Closes the 'refactoring-only endpoint too narrow' risk flagged by the
cross-family rubber-duck. Adds two boundary stimuli never used in trim tuning:
9. Separate a smuggled behavior change from a requested rename (rename +
smuggled 10%->12% discount change) -> should separate/flag, not bundle.
10. Recognize a behavior-changing simplification is not a refactor (remove
free-shipping-over-\ rule under a 'cleanup' framing) -> should not
silently change observable behavior.
Executor reverted to claude-opus-4.6 / judge gpt-5.5 (re-judge) to match the
stringent Confirm A family where boundary behavior looked weakest.
Eval-branch only; not on PR #873.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 3c9f9823-7f2f-4f7d-9d1b-f2b9e7a20c60
CI-only eval branch (NOT part of PR #873). Carries the uncommitted
cost-trim + PR-comment fix on both SKILL.md, the eval.yaml rubric
re-alignment, and two new eval.vally.yaml specs so the vally CI can
evaluate whether the current skill content helps before merging.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 3c9f9823-7f2f-4f7d-9d1b-f2b9e7a20c60
Abhitej John