Files
ComfyAssets-ComfyUI_PromptM…/tests/test_repair_foreign_links.py
T
Vito b5ca2eda94 feat(tools): reviewed repair of the foreign dataset links (#247, PR 3) (#468)
* feat(inspector): use recorded run history when the graph alone can't name the prompt (#386)

When a file's own graph leaves the prompt open, both inspect routes ask
recorded run history about the file (one run reported it and it was written
during that run). The save node that run reported it from anchors the walk
like a file-name match, so dataset branches that share one saver prefix
show their own prompt, labelled "Recorded run". Still open at one sampler
whose PromptManager text was recorded at execution (a language model's
output), the recorded text shows as "Execution recorded". Results the file
resolves alone never change; a failed lookup judges the file alone.

* fix(inspector): recorded texts follow history's saver; conflicts anchor nothing (#386)

Review follow-ups: the texts PromptManager recorded are looked up at the
sampler history's saver leads to, never at a sampler the unanchored walk
named; a file name naming a different saver than history anchors nothing;
outputs and texts are read in one transaction; "Recorded run" ranks below
every workflow-inferred source; unexpected lookup errors log at error level.

* fix(history): look up recorded runs by history's own spelling of the file (#386)

The history route inspects a case-normalized target on Windows, while
history matches file names exactly, so the occurrence's reference names
the file.

* refactor(inspector): share the inspector's resolve as inspection_resolution

inspect_prompt_evidence now calls inspection_resolution, which returns the
resolution to use, the anchored result and whether the recorded saver chose
it. Ingestion can call the same helper for files the default profile cannot
decide (#247).

* feat(ingestion): one per-file prompt decision for the scan and the monitor

utils/file_prompt.py holds decide_file_prompt, the ladder the output scan
runs today plus the inspector's rule (inspection profile, then the recorded
saver) before the legacy parser, with a SCAN and a MONITOR policy. Junk
text (blank, numbers, LoRA tags only, model file names) is never stored.
graph_prompt_text and parse_comfyui_prompt move here; the parser accepts
parsed metadata (#247).

* feat(ingestion): store a file's prompt in one transaction, one prompt per file

database/scanned_prompts.py links a file to the prompt of one text, creating
it when new, inside one BEGIN IMMEDIATE transaction: a file linked to
another prompt is a conflict, a failed link leaves no prompt behind and two
writers store one prompt. pair_ingestion gains file_link_rows,
link_conflict and Marks/mark_created; ingest_resolved_pair takes optional
marks for the components it creates. recorded_runs and named_prompt in
run_attribution become public (#247).

* feat(scan): decide each scanned file with the shared ladder (#247)

_ingest_scanned_file calls decide_file_prompt (scan policy) and stores the
result: pairs through ingest_resolved_pair and positives through
store_scanned_prompt, both with the scan marks. Files the default profile
leaves undecided now get the inspector's resolve, with the saver recorded
history names, before the legacy parser, so each branch of a shared-prefix
dataset run links its own prompt. Junk text is never stored, a file linked
to another prompt is a conflict instead of a second link, and a failed link
leaves no prompt behind. _BatchHistory reads the stored prompt and the
recorded saver from one recorded_runs pass. _parse_comfyui_prompt calls the
moved parse_comfyui_prompt. TESTING.md documents the decision.

* fix(ingestion): keep the file-name saver anchor out of the ladder (#390)

The #390 ruling queues a file that only its saver's file name resolves for
Needs review, never linking it. inspection_resolution gains name_anchor;
the ladder passes False, so such a file falls to the legacy floor in the
scan (and to Needs review) and is never stored by the monitor, while the
recorded saver still decides. The inspector keeps the name anchor.

* fix(ingestion): no joined PromptManager text from the legacy floor; junk keeps its step's status

The legacy parser returns prepend + text + append, so its answer is refused
when a PromptManager-family node has a prepend or append part (#343). Junk
found at the undecided-graph step keeps that step's unlinked status and
review, so an ambiguous file is still queued for Needs review. The monitor
policy's ambiguous file no longer asks for the recorded run, and the file
size may be read lazily.

* fix(ingestion): keep the legacy answer that is a PromptManager node's own text

The joined-text refusal also refused the #170 parity files whose
PromptManager prepend is a link the browser parser does not follow: its
answer is then the node's literal text, which is what the node stores.
Refuse only an answer that is not such a node's own text.

* fix(scan): one prompt per file for recorded-run links; writes survive a library move

The recorded run's stored prompt now links in one transaction with the file's
link rows, so a file linked to another prompt is a conflict instead of a
second link. The scan's stores run through survive_library_switch. A single
file asks history once (a one-file _BatchHistory), the scan passes
in_output=False and reads the file size only for files with prompt
metadata. A conflict row reads "Kept: already linked to a different
prompt". TESTING.md records the rules.

* feat(tools): reviewed repair of the foreign dataset links (#247)

tools/repair_foreign_links.py judges every link row of a file that only
foreign runs reported with the shared ladder (scan policy, recorded saver).
The dry run judges a copy, writes a JSON plan and a Markdown list, and
rehearses the apply on that copy to audit the prompts that would lose
every link (deleting them is off unless chosen). --apply refuses while
ComfyUI runs, takes a backup, re-judges every row inside one BEGIN
IMMEDIATE transaction, creates the targets with the scan's marks, relinks
and drops pair links, keeps UNIQUE(prompt_id, file_path), and rolls back
with exit 2 on any drift.

