#!/usr/bin/env bash
# One-command reproduction of the paper's biological-model tier (see REPRODUCING.md).
#
#   ./reproduce.sh              env -> tests -> biological model at committed seeds -> figures
#   ./reproduce.sh --with-gpu   also runs the trained-network, MNIST, and language-model tiers
#
# Writes REPRODUCED.md: every artifact's recomputed content hash next to the committed one, so a
# reader can see at a glance which bundles reproduced bitwise. The biological-model tier must match
# exactly; GPU tiers are statistically reproducible only (REPRODUCING.md section 5).
set -euo pipefail

WITH_GPU=0
[[ "${1:-}" == "--with-gpu" ]] && WITH_GPU=1

cd "$(dirname "$0")"
START=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
say() { printf '\n\033[1m== %s\033[0m\n' "$1"; }

say "Environment (uv sync from the committed uv.lock)"
if ! command -v uv >/dev/null; then
  echo "uv not found. Install it: curl -LsSf https://astral.sh/uv/install.sh | sh" >&2
  exit 1
fi
if [[ $WITH_GPU -eq 1 ]]; then
  uv sync --extra dev --extra neural --extra mnist --extra llm
else
  uv sync --extra dev
fi

say "Tests (correctness + closed-form scientific validation)"
uv run pytest -q

say "Biological-model tier at the committed seeds"
make layer1

if [[ $WITH_GPU -eq 1 ]]; then
  say "Trained-network tier"; make neural
  say "Real-MNIST tier";      make mnist
  say "Language-model tier";  make llm
  say "LLM predictive test";  make llm-epistasis
fi

say "Figures (pure functions of the artifacts)"
make figures
make paper-figures

say "Hash report -> REPRODUCED.md"
uv run python - "$START" "$WITH_GPU" <<'EOF'
import hashlib, json, pathlib, subprocess, sys, datetime

start, with_gpu = sys.argv[1], sys.argv[2] == "1"
commit = subprocess.run(["git", "rev-parse", "HEAD"], capture_output=True, text=True).stdout.strip()
rows, exact, differ, missing = [], 0, 0, 0
for man_path in sorted(pathlib.Path("results").glob("*/manifest.json")):
    man = json.loads(man_path.read_text())
    pq = man_path.parent / "results.parquet"
    want = man.get("results_sha256", "")
    if not pq.exists():
        status, got, missing = "not run", "-", missing + 1
    else:
        got = hashlib.sha256(pq.read_bytes()).hexdigest()
        if got == want:
            status, exact = "bitwise match", exact + 1
        else:
            status, differ = "differs", differ + 1
    rows.append((man_path.parent.name, man.get("master_seed", "-"), status, want[:12], got[:12]))

out = [
    "# Reproduction report", "",
    f"- Started: {start}", f"- Finished: {datetime.datetime.now(datetime.UTC):%Y-%m-%dT%H:%M:%SZ}",
    f"- Commit: `{commit}`", f"- GPU tiers included: {'yes' if with_gpu else 'no'}",
    f"- Bundles: {exact} bitwise match, {differ} differ, {missing} not run", "",
    "The biological-model tier is bitwise reproducible and must show `bitwise match`. GPU tiers are",
    "statistically reproducible only, so `differs` is expected there (see REPRODUCING.md section 5).",
    "", "| Bundle | Seed | Status | Committed sha256 | Recomputed |", "|---|---|---|---|---|",
]
out += [f"| `{n}` | {s} | {st} | `{w}…` | `{g}…` |" for n, s, st, w, g in rows]
pathlib.Path("REPRODUCED.md").write_text("\n".join(out) + "\n")
print(f"{exact} bitwise match, {differ} differ, {missing} not run -> REPRODUCED.md")
EOF

say "Done. See REPRODUCED.md, and REPRODUCING.md for the figure-by-figure map."