refactor(ui): settings-card primitives + fix threshold clamp / card misgroup (#161)

Tier-3 frontend DRY for the ML settings cards, plus the F-D2 clamp bug and the
F-D3 card misgrouping.

New primitives (components/common + composables):
- <SettingToggleRow> — the accent-icon + .fc-section-h label + right-aligned
  switch row (HeadsCard x3, CropProposersCard). iconColor prop absorbs the
  on/off dim.
- <SettingNumberField> — compact numeric field that CLAMPS to [min,max] on
  commit. This fixes F-D2: HeadsCard/CropProposersCard previously sent
  Number(raw) straight to the API, so an out-of-range threshold bounced off the
  400 validator (only TranslationCard clamped). density prop for the grid cards.
- useSettingSave(patchFn) — the busy + patch + toast + revert-on-failure flow
  each card hand-rolled (HeadsCard x6 handlers, CropProposersCard, MLBackfillCard,
  VideoEmbeddingCard). Returns ok/false for the optimistic-switch revert.

Adopted in HeadsCard, CropProposersCard, MLBackfillCard (handler only — its
plain labelled switch is a different affordance), VideoEmbeddingCard.

F-D3: MLThresholdSliders.vue actually rendered a "Video embedding" (frame-
sampling) card but sat under "Tagging → Suggestion thresholds". Renamed it
VideoEmbeddingCard.vue and moved it to the "GPU agent & embeddings" section.

Left deliberately (over-DRY guard): TranslationCard uses an inline error ALERT
(not a toast), already clamps its confidence with a NaN fallback, and lives on
the ImportStore — a genuinely different save pattern, so forcing it onto
useSettingSave would change its UX.

Behaviour-preserving refactor; CI has no Vue type-check so this needs a live
UI pass (toggles persist + revert on failure, thresholds clamp on blur, video
card now under Embeddings).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NsmJSQxnNxGgtM5Yz4GAqi

.forgejo/workflows/ci.yml

@@ -9,10 +9,15 @@ name: CI
 on:
   push:
     branches: [dev, main]
-  # pull_request trigger intentionally absent — with branches: [dev, main]
-  # above, every PR commit already fires CI via the push event on dev. Adding
-  # pull_request would duplicate runs on dev→main PRs. FC has no fork PRs
-  # (single-operator Forgejo repo) so push coverage is complete.
+  # Renovate opens PRs from `renovate/*` branches into `dev`. Those branches
+  # never push to dev/main, so the push trigger above gives them NO pre-merge
+  # CI — a bump could only be validated after it was already merged. This
+  # pull_request trigger (base `dev` only) validates Renovate PRs before merge.
+  # It deliberately does NOT fire on dev→main PRs (base `main`), which still
+  # rely on the dev push run — so no duplicate runs. FC has no fork PRs
+  # (single-operator Forgejo repo), so secrets-on-PR is not a concern.
+  pull_request:
+    branches: [dev]
 
 jobs:
   # Fast-fail lint lane. ruff is pre-installed in the ci-python image, so
@@ -92,10 +97,10 @@ jobs:
       # If we want strict lockfile-based reproducibility later, commit a
       # package-lock.json and flip this back to `npm ci`.
       - run: npm install --no-audit --no-fund
-      # `npm run check` (vue-tsc --noEmit) skipped: the frontend is pure JS
-      # with no .ts files and no JSDoc annotations, so vue-tsc has nothing
-      # to type-check. Re-enable once we add a tsconfig.json and either
-      # convert to TS or add JSDoc.
+      # No type-check step: the frontend is pure JS (no .ts files, no JSDoc),
+      # so a type-checker has nothing to do. The vue-tsc devDep + its `check`
+      # script were dropped 2026-07-11 rather than bumped to v3. If we add
+      # TS/JSDoc later, re-add a tsconfig.json + vue-tsc + a type-check step.
       - run: npm run test:unit
       - run: npm run build
 

.forgejo/workflows/extension.yml

@@ -20,7 +20,7 @@ jobs:
   lint:
     runs-on: python-ci
     container:
-      image: node:22-bookworm-slim
+      image: node:24-bookworm-slim
     steps:
       - uses: actions/checkout@v4
       - name: Install web-ext

Dockerfile

@@ -1,6 +1,6 @@
-# syntax=docker/dockerfile:1.7
+# syntax=docker/dockerfile:1.25
 
-FROM node:22-alpine AS frontend-builder
+FROM node:24-alpine AS frontend-builder
 WORKDIR /build
 COPY frontend/package.json frontend/package-lock.json* ./
 # No package-lock.json is tracked yet (we don't run npm locally per

Dockerfile.ml

@@ -1,4 +1,4 @@
-# syntax=docker/dockerfile:1.7
+# syntax=docker/dockerfile:1.25
 
 FROM python:3.14-slim
 ENV PYTHONUNBUFFERED=1 \

alembic/versions/0084_translation_strictness_override.py

@@ -0,0 +1,51 @@
+"""translation strictness setting + per-post translation override (milestone 155)
+
+ImportSettings gains ``translation_min_confidence`` (the latin-script acceptance
+floor, now operator-tunable in the UI; default 0.9 — stricter than the old
+hardcoded 0.8, since Interpreter confidently mis-detects short ASCII English at
+~0.86). Post gains ``translation_override`` — a sticky per-post choice of
+auto / force / original so the operator can force a skipped translation on, or
+knock a wrongly-translated one back to the original, and have it survive a
+Re-translate-all.
+
+Revision ID: 0084
+Revises: 0083
+Create Date: 2026-07-10
+"""
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+revision: str = "0084"
+down_revision: Union[str, None] = "0083"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "import_settings",
+        sa.Column(
+            "translation_min_confidence", sa.Float(), nullable=False,
+            server_default=sa.text("0.9"),
+        ),
+    )
+    op.add_column(
+        "post",
+        sa.Column(
+            "translation_override", sa.String(16), nullable=False,
+            server_default="auto",
+        ),
+    )
+    op.create_check_constraint(
+        "ck_post_translation_override",
+        "post",
+        "translation_override IN ('auto', 'force', 'original')",
+    )
+
+
+def downgrade() -> None:
+    op.drop_constraint("ck_post_translation_override", "post", type_="check")
+    op.drop_column("post", "translation_override")
+    op.drop_column("import_settings", "translation_min_confidence")

alembic/versions/0085_wip_title_tagging.py

@@ -0,0 +1,35 @@
+"""title-based WIP auto-tagging (task #1458) — ImportSettings toggle
+
+ImportSettings gains wip_title_tagging_enabled (ON by default): when a freshly
+imported post's title explicitly declares work-in-progress ("WIP" / "work in
+progress"), the importer applies the `wip` system tag to its images. No new
+table — the tag itself is the seeded `wip` system tag (migration 0075) and the
+application reuses image_tag with source='wip_title'.
+
+Revision ID: 0085
+Revises: 0084
+Create Date: 2026-07-12
+"""
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+revision: str = "0085"
+down_revision: Union[str, None] = "0084"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "import_settings",
+        sa.Column(
+            "wip_title_tagging_enabled", sa.Boolean(), nullable=False,
+            server_default=sa.text("true"),
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("import_settings", "wip_title_tagging_enabled")

alembic/versions/0086_process_auto_apply_settings.py

@@ -0,0 +1,61 @@
+"""process auto-apply settings + review mode (#1464) — system-tag refactor
+
+The system-tag behavior refactor gives `wip` / `editor screenshot` (the PROCESS
+group) their own provisional auto-apply, parallel to the presentation (chrome)
+sweep. MLSettings gains three knobs: enabled (OFF by default — a new whole-library
+auto-tagger is opt-in), the flat apply threshold, and the ring-loud conflict
+threshold. presentation_review gains a `mode` column so one review surface serves
+both chrome and process flags (existing rows backfill 'chrome'). server_defaults
+so the existing rows fill cleanly.
+
+Revision ID: 0086
+Revises: 0085
+Create Date: 2026-07-13
+"""
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+revision: str = "0086"
+down_revision: Union[str, None] = "0085"
+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(
+            "process_auto_apply_enabled", sa.Boolean(), nullable=False,
+            server_default=sa.text("false"),
+        ),
+    )
+    op.add_column(
+        "ml_settings",
+        sa.Column(
+            "process_auto_apply_threshold", sa.Float(), nullable=False,
+            server_default="0.90",
+        ),
+    )
+    op.add_column(
+        "ml_settings",
+        sa.Column(
+            "process_conflict_threshold", sa.Float(), nullable=False,
+            server_default="0.50",
+        ),
+    )
+    op.add_column(
+        "presentation_review",
+        sa.Column(
+            "mode", sa.String(16), nullable=False,
+            server_default="chrome",
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("presentation_review", "mode")
+    op.drop_column("ml_settings", "process_conflict_threshold")
+    op.drop_column("ml_settings", "process_auto_apply_threshold")
+    op.drop_column("ml_settings", "process_auto_apply_enabled")

alembic/versions/0087_wip_soft_title_tagging.py

@@ -0,0 +1,33 @@
+"""soft WIP title tier toggle (#1474) — ImportSettings.wip_soft_title_tagging_enabled
+
+The soft tier also tags sketch/doodle/scribble titles, but with a provisional source
+that never trains the head. OFF by default (a lower-precision tier is opt-in).
+server_default so the existing singleton row (id=1) fills cleanly.
+
+Revision ID: 0087
+Revises: 0086
+Create Date: 2026-07-13
+"""
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+revision: str = "0087"
+down_revision: Union[str, None] = "0086"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "import_settings",
+        sa.Column(
+            "wip_soft_title_tagging_enabled", sa.Boolean(), nullable=False,
+            server_default=sa.text("false"),
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("import_settings", "wip_soft_title_tagging_enabled")

backend/app/api/gallery.py

@@ -145,6 +145,20 @@ async def similar():
         filters, _sort = _parse_filters()
     except (KeyError, ValueError):
         return jsonify({"error": "similar_to query param required"}), 400
+    # Explore passes exclude_wip=1 to also drop work-in-progress from the
+    # rabbit-hole; the gallery's own "similar" button omits it (keeps wip, #1274).
+    exclude_wip = request.args.get("exclude_wip") in ("1", "true", "True")
+    # Explore reach (#1476): 0 = nearest (gallery default), →1 reaches into farther
+    # distance bands so the walk can escape a dense cluster. exclude_ids = the
+    # breadcrumb, so already-walked images aren't re-served as neighbours.
+    try:
+        reach = max(0.0, min(1.0, float(request.args.get("reach", "0"))))
+    except ValueError:
+        reach = 0.0
+    exclude_ids = [
+        int(x) for x in request.args.get("exclude_ids", "").split(",")
+        if x.strip().isdigit()
+    ] or None
     # post_id is the exclusive post-detail view — not a similarity scope.
     # include_hidden is a gallery-browse flag; similar() has its OWN presentation
     # exclusion (a similarity-quality concern, #1274), so drop it here (#141).
@@ -154,7 +168,9 @@ async def similar():
     async with get_session() as session:
         svc = GalleryService(session)
         try:
-            images = await svc.similar(image_id=similar_to, limit=limit, **scope)
+            images = await svc.similar(
+                image_id=similar_to, limit=limit, exclude_wip=exclude_wip,
+                reach=reach, exclude_ids=exclude_ids, **scope)
         except ValueError as exc:
             return jsonify({"error": str(exc)}), 400
     if images is None:
@@ -232,8 +248,10 @@ async def jump():
 #    content", surfaced in the gallery's Show-hidden review strip. -----------
 @gallery_bp.route("/hidden-review", methods=["GET"])
 async def hidden_review():
-    """Unresolved presentation auto-hide flags, most-concerning first (highest
-    content score) — for the gallery's Hidden-view review strip."""
+    """Unresolved system-tag auto-apply review flags (chrome + process, #1464),
+    most-concerning first (highest content score) — for the review strip. `mode`
+    tells the client whether the flagged tag hid the image ('chrome') or left it
+    visible ('process'), which decides the resolve labels (un-hide vs remove-tag)."""
     ptag = aliased(Tag)
     ctag = aliased(Tag)
     async with get_session() as session:
@@ -243,6 +261,7 @@ async def hidden_review():
                 PresentationReview.tag_id,
                 PresentationReview.conflict_tag_id,
                 PresentationReview.conflict_score,
+                PresentationReview.mode,
                 ImageRecord.path, ImageRecord.thumbnail_path,
                 ImageRecord.sha256, ImageRecord.mime,
                 ptag.name.label("tag_name"),
@@ -262,6 +281,7 @@ async def hidden_review():
             "conflict_tag_id": r.conflict_tag_id,
             "conflict_name": r.conflict_name,
             "conflict_score": r.conflict_score,
+            "mode": r.mode,
             "thumbnail_url": thumbnail_url(r.thumbnail_path, r.sha256, r.mime),
             "image_url": image_url(r.path),
         }

backend/app/api/gpu.py

@@ -256,9 +256,7 @@ async def lease():
         if not await _agent_authed(session):
             return jsonify({"error": "unauthorized"}), 401
         jobs = await GpuJobService(session).lease(agent_id, batch_size=batch)
-        ml = (
-            await session.execute(select(MLSettings).where(MLSettings.id == 1))
-        ).scalar_one()
+        ml = await MLSettings.load(session)
         # image rows for url/mime in one shot
         ids = [j.image_record_id for j in jobs]
         imgs = {

backend/app/api/ml_admin.py

@@ -4,6 +4,7 @@ from quart import Blueprint, jsonify, request
 
 from ..extensions import get_session
 from ..models import MLSettings
+from ..services.ml.heads import AUTO_APPLY_THRESHOLD_MAX, AUTO_APPLY_THRESHOLD_MIN
 
 ml_admin_bp = Blueprint("ml_admin", __name__, url_prefix="/api/ml")
 
@@ -42,6 +43,9 @@ _EDITABLE = (
     "presentation_auto_apply_enabled",
     "presentation_auto_apply_threshold",
     "presentation_conflict_threshold",
+    "process_auto_apply_enabled",
+    "process_auto_apply_threshold",
+    "process_conflict_threshold",
     "embedder_model_name",
     "embedder_model_version",
     *_DETECTOR_FIELDS,
@@ -80,45 +84,21 @@ async def embedder_models():
 
 @ml_admin_bp.route("/settings", methods=["GET"])
 async def get_settings():
-    from sqlalchemy import select
-
     async with get_session() as session:
-        s = (
-            await session.execute(select(MLSettings).where(MLSettings.id == 1))
-        ).scalar_one()
-    return jsonify(
-        {
-            "cpu_embed_enabled": s.cpu_embed_enabled,
-            "video_frame_interval_seconds": s.video_frame_interval_seconds,
-            "video_max_frames": s.video_max_frames,
-            "embedder_model_version": s.embedder_model_version,
-            "head_min_positives": s.head_min_positives,
-            "head_auto_apply_precision": s.head_auto_apply_precision,
-            "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,
-            "presentation_auto_apply_enabled": s.presentation_auto_apply_enabled,
-            "presentation_auto_apply_threshold": s.presentation_auto_apply_threshold,
-            "presentation_conflict_threshold": s.presentation_conflict_threshold,
-            "embedder_model_name": s.embedder_model_name,
-            **{f: getattr(s, f) for f in _DETECTOR_FIELDS},
-        }
-    )
+        s = await MLSettings.load(session)
+    # Table-driven off _EDITABLE (which PATCH also writes) so a new settings field
+    # can never be silently absent from GET — the split that historically dropped
+    # fields. _EDITABLE already includes *_DETECTOR_FIELDS.
+    return jsonify({f: getattr(s, f) for f in _EDITABLE})
 
 
 @ml_admin_bp.route("/settings", methods=["PATCH"])
 async def patch_settings():
-    from sqlalchemy import select
-
     body = await request.get_json()
     if not isinstance(body, dict):
         return jsonify({"error": "body must be an object"}), 400
     async with get_session() as session:
-        s = (
-            await session.execute(select(MLSettings).where(MLSettings.id == 1))
-        ).scalar_one()
+        s = await MLSettings.load(session)
 
         # Merge the patch over current values, then validate the result as a
         # whole — the store-floor invariant couples three fields, so they
@@ -148,20 +128,26 @@ def _validate(p: dict) -> str | None:
     # Head training (#114).
     if int(p["head_min_positives"]) < 1:
         return "head_min_positives must be >= 1"
-    if not (0.5 <= float(p["head_auto_apply_precision"]) <= 0.999):
-        return "head_auto_apply_precision must be between 0.5 and 0.999"
+    if not (AUTO_APPLY_THRESHOLD_MIN <= float(p["head_auto_apply_precision"]) <= AUTO_APPLY_THRESHOLD_MAX):
+        return f"head_auto_apply_precision must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
     if int(p["head_auto_apply_min_positives"]) < 1:
         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"
+    if not (AUTO_APPLY_THRESHOLD_MIN <= float(p["ccip_match_threshold"]) <= AUTO_APPLY_THRESHOLD_MAX):
+        return f"ccip_match_threshold must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
+    if not (AUTO_APPLY_THRESHOLD_MIN <= float(p["ccip_auto_apply_threshold"]) <= AUTO_APPLY_THRESHOLD_MAX):
+        return f"ccip_auto_apply_threshold must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
     # Presentation chrome auto-hide (#141). Auto-apply runs high (hiding is
     # consequential); the conflict cut is a plain probability [0,1].
-    if not (0.5 <= float(p["presentation_auto_apply_threshold"]) <= 0.999):
-        return "presentation_auto_apply_threshold must be between 0.5 and 0.999"
+    if not (AUTO_APPLY_THRESHOLD_MIN <= float(p["presentation_auto_apply_threshold"]) <= AUTO_APPLY_THRESHOLD_MAX):
+        return f"presentation_auto_apply_threshold must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
     if not (0.0 <= float(p["presentation_conflict_threshold"]) <= 1.0):
         return "presentation_conflict_threshold must be between 0 and 1"
+    # Process auto-apply (#1464). wip/editor stay VISIBLE so a false apply is
+    # low-harm (excludes-from-training + a review flag), but keep the same bar.
+    if not (AUTO_APPLY_THRESHOLD_MIN <= float(p["process_auto_apply_threshold"]) <= AUTO_APPLY_THRESHOLD_MAX):
+        return f"process_auto_apply_threshold must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
+    if not (0.0 <= float(p["process_conflict_threshold"]) <= 1.0):
+        return "process_conflict_threshold must be between 0 and 1"
     # Embedder model swap (#1190): both must be non-empty. Changing them means a
     # different embedding space — the operator must re-embed + retrain after.
     for key in ("embedder_model_name", "embedder_model_version"):

backend/app/api/posts.py

@@ -3,12 +3,28 @@
 from quart import Blueprint, jsonify, request
 
 from ..extensions import get_session
+from ..models import ImportSettings, Post
+from ..services import interpreter_client as ic
 from ..services.post_feed_service import PostFeedService
 from ..services.source_service import KNOWN_PLATFORMS
+from ..utils.text import html_to_plain
 from ._responses import error_response as _bad
 
 posts_bp = Blueprint("posts", __name__, url_prefix="/api/posts")
 
