refactor(ml): drop dead tagger/suggestion settings + columns (#1199)

Hygiene follow-up to the Camie retirement (#1189) — these were left inert to
bound that change; nothing reads them now. Migration 0068 drops:
- ml_settings: tagger_store_floor, tagger_model_version, suggestion_threshold_
  character/general (already dead pre-retirement — scoring uses per-head
  thresholds), video_min_tag_frames (only the deleted video-prediction
  aggregator used it).
- image_record: tagger_model_version (no writer), centroid_scores (dead JSON
  cache, no reader).

Also: ml_admin _EDITABLE/GET/_validate pruned (dropped the store-floor invariant
+ video_min_tag_frames check); MLThresholdSliders trimmed to a video-embedding
card (interval + max frames only); importer no longer resets the dropped cols;
download_models drops the Camie fetch; stale CASCADE comments in cleanup_service
no longer name the removed tables. Tests updated.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa

alembic/versions/0068_drop_dead_tagger_settings.py

@@ -0,0 +1,80 @@
+"""drop dead tagger/suggestion settings + columns left after Camie retirement (#1199)
+
+Hygiene follow-up to #1189. These were left inert to bound that change; nothing
+reads them now:
+- ml_settings: tagger_store_floor + tagger_model_version (only the deleted Camie
+  tagger used them), suggestion_threshold_character/general (already dead pre-
+  retirement — scoring uses per-head thresholds), video_min_tag_frames (only the
+  deleted video-prediction aggregator used it).
+- image_record: tagger_model_version (no writer now), centroid_scores (long-dead
+  JSON cache, no reader).
+
+Revision ID: 0068
+Revises: 0067
+Create Date: 2026-06-30
+"""
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+revision: str = "0068"
+down_revision: Union[str, None] = "0067"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.drop_column("ml_settings", "suggestion_threshold_character")
+    op.drop_column("ml_settings", "suggestion_threshold_general")
+    op.drop_column("ml_settings", "tagger_store_floor")
+    op.drop_column("ml_settings", "video_min_tag_frames")
+    op.drop_column("ml_settings", "tagger_model_version")
+    op.drop_column("image_record", "tagger_model_version")
+    op.drop_column("image_record", "centroid_scores")
+
+
+def downgrade() -> None:
+    op.add_column(
+        "image_record",
+        sa.Column("centroid_scores", sa.JSON(), nullable=True),
+    )
+    op.add_column(
+        "image_record",
+        sa.Column("tagger_model_version", sa.String(length=128), nullable=True),
+    )
+    op.add_column(
+        "ml_settings",
+        sa.Column(
+            "tagger_model_version", sa.String(length=128), nullable=False,
+            server_default="camie-tagger-v2",
+        ),
+    )
+    op.add_column(
+        "ml_settings",
+        sa.Column(
+            "video_min_tag_frames", sa.Integer(), nullable=False,
+            server_default="3",
+        ),
+    )
+    op.add_column(
+        "ml_settings",
+        sa.Column(
+            "tagger_store_floor", sa.Float(), nullable=False,
+            server_default="0.7",
+        ),
+    )
+    op.add_column(
+        "ml_settings",
+        sa.Column(
+            "suggestion_threshold_general", sa.Float(), nullable=False,
+            server_default="0.7",
+        ),
+    )
+    op.add_column(
+        "ml_settings",
+        sa.Column(
+            "suggestion_threshold_character", sa.Float(), nullable=False,
+            server_default="0.7",
+        ),
+    )

backend/app/api/ml_admin.py

@@ -9,12 +9,8 @@ ml_admin_bp = Blueprint("ml_admin", __name__, url_prefix="/api/ml")
 
