Restore the skip-objects list after a restart mid-print

The object list lives in PrinterState and is filled by the print-start path,
which bambu_mqtt suppresses on the first RUNNING push after startup so a
running print is not archived twice (#1304). Everything else that moment
restores came back - the archive into _active_prints, the filament
attribution session, the timelapse baseline - and the object list did not.
So the card saw zero objects and greyed out its Skip button for the rest of
the print. Measured on the maintainer's H2C: 8 objects loaded at 09:02, a
restart at 09:17, Skip dead for the remaining hour.

Nothing could bring it back either. GET /print/objects rebuilds the list
whenever it is empty, but its only caller is the modal that the greyed-out
button opens.

on_print_running_observed now reloads the objects from the archive of the
print that is still running, anchored on subtask_id - the firmware mints one
per print, so a leftover status="printing" row from a completion that was
never seen cannot lend its objects to another job. Without an id nothing is
loaded rather than guessed; the endpoint's own reload covers that on demand.

That endpoint now reads the archived 3MF from disk before it asks the
printer. The archive of a running print normally holds the very file the
printer is executing, so the fan-out was fetching back 15 MB Bambuddy
already had, over the printer's single FTP socket, while it was printing -
and on a printer that kept the file on internal storage it cannot succeed at
all. FTP stays as the fallback. skipped_objects is left alone: a reload is
not a new print, and what the user has already skipped only lives there.

The plate image had the same fault one layer down. Opening the modal asks
for the cover, the top view and the object-ID mask, and the in-memory 3MF
cache those share dies with the process - so after a restart all three went
back to the printer at once: three fan-outs, thirteen seconds, and a 0-byte
read from socket contention, which is the storm #972 was about. The cover
flow takes the running print's archived file too, resolved in the caller's
short-lived session and passed in so _produce_cover_image still does no DB
work, and marked as a shared file so the cleanup cannot delete the archive.

Finally the card: a running print always has at least one object, so a count
of zero means "not loaded", not "nothing to skip". Exactly one object is the
real nothing-to-skip case and still disables the button.

---

Stop a test's printer client leaking into the next test

POST /api/v1/printers really connects, so a test that creates a printer
through the API leaves a live client in the printer_manager singleton. The
singleton outlives the per-test in-memory database, so the next test on that
xdist worker - whose own first printer is handed the same primary key - reads
that leftover client as its own live status.

test_scheduled_drying_routes was the visible victim: an "online" printer with
no firmware version fails the drying preflight, so scheduling came back 400
instead of 200. It only bites when --dist load happens to put victim and
leaker on one worker, which is why it passes on its own and flakes under -n.