+_TRANSLATION_OVERRIDES = ("auto", "force", "original")
+
+
+def _queue_for_sweep(post: Post) -> None:
+    """Mark a post untranslated (all translation columns NULL) so the periodic
+    sweep re-runs it under its new override — used when Interpreter is down and we
+    can't translate inline."""
+    post.post_title_translated = None
+    post.description_translated = None
+    post.translated_source_lang = None
+    post.translation_engine_version = None
+    post.translated_at = None
+
 
 @posts_bp.route("", methods=["GET"])
 async def list_posts():
@@ -82,3 +98,70 @@ async def get_post(post_id: int):
     if item is None:
         return _bad("not_found", status=404, detail=f"post id={post_id}")
     return jsonify(item)
+
+
+@posts_bp.route("/<int:post_id>/translation-override", methods=["POST"])
+async def set_translation_override(post_id: int):
+    """Sticky per-post translation override (milestone 155). Body:
+    ``{"override": "auto" | "force" | "original"}``.
+
+    'original' keeps the original (clears any stored translation now — no
+    Interpreter needed). 'force'/'auto' translate the post immediately if the
+    service is up (force bypasses the acceptance floor; auto re-runs the gate);
+    if it's down we save the flag and mark the post untranslated so the next sweep
+    applies it. The override persists, so the sweep + Re-translate-all keep
+    honoring it. Returns the updated translation fields + an ``applied`` status."""
+    body = await request.get_json(silent=True) or {}
+    override = body.get("override")
+    if override not in _TRANSLATION_OVERRIDES:
+        return _bad(
+            "invalid_override",
+            detail=f"override must be one of {list(_TRANSLATION_OVERRIDES)}",
+        )
+
+    # Lazy import (mirrors settings.py) so the API module doesn't pull the celery
+    # task graph at import time.
+    from ..tasks.translation import _store_translation, _translate_field
+
+    async with get_session() as session:
+        post = await session.get(Post, post_id)
+        if post is None:
+            return _bad("not_found", status=404, detail=f"post id={post_id}")
+        post.translation_override = override
+        cfg = await ImportSettings.load(session)
+        target = (cfg.translation_target_lang or "en").strip() or "en"
+
+        if override == "original":
+            _store_translation(post, (None, None, None), (None, None, None), target)
+            applied = "cleared"
+        else:
+            base_url = (cfg.interpreter_base_url or "").strip()
+            if cfg.translation_enabled and base_url and ic.health(base_url):
+                force = override == "force"
+                title = (post.post_title or "").strip()
+                desc = (html_to_plain(post.description) if post.description else "") or ""
+                desc = desc.strip()
+                mc = cfg.translation_min_confidence
+                try:
+                    title_res = _translate_field(title, base_url, target, mc, force=force)
+                    desc_res = _translate_field(desc, base_url, target, mc, force=force)
+                except ic.InterpreterUnavailable:
+                    _queue_for_sweep(post)
+                    applied = "queued"
+                else:
+                    _store_translation(post, title_res, desc_res, target)
+                    applied = "translated"
+            else:
+                # Disabled / no URL / unhealthy → let the sweep apply it later.
+                _queue_for_sweep(post)
+                applied = "queued"
+
+        await session.commit()
+        return jsonify({
+            "id": post.id,
+            "translation_override": post.translation_override,
+            "post_title_translated": post.post_title_translated,
+            "description_translated": post.description_translated,
+            "translated_source_lang": post.translated_source_lang,
+            "applied": applied,
+        })

backend/app/api/settings.py

@@ -16,6 +16,7 @@ from ..models import (
     ImportTask,
     Post,
     Tag,
+    TaskRun,
 )
 from ..services import interpreter_client as ic
 
@@ -46,6 +47,9 @@ _EDITABLE_FIELDS = (
     "translation_enabled",
     "interpreter_base_url",
     "translation_target_lang",
+    "translation_min_confidence",
+    "wip_title_tagging_enabled",
+    "wip_soft_title_tagging_enabled",
 )
 
 # Per-host external-download toggles — all plain booleans, validated uniformly.
@@ -62,31 +66,9 @@ _EXTDL_TOGGLE_FIELDS = (
 async def get_import_settings():
     async with get_session() as session:
         row = await ImportSettings.load(session)
-    return jsonify({
-        "min_width": row.min_width,
-        "min_height": row.min_height,
-        "skip_transparent": row.skip_transparent,
-        "transparency_threshold": row.transparency_threshold,
-        "skip_single_color": row.skip_single_color,
-        "single_color_threshold": row.single_color_threshold,
-        "single_color_tolerance": row.single_color_tolerance,
-        "phash_threshold": row.phash_threshold,
-        "download_rate_limit_seconds": row.download_rate_limit_seconds,
-        "download_validate_files": row.download_validate_files,
-        "download_schedule_default_seconds": row.download_schedule_default_seconds,
-        "download_event_retention_days": row.download_event_retention_days,
-        "download_failure_warning_threshold": row.download_failure_warning_threshold,
-        "series_suggest_enabled": row.series_suggest_enabled,
-        "series_suggest_threshold": row.series_suggest_threshold,
-        "extdl_mega_enabled": row.extdl_mega_enabled,
-        "extdl_gdrive_enabled": row.extdl_gdrive_enabled,
-        "extdl_mediafire_enabled": row.extdl_mediafire_enabled,
-        "extdl_dropbox_enabled": row.extdl_dropbox_enabled,
-        "extdl_pixeldrain_enabled": row.extdl_pixeldrain_enabled,
-        "translation_enabled": row.translation_enabled,
-        "interpreter_base_url": row.interpreter_base_url,
-        "translation_target_lang": row.translation_target_lang,
-    })
+    # Table-driven off _EDITABLE_FIELDS (which PATCH also writes) so a new field
+    # can't be silently absent from GET.
+    return jsonify({f: getattr(row, f) for f in _EDITABLE_FIELDS})
 
 
 @settings_bp.route("/settings/import", methods=["PATCH"])
@@ -154,12 +136,32 @@ async def update_import_settings():
     for key in ("interpreter_base_url", "translation_target_lang"):
         if key in body and not isinstance(body[key], str):
             return jsonify({"error": f"{key} must be a string"}), 400
+    # Acceptance floor (milestone 155): latin-script translations below this
+    # Interpreter confidence are kept as the original.
+    if "translation_min_confidence" in body:
+        v = body["translation_min_confidence"]
+        if not isinstance(v, (int, float)) or isinstance(v, bool) or v < 0 or v > 1:
+            return jsonify(
+                {"error": "translation_min_confidence must be a number in [0, 1]"}
+            ), 400
     if "series_suggest_threshold" in body:
         v = body["series_suggest_threshold"]
         if not isinstance(v, (int, float)) or isinstance(v, bool) or v < 0 or v > 1:
             return jsonify(
                 {"error": "series_suggest_threshold must be a number in [0, 1]"}
             ), 400
+    if "wip_title_tagging_enabled" in body and not isinstance(
+        body["wip_title_tagging_enabled"], bool
+    ):
+        return jsonify(
+            {"error": "wip_title_tagging_enabled must be a boolean"}
+        ), 400
+    if "wip_soft_title_tagging_enabled" in body and not isinstance(
+        body["wip_soft_title_tagging_enabled"], bool
+    ):
+        return jsonify(
+            {"error": "wip_soft_title_tagging_enabled must be a boolean"}
+        ), 400
 
     async with get_session() as session:
         row = await ImportSettings.load(session)
@@ -171,6 +173,18 @@ async def update_import_settings():
     return await get_import_settings()
 
 
+@settings_bp.route("/settings/wip-title/scan", methods=["POST"])
+async def wip_title_scan():
+    """Enqueue the back-catalogue WIP-title scan (task #1458 Settings button):
+    apply the `wip` system tag to EXISTING posts whose title declares
+    work-in-progress. New imports are tagged live by the importer; this catches
+    the existing library. Returns the Celery task id (202)."""
+    from ..tasks.maintenance import backfill_wip_title_tags
+
+    r = backfill_wip_title_tags.delay()
+    return jsonify({"celery_task_id": r.id}), 202
+
+
 @settings_bp.route("/system/stats", methods=["GET"])
 async def system_stats():
     async with get_session() as session:
@@ -306,6 +320,10 @@ async def translation_status():
     """For the Settings card: is it on, is a URL set, is the service reachable,
     and how many posts still await translation. Health runs the sync client in a
     thread so the event loop isn't blocked."""
+    translation_tasks = (
+        "backend.app.tasks.translation.translate_posts",
+        "backend.app.tasks.translation.retranslate_posts",
+    )
     async with get_session() as session:
         cfg = await ImportSettings.load(session)
         untranslated = (await session.execute(
@@ -315,6 +333,21 @@ async def translation_status():
                 Post.post_title.is_not(None), Post.description.is_not(None),
             ))
         )).scalar_one()
+        # Live progress: is a sweep running now, and what did the last one do?
+        # (run-until-done re-enqueues itself, so `active` stays true across a
+        # bulk re-translate; `last_run` surfaces a completed run's outcome.)
+        active = (await session.execute(
+            select(func.count(TaskRun.id))
+            .where(TaskRun.task_name.in_(translation_tasks))
+            .where(TaskRun.status == "running")
+        )).scalar_one()
+        last = (await session.execute(
+            select(TaskRun.task_name, TaskRun.status, TaskRun.finished_at)
+            .where(TaskRun.task_name.in_(translation_tasks))
+            .where(TaskRun.finished_at.is_not(None))
+            .order_by(TaskRun.finished_at.desc())
+            .limit(1)
+        )).first()
     base_url = (cfg.interpreter_base_url or "").strip()
     healthy = await asyncio.to_thread(ic.health, base_url) if base_url else False
     return jsonify({
@@ -322,6 +355,12 @@ async def translation_status():
         "base_url_set": bool(base_url),
         "healthy": healthy,
         "untranslated_count": int(untranslated),
+        "active": int(active) > 0,
+        "last_run": {
+            "task": last[0].rsplit(".", 1)[-1],
+            "status": last[1],
+            "finished_at": last[2].isoformat() if last[2] else None,
+        } if last else None,
     })
 
 
@@ -338,9 +377,49 @@ async def translation_test():
     return jsonify({"healthy": healthy})
 
 
+@settings_bp.route("/settings/translation/probe", methods=["POST"])
+async def translation_probe():
+    """Diagnostic for the Settings 'Test translation' box: translate a pasted
+    snippet WITHOUT saving anything, returning what Interpreter *detected*
+    (language + confidence) alongside the result. Lets the operator see why a
+    given string was (mis-)detected — e.g. a short English title flagged as
+    another language — so a detection guard can be tuned from real numbers.
+    Read-only: no post is touched. Uses the currently-saved base URL + target."""
+    body = await request.get_json(silent=True)
+    body = body if isinstance(body, dict) else {}
+    text = (body.get("text") or "").strip()
+    if not text:
+        return jsonify({"error": "provide text to translate"}), 400
+    async with get_session() as session:
+        cfg = await ImportSettings.load(session)
+    base_url = (cfg.interpreter_base_url or "").strip()
+    if not base_url:
+        return jsonify({"error": "no Interpreter base URL is set"}), 400
+    target = (cfg.translation_target_lang or "en").strip() or "en"
+    try:
+        res = await asyncio.to_thread(
+            ic.translate, [text], base_url=base_url, target=target,
+        )
+    except ic.InterpreterUnavailable as e:
+        return jsonify({"error": f"Interpreter unavailable: {e}"}), 503
+    except ic.InterpreterBadRequest as e:
+        return jsonify({"error": f"Interpreter rejected the request: {e}"}), 400
+    translations = res.get("translations") or []
+    return jsonify({
+        "target": target,
+        "detected_lang": res.get("detected_lang"),
+        "detected_confidence": res.get("detected_confidence"),
+        "engine": res.get("engine"),
+        "engine_version": res.get("engine_version"),
+        "translated": translations[0] if translations else None,
+    })
+
+
 @settings_bp.route("/settings/translation/run", methods=["POST"])
 async def translation_run():
-    """Enqueue the translate sweep now (the Settings 'Translate now' button)."""
+    """Enqueue the translate sweep now (the Settings 'Translate now' button).
+    Runs in drain mode — run-until-done — so one press chases the whole
+    untranslated backlog to zero rather than a single 300-post chunk."""
     async with get_session() as session:
         cfg = await ImportSettings.load(session)
     if not cfg.translation_enabled or not (cfg.interpreter_base_url or "").strip():
@@ -349,5 +428,41 @@ async def translation_run():
         ), 400
     from ..tasks.translation import translate_posts
 
-    r = translate_posts.delay()
+    r = translate_posts.delay(drain=True)
+    return jsonify({"celery_task_id": r.id}), 202
+
+
+@settings_bp.route("/settings/translation/retranslate", methods=["POST"])
+async def translation_retranslate():
+    """Re-translate stored translations after a model change (m146). Body:
+    ``{"artist_id": <int>}`` aims at one artist; ``{"all": true}`` re-runs every
+    artist. ``all`` must be explicit so an empty/typo body can't wipe everything.
+    Clears the scoped translations and enqueues the run-until-done retranslate
+    sweep (the Interpreter cache re-translates on a changed model, is cache-fast
+    otherwise). Same enabled + base-URL guard as 'Translate now'."""
+    body = await request.get_json(silent=True)
+    body = body if isinstance(body, dict) else {}
+    artist_id = body.get("artist_id")
+    do_all = bool(body.get("all"))
+    if artist_id is None and not do_all:
+        return jsonify(
+            {"error": "provide artist_id, or all=true to re-translate everything"}
+        ), 400
+    if artist_id is not None:
+        try:
+            artist_id = int(artist_id)
+        except (TypeError, ValueError):
+            return jsonify({"error": "artist_id must be an integer"}), 400
+
+    async with get_session() as session:
+        cfg = await ImportSettings.load(session)
+    if not cfg.translation_enabled or not (cfg.interpreter_base_url or "").strip():
+        return jsonify(
+            {"error": "translation is disabled or no base URL is set"}
+        ), 400
+    from ..tasks.translation import retranslate_posts
+
+    # artist_id wins when both are sent; otherwise all=true → None (every artist).
+    artist_ids = [artist_id] if artist_id is not None else None
+    r = retranslate_posts.delay(artist_ids=artist_ids)
     return jsonify({"celery_task_id": r.id}), 202

backend/app/api/suggestions.py

@@ -11,10 +11,11 @@ suggestions_bp = Blueprint("suggestions", __name__, url_prefix="/api")
 
 @suggestions_bp.route("/images/<int:image_id>/suggestions", methods=["GET"])
 async def get_suggestions(image_id: int):
-    # ?min=<float> overrides the configured per-category thresholds so the typed
-    # tag-input dropdown can surface EVERY stored prediction (min=0), including
-    # low-confidence actions/features, in canonical formatting. Omitted → the
-    # curated above-threshold list the Suggestions panel uses.
+    # ?min=<float> overrides the per-head suggest thresholds for INCLUSION. The
+    # rail sends min=0 in its single per-image fetch to get EVERY head (each row
+    # still carries above_threshold vs its natural cut), then derives the panel
+    # (above_threshold) and the typed dropdown (all, filtered by text) client-side
+    # — no second request. Omitted → only above-threshold rows.
     override = None
     raw_min = request.args.get("min")
     if raw_min is not None:
@@ -36,12 +37,11 @@ async def get_suggestions(image_id: int):
                         "category": s.category,
                         "score": round(s.score, 4),
                         "source": s.source,
-                        "creates_new_tag": s.creates_new_tag,
-                        # raw model key (alias is stored under this) + whether an
-                        # operator alias produced this suggestion — drive the
-                        # modal's "Treat as alias"/"Remove alias" affordances.
-                        "raw_name": s.raw_name,
-                        "via_alias": s.via_alias,
+                        # whether the score cleared the head's own suggest cut.
+                        # The single min=0 fetch returns every head; the panel
+                        # shows above_threshold, the typed dropdown shows all and
+                        # annotates each match with its score.
+                        "above_threshold": s.above_threshold,
                         # operator dismissed this tag for this image — surfaced
                         # (not dropped) so the rail can show it rejected + offer
                         # one-click un-reject.
@@ -73,26 +73,6 @@ async def accept_suggestion(image_id: int):
     return jsonify({"accepted": True, "tag_id": tag_id})
 
