Add TauBench Verified benchmark integration

[ping-Toven]

Summary

Add a new TauBench Verified benchmark suite by mirroring the existing TauBench integration and wiring it through registry, config, and docs metadata.

What are you adding?

• Bug fix (non-breaking change which fixes an issue)
• New benchmark/evaluation
• New model provider
• CLI enhancement
• Performance improvement
• Documentation update
• API/SDK feature
• Integration (CI/CD, tools)
• Export/import functionality
• Code refactoring
• Breaking change
• Other

Changes Made

• Added tau_bench_verified_{retail,airline,telecom} evals plus dataset/solver/scorer wrappers following the existing TauBench file pattern.
• Extended TauBench dataset/solver internals to support verified data sourcing and per-sample TAU2_DATA_DIR switching safely.
• Registered benchmark metadata/eval group, added dependency group entries, regenerated docs benchmark snippet, and added dataset unit tests.

Testing

• I have run the existing test suite (pytest)
• I have added tests for my changes
• I have tested with multiple model providers (if applicable)
• I have run pre-commit hooks (pre-commit run --all-files)

Checklist

• My code follows the project's style guidelines
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation (if applicable)
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

Related Issues

N/A

Additional Context

Verified TauBench data can be overridden via OPENBENCH_TAU2_VERIFIED_DATA_DIR when needed.