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

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