You'll notice
Fixed a wrong empty-result count shown in the subagent usage summary.
The routine that builds the <usage> summary block for subagent/workflow runs (<agents_done>, <agents_error>, <agents_skipped>, <agents_empty_result>) previously checked resultPreview against a stale outer-scope variable instead of the current loop item, which could produce a wrong empty-result count. It now checks R.resultPreview on the actual agent being iterated, fixing the agents_empty_result count reported in the usage summary.