bvandeusen
2d44a26bdf
Makes auto-apply truly "soft" for heads: _ids_with_tag (head positives) and _eligible_tag_ids (graduation count) now count human-applied + operator-confirmed tags only, via a shared _AUTO_SOURCES (head_auto/ccip_auto/ml_auto) exclusion. Unconfirmed auto-applied tags no longer train the head that judges them, so a misfire can't reinforce itself and the retraction sweep can actually drop it. Confirming a tag (TagPositiveConfirmation) promotes it to a positive AND protects it from retraction. sklearn-free tests. CCIP reference exclusion is the companion piece, next. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
70 lines
2.4 KiB
Python
70 lines
2.4 KiB
Python
"""Soft auto-apply (milestone 139): unconfirmed auto-applied tags do NOT train a
|
|
head. _ids_with_tag (positives) + _eligible_tag_ids (graduation count) count
|
|
human-applied + operator-confirmed tags only. Sklearn-free, so tested via
|
|
db_sync."""
|
|
import pytest
|
|
|
|
from backend.app.models import ImageRecord, Tag, TagKind, TagPositiveConfirmation
|
|
from backend.app.models.tag import image_tag
|
|
from backend.app.services.ml.heads import _eligible_tag_ids
|
|
from backend.app.services.ml.training_data import _ids_with_tag
|
|
|
|
pytestmark = pytest.mark.integration
|
|
|
|
|
|
def _img(db, sha: str) -> ImageRecord:
|
|
img = ImageRecord(
|
|
path=f"/images/{sha}.jpg", sha256=sha, size_bytes=1, mime="image/jpeg",
|
|
width=1, height=1, origin="imported_filesystem",
|
|
integrity_status="unknown",
|
|
)
|
|
db.add(img)
|
|
db.flush()
|
|
return img
|
|
|
|
|
|
def _tag(db, name: str) -> Tag:
|
|
t = Tag(name=name, kind=TagKind.general)
|
|
db.add(t)
|
|
db.flush()
|
|
return t
|
|
|
|
|
|
def _apply(db, image_id: int, tag_id: int, source: str) -> None:
|
|
db.execute(image_tag.insert().values(
|
|
image_record_id=image_id, tag_id=tag_id, source=source,
|
|
))
|
|
|
|
|
|
def test_positives_exclude_unconfirmed_auto(db_sync):
|
|
tag = _tag(db_sync, "glasses")
|
|
man = _img(db_sync, "a" * 64)
|
|
auto = _img(db_sync, "b" * 64)
|
|
conf = _img(db_sync, "c" * 64)
|
|
acc = _img(db_sync, "d" * 64)
|
|
_apply(db_sync, man.id, tag.id, "manual")
|
|
_apply(db_sync, auto.id, tag.id, "head_auto") # unconfirmed → excluded
|
|
_apply(db_sync, conf.id, tag.id, "head_auto") # confirmed → included
|
|
_apply(db_sync, acc.id, tag.id, "ml_accepted")
|
|
db_sync.add(TagPositiveConfirmation(image_record_id=conf.id, tag_id=tag.id))
|
|
db_sync.commit()
|
|
|
|
pos = set(_ids_with_tag(db_sync, tag.id))
|
|
assert pos == {man.id, conf.id, acc.id}
|
|
assert auto.id not in pos
|
|
|
|
|
|
def test_eligibility_counts_positives_only(db_sync):
|
|
# A concept whose only tags are unconfirmed auto-applies does NOT graduate.
|
|
tag = _tag(db_sync, "autotag")
|
|
for i in range(3):
|
|
_apply(db_sync, _img(db_sync, f"e{i}" * 32).id, tag.id, "head_auto")
|
|
db_sync.commit()
|
|
assert tag.id not in _eligible_tag_ids(db_sync, min_pos=2)
|
|
|
|
# Two human positives → now eligible at min_pos=2.
|
|
for i in range(2):
|
|
_apply(db_sync, _img(db_sync, f"h{i}" * 32).id, tag.id, "manual")
|
|
db_sync.commit()
|
|
assert tag.id in _eligible_tag_ids(db_sync, min_pos=2)
|