 
 _EDITABLE = (
-    "suggestion_threshold_character",
-    "suggestion_threshold_general",
-    "tagger_store_floor",
     "video_frame_interval_seconds",
     "video_max_frames",
-    "video_min_tag_frames",
     "head_min_positives",
     "head_auto_apply_precision",
     "head_auto_apply_enabled",
@@ -37,13 +33,8 @@ async def get_settings():
         ).scalar_one()
     return jsonify(
         {
-            "suggestion_threshold_character": s.suggestion_threshold_character,
-            "suggestion_threshold_general": s.suggestion_threshold_general,
-            "tagger_store_floor": s.tagger_store_floor,
             "video_frame_interval_seconds": s.video_frame_interval_seconds,
             "video_max_frames": s.video_max_frames,
-            "video_min_tag_frames": s.video_min_tag_frames,
-            "tagger_model_version": s.tagger_model_version,
             "embedder_model_version": s.embedder_model_version,
             "head_min_positives": s.head_min_positives,
             "head_auto_apply_precision": s.head_auto_apply_precision,
@@ -88,31 +79,12 @@ async def patch_settings():
 
 
 def _validate(p: dict) -> str | None:
-    """Returns an error string if the proposed settings are invalid, else None.
+    """Returns an error string if the proposed settings are invalid, else None."""
-
+    # Video embedding (#747).
-    Invariant (plan-task #764): the per-category suggestion thresholds can't
-    drop below tagger_store_floor — nothing below the floor is stored, so a
-    lower threshold would silently surface nothing in that gap. The UI clamps
-    the sliders to the floor; this is the server-side backstop.
-    """
-    floor = p["tagger_store_floor"]
-    if not (0.0 <= floor <= 1.0):
-        return "tagger_store_floor must be between 0 and 1"
-    for cat in ("character", "general"):
-        if p[f"suggestion_threshold_{cat}"] < floor:
-            return (
-                f"suggestion_threshold_{cat} cannot be below tagger_store_floor "
-                f"({floor}) — predictions below the floor are not stored"
-            )
-    # Video tagging (#747).
     if p["video_frame_interval_seconds"] <= 0:
         return "video_frame_interval_seconds must be > 0"
     if p["video_max_frames"] < 1:
         return "video_max_frames must be >= 1"
-    if p["video_min_tag_frames"] < 1:
-        return "video_min_tag_frames must be >= 1"
-    if p["video_min_tag_frames"] > p["video_max_frames"]:
-        return "video_min_tag_frames cannot exceed video_max_frames"
     # Head training (#114).
     if int(p["head_min_positives"]) < 1:
         return "head_min_positives must be >= 1"

backend/app/models/image_record.py

@@ -9,7 +9,6 @@ from datetime import datetime
 
 from pgvector.sqlalchemy import Vector
 from sqlalchemy import (
-    JSON,
     BigInteger,
     DateTime,
     Enum,
@@ -77,19 +76,13 @@ class ImageRecord(Base):
         ForeignKey("artist.id", ondelete="SET NULL"), nullable=True, index=True
     )
 
-    # ML fields (populated by FC-2's ml-worker). Per-tag predictions live in the
+    # ML fields (populated by the ml-worker / GPU agent). 1152 = SigLIP-so400m
-    # normalized image_prediction table (#768) — the tagger_predictions JSON
+    # embedding dim; siglip_model_version stamps which model produced it (so an
-    # column was dropped in migration 0046. tagger_model_version stays as the
+    # operator model swap, #1190, can re-embed the stale rows). A different-dim
-    # "has this been tagged / is it current?" signal the backfill sweep reads.
+    # model would need a column-width migration.
-    tagger_model_version: Mapped[str | None] = mapped_column(String(128), nullable=True)
-    # 1152 = SigLIP-so400m embedding dim. Swapping models in FC-2 may require
-    # a column-width migration.
     siglip_embedding: Mapped[list[float] | None] = mapped_column(Vector(1152), nullable=True)
     siglip_model_version: Mapped[str | None] = mapped_column(String(128), nullable=True)
 
-    # Centroid score cache (populated post-tagging)
-    centroid_scores: Mapped[dict | None] = mapped_column(JSON, nullable=True)
-
     created_at: Mapped[datetime] = mapped_column(
         DateTime(timezone=True), nullable=False, server_default=func.now()
     )

backend/app/models/ml_settings.py

@@ -23,39 +23,16 @@ class MLSettings(Base):
     __table_args__ = (CheckConstraint("id = 1", name="singleton"),)
 
