feat: add ground truth assertion support to Goal Success Rate evaluator

[ybdarrenwang]

Description

This PR enhances the GoalSuccessRateEvaluator to support assertion-based evaluation mode alongside the existing conversation-analysis mode. The evaluator now accepts ground truth assertions via metadata and validates agent behavior against these explicit success criteria.

Related Issues

#95

Documentation PR

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]

1. I would prefer the assertions to be expected_criteria / expected_goal to align with what other evaluators have, and to avoid confusion between deterministic assertions
   1.2. Add expected_criteria : str | None = None to EvaluationData and Case
2. How useful is the additional_context?
3. Can't the prompt be goal_success_rate_v1? what's the major diff?

[ybdarrenwang]

1. I would prefer the assertions to be expected_criteria / expected_goal to align with what other evaluators have, and to avoid confusion between deterministic assertions
   1.2. Add expected_criteria : str | None = None to EvaluationData and Case
2. How useful is the additional_context?
3. Can't the prompt be goal_success_rate_v1? what's the major diff?

1. That makes sense. Will incorporate that in the next revision.
2. @kangISU @subbu10123 can you answer this?
3. I don't think so. goal_success_rate and goal_success_rate_with_assertions are fundamentally different prompts. In the future their versions have to evolve separately.

[kangISU]

• How useful is the additional_context?

This is for flexibility. Customers may want to include additional context for their specific use cases/domains, to further guide/help the evaluation. However, it can be removed if flexibility is not a high priority here.