Vito
3be0ada6a1
* fix(ingestion): link an image only to a prompt that provably produced it An LLM fed a PromptManagerPair's prepend_text while its text editor was empty. The node refused to save (an empty positive raised and logged a warning), and the image monitor then linked the image to a stale tracker entry or to the newest prompt in the database. - Nodes: an empty text editor saves and tracks nothing (prepend and append text are never the stored prompt), logs at info, and marks the node's run key empty so no earlier entry can be used for its images. - Tracker entries carry a run key: a digest of the prompt node and its whole upstream graph, the identity ComfyUI's cache uses. The monitor computes the same key from the image's embedded graph and uses a queued or snapshot entry only when the keys match (a snapshot also needs a known run with one entry, so a batch's last item is never applied to every image). - The recency fallback is gone; anything uncertain stays unlinked and is logged at info. - Recorded execution history attributes a file when exactly one run reported it, the file was written during that run, and the run's positive contexts name one stored prompt. The monitor and the output scan use it as their last certain source. - The scan and pair ingestion treat a resolved pair with an empty stored positive as unresolved instead of raising. - tools/review_image_links.py reviews selected links by these rules; dry run by default, --apply changes only named ids after a backup. Closes #342 * test(ingestion): real-host attribution case and the #342 testing contract The managed host disables the image monitor, so the owned fixture pack gains a route that starts and stops the plugin's monitor singleton for the attribution case only. The case runs in both renderers: a typed Pair image links, a Pair image whose positive is only linked prepend text stays unlinked with nothing stored, an unknown node feeding text links through its run key, and its cached re-run links again. * fix(ingestion): take a queued entry only from the run the image appeared in Dropping a key's older queue entries whenever the node ran again let a later queued run, executing during the monitor's processing delay, take the earlier image's entry. The snapshot taken when the image appears now names the key's latest run, and the queue is popped by key and run: same-key entries of earlier runs ahead of it are stale, entries of later runs wait for their own images. Also keeps the attribution case out of the stock real-host suite. * test(ingestion): host lookups degrade to no proof * fix(ingestion): address the #344 review (history re-check, keys, repair) - Images without an embedded API graph: the scan now asks recorded history before skipping a file with no prompt metadata, and the monitor gives a keyless unlinked image one history-only re-check when its run's outputs are recorded (a seal notification from the outputs write; at most 1000 waiting images, each for an hour). - Run keys: an image is unkeyable when any positive node has no key, so a two-pass graph is never linked through the other pass; links follow ComfyUI's is_link exactly. - A failed save marks the node's run key like an empty editor, so an older entry of that key can't stand in for this run. - A placeholder is the latest entry: the image stays unlinked without falling through to history, the same rule as a popped placeholder. - An index on execution_run_outputs(filename, subfolder, root_key, path_style) for the history lookup, added by migration and accepted by the output schema check (any other index is still refused). - Repair tool: unlink removes only the link record and only while the image is still linked to the prompt it was judged on; every run prints what --apply does. - Real-host case proves the re-run's PromptManager node was cached. * test(ingestion): real-host bare-output re-check and the review-round contract A metadata-disabled save, held open behind the fixture gate after SaveImage, waits unlinked while its run is open and links once the run's outputs are recorded. The fixture's monitor route lists the waiting files. TESTING.md covers the history re-check, the read index and what the repair tool's --apply does. * fix(ingestion): batch history lookups instead of adding an index An index on execution_run_outputs would make the library unopenable by older builds, whose schema check refuses any extra index there. The migration and the schema-check allowance are reverted, so the history schema is exactly main's. stored_run_prompts instead looks up a batch of files with one parameterized filename IN (...) query per chunk of at most 500 names and matches in memory; the scan computes it once per scan batch. * fix(ingestion): address the #344 re-review (seal race, linked roots) - A sealed history re-check that can't be scheduled yet (the image's own pass still pending, or the pending set full) is kept due and scheduled when a pending image finishes, instead of being dropped. - History matches a file through ComfyUI's spelling of its output folder first, then with both sides resolved, so a symlinked or junction output folder still attributes the scan's resolved paths; waiting files are keyed by their resolved path. - The scan makes its batch history lookup only when a file needs it. - set_current_prompt pushes to the queue last, so marking a failed execution never adds a second queue slot. - A keyless image outside the output folder doesn't take a waiting slot.
