The resolution implicit in the post is that there’s a “value change” when the reward before and reward after are not better compressed by viewing them as generated by a single “values”. So in the salt case, insofar as the reward is best compressed by viewing it as always valuing homeostasis, that would be the “true values”. But insofar as the reward is not better compressed by one “values” than by two, there’s a values change.
The resolution implicit in the post is that there’s a “value change” when the reward before and reward after are not better compressed by viewing them as generated by a single “values”. So in the salt case, insofar as the reward is best compressed by viewing it as always valuing homeostasis, that would be the “true values”. But insofar as the reward is not better compressed by one “values” than by two, there’s a values change.