* fix(tools): the repair list keeps whole file paths and shows each target hash

* fix(tools): harden the #247 repair apply after review

- refuse while any other process holds the library, its -wal or -shm open
  (tools/comfyui_stopped.py), also in a rehearsal; without /proc only with
  --i-stopped-comfyui; require main.py in --comfyui-dir; check again just
  before BEGIN IMMEDIATE
- the plan records its library (normcase realpath) and max row id; apply
  refuses on another library
- refuse when opening the library changes its schema (run from a checkout
  at the live code version)
- verify the backup (integrity_check and counts) and never overwrite one
- target_text is a drift key and must match its hash; keep compares the
  linked text's hash, not the stored column
- the dry run rehearses the orphan deletes when --delete-orphans is chosen
- a .md plan path is refused; the list is <stem>.list.md
- any error during apply rolls back, names the backup, exits 2
- relpath on another drive falls back to the full path

* fix(ingestion): match a file's link rows under its resolved spelling too

The scan stores realpath spellings and the monitor the watcher's raw path,
so a file reached through a symlinked or junction output folder could get a
second generated_images row. file_link_rows now queries the path and its
realpath (each normalized and raw) and dedupes by row id. TESTING.md notes
the reverse order is matched only when the raw spelling is the realpath.

* fix(ingestion): a switched-off PromptManager node behind a pass-through stores nothing (#90)

The #90 graph walk follows only prompt-like inputs, so a PromptManagerText
with Save to library off reaching the encoder through another input name
(easy showAnything.anything, a custom node's value) was invisible to it,
and the inspector's resolve stored its text. The ladder now checks the
positive every step names: a resolved or inspected positive whose path
passes a node that is off, or a legacy answer that is such a node's own
text, makes the file not_saved.

* fix(ingestion): any switched-off node upstream of a positive stores nothing (#90)

The ladder walks every input upstream of each sampler or guider positive
(not negative, model, clip, latent or image inputs) for PromptManager nodes
whose Save to library is off or wired from an unreadable node, so the
sampler-less step, an off node with a prepend part and a PromptManagerPair
behind a pass-through no longer store its text. The legacy-floor guard reads
a node's resolved text. Every guard reports not_saved for a switch that is
off and not_saved_wired for one it cannot read.

* fix(ingestion): the switch walk skips negative inputs by #90's own rule

The upstream walk treated only names containing "negative" as negative, so
an off node on a neg, neg_text or text_neg input blocked an enabled
positive. prompt_graph gains is_negative_input (the _NEGATIVE_KEY rule, also
used by follows_input) and the walk uses it. The guards accept a node with
null inputs and a side whose provenance is not an object.

* fix(ingestion): the switch walk also skips any input named with "negative"

#90's rule matches only whole underscore-separated words, so negative2,
negativeprompt and NegativePrompt counted as positive inputs and an off
node wired only to one of them blocked the file. The walk skips those too;
follows_input is unchanged.

* test(tools): the #247 repair never relinks a switched-off node's text (#90)

The plan decides every file through decide_file_prompt, so a not_saved or
not_saved_wired file is a skip. Cover an off node behind a pass-through, an
off node in the recorded saver's branch (literal and wired switch), an off
node on another branch, and an off node wired only to the negative (still
repaired).
2026-10-29 12:00:36 +00:00