     id: Mapped[int] = mapped_column(Integer, primary_key=True)
-    suggestion_threshold_character: Mapped[float] = mapped_column(
+    # Video embedding (#747). Sample one frame every N seconds (fixed CADENCE, not
-        Float, nullable=False, default=0.70
+    # a fixed count) so coverage reflects real screen time regardless of length;
-    )
+    # cap the total so a long video can't explode into hundreds of embeds. The
-    # Default raised 0.50 → 0.70 on 2026-06-02 — operator-flagged 0.50
+    # per-frame SigLIP embeddings are mean-pooled. Operator-tunable.
-    # surfaced too many low-confidence picks; 0.70 keeps the rail
-    # signal-rich while still surfacing more than the original 0.95
-    # which hid almost everything. Operator-tunable via Settings → ML.
-    suggestion_threshold_general: Mapped[float] = mapped_column(
-        Float, nullable=False, default=0.70
-    )
-    # Ingest floor: tagger predictions below this confidence are not stored
-    # (tagger.Tagger.infer). Default 0.70 — the suggestion path already filters
-    # there, so the sub-0.70 tail is redundant weight (it had bloated
-    # image_record's TOAST to ~100 GB; plan-task #764). Operator-tunable via
-    # Settings → ML; must stay ≤ the suggestion thresholds.
-    tagger_store_floor: Mapped[float] = mapped_column(
-        Float, nullable=False, default=0.70
-    )
-    # Video tagging (#747). Sample one frame every N seconds (fixed CADENCE, not a
-    # fixed count) so a tag's frame-presence reflects real screen time regardless
-    # of video length; cap the total so a long video can't explode into hundreds
-    # of inferences (the cadence stretches past the cap). A tag is kept only if it
-    # appears in >= video_min_tag_frames sampled frames (≈ that many × interval
-    # seconds on screen) — duration-independent noise rejection. Operator-tunable.
     video_frame_interval_seconds: Mapped[float] = mapped_column(
         Float, nullable=False, default=4.0
     )
     video_max_frames: Mapped[int] = mapped_column(
         Integer, nullable=False, default=64
     )
-    video_min_tag_frames: Mapped[int] = mapped_column(
-        Integer, nullable=False, default=3
-    )
     # Tagging-v2 head training (#114). The head is the suggestion source that
     # LEARNS from the operator's tags (replacing Camie + centroid). A concept
     # needs >= head_min_positives labelled images before a head is trained;
@@ -94,9 +71,6 @@ class MLSettings(Base):
     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"
-    )
     embedder_model_version: Mapped[str] = mapped_column(
         String(128), nullable=False, default="siglip-so400m-patch14-384"
     )

backend/app/scripts/download_models.py

@@ -7,7 +7,6 @@ import sys
 from pathlib import Path
 
 MODEL_ROOT = Path(os.environ.get("ML_MODEL_DIR", "/models"))
-CAMIE_REPO = os.environ.get("CAMIE_HF_REPO", "Camais03/camie-tagger-v2")
 SIGLIP_REPO = os.environ.get(
     "SIGLIP_HF_REPO", "google/siglip-so400m-patch14-384"
 )
@@ -24,34 +23,6 @@ def _snapshot(repo_id: str, dest: Path, allow_patterns: list[str] | None) -> Non
     )
 
 
-def ensure_camie() -> None:
-    """Fetch Camie v2 weights + metadata.
-
-    v2 layout (HuggingFace Camais03/camie-tagger-v2): the ONNX file is
-    named camie-tagger-v2.onnx (not model.onnx) and tags ship inside
-    camie-tagger-v2-metadata.json (not selected_tags.csv). Both at root.
-    The repo also contains app/, game/, training/, images/ subdirs full
-    of setup/demo files we don't need — allow_patterns scopes the fetch
-    to just the inference essentials (~790 MB instead of ~2 GB).
-    """
-    dest = MODEL_ROOT / "camie"
-    model_file = dest / "camie-tagger-v2.onnx"
-    meta_file = dest / "camie-tagger-v2-metadata.json"
-    if model_file.is_file() and meta_file.is_file():
-        print(f"[download_models] Camie present at {dest}")
-        return
-    print(f"[download_models] Fetching {CAMIE_REPO} -> {dest}")
-    _snapshot(
-        CAMIE_REPO, dest,
-        [
-            "camie-tagger-v2.onnx",
-            "camie-tagger-v2-metadata.json",
-            "config.json",
-            "config.yaml",
-        ],
-    )
-
-
 def ensure_siglip() -> None:
     dest = MODEL_ROOT / "siglip"
     if (dest / "config.json").is_file() and any(dest.glob("*.safetensors")):
@@ -62,7 +33,6 @@ def ensure_siglip() -> None:
 
