feat: add correctness evaluator, trace-based and reference-based

[ybdarrenwang]

Description

Add correctness evaluator, supporting both trace-based and reference-based evaluation

Related Issues

#95

Documentation PR

strands-agents/docs#714

Type of Change

New feature

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.

[poshinchen]

🤔 I'm a bit confused about expected_assertion, and the expected_output now.
What is the difference? Can't we always use one or another in trace-based evaluators?

[ybdarrenwang]

🤔 I'm a bit confused about expected_assertion, and the expected_output now. What is the difference? Can't we always use one or another in trace-based evaluators?

After discussion offline, we confirmed that it shouldn't make difference, and we'll use expected_assertions for both

• GoalSuccessRateEvaluator with assertion
• CorrectnessEvaluator with reference