- Introduced LLMTool interface for LLM providers, defining methods for text generation and health checks.
- Created PromptGeneratorTool interface for generating database-specific prompts, including SQL to natural language and vice versa.
- Implemented FileStorageTool and MetadataStoreTool interfaces for file operations and metadata persistence, respectively.
- Defined core types including DatabaseType, QueryHash, and QueryMetric to support optimization flows.
- Established exception handling with specific error classes for query validation, LLM provider issues, and optimization errors.
- Added data models for optimization metadata and results, supporting serialization and versioning.
- Added PostgreSQLPromptGenerator for generating prompts optimized for PostgreSQL features.
- Introduced SQLitePromptGenerator to handle SQLite-specific optimizations and features.
- Created SQLServerPromptGenerator for Microsoft SQL Server, including detailed analysis and optimization requirements.
- Developed a template system for rendering SQL-to-natural language and natural-to-SQL prompts.
- Established core tools for SQL analysis, optimization, and comparison, including complexity assessment and comment stripping.
- Integrated a team application to manage SQL optimization tasks and agent interactions.
- Added utility functions for handling SQL files and ensuring valid SQL input.
