feat: Add FaithfulnessEvaluator

[jjbuck]

Description

1. Add FaithfulnessEvaluator to assess whether agent responses conflict with conversation history
2. Implement 5-level scoring system (Not At All, Not Generally, Neutral/Mixed, Generally Yes, Completely Yes
3. Add faithfulness prompt templates (v0) with evaluation guidelines
4. Include example usage and comprehensive unit tests
5. Update naming of low-level data types (turn -> trace, conversation -> session) to align better with OTEL conventions.

Related Issues

1. feat: add GoalSuccessRateEvaluator for conversation goal tracking #22 (goal success rate)
2. Implement trace-based evaluation with helpfulness evaluator. #16 (helpfulness)

Documentation PR

N/A

Type of Change

1. New feature ("Faithfulness Evaulator")
2. Refactor Update naming of low-level data types (turn -> trace, conversation -> session) to align better with OTEL conventions.

Testing

• I ran hatch run prepare

Checklist

• I have read the CONTRIBUTING document
• I have added any necessary tests that prove my fix is effective or my feature works
• I have updated the documentation accordingly
• I have added an appropriate example to the documentation to outline the feature, or no new docs are needed
• My changes generate no new warnings
• Any dependent changes have been merged and published

---

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

[jjbuck]

@poshinchen just rebased on the tip of main (which now includes #25).

[jjbuck]

@poshinchen addressed your comments above in the latest edits.