feat(homeassistant): a scheduled OS update reboots the machine and is done once the new version runs (#6755)
CI / lint (push) Successful in 1s
CI / unit (push) Successful in 1m37s
CI / integration (push) Failing after 2m0s
CI / publish (push) Skipped

Home Assistant writes an OS update and leaves the reboot to someone, so a scheduled
one never finished unattended. The schedule now asks for the reboot once, follows it
through Home Assistant going away, and counts it done when the Supervisor reports a
different version with nothing pending. A machine that doesn't come back or falls
back to the old version fails after 20 minutes, which ends the slot and raises
update_failed. Install on the page and through MCP still leave the reboot to the person.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-11-01 19:15:03 -05:00
co-authored by Claude Opus 5.5
parent 4c57735dd9
commit ecc59cc882
10 changed files with 262 additions and 41 deletions
+54 -7
View File
@@ -17,11 +17,13 @@ from .timeline import update_entry
logger = logging.getLogger(__name__)
UNDER_WAY = ("backing_up", "installing")
UNDER_WAY = ("backing_up", "installing", "rebooting")
BACKUP_DEADLINE_S = 30 * 60
REBOOT_DEADLINE_S = 20 * 60
# An OS update downloads and writes a whole system image, which is slow on a Pi. Home
# Assistant reports the new version as soon as that's written, before the reboot that
# makes it run, and raises a repair asking for that reboot.
# makes it run, and raises a repair asking for that reboot. The schedule's own OS
# updates make that reboot; one started by a person leaves it to them.
INSTALL_DEADLINE_S = {"addon": 20 * 60, "core": 30 * 60, "os": 45 * 60}
@@ -42,10 +44,11 @@ async def under_way(session) -> HomeAssistantUpdate | None:
HomeAssistantUpdate.state.in_(UNDER_WAY)))).scalars().first()
async def start_update(app, entity_id: str, username: str, transport=None) -> HomeAssistantUpdate:
async def start_update(app, entity_id: str, username: str, transport=None, *, reboot_after: bool = False) -> HomeAssistantUpdate:
"""Start installing `entity_id`, an explicit action that may contact Home
Assistant. Raises CannotStart, with nothing started, unless the update is
still waiting and the signed-in user may install it."""
still waiting and the signed-in user may install it. `reboot_after` reboots
the machine once it's written, and it's done when the new version is running."""
async with app.db_sessionmaker() as session:
connection = (await session.execute(select(HomeAssistantConnection))).scalars().first()
if connection is None:
@@ -79,7 +82,7 @@ async def start_update(app, entity_id: str, username: str, transport=None) -> Ho
entity_id=entity_id, title=known["title"], kind=known["kind"],
from_version=attrs.get("installed_version"), to_version=attrs.get("latest_version"),
started_by=username, backup_before=backup.get("state"),
backup_event_before=(event or {}).get("state"))
backup_event_before=(event or {}).get("state"), reboot_after=reboot_after)
async with app.db_sessionmaker() as session:
try:
async with session.begin():
@@ -117,7 +120,7 @@ async def _finish(app, run_id: str, state: str, message: str | None) -> None:
logger.exception("Home Assistant update %s: its timeline entry could not be written", run_id)
async def advance(app, transport=None) -> None:
async def advance(app, transport=None, connect=None) -> None:
"""Move the update under way one step on, if there is one."""
async with app.db_sessionmaker() as session:
run = await under_way(session)
@@ -130,8 +133,10 @@ async def advance(app, transport=None) -> None:
try:
if run.state == "backing_up":
await _advance_backup(app, run, connection, transport)
else:
elif run.state == "installing":
await _advance_install(app, run, connection, transport)
else:
await _advance_reboot(app, run, connection, transport, connect)
except client.Refused as exc:
await _mark_refused(app, connection.id, str(exc))
await _finish(app, run.id, "failed", str(exc))
@@ -158,6 +163,10 @@ async def _past_deadline(app, run) -> bool:
await _finish(app, run.id, "failed",
f"Still not on {run.to_version} after {limit // 60} minutes. Look in Home Assistant.")
return True
if run.state == "rebooting" and _elapsed(run.reboot_sent_at or run.install_sent_at or run.started_at) > REBOOT_DEADLINE_S:
await _finish(app, run.id, "failed", f"{run.to_version} was installed, but isn't running "
f"{REBOOT_DEADLINE_S // 60} minutes after the reboot. Look in Home Assistant.")
return True
return False
@@ -207,6 +216,44 @@ async def _advance_install(app, run, connection, transport) -> None:
installed = attrs.get("installed_version")
if installed and (installed == run.to_version
or (current.get("state") == "off" and installed != run.from_version)):
if run.reboot_after:
async with app.db_sessionmaker() as session:
async with session.begin():
row = await session.get(HomeAssistantUpdate, run.id)
row.state = "rebooting"
return
await _finish(app, run.id, "done", None)
return
await _past_deadline(app, run)
async def _mark_reboot_sent(app, run_id: str, at: datetime | None) -> None:
async with app.db_sessionmaker() as session:
async with session.begin():
row = await session.get(HomeAssistantUpdate, run_id)
row.reboot_sent_at = at
async def _advance_reboot(app, run, connection, transport, connect) -> None:
"""Reboot once, and wait for the new version to be what's running. The version
is judged against the old one, so a machine that fell back to it fails at the
deadline, as does one that never comes back."""
token = await client.access_token(connection, transport)
url, verify = connection.url, connection.verify_tls
if run.reboot_sent_at is None:
await _mark_reboot_sent(app, run.id, datetime.now(timezone.utc))
try:
await client.call_action(url, "hassio", "host_reboot", {}, token, verify, transport)
except client.Unreachable:
await _mark_reboot_sent(app, run.id, None)
await _past_deadline(app, run)
return
except client.Rejected as exc:
await _finish(app, run.id, "failed", f"{run.to_version} was installed, but Home Assistant "
f"wouldn't reboot: {exc} It needs a reboot to take effect.")
return
found = await client.read_os(url, token, verify, connect)
if found and found.get("version") not in (None, run.from_version) and not found.get("version_pending"):
await _finish(app, run.id, "done", None)
return
await _past_deadline(app, run)