675 lines
27 KiB
Python
675 lines
27 KiB
Python
"""#342: recorded history attributes a file only to one certain, stored prompt."""
|
|
|
|
import json
|
|
import os
|
|
import sqlite3
|
|
import threading
|
|
import time
|
|
import unittest
|
|
from pathlib import Path
|
|
from unittest import mock
|
|
|
|
from database.run_attribution import stored_run_prompt
|
|
from tests import test_execution_history_database as history_tests
|
|
from tests.test_api_admin import AdminAPITestCase
|
|
from tests.test_execution_context_database import snapshot
|
|
from tests.test_prompt_attribution import issue_graph, llm_text_graph, make_tracker
|
|
from utils.execution_contexts import ContextBundle, RecipeContext
|
|
from utils.execution_outputs import (
|
|
OutputBundle,
|
|
OutputReference,
|
|
snapshot_output_roots,
|
|
)
|
|
from utils.hashing import generate_prompt_hash
|
|
from utils.image_monitor import ImageGenerationHandler
|
|
|
|
STYLE = "windows" if os.name == "nt" else "posix"
|
|
LLM_TEXT = "Photorealistic aerial landscape of misty mountains at dawn"
|
|
|
|
|
|
def now_ms():
|
|
return time.time_ns() // 1_000_000
|
|
|
|
|
|
class RecordedRuns:
|
|
"""Write runs into execution history the way the capture pipeline does."""
|
|
|
|
start = history_tests.HistoryDatabaseTests.start
|
|
finish = history_tests.HistoryDatabaseTests.finish
|
|
|
|
def record_run(self, db, output_root, files, positives, item=0, window=None):
|
|
started, finished = window or (now_ms() - 5000, now_ms() + 5000)
|
|
start = self.start(db, item, started)
|
|
db.write_execution_start(start)
|
|
finish = self.finish(start, time=finished)
|
|
db.write_execution_finish(finish)
|
|
db.write_execution_contexts(
|
|
start.run_id,
|
|
start.storage_epoch,
|
|
ContextBundle(
|
|
tuple(
|
|
RecipeContext(str(4 + i), snapshot(text), snapshot(""), "inferred")
|
|
for i, text in enumerate(positives)
|
|
),
|
|
"complete",
|
|
"captured",
|
|
),
|
|
)
|
|
root = snapshot_output_roots(STYLE, output_root, output_root).output_key
|
|
references = tuple(
|
|
OutputReference("9", i, "output", sub, name, STYLE, root)
|
|
for i, (sub, name) in enumerate(files)
|
|
)
|
|
db.write_execution_outputs_for_finish(
|
|
finish, OutputBundle(references, "complete", "reported")
|
|
)
|
|
return start.run_id
|
|
|
|
|
|
class TestStoredRunPrompt(RecordedRuns, unittest.TestCase):
|
|
setUp = history_tests.HistoryDatabaseTests.setUp
|
|
close_databases = history_tests.HistoryDatabaseTests.close_databases
|
|
database = history_tests.HistoryDatabaseTests.database
|
|
|
|
def setUp(self): # noqa: F811 - the shared temp dir and database list first
|
|
history_tests.HistoryDatabaseTests.setUp(self)
|
|
self.db = self.database()
|
|
self.output = str(Path(self.temp.name) / "output")
|
|
os.makedirs(os.path.join(self.output, "sub"))
|
|
self.image = os.path.join(self.output, "sub", "img_00001_.png")
|
|
Path(self.image).write_bytes(b"png")
|
|
|
|
def save(self, text):
|
|
return self.db.save_prompt(text=text, prompt_hash=generate_prompt_hash(text))
|
|
|
|
def attribute(self, path=None):
|
|
return stored_run_prompt(self.db, path or self.image, self.output)
|
|
|
|
def test_one_run_naming_one_stored_prompt_attributes_the_file(self):
|
|
prompt_id = self.save("an llm prompt")
|
|
self.record_run(
|
|
self.db, self.output, [("sub", "img_00001_.png")], ["an llm prompt"]
|
|
)
|
|
self.assertEqual(self.attribute(), prompt_id)
|
|
|
|
def test_text_that_is_not_stored_attributes_nothing(self):
|
|
"""The #342 run: raw editor text was empty, nothing was stored."""