 
 def main() -> int:
-    ensure_camie()
     ensure_siglip()
     print("[download_models] Done.")
     return 0

backend/app/services/cleanup_service.py

@@ -395,9 +395,8 @@ def delete_images(
 def delete_tag(session: Session, *, tag_id: int) -> dict:
     """Simple DELETE FROM tag WHERE id=?.
 
-    Postgres cascades the rest (image_tag, tag_alias, tag_allowlist,
+    Postgres cascades the rest (image_tag, tag_alias, tag_suggestion_rejection,
-    tag_reference_embedding, tag_suggestion_rejection, series_page).
+    series_page). Returns counts BEFORE delete so the caller can surface them.
-    Returns counts BEFORE delete so the caller can surface them.
     Raises LookupError if tag_id not found.
     """
     tag = session.get(Tag, tag_id)
@@ -742,8 +741,7 @@ def purge_legacy_tags(session: Session, *, dry_run: bool = False) -> dict:
     artist-kind tags PLUS general tags whose name matches a legacy
     prefix (source:*).
 
-    CASCADE on image_tag / tag_alias / tag_allowlist /
+    CASCADE on image_tag / tag_alias / tag_suggestion_rejection / series_page
-    tag_reference_embedding / tag_suggestion_rejection / series_page
     clears the related rows on the parent DELETE.
 
     Returns:
@@ -785,23 +783,21 @@ def purge_legacy_tags(session: Session, *, dry_run: bool = False) -> dict:
     return result
 
 
-# The Camie-suggestable CONTENT vocabulary. "Reset content tagging" wipes
+# The CONTENT vocabulary. "Reset content tagging" wipes these so the operator
-# these so the operator can re-tag from scratch via auto-suggest. fandom +
+# can re-tag from scratch. fandom + series (and series_page ordering) are
-# series (and series_page ordering) are deliberately NOT here — they're kept.
+# deliberately NOT here — they're kept.
 RESETTABLE_TAG_KINDS = ("general", "character")
 
 
 def reset_content_tagging(session: Session, *, dry_run: bool = False) -> dict:
     """Count (dry_run) or DELETE every general + character tag so the operator
-    can re-tag from scratch via the Camie auto-suggest.
+    can re-tag from scratch (heads/CCIP repopulate suggestions).
 
-    PRESERVED: fandom + series tags and their series_page ordering, plus every
+    PRESERVED: fandom + series tags and their series_page ordering. CASCADE on
-    image's image_prediction rows (untouched) so suggestions
+    image_tag / tag_alias / tag_suggestion_rejection clears each deleted tag's
-    repopulate immediately. CASCADE on image_tag / tag_alias / tag_allowlist /
+    applications + metadata. Tag.fandom_id is SET NULL, so deleting character
-    tag_reference_embedding / tag_suggestion_rejection clears each deleted
+    tags never touches the fandom rows. Irreversible except via DB backup
-    tag's applications + metadata. Tag.fandom_id is SET NULL, so deleting
+    restore.
-    character tags never touches the fandom rows. Irreversible except via DB
-    backup restore.
 
     Returns:
       {"by_kind": {"general": N, "character": M},

backend/app/services/importer.py

@@ -1475,10 +1475,8 @@ class Importer:
         existing.duration_seconds = duration  # #871: keep the kept copy's duration
         existing.thumbnail_path = None
         existing.integrity_status = "unknown"
-        existing.tagger_model_version = None
         existing.siglip_embedding = None
         existing.siglip_model_version = None
-        existing.centroid_scores = None
         # created_at intentionally preserved; updated_at auto-bumps.
         self.session.flush()
         self.session.commit()

