#!/usr/bin/env python3 """ Build NeMo/Nemotron external replay request JSONL from AWOOOI candidate inputs. This script does not call NVIDIA APIs, NIM endpoints, tools, or LLMs. """ from __future__ import annotations import argparse import json import sys from pathlib import Path from typing import Any ROOT = Path(__file__).resolve().parents[2] API_SRC = ROOT / "apps" / "api" sys.path.insert(0, str(API_SRC)) from src.services.agent_nemotron_replay_adapter import ( # noqa: E402 build_nemotron_replay_requests, ) def main() -> int: parser = argparse.ArgumentParser( description="Build NeMo/Nemotron replay request JSONL." ) parser.add_argument("--inputs", required=True, help="candidate input JSONL") parser.add_argument("--output", required=True, help="Nemotron request JSONL") parser.add_argument("--report", help="optional request-pack build report JSON") parser.add_argument( "--candidate-variant-id", help="optional Nemotron candidate variant id, e.g. contract tuned v1", ) parser.add_argument("--max-records", type=int, help="optional local smoke limit") args = parser.parse_args() candidate_inputs = _read_jsonl(Path(args.inputs)) if args.max_records is not None: candidate_inputs = candidate_inputs[: args.max_records] requests = build_nemotron_replay_requests( candidate_inputs, candidate_variant_id=args.candidate_variant_id, ) with Path(args.output).open("w", encoding="utf-8") as handle: for request in requests: handle.write(json.dumps(request.to_dict(), ensure_ascii=False, sort_keys=True)) handle.write("\n") report = { "schema_version": "agent_nemotron_request_pack_build_report_v1", "inputs": args.inputs, "output": args.output, "records": len(requests), "external_calls": False, "request_only": True, "candidate_id": "nemo_nemotron_fabric", "candidate_variant_id": args.candidate_variant_id, "max_records": args.max_records, } if args.report: Path(args.report).write_text( json.dumps(report, ensure_ascii=False, indent=2, sort_keys=True) + "\n", encoding="utf-8", ) print(json.dumps(report, ensure_ascii=False, sort_keys=True)) return 0 def _read_jsonl(path: Path) -> list[dict[str, Any]]: records: list[dict[str, Any]] = [] with path.open(encoding="utf-8") as handle: for line_number, line in enumerate(handle, start=1): line = line.strip() if not line or line.startswith("#"): continue try: records.append(json.loads(line)) except Exception as exc: raise SystemExit(f"{path}:{line_number}: invalid JSONL: {exc}") from exc return records if __name__ == "__main__": raise SystemExit(main())