feat: add Qdrant configuration and handle disabled state in QdrantService

feat: update subscription response to track AI credits instead of tokens

feat: add token usage tracking for AI recommendations and subscription management

feat: add subscription management with user plan tracking and response schema

Remove compiled Python cache files from backend and tests

Add example images for virtual try-on feature

Add chat conversations and try-on history endpoints

Use OpenAI GPT-4.1-mini for AI Stylist recommendations

Add virtual try-on for Marketplace and Dashboard items

Add OpenAI vision model configuration and garment masking functionality

Update .gitignore to include specific __pycache__ directories and adjust patterns for Python files

Fail fast on hard Gemini quota instead of spamming every key

Add Gemini API key rotation

Switch try-on and garment analysis to external image APIs

feat: implement conversational chatbot with routing and chat history support

feat: default STORAGE_MODE to cloudinary and force real CatVTON execution on CPU

feat: add CPU simulation fallback mode for tryon to prevent hangs/OOM on CPU spaces

perf: optimize CatVTON on CPU with float32 and 20 steps, increase frontend polling to 10 min

feat: proactively create chest_cm, waist_cm, hips_cm columns on startup if missing

feat: add Cloudinary support as an alternative image storage mode

feat: add chest, waist, and hips measurements support in profile and LLM service

chore: move CatVTON inside backend and resolve paths dynamically without binary resources

fix: auth headers and postgresql connection for cloud deployment

Auto-append ssl_cert_reqs=CERT_NONE to rediss URL in config

Add REDIS_URL and QDRANT_URL environment variable support

feat: integrate local CatVTON virtual try-on and secure env files

Allow Vite preview port 4173 in CORS origins

Support and default to STORAGE_MODE=local for zero-key local development

Initialize production-grade FastAPI backend with models, routes, celery workers, and test suite