 
-@suggestions_bp.route(
-    "/images/<int:image_id>/suggestions/alias", methods=["POST"]
-)
-async def alias_suggestion(image_id: int):
-    body = await request.get_json()
-    required = {"alias_string", "alias_category", "canonical_tag_id"}
-    if not body or not required.issubset(body):
-        return jsonify({"error": f"required: {sorted(required)}"}), 400
-    canonical_tag_id = body["canonical_tag_id"]
-    async with get_session() as session:
-        await AllowlistService(session).add_alias_and_accept(
-            image_id,
-            body["alias_string"],
-            body["alias_category"],
-            canonical_tag_id,
-        )
-        await session.commit()
-    return jsonify({"accepted": True, "tag_id": canonical_tag_id})
-
-
 @suggestions_bp.route(
     "/images/<int:image_id>/suggestions/dismiss", methods=["POST"]
 )

backend/app/celery_app.py

@@ -70,6 +70,14 @@ def make_celery() -> Celery:
         },
         # Heavy ML tasks need fair dispatch — see ImageRepo's precedent.
         task_acks_late=True,
+        # Deploy graceful-shutdown safety: with acks_late, a task killed because
+        # it outran the container's stop-grace window (SIGKILL) is re-queued
+        # rather than silently lost. Safe because our long tasks are idempotent +
+        # chunked (translation per-post commit, downloads terminal-status, audits
+        # chunk) and the 5-min recovery sweeps re-drive anything left non-terminal
+        # — a re-run resumes cleanly and never corrupts. No redeliver-loop risk:
+        # heavy GPU work is tombstoned via gpu_queue, not run inline in a worker.
+        task_reject_on_worker_lost=True,
         worker_prefetch_multiplier=1,
         # Broker resilience (2026-06-24): a swarm overlay-network blip after a
         # redeploy left Redis healthy but transiently unreachable, and a worker
@@ -107,6 +115,11 @@ def make_celery() -> Celery:
                 "task": "backend.app.tasks.maintenance.cleanup_old_tasks",
                 "schedule": 86400.0,  # daily
             },
+            "cleanup-orphaned-temp-files": {
+                "task": "backend.app.tasks.maintenance.cleanup_orphaned_temp_files",
+                "schedule": 86400.0,  # daily — sweep .part/.partial left by a
+                # download/import killed mid-write (graceful-shutdown fallout)
+            },
             "train-heads-nightly": {
                 "task": "backend.app.tasks.ml.scheduled_train_heads",
                 "schedule": 86400.0,  # passive cadence; manual retrain stays available
@@ -158,16 +171,30 @@ def make_celery() -> Celery:
             },
             "presentation-auto-apply-daily": {
                 "task": "backend.app.tasks.ml.scheduled_presentation_auto_apply",
-                "schedule": 86400.0,  # auto-hide banner/editor chrome (#141);
+                "schedule": 86400.0,  # auto-hide banner chrome (#141);
                 # no-op unless presentation_auto_apply_enabled
             },
+            "process-auto-apply-daily": {
+                "task": "backend.app.tasks.ml.scheduled_process_auto_apply",
+                "schedule": 86400.0,  # auto-tag wip/editor process art (#1464);
+                # no-op unless process_auto_apply_enabled (opt-in)
+            },
+            "soft-wip-conflict-audit-daily": {
+                "task": "backend.app.tasks.ml.scheduled_soft_wip_conflict_audit",
+                "schedule": 86400.0,  # flag ring-loud soft-WIP (sketch/doodle) tags
+                # for review (#1474); no-op with no content heads
+            },
             "prune-presentation-reviews-daily": {
                 "task": "backend.app.tasks.ml.prune_presentation_reviews",
                 "schedule": 86400.0,  # retention: drop resolved review flags >30d
             },
-            "translate-posts-daily": {
+            "translate-posts-8h": {
                 "task": "backend.app.tasks.translation.translate_posts",
-                "schedule": 86400.0,  # no-op unless translation configured + healthy
+                "schedule": 28800.0,  # every 8h: steady-state cadence for the
+                # trickle of newly-imported posts (no-op unless translation
+                # configured + healthy). One bounded 300-chunk per fire — the
+                # one-time backlog drains via the "Translate now" button
+                # (drain=True, run-until-done), not this sweep.
             },
             "snapshot-head-metrics-daily": {
                 "task": "backend.app.tasks.maintenance.snapshot_head_metrics",

backend/app/models/import_settings.py

@@ -106,6 +106,33 @@ class ImportSettings(Base):
     translation_target_lang: Mapped[str] = mapped_column(
         Text, nullable=False, default="en", server_default="en",
     )
+    # The latin-script acceptance floor for the translation gate: a translation
+    # whose Interpreter-reported confidence is below this is kept as the original
+    # (operator-tunable, milestone 155). Default 0.9 — stricter than the old
+    # hardcoded 0.8, because Interpreter confidently mis-detects short ASCII
+    # English (e.g. "… WIP Part 1") as a European language at ~0.86. CJK stays
+    # trusted regardless (script-detected). Per-post overrides handle the misses.
+    translation_min_confidence: Mapped[float] = mapped_column(
+        Float, nullable=False, default=0.9, server_default="0.9",
+    )
+
+    # Title-based WIP auto-tagging (task #1458). When a freshly-imported post's
+    # TITLE explicitly declares work-in-progress ("WIP" / "work in progress"),
+    # the importer applies the `wip` system tag to its images — the artist's own
+    # label, used to keep unfinished pieces out of the Explore/gallery browse. ON
+    # by default (rule 26 — the feature works out of the box). Gates only the
+    # LIVE import hook; the existing catalogue is caught by the operator-triggered
+    # "Scan existing posts" backfill (which runs regardless of this flag).
+    wip_title_tagging_enabled: Mapped[bool] = mapped_column(
+        Boolean, nullable=False, default=True, server_default="true",
+    )
+    # Soft WIP title tier (#1474): also tag sketch/doodle/scribble titles, but with
+    # a PROVISIONAL source (`wip_title_soft`) that never trains the head, since these
+    # are lower-precision (a finished "sketch" isn't WIP). OFF by default — a lower-
+    # precision tier is opt-in (the ring-loud audit surfaces false positives).
+    wip_soft_title_tagging_enabled: Mapped[bool] = mapped_column(
+        Boolean, nullable=False, default=False, server_default="false",
+    )
 
     @classmethod
     async def load(cls, session) -> ImportSettings:

backend/app/models/ml_settings.py

@@ -10,6 +10,7 @@ from sqlalchemy import (
     Integer,
     String,
     func,
+    select,
 )
 from sqlalchemy.orm import Mapped, mapped_column
 
@@ -85,12 +86,14 @@ class MLSettings(Base):
         Float, nullable=False, default=0.95
     )
     # -- Presentation chrome auto-hide (#141) -------------------------------
-    # banner / editor screenshot auto-apply on the sweep with their OWN flat
-    # threshold (decoupled from content-head graduation). Hiding is consequential
-    # so it runs HIGH. `wip` is never auto-applied. When an image would be
-    # auto-hidden but ALSO scores >= presentation_conflict_threshold on a content
-    # head, it's still hidden but flagged for review (PresentationReview) instead
-    # of buried silently. ON by default (opt-out); every auto-tag is reversible.
+    # `banner` (chrome — clusters on UI, not content) auto-applies on the sweep
+    # with its OWN flat threshold (decoupled from content-head graduation) and is
+    # HIDDEN from the gallery. Hiding is consequential so it runs HIGH. When an
+    # image would be auto-hidden but ALSO scores >= presentation_conflict_threshold
+    # on a content head, it's still hidden but flagged for review
+    # (PresentationReview, mode='chrome') instead of buried silently. ON by default
+    # (opt-out); every auto-tag is reversible. NOTE (#1464): `wip` + `editor
+    # screenshot` are no longer chrome — they went to the PROCESS path below.
     presentation_auto_apply_enabled: Mapped[bool] = mapped_column(
         Boolean, nullable=False, default=True
     )
@@ -100,6 +103,26 @@ class MLSettings(Base):
     presentation_conflict_threshold: Mapped[float] = mapped_column(
         Float, nullable=False, default=0.50
     )
+    # -- Process auto-apply (#1464) ----------------------------------------
+    # `wip` / `editor screenshot` are PROCESS art — unfinished pieces + program
+    # screenshots that must stay OUT of head/CCIP training but, unlike chrome,
+    # remain VISIBLE in the gallery (operator 2026-07-12). They auto-apply on the
+    # sweep with their OWN flat threshold and a PROVISIONAL source (`process_auto`,
+    # in training_data._AUTO_SOURCES) so the head NEVER trains on its own output —
+    # it learns only from title (`wip_title`) + manual labels, which breaks the
+    # runaway loop. When a process tag would be applied but the image ALSO scores
+    # >= process_conflict_threshold on a content head, it's flagged for review
+    # (PresentationReview, mode='process') rather than silently marked. OFF by
+    # default — a new whole-library auto-tagger is opt-in; every auto-tag reversible.
+    process_auto_apply_enabled: Mapped[bool] = mapped_column(
+        Boolean, nullable=False, default=False
+    )
+    process_auto_apply_threshold: Mapped[float] = mapped_column(
+        Float, nullable=False, default=0.90
+    )
+    process_conflict_threshold: Mapped[float] = mapped_column(
+        Float, nullable=False, default=0.50
+    )
     # Default = SigLIP 2 (so400m, 512px) for new installs (migration 0069);
     # existing libraries keep their stored value until the operator re-embeds.
     embedder_model_version: Mapped[str] = mapped_column(
@@ -190,3 +213,14 @@ class MLSettings(Base):
     updated_at: Mapped[datetime] = mapped_column(
         DateTime(timezone=True), nullable=False, server_default=func.now()
     )
+
+    @classmethod
+    async def load(cls, session) -> MLSettings:
+        """The singleton settings row (id=1), via an async session. Mirrors
+        ImportSettings.load — the shared singleton-loader pattern."""
+        return (await session.execute(select(cls).where(cls.id == 1))).scalar_one()
+
+    @classmethod
+    def load_sync(cls, session) -> MLSettings:
+        """The singleton settings row (id=1), via a sync session."""
+        return session.execute(select(cls).where(cls.id == 1)).scalar_one()

backend/app/models/post.py

@@ -8,7 +8,17 @@ artist-filter queries don't depend on the Source detour).
 
 from datetime import datetime
 
-from sqlalchemy import JSON, DateTime, ForeignKey, Integer, String, Text, UniqueConstraint, func
+from sqlalchemy import (
+    JSON,
+    CheckConstraint,
+    DateTime,
+    ForeignKey,
+    Integer,
+    String,
+    Text,
+    UniqueConstraint,
+    func,
+)
 from sqlalchemy.orm import Mapped, mapped_column
 
 from .base import Base
@@ -23,6 +33,10 @@ class Post(Base):
         # (created in alembic 0030) covers that case via
         # (artist_id, external_post_id).
         UniqueConstraint("source_id", "external_post_id", name="uq_post_source_external_id"),
+        CheckConstraint(
+            "translation_override IN ('auto', 'force', 'original')",
+            name="ck_post_translation_override",
+        ),
     )
 
     id: Mapped[int] = mapped_column(Integer, primary_key=True)
@@ -64,6 +78,16 @@ class Post(Base):
     translated_at: Mapped[datetime | None] = mapped_column(
         DateTime(timezone=True), nullable=True
     )
+    # Sticky per-post override of the translation decision (milestone 155):
+    # 'auto' = the acceptance gate decides; 'force' = always store Interpreter's
+    # translation even below the confidence floor (rescue a skipped legit-foreign
+    # title); 'original' = never translate, keep the original (kill a confidently
+    # mis-flagged one the floor can't catch). The sweep reads this on every run,
+    # and re-translate leaves 'original' posts alone, so the choice survives a
+    # Re-translate-all.
+    translation_override: Mapped[str] = mapped_column(
+        String(16), nullable=False, default="auto", server_default="auto",
+    )
 
     downloaded_at: Mapped[datetime] = mapped_column(
         DateTime(timezone=True), nullable=False, server_default=func.now()

backend/app/models/presentation_review.py

@@ -1,15 +1,17 @@
-"""PresentationReview — an auto-hidden presentation tag that ALSO looked like
-real content, flagged for operator review (milestone 141).
+"""PresentationReview — a system-tag the auto-apply sweep applied that ALSO looked
+like real content, flagged for operator review (milestone 141 + #1464).
 
-When the auto-apply sweep hides an image as chrome (banner / editor screenshot)
-but the image ALSO scores highly on a content head, it still hides it but records
-this row so the Hidden view can surface it ("⚠ also looks like <conflict tag>")
-for a keep-hidden / un-hide decision. Resolved rows are pruned by retention.
+When a sweep applies a system tag but the image ALSO scores highly on a content
+head, it still applies the tag but records this row so a review strip can surface
+it ("⚠ also looks like <conflict tag>"). Two modes (#1464): 'chrome' (banner —
+image is HIDDEN, review is keep-hidden / un-hide) and 'process' (wip / editor
+screenshot — image stays VISIBLE, review is confirm / remove-tag). Resolved rows
+are pruned by retention.
 """
 
 from datetime import datetime
 
-from sqlalchemy import DateTime, Float, ForeignKey, func
+from sqlalchemy import DateTime, Float, ForeignKey, String, func
 from sqlalchemy.orm import Mapped, mapped_column
 
 from .base import Base
@@ -31,6 +33,12 @@ class PresentationReview(Base):
         ForeignKey("tag.id", ondelete="SET NULL"), nullable=True
     )
     conflict_score: Mapped[float] = mapped_column(Float, nullable=False)
+    # Which sweep flagged this (#1464): 'chrome' (banner, hidden) or 'process'
+    # (wip / editor screenshot, shown). Drives which review strip surfaces it and
+    # what "resolve" means (un-hide vs remove-tag). Existing rows backfill 'chrome'.
+    mode: Mapped[str] = mapped_column(
+        String(16), nullable=False, default="chrome", server_default="chrome"
+    )
     created_at: Mapped[datetime] = mapped_column(
         DateTime(timezone=True), nullable=False, server_default=func.now()
     )

backend/app/models/tag.py

@@ -43,11 +43,20 @@ class TagKind(StrEnum):
     # to keep historic tag rows queryable.
 
 
-# The seeded system tags (migration 0075). PRESENTATION tags additionally
-# hide from whole-image similarity results — they cluster on UI chrome, not
-# content. `wip` is real art: only the training pipelines exclude it.
+# The seeded system tags (migration 0075). Two behavior groups (#1464):
+#   CHROME (banner): clusters on UI chrome, not content → HIDDEN from the default
+#     gallery + from similarity; auto-applied via the sweep's chrome mode.
+#   PROCESS (wip, editor screenshot): real-but-unfinished art / program screenshots
+#     → SHOWN in the gallery (operator 2026-07-12), but excluded from the Explore
+#     rabbit-hole; auto-applied via the sweep's process mode (provisional source,
+#     ring-loud review guard).
+# ALL three are excluded from OTHER concepts' head/CCIP training (training-hygiene,
+# keyed on is_system); a system tag's OWN head trains on them — that's what makes
+# auto-flagging work.
 SYSTEM_TAG_NAMES = ("wip", "banner", "editor screenshot")
-PRESENTATION_SYSTEM_TAGS = ("banner", "editor screenshot")
+CHROME_SYSTEM_TAGS = ("banner",)
+PROCESS_SYSTEM_TAGS = ("wip", "editor screenshot")
+WIP_SYSTEM_TAG = "wip"
 
 image_tag = Table(
     "image_tag",

backend/app/services/extension_service.py

@@ -35,9 +35,14 @@ class InvalidUrlError(Exception):
 # reviewers catch drift.
 _PLATFORM_PATTERNS: list[tuple[str, re.Pattern[str]]] = [
     ("patreon", re.compile(
+        # Three creator URL shapes — bare (patreon.com/Atole), `c/`, and `cw/`
+        # (the "creator workspace" URL served once subscribed, see
+        # patreon_resolver._VANITY_RE). A trailing sub-path is allowed so a
+        # creator's inner page still derives the slug. Nav pages stay excluded.
         r"^https?://(?:www\.)?patreon\.com/"
-        r"(?!home$|search\b|messages\b|notifications\b|library\b|settings\b|posts\b|c/)"
-        r"(?P<slug>[^/?#]+)/?$",
+        r"(?:cw/|c/)?"
+        r"(?!(?:home|search|messages|notifications|library|settings|posts)(?:[/?#]|$))"
+        r"(?P<slug>[^/?#]+)",
         re.IGNORECASE,
     )),
     ("subscribestar", re.compile(

backend/app/services/gallery_service.py

@@ -31,7 +31,7 @@ from ..models import (
     Tag,
     TagPositiveConfirmation,
 )
-from ..models.tag import PRESENTATION_SYSTEM_TAGS, image_tag
+from ..models.tag import CHROME_SYSTEM_TAGS, PROCESS_SYSTEM_TAGS, image_tag
 from .pagination import decode_cursor, encode_cursor
 from .tag_query import (
     fandom_join_alias,
@@ -396,6 +396,25 @@ def _diversify_similar(src, rows, limit, *, dup_threshold=8, lam=0.40):
     return [kept[i] for i in order]
 
