Files
ComfyAssets-ComfyUI_PromptM…/tests/test_job_admission.py
T
Vito d11b354ed6 fix(tagging): legacy pages tag each image, not its prompt (#379, PR 2) (#394)
* fix(tagging): Tag output images tags each image, not its prompt (#379, PR 1)

The native "Tag output images" job now runs the image-tags loop over every
still image the output folders list, linked or not: each image gets its own
model tags (at most "Suggestions per image") in its image tag set, and its
bytes are marked auto-tagged in a new media_image_autotags table. No prompt
tag or prompt text is written.

- database/autotag_schema.py: one forward-only WITHOUT ROWID table, optional
  in old backups, refused without the annotation group.
- add_image_tags/replace_image_tags take mark_autotagged; autotag_state and
  autotagged_locators read the marks through the one current-record rule.
- "Skip already tagged" skips images whose current bytes are marked, counted
  in a stat-only pre-pass; hand tags do not count.
- The review counts images and estimates the time (WD14 on CPU or CUDA).
- System > Auto-tagging review rows and copy, D134 and the Auto-tagging
  contract follow.

Part of #379

* fix(tagging): end the batch job after its cleanup and report pre-pass progress (#379)

The job read as ended while it still held the model gate, so a quick
restart could be refused with model-busy. Pre-pass chunks now publish
progress, and a cancel between chunks keeps exact counts.

Part of #379

* fix(tagging): measured GPU rate, and an ended image-tags job shows no time left (#379)

The live check measured WD14 on CUDA at 0.167 s per image (100 images in
16.7 s with the model load), so the review estimate uses 0.17 s. A finished
or cancelled Auto-tag/Add tags job kept "Processing file N of N · about X
min left"; it now ends with "<verb> <state> · N files processed".

Part of #379

* fix(tagging): legacy pages tag each image, not its prompt (#379, PR 2)

The admin and gallery batch starts the shared Tag output images job
("Tag output images (legacy page)") and relays its progress; closing the
window cancels it. Review asks per image with Skip first and applies by
image and sha256; apply refuses a prompt_id body. The Tag image dialog
marks an image auto-tagged only after Generate suggestions on that
capture. A second legacy batch (also one that wins the start race)
answers JSON 409, and both pages now show that sentence.

* test(tagging): gallery review units apply by image; record each progress change

The gallery review unit tests still pinned the removed prompt_id apply.
The legacy batch spec read the progress text once per observer callback,
so a phase frame and the first image frame landing in one task lost the
phase (WebKit); it now records every mutation record.
2026-10-27 22:40:57 +00:00

