Validate shared-engine lexical performance harness on Windows

tools/scale-eval/summarize.py

@@ -0,0 +1,45 @@
+"""Summarize retained raw samples; nearest-rank p95, no gate claims."""
+import json
+import math
+import sys
+
+
+def percentile(values, probability):
+    if not values or not 0 < probability <= 1:
+        raise ValueError("nonempty samples and probability in (0, 1] required")
+    if any(not math.isfinite(value) or value < 0 for value in values):
+        raise ValueError("samples must be finite nonnegative milliseconds")
+    ordered = sorted(values)
+    return ordered[math.ceil(len(ordered) * probability) - 1]
+
+
+def summarize(report):
+    if report.get("kind") != "synthetic_lexical_index_only":
+        raise ValueError("unsupported report")
+    rows = []
+    for case in report["cases"]:
+        if len(case["basic"]) != len(case["debug"]) or not case["basic"]:
+            raise ValueError("paired basic/debug samples required")
+        row = {"case": case["case"], "samples_per_mode": len(case["basic"])}
+        for mode in ("basic", "debug"):
+            values = [sample["wall_ms"] for sample in case[mode]]
+            row[mode] = {
+                "p50_ms": percentile(values, 0.5),
+                "p95_ms": percentile(values, 0.95),
+                "maximum_ms": max(values),
+                "engine_p95_ms": percentile(
+                    [sample["metrics"]["total_ms"] for sample in case[mode]], 0.95
+                ),
+            }
+        # Pair order follows the same deterministic request IDs in both arrays.
+        row["mean_paired_debug_minus_basic_ms"] = sum(
+            debug["wall_ms"] - basic["wall_ms"]
+            for basic, debug in zip(case["basic"], case["debug"])
+        ) / len(case["basic"])
+        rows.append(row)
+    return {"kind": report["kind"], "production_gate_pass": None, "cases": rows}
+
+
+if __name__ == "__main__":
+    with open(sys.argv[1], encoding="utf-8") as source:
+        print(json.dumps(summarize(json.load(source)), indent=2))