Merge pull request 'CCIP automation + reference quality (auto-enqueue, auto-apply, contamination fix, cache)' (#152) from dev into main

alembic/versions/0064_ccip_auto_apply.py

@@ -0,0 +1,42 @@
+"""ml_settings: CCIP auto-apply switch + threshold (#114)
+
+Confident CCIP character matches auto-tag (source='ccip_auto') on a daily sweep,
+so identity tags keep flowing without pressing a button. ON by default (opt-out,
+like head auto-apply); the high threshold (0.92, above the 0.85 suggest cut) +
+single-character references keep it safe, and every auto-tag is reversible.
+
+Revision ID: 0064
+Revises: 0063
+Create Date: 2026-06-30
+"""
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+revision: str = "0064"
+down_revision: Union[str, None] = "0063"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "ml_settings",
+        sa.Column(
+            "ccip_auto_apply_enabled", sa.Boolean(), nullable=False,
+            server_default=sa.true(),
+        ),
+    )
+    op.add_column(
+        "ml_settings",
+        sa.Column(
+            "ccip_auto_apply_threshold", sa.Float(), nullable=False,
+            server_default="0.92",
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("ml_settings", "ccip_auto_apply_threshold")
+    op.drop_column("ml_settings", "ccip_auto_apply_enabled")

backend/app/api/ccip.py

@@ -62,6 +62,13 @@ async def overview():
                 )
             ).all() if v
         ]
+        auto_applied = (
+            await session.execute(
+                select(func.count()).select_from(image_tag).where(
+                    image_tag.c.source == "ccip_auto"
+                )
+            )
+        ).scalar_one()
     return jsonify({
         "regions_by_kind": by_kind,
         "images_with_figure_ccip": images_with_figure_ccip,
@@ -70,6 +77,7 @@ async def overview():
             {"tag_id": t, "name": n, "n_refs": c} for (t, n, c) in ref_rows
         ],
         "embedding_versions": versions,
+        "auto_applied": auto_applied,
     })
 
 

backend/app/api/ml_admin.py

@@ -22,6 +22,8 @@ _EDITABLE = (
     "head_auto_apply_enabled",
     "head_auto_apply_min_positives",
     "ccip_match_threshold",
+    "ccip_auto_apply_enabled",
+    "ccip_auto_apply_threshold",
 )
 
 
@@ -50,6 +52,8 @@ async def get_settings():
             "head_auto_apply_enabled": s.head_auto_apply_enabled,
             "head_auto_apply_min_positives": s.head_auto_apply_min_positives,
             "ccip_match_threshold": s.ccip_match_threshold,
+            "ccip_auto_apply_enabled": s.ccip_auto_apply_enabled,
+            "ccip_auto_apply_threshold": s.ccip_auto_apply_threshold,
         }
     )
 
@@ -119,6 +123,8 @@ def _validate(p: dict) -> str | None:
         return "head_auto_apply_min_positives must be >= 1"
     if not (0.5 <= float(p["ccip_match_threshold"]) <= 0.999):
         return "ccip_match_threshold must be between 0.5 and 0.999"
+    if not (0.5 <= float(p["ccip_auto_apply_threshold"]) <= 0.999):
+        return "ccip_auto_apply_threshold must be between 0.5 and 0.999"
     return None
 
 

backend/app/celery_app.py

@@ -121,6 +121,15 @@ def make_celery() -> Celery:
                 "task": "backend.app.tasks.ml.recover_orphaned_gpu_jobs",
                 "schedule": 60.0,  # quick pickup of work a dead agent orphaned
             },
+            "enqueue-ccip-backfill-hourly": {
+                "task": "backend.app.tasks.ml.enqueue_gpu_backfill",
+                "schedule": 3600.0,  # auto-feed new images (+ retry errored) so
+                "args": ("ccip",),   # the queue keeps moving without the button
+            },
+            "ccip-auto-apply-daily": {
+                "task": "backend.app.tasks.ml.scheduled_ccip_auto_apply",
+                "schedule": 86400.0,  # no-op unless ccip_auto_apply_enabled
+            },
             "snapshot-head-metrics-daily": {
                 "task": "backend.app.tasks.maintenance.snapshot_head_metrics",
                 "schedule": 86400.0,

backend/app/models/ml_settings.py

@@ -92,6 +92,15 @@ class MLSettings(Base):
     ccip_match_threshold: Mapped[float] = mapped_column(
         Float, nullable=False, default=0.85
     )
+    # CCIP auto-apply (#114). Confident matches (>= ccip_auto_apply_threshold,
+    # above the suggest cut) auto-tag on a daily sweep. ON by default (opt-out);
+    # single-character references + the high bar keep it safe, every tag reversible.
+    ccip_auto_apply_enabled: Mapped[bool] = mapped_column(
+        Boolean, nullable=False, default=True
+    )
+    ccip_auto_apply_threshold: Mapped[float] = mapped_column(
+        Float, nullable=False, default=0.92
+    )
     tagger_model_version: Mapped[str] = mapped_column(
         String(128), nullable=False, default="camie-tagger-v2"
     )

backend/app/services/ml/ccip.py

@@ -13,7 +13,7 @@ exact CCIP difference metric/threshold gets validated against the model during
 the hands-on eval. numpy is imported lazily (API worker has it via pgvector).
 """
 
