NN training: realistic persona data, graphs, hot-reload endpoint

Add life events, goals, pregnancy system; fix profile editor bugs

Fix quota runtime estimates: use RPM as bottleneck, sync top probability slider

Add quota-aware LLM switching: budget calculator, probability slider, Gemini/Groq support

Diversify agent activities, add local training script, scheduled Gemini cycle, architecture diagram

Add NN self-improvement pipeline: collect, train, push

Fix GGUF export: clone llama.cpp for bundled gguf-py; update Modelfile

Add GGUF export script for Windows (merge LoRA + quantise)

Add multi-model support to fine-tune pipeline (0.5b–8b)

Add Soci fine-tuned model and training data pipeline