"""Explicit execution gate for resource-intensive pipeline commands.""" import argparse import json from pathlib import Path def load_config(path): path = Path(path) config = json.loads(path.read_text(encoding="utf-8")) if isinstance(config, dict) and "extends" in config: parent = load_config(path.parent / config.pop("extends")) config = {**parent, **{key: {**parent[key], **value} if isinstance(value, dict) and isinstance(parent.get(key), dict) else value for key, value in config.items()}} if not isinstance(config, dict) or isinstance(config.get("seed"), bool) or not isinstance(config.get("seed"), int): raise ValueError("Config must be an object with an integer seed") for section in ("prepare", "pairs", "evaluate", "train", "search"): if not isinstance(config.get(section), dict): raise ValueError(f"Missing config section: {section}") positive = { "prepare": ["batch_size", "threads"], "pairs": ["max_train_pairs", "max_queries", "max_corpus", "threads"], "evaluate": ["batch_size", "query_chunk_size", "max_seq_length"], "train": ["max_pairs", "batch_size", "mini_batch_size", "max_seq_length", "epochs", "learning_rate"], "search": ["batch_size", "max_seq_length", "top_k", "max_candidates"], } for section, fields in positive.items(): for field in fields: value = config[section][field] if isinstance(value, bool) or not isinstance(value, (int, float)) or value <= 0: raise ValueError(f"{section}.{field} must be positive") if field not in {"epochs", "learning_rate"} and not isinstance(value, int): raise ValueError(f"{section}.{field} must be an integer") if config["prepare"]["max_rows"] is not None and (not isinstance(config["prepare"]["max_rows"], int) or config["prepare"]["max_rows"] <= 0): raise ValueError("prepare.max_rows must be null or a positive integer") if config["prepare"]["description_characters"] < 0: raise ValueError("description_characters must be nonnegative") if config["pairs"]["max_corpus"] < config["pairs"]["max_queries"]: raise ValueError("max_corpus must be >= max_queries") if not isinstance(config["pairs"]["require_shared_gtin"], bool): raise ValueError("require_shared_gtin must be a boolean") if config["evaluate"]["backend"] not in {"lexical", "embedding"}: raise ValueError("Evaluation backend must be lexical or embedding") if not 0 <= config["train"]["warmup_ratio"] <= 1: raise ValueError("warmup_ratio must be between 0 and 1") if config["train"]["mini_batch_size"] > config["train"]["batch_size"]: raise ValueError("mini_batch_size must not exceed batch_size") return config def main(argv=None): parser = argparse.ArgumentParser(description=__doc__) parser.add_argument("command", choices=("prepare", "pairs", "evaluate", "train", "search")) parser.add_argument("--config", type=Path, default=Path("configs/local.json")) parser.add_argument("--execute", action="store_true", help="Explicitly authorize this resource-intensive stage") parser.add_argument("--allow-download", action="store_true", help="Allow model downloads for this execution (default: cached/local files only)") args = parser.parse_args(argv) try: config = load_config(args.config) section = config[args.command] if not args.execute: print(json.dumps({"status": "dry_run", "command": args.command, "seed": config["seed"], "config": section, "note": "No corpus scan, optional-library import, model download, or GPU work performed. Add --execute only when resources are available."}, indent=2)) return if args.command == "prepare": from .prepare import prepare result = prepare(section, config["seed"]) elif args.command == "pairs": from .pairs import build_datasets result = build_datasets(section, config["seed"]) elif args.command == "evaluate": from .evaluate import evaluate result = evaluate(section, args.allow_download) elif args.command == "train": from .train import train result = train(section, config["seed"], args.allow_download) else: from .search import search result = search(section, args.allow_download) print(json.dumps(result, indent=2)) except (ValueError, OSError, KeyError, ImportError, RuntimeError) as exc: parser.exit(1, f"Error: {exc}\n") if __name__ == "__main__": main()