nodes/ComfyAssets-ComfyUI_PromptManager
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat(review): supersede stale items and inspect each file state once

Browse Source 
A semantics table or resolver version change no longer leaves two pending
items for one file. A new item supersedes the other items of the same bytes
when every one is pending and undecided (revision 0, no decision row, the
self-heal's safe delete). Beside a decided or advanced item nothing new is
stored, and the rescan's stat shortcut skips those bytes under any version.

The inspection item version now folds a narrower fingerprint: the table
restricted to the graph's node classes plus its class-independent parts, so
an edit about other classes leaves every item alone.

The inspection profile runs once per file state. The scan resolves the
untraced file at batch level, skips files already queued or decided at their
current size and mtime under their version, and remembers files it found
untraced in this process. The capture reuses the scan's result when it holds
the same records.
This commit is contained in:
Vito Sansevero
2026-10-23 16:02:49 -07:00
parent 341757ea8e
commit 143b2a6b44
8 changed files with 705 additions and 126 deletions
Download Patch File Download Diff File Expand all files Collapse all files
py/api/admin.py
+23 -31
View File
@@ -45,7 +45,7 @@ try:
parse_page_json,
)
from ...utils.prompt_pair_resolver import resolve_prompt_pair
from ...utils.review_capture import inspection_offers_choice, reviewable
from ...utils.review_capture import reviewable
except ImportError:
from database.operations import PromptDatabase
from database.pair_ingestion import ingest_resolved_pair
@@ -56,7 +56,7 @@ except ImportError:
parse_page_json,
)
from utils.prompt_pair_resolver import resolve_prompt_pair
from utils.review_capture import inspection_offers_choice, reviewable
from utils.review_capture import reviewable
try:
@@ -252,22 +252,6 @@ def _file_size(path):
return None
def _untraced_outcome(media_file, canonical, ambiguous, untraced):
"""The status of an unlinked file the default profile found ambiguous
without a choice: ``"ambiguous"`` when the inspection profile offers one
(the file moves from ``untraced`` to ``ambiguous``), else ``"unresolved"``.
Asked only when ``ambiguous`` is a list (the scan, which records review
items), so other callers never pay for the heavier profile.
"""
if ambiguous is None or not inspection_offers_choice(canonical):
return "unresolved"
if untraced is not None and media_file in untraced:
untraced.remove(media_file)
ambiguous.append(media_file)
return "ambiguous"
def _with_file_size(canonical, media_file):
"""Record the file's size in ``file_info`` unless the metadata carries one.
@@ -1662,7 +1646,7 @@ class AdminRoutesMixin:
if self._scan_job and self._scan_job.cancelled:
break
counts["processed"] += 1
ambiguous, untraced = [], []
ambiguous, untraced, records = [], [], {}
try:
outcome = self._ingest_scanned_file(
media_file,
@@ -1670,6 +1654,7 @@ class AdminRoutesMixin:
detailed=True,
ambiguous=ambiguous,
untraced=untraced,
records=records,
)
except Exception as e:
self.logger.error(f"Error processing {media_file.name}: {e}")
@@ -1682,7 +1667,11 @@ class AdminRoutesMixin:
else:
self._record_scanned_review(media_file, roots, review)
elif untraced and outcome == "unresolved":
self._settle_untraced_reviews(untraced, roots, review)
# Untraced by the default profile: the inspection profile may
# still offer a choice (queued for review, never linked).
outcome = self._untraced_scan_outcome(
media_file, roots, records.get("canonical"), review
)
if outcome is None:
note(media_file, None)
continue
@@ -1717,7 +1706,13 @@ class AdminRoutesMixin:
return positive.strip() or None
def _ingest_scanned_file(
self, media_file, metadata, detailed=False, ambiguous=None, untraced=None
self,
media_file,
metadata,
detailed=False,
ambiguous=None,
untraced=None,
records=None,
):
"""Enrich exact pairs; retain legacy positive-only import for absent pairs.
@@ -1730,10 +1725,9 @@ class AdminRoutesMixin:
``"ambiguous"`` (nothing linked it) is a Needs review case. An
ambiguous result with nothing to choose (``reviewable`` is False: fewer
than two candidates carry a prompt) that nothing links returns
``"unresolved"`` instead, and ``media_file`` goes to ``untraced``,
unless the inspection profile offers a choice (only asked when
``ambiguous`` is a list, so only by the scan): then it is
``"ambiguous"`` and goes to ``ambiguous``. That profile never links.
``"unresolved"`` instead, and ``media_file`` goes to ``untraced``;
its parsed records go to ``records["canonical"]`` when ``records`` is
a dict.
"""
if not metadata:
return None
@@ -1754,6 +1748,8 @@ class AdminRoutesMixin:
if unchoosable:
if untraced is not None:
untraced.append(media_file)
if records is not None:
records["canonical"] = canonical
elif resolution["state"] == "ambiguous" and ambiguous is not None:
ambiguous.append(media_file)
if resolution["state"] == "resolved":
@@ -1775,13 +1771,9 @@ class AdminRoutesMixin:
# Graphs without a recognized sampler keep the legacy extractor below.
prompt_text = self._graph_prompt_text(metadata)
if not prompt_text:
if unchoosable:
