refactor(per-horizon): N_HORIZONS 5→3 — sweep configs + generator script

5 sweep YAMLs updated to reference the new checkpoint filename:
- config/ml/sweep_smoke.yaml: trunk_best_h6000.bin → trunk_best_h1000.bin
- config/ml/sweep_perhoriz_diag.yaml: same
- config/ml/sweep_threshold_tuning.yaml: same
- config/ml/sweep_deployability.yaml: same
- config/ml/sweep_smoke_perhoriz_cfc.yaml: same + 3 comment updates
  (WIN-gate criteria, header doc, best-checkpoint annotation)

scripts/generate_sweep_variants.py:61 updated atomically — without this
the next regeneration of sweep_deployability.yaml would silently
re-introduce trunk_best_h6000.bin.

Argo workflow templates (alpha-perception, alpha-cv, lob-backtest-sweep)
did NOT need text changes — they're already horizon-agnostic:
- They forward CLI flags via {{workflow.parameters.*}} to binaries
- Don't grep alpha_train_summary.json inline
- Don't reference per-horizon field names
- early-stop-metric default is "mean_auc" (horizon-agnostic)

Intentionally left:
- alpha-cv-template.yaml stacker-horizon: "6000" (unrelated TFT lookback)
- alpha-cv-template.yaml horizon: "1200" (DQN execution horizon in bars)
- lob-backtest-sweep-template.yaml ci-training-h100 (GPU pool name)

NOTE: kubectl apply of workflow templates is deferred to Task 10 (push
+ dispatch). Verified all 5 sweep YAMLs parse with python3 yaml.safe_load.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

config/ml/sweep_deployability.yaml

@@ -13,7 +13,7 @@ base:
   max_events: 0
   seed: 12648430
   # __SHA__ replaced by submitter with post-trunk-grows training short-SHA.
-  checkpoint: /feature-cache/alpha-perception-runs/__SHA__/trunk_best_h6000.bin
+  checkpoint: /feature-cache/alpha-perception-runs/__SHA__/trunk_best_h1000.bin
   sim_variants:
     - { name: c0_l0_p60, threshold: 0.4, cost_per_lot_per_side: 0.0625, latency_ns: 100000000 }
     - { name: c0_l0_p70, threshold: 0.55, cost_per_lot_per_side: 0.0625, latency_ns: 100000000 }

config/ml/sweep_perhoriz_diag.yaml

@@ -0,0 +1,20 @@
+base:
+  data: /mnt/training-data/futures-baseline-mbp10/ES.FUT
+  predecoded_dir: /feature-cache/predecoded
+  n_parallel: 1
+  latency_ns: 200000000
+  target_annual_vol_units: 50.0
+  annualisation_factor: 825.0
+  max_lots: 5
+  max_events: 2000000
+  seed: 12648430
+  checkpoint: /feature-cache/alpha-perception-runs/8b2ac1e57/trunk_best_h1000.bin
+  min_reasonable_px: 1000.0
+  max_reasonable_px: 20000.0
+  delta_floor: 1.0
+  per_horizon_logit_sampling_stride: 1000
+  sim_variants:
+    - { name: t0c1l200_perhoriz_diag, threshold: 0.0, cost_per_lot_per_side: 0.125,
+        latency_ns: 200000000, max_hold_ns: 60000000000 }
+cells:
+  - { name: perhoriz_diag }

config/ml/sweep_smoke.yaml

@@ -24,7 +24,7 @@ base:
   max_events: 2000000              # ~2M events, ~10k decisions, ~16 min wall
   seed: 12648430
   # dbd500ecf is the post-trunk-grows training checkpoint.
-  checkpoint: /feature-cache/alpha-perception-runs/dbd500ecf/trunk_best_h6000.bin
+  checkpoint: /feature-cache/alpha-perception-runs/dbd500ecf/trunk_best_h1000.bin
   min_reasonable_px: 1000.0    # ES futures: reject sub-$1000 (catches $48-100 outliers + negatives)
   max_reasonable_px: 20000.0   # ES futures: reject super-$20000 (catches $53k outliers; > ES all-time-high ~$7000)
   delta_floor: 1.0             # CRT.1 C1.3: skip seeding when |target − effective| < 1 lot

config/ml/sweep_smoke_perhoriz_cfc.yaml

@@ -0,0 +1,31 @@
+# Per-horizon CfC architecture validation smoke.
+# Loads the trunk_best_h1000.bin checkpoint from Smoke 1 (commit bf4d0c899).
+# Single cell. Same anchor as sweep_smoke.yaml (1-tick cost, 200ms latency)
+# but with the per-horizon CfC architecture checkpoint.
+#
+# CRT.diag emitted by the harness (mean_run_len, flip_count, run_length_hist)
+# per horizon — used to evaluate Smoke 2's WIN gate:
+#   mean_run_len[h1000] / mean_run_len[h10] >= 10x
+#   mean_run_len[h1000] >= 100 events
+
+base:
+  data: /mnt/training-data/futures-baseline-mbp10/ES.FUT
+  predecoded_dir: /feature-cache/predecoded
+  n_parallel: 1
+  latency_ns: 200000000
+  target_annual_vol_units: 50.0
+  annualisation_factor: 825.0
+  max_lots: 5
+  max_events: 2000000
+  seed: 12648430
+  # Per-horizon CfC architecture checkpoint (Smoke 1's best_h1000 from N_HORIZONS=3 run).
+  checkpoint: /feature-cache/alpha-perception-runs/8b2ac1e57/trunk_best_h1000.bin
+  min_reasonable_px: 1000.0
+  max_reasonable_px: 20000.0
+  delta_floor: 1.0
+  sim_variants:
+    - { name: t0c1l200_perhoriz_cfc, threshold: 0.0, cost_per_lot_per_side: 0.125,
+        latency_ns: 200000000, max_hold_ns: 60000000000 }
+
+cells:
+  - { name: perhoriz_smoke }

config/ml/sweep_threshold_tuning.yaml

@@ -18,7 +18,7 @@ base:
   seed: 12648430
   # __SHA__ is replaced by argo-lob-sweep.sh / the operator at submission time
   # with the post-trunk-grows training short-SHA (9 chars).
-  checkpoint: /feature-cache/alpha-perception-runs/__SHA__/trunk_best_h6000.bin
+  checkpoint: /feature-cache/alpha-perception-runs/__SHA__/trunk_best_h1000.bin
   # 8 thresholds spanning p60-p95 (5pt steps). Cost held at the realistic
   # anchor (1 tick = 0.125 price units) so threshold-tuning Sharpe reflects
   # what the deployability sweep will see at that cost.

scripts/generate_sweep_variants.py

@@ -58,7 +58,7 @@ print("  max_lots: 5")
 print("  max_events: 0")
 print("  seed: 12648430")
 print("  # __SHA__ replaced by submitter with post-trunk-grows training short-SHA.")
-print("  checkpoint: /feature-cache/alpha-perception-runs/__SHA__/trunk_best_h6000.bin")
+print("  checkpoint: /feature-cache/alpha-perception-runs/__SHA__/trunk_best_h1000.bin")
 print("  sim_variants:")
 
 for ci, cost in enumerate(COSTS):