Extract RAI scorer token metrics into Score metadata and save to memory

[slister1001]

• Extract token usage (prompt_tokens, completion_tokens, total_tokens) from RAI service eval_result via sample.usage or result properties.metrics
• Add token_usage to score_metadata dict in RAIServiceScorer
• Save scores to PyRIT CentralMemory after creation (fail-safe)
• Propagate scorer token_usage through ResultProcessor to output item properties.metrics for downstream aggregation
• Add 5 unit tests covering token extraction, memory save, and error handling

Description

Please add an informative description that covers that changes made by the pull request and link all relevant issues.

If an SDK is being regenerated based on a new API spec, a link to the pull request containing these API spec changes should be included above.

All SDK Contribution checklist:

• The pull request does not introduce [breaking changes]
• CHANGELOG is updated for new features, bug fixes or other significant changes.
• I have read the contribution guidelines.

General Guidelines and Best Practices

• Title of the pull request is clear and informative.
• There are a small number of commits, each of which have an informative message. This means that previously merged commits do not appear in the history of the PR. For more information on cleaning up the commits in your PR, see this page.

Testing Guidelines

• Pull request includes test coverage for the included changes.

[Copilot]

Pull request overview

This PR enhances red teaming result fidelity by extracting RAI scorer token usage into score metadata, persisting scores into PyRIT CentralMemory, and propagating token metrics into output item properties.metrics for downstream aggregation.

Changes:

• Extract token usage (prompt_tokens, completion_tokens, total_tokens, cached_tokens) from RAI evaluation results and attach it to Score.score_metadata.
• Save created scores into PyRIT CentralMemory (best-effort) to support later retrieval (e.g., attack_result.last_score).
• Propagate scorer token usage through ResultProcessor into output item properties.metrics, with unit tests covering extraction + memory behavior.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.

File	Description
sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/red_team/_foundry/_rai_scorer.py	Adds token usage extraction + score metadata builder; persists scores to CentralMemory.
sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/red_team/_result_processor.py	Reads token usage from serialized score metadata and propagates it into output properties.metrics when eval metrics aren’t present.
sdk/evaluation/azure-ai-evaluation/tests/unittests/test_redteam/test_foundry.py	Adds unit tests for token usage extraction paths and fail-safe memory persistence.

[nagkumar91]

Clean, well-scoped PR. No issues found.

• Token extraction with two-level fallback (sample.usage → result.properties.metrics) is robust ✅
• Memory save with graceful degradation on failure ✅
• String metadata handling for PyRIT serialization ✅
• Scorer token usage propagation as fallback when eval_row lacks metrics ✅
• 5 tests covering extraction, fallback, absent data, memory save, and memory failure ✅

LGTM.