Feat: Enable native parallelize=True flag for efficient batch persona generation

Fix: ensure robust person parsing

Feat: Adapt tinytroupe_manager to use new persona_pipeline logic

Fix: Fallback to sequential persona generation with delay to prevent Google 429 Too Many Requests errors

Fix: Fallback handling for empty JSON extraction in backend manager

Refactor: Use TinyPersonFactory and ResultsExtractor for production LLM stability

Feat: Enable real LLM querying inside TinyTroupe simulation loops

Upload folder using huggingface_hub