555 lines
22 KiB
Python

"""Registry admission classes and the legacy routes that hold the registry.
Record-changing work never runs together (Activity design): a ``records``
job is refused while any ``records`` or ``guarded`` job runs, a ``guarded``
job (thumbnails) while a ``records`` job runs, and ``read`` jobs only share
the one-per-kind rule. The legacy admin and gallery routes that change
records or files take a registry hold for their duration, so a workspace job
and a legacy-page operation refuse each other, naming the one that runs.
Fake runners and gated executor calls only; ordering is driven by events.
"""
import asyncio
import hashlib
import json
import os
import sys
import threading
import unittest
from pathlib import Path
from unittest.mock import MagicMock, patch
_mock_server = MagicMock()
_mock_server.PromptServer.instance.routes = MagicMock()
sys.modules.setdefault("server", _mock_server)
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from py.api.jobs import ( # noqa: E402
ADMISSIONS,
Job,
JobBusy,
JobRegistry,
)
try:
from tests.test_api_admin import AdminAPITestCase # noqa: E402
except ImportError: # discovered with tests/ as the top-level directory
from test_api_admin import AdminAPITestCase # noqa: E402
def _gated(gate):
async def runner(job):
await gate.wait()
return runner
async def _noop(job):
return None
class TestAdmissionClasses(unittest.IsolatedAsyncioTestCase):
def _start(self, registry, kind, admission, gate=None, **kwargs):
return registry.start(
kind,
kind.title(),
admission=admission,
scope={},
runner=_gated(gate) if gate is not None else _noop,
**kwargs,
)
async def test_admission_names_and_explicit_read(self):
self.assertEqual(ADMISSIONS, ("read", "guarded", "records", "exclusive"))
registry = JobRegistry()
job = registry.start(
"report", "Report", admission="read", scope={}, runner=_noop
)
await asyncio.wait_for(job.task, 2)
self.assertEqual(job.admission, "read")
self.assertFalse(job.record_changing)
with self.assertRaises(ValueError):
registry.start("x", "X", admission="bogus", scope={}, runner=_noop)
with self.assertRaises(ValueError):
registry.start(
"x",
"X",
admission="read",
record_changing=True,
scope={},
runner=_noop,
)
async def test_start_requires_an_admission_class(self):
# A job that forgets its class must not silently run as "read" beside
# a scan or restore: every start call decides.
registry = JobRegistry()
with self.assertRaises(TypeError) as raised:
registry.start("review", "Review", scope={}, runner=_noop)
self.assertIn("admission", str(raised.exception))
self.assertEqual(registry.list(), [])
job = registry.start(
"review", "Review", record_changing=False, scope={}, runner=_noop
)
await asyncio.wait_for(job.task, 2)
self.assertEqual(job.admission, "read")
async def test_record_changing_is_an_alias_for_records(self):
registry = JobRegistry()
gate = asyncio.Event()
job = registry.start(
"scan", "Scan", record_changing=True, scope={}, runner=_gated(gate)
)
self.assertEqual(job.admission, "records")
self.assertTrue(job.record_changing)
self.assertEqual(job.summary()["admission"], "records")
self.assertIs(
registry.blocker("image-tags", record_changing=True), job
) # the existing call shape keeps working
gate.set()
await asyncio.wait_for(job.task, 2)
async def test_records_job_refused_while_guarded_runs(self):
registry = JobRegistry()
gate = asyncio.Event()
thumbs = self._start(registry, "thumbnails", "guarded", gate)
with self.assertRaises(JobBusy) as raised:
self._start(registry, "scan", "records")
self.assertIs(raised.exception.running, thumbs)
self.assertIs(registry.blocker("restore", admission="records"), thumbs)
gate.set()
await asyncio.wait_for(thumbs.task, 2)
scan = self._start(registry, "scan", "records")
await asyncio.wait_for(scan.task, 2)
self.assertEqual(scan.state, "finished")
async def test_guarded_refused_while_records_runs(self):
registry = JobRegistry()
gate = asyncio.Event()
scan = self._start(registry, "scan", "records", gate)
with self.assertRaises(JobBusy) as raised:
self._start(registry, "thumbnails", "guarded")
self.assertIs(raised.exception.running, scan)
# A second guarded kind may run beside a guarded one, not beside records.
gate.set()
await asyncio.wait_for(scan.task, 2)
hold = asyncio.Event()
thumbs = self._start(registry, "thumbnails", "guarded", hold)
backup = self._start(registry, "backup", "guarded")
await asyncio.wait_for(backup.task, 2)
self.assertEqual(backup.state, "finished")
hold.set()
await asyncio.wait_for(thumbs.task, 2)
async def test_read_jobs_run_in_parallel(self):
registry = JobRegistry()
gate = asyncio.Event()
scan = self._start(registry, "scan", "records", gate)