-from sqlalchemy import select
+from sqlalchemy import func, select
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from ...models import ImageRegion, MLSettings, Tag, TagKind
@@ -41,10 +41,54 @@ def _l2norm(mat, np):
     return mat / n
 
 
+# Single-shot cache of the (expensive) reference load, keyed on a cheap
+# signature that changes exactly when references could: a character tag added/
+# removed (n_char_tags) or a figure embedded (max/ n of ccip regions). Shared by
+# the live matcher (every modal open) and the auto-apply sweep.
+_REF_CACHE: dict = {"sig": None, "refs": None}
+
+
+def _single_character_images():
+    """Subquery of image ids carrying EXACTLY ONE character tag. References come
+    only from these — on a multi-character image the tag is image-level, so every
+    figure would otherwise pollute each character's prototype set (a 2-character
+    image tagged 'Velma' would make Daphne's figure a Velma reference)."""
+    return (
+        select(image_tag.c.image_record_id)
+        .join(Tag, Tag.id == image_tag.c.tag_id)
+        .where(Tag.kind == TagKind.character)
+        .group_by(image_tag.c.image_record_id)
+        .having(func.count() == 1)
+    )
+
+
+async def _ref_signature(session: AsyncSession) -> tuple:
+    n_tags = (
+        await session.execute(
+            select(func.count())
+            .select_from(image_tag)
+            .join(Tag, Tag.id == image_tag.c.tag_id)
+            .where(Tag.kind == TagKind.character)
+        )
+    ).scalar_one()
+    n_regs, max_id = (
+        await session.execute(
+            select(func.count(), func.max(ImageRegion.id)).where(
+                ImageRegion.kind.in_(_FIGURE_KINDS),
+                ImageRegion.ccip_embedding.is_not(None),
+            )
+        )
+    ).one()
+    return (n_tags, n_regs, max_id)
+
+
 async def character_references(session: AsyncSession) -> dict[int, list]:
     """Per character-tag CCIP reference vectors: figure/face-region CCIP
-    embeddings on images that carry that character tag (the operator's examples).
-    Multi-prototype — several vectors per character."""
+    embeddings on UNAMBIGUOUS (single-character) images carrying that tag.
+    Multi-prototype — several vectors per character. Cached on a cheap signature."""
+    sig = await _ref_signature(session)
+    if _REF_CACHE["sig"] == sig and _REF_CACHE["refs"] is not None:
+        return _REF_CACHE["refs"]
     rows = (
         await session.execute(
             select(image_tag.c.tag_id, ImageRegion.ccip_embedding)
@@ -57,11 +101,13 @@ async def character_references(session: AsyncSession) -> dict[int, list]:
             .where(Tag.kind == TagKind.character)
             .where(ImageRegion.kind.in_(_FIGURE_KINDS))
             .where(ImageRegion.ccip_embedding.is_not(None))
+            .where(ImageRegion.image_record_id.in_(_single_character_images()))
         )
     ).all()
     refs: dict[int, list] = {}
     for tag_id, vec in rows:
         refs.setdefault(tag_id, []).append(vec)
+    _REF_CACHE.update(sig=sig, refs=refs)
     return refs
 
 

