Refactoring the Report Generation Agent demo UI and evaluation script

[lotif]

Summary

Refactoring the Report Generation Agent to have a file structure similar to the other systems in the repo.

Clickup Ticket(s): Na

Type of Change

• 🐛 Bug fix (non-breaking change that fixes an issue)
• ✨ New feature (non-breaking change that adds functionality)
• 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)
• 📝 Documentation update
• 🔧 Refactoring (no functional changes)
• ⚡ Performance improvement
• 🧪 Test improvements
• 🔒 Security fix

Changes Made

• Moved core agent, evaluation code and prompts to their own modules in aieng/agent_evals/report_generation
• Changed the main.py to demo.py which reflects better the demo nature of the UI
• Updated the .env files with the env vars for the report generation, and made an env_vars.py file to access them or their defaults if they haven't been provided
• Moved the import dataset function to the langfuse.py module

Testing

• Tests pass locally (uv run pytest tests/)
• Type checking passes (uv run mypy <src_dir>)
• Linting passes (uv run ruff check src_dir/)
• Manual testing performed (describe below)

Manual testing details:
Ran the UI and the evaluation script to make sure it all work

Checklist

• Code follows the project's style guidelines
• Self-review of code completed
• Documentation updated (if applicable)
• No sensitive information (API keys, credentials) exposed

[amrit110]

LGTM! Just the minor comment

[amrit110]

Good to merge once the tests pass!