test: single-level upload, launch and final-wait failures fail the instance

Fault injection with the existing host fakes for FixedPatchStepper(
refinements=[]): an initialize upload failure, a BlockHaloCopy,
BlockCurvedBoundary or BlockStep launch failure, and a failing final
stream wait each raise, leave the instance failed (step/download refused)
and keep the completed step count; a failed launch never reaches the wait.

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

tests/unit/test_single_level.py

@@ -1,7 +1,8 @@
 """Host contract of FixedPatchStepper(refinements=[]): one blocked level (mocked driver).
 
 Per step: halo refresh -> static BFL (circles only) -> BlockStep with a null
-kind, one stream wait per step(n) call, NaN spare after initialize.
+kind, one stream wait per step(n) call, NaN spare after initialize. An upload,
+launch or wait failure fails the instance and keeps its step count.
 """
 from contextlib import nullcontext
 from unittest.mock import Mock
@@ -19,12 +20,20 @@ def circle(center=(15.5, 11.5), radius=4.3):
     return SimObject(0, geometry=CircleGeometry(*center, radius), center=center, radius=radius)
 
 
-def backend(objects=()):
+def backend(objects=(), failing_kernel=None, initialize=True):
     host, log = host_module(), []
+    host.armed = False  # set True to make failing_kernel raise
+
+    def launch(name):
+        def run(*a, **k):
+            log.append((name, a))
+            if name == failing_kernel and host.armed:
+                raise RuntimeError(name + " launch failed")
+        return run
+
     module = Mock()
     module.get_global.return_value = (Mock(), 20)
-    module.get_function.side_effect = lambda name: Mock(
-        side_effect=lambda *a, **k: log.append((name, a)))
+    module.get_function.side_effect = lambda name: Mock(side_effect=launch(name))
     host.compiler.build_module.return_value = module
     host.cuda.mem_alloc.side_effect = lambda size: Mock(size=size)
     host.cuda.memcpy_htod.side_effect = lambda pointer, array: log.append(("upload", (pointer, array)))
@@ -33,13 +42,18 @@ def backend(objects=()):
                                  refinements=[], level_blocks=[(12, 16)], level_objects=[objects])
     run._stream.synchronize.side_effect = lambda: log.append(("sync", ()))
     log.clear()
-    run.initialize(np.full(run._levels[0].shape, 1 / 9, np.float32))
-    return run, log
+    if initialize:
+        run.initialize(np.full(run._levels[0].shape, 1 / 9, np.float32))
+    return run, log, host
+
+
+def state():
+    return np.full((9, 24, 32), 1 / 9, np.float32)
 
 
 class SingleLevel(unittest.TestCase):
     def test_spare_starts_nan_and_current_holds_state(self):
-        run, log = backend()
+        run, log, _ = backend()
         level = run._levels[0]
         uploads = {id(a[0]): a[1] for name, a in log if name == "upload"}
         self.assertTrue(np.isnan(uploads[id(level.spare)]).all())
@@ -49,7 +63,7 @@ class SingleLevel(unittest.TestCase):
         for objects, order in (((), ["BlockHaloCopy", "BlockStep"]),
                                ((circle(),), ["BlockHaloCopy", "BlockCurvedBoundary", "BlockStep"])):
             with self.subTest(bodies=len(objects)):
-                run, log = backend(objects)
+                run, log, _ = backend(objects)
                 log.clear()
                 run.step(2)
                 self.assertEqual([name for name, _ in log], order * 2 + ["sync"])
@@ -57,11 +71,43 @@ class SingleLevel(unittest.TestCase):
                 self.assertEqual(int(step[4]), 0)  # null kind: every core cell ACTIVE
 
     def test_circle_solids_are_not_state(self):
-        run, _ = backend((circle(),))
+        run, _, _ = backend((circle(),))
         solid = run._level_boundaries[0].tables["solid"]
         self.assertTrue(solid.any())
         np.testing.assert_array_equal(run._state[0], ~solid)
 
+    def test_initialize_upload_failure_fails_instance(self):
+        run, _, host = backend(initialize=False)
+        host.cuda.memcpy_htod.side_effect = RuntimeError("upload failed")
+        with self.assertRaisesRegex(RuntimeError, "upload failed"):
+            run.initialize(state())
+        with self.assertRaisesRegex(RuntimeError, "failed"):
+            run.step(1)
+
+    def test_launch_failure_fails_instance_and_keeps_step_count(self):
+        for kernel, objects in (("BlockHaloCopy", ()), ("BlockCurvedBoundary", (circle(),)),
+                                ("BlockStep", ())):
+            with self.subTest(kernel=kernel):
+                run, log, host = backend(objects, failing_kernel=kernel)
+                run.step(1)
+                host.armed = True
+                log.clear()
+                with self.assertRaisesRegex(RuntimeError, kernel + " launch failed"):
+                    run.step(2)
+                self.assertEqual(run.step_count, 1)
+                self.assertNotIn("sync", [name for name, _ in log])
+                with self.assertRaisesRegex(RuntimeError, "failed"):
+                    run.download()
+
+    def test_final_wait_failure_fails_instance_and_keeps_step_count(self):
+        run, _, _ = backend()
+        run._stream.synchronize.side_effect = RuntimeError("device error")
+        with self.assertRaisesRegex(RuntimeError, "device error"):
+            run.step(3)
+        self.assertEqual(run.step_count, 0)
+        with self.assertRaisesRegex(RuntimeError, "failed"):
+            run.step(1)
+
 
 if __name__ == "__main__":
     unittest.main()