fix(review): never queue an ambiguous file with nothing to choose

The maintainer's live queue held 39 items whose candidates all read
"unresolved" ("No positive / No negative"). An ambiguous result is now
reviewable only when at least two candidates are resolved with non-blank
positive text. With none the file could not be traced; with exactly one,
the untraced branches may still have made the file, so that text is not
certain either. Both are reported unresolved, never linked and never
queued (also the A1111 two-delimiter case, which has no candidates).

A rescan removes the pending items of such files whose own evidence
offers no choice, with the same safe delete as the linked settle
(pending, revision 0, no decision row). A limited item (over 16 candidates) that holds at least two
candidates is kept. The job scope gains review_untraced and the log
"= N images left Needs review · nothing to choose".
This commit is contained in:
Vito Sansevero
2026-10-23 13:03:10 -07:00
parent 9e125ee4a3
commit 18d81c9d96
12 changed files with 607 additions and 55 deletions
+30 -10
View File
@@ -44,6 +44,7 @@ try:
parse_page_json,
)
from ...utils.prompt_pair_resolver import resolve_prompt_pair
from ...utils.review_capture import reviewable
except ImportError:
from database.operations import PromptDatabase
from database.pair_ingestion import ingest_resolved_pair
@@ -54,6 +55,7 @@ except ImportError:
parse_page_json,
)
from utils.prompt_pair_resolver import resolve_prompt_pair
from utils.review_capture import reviewable
try:
@@ -214,8 +216,9 @@ def _time_left(done, total, batches, elapsed):
def new_review_counts():
"""The scan's Needs review tally: ``added`` new items, ``queued`` files
in the queue after this scan (new or already there), ``settled`` items
removed because their file is linked now, and ``errors``."""
return {"added": 0, "queued": 0, "settled": 0, "errors": 0}
removed because their file is linked now, ``untraced`` items removed
because they offer nothing to choose, and ``errors``."""
return {"added": 0, "queued": 0, "settled": 0, "untraced": 0, "errors": 0}
def _review_scope(review):
@@ -229,6 +232,7 @@ def _review_scope(review):
"review_items": review["queued"],
"review_added": review["added"],
"review_settled": review["settled"],
"review_untraced": review["untraced"],
"review_errors": review["errors"],
}
@@ -1612,7 +1616,9 @@ class AdminRoutesMixin:
whose final outcome is ambiguous and unlinked (the resolver found it
ambiguous and the fallback did not link it) is recorded for Needs
review (best effort, counted in ``review`` when given); one a saved
row already links is reported ``unchanged`` and never queued.
row already links is reported ``unchanged`` and never queued. An
ambiguous file with nothing to choose is reported ``unresolved`` and
its pending items without a choice leave the queue.
"""
counts = dict.fromkeys(SCAN_COUNT_KEYS, 0)
@@ -1624,10 +1630,14 @@ class AdminRoutesMixin:
if self._scan_job and self._scan_job.cancelled:
break
counts["processed"] += 1
ambiguous = []
ambiguous, untraced = [], []
try:
outcome = self._ingest_scanned_file(
media_file, metadata, detailed=True, ambiguous=ambiguous
media_file,
metadata,
detailed=True,
ambiguous=ambiguous,
untraced=untraced,
)
except Exception as e:
self.logger.error(f"Error processing {media_file.name}: {e}")
@@ -1639,6 +1649,8 @@ class AdminRoutesMixin:
outcome = "unchanged" # already linked: not a review case
else:
self._record_scanned_review(media_file, roots, review)
elif untraced and outcome == "unresolved":
self._settle_untraced_reviews(untraced, roots, review)
if outcome is None:
note(media_file, None)
continue
@@ -1673,7 +1685,7 @@ class AdminRoutesMixin:
return positive.strip() or None
def _ingest_scanned_file(
self, media_file, metadata, detailed=False, ambiguous=None
self, media_file, metadata, detailed=False, ambiguous=None, untraced=None
):
"""Enrich exact pairs; retain legacy positive-only import for absent pairs.
@@ -1683,7 +1695,10 @@ class AdminRoutesMixin:
the pair counts. When the resolver finds the file ambiguous (whether
or not the browser parser then links it) and ``ambiguous`` is a list,
``media_file`` is appended to it; only a file that then returns
``"ambiguous"`` (nothing linked it) is a Needs review case.
``"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``.
"""
if not metadata:
return None
@@ -1699,7 +1714,12 @@ class AdminRoutesMixin:
return None
_with_file_size(canonical, media_file)
resolution = resolve_prompt_pair(canonical)
if resolution["state"] == "ambiguous" and ambiguous is not None:
# Ambiguous without a choice: unresolved unless something links it.
unchoosable = resolution["state"] == "ambiguous" and not reviewable(resolution)
if unchoosable:
if untraced is not None:
untraced.append(media_file)
elif resolution["state"] == "ambiguous" and ambiguous is not None:
ambiguous.append(media_file)
if resolution["state"] == "resolved":
result = ingest_resolved_pair(
@@ -1720,9 +1740,9 @@ class AdminRoutesMixin:
# Graphs without a recognized sampler keep the legacy extractor below.
prompt_text = self._graph_prompt_text(metadata)
if not prompt_text:
return resolution["state"]
return "unresolved" if unchoosable else resolution["state"]
elif resolution["state"] == "ambiguous":
return "ambiguous"
return "unresolved" if unchoosable else "ambiguous"
elif resolution["state"] == "unresolved" and not isinstance(
canonical.get("parameters"), str
):