fix(benchmark): validate EdgeBench pass rates

Reject compact EdgeBench results whose best_pass_rate falls outside [0,1], and cover upper and lower out-of-range values.

Co-authored-by: TRAE CLI <noreply@bytedance.com>

Author: wangyuchao.404

examples/edgebench-benchmark-adapter-smoke.py

@@ -162,6 +162,22 @@ def test_contracts() -> None:
     assert mismatched["first_blocker"] == "edgebench_submission_rounds_mismatch"
     assert_boundary(mismatched)
 
+    for invalid_pass_rate in (1.5, -0.1):
+        invalid = reduce_edgebench_final_result(
+            task_id="ad_placement_optimization",
+            run_id=f"edgebench-smoke-pass-rate-{invalid_pass_rate}",
+            result={
+                "best_pass_rate": invalid_pass_rate,
+                "total_rounds": 1,
+                "agent_submissions": 1,
+                "auto_submissions": 0,
+                "runtime_seconds": 60.0,
+            },
+        )
+        assert invalid["countable"] is False
+        assert invalid["first_blocker"] == "edgebench_pass_rate_out_of_range"
+        assert_boundary(invalid)
+
 
 def run_cli(*args: str) -> subprocess.CompletedProcess[str]:
     return subprocess.run(

loopx/benchmark_adapters/edgebench.py

@@ -244,6 +244,8 @@ def reduce_edgebench_final_result(
     blockers: list[str] = []
     if best_score is None and best_pass_rate is None:
         blockers.append("edgebench_best_metric_missing")
+    if best_pass_rate is not None and not 0.0 <= best_pass_rate <= 1.0:
+        blockers.append("edgebench_pass_rate_out_of_range")
     if total_rounds is None or total_rounds <= 0:
         blockers.append("edgebench_submission_rounds_missing")
     elif (