#!/usr/bin/env bash
# Tier 1.5 local mid-smoke — RTX 3050 Ti, b=128, 2000 train + 500 eval steps.
#
# Closes the 700× dev-cycle gap between Tier 1 (6 sec local correctness) and
# Tier 2 (70 min cluster eval). Gates 80%+ of bad hypotheses before they reach
# cluster. Target wall-clock: ≤ 10 min on RTX 3050.
#
# Spec: docs/superpowers/specs/2026-06-02-fast-dev-cycle.md §3.2
# Verdict: python3 scripts/tier1_5_verdict.py <out-dir>
#
# Data: test_data/futures-baseline-mid/ES.FUT/ — symlinks to 2024-Q1 (train,
# 4.8GB) + 2024-Q2 (eval, 14GB) MBP-10 files from the canonical PVC.
# Walk-forward split: --n-folds 2 --fold-idx 0 → train=Q1, eval=Q2.
#
# Usage:
#   ./scripts/local-mid-smoke.sh                                # default seed=42
#   ./scripts/local-mid-smoke.sh --seed 123                     # override seed
#   ./scripts/local-mid-smoke.sh --out /tmp/foxhunt-alt         # custom out dir
#   ./scripts/local-mid-smoke.sh --n-backtests 64               # smaller batch
#
# Per `feedback_local_smoke_before_cluster`: run this BEFORE every cluster
# smoke when touching .cu / trait impls / buffers / N_ACTIONS / ISV slots.

set -euo pipefail

SEED=42
OUT_DIR="/tmp/foxhunt-mid-smoke"
N_BACKTESTS=128
N_STEPS=2000
N_EVAL_STEPS=500
N_FOLDS=2
FOLD_IDX=0

usage() {
  cat <<EOF
Usage: $(basename "$0") [OPTIONS]

Tier 1.5 mid-smoke — b=128, 2000+500 steps, ~10 min on RTX 3050.

Options:
  --seed N             RNG seed (default: $SEED — reproducible)
  --out DIR            Output directory (default: $OUT_DIR)
  --n-backtests N      Batch size (default: $N_BACKTESTS; drop to 64 if OOM)
  --n-steps N          Train steps (default: $N_STEPS)
  --n-eval-steps N     Eval steps (default: $N_EVAL_STEPS)
  --n-folds K          Walk-forward fold count (default: $N_FOLDS)
  --fold-idx K         Walk-forward fold index (default: $FOLD_IDX)
  -h, --help           Show this help

Output:
  \$OUT_DIR/diag.jsonl              — per-step train diag (642 scalars/step)
  \$OUT_DIR/eval_diag.jsonl         — per-step eval diag
  \$OUT_DIR/alpha_rl_train_summary.json  — final summary
EOF
}

while [[ $# -gt 0 ]]; do
  case "$1" in
    --seed)           SEED="$2"; shift 2 ;;
    --out)            OUT_DIR="$2"; shift 2 ;;
    --n-backtests)    N_BACKTESTS="$2"; shift 2 ;;
    --n-steps)        N_STEPS="$2"; shift 2 ;;
    --n-eval-steps)   N_EVAL_STEPS="$2"; shift 2 ;;
    --n-folds)        N_FOLDS="$2"; shift 2 ;;
    --fold-idx)       FOLD_IDX="$2"; shift 2 ;;
    -h|--help)        usage; exit 0 ;;
    *) echo "Unknown option: $1" >&2; usage >&2; exit 2 ;;
  esac
done

REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
cd "$REPO_ROOT"

# --mbp10-data-dir points DIRECTLY at the instrument's .dbn.zst directory
# (matches argo-rl template line: --mbp10-data-dir /data/futures-baseline-mbp10/ES.FUT).
MBP10_DIR="$REPO_ROOT/test_data/futures-baseline-mid/ES.FUT"
PREDECODED_DIR="$REPO_ROOT/test_data/futures-baseline-mid"

# Sanity checks.
if [[ ! -d "$MBP10_DIR" ]]; then
  echo "ERROR: $MBP10_DIR not found." >&2
  echo "Run setup: see CLAUDE.md 'Tier 1.5 data path' or docs/superpowers/specs/2026-06-02-fast-dev-cycle.md §3.1" >&2
  exit 3
fi

n_mbp_files=$(find -L "$MBP10_DIR" -maxdepth 1 -name '*.dbn.zst' 2>/dev/null | wc -l)
if [[ "$n_mbp_files" -lt 2 ]]; then
  echo "ERROR: $MBP10_DIR has $n_mbp_files MBP-10 files; need ≥ 2 for walk-forward split." >&2
  exit 3
fi

mkdir -p "$OUT_DIR"

echo "=== Tier 1.5 mid-smoke ==="
echo "  Repo:           $REPO_ROOT"
echo "  Seed:           $SEED"
echo "  Batch:          $N_BACKTESTS"
echo "  Steps:          $N_STEPS train + $N_EVAL_STEPS eval"
echo "  Walk-forward:   fold $FOLD_IDX of $N_FOLDS"
echo "  MBP-10 dir:     $MBP10_DIR (${n_mbp_files} files)"
echo "  Out dir:        $OUT_DIR"
echo

# Build (sccache + dev-release for fast iteration; --release matches cluster).
echo "[build] cargo build --release --example alpha_rl_train -p ml-alpha"
SQLX_OFFLINE=true cargo build --release --example alpha_rl_train -p ml-alpha

BINARY="$REPO_ROOT/target/release/examples/alpha_rl_train"
if [[ ! -x "$BINARY" ]]; then
  echo "ERROR: binary not found at $BINARY after build." >&2
  exit 4
fi

echo
echo "[run] $BINARY ..."
START_TS=$(date +%s)

# Per `feedback_no_stubs`: the binary owns its full life cycle. We just
# invoke it and capture wall time. Exit code 2 = G8 NaN abort (per binary
# docstring); we propagate it so the caller knows the run died.
"$BINARY" \
  --mbp10-data-dir "$MBP10_DIR" \
  --predecoded-dir "$PREDECODED_DIR" \
  --out "$OUT_DIR" \
  --diag-jsonl "$OUT_DIR/diag.jsonl" \
  --eval-diag-jsonl "$OUT_DIR/eval_diag.jsonl" \
  --n-steps "$N_STEPS" \
  --n-eval-steps "$N_EVAL_STEPS" \
  --n-backtests "$N_BACKTESTS" \
  --n-folds "$N_FOLDS" \
  --fold-idx "$FOLD_IDX" \
  --seed "$SEED" \
  --instrument-mode front-month \
  --log-every 200 \
  --gpu-idx 0

END_TS=$(date +%s)
ELAPSED=$((END_TS - START_TS))
ELAPSED_MIN=$((ELAPSED / 60))
ELAPSED_SEC=$((ELAPSED % 60))

echo
echo "=== Mid-smoke complete in ${ELAPSED_MIN}m ${ELAPSED_SEC}s ==="
echo "Outputs:"
ls -lh "$OUT_DIR" 2>/dev/null
echo
echo "Next:"
echo "  python3 $REPO_ROOT/scripts/tier1_5_verdict.py $OUT_DIR"