feat: replace manual web scraping with an agentic tool-selection engine

refactor: replace daily usage increment with atomic reservation

feat: implement WebSocket-based streaming chat

refactor: replace standard logging with a centralized loguru configuration and interception handler

feat: implement Redis-first refresh token storage with Supabase fallback

feat: migrate RAG chatbot model from Groq Llama 3.1 to Ministral 8b

feat: implement LLM fallback for quiz generation and enhance OAuth error handling

feat: optimize auth concurrency and enable full account deletion

feat: implement in-memory email rate limiting and adjust RAG search parameters

feat: fix LLM model names, increase RAG retrieval and memory limits

feat: implement password update functionality and add signup, forgot-password, and update-password pages

feat: improve chatbot search quality, implement refusal filtering.

refactor: optimize RAG prompt instructions, update web search tool configuration, and streamline search logic.

refactor: decouple usage increment from rate limit checks, add session refresh error handling.

feat: increase quiz generation capacity with dedicated high-token LLM.

feat: add religious, political and NSFW topics in prohibited content criteria in quiz and summary generators

refactor: update system prompts safety guidelines

refactor: add NSFW and gibbreish words filtering

refactor: update content limits for quiz and summary generation modules

refactor: changing to gemini model, modularize constants and schemas and update user daily generation limit

feat: enforce user ownership verification for material access across all API routes

fix: improve security, session handling, and UI responsiveness for topic management and document rendering

feat: configure LLM generation parameters and implement text truncation for summarization inputs

feat: enable AI-generated summaries for topic-based materials by integrating Wikipedia and Arxiv search providers.

refactor: implement async execution for blocking database operations and add title collision auto-increment for new materials

feat: improve quiz generation logic and RAG tool robustness with enhanced prompt engineering and search error handling

refactor: add structured logging across summary and quiz generation modules

refactor: replace legacy login page with integrated Google OAuth landing page and dashboard redirect logic

feat: implement daily request rate limiting with per-user usage tracking and admin bypass

feat: implement search functionality, add background task queue logic for title conflicts, and enhance auth state synchronization

feat: Adding Parallel Processing and enhance main dashboard, summary and chat styles

feat: implement async quiz generation, add quiz result persistence, and integrate Supabase authentication

feat: migrate UI to Next.js with extensive component library and integrate Hugging Face deployment workflow

refactor: restructure project into modular src architecture and implement database store layer