User Settings

The .rover/settings.json file stores user-specific preferences that should not be shared across your team. This file is automatically added to .gitignore when you run rover init.

Configuration Options

Field	Description
`aiAgents`	List of AI agents installed on your machine
`defaults.aiAgent`	Your preferred AI agent to use by default
`defaults.models`	Default model to use for each AI agent
`defaults.watchIntervalSeconds`	Polling interval for `rover list --watch` (1-60 seconds, default: 3)

Basic Structure

Here’s a typical user settings file:

{
  // Schema version for automatic migration
  "version": "1.0",

  // AI agents installed on this machine
  "aiAgents": ["claude", "gemini"],

  // Default preferences
  "defaults": {
    "aiAgent": "claude",
    "models": {
      "claude": "sonnet"
    }
  }
}

Setting a Default Agent

Choose your preferred AI agent:

{
  "version": "1.0",
  "aiAgents": ["claude", "gemini"],
  "defaults": {
    "aiAgent": "gemini"
  }
}

The default agent is used when you create tasks without explicitly specifying an agent. You can always override this choice for specific tasks:

rover task --agent claude "Fix the login bug"

Default Models

Configure which model each AI agent should use by default. This is useful when you want to use a specific model tier (like Claude’s Opus or Sonnet) without specifying it every time.

{
  "version": "1.0",
  "aiAgents": ["claude", "gemini"],
  "defaults": {
    "aiAgent": "claude",
    "models": {
      "claude": "opus",
      "gemini": "flash"
    }
  }
}

The available models depend on each AI agent. Common options include:

Agent	Example Models
`claude`	`opus`, `sonnet`, `haiku`
`gemini`	`pro`, `flash`

You can override the default model for specific tasks using the --agent agent:model syntax:

rover task --agent claude:sonnet "Quick code review"

Reference

For a complete list of all available configuration options, see the User Config Reference.

Telemetry

Rover has basic telemetry reporting to help understand how the tool is used. This telemetry does not identify you, as it generates a fully random hash you can change. You can find your random ID at ~/.config/rover/.user.

The only information recorded by telemetry is which action was invoked and basic metadata like the action source (CLI or VS Code Extension). Telemetry does not record any data from prompts, task titles, or descriptions.

Disabling Telemetry

There are two ways to disable telemetry in Rover.

Option 1: Create a no-telemetry file

Disable via file

1
Terminal window
```
mkdir -p ~/.config/rover
```
2
Terminal window
```
touch ~/.config/rover/.no-telemetry
```

Option 2: Use an environment variable

Set the ROVER_NO_TELEMETRY environment variable:

# For a single command
ROVER_NO_TELEMETRY=true rover list

# Or export it globally
export ROVER_NO_TELEMETRY=true

Next Steps

Project Configuration Configure project-wide settings

Hooks Run custom commands at task lifecycle events