 
+def _reach_sample(rows, limit, reach):
+    """From a distance-sorted candidate pool (nearest first), pick a spread of ranks
+    that MIXES near (tag the current cluster) and mid-far (escape it) BEFORE dedup +
+    MMR — the Explore "reach" dial (#1476).
+
+    reach in (0, 1]: the sampled span grows outward from the anchor (0.25→1.0 of the
+    pool), evenly strided from rank 0 so the nearest are still represented. In a
+    dense signature the nearest ranks are near-identical, so reaching farther is the
+    only way to hand MMR genuinely different content — MMR alone can't escape a pool
+    that's already all-near. reach<=0 or a small pool passes through unchanged."""
+    n = len(rows)
+    want = max(limit * 8, 100)
+    if reach <= 0 or n <= want:
+        return rows
+    span = int(min(1.0, 0.25 + 0.75 * reach) * n)
+    idx = sorted({min(int(i * span / want), n - 1) for i in range(want)})
+    return [rows[i] for i in idx]
+
+
 async def _artists_for(session, image_ids: list[int]) -> dict[int, dict]:
     """Map image_id -> {"name","slug"} via the canonical
     image_record.artist_id (FC-2d-vii-c). Bounded by page size."""
@@ -419,16 +438,17 @@ class GalleryService:
     async def _hidden_tag_ids(
         self, include_hidden, tag_ids, tag_or_groups,
     ) -> list[int] | None:
-        """Presentation-chrome tag ids to implicitly exclude from a gallery query,
-        or None. None when the caller asked to include hidden, when the operator
-        is explicitly filtering FOR a presentation tag (they clearly want to see
-        it), or when no presentation tags exist. (milestone 141)"""
+        """Chrome (banner) tag ids to implicitly exclude from a gallery query, or
+        None. None when the caller asked to include hidden, when the operator is
+        explicitly filtering FOR a chrome tag (they clearly want to see it), or when
+        no chrome tags exist. (milestone 141; #1464: editor screenshot is now PROCESS
+        — shown — so only `banner` hides here.)"""
         if include_hidden:
             return None
         rows = await self.session.execute(
             select(Tag.id).where(
                 Tag.is_system.is_(True),
-                Tag.name.in_(PRESENTATION_SYSTEM_TAGS),
+                Tag.name.in_(CHROME_SYSTEM_TAGS),
             )
         )
         pres = [r[0] for r in rows]
@@ -715,6 +735,8 @@ class GalleryService:
         platform: str | None = None,
         untagged: bool = False, no_artist: bool = False,
         date_from: datetime | None = None, date_to: datetime | None = None,
+        exclude_wip: bool = False,
+        reach: float = 0.0, exclude_ids: list[int] | None = None,
     ) -> list[GalleryImage] | None:
         """Visual "more like this": images near `image_id`'s SigLIP embedding
         (pgvector, HNSW-indexed — alembic 0036), then DIVERSIFIED so the result
@@ -743,22 +765,33 @@ class GalleryService:
         # wide pool there's nothing but the near-dupes to choose from. Widened
         # (5×→8×, cap 200→400) so the stronger MMR has genuinely distinct
         # neighbourhoods to reach into for more variance (operator, 2026-07-01).
-        pool_n = min(400, max(limit * 8, 100))
+        # Explore's reach>0 (#1476) widens it a LOT more: in a dense signature the
+        # nearest few hundred are all near-identical, so far-enough candidates only
+        # exist deeper in the ranked pool. _reach_sample then strides across them.
+        if reach > 0:
+            pool_n = min(1000, max(limit * 25, 100))
+        else:
+            pool_n = min(400, max(limit * 8, 100))
         distance = ImageRecord.siglip_embedding.cosine_distance(src.siglip_embedding)
         eff = _effective_date_col()
         stmt = select(ImageRecord, Post.post_date, eff.label("eff"))
         stmt = _outer_join_primary_post(stmt)
-        # Presentation images (banner / editor-screenshot system tags, #128)
-        # cluster on UI chrome rather than content, so near any one of them
-        # they'd fill the grid. Excluded from CANDIDATES only — the anchor
-        # itself may be a banner, and `wip` stays surfaced (real art; only
-        # the training pipelines exclude it).
+        # Chrome (banner, #128) clusters on UI rather than content, so near any one
+        # of them they'd fill the grid → excluded from CANDIDATES always (the anchor
+        # itself may be a banner). PROCESS art (wip / editor screenshot) stays
+        # surfaced here by default (real content; only the training pipelines exclude
+        # it), but the Explore rabbit-hole passes exclude_wip to also drop the whole
+        # process group so a browse doesn't keep surfacing work-in-progress
+        # (operator, 2026-07-08; #1464 — editor now rides with wip here).
+        excluded_system_tags = CHROME_SYSTEM_TAGS
+        if exclude_wip:
+            excluded_system_tags = (*CHROME_SYSTEM_TAGS, *PROCESS_SYSTEM_TAGS)
         presentation = (
             select(image_tag.c.image_record_id)
             .join(Tag, Tag.id == image_tag.c.tag_id)
             .where(
                 Tag.is_system.is_(True),
-                Tag.name.in_(PRESENTATION_SYSTEM_TAGS),
+                Tag.name.in_(excluded_system_tags),
             )
         )
         stmt = stmt.where(
@@ -766,6 +799,10 @@ class GalleryService:
             ImageRecord.id != image_id,
             ImageRecord.id.not_in(presentation),
         )
+        # Anti-revisit (#1476): the Explore walk passes its breadcrumb so already-
+        # walked images aren't re-served as neighbours — → can't loop you back in.
+        if exclude_ids:
+            stmt = stmt.where(ImageRecord.id.not_in(exclude_ids))
         stmt = _apply_scope(
             stmt, tag_ids=tag_ids, post_id=None,
             artist_id=artist_id, media_type=media_type,
@@ -775,6 +812,10 @@ class GalleryService:
         )
         stmt = stmt.order_by(distance.asc()).limit(pool_n)
         rows = (await self.session.execute(stmt)).all()
+        # Explore reach: stride across an outward-growing distance span so the pool
+        # handed to MMR spans near→mid-far, not just the tight cluster (#1476).
+        if reach > 0:
+            rows = _reach_sample(rows, limit, reach)
         rows = _diversify_similar(src, rows, limit)
         artists = await _artists_for(self.session, [r[0].id for r in rows])
         return _gallery_images(rows, artists)

backend/app/services/importer.py

@@ -47,9 +47,21 @@ from .attachment_store import AttachmentStore
 from .audits import single_color
 from .link_extract import extract_external_links
 from .thumbnailer import Thumbnailer
+from .wip_title import (
+    WIP_TITLE_SOFT_SOURCE,
+    WIP_TITLE_SOURCE,
+    apply_wip_image_tags,
+    matches_soft_wip_title,
+    matches_wip_title,
+    resolve_wip_tag_id,
+)
 
 log = logging.getLogger(__name__)
 
+# Sentinel for the lazily-resolved wip tag id (distinguishes "not resolved yet"
+# from a genuine None = tag absent, so absence is cached and not re-queried).
+_UNSET = object()
+
 
 class SkipReason(StrEnum):
     too_small = "too_small"
@@ -183,6 +195,10 @@ class Importer:
         # invalidated mid-Importer (Importer instances are per-task /
         # per-archive-import so cross-instance staleness is harmless).
         self._phash_candidates: list[tuple] | None = None
+        # Lazily-resolved `wip` system tag id for title-based WIP auto-tagging
+        # (task #1458). Sentinel _UNSET so a genuine None (tag absent) is cached
+        # and not re-queried per media. Importer is per-task, so this can't stale.
+        self._wip_tag_id: int | None = _UNSET
 
     def _phash_candidates_cache(self) -> list[tuple]:
         """Cached `(phash, width, height, id)` rows from image_record.
@@ -933,6 +949,10 @@ class Importer:
         # Thumbnail is queued separately by the calling task; the importer
         # does not generate thumbnails inline so the import queue stays moving.
 
+        # Title-based WIP auto-tag (task #1458): fresh import only, after the
+        # sidecar has linked the post so record.primary_post_id / its title exist.
+        self._maybe_apply_wip_title(record)
+
         self.session.commit()
         return ImportResult(status="imported", image_id=record.id)
 
@@ -976,6 +996,47 @@ class Importer:
         self.session.commit()
         return ImportResult(status="refreshed", image_id=existing.id)
 
+    def _maybe_apply_wip_title(self, record: ImageRecord) -> None:
+        """Auto-apply the `wip` system tag to a FRESHLY-imported image when its
+        primary post's TITLE explicitly declares work-in-progress (task #1458 —
+        the artist's own "WIP" / "work in progress" label).
+
+        Called ONLY from the two new-record paths (never deep-scan / supersede),
+        so a manually-removed WIP tag is never re-applied by a routine re-scan —
+        removal sticks. The existing catalogue is covered separately by the
+        operator-triggered backfill sweep. Gated by the settings toggle, and
+        best-effort: any failure is logged, never allowed to fail the import."""
+        hard_on = self.settings.wip_title_tagging_enabled
+        soft_on = self.settings.wip_soft_title_tagging_enabled
+        if not (hard_on or soft_on):
+            return
+        if record.primary_post_id is None:
+            return
+        try:
+            title = self.session.execute(
+                select(Post.post_title).where(Post.id == record.primary_post_id)
+            ).scalar_one_or_none()
+            # HARD tier ("WIP"/"work in progress") wins — higher precision, and it
+            # trains the head; SOFT (sketch/doodle, #1474) is the provisional fallback
+            # that never trains (source wip_title_soft).
+            if hard_on and matches_wip_title(title):
+                source = WIP_TITLE_SOURCE
+            elif soft_on and matches_soft_wip_title(title):
+                source = WIP_TITLE_SOFT_SOURCE
+            else:
+                return
+            if self._wip_tag_id is _UNSET:
+                self._wip_tag_id = resolve_wip_tag_id(self.session)
+            if self._wip_tag_id is None:
+                return
+            apply_wip_image_tags(
+                self.session, [record.id], self._wip_tag_id, source=source
+            )
+        except Exception as exc:  # noqa: BLE001 — a tag must never fail an import
+            log.warning(
+                "wip-title auto-tag failed for image %s: %s", record.id, exc
+            )
+
     def _apply_post_fields(self, post: Post, sd) -> None:
         """Write a parsed sidecar's post-level fields onto a Post — the SINGLE
         predicate shared by BOTH ingest paths: the per-media path (_apply_sidecar)
@@ -1253,6 +1314,10 @@ class Importer:
         # per-post Source row.
         self._apply_sidecar(record, path, artist, explicit_source=source)
 
+        # Title-based WIP auto-tag (task #1458): fresh import only, see the
+        # matching call in _import_media.
+        self._maybe_apply_wip_title(record)
+
         self.session.commit()
         return ImportResult(status="imported", image_id=record.id)
 

backend/app/services/interpreter_client.py

@@ -8,12 +8,24 @@ behind a reverse proxy). Full API contract: Scribe note #1347.
 """
 from __future__ import annotations
 
+from datetime import UTC, datetime
+from email.utils import parsedate_to_datetime
+
 import requests
+from requests.adapters import HTTPAdapter
+from urllib3.util.retry import Retry
 
 
 class InterpreterUnavailable(Exception):
-    """The translation engine is down / unreachable (HTTP 503 or a connection
-    error) — retry later, don't drop the item."""
+    """The translation engine is down / unreachable / draining — a connection
+    error, HTTP 429, or a 5xx (commonly 502/503/504 through a reverse proxy while
+    the service restarts). Retry later, don't drop the item. ``retry_after`` holds
+    the server's Retry-After hint in seconds when it sent one, so the caller can
+    back off exactly as long as it's asked to."""
+
+    def __init__(self, message: str, *, retry_after: float | None = None):
+        super().__init__(message)
+        self.retry_after = retry_after
 
 
 class InterpreterBadRequest(Exception):
@@ -24,13 +36,52 @@ def _url(base_url: str, path: str) -> str:
     return f"{base_url.rstrip('/')}{path}"
 
 
+def _parse_retry_after(resp) -> float | None:
+    """Parse a Retry-After header (RFC 7231: delta-seconds or an HTTP-date) into
+    non-negative seconds, or None if absent/unparseable — so a gracefully-
+    draining Interpreter can tell Curator exactly how long to wait before it
+    tries again."""
+    raw = (resp.headers.get("Retry-After") or "").strip()
+    if not raw:
+        return None
+    try:
+        return max(0.0, float(int(raw)))       # delta-seconds form
+    except ValueError:
+        pass
+    try:                                        # HTTP-date form
+        when = parsedate_to_datetime(raw)
+    except (TypeError, ValueError):
+        return None
+    if when is None:
+        return None
+    if when.tzinfo is None:
+        when = when.replace(tzinfo=UTC)
+    return max(0.0, (when - datetime.now(UTC)).total_seconds())
+
+
+# A shared session pools the keep-alive connection across the per-post sweep
+# calls, and retries CONNECT failures only (connect=2, short backoff) — smoothing
+# the instant a reverse proxy reloads. Status codes are deliberately NOT retried
+# (status=0, raise_on_status=False): translate() maps 429/5xx → InterpreterUnavailable
+# itself, and letting urllib3 retry a draining 503 would defeat the Retry-After
+# backoff we honour upstream.
+_retry = Retry(
+    total=None, connect=2, read=0, redirect=0, status=0,
+    backoff_factor=0.3, raise_on_status=False,
+)
+session = requests.Session()
+_adapter = HTTPAdapter(max_retries=_retry)
+session.mount("http://", _adapter)
+session.mount("https://", _adapter)
+
+
 def health(base_url: str, *, timeout: float = 5.0) -> bool:
     """True iff the Interpreter LLM engine is up. Any error (unset URL, network,
     non-200, engine down) → False, so the sweep just no-ops rather than raising."""
     if not base_url:
         return False
     try:
-        r = requests.get(_url(base_url, "/v1/health"), timeout=timeout)
+        r = session.get(_url(base_url, "/v1/health"), timeout=timeout)
     except requests.RequestException:
         return False
     if r.status_code != 200:
@@ -45,22 +96,25 @@ def translate(
 ) -> dict:
     """Translate a batch. Returns::
 
-        {"translations": [str, ...],   # SAME order & length as `texts`
-         "detected_lang": str | None,  # aggregate: describes the FIRST item
+        {"translations": [str, ...],        # SAME order & length as `texts`
+         "detected_lang": str | None,       # aggregate: describes the FIRST item
+         "detected_confidence": float | None,  # detector's confidence, if given
          "engine": str | None,
          "engine_version": str | None}
 
     Interpreter batch metadata is aggregate (first item only) — fine for one
     post's ``[title, description]`` batch since they share a language. Passthrough
     items (already target-language / emoji-only) come back UNCHANGED in their
-    slot. Raises InterpreterUnavailable on 503 / connection error (retry later),
-    InterpreterBadRequest on 400. (Scribe note #1347.)
+    slot. Raises InterpreterUnavailable on a connection error / 429 / 5xx (retry
+    later, honouring Retry-After), InterpreterBadRequest on 400. (Scribe note
+    #1347.)
     """
     if not texts:
         return {"translations": [], "detected_lang": None,
+                "detected_confidence": None,
                 "engine": None, "engine_version": None}
     try:
-        r = requests.post(
+        r = session.post(
             _url(base_url, "/v1/translate"),
             json={"q": list(texts), "source": source,
                   "target": target, "engine": "auto"},
@@ -68,10 +122,18 @@ def translate(
         )
     except requests.RequestException as e:
         raise InterpreterUnavailable(str(e)) from e
-    if r.status_code == 503:
-        raise InterpreterUnavailable("interpreter engine unavailable")
     if r.status_code == 400:
         raise InterpreterBadRequest((r.json() or {}).get("error", "bad request"))
+    # A gracefully-draining service — often behind a reverse proxy — returns 429
+    # or a 5xx gateway error (502/503/504), not always a clean 503. Treat every
+    # one as "unavailable, retry later" and honour any Retry-After it sends, so a
+    # rolling Interpreter restart interrupts the sweep cleanly (instead of raising
+    # an opaque HTTPError) and resumes exactly when the service says it's ready.
+    if r.status_code == 429 or r.status_code >= 500:
+        raise InterpreterUnavailable(
+            f"interpreter unavailable (HTTP {r.status_code})",
+            retry_after=_parse_retry_after(r),
+        )
     r.raise_for_status()
     body = r.json() or {}
     out = body.get("translatedText")
@@ -80,9 +142,11 @@ def translate(
     if not isinstance(out, list):
         out = [out]
     interp = body.get("interpreter") or {}
+    detected = body.get("detectedLanguage") or {}
     return {
         "translations": out,
-        "detected_lang": (body.get("detectedLanguage") or {}).get("language"),
+        "detected_lang": detected.get("language"),
+        "detected_confidence": detected.get("confidence"),
         "engine": interp.get("engine"),
         "engine_version": interp.get("engine_version"),
     }

backend/app/services/ml/allowlist.py

@@ -12,13 +12,11 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 from ...models import TagSuggestionRejection
 from ...models.tag import image_tag
-from .aliases import AliasService
 
 
 class AllowlistService:
     def __init__(self, session: AsyncSession):
         self.session = session
-        self.aliases = AliasService(session)
 
     async def _apply_image_tag(self, image_id: int, tag_id: int, source: str):
         stmt = insert(image_tag).values(
@@ -41,18 +39,6 @@ class AllowlistService:
         await self._apply_image_tag(image_id, tag_id, source="ml_accepted")
         await self._clear_rejection(image_id, tag_id)
 