952 lines
36 KiB
Python

"""tools/repair_foreign_links.py: the reviewed repair of the #247 dataset links.
The fixture is a library whose foreign (no PromptManager node) dataset run
wrote shared-prefix files that the old scan linked to the wrong branch text.
Recorded history names each file's saver, so the ladder (``recorded-run``)
names the right branch.
"""
import contextlib
import hashlib
import io
import json
import os
import shutil
import sqlite3
import tempfile
import unittest
import unittest.mock
from pathlib import Path
from PIL import Image
from PIL.PngImagePlugin import PngInfo
try:
from tests.open_handles import assert_closed
except ImportError: # discovered with tests/ as the top-level directory
from open_handles import assert_closed
from database.models import PromptModel
from database.operations import PromptDatabase
from tests import saver_anchor_graphs as shapes
from tests.test_run_attribution import RecordedRuns
from tools import repair_foreign_links as tool
from utils.file_prompt import Decision
from utils.hashing import generate_prompt_hash
TEXTS = shapes.BRANCH_TEXTS
NAME = "IMG_GEN_{:05}_.png"
def png(path, graph):
info = PngInfo()
info.add_text("prompt", json.dumps(graph))
Image.new("RGB", (4, 4)).save(path, pnginfo=info)
def sha(text):
return hashlib.sha256(text.encode("utf-8")).hexdigest()
def file_sha(path):
return hashlib.sha256(Path(path).read_bytes()).hexdigest()
def dump(path):
"""The database's logical content (independent of WAL checkpoints)."""
conn = sqlite3.connect(path)
try:
return list(conn.iterdump())
finally:
conn.close()
def not_running(_comfyui_dir, _port):
return []
def no_handles(_database):
return []
class RepairFixture(RecordedRuns, unittest.TestCase):
"""Rows: A relink to a new prompt, B relink to a stored prompt (with a
pair link), C keep, D file gone, E two savers (skip), F the UNIQUE case
(a wrong row beside a correct row), H relink from a rated prompt, G a
PromptManager run (not a candidate)."""
def setUp(self):
self.tmp = tempfile.mkdtemp()
self.addCleanup(shutil.rmtree, self.tmp, True)
self.addCleanup(assert_closed, self, self.tmp)
self.addCleanup(PromptModel.reset_schema_cache)
self.output = os.path.join(self.tmp, "output")
os.makedirs(os.path.join(self.output, "dataset"))
self.db_path = os.path.join(self.tmp, "prompts.db")
self.plan_path = os.path.join(self.tmp, "plan.json")
self.backups = os.path.join(self.tmp, "backups")
os.makedirs(self.backups)
self.comfy = os.path.join(self.tmp, "comfy")
os.makedirs(self.comfy)
Path(self.comfy, "main.py").write_text("# ComfyUI\n", encoding="utf-8")
self.files = {}
for key, number in zip("ABCDEFHG", range(1, 9)):
path = os.path.join(self.output, "dataset", NAME.format(number))
png(path, shapes.shared_prefix())
self.files[key] = path
db = PromptDatabase(self.db_path)
try:
self.build(db)
finally:
db.close_all()
os.remove(self.files["D"])
def build(self, db):
save = lambda text, **kw: db.save_prompt( # noqa: E731
text=text, prompt_hash=generate_prompt_hash(text), **kw
)
self.p0 = save(TEXTS[0], category="scanned", tags=["auto-scanned"])
self.p2 = save(TEXTS[2], category="scanned", tags=["auto-scanned"])
self.orphan = save(
"an old guess",
category="scanned",
tags=["auto-scanned"],
notes="Auto-scanned from IMG_GEN_00001_.png",
)
self.rated = save("a rated guess", rating=5)
link = lambda prompt, key: db.link_image_to_prompt( # noqa: E731
prompt, self.files[key], metadata={}
)
self.rows = {
"A": link(self.orphan, "A"),
"B": link(self.p0, "B"),
"C": link(self.p0, "C"),
"D": link(self.p0, "D"),
"E": link(self.p0, "E"),
"F": link(self.p0, "F"),
"F_ok": link(self.p2, "F"),
"H": link(self.rated, "H"),
"G": link(self.p0, "G"),
}
conn = db.model.get_connection()
with conn:
pair = conn.execute(
"INSERT INTO prompt_pairs(positive_prompt_id) VALUES(?)", (self.p0,)
).lastrowid
conn.execute(
"INSERT INTO image_prompt_pairs(image_id, pair_id, provenance) "
"VALUES(?,?,'{}')",
(self.rows["B"], pair),
)
name = lambda key: ("dataset", os.path.basename(self.files[key])) # noqa
# Savers of the shared-prefix graph: "13", "23", "33", "43" (branches 1-4)
self.record_run(
db,
self.output,
[name(k) for k in "CDEAEBFH"],
[],
nodes=["13", "13", "13", "23", "23", "33", "33", "43"],
)
self.record_run(db, self.output, [name("G")], [TEXTS[0]], item=1, nodes=["23"])
def dry_run(self, *args):
out = io.StringIO()
code = tool.main(
[
self.db_path,
"--output-dir",
self.output,
"--plan",
self.plan_path,
*args,
],
out=out,
)
return code, out.getvalue()
def apply(self, *args, probe=not_running, handles=no_handles):
out = io.StringIO()
code = tool.main(
[
self.db_path,
"--apply",
self.plan_path,
"--comfyui-dir",
os.path.join(self.tmp, "comfy"),
"--backup-dir",
self.backups,
*args,
],
out=out,
probe=probe,
handles=handles,
)
return code, out.getvalue()
def plan(self):
with open(self.plan_path, encoding="utf-8") as stream:
