Editor Settings
Customize RightNow AI preferences and behavior
AI Preferences
Default Provider
Set your preferred AI provider for consistent experience across features.
- Choose between OpenRouter, Ollama, vLLM, or LM Studio
- Default provider used for chat, autocomplete, and code edits
- Can be overridden per-feature if needed
Autocomplete Settings
Configure AI-powered code completions:
- Enable/disable: Toggle AI-powered completions on/off
- Context window: Adjust how much code context to send to AI (512-4096 tokens)
- Trigger delay: Configure autocomplete response timing (0-1000ms)
- Inline suggestions: Show/hide ghost text previews
Chat Preferences
Customize chat assistant behavior:
- Model selection: Choose specific models for chat interactions
- Message history: Set conversation retention limits (10-100 messages)
- System prompts: Customize AI behavior and response style
- Code context: Include/exclude current file context automatically
Profiling Preferences
Auto-Profile Settings
Configure automatic profiling behavior:
- Automatic profiling: Profile kernels automatically when executed
- Metrics selection: Choose which NCU metrics to display
- Performance thresholds: Customize color-coding thresholds (green/yellow/red)
- Profiling on save: Run profiling automatically when saving files
Display Options
Control how profiling data appears:
- CodeLens metrics: Show/hide inline performance data above kernels
- Gutter buttons: Enable/disable play buttons in editor margins
- Profiling panel: Configure dedicated results view layout
- Metric precision: Decimal places for displayed values
Data Retention
Manage profiling history:
- Historical data: Set profiling session retention period (7-90 days)
- Export options: Configure data export formats (JSON, CSV)
- Team sharing: Enable/disable profiling data collaboration
- Auto-cleanup: Automatically remove old profiling sessions
Editor Preferences
Code Formatting
Configure code formatting options:
- Auto-save: Enable for seamless profiling workflow
- Format on save: Keep CUDA code properly formatted
- IntelliSense: Enable for enhanced CUDA syntax support
- Code style: Choose indentation, brace placement, spacing
Performance Settings
Optimize editor performance:
- Memory usage: Optimize for large codebases (limit indexing)
- Indexing: Configure workspace scanning preferences
- Cache management: Control temporary file storage limits
- Background tasks: Throttle analysis and profiling operations
Visual Customization
Personalize the editor appearance:
- Theme preferences: Light/dark mode compatibility
- Font settings: Optimize for code readability (font family, size, ligatures)
- Layout options: Customize panel arrangements (side-by-side, stacked)
- Color schemes: Performance indicator colors
Hardware Detection Settings
GPU Configuration
Configure GPU detection and selection:
- Auto-detection: Enable automatic GPU hardware detection
- Manual override: Specify GPU models and capabilities
- Multi-GPU: Configure device selection preferences
- GPU monitoring: Enable real-time GPU status tracking
CUDA Environment
Configure CUDA Toolkit settings:
- Toolkit detection: Automatic vs manual path configuration
- Compiler settings:
nvccflags and optimization levels - Debug options: Enable detailed profiling diagnostics
- Build settings: Compile flags, architecture targets, PTX generation
Privacy & Security
Data Handling
Control how your data is processed:
- Local processing: Prefer local models when available
- Network usage: Control cloud provider communications
- Telemetry: Customize usage analytics reporting (opt-in/opt-out)
- Code privacy: Restrict code snippets sent to AI providers
API Key Management
Secure credential handling:
- Secure storage: Encrypted local credential storage
- Key rotation: Automatic API key update notifications
- Access control: Per-project API key configurations
- Validation: Test API keys before saving
Access Settings: Open all settings through Settings → RightNow AI or use the Command Palette: RightNow: Open Settings
Quick Settings Reference
Essential Settings
- AI Provider selection
- Autocomplete enable/disable
- Profiling display options
- GPU detection mode
Performance Tuning
- Context window size
- Memory usage limits
- Background task throttling
- Cache management
Privacy Controls
- Local vs cloud processing
- Telemetry preferences
- API key storage
- Code privacy options
Advanced Options
- Custom compiler flags
- Multi-GPU configuration
- Remote GPU settings
- Debug diagnostics
Tip: Export your settings for backup or share configurations with team members via Settings → Export Configuration