|
|
self.save("a woman holding a coffee cup")
|
|
self.record_run(self.db, self.output, [("sub", "img_00001_.png")], [""])
|
|
self.assertIsNone(self.attribute())
|
|
|
|
def test_two_runs_reporting_the_same_file_attribute_nothing(self):
|
|
self.save("first")
|
|
self.save("second")
|
|
self.record_run(self.db, self.output, [("sub", "img_00001_.png")], ["first"])
|
|
self.record_run(
|
|
self.db, self.output, [("sub", "img_00001_.png")], ["second"], item=1
|
|
)
|
|
self.assertIsNone(self.attribute())
|
|
|
|
def test_a_file_written_outside_the_run_attributes_nothing(self):
|
|
self.save("an llm prompt")
|
|
self.record_run(
|
|
self.db,
|
|
self.output,
|
|
[("sub", "img_00001_.png")],
|
|
["an llm prompt"],
|
|
window=(1_000_000, 2_000_000),
|
|
)
|
|
self.assertIsNone(self.attribute())
|
|
|
|
def test_contexts_naming_different_prompts_attribute_nothing(self):
|
|
self.save("left")
|
|
self.save("right")
|
|
self.record_run(
|
|
self.db, self.output, [("sub", "img_00001_.png")], ["left", "right"]
|
|
)
|
|
self.assertIsNone(self.attribute())
|
|
|
|
def test_files_outside_the_output_root_or_unrecorded_attribute_nothing(self):
|
|
self.save("an llm prompt")
|
|
self.record_run(
|
|
self.db, self.output, [("sub", "img_00001_.png")], ["an llm prompt"]
|
|
)
|
|
outside = os.path.join(self.temp.name, "img_00001_.png")
|
|
Path(outside).write_bytes(b"png")
|
|
self.assertIsNone(self.attribute(outside))
|
|
other = os.path.join(self.output, "sub", "other.png")
|
|
Path(other).write_bytes(b"png")
|
|
self.assertIsNone(self.attribute(other))
|
|
self.assertIsNone(stored_run_prompt(self.db, self.image, None))
|
|
self.assertIsNone(stored_run_prompt(self.db, self.image, "relative/root"))
|
|
|
|
def test_a_library_without_history_tables_attributes_nothing(self):
|
|
broken = mock.Mock()
|
|
broken.model.get_connection.return_value.execute.side_effect = (
|
|
sqlite3.OperationalError("no such table")
|
|
)
|
|
self.assertIsNone(stored_run_prompt(broken, self.image, self.output))
|
|
|
|
def test_the_monitor_links_from_history_when_nothing_else_is_certain(self):
|
|
prompt_id = self.save(LLM_TEXT)
|
|
self.record_run(self.db, self.output, [("sub", "img_00001_.png")], [LLM_TEXT])
|
|
handler = ImageGenerationHandler(self.db, make_tracker(self.db))
|
|
linked = []
|
|
handler.link_image_to_prompt = lambda path, prompt, meta: linked.append(
|
|
prompt["id"]
|
|
)
|
|
with (
|
|
mock.patch(
|
|
"utils.image_monitor.host_output_directory", return_value=self.output
|
|
),
|
|
mock.patch.object(
|
|
handler.metadata_extractor,
|
|
"extract_metadata",
|
|
return_value={"prompt": llm_text_graph()},
|
|
),
|
|
):
|
|
handler.process_new_image(self.image)
|
|
self.assertEqual(linked, [prompt_id])
|
|
|
|
|
|
class TestScanUsesHistory(RecordedRuns, AdminAPITestCase):
|
|
"""The output scan applies the same rules as the monitor."""
|
|
|
|
def linked_prompt(self, path):
|
|
row = (
|
|
self.api.db.model.get_connection()
|
|
.execute(
|
|
"SELECT prompt_id FROM generated_images WHERE image_path=?",
|
|
(str(path),),
|
|
)
|
|
.fetchone()
|
|
)
|
|
return row[0] if row else None
|
|
|
|
def write(self, name):
|
|
path = self.output_dir / name
|
|
path.write_bytes(b"png")
|
|
return path
|
|
|
|
def test_an_llm_text_file_links_to_the_prompt_its_run_stored(self):
|
|
db = self.api.db
|
|
prompt_id = db.save_prompt(
|
|
text=LLM_TEXT, prompt_hash=generate_prompt_hash(LLM_TEXT)
|
|
)
|
|
path = self.write("llm_00001_.png")
|
|
self.record_run(db, str(self.output_dir), [("", path.name)], [LLM_TEXT])
|
|
meta = {"prompt": json.dumps(llm_text_graph())}
|
|
self.assertEqual(self.api._ingest_scanned_file(path, meta), "linked")
|
|
self.assertEqual(self.linked_prompt(path), prompt_id)
|
|
|
|
def test_a_metadata_less_file_links_through_its_recorded_run(self):
|
|
"""I1: --disable-metadata outputs carry no prompt; history still proves one."""
