chore: checkpoint local wip for issue 892

scripts/benchmarks/run_suite.py

@@ -17,7 +17,7 @@ import importlib.util
 import json
 import sys
 import time
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from pathlib import Path
 
 import requests
@@ -216,7 +216,7 @@ def generate_markdown(all_results: dict, run_date: str) -> str:
                 lines.append(f"- **Result:** {bres.get('detail', bres.get('error', 'n/a'))}")
                 snippet = bres.get("code_snippet", "")
                 if snippet:
-                    lines.append(f"- **Generated code snippet:**")
+                    lines.append("- **Generated code snippet:**")
                     lines.append("  ```python")
                     for ln in snippet.splitlines()[:8]:
                         lines.append(f"  {ln}")
@@ -287,7 +287,7 @@ def parse_args() -> argparse.Namespace:
 
 def main() -> int:
     args = parse_args()
-    run_date = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M UTC")
+    run_date = datetime.now(UTC).strftime("%Y-%m-%d %H:%M UTC")
 
     print(f"Model Benchmark Suite — {run_date}")
     print(f"Testing {len(args.models)} model(s): {', '.join(args.models)}")