health = self._start(registry, "health", "read", gate)
duplicates = self._start(registry, "duplicates", "read", gate)
self.assertTrue(all(j.running for j in (scan, health, duplicates)))
with self.assertRaises(JobBusy) as raised: # one job of a kind
self._start(registry, "health", "read")
self.assertIs(raised.exception.running, health)
gate.set()
await asyncio.wait_for(
asyncio.gather(scan.task, health.task, duplicates.task), 2
)
async def test_non_cancellable_job_ignores_cancel(self):
registry = JobRegistry()
gate = asyncio.Event()
job = self._start(registry, "restore", "records", gate, cancellable=False)
self.assertIs(job.summary()["cancellable"], False)
self.assertFalse(registry.cancel(job.id))
self.assertFalse(job.cancelled)
gate.set()
await asyncio.wait_for(job.task, 2)
self.assertEqual(job.state, "finished")
async def test_hold_registers_a_running_non_cancellable_job(self):
registry = JobRegistry()
held = registry.hold(
"restore", "Database restore (admin page)", admission="records"
)
async with held as job:
self.assertIs(registry.active("restore"), job)
self.assertEqual(job.state, "running")
self.assertEqual(
(job.summary()["cancellable"], job.summary()["admission"]),
(False, "records"),
)
self.assertFalse(registry.cancel(job.id))
with self.assertRaises(JobBusy) as raised:
self._start(registry, "scan", "records")
self.assertIn("Database restore (admin page)", str(raised.exception))
self.assertEqual(job.state, "finished")
self.assertIsNone(registry.active("restore"))
self.assertIs(registry.list()[0], job)
async def test_hold_refused_without_waiting(self):
registry = JobRegistry()
gate = asyncio.Event()
scan = self._start(registry, "scan", "records", gate)
with self.assertRaises(JobBusy) as raised:
async with registry.hold("maintenance", "Maintenance", admission="records"):
self.fail("a refused hold must not run its body")
self.assertIs(raised.exception.running, scan)
self.assertEqual([j.kind for j in registry.list()], ["scan"])
gate.set()
await asyncio.wait_for(scan.task, 2)
async def test_hold_released_on_exception(self):
registry = JobRegistry()
with self.assertRaises(RuntimeError):
async with registry.hold(
"maintenance", "Maintenance", admission="records"
) as job:
raise RuntimeError("boom")
self.assertEqual(job.state, "failed")
again = registry.hold("maintenance", "Maintenance", admission="records")
async with again as second:
second.finish("failed") # the body may end it itself
self.assertEqual(second.state, "failed")
async def test_hold_admits_on_entry_not_at_the_call(self):
# A hold created but never entered (an await or an exception between
# the call and ``async with``) must not leave a running records job
# behind that blocks all record work until a restart.
registry = JobRegistry()
held = registry.hold("restore", "Restore", admission="records")
self.assertEqual(registry.list(), [])
self.assertIsNone(registry.blocker("scan", admission="records"))
del held
async with registry.hold("restore", "Restore", admission="records") as job:
self.assertIs(registry.active("restore"), job)
self.assertEqual(job.state, "finished")
def test_job_defaults_stay_read_and_cancellable(self):
job = Job("duplicates", "Duplicate scan")
self.assertEqual((job.admission, job.cancellable), ("read", True))
class _LegacyHoldCase(AdminAPITestCase):
"""The admin test app plus a running workspace job on demand."""
def _run_job(self, kind="scan", title="Scan for metadata", admission="records"):
gate = asyncio.Event()
job = self.api._jobs.start(
kind, title, admission=admission, scope={}, runner=_gated(gate)
)
self.addAsyncCleanup(self._release, gate, job)
return gate, job
@staticmethod
async def _release(gate, job):
gate.set()
await asyncio.wait_for(job.task, 5)
def _db_digest(self):
path = Path(self.api.db.model.db_path)
return {
suffix: hashlib.sha256(Path(f"{path}{suffix}").read_bytes()).hexdigest()
for suffix in ("", "-wal")
if Path(f"{path}{suffix}").exists()
}
async def _busy(self, resp, title="Scan for metadata"):
body = await resp.json()
self.assertEqual(resp.status, 409)
self.assertEqual(body, {"success": False, "error": f"{title} already running"})
class TestLegacyRoutesHoldTheRegistry(_LegacyHoldCase):
async def test_hold_is_listed_as_running_job(self):
held = self.api._jobs.hold(
"restore", "Database restore (admin page)", admission="records"
)
async with held:
resp = await self.client.request("GET", "/prompt_manager/jobs")
jobs = (await resp.json())["jobs"]
self.assertEqual(len(jobs), 1)
job = jobs[0]
self.assertEqual(
(job["kind"], job["title"], job["state"]),
("restore", "Database restore (admin page)", "running"),
)
self.assertIs(job["cancellable"], False)