-    async def add_alias_and_accept(
-        self,
-        image_id: int,
-        alias_string: str,
-        alias_category: str,
-        canonical_tag_id: int,
-    ) -> None:
-        await self.aliases.create(
-            alias_string, alias_category, canonical_tag_id
-        )
-        await self.accept(image_id, canonical_tag_id)
-
     async def dismiss(self, image_id: int, tag_id: int) -> None:
         stmt = insert(TagSuggestionRejection).values(
             image_record_id=image_id, tag_id=tag_id

backend/app/services/ml/character_prototypes.py

@@ -150,9 +150,7 @@ def refresh_character_prototypes(
     """Incrementally refresh the prototype store. `full=True` rebuilds every
     character regardless of the gate/fingerprints (nightly reconcile). Returns
     {skipped, rebuilt, removed}; commits."""
-    settings = session.execute(
-        select(MLSettings).where(MLSettings.id == 1)
-    ).scalar_one()
+    settings = MLSettings.load_sync(session)
     sig = _global_signature(session)
     if not full and settings.ccip_ref_signature == sig:
         return {"skipped": True, "rebuilt": 0, "removed": 0}
@@ -204,9 +202,7 @@ def retract_auto_applied_ccip(session: Session) -> int:
     n_retracted."""
     import numpy as np
 
-    settings = session.execute(
-        select(MLSettings).where(MLSettings.id == 1)
-    ).scalar_one()
+    settings = MLSettings.load_sync(session)
     if not settings.ccip_auto_apply_enabled:
         return 0
     thr = float(settings.ccip_auto_apply_threshold)

backend/app/services/ml/heads.py

@@ -23,6 +23,7 @@ from datetime import UTC, datetime
 from typing import Any
 
 from sqlalchemy import delete, exists, func, select
+from sqlalchemy.dialects.postgresql import insert as pg_insert
 from sqlalchemy.ext.asyncio import AsyncSession
 from sqlalchemy.orm import Session
 
@@ -39,9 +40,10 @@ from ...models import (
     TagPositiveConfirmation,
     TagSuggestionRejection,
 )
-from ...models.tag import PRESENTATION_SYSTEM_TAGS, image_tag
+from ...models.tag import CHROME_SYSTEM_TAGS, PROCESS_SYSTEM_TAGS, image_tag
 from .training_data import (
     _AUTO_SOURCES,
+    _applied_or_rejected,
     _auto_apply_point,
     _hygiene_excluded_ids,
     _ids_with_tag,
@@ -61,6 +63,14 @@ MIN_POSITIVES_FLOOR = 8     # hard floor; settings.head_min_positives can raise
 _UNLABELED_POOL = 4000
 _EXAMPLES_MIN = 8           # need at least this many embedded +/- to fit a head
 
+# Auto-apply / match confidence operating range. Every graduated auto-apply or
+# CCIP-match threshold the operator can set lives in this band, and the head
+# precision target is clamped to it: below 0.5 "auto-apply" is meaningless, and
+# 1.0 is unachievable so 0.999 is the ceiling. One source shared by the service
+# clamp (_normalize_params) and the API validator (ml_admin._validate).
+AUTO_APPLY_THRESHOLD_MIN = 0.5
+AUTO_APPLY_THRESHOLD_MAX = 0.999
+
 # Only these tag kinds get heads (the surfaced suggestion categories).
 _HEAD_KINDS = (TagKind.general, TagKind.character)
 # tag.kind -> the suggestion category the rail groups under.
@@ -78,6 +88,38 @@ _CATEGORY = {TagKind.general: "general", TagKind.character: "character"}
 _SYSTEM_TAG_SUGGEST_FLOOR = 0.65
 
 
+def _sigmoid(z, np):
+    """Logistic sigmoid 1/(1+e^-z): the head score→probability transform. One home
+    for what was inlined at every scoring site (suggest, both sweeps, retract)."""
+    return 1.0 / (1.0 + np.exp(-z))
+
+
+def _conflict_scores(Xn, Wc, bc, np):
+    """The presentation conflict signal (#141): per row, the MAX content-head
+    probability and WHICH head produced it. Shared by the system-tag sweep's guard-2
+    and the soft-wip audit — both ask "does this ALSO look like real content?"."""
+    cprobs = _sigmoid(Xn @ Wc.T + bc, np)
+    return cprobs.max(axis=1), cprobs.argmax(axis=1)
+
+
+def _insert_presentation_review(
+    session, *, image_record_id, tag_id, conflict_tag_id, conflict_score, mode,
+):
+    """Single-source the ring-loud PresentationReview row shape so the two writers
+    (system-tag sweep guard-2 + soft-wip audit) can't drift on columns or `mode` —
+    they share the (image_record_id, tag_id) composite PK, so a divergent `mode`
+    would be a silent first-writer-wins bug."""
+    session.execute(
+        pg_insert(PresentationReview)
+        .values(
+            image_record_id=image_record_id, tag_id=tag_id,
+            conflict_tag_id=conflict_tag_id, conflict_score=conflict_score,
+            mode=mode,
+        )
+        .on_conflict_do_nothing()
+    )
+
+
 class HeadTrainingAlreadyRunning(Exception):
     """Raised by start_head_training_run when a run is already in flight."""
 
@@ -103,9 +145,7 @@ def start_head_training_run(session: Session, params: dict[str, Any]) -> int:
 
 
 def _settings(session: Session) -> MLSettings:
-    return session.execute(
-        select(MLSettings).where(MLSettings.id == 1)
-    ).scalar_one()
+    return MLSettings.load_sync(session)
 
 
 def _normalize_params(session: Session, params: dict[str, Any] | None) -> dict[str, Any]:
@@ -124,7 +164,7 @@ def _normalize_params(session: Session, params: dict[str, Any] | None) -> dict[s
     except (TypeError, ValueError):
         cv_folds = DEFAULT_CV_FOLDS
     try:
-        precision_target = min(max(float(params.get("precision_target", s.head_auto_apply_precision)), 0.5), 0.999)
+        precision_target = min(max(float(params.get("precision_target", s.head_auto_apply_precision)), AUTO_APPLY_THRESHOLD_MIN), AUTO_APPLY_THRESHOLD_MAX)
     except (TypeError, ValueError):
         precision_target = s.head_auto_apply_precision
     return {
@@ -500,13 +540,19 @@ async def score_image(
     session: AsyncSession, image_id: int, threshold_override: float | None = None,
 ) -> list[dict]:
     """Suggestions for one image from the trained heads: [{tag_id, name,
-    category, score}], ranked. A concept surfaces when its score clears the
-    head's own suggest_threshold — or, when threshold_override is given (the
-    typed-dropdown "show everything" mode), that flat floor instead (0 → every
-    head). System-tag heads (wip/banner/editor) instead use a flat
-    _SYSTEM_TAG_SUGGEST_FLOOR so their false positives surface for rejection
-    (still overridden by threshold_override). Empty if the image has no
-    embedding or no heads exist yet.
+    category, score, above_threshold, grounding}], ranked. A concept is INCLUDED
+    when its score clears the head's own suggest_threshold — or, when
+    threshold_override is given (the typed-dropdown "show everything" mode), that
+    flat floor instead (0 → every head). System-tag heads (wip/banner/editor)
+    instead use a flat _SYSTEM_TAG_SUGGEST_FLOOR so their false positives surface
+    for rejection (still overridden by threshold_override). Empty if the image has
+    no embedding or no heads exist yet.
+
+    ``above_threshold`` is reported SEPARATELY from inclusion: it's always whether
+    the score cleared the head's NATURAL cut (suggest_threshold, or the system
+    floor), regardless of any override. So the single min=0 fetch returns every
+    head, and the caller can split panel (above_threshold) from dropdown (all)
+    without a second request.
 
     MAX-OVER-BAG: the image is scored as a BAG of embeddings — the whole-image
     vector PLUS every concept-region crop the agent embedded (same model
@@ -530,28 +576,32 @@ async def score_image(
     norms[norms == 0] = 1.0
     Xn = X / norms
     Z = Xn @ heads["W"].T + heads["b"]                  # (B, H)
-    probs_bag = 1.0 / (1.0 + np.exp(-Z))                # (B, H)
+    probs_bag = _sigmoid(Z, np)                         # (B, H)
     probs = probs_bag.max(axis=0)                       # (H,) best over the bag
     # ARGMAX beside the max: WHICH bag row won each head → the region that grounds
     # the tag (bag_meta[win]); None when the whole-image vector won (#1206).
     winners = probs_bag.argmax(axis=0)                  # (H,)
     out = []
     for i, p in enumerate(probs):
-        if threshold_override is not None:
-            cut = threshold_override
-        elif heads["meta"][i]["is_system"]:
-            # System tags surface at the flat floor (see _SYSTEM_TAG_SUGGEST_FLOOR)
-            # so their false positives show up for the operator to reject.
-            cut = _SYSTEM_TAG_SUGGEST_FLOOR
-        else:
-            cut = heads["thr"][i]
+        m = heads["meta"][i]
+        # The head's NATURAL suggest cut — system tags use the flat floor (see
+        # _SYSTEM_TAG_SUGGEST_FLOOR) so their false positives show up for the
+        # operator to reject; content heads use their own precision-tuned
+        # threshold. This is what "above threshold" means (drives the panel).
+        natural = (
+            _SYSTEM_TAG_SUGGEST_FLOOR if m["is_system"] else float(heads["thr"][i])
+        )
+        # INCLUSION is looser under threshold_override (dropdown show-all,
+        # override=0): every head comes back so a low-confidence concept can still
+        # be typed + picked, each carrying its own above_threshold flag.
+        cut = threshold_override if threshold_override is not None else natural
         if p >= cut:
-            m = heads["meta"][i]
             out.append({
                 "tag_id": m["tag_id"],
                 "name": m["name"],
                 "category": m["category"],
                 "score": float(p),
+                "above_threshold": bool(p >= natural),
                 "grounding": bag_meta[int(winners[i])],
             })
     out.sort(key=lambda d: d["score"], reverse=True)
@@ -604,9 +654,7 @@ async def ground_applied_tag(
 
 
 async def _settings_async(session: AsyncSession) -> MLSettings:
-    return (
-        await session.execute(select(MLSettings).where(MLSettings.id == 1))
-    ).scalar_one()
+    return await MLSettings.load(session)
 
 
 # --- Earned auto-apply (sync, ml worker) ---------------------------------
@@ -677,7 +725,6 @@ def auto_apply_sweep(
     embeddings in chunks; commits per chunk on a real run. Returns
     {n_applied, concepts:[{tag_id,name,applied,scanned,threshold}]}."""
     import numpy as np
-    from sqlalchemy.dialects.postgresql import insert as pg_insert
 
     settings = _settings(session)
     rows = _auto_apply_heads(
@@ -694,18 +741,7 @@ def auto_apply_sweep(
     names = [r.name for r in rows]
 
     # Skip images that already carry, or have rejected, each tag.
-    skip = {tid: set() for tid in tag_ids}
-    for tid in tag_ids:
-        for (iid,) in session.execute(
-            select(image_tag.c.image_record_id).where(image_tag.c.tag_id == tid)
-        ):
-            skip[tid].add(iid)
-        for (iid,) in session.execute(
-            select(TagSuggestionRejection.image_record_id).where(
-                TagSuggestionRejection.tag_id == tid
-            )
-        ):
-            skip[tid].add(iid)
+    skip = _applied_or_rejected(session, tag_ids)
 
     applied = [0] * len(rows)
     scanned = 0
@@ -719,7 +755,7 @@ def auto_apply_sweep(
         if not cids:
             continue
         Xn = _l2norm(np.vstack([emb[i] for i in cids]).astype(np.float32), np)
-        probs = 1.0 / (1.0 + np.exp(-(Xn @ W.T + b)))   # (N, H)
+        probs = _sigmoid(Xn @ W.T + b, np)              # (N, H)
         scanned += len(cids)
         for h in range(len(rows)):
             tid = tag_ids[h]
@@ -749,18 +785,42 @@ def auto_apply_sweep(
 
 
 _PRESENTATION_SOURCE = "presentation_auto"
+_PROCESS_SOURCE = "process_auto"
+
+# System-tag auto-apply modes (#1464). Both modes run the identical sweep — apply
+# a system tag at a flat threshold with a PROVISIONAL source + a ring-loud review
+# guard — and differ ONLY in which tags, which settings knobs, and which
+# source/review-mode. 'chrome' (banner) is HIDDEN from the gallery; 'process'
+# (wip / editor screenshot) stays VISIBLE (the hide is a gallery-query effect of
+# the tag's group membership, not of this sweep).
+_SWEEP_MODES = {
+    "chrome": {
+        "names": CHROME_SYSTEM_TAGS,
+        "enabled": "presentation_auto_apply_enabled",
+        "threshold": "presentation_auto_apply_threshold",
+        "conflict": "presentation_conflict_threshold",
+        "source": _PRESENTATION_SOURCE,
+    },
+    "process": {
+        "names": PROCESS_SYSTEM_TAGS,
+        "enabled": "process_auto_apply_enabled",
+        "threshold": "process_auto_apply_threshold",
+        "conflict": "process_conflict_threshold",
+        "source": _PROCESS_SOURCE,
+    },
+}
 
 
-def _presentation_heads(session: Session, embedding_version: str):
-    """Trained heads for the presentation chrome tags (banner / editor screenshot).
-    They fire at the FLAT presentation threshold regardless of graduation — a head
-    exists once the operator has labelled enough chrome (head_min_positives)."""
+def _system_tag_heads(session: Session, embedding_version: str, names):
+    """Trained heads for a system-tag group (chrome banner / process wip+editor).
+    They fire at the group's FLAT threshold regardless of graduation — a head
+    exists once the operator has labelled enough (head_min_positives)."""
     return session.execute(
         select(TagHead.tag_id, Tag.name, TagHead.weights, TagHead.bias)
         .join(Tag, Tag.id == TagHead.tag_id)
         .where(TagHead.embedding_version == embedding_version)
         .where(Tag.is_system.is_(True))
-        .where(Tag.name.in_(PRESENTATION_SYSTEM_TAGS))
+        .where(Tag.name.in_(names))
     ).all()
 
 
@@ -792,27 +852,32 @@ def _valued_image_ids(session: Session) -> set[int]:
     return {r[0] for r in rows}
 
 
-def presentation_auto_apply_sweep(session: Session, dry_run: bool = False) -> dict:
-    """Auto-hide presentation chrome (banner / editor screenshot) at the FLAT
-    presentation threshold (#141) — NOT the per-head graduated threshold. Two
-    guards keep it safe: (1) never hide an image carrying a human/confirmed content
-    tag; (2) if an image about to be hidden ALSO scores >= the conflict threshold
-    on a content head, still hide it but flag it (PresentationReview) so the Hidden
-    view surfaces "also looks like <X>" for review. No-op unless
-    presentation_auto_apply_enabled. numpy-only (no sklearn). Returns
-    {n_applied, n_flagged, concepts}."""
+def system_tag_auto_apply_sweep(
+    session: Session, *, mode: str, dry_run: bool = False
+) -> dict:
+    """Auto-apply a system-tag group at its FLAT threshold. mode='chrome' (banner,
+    #141) hides the image; mode='process' (wip / editor screenshot, #1464) keeps it
+    VISIBLE — the ONLY difference is the tag group's gallery membership, not this
+    sweep. Two guards keep it safe: (1) never touch an image carrying a
+    human/confirmed content tag; (2) if the image ALSO scores >= the conflict
+    threshold on a content head, still apply but flag it (PresentationReview,
+    mode=<mode>) so the review strip surfaces "also looks like <X>". The source is
+    PROVISIONAL so the head never trains on its own output. No-op unless the mode's
+    enabled flag is set. numpy-only (no sklearn). Returns {n_applied, n_flagged,
+    concepts}."""
     import numpy as np
-    from sqlalchemy.dialects.postgresql import insert as pg_insert
 
+    cfg = _SWEEP_MODES[mode]
     settings = _settings(session)
-    if not dry_run and not settings.presentation_auto_apply_enabled:
+    if not dry_run and not getattr(settings, cfg["enabled"]):
         return {"n_applied": 0, "n_flagged": 0, "concepts": []}
     ver = settings.embedder_model_version
-    pres = _presentation_heads(session, ver)
+    pres = _system_tag_heads(session, ver, cfg["names"])
     if not pres:
         return {"n_applied": 0, "n_flagged": 0, "concepts": []}
-    thr = float(settings.presentation_auto_apply_threshold)
-    conflict_thr = float(settings.presentation_conflict_threshold)
+    thr = float(getattr(settings, cfg["threshold"]))
+    conflict_thr = float(getattr(settings, cfg["conflict"]))
+    source = cfg["source"]
 
     Wp = np.vstack([np.asarray(r.weights, dtype=np.float32) for r in pres])
     bp = np.asarray([r.bias for r in pres], dtype=np.float32)
@@ -829,18 +894,7 @@ def presentation_auto_apply_sweep(session: Session, dry_run: bool = False) -> di
     valued = _valued_image_ids(session)
 
