default

BigQuery MCP Development Standards

Code Quality

• Write clean, efficient, minimal code
• No unnecessary complexity or over-engineering
• Follow existing patterns and conventions
• Use descriptive variable names, avoid abbreviations

Version Control

• Update version numbers consistently across all files when making releases
• Use semantic versioning (MAJOR.MINOR.PATCH)
• Keep commits focused and atomic
• Write clear, concise commit messages

Code Standards

• Run ruff format before committing
• Run ruff check --fix to resolve linting issues
• Add type hints for function parameters and returns
• Include docstrings for public functions and classes

Testing

• Add tests for new functionality
• Run pytest before committing
• Ensure all tests pass in CI

Documentation

• Keep documentation minimal and focused
• Update relevant docs when changing functionality
• Use clear, direct language - no fluff or emojis
• Focus on what users need to know, not implementation details

Changelog Formatting

• Use clean, elegant formatting without bold text
• Write concise, descriptive entries
• No unnecessary formatting or emphasis
• Keep entries focused on what actually changed

Architecture

• Prefer command-line arguments over config files
• Keep dependencies minimal
• Follow MCP protocol standards
• Maintain backwards compatibility when possible

Error Handling

• Use custom exception classes for specific error types
• Provide actionable error messages
• Log errors appropriately for debugging

User Preferences

• Avoid over-engineering and unnecessary complexity
• Don't overthink security implementations unless specifically requested
• Focus on what's needed, not what could be possible
• Maintain high repository standards suitable for GitHub
• Keep configuration clean with proper .example files and gitignored personal configs