return json.load(stream)
def write_plan(self, plan):
with open(self.plan_path, "w", encoding="utf-8") as stream:
json.dump(plan, stream)
def query(self, sql, args=()):
conn = sqlite3.connect(self.db_path)
try:
return conn.execute(sql, args).fetchall()
finally:
conn.close()
def query_write(self, sql, args):
conn = sqlite3.connect(self.db_path)
try:
with conn:
conn.execute(sql, args)
finally:
conn.close()
def links(self):
return dict(self.query("SELECT id, prompt_id FROM generated_images"))
class DryRunTests(RepairFixture):
def test_plan_names_relink_keep_and_skip_rows(self):
code, out = self.dry_run()
self.assertEqual(code, 0, out)
items = {item["row_id"]: item for item in self.plan()["rows"]}
rows = self.rows
self.assertNotIn(rows["G"], items, "a PromptManager run is not foreign")
actions = {key: items[rows[key]]["action"] for key in rows if key != "G"}
self.assertEqual(
actions,
{
"A": "relink",
"B": "relink",
"C": "keep",
"D": "skip",
"E": "skip",
"F": "relink",
"F_ok": "keep",
"H": "relink",
},
)
a = items[rows["A"]]
self.assertEqual(a["current_prompt_id"], self.orphan)
self.assertEqual(a["current_text_sha256"], sha("an old guess"))
self.assertEqual(a["target_text"], TEXTS[1])
self.assertEqual(a["target_hash"], generate_prompt_hash(TEXTS[1]))
self.assertEqual(a["target_prompt_id"], "new")
self.assertEqual(a["file"], self.files["A"])
self.assertEqual(items[rows["B"]]["target_prompt_id"], self.p2)
self.assertEqual(items[rows["H"]]["target_prompt_id"], "new")
self.assertEqual(items[rows["D"]]["reason"], "file gone")
self.assertEqual(
items[rows["E"]]["reason"], "not decided by the recorded saver"
)
self.assertIn("relink: 4", out)
self.assertIn("keep: 2", out)
self.assertIn("skip: 2", out)
def test_orphan_audit_lists_the_prompts_losing_every_link(self):
self.dry_run()
plan = self.plan()
orphans = {o["id"]: o for o in plan["orphans"]}
self.assertEqual(set(orphans), {self.orphan, self.rated})
self.assertEqual(orphans[self.orphan]["blockers"], [])
self.assertTrue(orphans[self.orphan]["safe"])
self.assertEqual(orphans[self.rated]["blockers"], ["usage or rating"])
self.assertFalse(orphans[self.rated]["safe"])
self.assertFalse(plan["delete_orphans"], "off by default")
self.dry_run("--delete-orphans")
self.assertTrue(self.plan()["delete_orphans"])
def test_dry_run_writes_nothing_and_writes_the_markdown_list(self):
before = file_sha(self.db_path)
listing = sorted(os.listdir(self.tmp))
code, out = self.dry_run()
self.assertEqual(code, 0)
self.assertEqual(file_sha(self.db_path), before)
self.assertIn("Dry run: nothing was changed.", out)
# A read-only reader of a WAL library may leave its empty side files
sidecars = {"prompts.db-shm", "prompts.db-wal"}
self.assertEqual(
sorted(set(os.listdir(self.tmp)) - sidecars),
sorted(set(listing + ["plan.json", "plan.list.md"]) - sidecars),
)
wal = Path(self.tmp, "prompts.db-wal")
self.assertEqual(wal.stat().st_size if wal.exists() else 0, 0)
markdown = Path(self.tmp, "plan.list.md").read_text(encoding="utf-8")
self.assertIn(f"| {self.rows['A']} |", markdown)
long_path = os.path.join("dataset", NAME.format(1))
self.assertIn(f"| {long_path} |", markdown, "file paths are never cut")
self.assertIn(generate_prompt_hash(TEXTS[1])[:12], markdown)
self.assertIn("new", markdown)
self.assertIn("would lose every link", markdown)
class DryRunReviewTests(RepairFixture):
def test_plan_records_its_library_and_fingerprint(self):
self.dry_run()
plan = self.plan()
self.assertEqual(
plan["source_db"], os.path.normcase(os.path.realpath(self.db_path))
)
self.assertEqual(plan["max_row_id"], max(self.links()))
def test_a_markdown_plan_path_is_refused(self):
out = io.StringIO()
with (
self.assertRaises(SystemExit),
contextlib.redirect_stderr(io.StringIO()),
):
tool.main(
[
self.db_path,
"--output-dir",
self.output,
"--plan",
os.path.join(self.tmp, "plan.md"),
],
out=out,
)
self.assertFalse(os.path.exists(os.path.join(self.tmp, "plan.md")))
def test_keep_compares_the_linked_text_not_the_stored_hash(self):
self.query_write("UPDATE prompts SET hash='stale' WHERE id=?", (self.p0,))
self.dry_run()
items = {item["row_id"]: item for item in self.plan()["rows"]}
self.assertEqual(items[self.rows["C"]]["action"], "keep")
def test_delete_orphans_is_rehearsed_with_the_deletes(self):
code, out = self.dry_run("--delete-orphans")
self.assertEqual(code, 0, out)
simulated = self.plan()["simulated"]
self.assertEqual(simulated["result"]["orphans_deleted"], 1)
self.assertEqual(
simulated["after"]["prompts"], simulated["before"]["prompts"] + 2 - 1
)
def test_a_file_on_another_drive_is_listed_by_its_full_path(self):
self.dry_run()
plan = self.plan()
with unittest.mock.patch.object(
tool.os.path, "relpath", side_effect=ValueError("other drive")
):
listing = tool.markdown(plan, {})
self.assertIn(self.files["A"], listing)
class ApplyTests(RepairFixture):
def setUp(self):
super().setUp()
