feat(clinical): add deterministic summary length budgets

[maziyarpanahi]

Pull Request

Description

Adds deterministic, local-only length budgeting for clinical-summary
generation. A closed policy allocates explicit output-token caps across
approved evidence classes and returns value-free truncation metadata naming
classes whose requested evidence was deferred.

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 the versioned clinical_summary_v1 policy with safety-first priority,
  minimum/maximum bounds, and deterministic weighted allocation.
• Added immutable per-class allocations and SummaryTruncationMetadata with
  deferred class identifiers, counts, fixed statuses, and clinician-review
  guardrails.
• Kept the planner metadata-only: it accepts token counts, never stores source
  values, and performs no model loading or mandatory network call.
• Added the clinical guide and MkDocs/publication navigation entries.

Testing

• 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
• I have tested this change with different models/inputs

Exact local validation:

• .venv/bin/python -m pytest tests/unit/clinical/test_summary_length_budget.py -q — 7 passed
• .venv/bin/python -m pytest tests/unit/clinical/test_summary_length_budget.py tests/unit/clinical/test_summary_card.py tests/unit/clinical/test_citation_ordering.py -q — 35 passed
• .venv/bin/python -m mypy openmed/clinical/summary_length_budget.py — passed
• .venv/bin/python -m py_compile openmed/clinical/summary_length_budget.py tests/unit/clinical/test_summary_length_budget.py — passed
• make format — passed; 2036 files left unchanged
• make lint — passed
• make format-check — passed; 2036 files already formatted
• make docs-build — passed, including strict MkDocs staging and publication validation
• git diff --check — passed

Checks intentionally not run: the full repository test suite, model-backed or
benchmark checks, Swift checks (no Swift files changed), and remote CI waiting.

Documentation

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

Code Quality

• I ran make format, make lint, and make format-check
• For Swift/OpenMedKit changes, I ran make format-swift and make lint-swift
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• My changes generate no new warnings

Dependencies

• I have not added any new dependencies
• OR I have added new dependencies and they are justified because: ____

Checklist

• I have read the contributing guide, Code of Conduct, and maintainer guide
• My commits have clear, descriptive messages
• I have squashed/organized my commits appropriately

Related Issues

Closes #2706

Screenshots/Examples

The synthetic API and truncation examples are covered in
tests/unit/clinical/test_summary_length_budget.py and
docs/clinical/summary-length-budgets.md; no patient or restricted data is
used.