fix(runtime): recover awake ownership and batch model failures

tests/unit/agents/test_flash_runner_ledger.py

@@ -429,6 +429,44 @@ def _report(status="completed", tc_id="tc-report", **extra):
 _INITIAL_OBSERVATION = ("shot0.png", b"IMG0", "[1] Settings")
 
 
+@pytest.mark.asyncio
+async def test_generation_failure_uses_fallback_without_repeating_device_actions(mock_context):
+    from artemis.llm.response_guard import ResponseIntegrityError
+    from artemis.services import llm as gateway
+
+    click = AIMessage(
+        content="tap", tool_calls=[{"name": "click", "args": {"index": 1}, "id": "click"}]
+    )
+    with patch("artemis.controllers.unified_controller.get_driver"):
+        runner = _make_runner(mock_context, [])
+    primary = runner._init_llm.return_value
+    fallback = Mock()
+    calls = []
+
+    async def invoke(model, tools, messages):
+        calls.append(model)
+        if len(calls) == 1:
+            assert gateway._FALLBACK_AVAILABLE.get()
+            raise ResponseIntegrityError("missing completed response")
+        if model is fallback:
+            assert not gateway._FALLBACK_AVAILABLE.get()
+            return click
+        return _report()
+
+    runner._invoke_model = AsyncMock(side_effect=invoke)
+    with (
+        patch(
+            "artemis.agents.flash.runner.capture_screenshot_and_parse_ui",
+            AsyncMock(return_value=_INITIAL_OBSERVATION),
+        ),
+        patch("artemis.agents.flash.runner.get_llm", return_value=fallback),
+    ):
+        result = await runner.run(State(initial_goal="Open Settings"))
+    assert result["status"] == "completed"
+    assert calls == [primary, fallback, primary]
+    assert runner.executor.execute.await_count == 1
+
+
 @pytest.mark.asyncio
 @pytest.mark.parametrize("fallback_succeeds", [True, False])
 async def test_failed_actions_have_finite_fallback_and_restore_primary(

tests/unit/agents/test_operator_recovery.py

@@ -82,6 +82,31 @@ async def run_loop(operator, monkeypatch, responses):
     return result, messages, invoke
 
 
+@pytest.mark.asyncio
+async def test_generation_failure_hands_over_before_pausing(operator, monkeypatch):
+    from artemis.llm.response_guard import ResponseIntegrityError
+    from artemis.services import llm as gateway
+
+    node, state = operator
+    primary, fallback = Mock(), Mock()
+    contexts = []
+
+    async def invoke(model, messages):
+        contexts.append(gateway._FALLBACK_AVAILABLE.get())
+        if model is primary.bind_tools.return_value:
+            raise ResponseIntegrityError("missing completed response")
+        assert model is fallback.bind_tools.return_value
+        return click()
+
+    monkeypatch.setattr("artemis.agents.operator.operator.acomplete", invoke)
+    monkeypatch.setattr("artemis.agents.operator.operator.get_llm", Mock(return_value=fallback))
+    messages = []
+    result = await node._invoke_llm_loop(primary, messages, [], [], state)
+    assert contexts == [True, False]
+    assert len(result[0]) == 1
+    assert len([m for m in messages if isinstance(m, AIMessage)]) == 1
+
+
 @pytest.mark.asyncio
 async def test_prose_retry_keeps_context_and_recovers_once(operator, monkeypatch):
     prose = AIMessage(content="I will click the model menu.")