code, out = self.dry_run()
self.assertEqual(code, 0, out)
def test_apply_relinks_creates_targets_and_drops_pair_links(self):
code, out = self.apply()
self.assertEqual(code, 0, out)
links = self.links()
new = dict(self.query("SELECT hash, id FROM prompts"))
target_a = new[generate_prompt_hash(TEXTS[1])]
target_h = new[generate_prompt_hash(TEXTS[3])]
self.assertEqual(links[self.rows["A"]], target_a)
self.assertEqual(links[self.rows["B"]], self.p2)
self.assertEqual(links[self.rows["H"]], target_h)
self.assertEqual(links[self.rows["C"]], self.p0, "keep")
self.assertEqual(links[self.rows["E"]], self.p0, "skip")
self.assertEqual(links[self.rows["G"]], self.p0, "not foreign")
self.assertEqual(
self.query(
"SELECT COUNT(*) FROM image_prompt_pairs WHERE image_id=?",
(self.rows["B"],),
),
[(0,)],
)
category, notes = self.query(
"SELECT category, notes FROM prompts WHERE id=?", (target_a,)
)[0]
self.assertEqual(category, "scanned")
self.assertEqual(
notes, f"Auto-scanned from {os.path.basename(self.files['A'])}"
)
tags = self.query(
"SELECT t.name FROM prompt_tags pt JOIN tags t ON t.id=pt.tag_id "
"WHERE pt.prompt_id=?",
(target_a,),
)
self.assertEqual(tags, [("auto-scanned",)])
self.assertIn("integrity_check", out)
self.assertIn("foreign_key_check", out)
self.assertRegex(out, r"integrity_check\s+ok\s+ok")
# Orphans are kept unless the plan chose to delete them
self.assertTrue(self.query("SELECT 1 FROM prompts WHERE id=?", (self.orphan,)))
def test_unique_case_deletes_the_wrong_row(self):
code, out = self.apply()
self.assertEqual(code, 0, out)
links = self.links()
self.assertNotIn(self.rows["F"], links)
self.assertEqual(links[self.rows["F_ok"]], self.p2)
rows = self.query(
"SELECT prompt_id FROM generated_images WHERE image_path=?",
(self.files["F"],),
)
self.assertEqual(rows, [(self.p2,)])
def test_backup_is_taken_before_writing(self):
before = self.links()
code, out = self.apply()
self.assertEqual(code, 0, out)
names = os.listdir(self.backups)
self.assertEqual(len(names), 1)
self.assertRegex(names[0], r"^prompts\.db\.pre-247-repair_\d{8}_\d{6}$")
backup = os.path.join(self.backups, names[0])
conn = sqlite3.connect(backup)
try:
saved = dict(conn.execute("SELECT id, prompt_id FROM generated_images"))
finally:
conn.close()
self.assertEqual(saved, before)
self.assertIn(f"Backup: {backup}", out)
def test_backup_beside_the_database_by_default(self):
out = io.StringIO()
code = tool.main(
[
self.db_path,
"--apply",
self.plan_path,
"--comfyui-dir",
os.path.join(self.tmp, "comfy"),
],
out=out,
probe=not_running,
handles=no_handles,
)
self.assertEqual(code, 0, out.getvalue())
self.assertTrue(
any(
n.startswith("prompts.db.pre-247-repair_") for n in os.listdir(self.tmp)
)
)
def test_refuses_while_comfyui_runs(self):
before = file_sha(self.db_path)
code, out = self.apply(probe=lambda _d, _p: ["process 42 (main.py)"])
self.assertEqual(code, 2)
self.assertIn("REFUSED", out)
self.assertIn("process 42", out)
self.assertEqual(os.listdir(self.backups), [], "no backup either")
self.assertEqual(file_sha(self.db_path), before)
def test_rehearsal_skips_the_running_check_on_a_copy_only(self):
code, out = self.apply("--rehearsal", probe=lambda _d, _p: ["port 8188"])
self.assertEqual(code, 0, out)
self.assertIn("rehearsal", out)
# The live library of that ComfyUI folder: --rehearsal is refused
live_dir = os.path.join(self.tmp, "comfy", "user", "__promptmanager")
os.makedirs(live_dir)
live = os.path.join(live_dir, "prompts.db")
shutil.copy(self.db_path, live)
out = io.StringIO()
code = tool.main(
[
live,
"--apply",
self.plan_path,
"--comfyui-dir",
os.path.join(self.tmp, "comfy"),
"--rehearsal",
],
out=out,
probe=lambda _d, _p: [],
handles=no_handles,
)
self.assertEqual(code, 2)
self.assertIn("--rehearsal", out.getvalue())
def test_drift_refuses_and_changes_nothing(self):
cases = {
"row moved": lambda: self.query_write(
"UPDATE generated_images SET prompt_id=? WHERE id=?",
(self.p2, self.rows["H"]),
),
"text changed": lambda: self.query_write(
"UPDATE prompts SET text='an older guess' WHERE id=?", (self.orphan,)
),
"file changed": lambda: png(self.files["B"], shapes.branch_bench()),
"target stored since": lambda: self.query_write(
"INSERT INTO prompts(text, hash) VALUES(?,?)",
(TEXTS[1], generate_prompt_hash(TEXTS[1])),
),
}
pristine = os.path.join(self.tmp, "pristine.db")
shutil.copy(self.db_path, pristine)
image = Path(self.files["B"]).read_bytes()
for name, drift in cases.items():
with self.subTest(name):
shutil.copy(pristine, self.db_path)
Path(self.files["B"]).write_bytes(image)
shutil.rmtree(self.backups)
os.makedirs(self.backups)
drift()
before = dump(self.db_path)
code, out = self.apply()
self.assertEqual(code, 2, out)
self.assertIn("REFUSED (rolled back, nothing changed)", out)
self.assertEqual(dump(self.db_path), before)
def test_late_failure_rolls_back_every_write(self):
plan = self.plan()
plan["delete_orphans"] = True
