#!/usr/bin/env python3 """ Classify market discovery repositories using primary GitHub metadata. The command is read-only. It does not add watch-registry entries, install SDKs, call LLMs, approve paid provider use, enter replay, or change production. """ from __future__ import annotations import argparse import importlib.util import json import sys from pathlib import Path from typing import Any from urllib.request import Request, urlopen ROOT = Path(__file__).resolve().parents[2] SERVICE_PATH = ROOT / "apps" / "api" / "src" / "services" / "agent_market_discovery_classifier.py" def main() -> int: parser = argparse.ArgumentParser(description="Classify AWOOOI Agent discovery candidates.") parser.add_argument("--discovery-review", required=True, help="agent_market_discovery_review_v1 JSON") parser.add_argument("--metadata", help="optional repository metadata JSON keyed by repository_full_name") parser.add_argument("--output", help="classification output JSON") parser.add_argument("--timeout-seconds", type=int, default=12) args = parser.parse_args() discovery_review = _read_json(Path(args.discovery_review)) metadata = ( _read_json(Path(args.metadata)) if args.metadata else _fetch_repository_metadata(discovery_review, args.timeout_seconds) ) service = _load_service() report = service.run_agent_market_discovery_classification( discovery_review=discovery_review, repository_metadata=metadata, ) rendered = json.dumps(report, ensure_ascii=False, indent=2, sort_keys=True) if args.output: Path(args.output).write_text(rendered + "\n", encoding="utf-8") else: print(rendered) print(json.dumps(report["summary"], ensure_ascii=False, sort_keys=True)) return 0 def _fetch_repository_metadata( discovery_review: dict[str, Any], timeout_seconds: int, ) -> dict[str, dict[str, Any]]: metadata: dict[str, dict[str, Any]] = {} for draft in discovery_review.get("candidate_drafts") or []: if draft.get("status") != "needs_primary_source_classification": continue repo = str(draft.get("repository_full_name", "")) if not repo: continue try: metadata[repo] = _fetch_one_repository(repo, timeout_seconds) except Exception as exc: # noqa: BLE001 metadata[repo] = { "full_name": repo, "html_url": draft.get("html_url"), "description": None, "topics": [], "stargazers_count": draft.get("stargazers_count_max"), "error": str(exc), } return metadata def _fetch_one_repository(repo: str, timeout_seconds: int) -> dict[str, Any]: request = Request( f"https://api.github.com/repos/{repo}", headers={ "User-Agent": "awoooi-agent-market-discovery-classifier/1.0", "Accept": "application/vnd.github+json", }, ) with urlopen(request, timeout=timeout_seconds) as response: # noqa: S310 payload = json.loads(response.read().decode("utf-8")) return { "full_name": str(payload.get("full_name") or repo), "html_url": payload.get("html_url"), "description": payload.get("description"), "homepage": payload.get("homepage"), "topics": list(payload.get("topics") or []), "language": payload.get("language"), "stargazers_count": payload.get("stargazers_count"), "pushed_at": payload.get("pushed_at"), "archived": bool(payload.get("archived", False)), } def _read_json(path: Path) -> dict[str, Any]: with path.open(encoding="utf-8") as handle: payload = json.load(handle) if not isinstance(payload, dict): raise SystemExit(f"{path}: expected JSON object") return payload def _load_service() -> Any: module_name = "awoooi_agent_market_discovery_classifier_service" spec = importlib.util.spec_from_file_location(module_name, SERVICE_PATH) if spec is None or spec.loader is None: raise SystemExit(f"cannot load discovery classifier service from {SERVICE_PATH}") module = importlib.util.module_from_spec(spec) sys.modules[module_name] = module spec.loader.exec_module(module) return module if __name__ == "__main__": raise SystemExit(main())