Vito Sansevero
144e6b1145
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
238 lines
8.9 KiB
Python
238 lines
8.9 KiB
Python
"""#342: recorded history attributes a file only to one certain, stored prompt."""
|
|
|
|
import json
|
|
import os
|
|
import sqlite3
|
|
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_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"], [])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|