self.write_plan(plan)
# The safe orphan gained a user tag after the dry run
self.query_write("INSERT INTO tags(name) VALUES('mine')", ())
self.query_write(
"INSERT INTO prompt_tags(prompt_id, tag_id) "
"SELECT ?, id FROM tags WHERE name='mine'",
(self.orphan,),
)
before = self.links()
prompts = self.query("SELECT COUNT(*) FROM prompts")
code, out = self.apply()
self.assertEqual(code, 2, out)
self.assertIn(f"prompt {self.orphan}", out)
self.assertIn("user tags", out)
self.assertEqual(self.links(), before, "the relinks were rolled back")
self.assertEqual(self.query("SELECT COUNT(*) FROM prompts"), prompts)
def test_orphans_are_deleted_only_when_chosen_and_unreferenced(self):
plan = self.plan()
plan["delete_orphans"] = True
self.write_plan(plan)
code, out = self.apply()
self.assertEqual(code, 0, out)
self.assertFalse(self.query("SELECT 1 FROM prompts WHERE id=?", (self.orphan,)))
self.assertTrue(
self.query("SELECT 1 FROM prompts WHERE id=?", (self.rated,)),
"a prompt with a rating is never deleted",
)
self.assertIn("orphans_deleted", out)
def test_an_applied_plan_refuses_a_second_time(self):
self.assertEqual(self.apply()[0], 0)
before = dump(self.db_path)
code, out = self.apply()
self.assertEqual(code, 2)
self.assertIn("REFUSED", out)
self.assertEqual(dump(self.db_path), before)
class ApplySafetyTests(RepairFixture):
def setUp(self):
super().setUp()
code, out = self.dry_run()
self.assertEqual(code, 0, out)
def assert_unchanged(self, before, code, out):
self.assertEqual(code, 2, out)
self.assertEqual(dump(self.db_path), before)
def test_refuses_when_another_process_has_the_library_open(self):
before = dump(self.db_path)
held = lambda _db: ["process 7 has prompts.db-wal open"] # noqa: E731
for args in ((), ("--rehearsal",)):
with self.subTest(args):
code, out = self.apply(*args, handles=held)
self.assert_unchanged(before, code, out)
self.assertIn("process 7", out)
self.assertEqual(os.listdir(self.backups), [])
def test_the_running_check_runs_again_just_before_writing(self):
calls = []
def late(_d, _p):
calls.append(1)
return [] if len(calls) == 1 else ["something listens on port 8188"]
before = dump(self.db_path)
code, out = self.apply(probe=late)
self.assert_unchanged(before, code, out)
self.assertEqual(len(calls), 2)
self.assertIn("rolled back", out)
self.assertIn("Backup:", out)
def test_without_proc_only_an_explicit_stop_lets_it_through(self):
blind = lambda _db: [tool.NO_PROC] # noqa: E731
before = dump(self.db_path)
code, out = self.apply(handles=blind)
self.assert_unchanged(before, code, out)
self.assertIn("--i-stopped-comfyui", out)
code, out = self.apply("--i-stopped-comfyui", handles=blind)
self.assertEqual(code, 0, out)
def test_a_folder_without_main_py_is_refused(self):
os.remove(os.path.join(self.comfy, "main.py"))
before = dump(self.db_path)
code, out = self.apply()
self.assert_unchanged(before, code, out)
self.assertIn("main.py", out)
def test_a_plan_for_another_library_is_refused(self):
other = os.path.join(self.tmp, "other.db")
shutil.copy(self.db_path, other)
out = io.StringIO()
code = tool.main(
[other, "--apply", self.plan_path, "--comfyui-dir", self.comfy],
out=out,
probe=not_running,
handles=no_handles,
)
self.assertEqual(code, 2)
self.assertIn("made for", out.getvalue())
def test_opening_the_library_must_not_change_its_schema(self):
self.query_write("DROP INDEX idx_prompt_pairs_positive_only", ())
PromptModel.reset_schema_cache()
code, out = self.apply()
self.assertEqual(code, 2, out)
self.assertIn("schema", out)
self.assertIn("live code version", out)
def test_an_existing_backup_file_is_refused(self):
stamp = "20261028_000000"
Path(self.backups, f"prompts.db.pre-247-repair_{stamp}").write_bytes(b"x")
before = dump(self.db_path)
with unittest.mock.patch.object(tool, "_stamp", return_value=stamp):
code, out = self.apply()
self.assert_unchanged(before, code, out)
self.assertIn("already exists", out)
def test_a_backup_that_does_not_match_is_refused(self):
real = tool.backup_database
def short(source, target):
real(source, target)
conn = sqlite3.connect(target)
try:
with conn:
conn.execute("DELETE FROM image_prompt_pairs")
finally:
conn.close()
before = dump(self.db_path)
with unittest.mock.patch.object(tool, "backup_database", short):
code, out = self.apply()
self.assert_unchanged(before, code, out)
self.assertIn("backup", out)
def test_a_changed_target_text_is_refused(self):
plan = self.plan()
for item in plan["rows"]:
if item["row_id"] == self.rows["A"]:
item["target_text"] = "something else"
self.write_plan(plan)
before = dump(self.db_path)
code, out = self.apply()
self.assert_unchanged(before, code, out)
self.assertIn("target_text", out)
def test_an_orphan_gone_or_changed_at_apply_is_refused(self):
plan = self.plan()
plan["delete_orphans"] = True
plan["orphans"][0]["text_sha256"] = "0" * 64
self.write_plan(plan)
before = dump(self.db_path)