     # Skip images that already carry, or have rejected, each presentation tag.
-    skip = {tid: set() for tid in pres_tag_ids}
-    for tid in pres_tag_ids:
-        for (iid,) in session.execute(
-            select(image_tag.c.image_record_id).where(image_tag.c.tag_id == tid)
-        ):
-            skip[tid].add(iid)
-        for (iid,) in session.execute(
-            select(TagSuggestionRejection.image_record_id).where(
-                TagSuggestionRejection.tag_id == tid
-            )
-        ):
-            skip[tid].add(iid)
+    skip = _applied_or_rejected(session, pres_tag_ids)
 
     applied = [0] * len(pres)
     n_flagged = 0
@@ -855,11 +909,9 @@ def presentation_auto_apply_sweep(session: Session, dry_run: bool = False) -> di
         if not cids:
             continue
         Xn = _l2norm(np.vstack([emb[i] for i in cids]).astype(np.float32), np)
-        probs = 1.0 / (1.0 + np.exp(-(Xn @ Wp.T + bp)))       # (N, P)
+        probs = _sigmoid(Xn @ Wp.T + bp, np)                  # (N, P)
         if Wc is not None:
-            cprobs = 1.0 / (1.0 + np.exp(-(Xn @ Wc.T + bc)))  # (N, C)
-            max_c = cprobs.max(axis=1)
-            arg_c = cprobs.argmax(axis=1)
+            max_c, arg_c = _conflict_scores(Xn, Wc, bc, np)   # (N,), (N,)
         scanned += len(cids)
         for p in range(len(pres)):
             tid = pres_tag_ids[p]
@@ -874,22 +926,22 @@ def presentation_auto_apply_sweep(session: Session, dry_run: bool = False) -> di
                         pg_insert(image_tag)
                         .values(
                             image_record_id=iid, tag_id=tid,
-                            source=_PRESENTATION_SOURCE,
+                            source=source,
                         )
                         .on_conflict_do_nothing()
                     )
-                # Guard 2: also looks like content → hide but flag for review.
+                # Guard 2: also looks like real content → still apply, but flag it
+                # for the review strip instead of silently marking (chrome hides,
+                # process stays visible — either way the operator gets a heads-up).
                 if Wc is not None and float(max_c[idx]) >= conflict_thr:
                     n_flagged += 1
                     if not dry_run:
-                        session.execute(
-                            pg_insert(PresentationReview)
-                            .values(
-                                image_record_id=iid, tag_id=tid,
-                                conflict_tag_id=conf_tag_ids[int(arg_c[idx])],
-                                conflict_score=float(max_c[idx]),
-                            )
-                            .on_conflict_do_nothing()
+                        _insert_presentation_review(
+                            session,
+                            image_record_id=iid, tag_id=tid,
+                            conflict_tag_id=conf_tag_ids[int(arg_c[idx])],
+                            conflict_score=float(max_c[idx]),
+                            mode=mode,
                         )
         if not dry_run:
             session.commit()
@@ -904,6 +956,68 @@ def presentation_auto_apply_sweep(session: Session, dry_run: bool = False) -> di
     }
 
 
+def soft_wip_conflict_audit(session: Session, dry_run: bool = False) -> dict:
+    """Ring-loud audit for the SOFT WIP-title cohort (#1474). Images auto-tagged
+    `wip` from a low-precision sketch/doodle title (source='wip_title_soft') that ALSO
+    score >= the process conflict threshold on a content head are probably FINISHED
+    art mis-tagged as process — flag them (PresentationReview, mode='process') so the
+    review strip surfaces them ("also looks like <X>", Keep tag / Remove tag). Does
+    NOT remove the tag; the operator decides. No-op when there are no content heads.
+    numpy-only. Returns {n_scanned, n_flagged}."""
+    import numpy as np
+
+    from ..wip_title import WIP_TITLE_SOFT_SOURCE, resolve_wip_tag_id
+
+    settings = _settings(session)
+    ver = settings.embedder_model_version
+    conflict_thr = float(settings.process_conflict_threshold)
+    conf = _conflict_heads(session, ver)
+    wip_id = resolve_wip_tag_id(session)
+    if not conf or wip_id is None:
+        return {"n_scanned": 0, "n_flagged": 0}
+    Wc = np.vstack([np.asarray(r.weights, dtype=np.float32) for r in conf])
+    bc = np.asarray([r.bias for r in conf], dtype=np.float32)
+    conf_tag_ids = [r.tag_id for r in conf]
+
+    soft_ids = [iid for (iid,) in session.execute(
+        select(image_tag.c.image_record_id)
+        .where(image_tag.c.tag_id == wip_id)
+        .where(image_tag.c.source == WIP_TITLE_SOFT_SOURCE)
+    )]
+    # Skip images already flagged for this tag (idempotent re-runs).
+    flagged = {iid for (iid,) in session.execute(
+        select(PresentationReview.image_record_id)
+        .where(PresentationReview.tag_id == wip_id)
+    )}
+    soft_ids = [i for i in soft_ids if i not in flagged]
+
+    n_flagged = 0
+    scanned = 0
+    for start in range(0, len(soft_ids), _AUTO_APPLY_CHUNK):
+        chunk = soft_ids[start:start + _AUTO_APPLY_CHUNK]
+        emb = _load_embeddings(session, chunk)
+        cids = [i for i in chunk if i in emb]
+        if not cids:
+            continue
+        scanned += len(cids)
+        Xn = _l2norm(np.vstack([emb[i] for i in cids]).astype(np.float32), np)
+        max_c, arg_c = _conflict_scores(Xn, Wc, bc, np)
+        for k in range(len(cids)):
+            if float(max_c[k]) >= conflict_thr:
+                n_flagged += 1
+                if not dry_run:
+                    _insert_presentation_review(
+                        session,
+                        image_record_id=cids[k], tag_id=wip_id,
+                        conflict_tag_id=conf_tag_ids[int(arg_c[k])],
+                        conflict_score=float(max_c[k]),
+                        mode="process",
+                    )
+        if not dry_run:
+            session.commit()
+    return {"n_scanned": scanned, "n_flagged": n_flagged}
+
+
 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
@@ -951,7 +1065,7 @@ def retract_auto_applied_heads(session: Session) -> int:
             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))))
+        probs = _sigmoid(Xn @ w + float(bias), np)
         below = [cids[k] for k in np.where(probs < float(thr))[0]]
         for iid in below:
             session.execute(

backend/app/services/ml/suggestions.py

@@ -22,22 +22,20 @@ from .heads import score_image
 
 @dataclass(frozen=True)
 class Suggestion:
-    # canonical_tag_id is None when this is a raw Camie tag with no alias and
-    # no existing Tag row — accepting it will create the tag.
-    canonical_tag_id: int | None
+    # Every suggestion is a canonical Tag: heads/CCIP only score EXISTING concept
+    # tags (tagging-v2, #114). The old raw-model-key / creates-new / alias-remap
+    # cases are gone — a suggestion always maps to a real tag id.
+    canonical_tag_id: int
     display_name: str
     category: str
     score: float
     source: str  # 'head' | 'ccip' | 'both' (Camie tagger/centroid removed in v2)
-    creates_new_tag: bool
-    # raw_name = the booru model vocab key behind this suggestion. It's the key
-    # an alias MUST be stored under (resolution looks up the raw key), so the
-    # modal needs it to author an alias correctly. None for centroid-only hits
-    # (no underlying prediction → nothing to alias).
-    raw_name: str | None = None
-    # via_alias = this suggestion was surfaced because an operator alias remapped
-    # the raw prediction to this canonical tag. Lets the UI mark it + offer undo.
-    via_alias: bool = False
+    # above_threshold = the score cleared the head's own suggest cut (or the
+    # system floor). The Suggestions PANEL shows only these; the typed-tag
+    # dropdown fetches ALL suggestions (every head, min=0) and just annotates each
+    # matching row with its score, so a low-confidence concept can still be typed
+    # and picked. CCIP character matches are always above their match threshold.
+    above_threshold: bool
     # rejected = the operator dismissed this tag for this image (a stored
     # TagSuggestionRejection). It stays in the list — flagged, not dropped — so
     # the rejection is VISIBLE and REVERSIBLE in the rail (misclick recovery,
@@ -108,6 +106,7 @@ class SuggestionService:
         for h in hits:
             merged[(h["category"], h["tag_id"])] = {
                 "name": h["name"], "score": h["score"], "source": "head",
+                "above_threshold": h["above_threshold"],
                 "grounding": h.get("grounding"),
             }
         for c in ccip_hits:
@@ -116,12 +115,16 @@ class SuggestionService:
             if ex is not None:
                 ex["source"] = "both"
                 ex["score"] = max(ex["score"], c["score"])
+                # CCIP only returns matches above its own threshold, so a CCIP
+                # corroboration always makes the merged suggestion above-threshold.
+                ex["above_threshold"] = True
                 # Keep the head's localized crop if it had one; else fall back to
                 # the CCIP figure so a corroborated character still grounds (#1206).
                 ex["grounding"] = ex.get("grounding") or c.get("grounding")
             else:
                 merged[key] = {
                     "name": c["name"], "score": c["score"], "source": "ccip",
+                    "above_threshold": True,
                     "grounding": c.get("grounding"),
                 }
 
@@ -136,7 +139,7 @@ class SuggestionService:
                     category=cat,
                     score=m["score"],
                     source=m["source"],
-                    creates_new_tag=False,
+                    above_threshold=m["above_threshold"],
                     rejected=tag_id in rejected,
                     grounding=m.get("grounding"),
                 )
@@ -157,8 +160,7 @@ class SuggestionService:
         was suggested for (or already applied to) >= threshold fraction of
         the selection AND was acceptable on >= 1 image. Confidence is the
         mean over images where it was suggested. Aggregated by
-        canonical_tag_id; creates-new (no canonical id) suggestions are
-        skipped (bulk Accept applies by tag id)."""
+        canonical_tag_id (every suggestion is a canonical tag now)."""
         if not image_ids:
             return {}
         threshold = min(1.0, max(0.0, threshold))
@@ -169,8 +171,6 @@ class SuggestionService:
             sl = await self.for_image(image_id)
             for category, items in sl.by_category.items():
                 for s in items:
-                    if s.canonical_tag_id is None or s.creates_new_tag:
-                        continue
                     # for_image keeps rejected tags (flagged) for the rail;
                     # bulk consensus must still ignore them — a tag dismissed on
                     # an image isn't a suggestion for that image.

backend/app/services/ml/training_data.py

@@ -29,7 +29,15 @@ from ...models.tag import image_tag
 # 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", "presentation_auto")
+# `process_auto` (#1464): wip/editor screenshot applied by the process sweep are
+# ALSO provisional — the head must learn only from title (`wip_title`) + manual
+# labels, never its own auto-applied output, or it would runaway (operator 2026-07-12).
+# `wip_title_soft` (#1474): the soft title tier (sketch/doodle) is LOW-precision, so
+# it's provisional too — a finished piece titled "sketch" must not train the wip head.
+_AUTO_SOURCES = (
+    "head_auto", "ccip_auto", "ml_auto", "presentation_auto", "process_auto",
+    "wip_title_soft",
+)
 
 
 def _hygiene_excluded_ids(session: Session) -> set[int]:
@@ -86,6 +94,24 @@ def _rejected_ids(session: Session, tag_id: int) -> list[int]:
     ]
 
 
+def _applied_or_rejected(session: Session, tag_ids) -> dict[int, set[int]]:
+    """Per-tag skip set for the auto-apply sweeps: every image that ALREADY carries
+    the tag (ANY source — not just training positives) OR has rejected it. A sweep
+    never re-applies to these. Shared by auto_apply_sweep + system_tag_auto_apply_sweep
+    (heads.py) and scheduled_ccip_auto_apply (tasks/ml.py). Callers mutate the returned
+    sets in-place to also dedupe within a single run."""
+    skip: dict[int, set[int]] = {}
+    for tid in tag_ids:
+        ids = {
+            r[0] for r in session.execute(
+                select(image_tag.c.image_record_id).where(image_tag.c.tag_id == tid)
+            ).all()
+        }
+        ids.update(_rejected_ids(session, tid))
+        skip[tid] = ids
+    return skip
+
+
 def _sample_unlabeled(session: Session, exclude: set[int], limit: int) -> list[int]:
     """Random image ids (with an embedding) NOT carrying the tag. Concepts are
     sparse, so an untagged image is almost always a true negative."""

backend/app/services/patreon_resolver.py

@@ -91,48 +91,46 @@ def _sync_lookup(vanity: str, cookies_path: str | None) -> str | None:
     )
 
 
-def _lookup_via_api(vanity: str, cookies_path: str | None) -> str | None:
+def _campaigns_api_first(vanity: str, cookies_path: str | None) -> dict | None:
+    """The first `data` object from Patreon's campaigns API filtered by vanity
+    (`?filter[vanity]=<vanity>&fields[campaign]=name`), or None on any failure
+    (network / non-200 / non-JSON / empty). The single request shape shared by
+    _lookup_via_api (plucks the campaign id) and resolve_display_name (plucks the
+    display name)."""
     jar = _load_cookie_jar(cookies_path)
-    headers = {
-        "User-Agent": _USER_AGENT,
-        "Accept": "application/vnd.api+json",
-    }
-    params = {
-        "filter[vanity]": vanity,
-        "fields[campaign]": "name",
-    }
     try:
         resp = requests.get(
             _CAMPAIGNS_URL,
-            params=params,
-            headers=headers,
+            params={"filter[vanity]": vanity, "fields[campaign]": "name"},
+            headers={"User-Agent": _USER_AGENT, "Accept": "application/vnd.api+json"},
             cookies=jar,
             timeout=_TIMEOUT_SECONDS,
         )
     except requests.RequestException as exc:
         log.warning("Patreon campaigns API request failed for vanity=%s: %s", vanity, exc)
         return None
-
     if resp.status_code != 200:
         log.warning(
             "Patreon campaigns API returned HTTP %d for vanity=%s",
             resp.status_code, vanity,
         )
         return None
-
     try:
         payload = resp.json()
     except ValueError as exc:
         log.warning("Patreon campaigns API returned non-JSON for vanity=%s: %s", vanity, exc)
         return None
+    data = payload.get("data") if isinstance(payload, dict) else None
+    if not isinstance(data, list) or not data or not isinstance(data[0], dict):
+        return None
+    return data[0]
 
-    if not isinstance(payload, dict):
+
+def _lookup_via_api(vanity: str, cookies_path: str | None) -> str | None:
+    first = _campaigns_api_first(vanity, cookies_path)
+    if first is None:
         return None
-    data = payload.get("data")
-    if not isinstance(data, list) or not data:
-        return None
-    first = data[0] if isinstance(data[0], dict) else None
-    campaign_id = first.get("id") if first else None
+    campaign_id = first.get("id")
     if not isinstance(campaign_id, str) or not campaign_id:
         return None
     log.info("Resolved Patreon vanity=%s → campaign_id=%s", vanity, campaign_id)
@@ -144,24 +142,10 @@ def resolve_display_name(vanity: str, cookies_path: str | None) -> str | None:
     (`fields[campaign]=name`), used to name the Artist at add-time (#130). None
     on any failure — the caller falls back to the vanity handle. Sync: call from
     an executor."""
-    jar = _load_cookie_jar(cookies_path)
-    try:
-        resp = requests.get(
-            _CAMPAIGNS_URL,
-            params={"filter[vanity]": vanity, "fields[campaign]": "name"},
-            headers={"User-Agent": _USER_AGENT, "Accept": "application/vnd.api+json"},
-            cookies=jar,
-            timeout=_TIMEOUT_SECONDS,
-        )
-        if resp.status_code != 200:
-            return None
-        data = resp.json().get("data")
-    except (requests.RequestException, ValueError) as exc:
-        log.warning("Patreon name lookup failed for vanity=%s: %s", vanity, exc)
+    first = _campaigns_api_first(vanity, cookies_path)
+    if first is None:
         return None
-    if not isinstance(data, list) or not data or not isinstance(data[0], dict):
-        return None
-    name = (data[0].get("attributes") or {}).get("name")
+    name = (first.get("attributes") or {}).get("name")
     return name.strip() if isinstance(name, str) and name.strip() else None
 
 

backend/app/services/post_feed_service.py

@@ -397,6 +397,8 @@ class PostFeedService:
             "post_title_translated": post.post_title_translated,
             "description_translated": desc_trans_short,
             "translated_source_lang": post.translated_source_lang,
+            # Sticky per-post translation choice (auto/force/original, #155).
+            "translation_override": post.translation_override,
             "artist": {"id": artist.id, "name": artist.name, "slug": artist.slug},
             "source": (
                 {"id": source.id, "platform": source.platform}

backend/app/services/provenance_service.py

@@ -35,6 +35,7 @@ def _post_dict(p: Post) -> dict:
         "title_translated": p.post_title_translated,
         "description_translated": p.description_translated,
         "translated_source_lang": p.translated_source_lang,
+        "translation_override": p.translation_override,
     }
 
