Validate shared-engine lexical performance harness on Windows

tools/scale-eval/test_summary.py

@@ -0,0 +1,30 @@
+import unittest
+from summarize import percentile, summarize
+
+
+class SummaryTests(unittest.TestCase):
+    def test_nearest_rank_and_unsorted_input(self):
+        self.assertEqual(percentile(list(range(20, 0, -1)), 0.95), 19)
+        self.assertEqual(percentile([3, 1, 2], 0.5), 2)
+
+    def test_reject_invalid_samples(self):
+        for values in ([], [-1], [float("nan")], [float("inf")]):
+            with self.assertRaises(ValueError):
+                percentile(values, 0.95)
+
+    def test_paired_overhead_retains_negative_noise(self):
+        sample = lambda ms: {"wall_ms": ms, "metrics": {"total_ms": ms / 2}}
+        report = {"kind": "synthetic_lexical_index_only", "cases": [{
+            "case": "exact", "basic": [sample(4), sample(6)],
+            "debug": [sample(3), sample(5)],
+        }]}
+        result = summarize(report)
+        self.assertIsNone(result["production_gate_pass"])
+        self.assertEqual(result["cases"][0]["mean_paired_debug_minus_basic_ms"], -1)
+        report["cases"][0]["debug"].pop()
+        with self.assertRaises(ValueError):
+            summarize(report)
+
+
+if __name__ == "__main__":
+    unittest.main()