Auto-picks representative call-graph/search tasks from a repo's built
call graph, so mix beamscope.benchmark doesn't need hardcoded
per-repo function names — the same task shapes used for
docs/search-benchmark-2026-07.md's manual benchmark
(get_callers/get_callees/find_call_path/search_code), automated
instead of hand-picked, so the tool works against any repo.
Summary
Functions
Picks one task of each shape from graph. Returns nil for any shape
that couldn't be auto-discovered (e.g. find_call_path needs at least
one real edge to exist).