frontend/src/components/settings/MLThresholdSliders.vue

@@ -1,69 +1,30 @@
 <template>
   <MaintenanceTile
-    icon="mdi-tune"
+    icon="mdi-filmstrip"
-    title="Suggestion thresholds"
+    title="Video embedding"
-    blurb="Confidence cutoffs that gate auto-suggested tags + video sampling."
+    blurb="How videos are sampled into frames before embedding."
   >
     <div v-if="store.settings">
-      <v-row v-for="f in fields" :key="f.key">
-        <v-col cols="12">
-          <v-slider
-            v-model="local[f.key]" :label="f.label"
-            :min="f.floorMin ? local.tagger_store_floor : 0" max="1" step="0.05"
-            thumb-label hide-details
-            color="accent" @end="save"
-          />
-        </v-col>
-      </v-row>
-
-      <v-divider class="my-4" />
-
-      <v-row>
-        <v-col cols="12">
-          <v-slider
-            v-model="local.tagger_store_floor" label="Tagger store floor"
-            min="0" max="1" step="0.05" thumb-label hide-details
-            color="accent" @end="save"
-          />
-          <div class="text-caption fc-muted mt-1">
-            Tagger predictions below this confidence aren't stored — raising it
-            keeps the image library lean. Suggestions can't be shown below the
-            floor.
-          </div>
-        </v-col>
-      </v-row>
-
-      <v-divider class="my-4" />
-
-      <div class="text-subtitle-2 mb-1">Video tagging</div>
       <div class="text-caption fc-muted mb-3">
-        Videos are tagged by sampling frames at a fixed cadence. A tag is kept
+        Videos are embedded by sampling frames at a fixed cadence and mean-pooling
-        only if it shows up in enough frames (≈ that many × the interval in
+        their SigLIP embeddings. The interval sets the cadence; the cap bounds how
-        seconds of screen time), which filters one-frame noise without losing
+        many frames a long video samples.
-        tags that only appear in part of a longer video.
       </div>
       <v-row>
-        <v-col cols="12" sm="4">
+        <v-col cols="12" sm="6">
           <v-text-field
             v-model.number="local.video_frame_interval_seconds"
             label="Frame interval (s)" type="number" min="0.5" step="0.5"
             density="comfortable" hide-details @change="save"
           />
         </v-col>
-        <v-col cols="12" sm="4">
+        <v-col cols="12" sm="6">
           <v-text-field
             v-model.number="local.video_max_frames"
             label="Max frames" type="number" min="1" step="1"
             density="comfortable" hide-details @change="save"
           />
         </v-col>
-        <v-col cols="12" sm="4">
-          <v-text-field
-            v-model.number="local.video_min_tag_frames"
-            label="Min frames per tag" type="number" min="1" step="1"
-            density="comfortable" hide-details @change="save"
-          />
-        </v-col>
       </v-row>
     </div>
     <div v-else><v-skeleton-loader type="paragraph" /></div>
@@ -77,31 +38,14 @@ import { useMLStore } from '../../stores/ml.js'
 import MaintenanceTile from '../common/MaintenanceTile.vue'
 
 const store = useMLStore()
-// 'artist' (FC-2d-vii-c) and 'copyright' (2026-06-01) retired as
-// suggestion categories; their threshold rows are gone.
-// floorMin: the per-category suggestion thresholds can't drop below the
-// tagger store floor (nothing below the floor is stored to surface).
-const fields = [
-  { key: 'suggestion_threshold_character', label: 'Character', floorMin: true },
-  { key: 'suggestion_threshold_general', label: 'General', floorMin: true }
-]
 const local = reactive({})
 watch(() => store.settings, (s) => { if (s) Object.assign(local, s) }, { immediate: true })
 
 async function save() {
-  // Mirror the server invariant: keep the category thresholds at or above the
+  const patch = {
-  // store floor so a raised floor doesn't leave a threshold stranded below it.
+    video_frame_interval_seconds: local.video_frame_interval_seconds,
-  const floor = local.tagger_store_floor
+    video_max_frames: local.video_max_frames
-  local.suggestion_threshold_character = Math.max(local.suggestion_threshold_character, floor)
+  }
-  local.suggestion_threshold_general = Math.max(local.suggestion_threshold_general, floor)
-  // Mirror the server invariant: a tag can't require more frames than are sampled.
-  local.video_min_tag_frames = Math.min(local.video_min_tag_frames, local.video_max_frames)
-  const patch = {}
-  for (const f of fields) patch[f.key] = local[f.key]
-  patch.tagger_store_floor = local.tagger_store_floor
-  patch.video_frame_interval_seconds = local.video_frame_interval_seconds
-  patch.video_max_frames = local.video_max_frames
-  patch.video_min_tag_frames = local.video_min_tag_frames
   try { await store.patchSettings(patch) }
   catch (e) { toast({ text: e.message, type: 'error' }) }
 }