backend/app/tasks/ml.py

@@ -795,3 +795,124 @@ def recover_orphaned_gpu_jobs() -> int:
         )
         session.commit()
         return res.rowcount or 0
+
+
+@celery.task(
+    name="backend.app.tasks.ml.scheduled_ccip_auto_apply",
+    soft_time_limit=1800, time_limit=2100,
+)
+def scheduled_ccip_auto_apply() -> str:
+    """Auto-tag confident CCIP character matches (source='ccip_auto') so identity
+    tags keep flowing without a button. No-op unless ccip_auto_apply_enabled.
+    References come only from single-character images (unambiguous); a tag is
+    applied where any figure's best cosine to a character's prototypes clears
+    ccip_auto_apply_threshold and it isn't already applied/rejected. Reversible."""
+    import numpy as np
+    from sqlalchemy import func
+    from sqlalchemy import select as sa_select
+    from sqlalchemy.dialects.postgresql import insert as pg_insert
+
+    from ..models import ImageRegion, MLSettings, Tag, TagKind, TagSuggestionRejection
+    from ..models.tag import image_tag
+
+    fig = ("face", "figure")
+
+    def _l2(m):
+        n = np.linalg.norm(m, axis=1, keepdims=True)
+        n[n == 0] = 1.0
+        return m / n
+
+    SessionLocal = _sync_session_factory()
+    with SessionLocal() as session:
+        s = session.get(MLSettings, 1)
+        if s is None or not s.ccip_auto_apply_enabled:
+            return "disabled"
+        thr = float(s.ccip_auto_apply_threshold)
+
+        single = (
+            sa_select(image_tag.c.image_record_id)
+            .join(Tag, Tag.id == image_tag.c.tag_id)
+            .where(Tag.kind == TagKind.character)
+            .group_by(image_tag.c.image_record_id)
+            .having(func.count() == 1)
+        )
+        ref_rows = session.execute(
+            sa_select(image_tag.c.tag_id, ImageRegion.ccip_embedding)
+            .select_from(ImageRegion)
+            .join(
+                image_tag,
+                image_tag.c.image_record_id == ImageRegion.image_record_id,
+            )
+            .join(Tag, Tag.id == image_tag.c.tag_id)
+            .where(Tag.kind == TagKind.character)
+            .where(ImageRegion.kind.in_(fig))
+            .where(ImageRegion.ccip_embedding.is_not(None))
+            .where(ImageRegion.image_record_id.in_(single))
+        ).all()
+        if not ref_rows:
+            return "no-references"
+
+        by_char: dict[int, list] = {}
+        for tid, vec in ref_rows:
+            by_char.setdefault(tid, []).append(vec)
+        ref_tags = list(by_char)
+        mats = [_l2(np.asarray(by_char[t], dtype=np.float32)) for t in ref_tags]
+        allref = np.vstack(mats)                                  # (total, 768)
+        seg = np.cumsum([0] + [len(m) for m in mats])[:-1]        # per-char start
+
+        # Per character: images that already carry OR rejected the tag — skip.
+        skip = {t: set() for t in ref_tags}
+        for t in ref_tags:
+            for (iid,) in session.execute(
+                sa_select(image_tag.c.image_record_id).where(
+                    image_tag.c.tag_id == t
+                )
+            ):
+                skip[t].add(iid)
+            for (iid,) in session.execute(
+                sa_select(TagSuggestionRejection.image_record_id).where(
+                    TagSuggestionRejection.tag_id == t
+                )
+            ):
+                skip[t].add(iid)
+
+        img_ids = list(session.execute(
+            sa_select(ImageRegion.image_record_id)
+            .where(ImageRegion.kind.in_(fig), ImageRegion.ccip_embedding.is_not(None))
+            .distinct()
+        ).scalars())
+
+        applied = 0
+        chunk_n = 500
+        for start in range(0, len(img_ids), chunk_n):
+            chunk = img_ids[start:start + chunk_n]
+            rows = session.execute(
+                sa_select(ImageRegion.image_record_id, ImageRegion.ccip_embedding)
+                .where(
+                    ImageRegion.image_record_id.in_(chunk),
+                    ImageRegion.kind.in_(fig),
+                    ImageRegion.ccip_embedding.is_not(None),
+                )
+            ).all()
+            by_img: dict[int, list] = {}
+            for iid, vec in rows:
+                by_img.setdefault(iid, []).append(vec)
+            for iid, vecs in by_img.items():
+                q = _l2(np.asarray(vecs, dtype=np.float32))      # (nq, 768)
+                colmax = (q @ allref.T).max(axis=0)              # (total,)
+                charmax = np.maximum.reduceat(colmax, seg)       # (n_chars,)
+                for ci in np.where(charmax >= thr)[0]:
+                    t = ref_tags[int(ci)]
+                    if iid in skip[t]:
+                        continue
+                    skip[t].add(iid)
+                    session.execute(
+                        pg_insert(image_tag)
+                        .values(
+                            image_record_id=iid, tag_id=t, source="ccip_auto",
+                        )
+                        .on_conflict_do_nothing()
+                    )
+                    applied += 1
+            session.commit()
+        return f"applied={applied}"

