fix: include finite-sample offset in MinTRL

[stefan-jansen]

What

• Add the canonical finite-sample leading observation to MinTRL.
• Reuse the production MinTRL calculation in the statistical-validity visualization.
• Correct the MinTRL user-guide examples and reference-test terminology.
• Add a seeded Chapter 16 regression that requires Strategy_14 to report 213 observations.
• Bump the package version to 0.1.0b24.
• Align pre-commit Ruff with the project environment so release checks no longer disagree on import grouping.

Root cause

The production formula rounded the continuous asymptotic quantity without first adding the finite-sample leading observation. The visualization separately implemented the asymptotic form, so both paths understated the required track record by one observation in the Chapter 16 example.

Impact

For finite MinTRL results, the continuous quantity receives the canonical +1 before integer ceiling. The seeded Chapter 16 Strategy_14 result changes from 212 to 213 days. Infinite results and the observed-Sharpe-at-or-below-target behavior are unchanged.

Verification

• Focused MinTRL, DSR validation, and visualization tests: 122 passed
• Full suite: 5,286 passed, 21 skipped
• Ruff check and format: passed
• ty: passed
• pre-commit: passed
• Source distribution and wheel build: passed
• Isolated wheel smoke test: version 0.1.0b24, Strategy_14, MinTRL 213.0

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.