The wmmin bug has been a long-standing annoyance in the hyper package. I reported this to bugzilla in 2020 here, observing that maxp() sometimes fails due to a problem in constrOptim().

Anyway, today Léopold Guyot uploaded a proposed fix.

Actions on me:

1. Review Léopold's fix and report back to bugzilla
2. Review issues problem in skating_analysis vignette: #18 specificp.ne.test() bug #201 and bug in zapweak() #220
3. Review commit c9a65c7