feat: Add livelli_idrometrici task with unified adapter-level caching

Fix task output and test infrastructure

🎯 Complete OMIRL web services refactoring with workflow enhancement

🧹 Major cleanup: Remove obsolete code, modernize task-agnostic architecture

hard coded the 12 sensor types that were wrong in the table scraper and fixed test that were getting stuck because there was no browser session clean up

Set up of the project structure: langgraph and tool based agent. Implemented first tool and task: omirl_snapshot_summary adapter can scrape data from sensorstable omirl. Next step: add tool to agentic framework and deploy to hugging face. Next step: scrape data based on sensor filter.

Initial commit with docker image ready for Hugging Face Spaces deployment