tests/test_api_ml_admin.py

@@ -19,19 +19,18 @@ async def test_get_and_patch_settings(client):
     resp = await client.get("/api/ml/settings")
     assert resp.status_code == 200
     body = await resp.get_json()
-    # Default raised 0.50 → 0.70 on 2026-06-02 (alembic 0033) — 0.50
+    assert body["head_min_positives"] == 8
-    # was too noisy in practice. The 0.70 default keeps the rail
+    # Retired tagger/suggestion-threshold columns are gone from the payload
-    # signal-rich without hiding everything like the original 0.95.
+    # (Camie retirement #1189/#1199).
-    assert body["suggestion_threshold_general"] == pytest.approx(0.70)
+    assert "suggestion_threshold_general" not in body
-    # Retired threshold columns must not appear in the payload.
+    assert "tagger_store_floor" not in body
-    assert "suggestion_threshold_artist" not in body
+    assert "tagger_model_version" not in body
-    assert "suggestion_threshold_copyright" not in body
 
     resp = await client.patch(
-        "/api/ml/settings", json={"suggestion_threshold_general": 0.90}
+        "/api/ml/settings", json={"head_min_positives": 12}
     )
     assert resp.status_code == 200
-    assert (await resp.get_json())["suggestion_threshold_general"] == pytest.approx(0.90)
+    assert (await resp.get_json())["head_min_positives"] == 12
 
 
 @pytest.mark.asyncio
@@ -55,55 +54,29 @@ async def test_embedder_model_settable_and_empty_rejected(client):
 
 
 @pytest.mark.asyncio
-async def test_tagger_store_floor_default_and_patch(client):
+async def test_video_settings_default_and_patch(client):
-    body = await (await client.get("/api/ml/settings")).get_json()
+    """#747: video frame-sampling knobs are exposed + patchable."""
-    assert body["tagger_store_floor"] == pytest.approx(0.70)
-
-    resp = await client.patch("/api/ml/settings", json={"tagger_store_floor": 0.6})
-    assert resp.status_code == 200
-    assert (await resp.get_json())["tagger_store_floor"] == pytest.approx(0.6)
-
-
-@pytest.mark.asyncio
-async def test_suggestion_threshold_below_store_floor_rejected(client):
-    # Invariant (#764): a category threshold can't sit below the store floor —
-    # nothing below the floor is stored, so the gap would surface nothing.
-    # Floor defaults to 0.70; pushing general down to 0.50 must 400.
-    resp = await client.patch(
-        "/api/ml/settings", json={"suggestion_threshold_general": 0.50}
-    )
-    assert resp.status_code == 400
-    assert "tagger_store_floor" in (await resp.get_json())["error"]
-
-
-@pytest.mark.asyncio
-async def test_video_tagging_settings_default_and_patch(client):
-    """#747: video cadence/noise knobs are exposed + patchable."""
     body = await (await client.get("/api/ml/settings")).get_json()
     assert body["video_frame_interval_seconds"] == pytest.approx(4.0)
     assert body["video_max_frames"] == 64
-    assert body["video_min_tag_frames"] == 3
 
     resp = await client.patch(
         "/api/ml/settings",
-        json={"video_frame_interval_seconds": 5, "video_max_frames": 40,
+        json={"video_frame_interval_seconds": 5, "video_max_frames": 40},
-              "video_min_tag_frames": 4},
     )
     assert resp.status_code == 200
     out = await resp.get_json()
     assert out["video_frame_interval_seconds"] == pytest.approx(5.0)
     assert out["video_max_frames"] == 40
-    assert out["video_min_tag_frames"] == 4
 
