backend/app/services/ml/heads.py

@@ -22,7 +22,7 @@ import logging
 from datetime import UTC, datetime
 from typing import Any
 
-from sqlalchemy import delete, func, select
+from sqlalchemy import delete, exists, func, select
 from sqlalchemy.ext.asyncio import AsyncSession
 from sqlalchemy.orm import Session
 
@@ -40,6 +40,7 @@ from ...models import (
 )
 from ...models.tag import image_tag
 from .training_data import (
+    _AUTO_SOURCES,
     _auto_apply_point,
     _hygiene_excluded_ids,
     _ids_with_tag,
@@ -138,13 +139,20 @@ def _embedder_version(session: Session) -> str:
 
 
 def _eligible_tag_ids(session: Session, min_pos: int) -> list[int]:
-    """Concept tags (general/character) with >= min_pos labelled images — the
-    set that gets a head. Counts all sources; source-aware filtering (#1133) is
-    a separate, optional refinement."""
+    """Concept tags (general/character) with >= min_pos POSITIVE images — the set
+    that gets a head. Counts human-applied + operator-confirmed tags only;
+    unconfirmed auto-applied predictions do NOT count toward eligibility (they
+    don't train the head — milestone 139), so a concept can't graduate on its own
+    guesses."""
+    confirmed = exists().where(
+        TagPositiveConfirmation.image_record_id == image_tag.c.image_record_id,
+        TagPositiveConfirmation.tag_id == image_tag.c.tag_id,
+    )
     rows = session.execute(
         select(Tag.id)
         .join(image_tag, image_tag.c.tag_id == Tag.id)
         .where(Tag.kind.in_(_HEAD_KINDS))
+        .where(image_tag.c.source.not_in(_AUTO_SOURCES) | confirmed)
         .group_by(Tag.id)
         .having(func.count(image_tag.c.image_record_id) >= min_pos)
     ).all()

backend/app/services/ml/training_data.py

@@ -17,9 +17,20 @@ from typing import Any
 from sqlalchemy import func, select
 from sqlalchemy.orm import Session
 
-from ...models import ImageRecord, Tag, TagSuggestionRejection
+from ...models import (
+    ImageRecord,
+    Tag,
+    TagPositiveConfirmation,
+    TagSuggestionRejection,
+)
 from ...models.tag import image_tag
 
+# Auto-apply sources whose tags are PROVISIONAL: they never train a head (or seed
+# a CCIP reference) unless the operator confirms them (milestone 139). Keeping
+# auto-applied predictions out of training is what makes them "soft" — a misfire
+# can't reinforce itself, so the retraction sweep can actually drop it.
+_AUTO_SOURCES = ("head_auto", "ccip_auto", "ml_auto")
+
 
 def _hygiene_excluded_ids(session: Session) -> set[int]:
     """Ids of images carrying ANY system tag (wip / banner / editor
@@ -45,9 +56,23 @@ def _hygiene_excluded_ids(session: Session) -> set[int]:
 
 
 def _ids_with_tag(session: Session, tag_id: int) -> list[int]:
+    """Image ids that count as POSITIVES for this tag's head: human-applied
+    (manual / accepted) tags PLUS any auto-applied tag the operator explicitly
+    confirmed (TagPositiveConfirmation). Unconfirmed auto-applied tags are
+    EXCLUDED — they are provisional and must not train the head that judges
+    them (milestone 139)."""
+    confirmed = (
+        select(TagPositiveConfirmation.image_record_id)
+        .where(TagPositiveConfirmation.tag_id == tag_id)
+    )
     return [
         r[0] for r in session.execute(
-            select(image_tag.c.image_record_id).where(image_tag.c.tag_id == tag_id)
+            select(image_tag.c.image_record_id)
+            .where(image_tag.c.tag_id == tag_id)
+            .where(
+                image_tag.c.source.not_in(_AUTO_SOURCES)
+                | image_tag.c.image_record_id.in_(confirmed)
+            )
         ).all()
     ]
 

tests/test_head_positive_sources.py

@@ -0,0 +1,69 @@
+"""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)