#!/usr/bin/env python3
"""P6 helper: emit the 140 sim_variants for the deployability sweep.

Cross-product:  7 costs × 4 latencies × 5 thresholds = 140 variants.

Threshold values are placeholders — the actual values come from
config/ml/v2_prod_thresholds.json after the threshold-tuning step.
Re-run this script post-tuning to refresh sweep_deployability.yaml with
calibrated thresholds.

Usage:
  scripts/generate_sweep_variants.py > config/ml/sweep_deployability.yaml
"""
from __future__ import annotations
import json, sys
from pathlib import Path

# 7 costs (price-units / lot / side). 0.125 = 1 tick (ES), 0.0625 = 0.5 tick (best-case),
# stepping through realistic retail (0.25, 0.375 = 2-3 ticks), and worst-case (1.0 = 8 ticks).
COSTS = [0.0625, 0.125, 0.1875, 0.25, 0.375, 0.5, 1.0]

# 4 latencies (ns). 100M = 100ms (best), 200M = realistic anchor, 300M = degraded,
# 400M = stress anchor.
LATENCIES_NS = [100_000_000, 200_000_000, 300_000_000, 400_000_000]

# 5 thresholds — REPLACE THESE WITH THE OUTPUT OF THE THRESHOLD-TUNING PASS.
# Read from config/ml/v2_prod_thresholds.json if it exists; otherwise use
# the canonical p60-p95 placeholder (5 steps spanning the range).
THRESH_JSON = Path(__file__).resolve().parent.parent / "config" / "ml" / "v2_prod_thresholds.json"
if THRESH_JSON.exists():
    blob = json.loads(THRESH_JSON.read_text())
    THRESHOLDS = blob["thresholds_absolute"]   # e.g. {"p60": 0.42, "p70": 0.55, ...}
    THRESHOLD_NAMES = list(THRESHOLDS.keys())
    THRESHOLD_VALUES = list(THRESHOLDS.values())
    assert len(THRESHOLD_VALUES) == 5, f"expected 5 thresholds; got {len(THRESHOLD_VALUES)}"
else:
    print("# WARNING: v2_prod_thresholds.json missing — using p60-p95 placeholder thresholds",
          file=sys.stderr)
    THRESHOLD_NAMES  = ["p60",  "p70",  "p80",  "p90",  "p95"]
    THRESHOLD_VALUES = [0.40,   0.55,   0.70,   0.85,   0.95]

assert len(COSTS) == 7
assert len(LATENCIES_NS) == 4

print("# P6 deployability sweep — 4 windows × 140 sim_variants (7 cost × 4 latency × 5 threshold).")
print("# Generated by scripts/generate_sweep_variants.py — do NOT hand-edit.")
print("# Re-run after threshold-tuning to refresh threshold absolute values.")
print()
print("base:")
print("  data_template: /mnt/training-data/futures-baseline-mbp10/ES.FUT/ES.FUT_{window}.dbn.zst")
print("  predecoded_dir: /feature-cache/predecoded")
print("  n_parallel: 1                        # batched flow overrides with variants.len()=140")
print("  decision_stride: 4")
print("  latency_ns: 200000000                # default (overridden per variant)")
print("  target_annual_vol_units: 50.0")
print("  annualisation_factor: 825.0")
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_h1000.bin")
print("  sim_variants:")

for ci, cost in enumerate(COSTS):
    for li, latency in enumerate(LATENCIES_NS):
        for ti, (tname, tval) in enumerate(zip(THRESHOLD_NAMES, THRESHOLD_VALUES)):
            name = f"c{ci}_l{li}_{tname}"
            print(f"    - {{ name: {name}, threshold: {tval}, cost_per_lot_per_side: {cost}, latency_ns: {latency} }}")

print()
print("cells:")
print("  - { name: W1, window: 2025-Q2 }")
print("  - { name: W2, window: 2025-Q3 }")
print("  - { name: W3, window: 2025-Q4 }")
print("  - { name: W4, window: 2026-Q1 }")