self.assertEqual(job["admission"], "records")
async def test_legacy_maintenance_and_cleanup_refused_while_scan_runs(self):
self.api.db.save_prompt(text="keep me", prompt_hash="h1")
before = self._db_digest()
self._run_job()
resp = await self.client.request(
"POST",
"/prompt_manager/maintenance",
json={"operations": ["cleanup_duplicates", "vacuum"]},
)
await self._busy(resp)
resp = await self.client.request("POST", "/prompt_manager/cleanup")
await self._busy(resp)
self.assertEqual(self._db_digest(), before)
async def test_read_only_maintenance_runs_during_scan(self):
# The legacy statistics and consistency checks only read: they hold
# the registry as "read", so a long scan does not block them.
self.api.db.save_prompt(text="keep me", prompt_hash="h1")
_gate, scan = self._run_job()
listed = []
real = self.api._run_maintenance_operations
def observed(operations):
listed.extend(
(job.kind, job.admission, job.state) for job in self.api._jobs.list()
)
return real(operations)
self.api._run_maintenance_operations = observed
resp = await self.client.request(
"POST",
"/prompt_manager/maintenance",
json={
"operations": [
"statistics",
"check_consistency",
"check_hash_duplicates",
]
},
)
body = await resp.json()
self.assertEqual(resp.status, 200)
self.assertIs(body["success"], True)
self.assertEqual(
set(body["results"]),
{"statistics", "check_consistency", "check_hash_duplicates"},
)
self.assertIn(("maintenance", "read", "running"), listed)
self.assertEqual(scan.state, "running")
maintenance = self.api._jobs.list()[-1]
self.assertEqual(
(maintenance.kind, maintenance.admission, maintenance.state),
("maintenance", "read", "finished"),
)
async def test_mixed_maintenance_selection_is_refused_during_scan(self):
# One write operation among read-only ones makes the run "records".
self.api.db.save_prompt(text="keep me", prompt_hash="h1")
before = self._db_digest()
self._run_job()
resp = await self.client.request(
"POST",
"/prompt_manager/maintenance",
json={"operations": ["statistics", "vacuum"]},
)
await self._busy(resp)
self.assertEqual(self._db_digest(), before)
async def test_default_maintenance_selection_is_refused_during_scan(self):
# No "operations" key means the default list, which vacuums.
self.api.db.save_prompt(text="keep me", prompt_hash="h1")
before = self._db_digest()
self._run_job()
resp = await self.client.request("POST", "/prompt_manager/maintenance", json={})
await self._busy(resp)
self.assertEqual(self._db_digest(), before)
self.assertEqual([j.kind for j in self.api._jobs.list()], ["scan"])
async def test_legacy_maintenance_refused_while_image_tags_runs(self):
self._run_job("image-tags", "Add tags to 3 images")
resp = await self.client.request("POST", "/prompt_manager/maintenance")
await self._busy(resp, "Add tags to 3 images")
async def test_scan_refused_while_legacy_maintenance_holds(self):
entered = threading.Event()
release = threading.Event()
real = self.api._run_maintenance_operations
def gated(operations):
entered.set()
release.wait(10)
return real(operations)
self.api._run_maintenance_operations = gated
loop = asyncio.get_running_loop()
maintenance = asyncio.ensure_future(
self.client.request(
"POST", "/prompt_manager/maintenance", json={"operations": ["vacuum"]}
)
)
self.assertTrue(await loop.run_in_executor(None, entered.wait, 10))
resp = await self.client.request("POST", "/prompt_manager/jobs/scan")
body = await resp.json()
self.assertEqual((resp.status, body["code"]), (409, "busy"))
self.assertEqual(body["running"]["title"], "Maintenance (admin page)")
release.set()
self.assertEqual((await maintenance).status, 200)
listed = (
await (await self.client.request("GET", "/prompt_manager/jobs")).json()
)["jobs"]
self.assertEqual(
[(j["kind"], j["state"]) for j in listed], [("maintenance", "finished")]
)
async def test_legacy_duplicate_delete_refused_while_scan_runs(self):
victim = self.output_dir / "dup.png"
victim.write_bytes(b"x")
self._run_job()
resp = await self.client.request(
"POST",
"/prompt_manager/delete_duplicate_images",
json={"image_paths": [str(victim)]},
)
await self._busy(resp)
self.assertTrue(victim.exists())
# The duplicate family lock was not taken by the refused request.
self.assertIsNotNone(self.api._acquire_long_job(self.api.LONG_JOB_DUPLICATES))
async def test_lora_scan_refused_while_scan_runs(self):
from py.config import IntegrationConfig
lm = Path(self.tmpdir) / "custom_nodes" / "ComfyUI-Lora-Manager"
(lm / "py").mkdir(parents=True)
self._run_job()
imported = []
with (
patch.multiple(
IntegrationConfig, LORA_MANAGER_ENABLED=True, LORA_MANAGER_PATH=str(lm)
),
patch("py.lora_utils.resolve_lora_manager_path", return_value=str(lm)),
patch.object(