|
|
db = self.api.db
|
|
prompt_id = db.save_prompt(
|
|
text=LLM_TEXT, prompt_hash=generate_prompt_hash(LLM_TEXT)
|
|
)
|
|
path = self.write("bare_00001_.png")
|
|
self.record_run(db, str(self.output_dir), [("", path.name)], [LLM_TEXT])
|
|
self.assertEqual(self.api._ingest_scanned_file(path, {}), "linked")
|
|
self.assertEqual(self.linked_prompt(path), prompt_id)
|
|
self.assertEqual(self.api._ingest_scanned_file(path, None), "unchanged")
|
|
detailed = self.api._ingest_scanned_file(path, {}, detailed=True)
|
|
self.assertEqual(detailed["status"], "unchanged")
|
|
self.assertTrue(detailed["title"])
|
|
|
|
def test_a_metadata_less_file_without_a_recorded_run_is_still_skipped(self):
|
|
path = self.write("bare_00002_.png")
|
|
self.assertIsNone(self.api._ingest_scanned_file(path, {}))
|
|
self.assertIsNone(self.api._ingest_scanned_file(path, {"workflow": {}}))
|
|
self.assertIsNone(self.linked_prompt(path))
|
|
|
|
def test_the_issue_file_stays_unlinked_even_with_its_pair_record(self):
|
|
"""Resolved with an empty stored positive: before #342 the scan raised."""
|
|
db = self.api.db
|
|
db.save_prompt(
|
|
text="a woman holding a coffee cup",
|
|
prompt_hash=generate_prompt_hash("a woman holding a coffee cup"),
|
|
)
|
|
path = self.write("moss_00009_.png")
|
|
self.record_run(db, str(self.output_dir), [("", path.name)], [""])
|
|
evidence = {
|
|
"version": 1,
|
|
"nodes": {
|
|
"18:35": {
|
|
"records": [
|
|
{
|
|
"text": "",
|
|
"negative_text": "",
|
|
"positive_text": LLM_TEXT,
|
|
"negative_effective_text": "",
|
|
"prepend_text": LLM_TEXT,
|
|
"append_text": "",
|
|
}
|
|
]
|
|
}
|
|
},
|
|
}
|
|
meta = {
|
|
"prompt": json.dumps(issue_graph()),
|
|
"comfyassets_prompt_pairs": json.dumps(evidence),
|
|
}
|
|
self.assertEqual(self.api._ingest_scanned_file(path, meta), "unresolved")
|
|
self.assertIsNone(self.linked_prompt(path))
|
|
self.assertEqual(db.list_prompt_pairs()["pairs"], [])
|
|
|
|
|
|
class TestHostHelpers(unittest.TestCase):
|
|
"""The host lookups degrade to "no proof", never to an error."""
|
|
|
|
def test_host_output_directory(self):
|
|
import sys
|
|
import types
|
|
|
|
from database import run_attribution
|
|
|
|
cases = (
|
|
(types.SimpleNamespace(get_output_directory=lambda: "/out"), "/out"),
|
|
(types.SimpleNamespace(get_output_directory=lambda: ""), None),
|
|
(types.SimpleNamespace(get_output_directory=lambda: 1 / 0), None),
|
|
)
|
|
original = sys.modules.get("folder_paths")
|
|
try:
|
|
for module, expected in cases:
|
|
sys.modules["folder_paths"] = module
|
|
self.assertEqual(run_attribution.host_output_directory(), expected)
|
|
sys.modules["folder_paths"] = None # import fails: outside ComfyUI
|
|
self.assertIsNone(run_attribution.host_output_directory())
|
|
finally:
|
|
if original is None:
|
|
sys.modules.pop("folder_paths", None)
|
|
else:
|
|
sys.modules["folder_paths"] = original
|
|
|
|
def test_run_window_needs_integer_times_and_a_readable_file(self):
|
|
from database.run_attribution import _written_during
|
|
|
|
self.assertFalse(_written_during(__file__, None, 5))
|
|
self.assertFalse(_written_during(os.path.join("no", "such.png"), 0, 5))
|
|
|
|
def test_executing_run_id(self):
|
|
import sys
|
|
import types
|
|
|
|
from utils.run_keys import executing_run_id
|
|
|
|
def host(context):
|
|
def get_executing_context():
|
|
if isinstance(context, Exception):
|
|
raise context
|
|
return context
|
|
|
|
return types.SimpleNamespace(get_executing_context=get_executing_context)
|
|
|
|
original = sys.modules.get("comfy_execution.utils")
|
|
try:
|
|
for context, expected in (
|
|
(types.SimpleNamespace(prompt_id="run-1"), "run-1"),
|
|
(types.SimpleNamespace(prompt_id=""), None),
|
|
(None, None),
|
|
(RuntimeError("no context"), None),
|
|
):
|
|
sys.modules["comfy_execution.utils"] = host(context)
|
|
self.assertEqual(executing_run_id(), expected)
|
|
sys.modules["comfy_execution.utils"] = None
|
|
self.assertIsNone(executing_run_id())
|
|
finally:
|
|
if original is None:
|
|
sys.modules.pop("comfy_execution.utils", None)
|
|
else:
|
|
sys.modules["comfy_execution.utils"] = original
|
|
|
|
|
|
class TestMonitorHistoryRecheck(RecordedRuns, unittest.TestCase):
|
|
"""I1: a keyless image gets one history-only re-check when its run is sealed."""
