fix: add tool info to concisenss, harmfulness, helpfulness and response relevance evaluators

[ybdarrenwang]

Description

Previously, PR #77 intended to add tool info into traces for evaluation. However, some downstream evaluators didn't pick up that info properly, due to different implementation of the _format_prompt method.

This PR fixed this issue by:

• Duplicating the correctly implemented _format_prompt method from Faithfulness evaluator into the following evaluators:
  • Helpfulness
  • Harmfulness
  • Conciseness
  • Response Relevance
• Extracting the above 5 evaluators' shared method into parent class for reusability.
• Extending the unit tests making sure tool traces are presented to these evaluators in both sync and async evaluation calls.

Related Issues

#77

Documentation PR

N/A

Type of Change

Bug fix

Testing

How have you tested the change? Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli

• 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.