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

artemis/interfaces/cli/commands/run.py

@@ -164,6 +164,7 @@ async def execute_task(
         config.with_graph_config_callbacks(graph_config_callbacks)
 
     agent: Agent | None = None
+    task_started = False
     try:
         agent = Agent(config=config.build(), session_id=effective_sid)
         await agent.init(
@@ -196,7 +197,14 @@ async def execute_task(
             request.plugins = plugins
         elif plugin_choices is not None:
             request.plugins = TypeAdapter(list[PluginSelection]).validate_json(plugin_choices)
+        task_started = True
         await agent.run_task(request=request)
+    except Exception as exc:
+        if not task_started and effective_sid:
+            from artemis.runtime.task_result import save_failure_result
+
+            save_failure_result(str(effective_sid), str(exc), code="initialization_failed")
+        raise
     finally:
         if agent is not None:
             await agent.clean()

artemis/runtime/awake_service.py

@@ -101,7 +101,10 @@ def _configure_usb_stay_awake(device_id: str) -> str | None:
     # Migration cleanup belongs to the long-lived host. A queued task worker
     # must not wait on another process's optional legacy wake-lock cleanup.
     if os.environ.get("ARTEMIS_TASK_WORKER") != "1":
-        ScreenAwakeLease(device_id).cleanup_unowned_references()
+        try:
+            ScreenAwakeLease(device_id).cleanup_unowned_references()
+        except OSError as exc:
+            logger.warning(f"Could not prepare optional legacy awake cleanup on {device_id}: {exc}")
 
     commands = (
         (
@@ -209,6 +212,7 @@ class ScreenAwakeService:
         self._monitor_thread: threading.Thread | None = None
         self._shutdown_requested = False
         self._owners: dict[str, FileLock] = {}
+        self._ownership_warnings: set[str] = set()
 
     def start(self, device_ids: Iterable[str] | None = None) -> dict[str, str | None]:
         if self._shutdown_requested:
@@ -241,13 +245,24 @@ class ScreenAwakeService:
             existing = self._strategies.get(device_id)
             if existing is not None:
                 return existing
-            owner = _owner_lock(device_id)
             try:
+                owner = _owner_lock(device_id)
                 owner.acquire(timeout=0)
             except Timeout:
                 # Do not cache a follower as owner: discovery can take over if
                 # the process holding the OS lock exits or releases the device.
                 return None
+            except OSError as exc:
+                # Awake is optional. Never bypass ownership or let an ACL / I/O
+                # failure abort device connection, resume, or the host monitor.
+                if device_id not in self._ownership_warnings:
+                    logger.warning(
+                        f"Could not acquire awake ownership on {device_id}; skipping optional "
+                        f"stay-awake policy: {exc}"
+                    )
+                    self._ownership_warnings.add(device_id)
+                return None
+            self._ownership_warnings.discard(device_id)
             try:
                 strategy = _configure_usb_stay_awake(device_id)
             except BaseException:

artemis/sdk/agent.py

@@ -584,6 +584,7 @@ class Agent:
                 or getattr(getattr(task, "request", None), "task_name", None)
             )
             device_lock = None
+            execution_started = False
             try:
                 # Construct the runtime only inside the task's cleanup boundary. A
                 # cancelled queue wait or setup failure must not leave version pins.
@@ -761,6 +762,7 @@ class Agent:
                     publish_startup_progress(
                         "environment_ready", "Device environment is ready", session_id=str(sess_id)
                     )
+                    execution_started = True
                     try:
                         if request.profile and request.profile.lower() == "flash":
                             logger.info(f"[{task_name}] Invoking FlashRunner reactive loop...")
@@ -972,7 +974,11 @@ class Agent:
                 from artemis.runtime.task_result import save_failure_result
 
                 if sess_id:
-                    save_failure_result(str(sess_id), err)
+                    save_failure_result(
+                        str(sess_id),
+                        err,
+                        code="execution_failed" if execution_started else "initialization_failed",
+                    )
                 if context.data_engine:
                     context.data_engine.end_session("failed")
 

artemis/services/llm.py

@@ -317,12 +317,32 @@ async def _wait_for_resume(pause_file: Path) -> bool:
     """Wait for the pause file to be cleared. Returns False on deadline."""
     deadline = float(getattr(settings, "LLM_PAUSE_TIMEOUT_SECONDS", 0.0) or 0.0)
     waited = 0.0
-    while pause_file.exists():
-        if deadline > 0 and waited >= deadline:
-            return False
-        await asyncio.sleep(1)
-        waited += 1
-    return True
+    try:
+        owned = pause_file.stat()
+    except FileNotFoundError:
+        return True
+    try:
+        while pause_file.exists():
+            if deadline > 0 and waited >= deadline:
+                return False
+            await asyncio.sleep(1)
+            waited += 1
+        return True
+    finally:
+        # Cancellation (stop, guidance, outer deadline) also ends this wait.
+        # Do not leave a global pause behind or remove a newer request's pause.
+        try:
+            current = pause_file.stat()
+            if (current.st_ino, current.st_mtime_ns, current.st_size) == (
+                owned.st_ino,
+                owned.st_mtime_ns,
+                owned.st_size,
+            ):
+                pause_file.unlink(missing_ok=True)
+        except FileNotFoundError:
+            pass
+        except OSError as exc:
+            llm_logger.warning("Could not clear finished LLM pause: %s", exc)
 
 
 async def _wait_for_breaker(key: str) -> None:
@@ -510,10 +530,6 @@ async def _run_with_recovery[T](
                 "LLM pause deadline"
                 f" ({settings.LLM_PAUSE_TIMEOUT_SECONDS:.0f}s) exceeded; giving up."
             )
-            try:
-                pause_file.unlink(missing_ok=True)
-            except OSError:
-                pass
             raise LLMExhaustedError(
                 str(last_error), failure=last_failure, cause=last_error
             ) from last_error