feat(ml): soft auto-apply — retract auto-tags now below threshold (milestone 139)

Daily scheduled_retract_auto_tags re-scores standing auto-applied tags and drops
the ones the model no longer supports:
- retract_auto_applied_heads: per graduated head, re-score its source='head_auto'
  images (bounded — only the images already carrying the auto-tag, not the whole
  library) and remove ones now < auto_apply_threshold.
- retract_auto_applied_ccip: per source='ccip_auto' character tag, max-cosine the
  image's figure vectors vs that character's prototypes; remove ones now below the
  ccip auto-apply threshold.
Both SKIP operator-confirmed tags (TagPositiveConfirmation) and are SILENT — a low
score isn't proof the tag was wrong, so no hard negative is recorded (that's
reserved for an operator removal). No-op unless the relevant auto-apply switch is
on. New daily beat. sklearn-free tests for both paths + the disabled no-op.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM

backend/app/services/ml/heads.py

@@ -35,6 +35,7 @@ from ...models import (
     Tag,
     TagHead,
     TagKind,
+    TagPositiveConfirmation,
     TagSuggestionRejection,
 )
 from ...models.tag import image_tag
@@ -723,3 +724,64 @@ def auto_apply_sweep(
         for h in range(len(rows))
     ]
     return {"n_applied": sum(applied), "concepts": concepts}
+
+
+def retract_auto_applied_heads(session: Session) -> int:
+    """Soft auto-apply (milestone 139): re-score every standing source='head_auto'
+    tag against its CURRENT head and REMOVE the ones now BELOW the head's
+    auto_apply_threshold — i.e. the head sharpened (or the operator raised the bar)
+    and no longer supports them. Skips operator-confirmed tags
+    (TagPositiveConfirmation). SILENT: a low score isn't proof the tag was wrong,
+    so no hard negative is recorded — that's reserved for an operator removal.
+    No-op unless head_auto_apply_enabled. Only re-scores the images that ALREADY
+    carry the auto-tag (bounded), never the whole library. Returns n_retracted."""
+    import numpy as np
+
+    settings = _settings(session)
+    if not settings.head_auto_apply_enabled:
+        return 0
+    heads = session.execute(
+        select(
+            TagHead.tag_id, TagHead.weights, TagHead.bias,
+            TagHead.auto_apply_threshold,
+        )
+        .where(TagHead.embedding_version == settings.embedder_model_version)
+        .where(TagHead.auto_apply_threshold.is_not(None))
+    ).all()
+    retracted = 0
+    for tag_id, weights, bias, thr in heads:
+        auto_ids = [
+            iid for (iid,) in session.execute(
+                select(image_tag.c.image_record_id)
+                .where(image_tag.c.tag_id == tag_id)
+                .where(image_tag.c.source == "head_auto")
+            )
+        ]
+        if not auto_ids:
+            continue
+        confirmed = {
+            iid for (iid,) in session.execute(
+                select(TagPositiveConfirmation.image_record_id)
+                .where(TagPositiveConfirmation.tag_id == tag_id)
+                .where(TagPositiveConfirmation.image_record_id.in_(auto_ids))
+            )
+        }
+        candidates = [i for i in auto_ids if i not in confirmed]
+        emb = _load_embeddings(session, candidates)
+        cids = [i for i in candidates if i in emb]
+        if not cids:
+            continue
+        Xn = _l2norm(np.vstack([emb[i] for i in cids]).astype(np.float32), np)
+        w = np.asarray(weights, dtype=np.float32)
+        probs = 1.0 / (1.0 + np.exp(-(Xn @ w + float(bias))))
+        below = [cids[k] for k in np.where(probs < float(thr))[0]]
+        for iid in below:
+            session.execute(
+                image_tag.delete()
+                .where(image_tag.c.image_record_id == iid)
+                .where(image_tag.c.tag_id == tag_id)
+                .where(image_tag.c.source == "head_auto")
+            )
+            retracted += 1
+        session.commit()
+    return retracted