|
|
|
|
def setUp(self):
|
|
history_tests.HistoryDatabaseTests.setUp(self)
|
|
self.db = history_tests.HistoryDatabaseTests.database(self)
|
|
self.output = str(Path(self.temp.name) / "output")
|
|
os.makedirs(self.output)
|
|
self.handler = ImageGenerationHandler(self.db, make_tracker(self.db))
|
|
self.handler.processing_delay = 0
|
|
self.handler.settle_interval = 0.01
|
|
self.addCleanup(self.handler.shutdown)
|
|
self.linked = []
|
|
self.handler.link_image_to_prompt = lambda path, prompt, meta: (
|
|
self.linked.append((os.path.basename(path), prompt["id"]))
|
|
)
|
|
patches = (
|
|
mock.patch(
|
|
"utils.image_monitor.host_output_directory", return_value=self.output
|
|
),
|
|
mock.patch.object(
|
|
self.handler.metadata_extractor, "extract_metadata", return_value=None
|
|
),
|
|
)
|
|
for patch in patches:
|
|
patch.start()
|
|
self.addCleanup(patch.stop)
|
|
|
|
close_databases = history_tests.HistoryDatabaseTests.close_databases
|
|
|
|
def image(self, name):
|
|
path = os.path.join(self.output, name)
|
|
Path(path).write_bytes(b"png")
|
|
return path
|
|
|
|
def save(self, text):
|
|
return self.db.save_prompt(text=text, prompt_hash=generate_prompt_hash(text))
|
|
|
|
def wait_for(self, predicate, timeout=5.0):
|
|
deadline = time.monotonic() + timeout
|
|
while time.monotonic() < deadline:
|
|
if predicate():
|
|
return True
|
|
time.sleep(0.01)
|
|
return predicate()
|
|
|
|
def test_the_run_ending_after_processing_links_the_image_once(self):
|
|
prompt_id = self.save(LLM_TEXT)
|
|
path = self.image("late_00001_.png")
|
|
self.handler.process_new_image(path) # the run is still executing
|
|
self.assertEqual(self.linked, [])
|
|
self.assertIn(
|
|
os.path.normcase(os.path.realpath(path)), self.handler.awaiting_history()
|
|
)
|
|
self.record_run(self.db, self.output, [("", "late_00001_.png")], [LLM_TEXT])
|
|
self.assertTrue(self.wait_for(lambda: self.linked))
|
|
self.assertTrue(self.wait_for(lambda: self.handler.pending_count() == 0))
|
|
self.assertEqual(self.linked, [("late_00001_.png", prompt_id)])
|
|
self.assertEqual(self.handler.awaiting_history(), [])
|
|
# Another run reporting the same name later is not a second re-check
|
|
self.record_run(
|
|
self.db, self.output, [("", "late_00001_.png")], [LLM_TEXT], item=1
|
|
)
|
|
self.assertTrue(self.wait_for(lambda: self.handler.pending_count() == 0))
|
|
self.assertEqual(len(self.linked), 1)
|
|
|
|
def test_a_seal_during_the_first_pass_is_not_lost(self):
|
|
"""R1: the run seals while the image's own pass is still pending."""
