the relevant values for your project:
- You can temporarily set these environment variables in your current shell session using the following commands:
- For repeated use, you can add the environment variable to your `.env` file (located in the project directory or user home directory) or your shell's configuration file (like `~/.bashrc`, `~/.zshrc`, or `~/.profile`). For example, the following command adds the environment variable to a `~/.bashrc` file:
```bash
echo 'export GOOGLE_CLOUD_PROJECT_ID="YOUR_PROJECT_ID"' >> ~/.bashrc
source ~/.bashrc
```
- During startup, Gemini CLI will direct you to a webpage for authentication. Once authenticated, your credentials will be cached locally so the web login can be skipped on subsequent runs.
- Note that the web login must be done in a browser that can communicate with the machine Gemini CLI is being run from. (Specifically, the browser will be redirected to a localhost url that Gemini CLI will be listening on).
4. **Vertex AI:**
- If not using express mode:
- Ensure you have a Google Cloud project and have enabled the Vertex AI API.
- Set up Application Default Credentials (ADC), using the following command:
```bash
export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"
export GOOGLE_CLOUD_LOCATION="YOUR_PROJECT_LOCATION" # e.g., us-central1
export GOOGLE_GENAI_USE_VERTEXAI=true
```
- For repeated use, you can add the environment variables to your `.env` file (located in the project directory or user home directory) or your shell's configuration file (like `~/.bashrc`, `~/.zshrc`, or `~/.profile`). For example, the following commands adds the environment variables to a `~/.bashrc` file:
```bash
echo 'export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"' >> ~/.bashrc
echo 'export GOOGLE_CLOUD_LOCATION="YOUR_PROJECT_LOCATION"' >> ~/.bashrc
echo 'export GOOGLE_GENAI_USE_VERTEXAI=true' >> ~/.bashrc
source ~/.bashrc
gcloud auth application-default login
```
For more information, see [Set up Application Default Credentials for Google Cloud](https://cloud.google.com/docs/authentication/provide-credentials-adc).
- Set the `GOOGLE_CLOUD_PROJECT`, `GOOGLE_CLOUD_LOCATION`, and `GOOGLE_GENAI_USE_VERTEXAI` environment variables. In the following methods, replace `YOUR_PROJECT_ID` and `YOUR_PROJECT_LOCATION` with the relevant values for your project:
- You can temporarily set these environment variables in your current shell session using the following commands:
```bash
export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"
export GOOGLE_CLOUD_LOCATION="YOUR_PROJECT_LOCATION" # e.g., us-central1
export GOOGLE_GENAI_USE_VERTEXAI=true
```
- For repeated use, you can add the environment variables to your `.env` file (located in the project directory or user home directory) or your shell's configuration file (like `~/.bashrc`, `~/.zshrc`, or `~/.profile`). For example, the following commands adds the environment variables to a `~/.bashrc` file:
```bash
echo 'export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"' >> ~/.bashrc
echo 'export GOOGLE_CLOUD_LOCATION="YOUR_PROJECT_LOCATION"' >> ~/.bashrc
echo 'export GOOGLE_GENAI_USE_VERTEXAI=true' >> ~/.bashrc
source ~/.bashrc
```
- If using express mode:
- Set the `GOOGLE_API_KEY` environment variables. In the following methods, replace `YOUR_GOOGLE_API_KEY` with your Vertex AI API key provided by express mode:
- You can temporarily set these environment variables in your current shell session using the following commands:
```bash
export GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY"
export GOOGLE_GENAI_USE_VERTEXAI=true
```
- For repeated use, you can add the environment variables to your `.env` file (located in the project directory or user home directory) or your shell's configuration file (like `~/.bashrc`, `~/.zshrc`, or `~/.profile`). For example, the following commands adds the environment variables to a `~/.bashrc` file:
```bash
echo 'export GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY"' >> ~/.bashrc
echo 'export GOOGLE_GENAI_USE_VERTEXAI=true' >> ~/.bashrc
source ~/.bashrc
```
### Next Steps

View File

@ -28,14 +28,16 @@ export const validateAuthMethod = (authMethod: string): string | null => {
}
if (authMethod === AuthType.USE_VERTEX_AI) {
if (!process.env.GOOGLE_API_KEY) {
return 'GOOGLE_API_KEY environment variable not found. Add that to your .env and try again, no reload needed!';
}
if (!process.env.GOOGLE_CLOUD_PROJECT) {
return 'GOOGLE_CLOUD_PROJECT environment variable not found. Add that to your .env and try again, no reload needed!';
}
if (!process.env.GOOGLE_CLOUD_LOCATION) {
return 'GOOGLE_CLOUD_LOCATION environment variable not found. Add that to your .env and try again, no reload needed!';
const hasVertexProjectLocationConfig =
!!process.env.GOOGLE_CLOUD_PROJECT && !!process.env.GOOGLE_CLOUD_LOCATION;
const hasGoogleApiKey = !!process.env.GOOGLE_API_KEY;
if (!hasVertexProjectLocationConfig && !hasGoogleApiKey) {
return (
'Must specify GOOGLE_GENAI_USE_VERTEXAI=true and either:\n' +
'• GOOGLE_CLOUD_PROJECT and GOOGLE_CLOUD_LOCATION environment variables.\n' +
'• GOOGLE_API_KEY environment variable (if using express mode).\n' +
'Update your .env and try again, no reload needed!'
);
}
return null;
}

View File

@ -38,7 +38,7 @@ export function AuthDialog({
label: 'Login with Google Work',
value: AuthType.LOGIN_WITH_GOOGLE_ENTERPRISE,
},
{ label: 'Vertex API Key', value: AuthType.USE_VERTEX_AI },
{ label: 'Vertex AI', value: AuthType.USE_VERTEX_AI },
];
const isSelectedAuthInMore = allAuthItems