refactor(per-horizon): N_HORIZONS 5→3 — alpha_train example
Renames all *_h6000 references to *_h1000 (new longest horizon):
- AlphaTrainSummary struct fields: best_auc_h6000_* → best_auc_h1000_*,
best_h6000_ckpt_path → best_h1000_ckpt_path
- State vars: best_auc_h6000*, h6000_no_improvement → h1000 equivalents
- Checkpoint filename: trunk_best_h6000.bin → trunk_best_h1000.bin
- CLI early-stop metric: "auc_h6000" → "auc_h1000"
- Tracing log fields: w_h30..w_h6000 → w_h10/w_h100/w_h1000
- 4 hardcoded [seq.labels[0..4][k]] literals → std::array::from_fn
- MultiHorizonLoaderConfig.horizons + AlphaTrainSummary.horizons:
literal [30,100,300,1000,6000] → HORIZONS constant
- Doc comments: "5 horizons", "h6000-snapshot" → "N_HORIZONS", "longest-horizon"
KNOWN FOLLOW-UP (Task 7): 5 sweep YAMLs reference trunk_best_h6000.bin
filename — must update atomically when applying workflow template changes.
KNOWN FOLLOW-UP (Task 8): crates/ml-alpha/src/gpu_log.rs:176-192 still
decodes 5-horizon JSON fields (raw_h30..h6000, ema_h30..h6000, etc.).
cargo check --example alpha_train: PASS.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
81e9970d4c