 

backend/app/services/wip_title.py

@@ -0,0 +1,125 @@
+"""Title-based WIP auto-tagging (task #1458).
+
+Deterministic heuristic: when a post's TITLE explicitly declares work-in-progress
+(the artist's own "WIP" / "work in progress" label), the ``wip`` system tag is
+applied to that post's images — a cheap, high-precision complement to the
+image-based ML ``wip`` head. WIP images are excluded from the Explore/gallery
+browse (see gallery_service ``excluded_system_tags``), so honouring the artist's
+own label keeps unfinished pieces out of the main browse right at import.
+
+Precision over recall — a false WIP tag HIDES a finished post — so matching is
+token-anchored: ``swipe`` / ``wiped`` / ``wiping`` never trip it (a letter on the
+boundary blocks the match).
+
+Sync-only: both consumers (the importer and the backfill Celery task) run on a
+sync Session. Application is idempotent-additive (ON CONFLICT DO NOTHING) and
+stamps a distinct ``image_tag.source`` so a later pass can tell where a wip tag
+came from — the "manual" / "head_auto" / "ccip_auto" / "ml_accepted" provenance
+family gains one member.
+"""
+import re
+
+from sqlalchemy import select
+from sqlalchemy.dialects.postgresql import insert as pg_insert
+from sqlalchemy.orm import Session
+
+from ..models.tag import WIP_SYSTEM_TAG, Tag, image_tag
+
+# image_tag.source stamped on title-heuristic WIP tags — distinct from the other
+# apply sources so provenance stays legible and a future undo can target only these.
+# HARD tier ("WIP"/"work in progress") is high-precision → trains the wip head.
+WIP_TITLE_SOURCE = "wip_title"
+# SOFT tier (sketch/doodle/scribble, #1474) is LOWER-precision — a finished "sketch"
+# is often not WIP. This source is PROVISIONAL (in training_data._AUTO_SOURCES) so it
+# NEVER trains the wip head; a soft-tagged image that also looks like real content is
+# surfaced by the ring-loud audit for review.
+WIP_TITLE_SOFT_SOURCE = "wip_title_soft"
+
+# A standalone "WIP" / "W.I.P" token, or the phrase "work in progress"
+# (space/underscore/hyphen separated). The letter-boundary lookarounds are what
+# make this precision-first: `s|wip|e`, `|wip|ed`, `|wip|ing` all have a letter
+# abutting the token, so they're rejected. A trailing digit is allowed so
+# "WIP2" (= WIP part 2) still matches.
+_WIP_RE = re.compile(
+    r"(?<![A-Za-z])(?:w\.?i\.?p\.?|work[\s_-]+in[\s_-]+progress)(?![A-Za-z])",
+    re.IGNORECASE,
+)
+
+# Soft tier: sketch / doodle / scribble (+ plurals), letter-boundary anchored so
+# "sketchbook" / "kadoodle" don't trip it. Deliberately conservative — recall is
+# secondary because the soft source doesn't train the head and the ring-loud audit
+# catches false positives.
+_SOFT_WIP_RE = re.compile(
+    r"(?<![A-Za-z])(?:sketch|sketches|doodle|doodles|scribble|scribbles)(?![A-Za-z])",
+    re.IGNORECASE,
+)
+
+# Coarse SQL prefilters for the backfill sweep — narrow the post scan to rows that
+# COULD match before the precise regex confirms. Case-insensitive ILIKE patterns.
+# Each MUST stay a SUPERSET of its regex or the sweep would silently miss posts.
+WIP_TITLE_SQL_PREFILTER = ("%wip%", "%work%progress%")
+SOFT_WIP_TITLE_SQL_PREFILTER = ("%sketch%", "%doodle%", "%scribble%")
+
+# Chunk bulk inserts so a large sweep can't blow past psycopg's 65535-parameter
+# ceiling (3 params/row → ~21k rows max; 5k stays comfortably under).
+_INSERT_CHUNK = 5000
+
+
+def matches_wip_title(title: str | None) -> bool:
+    """True when a post title explicitly marks it work-in-progress (HARD tier)."""
+    if not title:
+        return False
+    return _WIP_RE.search(title) is not None
+
+
+def matches_soft_wip_title(title: str | None) -> bool:
+    """True when a title carries a SOFT WIP cue (sketch/doodle/scribble, #1474)."""
+    if not title:
+        return False
+    return _SOFT_WIP_RE.search(title) is not None
+
+
+def resolve_wip_tag_id(session: Session) -> int | None:
+    """The seeded ``wip`` system tag's id (migration 0075), or None if absent."""
+    return session.execute(
+        select(Tag.id).where(Tag.name == WIP_SYSTEM_TAG, Tag.is_system.is_(True))
+    ).scalar_one_or_none()
+
+
+def apply_wip_image_tags(
+    session: Session, image_ids, tag_id: int, *, source: str = WIP_TITLE_SOURCE
+) -> int:
+    """Attach ``tag_id`` (stamped with ``source``) to each image id, idempotently —
+    never disturbs an existing tag or its source. Returns the number of image_tag
+    rows newly inserted. Does NOT commit.
+
+    The insert count is computed from a pre-SELECT of already-tagged ids rather
+    than the statement's ``rowcount``: psycopg reports -1 for a multi-row
+    ON CONFLICT DO NOTHING insert (it runs via an executemany path), so rowcount
+    is unusable here. The SELECT is accurate within this single transaction (no
+    concurrent writer touches these (image, wip) rows); ON CONFLICT DO NOTHING
+    stays as a race-safety belt so a rare concurrent insert can't error."""
+    ids = list({int(i) for i in image_ids})
+    if not ids:
+        return 0
+    inserted = 0
+    for start in range(0, len(ids), _INSERT_CHUNK):
+        chunk = ids[start:start + _INSERT_CHUNK]
+        already = set(session.execute(
+            select(image_tag.c.image_record_id)
+            .where(image_tag.c.tag_id == tag_id)
+            .where(image_tag.c.image_record_id.in_(chunk))
+        ).scalars())
+        to_insert = [iid for iid in chunk if iid not in already]
+        if not to_insert:
+            continue
+        session.execute(
+            pg_insert(image_tag)
+            .values([
+                {"image_record_id": iid, "tag_id": tag_id, "source": source}
+                for iid in to_insert
+            ])
+            .on_conflict_do_nothing(index_elements=["image_record_id", "tag_id"])
+        )
+        inserted += len(to_insert)
+    return inserted

backend/app/tasks/maintenance.py

@@ -76,9 +76,19 @@ DOWNLOAD_STALL_THRESHOLD_MINUTES = 30
 OLD_TASK_DAYS = 7
 PHASH_PAGE = 500
 VERIFY_PAGE = 200
+# Title-based WIP backfill (task #1458): posts scanned per keyset page.
+WIP_BACKFILL_PAGE = 500
 FFPROBE_TIMEOUT_SECONDS = 10
 TASK_RUN_KEEP_OK_SECONDS = 24 * 3600       # 24 h
 TASK_RUN_KEEP_FAILURE_SECONDS = 7 * 24 * 3600  # 7 days
+# Orphaned staging files: downloads/imports stage into <name>.part / <name>.partial
+# then os.replace() into place (importer / external_fetch / native_ingest_common /
+# attachment_store), so a kill mid-write leaves a discardable temp, never a corrupt
+# final. cleanup_orphaned_temp_files sweeps ones left behind; the min-age guard
+# keeps it from deleting an in-flight download's staging file mid-write.
+IMAGES_ROOT = Path("/images")
+TEMP_STAGING_SUFFIXES = (".part", ".partial")
+ORPHAN_TEMP_MIN_AGE_HOURS = 6
 
 # Audit 2026-06-02: per-entity recovery sweep thresholds. Each must be
 # > the entity's longest legitimate runtime (its task's time_limit + a
@@ -339,6 +349,34 @@ def cleanup_old_tasks() -> int:
         return result.rowcount or 0
 
 
+@celery.task(name="backend.app.tasks.maintenance.cleanup_orphaned_temp_files")
+def cleanup_orphaned_temp_files() -> int:
+    """Delete orphaned .part/.partial staging files under the images root, left by
+    a download/import killed mid-write. Only removes files older than
+    ORPHAN_TEMP_MIN_AGE_HOURS so an in-flight download's staging file is never
+    pulled out from under it. Returns the count removed."""
+    if not IMAGES_ROOT.is_dir():
+        return 0
+    cutoff = datetime.now(UTC).timestamp() - ORPHAN_TEMP_MIN_AGE_HOURS * 3600
+    removed = 0
+    for path in IMAGES_ROOT.rglob("*"):
+        if path.suffix not in TEMP_STAGING_SUFFIXES or not path.is_file():
+            continue
+        try:
+            if path.stat().st_mtime >= cutoff:
+                continue          # too fresh — may be an active download
+            path.unlink()
+            removed += 1
+        except OSError as exc:
+            log.warning("cleanup_orphaned_temp_files: %s: %s", path, exc)
+    if removed:
+        log.info(
+            "cleanup_orphaned_temp_files: removed %d orphaned staging file(s)",
+            removed,
+        )
+    return removed
+
+
 @celery.task(name="backend.app.tasks.maintenance.recover_stalled_task_runs")
 def recover_stalled_task_runs() -> int:
     """Flip task_run rows stuck in 'running' past their queue-specific
@@ -738,89 +776,62 @@ def recover_stalled_library_audit_runs() -> int:
         return recovered
 
 
+def _recover_stalled_runs(model, *, stall_minutes: int, keep_runs: int, label: str) -> int:
+    """Shared recovery + retention sweep for the head run-tracking tables
+    (HeadTrainingRun / HeadAutoApplyRun, which share the
+    status/last_progress_at/started_at/finished_at/error/id columns): flip 'running'
+    rows with no progress past `stall_minutes` to 'error', then prune to the last
+    `keep_runs` (rule 89). Returns the number recovered. NOTE the two other recover
+    tasks are deliberately NOT folded in — library-audit has no prune tail and
+    backup uses a single started_at cutoff."""
+    SessionLocal = _sync_session_factory()
+    now = datetime.now(UTC)
+    cutoff = now - timedelta(minutes=stall_minutes)
+    with SessionLocal() as session:
+        result = session.execute(
+            update(model)
+            .where(model.status == "running")
+            .where(func.coalesce(model.last_progress_at, model.started_at) < cutoff)
+            .values(
+                status="error", finished_at=now,
+                error=f"stranded by recovery sweep (no progress for {stall_minutes} min)",
+            )
+        )
+        keep = session.execute(
+            select(model.id).order_by(model.id.desc()).limit(keep_runs)
+        ).scalars().all()
+        if keep:
+            session.execute(delete(model).where(model.id.not_in(keep)))
+        session.commit()
+        recovered = result.rowcount or 0
+        if recovered:
+            log.info("%s: recovered %d rows", label, recovered)
+        return recovered
+
+
 @celery.task(name="backend.app.tasks.maintenance.recover_stalled_head_training_runs")
 def recover_stalled_head_training_runs() -> int:
     """Flip HeadTrainingRun rows stuck in 'running' past the stall threshold to
     'error', and prune old runs to the last HEAD_TRAINING_KEEP_RUNS (retention,
     rule 89). Runs every 5 min on the maintenance lane; no-op when idle."""
-    SessionLocal = _sync_session_factory()
-    now = datetime.now(UTC)
-    cutoff = now - timedelta(minutes=HEAD_TRAINING_STALL_THRESHOLD_MINUTES)
-    with SessionLocal() as session:
-        result = session.execute(
-            update(HeadTrainingRun)
-            .where(HeadTrainingRun.status == "running")
-            .where(
-                func.coalesce(
-                    HeadTrainingRun.last_progress_at, HeadTrainingRun.started_at
-                )
-                < cutoff
-            )
-            .values(
-                status="error", finished_at=now,
-                error=(
-                    f"stranded by recovery sweep (no progress for "
-                    f"{HEAD_TRAINING_STALL_THRESHOLD_MINUTES} min)"
-                ),
-            )
-        )
-        keep = session.execute(
-            select(HeadTrainingRun.id).order_by(HeadTrainingRun.id.desc())
-            .limit(HEAD_TRAINING_KEEP_RUNS)
-        ).scalars().all()
-        if keep:
-            session.execute(
-                delete(HeadTrainingRun).where(HeadTrainingRun.id.not_in(keep))
-            )
-        session.commit()
-        recovered = result.rowcount or 0
-        if recovered:
-            log.info(
-                "recover_stalled_head_training_runs: recovered %d rows", recovered
-            )
-        return recovered
+    return _recover_stalled_runs(
+        HeadTrainingRun,
+        stall_minutes=HEAD_TRAINING_STALL_THRESHOLD_MINUTES,
+        keep_runs=HEAD_TRAINING_KEEP_RUNS,
+        label="recover_stalled_head_training_runs",
+    )
 
 
 @celery.task(name="backend.app.tasks.maintenance.recover_stalled_head_auto_apply_runs")
 def recover_stalled_head_auto_apply_runs() -> int:
     """Flip stalled HeadAutoApplyRun 'running' rows to 'error' + prune to the
     last HEAD_AUTO_APPLY_KEEP_RUNS (retention, rule 89). 5-min maintenance lane."""
-    SessionLocal = _sync_session_factory()
-    now = datetime.now(UTC)
-    cutoff = now - timedelta(minutes=HEAD_AUTO_APPLY_STALL_THRESHOLD_MINUTES)
-    with SessionLocal() as session:
-        result = session.execute(
-            update(HeadAutoApplyRun)
-            .where(HeadAutoApplyRun.status == "running")
-            .where(
-                func.coalesce(
-                    HeadAutoApplyRun.last_progress_at, HeadAutoApplyRun.started_at
-                )
-                < cutoff
-            )
-            .values(
-                status="error", finished_at=now,
-                error=(
-                    f"stranded by recovery sweep (no progress for "
-                    f"{HEAD_AUTO_APPLY_STALL_THRESHOLD_MINUTES} min)"
-                ),
-            )
-        )
-        keep = session.execute(
-            select(HeadAutoApplyRun.id).order_by(HeadAutoApplyRun.id.desc())
-            .limit(HEAD_AUTO_APPLY_KEEP_RUNS)
-        ).scalars().all()
-        if keep:
-            session.execute(
-                delete(HeadAutoApplyRun).where(HeadAutoApplyRun.id.not_in(keep))
-            )
-        session.commit()
-        recovered = result.rowcount or 0
-        if recovered:
-            log.info(
-                "recover_stalled_head_auto_apply_runs: recovered %d rows", recovered
-            )
-        return recovered
+    return _recover_stalled_runs(
+        HeadAutoApplyRun,
+        stall_minutes=HEAD_AUTO_APPLY_STALL_THRESHOLD_MINUTES,
+        keep_runs=HEAD_AUTO_APPLY_KEEP_RUNS,
+        label="recover_stalled_head_auto_apply_runs",
+    )
 
 
 # Keep ~6 months of daily head-metric snapshots (enough to see tuning trends).
@@ -1009,6 +1020,96 @@ def cleanup_old_download_events() -> int:
         return result.rowcount or 0
 
 
+def _backfill_wip_tier(session, tag_id, prefilter, matcher, source) -> int:
+    """One keyset-paginated pass over posts whose title matches a WIP tier, applying
+    `tag_id` (stamped `source`) to their images. Shared by the hard + soft tiers
+    (#1458 / #1474). Coarse `prefilter` (ILIKE superset) narrows the scan; the precise
+    `matcher` confirms. Idempotent-additive (ON CONFLICT DO NOTHING). Returns the row
+    count newly applied."""
+    from ..models import Post
+    from ..models.image_provenance import ImageProvenance
+    from ..services.wip_title import apply_wip_image_tags
+
+    applied = 0
+    last_id = 0
+    while True:
+        rows = session.execute(
+            select(Post.id, Post.post_title)
+            .where(Post.id > last_id)
+            .where(Post.post_title.is_not(None))
+            .where(or_(*[Post.post_title.ilike(p) for p in prefilter]))
+            .order_by(Post.id.asc())
+            .limit(WIP_BACKFILL_PAGE)
+        ).all()
+        if not rows:
+            break
+        last_id = rows[-1][0]
+        match_ids = [pid for pid, title in rows if matcher(title)]
+        if match_ids:
+            image_ids = session.execute(
+                select(ImageProvenance.image_record_id)
+                .where(ImageProvenance.post_id.in_(match_ids))
+            ).scalars().all()
+            applied += apply_wip_image_tags(session, image_ids, tag_id, source=source)
+            session.commit()
+    return applied
+
+
+@celery.task(
+    name="backend.app.tasks.maintenance.backfill_wip_title_tags",
+    # Coarse-prefiltered scan over posts; the candidate set is small on a typical
+    # library, but bound it like the other full-library sweeps.
+    soft_time_limit=1800, time_limit=2100,
+)
+def backfill_wip_title_tags() -> int:
+    """Scan EXISTING posts for WIP titles and apply the `wip` system tag to their
+    images — the operator-triggered back-catalogue catch-up (task #1458 hard tier +
+    #1474 soft tier). New imports are tagged live by the importer; this covers the
+    existing library.
+
+    HARD tier ("WIP"/"work in progress") always runs (the operator triggered the
+    scan); the SOFT tier (sketch/doodle, provisional source) runs only when
+    wip_soft_title_tagging_enabled, AFTER hard so a title matching both keeps the
+    trained hard tag (ON CONFLICT DO NOTHING). Keyset-paginated, restart-safe.
+
+    Deliberately NOT scheduled as a beat: a periodic re-run would re-apply to matching
+    posts and silently undo a manual WIP removal, so it stays an explicit operator
+    action (Settings → "Scan existing posts for WIP titles"). Returns rows applied.
+    """
+    from ..models import ImportSettings
+    from ..services.wip_title import (
+        SOFT_WIP_TITLE_SQL_PREFILTER,
+        WIP_TITLE_SOFT_SOURCE,
+        WIP_TITLE_SOURCE,
+        WIP_TITLE_SQL_PREFILTER,
+        matches_soft_wip_title,
+        matches_wip_title,
+        resolve_wip_tag_id,
+    )
+
+    SessionLocal = _sync_session_factory()
+    with SessionLocal() as session:
+        tag_id = resolve_wip_tag_id(session)
+        if tag_id is None:
+            log.warning(
+                "backfill_wip_title_tags: no `wip` system tag present; nothing to do"
+            )
+            return 0
+        settings = ImportSettings.load_sync(session)
+        applied = _backfill_wip_tier(
+            session, tag_id, WIP_TITLE_SQL_PREFILTER, matches_wip_title,
+            WIP_TITLE_SOURCE,
+        )
+        if settings.wip_soft_title_tagging_enabled:
+            applied += _backfill_wip_tier(
+                session, tag_id, SOFT_WIP_TITLE_SQL_PREFILTER, matches_soft_wip_title,
+                WIP_TITLE_SOFT_SOURCE,
+            )
+    if applied:
+        log.info("backfill_wip_title_tags: applied wip to %d image(s)", applied)
+    return applied
+
+
 @celery.task(name="backend.app.tasks.maintenance.vacuum_analyze")
 def vacuum_analyze() -> dict:
     """Periodic VACUUM (ANALYZE) over the high-churn tables (VACUUM_TABLES) to

backend/app/tasks/ml.py

@@ -105,9 +105,7 @@ def embed_image(self, image_id: int) -> dict:
             record = session.get(ImageRecord, image_id)
             if record is None:
                 return {"status": "missing", "image_id": image_id}
-            settings = session.execute(
-                select(MLSettings).where(MLSettings.id == 1)
-            ).scalar_one()
+            settings = MLSettings.load_sync(session)
 
             src = Path(record.path)
             is_vid = _is_video(src)
@@ -488,15 +486,10 @@ def scheduled_ccip_auto_apply() -> str:
     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 import ImageRegion, MLSettings, Tag, TagKind
     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
+    from ..services.ml.ccip import _FIGURE_KINDS
+    from ..services.ml.training_data import _applied_or_rejected, _l2norm
 
