* Introduced SqlNull type for nullable values with auto-casting.
* Implemented JSON, YAML, and XML marshaling/unmarshaling.
* Added specific types for common SQL types (e.g., SqlInt64, SqlString).
* Included utility functions for creating nullable types.
* Added SqlTimeStamp, SqlDate, and SqlTime types with custom formatting.
* Introduced QueryMode to select between stored procedure and direct SQL execution.
* Implemented dbCapability to check for stored procedure existence.
* Added methods to DatabaseTwoFactorProvider for configuring table names and query modes.
* Created direct SQL implementations for TOTP operations to handle cases where stored procedures are not available.
* Updated existing TOTP methods to utilize the new query mode logic.
* Commented out GRANT ALL ON TABLE statements for household, maintenance, family calendar, meal planning, professional CRM, stored files, project skills, and project guardrails.
* Introduced oauth_clients table with fields for client_id, client_name, redirect_uris, and created_at.
* Updated agent_persona_parts, agent_persona_skills, agent_persona_guardrails, agent_persona_traits, and arc_stage_parts tables to use unique constraints instead of primary keys for composite indexes.
* Corrected default values for various fields in SQL schema
* Changed tags field type from text[] to text[] with proper default
* Updated JSONB default values to remove unnecessary quotes
* Implement DescribeTool for listing available MCP tools with annotations.
* Add UpsertToolAnnotation and GetToolAnnotations methods for managing tool notes.
* Create tool_annotations table for storing tool usage notes.
* Implement tests for error functions like errRequiredField, errInvalidField, and errEntityNotFound.
* Ensure proper metadata is returned for various error scenarios.
* Validate error handling in CRM, Files, and other tools.
* Introduce tests for parsing stored file IDs and UUIDs.
* Enhance coverage for helper functions related to project resolution and session management.
* Added support for extracting Bearer tokens from Authorization header.
* Updated middleware to prefer explicit header over Bearer token.
* Improved test coverage for authentication scenarios.
* Serve LLM instructions at `/llm`
* Include markdown content for memory instructions
* Update README with LLM integration details
* Add tests for LLM instructions handler
* Modify database migrations to use GUIDs for thoughts and projects
* Introduced EmbeddingModel method in Client and Provider interfaces
* Updated InsertThought and SearchThoughts methods to handle embedding models
* Created embeddings table and updated match_thoughts function for model filtering
* Removed embedding column from thoughts table
* Adjusted permissions for new embeddings table
* Add tools for creating, retrieving, updating, and deleting thoughts.
* Implement project management tools for creating and listing projects.
* Introduce linking functionality between thoughts.
* Add search and recall capabilities for thoughts based on semantic queries.
* Implement statistics and summarization tools for thought analysis.
* Create database migrations for thoughts, projects, and links.
* Add helper functions for UUID parsing and project resolution.
Hein