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

artemis/agents/flash/runner.py

@@ -96,6 +96,7 @@ from artemis.services.llm import (
     get_openai_llm,
     get_llm,
     invoke_llm_with_timeout_message,
+    with_fallback,
 )
 from artemis.tools.history import history_tool_declarations
 from artemis.tools.android_files import android_file
@@ -1506,20 +1507,32 @@ class FlashRunner:
             turn_base = len(messages) - 1
             current_tools = report_only_tools if is_final else self._get_tools()
 
+            async def invoke_turn():
+                if using_tool_fallback:
+                    return await self._invoke_model(fallback_llm, current_tools, messages)
+
+                async def invoke_fallback():
+                    nonlocal fallback_llm
+                    if fallback_llm is None:
+                        fallback_llm = get_llm(self.ctx, name="operator", use_fallback=True)
+                    return await self._invoke_model(fallback_llm, current_tools, messages)
+
+                return await with_fallback(
+                    lambda: self._invoke_model(llm, current_tools, messages),
+                    invoke_fallback,
+                    none_should_fallback=False,
+                )
+
             if isinstance(control, TaskControl):
                 interrupted, response = await control.run_interruptibly(
-                    self._invoke_model(
-                        fallback_llm if using_tool_fallback else llm, current_tools, messages
-                    ),
+                    invoke_turn(),
                     on_pause=getattr(self.ctx, "on_task_pause", None),
                     on_resume=getattr(self.ctx, "on_task_resume", None),
                 )
             else:
                 interrupted, response = (
                     False,
-                    await self._invoke_model(
-                        fallback_llm if using_tool_fallback else llm, current_tools, messages
-                    ),
+                    await invoke_turn(),
                 )
 
             if interrupted or (

artemis/agents/operator/operator.py

@@ -35,7 +35,7 @@ from artemis.mcp.action_specs import OPERATOR_SHELL_ORDER, operator_shell_tool
 from artemis.llm.usage import usage_from_message
 from artemis.llm.structured import content_to_text
 from artemis.runtime.task_control import TaskControl, has_pending_instruction
-from artemis.services.llm import acomplete, get_llm, invoke_llm_with_timeout_message
+from artemis.services.llm import acomplete, get_llm, invoke_llm_with_timeout_message, with_fallback
 from artemis.tools.command_tool import (
     analyze_task_output_wrapper,
     get_adb_task_registry,
@@ -638,9 +638,19 @@ class OperatorNode:
                     and t.name not in {"plugin_load", "plugin_read_file", "plugin_read_result"}
                 ]
                 traced_tools.extend(plugins.langchain_tools())
-            bound_llm = active_llm.bind_tools(tools=traced_tools)
+
+            async def invoke(model):
+                bound = model.bind_tools(tools=traced_tools)
+                return await invoke_llm_with_timeout_message(acomplete(bound, current_messages))
+
             interrupted, response = await self._await_or_pause(
-                invoke_llm_with_timeout_message(acomplete(bound_llm, current_messages))
+                invoke(active_llm)
+                if using_tool_fallback
+                else with_fallback(
+                    lambda: invoke(base_llm),
+                    lambda: invoke(get_llm(ctx=self.ctx, name="operator", use_fallback=True)),
+                    none_should_fallback=False,
+                )
             )
             if interrupted:
                 return None, None, None, False