feat(hunt): contamination check (4.5): runs that used a reported repository are marked and kept out of any gain

contamination.py reads the repositories named by the held-out pilot manifest and by every
benchmark report (accepted_repos.json and NOTES.md links under benchmarks/measurements), marks
each run directory clean or contaminated with the report digest and time, and refuses to count
an unchecked run toward a gain. ablation.analyse carries excluded_from_gain when its run is
contaminated. Implemented by Codex (gpt-6-astra), gated here; the benchmark import is lazy so
the package imports without the benchmarks tree.

Co-Authored-By: Claude Fable 5.1 <[email protected]>

.kiro/specs/hunter-learning-loop/tasks.md

@@ -72,7 +72,7 @@
   - For every annotation, its effect when removed from the full set and when added to the baseline, with intervals and counts; an annotation stays only on a held-out effect whose interval excludes zero or when a kept annotation needs it; one that raises suspicions without raising recall is dropped and recorded
   - Done when the table is written for a fixture ablation and the rule's decisions match the fixture's expectations
   - _Requirements: 4.4, 4.5, 4.6_
-- [ ] 4.5 Contamination check
+- [x] 4.5 Contamination check
   - A training repository later found in the pilot or in a benchmark report marks every run that used it as contaminated and excludes those runs from any gain
   - Done when a fixture run is marked contaminated after its repository is added to a report list
   - _Requirements: 2.7_