|
|
prompt_id = self.save(LLM_TEXT)
|
|
path = self.image("race_00001_.png")
|
|
real = self.handler._history_prompt
|
|
sealed = []
|
|
|
|
def history(image_path):
|
|
result = real(image_path) # before the run's outputs commit: None
|
|
if not sealed:
|
|
sealed.append(True)
|
|
# The writer commits and notifies now; the path is still pending
|
|
self.record_run(
|
|
self.db, self.output, [("", "race_00001_.png")], [LLM_TEXT]
|
|
)
|
|
return result
|
|
|
|
self.handler._history_prompt = history
|
|
self.assertTrue(self.handler.schedule(path))
|
|
self.assertTrue(self.wait_for(lambda: self.linked))
|
|
self.assertTrue(self.wait_for(lambda: self.handler.pending_count() == 0))
|
|
self.assertEqual(self.linked, [("race_00001_.png", prompt_id)])
|
|
|
|
def test_a_seal_while_the_pending_set_is_full_is_rechecked_later(self):
|
|
from utils import image_monitor
|
|
|
|
prompt_id = self.save(LLM_TEXT)
|
|
path = self.image("full_00001_.png")
|
|
self.handler.process_new_image(path) # waiting, unlinked
|
|
blocker = self.image("blocker.png")
|
|
release = threading.Event()
|
|
original = self.handler.process_new_image
|
|
|
|
def slow(image_path, prompt_snapshot=None):
|
|
if image_path == blocker:
|
|
release.wait(5)
|
|
return original(image_path, prompt_snapshot=prompt_snapshot)
|
|
|
|
self.handler.process_new_image = slow
|
|
with mock.patch.object(image_monitor, "MAX_PENDING_IMAGES", 1):
|
|
self.assertTrue(self.handler.schedule(blocker))
|
|
self.assertTrue(self.wait_for(lambda: self.handler.pending_count() == 1))
|
|
self.record_run(self.db, self.output, [("", "full_00001_.png")], [LLM_TEXT])
|
|
self.assertEqual(self.linked, [], "not scheduled while the set is full")
|
|
release.set()
|
|
self.assertTrue(self.wait_for(lambda: self.linked))
|
|
self.assertTrue(self.wait_for(lambda: self.handler.pending_count() == 0))
|
|
self.assertEqual(self.linked, [("full_00001_.png", prompt_id)])
|
|
|
|
def test_a_run_naming_nothing_stored_leaves_the_image_unlinked(self):
|
|
path = self.image("empty_00001_.png")
|
|
self.handler.process_new_image(path)
|
|
self.record_run(self.db, self.output, [("", "empty_00001_.png")], [""])
|
|
self.assertTrue(self.wait_for(lambda: not self.handler.awaiting_history()))
|
|
self.assertTrue(self.wait_for(lambda: self.handler.pending_count() == 0))
|
|
self.assertEqual(self.linked, [])
|
|
|
|
def test_history_found_at_once_leaves_nothing_awaiting(self):
|
|
prompt_id = self.save(LLM_TEXT)
|
|
self.record_run(self.db, self.output, [("", "done_00001_.png")], [LLM_TEXT])
|
|
self.handler.process_new_image(self.image("done_00001_.png"))
|
|
self.assertEqual(self.linked, [("done_00001_.png", prompt_id)])
|
|
self.assertEqual(self.handler.awaiting_history(), [])
|
|
|
|
def test_keyed_images_do_not_wait_for_history(self):
|
|
with mock.patch.object(
|
|
self.handler.metadata_extractor,
|
|
"extract_metadata",
|
|
return_value={"prompt": llm_text_graph()},
|
|
):
|
|
self.handler.process_new_image(self.image("keyed_00001_.png"))
|
|
self.assertEqual(self.handler.awaiting_history(), [])
|
|
|
|
def test_the_waiting_set_is_bounded_and_expires(self):
|
|
from utils import image_monitor
|
|
|
|
with mock.patch.object(image_monitor, "MAX_AWAITING_HISTORY", 2):
|
|
for n in range(3):
|
|
self.handler.process_new_image(self.image(f"b_{n}.png"))
|
|
self.assertEqual(
|
|
[os.path.basename(p) for p in self.handler.awaiting_history()],
|
|
["b_1.png", "b_2.png"],
|
|
)
|
|
later = time.monotonic() + image_monitor.AWAIT_HISTORY_SECONDS + 1
|
|
with mock.patch.object(image_monitor.time, "monotonic", return_value=later):
|
|
self.assertEqual(self.handler.awaiting_history(), [])
|
|
|
|
def test_shutdown_forgets_waiting_images_and_a_dead_handler_is_dropped(self):
|
|
import gc
|
|
|
|
from database import run_attribution
|
|
|
|
self.handler.process_new_image(self.image("gone_00001_.png"))
|
|
self.handler.shutdown()
|
|
self.assertEqual(self.handler.awaiting_history(), [])
|
|
other = ImageGenerationHandler(self.db, make_tracker(self.db))
|
|
with mock.patch.object(
|
|
other.metadata_extractor, "extract_metadata", return_value=None
|
|
):
|
|
other.process_new_image(self.image("gone_00002_.png"))
|
|
del other
|
|
gc.collect()
|
|
run_attribution.notify_outputs_sealed("run", []) # no dead callback raises
|
|
|
|
|
|
class TestBoundedLookup(RecordedRuns, unittest.TestCase):
|
|
"""M5: history lookups are batched, and the history schema is unchanged."""