frontend/src/components/settings/GpuAgentCard.vue

@@ -76,6 +76,26 @@
       stricter — fewer but more confident matches. 0.85 recommended; below ~0.80
       a heavily-tagged character starts matching everything.
     </p>
+
+    <!-- Auto-apply -->
+    <div v-if="ml.settings" class="d-flex align-center mt-5" style="gap:12px">
+      <v-switch
+        v-model="autoApply" color="accent" hide-details density="compact"
+        :loading="savingAuto" label="Auto-apply confident matches"
+        @update:model-value="onSaveAuto"
+      />
+      <v-text-field
+        v-model.number="autoThreshold" type="number" min="0.80" max="0.99"
+        step="0.01" density="compact" hide-details variant="outlined"
+        style="max-width:96px" :disabled="!autoApply" label="at"
+        @change="onSaveAuto"
+      />
+    </div>
+    <p class="fc-muted text-caption mt-1 mb-0">
+      When on, a very-confident character match tags the image on its own (daily,
+      reversible) — so identity tags keep flowing without review. Stricter than
+      the suggest cut; 0.92 recommended.
+    </p>
   </MaintenanceTile>
 </template>
 
@@ -97,6 +117,9 @@ const rotating = ref(false)
 const backfilling = ref(false)
 const threshold = ref(0.85)
 const savingThreshold = ref(false)
+const autoApply = ref(true)
+const autoThreshold = ref(0.92)
+const savingAuto = ref(false)
 const queue = ref({ pending: 0, leased: 0, done: 0, error: 0 })
 let pollTimer = null
 
@@ -119,8 +142,27 @@ onMounted(async () => {
     if (ml.settings?.ccip_match_threshold != null) {
       threshold.value = ml.settings.ccip_match_threshold
     }
+    if (ml.settings?.ccip_auto_apply_enabled != null) {
+      autoApply.value = ml.settings.ccip_auto_apply_enabled
+      autoThreshold.value = ml.settings.ccip_auto_apply_threshold
+    }
   } catch { /* non-fatal */ }
 })
+
+async function onSaveAuto() {
+  savingAuto.value = true
+  try {
+    await ml.patchSettings({
+      ccip_auto_apply_enabled: autoApply.value,
+      ccip_auto_apply_threshold: autoThreshold.value,
+    })
+    toast({ text: 'Auto-apply settings saved', type: 'success' })
+  } catch (e) {
+    toast({ text: `Could not save: ${e.message}`, type: 'error' })
+  } finally {
+    savingAuto.value = false
+  }
+}
 onUnmounted(() => { if (pollTimer) clearInterval(pollTimer) })
 
 async function onSaveThreshold() {

tests/test_ccip.py

@@ -1,6 +1,7 @@
 """CCIP few-shot character matcher (#114). numpy cosine on stored vectors — no
 model needed, so it runs in CI with synthetic CCIP vectors."""
 import pytest
+from sqlalchemy import select
 
 from backend.app.models import ImageRecord, ImageRegion, TagKind
 from backend.app.models.tag import image_tag
@@ -103,3 +104,40 @@ async def test_threshold_gates_borderline_match(db):
 
     assert any(m["tag_id"] == raven.id for m in await match_image(db, query.id, 0.85))
     assert await match_image(db, query.id, 0.95) == []
+
+
+@pytest.mark.asyncio
+async def test_multi_character_image_not_used_as_reference(db):
+    # A figure on a 2-character image is ambiguous (tag is image-level), so it
+    # must NOT seed either character's prototypes — else it'd match both.
+    raven = await TagService(db).find_or_create("Raven", TagKind.character)
+    daphne = await TagService(db).find_or_create("Daphne", TagKind.character)
+    multi = await _img(db, "j" * 64)
+    await _figure(db, multi.id, _ccip(0))
+    await _tag_image(db, multi.id, raven.id)
+    await _tag_image(db, multi.id, daphne.id)
+    query = await _img(db, "k" * 64)
+    await _figure(db, query.id, _ccip(0))            # identical to the ambiguous figure
+    await db.commit()
+    assert await match_image(db, query.id) == []     # no clean references → nothing
+
+
+@pytest.mark.asyncio
+async def test_auto_apply_tags_confident_match(db):
+    raven = await TagService(db).find_or_create("Raven", TagKind.character)
+    ref = await _img(db, "l" * 64)
+    await _figure(db, ref.id, _ccip(0))
+    await _tag_image(db, ref.id, raven.id)           # single-character reference
+    query = await _img(db, "m" * 64)
+    await _figure(db, query.id, _ccip(0))            # identical → cosine 1.0
+    await db.commit()
+
+    from backend.app.tasks.ml import scheduled_ccip_auto_apply
+    assert "applied=" in scheduled_ccip_auto_apply()   # sync task, own session
+
+    rows = (await db.execute(
+        select(image_tag.c.tag_id, image_tag.c.source).where(
+            image_tag.c.image_record_id == query.id
+        )
+    )).all()
+    assert (raven.id, "ccip_auto") in [(t, s) for t, s in rows]