fix(host_agent): disks behind a RAID controller each keep their own name (#5806)

smartctl reports every disk behind a PERC/MegaRAID controller as /dev/bus/0
with type megaraid,N; the helper named a drive by its path alone, so all of
VDNT-Docker02's and Docker03's disks read as one drive "0", each overwriting
the last. The slot is now part of the name (bus0-megaraid3), and Steward gives
a repeated name an ordinal so two drives never share a series. Agent 1.20.1.

fix(ansible): Steward stopping mid-run logs no traceback (#5749)

The run's done-callback called exception() on a cancelled task, which raises;
it now logs a run cut short by shutdown at INFO. A finished run's in-memory
state is dropped by a timer rather than a sleeping task, which shutdown found
still pending.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

steward/ansible/executor.py

@@ -182,14 +182,17 @@ def deregister_listener(run_id: str, q: asyncio.Queue) -> None:
         listeners.remove(q)
 
 
+def _drop_run_state(run_id: str) -> None:
+    _run_lines.pop(run_id, None)
+    _run_done.pop(run_id, None)
+
+
 def _schedule_cleanup(run_id: str) -> None:
-    """Drop a finished run's in-memory state after a grace window."""
-    async def _cleanup() -> None:
-        await asyncio.sleep(_MEM_TTL_SECS)
-        _run_lines.pop(run_id, None)
-        _run_done.pop(run_id, None)
+    """Drop a finished run's in-memory state after a grace window. A timer,
+    not a task (#5749): a run cut short by shutdown schedules this as the
+    loop closes, and a sleeping task would be destroyed while pending."""
     try:
-        asyncio.create_task(_cleanup())
+        asyncio.get_running_loop().call_later(_MEM_TTL_SECS, _drop_run_state, run_id)
     except RuntimeError:
         pass  # no running loop (e.g. tests) — fine to skip
 

steward/ansible/runner.py

@@ -109,9 +109,18 @@ async def trigger_run(
             connection=connection, secret_vars=secret_vars, redact=redact,
         )
     )
-    task.add_done_callback(
-        lambda t: t.exception() and app.logger.error(
-            "Ansible run %s raised: %s", run_id, t.exception()
-        )
-    )
+    task.add_done_callback(run_ended(app, run_id))
     return run, source, None
+
+
+def run_ended(app, run_id: str):
+    """A run task's done-callback: an error is logged as one. A run cut short
+    by Steward stopping is not an error (#5749): `exception()` would raise
+    CancelledError on it, and the next start marks the run interrupted."""
+    def callback(t: asyncio.Task) -> None:
+        if t.cancelled():
+            app.logger.info("Ansible run %s interrupted: Steward is stopping; "
+                            "it is marked interrupted at the next start", run_id)
+        elif t.exception() is not None:
+            app.logger.error("Ansible run %s raised: %s", run_id, t.exception())
+    return callback