 
 @pytest.mark.asyncio
-async def test_video_min_tag_frames_above_max_rejected(client):
+async def test_video_max_frames_below_one_rejected(client):
     resp = await client.patch(
-        "/api/ml/settings",
+        "/api/ml/settings", json={"video_max_frames": 0},
-        json={"video_max_frames": 10, "video_min_tag_frames": 20},
     )
     assert resp.status_code == 400
-    assert "video_min_tag_frames" in (await resp.get_json())["error"]
+    assert "video_max_frames" in (await resp.get_json())["error"]
 
 
 @pytest.mark.asyncio

tests/test_download_models.py

@@ -1,6 +1,6 @@
 """download_models tests. No network in CI; we test the 'already present →
-skip' short-circuit by faking the expected files, and that main() wires
+skip' short-circuit by faking the expected files, and that main() wires the
-both ensure_* calls.
+SigLIP fetch. (Camie download retired with the tagger, #1199.)
 """
 
 from unittest.mock import patch
@@ -8,29 +8,6 @@ from unittest.mock import patch
 from backend.app.scripts import download_models as dm
 
 
-def test_ensure_camie_skips_when_present(tmp_path, monkeypatch):
-    """v2 layout (HF Camais03/camie-tagger-v2): the ONNX file is named
-    camie-tagger-v2.onnx (not model.onnx) and tags ship inside
-    camie-tagger-v2-metadata.json (not selected_tags.csv). Both at root.
-    Updated 2026-05-25 after the actual repo layout was confirmed via
-    WebFetch — the old assertion pinned the v1 filenames."""
-    monkeypatch.setattr(dm, "MODEL_ROOT", tmp_path)
-    camie = tmp_path / "camie"
-    camie.mkdir(parents=True)
-    (camie / "camie-tagger-v2.onnx").write_bytes(b"x")
-    (camie / "camie-tagger-v2-metadata.json").write_text("{}")
-    with patch.object(dm, "_snapshot") as snap:
-        dm.ensure_camie()
-        snap.assert_not_called()
-
-
-def test_ensure_camie_downloads_when_missing(tmp_path, monkeypatch):
-    monkeypatch.setattr(dm, "MODEL_ROOT", tmp_path)
-    with patch.object(dm, "_snapshot") as snap:
-        dm.ensure_camie()
-        snap.assert_called_once()
-
-
 def test_ensure_siglip_skips_when_present(tmp_path, monkeypatch):
     monkeypatch.setattr(dm, "MODEL_ROOT", tmp_path)
     sig = tmp_path / "siglip"
@@ -42,9 +19,15 @@ def test_ensure_siglip_skips_when_present(tmp_path, monkeypatch):
         snap.assert_not_called()
 
 
-def test_main_calls_both(monkeypatch):
+def test_ensure_siglip_downloads_when_missing(tmp_path, monkeypatch):
+    monkeypatch.setattr(dm, "MODEL_ROOT", tmp_path)
+    with patch.object(dm, "_snapshot") as snap:
+        dm.ensure_siglip()
+        snap.assert_called_once()
+
+
+def test_main_fetches_siglip(monkeypatch):
     calls = []
-    monkeypatch.setattr(dm, "ensure_camie", lambda: calls.append("camie"))
     monkeypatch.setattr(dm, "ensure_siglip", lambda: calls.append("siglip"))
     assert dm.main() == 0
-    assert calls == ["camie", "siglip"]
+    assert calls == ["siglip"]

tests/test_migration_0003.py

@@ -20,12 +20,15 @@ def test_new_tables_registered():
 
 def test_image_record_columns_renamed():
     cols = {c.name for c in ImageRecord.__table__.columns}
-    # tagger_predictions (the renamed wd14_predictions) was later dropped in
+    # Legacy tagger columns are all gone: tagger_predictions/wd14_* dropped in
-    # migration 0046 — predictions live in image_prediction now (#768).
+    # 0046, tagger_model_version + centroid_scores dropped in 0068 (#1199, Camie
-    assert "tagger_model_version" in cols
+    # retirement). The SigLIP embedding columns are the live ML fields.
+    assert "siglip_embedding" in cols
+    assert "siglip_model_version" in cols
+    assert "tagger_model_version" not in cols
+    assert "centroid_scores" not in cols
     assert "tagger_predictions" not in cols
     assert "wd14_predictions" not in cols
-    assert "wd14_model_version" not in cols
 
 
 def test_tag_alias_composite_pk():