|
|
|
|
setUp = history_tests.HistoryDatabaseTests.setUp
|
|
close_databases = history_tests.HistoryDatabaseTests.close_databases
|
|
database = history_tests.HistoryDatabaseTests.database
|
|
|
|
def output_lookups(self, db, action):
|
|
statements = []
|
|
conn = db.model.get_connection()
|
|
conn.set_trace_callback(statements.append)
|
|
try:
|
|
result = action()
|
|
finally:
|
|
conn.set_trace_callback(None)
|
|
return result, [s for s in statements if "FROM execution_run_outputs" in s]
|
|
|
|
def test_one_query_per_chunk_not_per_file_and_same_answers(self):
|
|
from database import run_attribution
|
|
|
|
db = self.database()
|
|
output = str(Path(self.temp.name) / "output")
|
|
os.makedirs(output)
|
|
prompt_id = db.save_prompt(
|
|
text=LLM_TEXT, prompt_hash=generate_prompt_hash(LLM_TEXT)
|
|
)
|
|
names = [f"img_{n:05}_.png" for n in range(25)]
|
|
paths = [os.path.join(output, name) for name in names]
|
|
for path in paths:
|
|
Path(path).write_bytes(b"png")
|
|
self.record_run(db, output, [("", n) for n in names[:10]], [LLM_TEXT])
|
|
self.record_run(db, output, [("", n) for n in names[5:10]], [""], item=1)
|
|
with mock.patch.object(run_attribution, "LOOKUP_CHUNK", 10):
|
|
result, lookups = self.output_lookups(
|
|
db, lambda: run_attribution.stored_run_prompts(db, paths, output)
|
|
)
|
|
self.assertEqual(len(lookups), 3) # 25 names in chunks of 10
|
|
expected = {path: None for path in paths}
|
|
expected.update({path: prompt_id for path in paths[:5]})
|
|
self.assertEqual(result, expected)
|
|
for path in paths[:12]:
|
|
self.assertEqual(
|
|
run_attribution.stored_run_prompt(db, path, output), expected[path]
|
|
)
|
|
|
|
def test_the_history_schema_gains_no_index(self):
|
|
from database.execution_history_schema import history_schema_error
|
|
|
|
db = self.database()
|
|
conn = db.model.get_connection()
|
|
indexes = [
|
|
row[1]
|
|
for row in conn.execute("PRAGMA index_list(execution_run_outputs)")
|
|
if row[3] != "pk"
|
|
]
|
|
self.assertEqual(indexes, [])
|
|
self.assertIsNone(history_schema_error(conn, allow_missing=False))
|
|
|
|
|
|
class TestScanBatchLookup(RecordedRuns, AdminAPITestCase):
|
|
"""M5: a scan batch asks history once per chunk of names, not per file."""
|
|
|
|
def test_a_batch_its_metadata_links_never_asks_history(self):
|
|
"""R3: the batch lookup is made only when a file needs it."""
