test: measurement-only refined DFG MRT timing harness

Wall-time A/B/C/E/E' variants over equal simulated duration, reusing
run_refined_dfg setup functions. Fresh state and identical warm-up per
repeat, 3 interleaved repeats, construction/JIT, warm-up and bitwise
population/NaN-mask parity checks outside timed regions. B, C and E' are
labelled timing-only (no valid force history). No numerical or
production change.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/unit/test_time_refined_dfg.py

@@ -0,0 +1,49 @@
+"""CPU contract of the measurement-only refined DFG timing harness (no CUDA)."""
+from pathlib import Path
+import sys
+import unittest
+
+import numpy as np
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "validation"))
+import time_refined_dfg as t  # noqa: E402
+
+
+class TimingHarnessContract(unittest.TestCase):
+    def test_equal_simulated_duration(self):
+        s = t.schedule(2000, 200)
+        self.assertEqual(s["refined"], (200, 2000))
+        self.assertEqual(s["uniform"], (400, 4000))  # one refined base step = two D80 steps
+        self.assertAlmostEqual(s["tstar_window"], 2000 * .01 / 40)
+        for bad in ((0, 1), (1, -1)):
+            with self.assertRaises(ValueError):
+                t.schedule(*bad)
+
+    def test_timing_only_labels(self):
+        for name in ("B", "C", "E'"):
+            self.assertFalse(t.VARIANTS[name]["force_history_valid"])
+            self.assertTrue(t.VARIANTS[name]["timing_only"])
+        for name in ("A", "E"):
+            self.assertTrue(t.VARIANTS[name]["force_history_valid"])
+        self.assertEqual({v["case"] for v in t.VARIANTS.values()}, {"refined", "uniform"})
+
+    def test_parity_detects_bits_and_nan_masks(self):
+        a = np.array([[1., np.nan], [2., 3.]], np.float32)
+        self.assertIsNone(t.same_state([a], [a.copy()]))
+        b = a.copy(); b[1, 1] = np.nextafter(np.float32(3), np.float32(4))
+        self.assertIn("bits", t.same_state([a], [b]))
+        c = a.copy(); c[0, 0] = np.nan
+        self.assertIn("NaN", t.same_state([a], [c]))
+
+    def test_summary_reports_differences_without_claims(self):
+        rows = [dict(variant=v, seconds=s) for v, s in
+                (("A", 3.), ("A", 5.), ("B", 2.), ("C", 1.), ("E", 2.), ("E'", 1.5))]
+        s = t.summarize(rows, .5)
+        self.assertEqual(s["A"]["median_seconds"], 4.)
+        self.assertEqual(s["A_minus_B_seconds"], 2.)
+        self.assertEqual(s["B_minus_C_seconds"], 1.)
+        self.assertEqual(s["A_over_E"], 2.)
+        self.assertIn("not exact causal", s["interpretation"])
+
+
+if __name__ == "__main__": unittest.main()