Test power spikes, calm wind and restart of the new model layers

A single 5-minute +700 W spike moves the room's thermal response by at
most 0.2 kW and leaves the baseline at the persistent load. In calm air
the wind terms vanish while natural ventilation remains. Extended and
ventilation coefficients and heat-source baselines survive a restart
unchanged (no hour of baseline re-learning), and enabling an extra
ventilation term later keeps everything learned for the others.

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

tests/test_windows.py

@@ -55,6 +55,10 @@ class GeometryTests(unittest.TestCase):
                                    [-9.0, -36.0, 21.6, -45.0, -9.0, 0.0]):
             self.assertAlmostEqual(value, expected)
         self.assertIsNone(wm.ventilation_vector(['vent_wind'], 20, 2, {**inputs, 'wind': None}))
+        # Calm air: wind terms vanish, natural ventilation stays.
+        calm = wm.ventilation_vector(features, 20.0, 2.0, {**inputs, 'wind': 0.0, 'gust': 0.0})
+        self.assertEqual([round(v, 9) for v in calm[1:4]], [0.0, 0.0, 0.0])
+        self.assertEqual(calm[0], -9.0)
         self.assertEqual(wm.ventilation_vector(['vent_natural'], 20, 2, {**inputs, 'wind': None}), [-9.0])
         self.assertIsNone(wm.ventilation_vector(['recovery'], 20, 2, {**inputs, 'recovery': 0.5}))
         self.assertEqual(wm.ventilation_vector(['recovery'], 19, 2, {**inputs, 'recovery': 0.5, 't_ref': 21}),