|
|
files = []
|
|
for n in range(3):
|
|
path = self.output_dir / f"typed_{n:05}_.png"
|
|
path.write_bytes(b"png")
|
|
files.append(path)
|
|
meta = {"prompt": json.dumps(issue_graph(text="typed mountains"))}
|
|
statements = []
|
|
conn = self.api.db.model.get_connection()
|
|
conn.set_trace_callback(statements.append)
|
|
try:
|
|
counts = self.api._ingest_scan_batch_sync([(f, meta) for f in files])
|
|
finally:
|
|
conn.set_trace_callback(None)
|
|
self.assertEqual(counts["added"] + counts["linked"], 3, counts)
|
|
lookups = [s for s in statements if "FROM execution_run_outputs" in s]
|
|
self.assertEqual(lookups, [])
|
|
|
|
def test_metadata_less_batch_links_with_one_history_lookup(self):
|
|
db = self.api.db
|
|
prompt_id = db.save_prompt(
|
|
text=LLM_TEXT, prompt_hash=generate_prompt_hash(LLM_TEXT)
|
|
)
|
|
files = []
|
|
for n in range(6):
|
|
path = self.output_dir / f"bare_{n:05}_.png"
|
|
path.write_bytes(b"png")
|
|
files.append(path)
|
|
self.record_run(
|
|
db, str(self.output_dir), [("", f.name) for f in files[:4]], [LLM_TEXT]
|
|
)
|
|
statements = []
|
|
conn = db.model.get_connection()
|
|
conn.set_trace_callback(statements.append)
|
|
try:
|
|
counts = self.api._ingest_scan_batch_sync([(f, {}) for f in files])
|
|
finally:
|
|
conn.set_trace_callback(None)
|
|
lookups = [s for s in statements if "FROM execution_run_outputs" in s]
|
|
self.assertEqual(len(lookups), 1)
|
|
self.assertEqual(counts["linked"], 4)
|
|
linked = {
|
|
row[0]
|
|
for row in conn.execute(
|
|
"SELECT filename FROM generated_images WHERE prompt_id=?",
|
|
(prompt_id,),
|
|
)
|
|
}
|
|
self.assertEqual(linked, {f.name for f in files[:4]})
|
|
|
|
|
|
class TestLinkedOutputRoot(RecordedRuns, unittest.TestCase):
|
|
"""R2: ComfyUI's output folder reached through a symlink or junction."""
|
|
|
|
setUp = history_tests.HistoryDatabaseTests.setUp
|
|
close_databases = history_tests.HistoryDatabaseTests.close_databases
|
|
database = history_tests.HistoryDatabaseTests.database
|
|
|
|
def linked_root(self):
|
|
self.real = str(Path(self.temp.name) / "big_drive" / "output")
|
|
os.makedirs(os.path.join(self.real, "sub"))
|
|
link = str(Path(self.temp.name) / "output_link")
|
|
try:
|
|
os.symlink(self.real, link, target_is_directory=True)
|
|
except (OSError, NotImplementedError) as error:
|
|
self.skipTest(f"symlinks unavailable: {error}")
|
|
return link
|
|
|
|
def test_either_spelling_of_the_file_is_attributed(self):
|
|
db = self.database()
|
|
link = self.linked_root()
|
|
prompt_id = db.save_prompt(
|
|
text=LLM_TEXT, prompt_hash=generate_prompt_hash(LLM_TEXT)
|
|
)
|
|
real_file = os.path.join(self.real, "sub", "img_00001_.png")
|
|
Path(real_file).write_bytes(b"png")
|
|
# History keeps the host's spelling of its output folder (the link)
|
|
self.record_run(db, link, [("sub", "img_00001_.png")], [LLM_TEXT])
|
|
link_file = os.path.join(link, "sub", "img_00001_.png")
|
|
self.assertEqual(stored_run_prompt(db, real_file, link), prompt_id)
|
|
self.assertEqual(stored_run_prompt(db, link_file, link), prompt_id)
|
|
# The real folder named as the root is another root key: not attributed
|
|
self.assertIsNone(stored_run_prompt(db, real_file, self.real))
|
|
|
|
def test_the_monitor_rechecks_a_file_seen_through_the_real_path(self):
|
|
db = self.database()
|
|
link = self.linked_root()
|
|
prompt_id = db.save_prompt(
|
|
text=LLM_TEXT, prompt_hash=generate_prompt_hash(LLM_TEXT)
|
|
)
|
|
real_file = os.path.join(self.real, "late_00001_.png")
|
|
Path(real_file).write_bytes(b"png")
|
|
handler = ImageGenerationHandler(db, make_tracker(db))
|
|
handler.processing_delay = 0
|
|
handler.settle_interval = 0.01
|
|
self.addCleanup(handler.shutdown)
|
|
linked = []
|
|
handler.link_image_to_prompt = lambda path, prompt, meta: linked.append(
|
|
prompt["id"]
|
|
)
|
|
with (
|
|
mock.patch("utils.image_monitor.host_output_directory", return_value=link),
|
|
mock.patch.object(
|
|
handler.metadata_extractor, "extract_metadata", return_value=None
|
|
),
|
|
):
|
|
handler.process_new_image(real_file)
|
|
self.assertEqual(linked, [])
|
|
self.record_run(db, link, [("", "late_00001_.png")], [LLM_TEXT])
|
|
deadline = time.monotonic() + 5
|
|
while not linked and time.monotonic() < deadline:
|
|
time.sleep(0.01)
|
|
self.assertEqual(linked, [prompt_id])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|