Registrations made during a test are now undone after it, ids the test did not
add are left alone, and disconnect_printer is what also drops the model and
printer-info caches and stops the paho thread the leaked client was keeping
alive against an unreachable address for the rest of the run.
This commit is contained in:
maziggy
2026-08-18 13:43:46 +02:00
parent d227d42272
commit cfecfa360e
13 changed files with 686 additions and 30 deletions
@@ -4494,3 +4494,186 @@ class TestClearPlateOnAPoweredDownPrinter:
body = response.json()
assert body["connected"] is False
assert body["awaiting_plate_clear"] is True
class TestPrintableObjectsReload:
"""Rebuilding the object list must ask the disk before the printer.
The archive of a running print normally holds the very 3MF the printer is
executing. Pulling it back over FTPS costs a full transfer from a machine
that is mid-print — 15 MB on the print this was written for — and on a
printer that kept the file on internal storage it cannot succeed at all.
"""
@pytest.mark.asyncio
@pytest.mark.integration
async def test_the_archive_on_disk_is_used_before_any_ftp(
self, async_client: AsyncClient, printer_factory, archive_factory, db_session
):
printer = await printer_factory(name="H2C-1")
await archive_factory(printer.id, status="printing", subtask_id="330151809")
client = MagicMock()
client.state = MagicMock(
printable_objects={},
skipped_objects=[],
subtask_id="330151809",
subtask_name="HULA",
state="RUNNING",
gcode_file="/data/Metadata/plate_1.gcode",
printable_objects_bbox_all=None,
)
ftp = AsyncMock(return_value=None)
with (
patch("backend.app.api.routes.printers.printer_manager.get_client", return_value=client),
patch(
"backend.app.services.archive.extract_printable_objects_from_archive",
return_value=({101: {"name": "left"}, 102: {"name": "right"}}, None),
) as from_disk,
patch("backend.app.services.bambu_ftp.download_file_try_paths_async", new=ftp),
):
response = await async_client.get(f"/api/v1/printers/{printer.id}/print/objects")
assert response.status_code == 200, response.text
assert response.json()["total"] == 2
from_disk.assert_called_once()
ftp.assert_not_awaited()
@pytest.mark.asyncio
@pytest.mark.integration
async def test_a_reload_that_the_disk_cannot_answer_still_asks_the_printer(
self, async_client: AsyncClient, printer_factory, archive_factory, db_session
):
"""The fan-out is the fallback, not dead code: a print whose archive has
no 3MF (or none at all) still has the printer to ask."""
printer = await printer_factory(name="H2C-1")
await archive_factory(printer.id, status="printing", subtask_id="330151809")
client = MagicMock()
client.state = MagicMock(
printable_objects={},
skipped_objects=[],
subtask_id="330151809",
subtask_name="HULA",
state="RUNNING",
gcode_file="/data/Metadata/plate_1.gcode",
printable_objects_bbox_all=None,
)
ftp = AsyncMock(return_value=None)
with (
patch("backend.app.api.routes.printers.printer_manager.get_client", return_value=client),
patch(
"backend.app.services.archive.extract_printable_objects_from_archive",
return_value=({}, None),
),
patch("backend.app.services.bambu_ftp.download_file_try_paths_async", new=ftp),
):
response = await async_client.get(f"/api/v1/printers/{printer.id}/print/objects")
assert response.status_code == 200, response.text
ftp.assert_awaited()
class TestCoverUsesTheRunningPrintsArchive:
"""The cover must not re-fetch a 3MF Bambuddy already has on disk.
The in-memory download cache dies with the process, so after a restart
mid-print every cover, top view and skip-objects plate mask went back to the
printer for the whole file — measured on the maintainer's H2C as three
concurrent fan-outs, thirteen seconds and a 0-byte read, on a machine that
was busy printing. The archive of the running print holds that exact file.
"""
@pytest.mark.asyncio
@pytest.mark.integration
async def test_the_archived_3mf_is_preferred_over_ftp(
self, async_client: AsyncClient, printer_factory, archive_factory, db_session, tmp_path
):
import zipfile
from backend.app.core.config import settings as app_settings
printer = await printer_factory(name="H2C-1")
# A 3MF that is a real zip but carries no cover, so the endpoint reaches
# its "no cover in this file" answer without any FTP work.
threemf = tmp_path / "job.3mf"
with zipfile.ZipFile(threemf, "w") as zf:
zf.writestr("Metadata/slice_info.config", "<config/>")
await archive_factory(
printer.id,
status="printing",
subtask_id="330151809",
file_path=str(threemf.relative_to(tmp_path)),
)
state = MagicMock(
subtask_name="job",
subtask_id="330151809",
state="RUNNING",
gcode_file="/data/Metadata/plate_1.gcode",
current_project_url="ftp://job.3mf",
sdcard=True,
sdcard_reported=True,
)
ftp = AsyncMock(return_value=None)
with (
patch.object(app_settings, "base_dir", tmp_path),
patch("backend.app.api.routes.printers.printer_manager.get_status", return_value=state),
patch("backend.app.api.routes.printers.resolve_plate_id", return_value=1),
patch("backend.app.api.routes.printers.get_cached_3mf", return_value=None),
patch("backend.app.api.routes.printers.download_file_try_paths_async", new=ftp),
):
response = await async_client.get(f"/api/v1/printers/{printer.id}/cover")
# No cover inside this 3MF, so a 404 — but reached from the file on disk.
assert response.status_code == 404, response.text
ftp.assert_not_awaited()
@pytest.mark.asyncio
@pytest.mark.integration
async def test_the_archived_file_is_never_deleted_by_the_cover_flow(
self, async_client: AsyncClient, printer_factory, archive_factory, db_session, tmp_path
):
"""The cover flow unlinks the file it downloaded. Handed the archive's
own copy, that would delete the print's 3MF."""
import zipfile
from backend.app.core.config import settings as app_settings
printer = await printer_factory(name="H2C-1")
threemf = tmp_path / "job.3mf"
with zipfile.ZipFile(threemf, "w") as zf:
zf.writestr("Metadata/slice_info.config", "<config/>")
await archive_factory(
printer.id,
status="printing",
subtask_id="330151809",
file_path=str(threemf.relative_to(tmp_path)),
)
state = MagicMock(
subtask_name="job",
subtask_id="330151809",
state="RUNNING",
gcode_file="/data/Metadata/plate_1.gcode",
current_project_url="ftp://job.3mf",
sdcard=True,
sdcard_reported=True,
)
with (
patch.object(app_settings, "base_dir", tmp_path),
patch("backend.app.api.routes.printers.printer_manager.get_status", return_value=state),
patch("backend.app.api.routes.printers.resolve_plate_id", return_value=1),
patch("backend.app.api.routes.printers.get_cached_3mf", return_value=None),
patch(
"backend.app.api.routes.printers.download_file_try_paths_async",
new=AsyncMock(return_value=None),
),
):
await async_client.get(f"/api/v1/printers/{printer.id}/cover")
assert threemf.is_file(), "the cover flow deleted the running print's archived 3MF"