return _untraced_outcome(media_file, canonical, ambiguous, untraced)
return resolution["state"]
return "unresolved" if unchoosable else resolution["state"]
elif resolution["state"] == "ambiguous":
if unchoosable:
return _untraced_outcome(media_file, canonical, ambiguous, untraced)
return "ambiguous"
return "unresolved" if unchoosable else "ambiguous"
elif resolution["state"] == "unresolved" and not isinstance(
canonical.get("parameters"), str
):
py/api/review_recording.py
+85 -4
View File
@@ -33,6 +33,7 @@ the file again.
"""
import os
from collections import OrderedDict
from pathlib import Path
from .admin import SCAN_LOG_PREFIXES, _plural, _scan_location, _scan_roots
@@ -44,10 +45,16 @@ QUEUED_OUTCOMES = ("recorded", "limited", "duplicate")
NEW_OUTCOMES = ("recorded", "limited")
try:
from ...utils import review_capture
from ...utils.review_capture import record_ambiguous_file
except ImportError:
from utils import review_capture
from utils.review_capture import record_ambiguous_file
# Untraced files remembered per process so a rescan of an unchanged file does
# not run the inspection profile again (oldest forgotten first).
MAX_UNTRACED_MEMORY = 65_536
# The scan log's reason for items that leave the queue with nothing to choose.
NOTHING_TO_CHOOSE = "nothing to choose"
@@ -55,11 +62,14 @@ NOTHING_TO_CHOOSE = "nothing to choose"
class ReviewRecordingMixin:
"""Record the scan's and the monitor's ambiguous files for Needs review."""
def _record_scanned_review(self, media_file, roots, review=None):
"""Record one ambiguous, unlinked scanned file (logged and counted)."""
def _record_scanned_review(self, media_file, roots, review=None, scanned=None):
"""Record one ambiguous, unlinked scanned file (logged and counted).
``scanned`` is the scan's ``(metadata, inspection_resolution)``.
"""
try:
outcome = self._record_review_sync(
media_file, roots, review, inspection=True
media_file, roots, review, inspection=True, scanned=scanned
)
except Exception:
self.logger.warning(
@@ -76,7 +86,9 @@ class ReviewRecordingMixin:
if outcome in QUEUED_OUTCOMES:
review["queued"] += 1
def _record_review_sync(self, media_file, roots, review=None, inspection=False):
def _record_review_sync(
self, media_file, roots, review=None, inspection=False, scanned=None
):
"""``record_ambiguous_file`` for a file under one of ``roots`` (blocking).
``inspection`` (the scan only) lets a file without a choice under the
@@ -95,11 +107,80 @@ class ReviewRecordingMixin:
index,
relative,
inspection=inspection,
scanned=scanned,
)
if outcome == "untraced":
self._settle_untraced_reviews([media_file], roots, review)
return outcome
def _untraced_scan_outcome(self, media_file, roots, canonical, review=None):
"""The scan status of an unlinked file the default profile left
ambiguous without a choice (blocking).
``ambiguous`` when the inspection profile offers a choice: the file is
recorded for review from that profile (never linked), or ``unchanged``
when a saved row links it already. Otherwise ``unresolved``, and its
pending items without a choice leave the queue. The profile runs at
most once per file state: not for bytes already queued (or decided)
at the file's current size and ``mtime_ns`` under the version that
its records depend on, and not again for a state it already found
untraced in this process.
"""
choice = self._inspection_choice(media_file, roots, canonical)
if choice is None:
self._settle_untraced_reviews([media_file], roots, review)
return "unresolved"
if self._review_file_linked(media_file, roots):
return "unchanged"
self._record_scanned_review(media_file, roots, review, scanned=choice)
return "ambiguous"
def _inspection_choice(self, media_file, roots, canonical):
"""``(canonical, resolution_or_None)`` when the file offers a choice.
The resolution is None when the file's current state is already in
the queue (so the profile did not run). None when it offers none.
"""
if canonical is None:
return None
version = review_capture.inspection_review_version(canonical)
located = self._review_location(media_file, roots)
if version is None or located is None:
return None
locator = os.path.normcase(located[3])
try:
facts = os.lstat(located[3])
except OSError:
facts = None
state = None
if facts is not None:
state = (facts.st_size, facts.st_mtime_ns, version)
if self.db.review_decided_at(
locator, facts.st_size, facts.st_mtime_ns
) or self.db.review_fingerprint_queued(
locator, facts.st_size, facts.st_mtime_ns, version
):
return canonical, None
memory = self._untraced_memory()
if state is not None and memory.get(locator) == state:
return None
resolution = review_capture.inspection_choice(canonical)
if resolution is not None:
memory.pop(locator, None)
return canonical, resolution
if state is not None:
memory[locator] = state
memory.move_to_end(locator)
while len(memory) > MAX_UNTRACED_MEMORY:
memory.popitem(last=False)
return None
def _untraced_memory(self):
memory = getattr(self, "_untraced_inspections", None)
if memory is None:
memory = self._untraced_inspections = OrderedDict()
return memory
@staticmethod
def _review_location(media_file, roots, real_roots=None):
"""``(root, root_index, relative, spelled)`` of a listed file, or None.