self.api, "_lora_scan_stream", side_effect=lambda *a: imported.append(a)
),
):
resp = await self.client.request("POST", "/prompt_manager/lora/scan")
text = await resp.text()
self.assertEqual(resp.status, 200) # the legacy page reads a stream
events = [json.loads(line[6:]) for line in text.split("\n\n") if line]
# The admin page's modal shows ``status`` and closes on ``type: error``.
message = "Scan for metadata already running"
self.assertEqual(
events,
[{"type": "error", "status": message, "progress": 0, "message": message}],
)
self.assertEqual(imported, [])
async def test_legacy_autotag_refused_while_scan_runs(self):
# Both pages read this route as a stream (a 409 reads as a lost
# connection there), so a refusal by another job is one error frame:
# the admin page keys on ``type``, the gallery on ``status``.
self._run_job()
resp = await self.client.request(
"POST", "/prompt_manager/autotag/start", json={}
)
text = await resp.text()
self.assertEqual(resp.status, 200)
self.assertEqual(resp.headers["Content-Type"], "text/event-stream")
events = [json.loads(line[6:]) for line in text.split("\n\n") if line]
message = "Scan for metadata already running"
self.assertEqual(
events, [{"type": "error", "status": "error", "message": message}]
)
self.assertEqual(
[j.kind for j in self.api._jobs.list() if j.kind == "autotag"], []
)
async def test_second_legacy_autotag_batch_keeps_its_json_409(self):
from py.api.autotag_routes import _BUSY_ERROR
self._run_job("autotag", "Tag output images (legacy page)")
resp = await self.client.request(
"POST", "/prompt_manager/autotag/start", json={}
)
self.assertEqual(resp.status, 409)
self.assertEqual(await resp.json(), {"success": False, "error": _BUSY_ERROR})
async def test_legacy_payloads_unchanged_when_idle(self):
resp = await self.client.request(
"POST", "/prompt_manager/maintenance", json={"operations": ["vacuum"]}
)
body = await resp.json()
self.assertEqual(resp.status, 200)
self.assertEqual(
set(body),
{"success", "operations_completed", "all_successful", "results", "message"},
)
resp = await self.client.request("POST", "/prompt_manager/cleanup")
body = await resp.json()
self.assertEqual(resp.status, 200)
self.assertEqual(set(body), {"success", "message", "duplicates_removed"})
resp = await self.client.request(
"POST", "/prompt_manager/delete_duplicate_images", json={"image_paths": []}
)
self.assertEqual(
(resp.status, await resp.json()),
(400, {"success": False, "error": "No image paths provided"}),
)
# Each hold ended with the request; refused input never took one.
listed = await self._listed()
self.assertEqual(
[(j["kind"], j["state"]) for j in listed],
[("maintenance", "finished"), ("maintenance", "finished")],
)
self.assertEqual(
[j["title"] for j in listed],
["Prompt cleanup (admin page)", "Maintenance (admin page)"],
)
async def _listed(self):
resp = await self.client.request("GET", "/prompt_manager/jobs")
return (await resp.json())["jobs"]
class TestHeldJobStates(_LegacyHoldCase):
"""Activity lists what a held legacy operation really did (Minor 7)."""
async def _listed(self):
resp = await self.client.request("GET", "/prompt_manager/jobs")
return [(j["kind"], j["state"]) for j in (await resp.json())["jobs"]]
async def test_refused_input_takes_no_hold(self):
resp = await self.client.request(
"POST", "/prompt_manager/delete_duplicate_images", json={}
)
self.assertEqual(resp.status, 400)
resp = await self.client.request(
"POST",
"/prompt_manager/images/generate-thumbnails",
data=b"{not json",
headers={"Content-Type": "application/json"},
)
self.assertEqual(resp.status, 400)
self.assertEqual(await self._listed(), [])
async def test_thumbnail_stream_that_ends_in_error_is_failed(self):
with patch.object(self.api, "_get_all_output_dirs", return_value=[]):
resp = await self.client.request(
"POST", "/prompt_manager/images/generate-thumbnails/progress"
)
text = await resp.text()
self.assertEqual(resp.status, 200)
self.assertIn("event: error", text)
self.assertEqual(await self._listed(), [("thumbnails", "failed")])
async def test_legacy_autotag_refused_at_start_leaves_no_job(self):
# #379: the legacy batch is the autotag job; a model that is not
# downloaded refuses the start (one error frame) and registers nothing.
service = MagicMock()
service.get_models_status.return_value = {} # model not downloaded
with patch("py.autotag.get_autotag_service", return_value=service):
resp = await self.client.request(
"POST", "/prompt_manager/autotag/start", json={}
)
text = await resp.text()
self.assertEqual(resp.status, 200)
self.assertIn('"type": "error"', text)
self.assertEqual(await self._listed(), [])
if __name__ == "__main__":
unittest.main()