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

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.")