minor tweak to switch LLM provider from Ollama to Gemini

Configured Ollaman and improved llm config functionality: now the default is ollama, the fallback is gemini 2.5 flash lite, and these can be changed modifying just on line in the yaml config file

feat: Add livelli_idrometrici task with unified adapter-level caching

LLM router and summarization currently working. Fixed agent initialization issues and basic llm-based summarization service

Add comprehensive environment debugging for HF Spaces

Fix: Implement lazy agent initialization and improve environment loading

Updated the adapter and the agent workflow (node, state, registry etc.). Updated web app, currently supporting omirl scraping

Initial commit with docker image ready for Hugging Face Spaces deployment