feat: add clinical domain coverage eval

[maziyarpanahi]

Pull Request

Description

Adds an offline aggregate coverage gate for the shipped clinical label maps and synthetic span fixtures.

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Code refactoring
• Performance improvement
• Test addition/improvement

Changes Made

• Added per-domain and per-label coverage reporting with offsets and counts only.
• Added missing-fixture, orphan-label, invalid-offset, and no-span failure checks.
• Registered the suite and benchmark CLI command, added synthetic fixtures, docs, and a CI gate.

Testing

• I have added tests that prove my fix is effective or that my feature works
• Focused evaluator, CLI, documentation, and label-map tests pass locally
• I have tested this change with different models/inputs

Documentation

• I have updated the documentation accordingly
• I have added docstrings to new functions/classes
• I have updated the CHANGELOG.md

Code Quality

• Changed-file Ruff lint and format checks pass
• I have performed a self-review of my own code
• My changes generate no new warnings

Dependencies

• I have not added any new dependencies

Related Issues

Closes #866

Screenshots/Examples

Not applicable.

[maziyarpanahi]

Integrated via #2693 after exact-head validation. The combined clinical/evaluation batch passed 468 focused tests, Ruff checks and format verification, and a strict documentation build; every intermediate and final Git tree matched the rehearsal.