feat(sleep): 3-way train/val/test split + gate_mode on|off

Data-split refactor (the anti-overfitting foundation the user asked for):
  - TaskRecord gains split∈{train,val,test} and origin∈{real,dream}.
  - assign_splits: real tasks deterministically split into val/test (disjoint);
    DREAM-augmented tasks (origin='dream') NEVER enter val/test — they only go to
    train. val gates updates; test is the final held-out measure.
  - gbrain loader maps its held-out.jsonl -> test, benchmark.jsonl -> train/val,
    so the gbrain held-out stays the true final score.
  - consolidate(): train drives reflect, val gates; adds gate_mode='off' (greedy,
    no hard filter) reporting val movement (greedy_improved/regressed/flat).
  - run_gbrain/transfer/experiment score on test (val fallback); run_gbrain gains
    --gate on|off. Legacy replay/holdout names normalized.

New test proves dream tasks never land in val/test. 21 tests pass; mock
experiment + gate=off both green.

Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>

skillopt/sleep/cycle.py

@@ -175,6 +175,7 @@ def run_sleep_cycle(
         edit_budget=cfg.get("edit_budget", 4),
         gate_metric=cfg.get("gate_metric", "mixed"),
         gate_mixed_weight=cfg.get("gate_mixed_weight", 0.5),
+        gate_mode=cfg.get("gate_mode", "on"),
         evolve_skill=cfg.get("evolve_skill", True),
         evolve_memory=cfg.get("evolve_memory", True),
         night=night,