feat(ai): add PixelRAG platform probe worker

2026-07-10 09:50:30 +08:00
parent 8ce2fe670d
commit 911369c119
11 changed files with 1098 additions and 9 deletions
--- a/scripts/ops/run_pixelrag_platform_probe_worker.py
+++ b/scripts/ops/run_pixelrag_platform_probe_worker.py
@@ -0,0 +1,108 @@
+#!/usr/bin/env python3
+"""Run or dry-run the PixelRAG platform probe worker."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[2]
+if str(ROOT) not in sys.path:
+    sys.path.insert(0, str(ROOT))
+
+from services.pixelrag_platform_probe_worker_service import (  # noqa: E402
+    run_pixelrag_platform_probe_worker,
+)
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(
+        description="執行或 dry-run PixelRAG platform probe worker。"
+    )
+    parser.add_argument(
+        "--artifact-root",
+        help="PixelRAG visual evidence artifact root；預設使用 production/container 設定。",
+    )
+    parser.add_argument(
+        "--vlm-receipt-root",
+        help="PixelRAG VLM replay receipt root；預設使用 production/container 設定。",
+    )
+    parser.add_argument(
+        "--output-root",
+        help="Platform probe worker receipt output root。",
+    )
+    parser.add_argument(
+        "--capture-output-root",
+        help="Public-context capture artifact output root；預設寫回 PixelRAG visual evidence root。",
+    )
+    parser.add_argument(
+        "--platform",
+        action="append",
+        dest="platforms",
+        help="限制平台，可重複指定，例如 --platform shopee_tw --platform coupang_tw。",
+    )
+    parser.add_argument(
+        "--max-age-hours",
+        type=int,
+        default=168,
+        help="receipt 最大新鮮度小時數。",
+    )
+    parser.add_argument(
+        "--limit",
+        type=int,
+        default=25,
+        help="最多處理 probe candidate 數。",
+    )
+    parser.add_argument(
+        "--timeout",
+        type=int,
+        default=30,
+        help="public-context capture timeout 秒數。",
+    )
+    parser.add_argument(
+        "--settle-ms",
+        type=int,
+        default=800,
+        help="頁面載入後等待毫秒數。",
+    )
+    parser.add_argument(
+        "--max-tiles",
+        type=int,
+        default=12,
+        help="每次 public-context capture 最多切出的 tiles。",
+    )
+    parser.add_argument(
+        "--execute",
+        action="store_true",
+        help="真的執行 public-context capture 或 structured fallback package；未指定時只做 no-write dry-run。",
+    )
+    parser.add_argument(
+        "--write-receipt",
+        action="store_true",
+        help="execute 後寫入 platform probe worker artifact receipt；不寫 DB。",
+    )
+    args = parser.parse_args()
+
+    payload = run_pixelrag_platform_probe_worker(
+        artifact_root=args.artifact_root,
+        vlm_receipt_root=args.vlm_receipt_root,
+        output_root=args.output_root,
+        capture_output_root=args.capture_output_root,
+        platform=tuple(args.platforms or ()),
+        max_age_hours=args.max_age_hours,
+        limit=args.limit,
+        timeout=args.timeout,
+        settle_ms=args.settle_ms,
+        max_tiles=args.max_tiles,
+        execute=args.execute,
+        write_receipt=bool(args.write_receipt and args.execute),
+    )
+    print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
+    return 0 if payload.get("success") else 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())