code, out = self.apply()
self.assert_unchanged(before, code, out)
self.assertIn("gone or text changed", out)
def test_any_error_rolls_back_and_names_the_backup(self):
before = dump(self.db_path)
with unittest.mock.patch.object(
tool, "_relink", side_effect=RuntimeError("disk on fire")
):
code, out = self.apply()
self.assert_unchanged(before, code, out)
self.assertIn("rolled back", out)
self.assertIn("disk on fire", out)
self.assertIn(self.backups, out)
def test_a_failed_integrity_check_after_writing_exits_1(self):
real = tool.counts
seen = []
def counts(path, readonly=True):
found = real(path, readonly)
if path == self.db_path:
seen.append(path)
if len(seen) > 1:
return {**found, "integrity_check": "corrupt"}
return found
with unittest.mock.patch.object(tool, "counts", counts):
code, out = self.apply()
self.assertEqual(code, 1, out)
self.assertIn("restore", out)
class BlockerTests(RepairFixture):
"""Each reference that keeps a prompt from being deleted."""
def test_every_blocker(self):
pid = self.orphan
cases = {
"linked images": None,
"saved pairs": "INSERT INTO prompt_pairs(positive_prompt_id) VALUES(:id)",
"recorded runs": "UPDATE execution_run_contexts "
"SET positive_prompt_id=:id",
"library state": "INSERT INTO prompt_library_state(prompt_id) "
"VALUES(:id)",
"user tags": "INSERT INTO prompt_tags(prompt_id, tag_id) "
"SELECT :id, id FROM tags WHERE name='mine'",
"usage or rating": "UPDATE prompts SET run_count=3 WHERE id=:id",
"category": "UPDATE prompts SET category='portraits' WHERE id=:id",
"notes": "UPDATE prompts SET notes='mine' WHERE id=:id",
}
conn = sqlite3.connect(self.db_path)
try:
conn.execute("INSERT INTO tags(name) VALUES('mine')")
conn.commit()
for name, sql in cases.items():
with self.subTest(name):
conn.execute("SAVEPOINT blocker")
if sql is None:
unused = {pid}
else:
conn.execute(
"DELETE FROM generated_images WHERE prompt_id=?", (pid,)
)
conn.execute(sql, {"id": pid})
unused = {pid}
found = tool.blockers(conn, pid, unused)
self.assertTrue(any(item.startswith(name) for item in found), found)
conn.execute("ROLLBACK TO blocker")
conn.execute("RELEASE blocker")
conn.execute("DELETE FROM generated_images WHERE prompt_id=?", (pid,))
self.assertEqual(tool.blockers(conn, pid, {pid}), [])
self.assertEqual(
tool.blockers(conn, pid, set()), ["not unused by the app's rule"]
)
conn.rollback()
finally:
conn.close()
def _off_text_node(text, save=False):
return {
"class_type": "PromptManagerText",
"inputs": {"text": text, "save_to_library": save},
}
def _encode_from(source):
return {
"class_type": "CLIPTextEncode",
"inputs": {"text": source, "clip": ["1", 1]},
}
def off_behind_pass_through(branch=2):
"""The dataset graph with ``branch``'s text coming from a switched-off
PromptManagerText through a pass-through the #90 walk does not follow."""
graph = shapes.shared_prefix()
graph["50"] = _off_text_node(TEXTS[branch - 1])
graph["51"] = {"class_type": "MyNode", "inputs": {"value": ["50", 0]}}
graph[str(branch * 10)] = _encode_from(["51", 0])
return graph
def off_target(branch=2, save=False):
"""``branch``'s text straight from a PromptManagerText whose switch is
``save`` (False, or a link to a node the graph cannot read)."""
graph = shapes.shared_prefix()
graph["50"] = _off_text_node(TEXTS[branch - 1], save)
graph[str(branch * 10)] = _encode_from(["50", 0])
if isinstance(save, list):
graph["52"] = {"class_type": "SomeBoolNode", "inputs": {}}
return graph
def off_negative_only():
"""Every branch's negative from a switched-off PromptManagerText."""
graph = shapes.shared_prefix()
graph["50"] = _off_text_node(shapes.NEGATIVE)
graph["3"] = _encode_from(["50", 0])
return graph
class SaveToLibraryTests(RecordedRuns, unittest.TestCase):
"""#90: the repair never relinks a file to a switched-off node's text.
The plan decides each file through ``decide_file_prompt``; every answer
but a positive from the recorded saver or the inspector is a skip, so a
``not_saved`` or ``not_saved_wired`` file is never written. Each file is
reported by a run without contexts (as a cached or unrecorded run is),
so only the ladder can stop it. Saver "23" is branch 2.
"""
def setUp(self):
self.tmp = tempfile.mkdtemp()
self.addCleanup(shutil.rmtree, self.tmp, True)
self.addCleanup(assert_closed, self, self.tmp)
self.addCleanup(PromptModel.reset_schema_cache)
self.output = os.path.join(self.tmp, "output")
os.makedirs(os.path.join(self.output, "dataset"))
self.db_path = os.path.join(self.tmp, "prompts.db")
def plan_for(self, graph):
path = os.path.join(self.output, "dataset", NAME.format(1))
png(path, graph)
db = PromptDatabase(self.db_path)
try:
wrong = db.save_prompt(
text=TEXTS[0], prompt_hash=generate_prompt_hash(TEXTS[0])
)
db.link_image_to_prompt(wrong, path, metadata={})
self.record_run(
db, self.output, [("dataset", NAME.format(1))], [], nodes=["23"]
)
plan = tool.build_plan(db, self.output, self.db_path)
