Enforce Gate 3 test quality budgets

scripts/write_test_evidence.py

@@ -97,14 +97,40 @@ def junit_snapshot(path: Path) -> dict[str, Any]:
     failures: list[str] = []
     errors: list[str] = []
     skipped: list[str] = []
-    durations: list[dict[str, str | float]] = []
+    durations: list[dict[str, Any]] = []
+    marker_totals: dict[str, dict[str, int | float]] = {}
+    missing_marker_nodeids: list[str] = []
     for case in cases:
         nodeid = f"{case.attrib.get('classname', '<unknown>')}::{case.attrib.get('name', '<unknown>')}"
         try:
             duration = float(case.attrib.get("time", "0"))
         except ValueError as exc:
             raise ValueError(f"JUnit testcase {nodeid} has invalid time") from exc
-        durations.append({"nodeid": nodeid, "seconds": duration})
+        if not math.isfinite(duration) or duration < 0:
+            raise ValueError(f"JUnit testcase {nodeid} has invalid time")
+        marker_property = None
+        properties = case.find("properties")
+        if properties is not None:
+            values = [
+                item.attrib.get("value", "")
+                for item in properties.findall("property")
+                if item.attrib.get("name") == "duration_markers"
+            ]
+            if len(values) > 1:
+                raise ValueError(f"JUnit testcase {nodeid} repeats duration_markers")
+            marker_property = values[0] if values else None
+        if marker_property is None:
+            missing_marker_nodeids.append(nodeid)
+        markers = sorted({
+            marker.strip()
+            for marker in (marker_property or "unmarked").split(",")
+            if marker.strip()
+        })
+        durations.append({"nodeid": nodeid, "seconds": duration, "markers": markers})
+        for marker in markers:
+            summary = marker_totals.setdefault(marker, {"tests": 0, "duration_seconds": 0.0})
+            summary["tests"] = int(summary["tests"]) + 1
+            summary["duration_seconds"] = float(summary["duration_seconds"]) + duration
         if case.find("failure") is not None:
             failures.append(nodeid)
         if case.find("error") is not None:
@@ -113,6 +139,20 @@ def junit_snapshot(path: Path) -> dict[str, Any]:
             skipped.append(nodeid)
     failed = set(failures) | set(errors) | set(skipped)
     durations.sort(key=lambda item: (-float(item["seconds"]), str(item["nodeid"])))
+    suites = list(root.iter("testsuite"))
+    raw_suite_duration = suites[0].attrib.get("time") if suites else None
+    try:
+        suite_duration = (
+            float(raw_suite_duration)
+            if raw_suite_duration is not None
+            else sum(float(item["seconds"]) for item in durations)
+        )
+    except ValueError as exc:
+        raise ValueError("JUnit testsuite has invalid time") from exc
+    if not math.isfinite(suite_duration) or suite_duration < 0:
+        raise ValueError("JUnit testsuite has invalid time")
+    for summary in marker_totals.values():
+        summary["duration_seconds"] = round(float(summary["duration_seconds"]), 3)
     return {
         "total": len(cases),
         "passed": len(cases) - len(failed),
@@ -120,6 +160,11 @@ def junit_snapshot(path: Path) -> dict[str, Any]:
         "errors": errors,
         "skipped": skipped,
         "duration_seconds": round(sum(float(item["seconds"]) for item in durations), 3),
+        "suite_duration_seconds": round(suite_duration, 3),
+        "durations": durations,
+        "marker_durations": dict(sorted(marker_totals.items())),
+        "marker_metadata_complete": not missing_marker_nodeids,
+        "missing_marker_nodeids": missing_marker_nodeids,
         "slowest": durations[:20],
     }