The collection bulk loader for resharding should take the aggregation pipeline from SERVER-49785, run it against a particular donor, and insert the returned documents into the new sharded collection on itself (a recipient).

• Serialize the aggregation pipeline from createCloningPipelineForResharding() using Pipeline::serializeToBson() and use the serialized form to create an AggregationRequest.
• Add the necessary read concern and hint to the AggregationRequest.
• Run the aggregate command on the remote donor. Unclear if this should be using ClusterAggregate::runAggregate() or some other mechanism. sharded_agg_helpers::attachCursorToPipeline() has come up as a way to having the merging happen on the local node (the recipient in the case of this ticket) for computing the new initial split; see also the changes from 262e5a9 as part of SERVER-49525.
• Use Collection::insertDocuments() to insert the documents into the new sharded collection.