run_phase0.py

#!/usr/bin/env python3
"""Phase 0 entrypoint: run Gate 0, write the report, HALT.

Usage:
    python run_phase0.py [configs/phase0.yaml]

Reads HF_TOKEN from the environment (or the vault .env via load_env) for the manifest
download. Never prints or persists the token.
"""
from __future__ import annotations

import os
import sys
from pathlib import Path

import yaml

ROOT = Path(__file__).resolve().parent
sys.path.insert(0, str(ROOT))

from eval.gates import run_gate0, write_report  # noqa: E402


def load_env_token() -> None:
    """Load HF_TOKEN from the vault .env if not already set. Token is never logged."""
    if os.environ.get("HF_TOKEN") or os.environ.get("HUGGING_FACE_HUB_TOKEN"):
        return
    env_path = ROOT.parent / ".env"
    if env_path.exists():
        for line in env_path.read_text().splitlines():
            line = line.strip()
            if line.startswith("HF_TOKEN") and "=" in line:
                val = line.split("=", 1)[1].strip().strip('"').strip("'")
                os.environ["HF_TOKEN"] = val
                os.environ["HUGGING_FACE_HUB_TOKEN"] = val
                break


def main() -> int:
    cfg_path = sys.argv[1] if len(sys.argv) > 1 else str(ROOT / "configs" / "phase0.yaml")
    with open(cfg_path) as f:
        cfg = yaml.safe_load(f)
    load_env_token()

    report = run_gate0(cfg)
    out = write_report(report, cfg["gate0"]["report_path"])

    print(f"\n=== Gate 0: {report['status']} ===")
    for m in report["metrics"]:
        flag = "PASS" if m["passed"] else ("GAP" if m["name"] == "token_bank_size" else "FAIL")
        print(f"  [{flag}] {m['name']}: {m['detail']}")
    if report["data_gaps"]:
        print("  data gaps:")
        for g in report["data_gaps"]:
            print(f"    - {g}")
    print(f"\nReport written to {out}")
    print("HALT. A human must set human_signoff='GO' before Phase 1.")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())