We need to measure the performance impact of our proposed solution to the reverse DISTINCT_SCAN for $sort+$group+$last.

There's no need to merge anything, but we should try updating the TSBS insert tests to manually include indexes on the missing {meta, min, max} or {meta, max, min} bucket index for each defined {meta, time} index.  After doubling the number of indexes, how is performance affected?  If there's not much change, we can proceed confidently with the plan to double these indexes.