XY-1163: R1 define model ladder and local background organizer benchmark gate

[yvette-carlisle]

Summary

• define the L0/L1/L2/L3/L4 model ladder and proposal-only local/background organizer contract
• add the R1 local organizer fixture, scoring, validation, markdown/reporting, and cargo make task
• update benchmark evidence, docs indexes, README, and aggregate tests

Validation

• cargo make fmt
• cargo make lint-fix
• cargo make checks
• cargo make real-world-memory-r1-local-organizer
• cargo test -p elf-eval --test real_world_job_benchmark local_organizer --no-fail-fast

Review

• Independent fresh-context review found two validation findings on the first committed head; both were repaired.
• Repair review checkpoint for current HEAD is clean.