finally:
db.close_all()
(item,) = plan["rows"]
return item
def test_an_off_node_behind_a_pass_through_is_skipped(self):
item = self.plan_for(off_behind_pass_through())
self.assertEqual(item["action"], "skip")
self.assertEqual(item["decision"], "not_saved/none")
self.assertNotIn("target_text", item)
def test_an_off_node_in_the_recorded_run_target_is_skipped(self):
cases = {
"off": (False, "not_saved/none"),
"wired": (["52", 0], "not_saved_wired/none"),
}
for name, (save, decision) in cases.items():
with self.subTest(name):
if os.path.exists(self.db_path):
os.remove(self.db_path)
item = self.plan_for(off_target(save=save))
self.assertEqual(item["action"], "skip")
self.assertEqual(item["decision"], decision)
def test_an_off_node_on_another_branch_still_skips_the_file(self):
"""The ladder judges the file's whole graph: any switched-off text
upstream of a positive makes the file not saved."""
item = self.plan_for(off_target(branch=3))
self.assertEqual(item["action"], "skip")
self.assertEqual(item["decision"], "not_saved/none")
def test_an_off_node_wired_only_to_the_negative_still_repairs(self):
item = self.plan_for(off_negative_only())
self.assertEqual(item["action"], "relink")
self.assertEqual(item["source"], "recorded-run")
self.assertEqual(item["target_text"], TEXTS[1])
def test_a_switched_on_node_in_the_target_still_repairs(self):
"""Regression guard: a switch that is on is no reason to skip."""
item = self.plan_for(off_target(save=True))
self.assertEqual(item["action"], "relink")
self.assertEqual(item["target_text"], TEXTS[1])
class ActionTests(unittest.TestCase):
"""Only the recorded saver relinks; a certain step naming the linked
prompt keeps it; the legacy floor and the rest are skipped."""
def test_action_by_decision(self):
linked = generate_prompt_hash("linked")
cases = [
(Decision("positive", "other", source="recorded-run"), "relink"),
(Decision("positive", "linked", source="recorded-run"), "keep"),
(Decision("positive", "linked", source="inspector"), "keep"),
(Decision("positive", "other", source="inspector"), "skip"),
(Decision("positive", "linked", source="legacy-parser"), "skip"),
(Decision("pair", "linked", source="resolver"), "skip"),
(Decision("never"), "skip"),
(Decision("not_saved"), "skip"),
(Decision("not_saved_wired"), "skip"),
(Decision("positive", "other", source="opted-out-negative"), "skip"),
]
for decision, action in cases:
with self.subTest(decision.source, text=decision.text):
self.assertEqual(tool.action_of(decision, linked), action)
class CommandLineTests(unittest.TestCase):
def test_running_probe_reports_a_listening_port(self):
import socket
with socket.socket() as server:
server.bind(("127.0.0.1", 0))
server.listen(1)
port = server.getsockname()[1]
found = tool.comfyui_running("/nonexistent/comfy", port)
self.assertTrue(any(str(port) in item for item in found))
def test_running_probe_is_quiet_when_nothing_runs(self):
import socket
with socket.socket() as probe:
probe.bind(("127.0.0.1", 0))
port = probe.getsockname()[1]
self.assertEqual(tool.comfyui_running("/nonexistent/comfy", port), [])
def fake_proc(self, tmp):
proc = Path(tmp, "proc")
db = Path(tmp, "prompts.db")
db.write_bytes(b"")
Path(tmp, "prompts.db-wal").write_bytes(b"")
comfy = Path(tmp, "comfy")
comfy.mkdir()
holder = proc / "125" / "fd"
holder.mkdir(parents=True)
os.symlink(Path(tmp, "prompts.db-wal"), holder / "3")
(proc / "125" / "cmdline").write_bytes(b"python\0main.py\0")
os.symlink(comfy, proc / "125" / "cwd")
(proc / "123").mkdir() # unreadable: no fd, cmdline or cwd
(proc / "self").mkdir() # not a pid
return proc, db, comfy
@unittest.skipIf(os.name == "nt", "symlinks need privileges on Windows")
def test_proc_scan_finds_holders_and_skips_unreadable_entries(self):
with tempfile.TemporaryDirectory() as tmp:
proc, db, comfy = self.fake_proc(tmp)
found = tool.open_by_others(str(db), proc=str(proc), own_pid=1)
self.assertEqual(len(found), 1)
self.assertIn("125", found[0])
self.assertEqual(
tool.open_by_others(str(db), proc=str(proc), own_pid=125), []
)
running = tool.comfyui_running(str(comfy), 1, proc=str(proc))
self.assertTrue(any("125" in item for item in running), running)
def test_without_proc_the_scan_says_it_cannot_tell(self):
self.assertEqual(
tool.open_by_others("/x/prompts.db", proc="/nonexistent/proc"),
[tool.NO_PROC],
)
def test_missing_database_is_an_argument_error(self):
with self.assertRaises(SystemExit), contextlib.redirect_stderr(io.StringIO()):
tool.main(
["/nonexistent/prompts.db", "--output-dir", "/tmp"], out=io.StringIO()
)
def test_apply_needs_the_comfyui_folder(self):
with tempfile.TemporaryDirectory() as tmp:
db = os.path.join(tmp, "prompts.db")
Path(db).write_bytes(b"")
with (
self.assertRaises(SystemExit),
contextlib.redirect_stderr(io.StringIO()),
):
tool.main([db, "--apply", "plan.json"], out=io.StringIO())
if __name__ == "__main__":
unittest.main()