     SessionLocal = _sync_session_factory()
     with SessionLocal() as session:
@@ -521,7 +514,7 @@ def scheduled_ccip_auto_apply() -> str:
             )
             .join(Tag, Tag.id == image_tag.c.tag_id)
             .where(Tag.kind == TagKind.character)
-            .where(ImageRegion.kind.in_(fig))
+            .where(ImageRegion.kind.in_(_FIGURE_KINDS))
             .where(ImageRegion.ccip_embedding.is_not(None))
             .where(ImageRegion.image_record_id.in_(single))
         ).all()
@@ -532,29 +525,16 @@ def scheduled_ccip_auto_apply() -> str:
         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]
+        mats = [_l2norm(np.asarray(by_char[t], dtype=np.float32), np) 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)
+        skip = _applied_or_rejected(session, ref_tags)
 
         img_ids = list(session.execute(
             sa_select(ImageRegion.image_record_id)
-            .where(ImageRegion.kind.in_(fig), ImageRegion.ccip_embedding.is_not(None))
+            .where(ImageRegion.kind.in_(_FIGURE_KINDS), ImageRegion.ccip_embedding.is_not(None))
             .distinct()
         ).scalars())
 
@@ -566,7 +546,7 @@ def scheduled_ccip_auto_apply() -> str:
                 sa_select(ImageRegion.image_record_id, ImageRegion.ccip_embedding)
                 .where(
                     ImageRegion.image_record_id.in_(chunk),
-                    ImageRegion.kind.in_(fig),
+                    ImageRegion.kind.in_(_FIGURE_KINDS),
                     ImageRegion.ccip_embedding.is_not(None),
                 )
             ).all()
@@ -574,7 +554,7 @@ def scheduled_ccip_auto_apply() -> str:
             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)
+                q = _l2norm(np.asarray(vecs, dtype=np.float32), np)  # (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]:
@@ -599,18 +579,54 @@ def scheduled_ccip_auto_apply() -> str:
     soft_time_limit=1800, time_limit=2100,
 )
 def scheduled_presentation_auto_apply() -> str:
-    """Auto-hide presentation chrome (banner / editor screenshot) on a daily
-    passive sweep (#141). No-op unless presentation_auto_apply_enabled. Idempotent
-    — already-hidden images are skipped — so an interrupted run simply re-runs next
-    cycle (that IS the recovery). Wall-clock bounded by the task time limits."""
-    from ..services.ml.heads import presentation_auto_apply_sweep
+    """Auto-hide presentation chrome (banner) on a daily passive sweep (#141).
+    No-op unless presentation_auto_apply_enabled. Idempotent — already-tagged images
+    are skipped — so an interrupted run simply re-runs next cycle (that IS the
+    recovery). Wall-clock bounded by the task time limits."""
+    from ..services.ml.heads import system_tag_auto_apply_sweep
 
     SessionLocal = _sync_session_factory()
     with SessionLocal() as session:
-        result = presentation_auto_apply_sweep(session)
+        result = system_tag_auto_apply_sweep(session, mode="chrome")
     return f"applied={result['n_applied']} flagged={result['n_flagged']}"
 
 
+@celery.task(
+    name="backend.app.tasks.ml.scheduled_process_auto_apply",
+    soft_time_limit=1800, time_limit=2100,
+)
+def scheduled_process_auto_apply() -> str:
+    """Auto-apply the PROCESS system tags (wip / editor screenshot) on a daily
+    passive sweep (#1464) — provisional source, ring-loud review guard, image stays
+    VISIBLE. No-op unless process_auto_apply_enabled (opt-in). Idempotent —
+    already-tagged/rejected images are skipped — so an interrupted run just re-runs
+    next cycle (the recovery). Wall-clock bounded by the task time limits."""
+    from ..services.ml.heads import system_tag_auto_apply_sweep
+
+    SessionLocal = _sync_session_factory()
+    with SessionLocal() as session:
+        result = system_tag_auto_apply_sweep(session, mode="process")
+    return f"applied={result['n_applied']} flagged={result['n_flagged']}"
+
+
+@celery.task(
+    name="backend.app.tasks.ml.scheduled_soft_wip_conflict_audit",
+    soft_time_limit=1800, time_limit=2100,
+)
+def scheduled_soft_wip_conflict_audit() -> str:
+    """Ring-loud audit over the SOFT WIP-title cohort (#1474) — flag sketch/doodle
+    auto-tags that ALSO look like real content for review. No-op when there are no
+    content heads; idempotent (already-flagged images skipped). Runs regardless of
+    the process-sweep toggle, since soft-title tags come from the importer, not that
+    sweep. Wall-clock bounded by the task time limits."""
+    from ..services.ml.heads import soft_wip_conflict_audit
+
+    SessionLocal = _sync_session_factory()
+    with SessionLocal() as session:
+        result = soft_wip_conflict_audit(session)
+    return f"scanned={result['n_scanned']} flagged={result['n_flagged']}"
+
+
 @celery.task(name="backend.app.tasks.ml.prune_presentation_reviews")
 def prune_presentation_reviews() -> str:
     """Retention (rule 89): drop RESOLVED presentation-review flags older than 30

backend/app/tasks/translation.py

@@ -1,16 +1,32 @@
-"""Post-text translation Celery task (milestone 143).
+"""Post-text translation Celery tasks (milestone 143 + re-translate m146).
 
 Backfills non-English post title/description to the target language via the
 self-hosted Interpreter LAN service, storing the result + engine_version so
 viewing is instant and re-runs are cache-fast. Sync (Celery workers are sync),
 same pattern as the other backfill sweeps. No-op unless translation is enabled,
 a base URL is set, and the service is healthy.
+
+Curator does NO language detection of its own: each field's translation is
+accepted or rejected purely on Interpreter's reported engine + detected language
++ confidence (see ``_accept``) — a short English title Interpreter mis-labels as
+a European language scores below the latin-script floor and is kept as-is.
+
+Two entry points:
+- ``translate_posts`` — the periodic untranslated sweep (every 8h;
+  translated_source_lang IS NULL only), one bounded chunk per fire. The Settings
+  "Translate now" button calls it with ``drain=True`` to chase the tail
+  run-until-done and clear the whole backlog in a single press.
+- ``retranslate_posts`` — after a model change, resets the stored translation
+  columns for a scoped set of posts (all, or a given set of artists) so the
+  untranslated selection re-runs them, then chases the tail until drained
+  (run-until-done). The Interpreter cache keys on engine_version: a changed
+  model genuinely re-translates, an unchanged one is ~1ms cache-fast.
 """
 import logging
 from datetime import UTC, datetime
 
 from celery.exceptions import SoftTimeLimitExceeded
-from sqlalchemy import or_, select
+from sqlalchemy import func, or_, select, update
 
 from ..celery_app import celery
 from ..models import ImportSettings, Post
@@ -24,78 +40,359 @@ log = logging.getLogger(__name__)
 # limit; the rest resumes next cycle (idempotent — only untranslated posts are
 # picked, so an interrupted run just re-runs = rule-89 recovery).
 _MAX_POSTS_PER_RUN = 300
+# Short gap between run-until-done chunks so a big re-translate finishes on its
+# own without monopolising the maintenance_long worker in one uninterrupted run.
+_RETRANSLATE_COUNTDOWN = 5
+# When Interpreter drains mid-chunk (graceful restart), resume the bulk
+# re-translate after the service's Retry-After hint if it sent one, else this
+# default; capped so a bogus/huge hint can't park the work longer than the daily
+# beat's own safety net would.
+_INTERRUPT_BACKOFF = 60
+_INTERRUPT_BACKOFF_MAX = 900
+
+# --- Translation acceptance gate (Scribe rule 133; contract note #1347) -------
+# Curator does NO language detection of its own — it accepts or rejects a
+# translation purely on Interpreter's reported detection. CJK is script-detected
+# (kana/hangul/kanji) and reliably high-confidence, so ja/ko/zh are trusted
+# outright (pure-kanji Japanese can even come back labelled zh ~0.75, still
+# correctly translated). Latin-script detection is a real statistical
+# probability, so a short English title Interpreter mis-labels as a European
+# language scores low; require it to clear this floor, else keep the original.
+# Calibrated 2026-07-09 against fresh (uncached) probes once Interpreter returned
+# real langdetect confidence: genuine German detected at 1.0, while a correctly-
+# detected but ambiguous latin string dipped to 0.86 — so a single constant can't win.
+# The floor is now operator-tunable (ImportSettings.translation_min_confidence,
+# milestone 155) with a stricter 0.90 default; per-post overrides
+# (Post.translation_override) rescue the false negatives it skips. Genuine German
+# and mis-flagged short English both land ~0.86, and single-word mis-flags sit at
+# a confident 1.0 no floor catches. Real langdetect fixed some cases at the
+# source (some short English titles now detect as English → passthrough), so this
+# floor is a safety net, not the primary fix. Re-tune via the "Test translation"
+# box (send fresh text — cache hits report 1.0).
+_CJK_LANGS = frozenset({"ja", "ko", "zh"})
+_DEFAULT_MIN_LATIN_CONFIDENCE = 0.90
+
+
+def _interrupt_backoff(retry_after) -> int:
+    """Seconds to wait before resuming after an Interpreter interruption: the
+    server's Retry-After hint (capped), else the default."""
+    if retry_after and retry_after > 0:
+        return int(min(retry_after, _INTERRUPT_BACKOFF_MAX))
+    return _INTERRUPT_BACKOFF
 
 
 @celery.task(
     name="backend.app.tasks.translation.translate_posts",
     soft_time_limit=1800, time_limit=2100,
 )
-def translate_posts() -> str:
+def translate_posts(drain: bool = False) -> str:
     """Translate untranslated non-English post title/description (default target
     en) via Interpreter. Per-post [title, description] batch → per-post detected
     language. Passthrough / already-target posts are marked handled (source ==
     target) with no stored translation. 503 or a connection error interrupts the
     run (retry next cycle); 400 stops it (fix config); posts done so far stay
-    committed. No-op unless configured + healthy. Returns a summary string."""
+    committed. No-op unless configured + healthy. Returns a summary string.
+
+    ``drain`` (the Settings "Translate now" button) chases the tail
+    run-until-done: on a clean chunk with work still remaining it re-enqueues
+    itself until the untranslated backlog is zero, like ``retranslate_posts``. The
+    periodic beat leaves it False → one bounded chunk per fire (the 8h cadence
+    drives the rest, enough for the trickle of newly-imported posts)."""
     SessionLocal = _sync_session_factory()
     with SessionLocal() as session:
-        cfg = ImportSettings.load_sync(session)
-        if not cfg.translation_enabled or not cfg.interpreter_base_url.strip():
-            return "disabled"
-        base_url = cfg.interpreter_base_url.strip()
-        target = (cfg.translation_target_lang or "en").strip() or "en"
-        if not ic.health(base_url):
-            return "interpreter unavailable"
+        ready = _translation_config(session)
+        if isinstance(ready, str):
+            return ready
+        base_url, target, min_confidence = ready
+        posts = _select_untranslated(session, None, _MAX_POSTS_PER_RUN)
+        status, translated, retry_after = _translate_batch(
+            session, posts, base_url, target, min_confidence,
+        )
+        # Drain mode (manual "Translate now"): chase the tail until the backlog is
+        # zero, so one press clears the whole pile instead of one 300-chunk.
+        # Termination is guaranteed — every handled post leaves the untranslated
+        # set, so the remaining count strictly decreases each chunk.
+        if status == "ok" and drain:
+            remaining = _count_untranslated(session, None)
+            if remaining:
+                translate_posts.apply_async(
+                    (), {"drain": True}, countdown=_RETRANSLATE_COUNTDOWN,
+                )
+                log.info(
+                    "translate_posts: draining — %d remaining → re-enqueued",
+                    remaining,
+                )
+        # Interpreter drained mid-chunk (graceful restart): don't make a manual
+        # "Translate now" wait a whole beat cycle — re-enqueue after its
+        # Retry-After hint (or the default backoff), preserving `drain` so a bulk
+        # drain resumes cleanly. Self-terminating: once the service is down the
+        # health gate returns "interpreter unavailable" early.
+        elif status == "interrupted" and _count_untranslated(session, None):
+            delay = _interrupt_backoff(retry_after)
+            translate_posts.apply_async((), {"drain": drain}, countdown=delay)
+            log.info(
+                "translate_posts: interrupted (service draining) → retry in %ss",
+                delay,
+            )
+    return _summary(status, translated, len(posts))
 
-        posts = session.execute(
-            select(Post)
-            .where(Post.translated_source_lang.is_(None))
-            .where(or_(
-                Post.post_title.is_not(None), Post.description.is_not(None),
-            ))
-            .limit(_MAX_POSTS_PER_RUN)
-        ).scalars().all()
 
-        translated = 0
+@celery.task(
+    name="backend.app.tasks.translation.retranslate_posts",
+    soft_time_limit=1800, time_limit=2100,
+)
+def retranslate_posts(artist_ids=None, _reset_done=False) -> str:
+    """Re-translate posts after a model change. On the first call resets the
+    stored translation columns to NULL for the scoped posts — all artists when
+    ``artist_ids`` is falsy, else ``WHERE artist_id IN artist_ids`` — so the
+    normal untranslated selection re-runs them through Interpreter. Then handles
+    one bounded chunk and re-enqueues itself until the scoped backlog is drained
+    (run-until-done; ``_reset_done`` guards against wiping fresh work on the
+    follow-up chunks). No reset happens unless the service is configured +
+    healthy, so translations are never cleared when they can't be rebuilt."""
+    SessionLocal = _sync_session_factory()
+    with SessionLocal() as session:
+        ready = _translation_config(session)
+        if isinstance(ready, str):
+            return ready
+        base_url, target, min_confidence = ready
+
+        if not _reset_done:
+            n = _reset_translations(session, artist_ids)
+            log.info(
+                "retranslate_posts: reset %d post(s) (artist_ids=%s)",
+                n, artist_ids,
+            )
+
+        posts = _select_untranslated(session, artist_ids, _MAX_POSTS_PER_RUN)
+        status, translated, retry_after = _translate_batch(
+            session, posts, base_url, target, min_confidence,
+        )
+
+        # run-until-done: chase the tail when the chunk finished cleanly.
+        # Termination is guaranteed: every handled post leaves the NULL set, so
+        # the remaining count strictly decreases each chunk.
+        if status == "ok":
+            remaining = _count_untranslated(session, artist_ids)
+            if remaining:
+                retranslate_posts.apply_async(
+                    (),
+                    {"artist_ids": artist_ids, "_reset_done": True},
+                    countdown=_RETRANSLATE_COUNTDOWN,
+                )
+                log.info(
+                    "retranslate_posts: %d remaining → re-enqueued", remaining,
+                )
+        # Interpreter drained mid-chunk (graceful restart / 429 / 5xx): don't
+        # stall the bulk re-translate until the daily beat — resume it after the
+        # service's Retry-After hint (or the default backoff), with
+        # _reset_done=True so the fresh work is never re-wiped. Self-terminating:
+        # if the service is still down next run, _translation_config's health gate
+        # returns "interpreter unavailable" early and nothing re-enqueues.
+        elif status == "interrupted" and _count_untranslated(session, artist_ids):
+            delay = _interrupt_backoff(retry_after)
+            retranslate_posts.apply_async(
+                (),
+                {"artist_ids": artist_ids, "_reset_done": True},
+                countdown=delay,
+            )
+            log.info(
+                "retranslate_posts: interrupted (service draining) → retry in %ss",
+                delay,
+            )
+    return _summary(status, translated, len(posts))
+
+
+def _translation_config(session):
+    """Resolve (base_url, target, min_confidence) if translation is enabled +
+    healthy, else a short status string ("disabled" / "interpreter unavailable")
+    for the caller to return. Centralises the guard so translate/retranslate agree
+    exactly, including the operator-tunable acceptance floor."""
+    cfg = ImportSettings.load_sync(session)
+    if not cfg.translation_enabled or not cfg.interpreter_base_url.strip():
+        return "disabled"
+    base_url = cfg.interpreter_base_url.strip()
+    target = (cfg.translation_target_lang or "en").strip() or "en"
+    min_confidence = cfg.translation_min_confidence
+    if not ic.health(base_url):
+        return "interpreter unavailable"
+    return base_url, target, min_confidence
+
+
+def _untranslated_filter(stmt, artist_ids):
+    """Add the untranslated-post predicate (+ optional artist scope) to a
+    select/count over Post. Untranslated = translated_source_lang IS NULL with
+    some text to translate."""
+    stmt = stmt.where(
+        Post.translated_source_lang.is_(None)
+    ).where(or_(
+        Post.post_title.is_not(None), Post.description.is_not(None),
+    ))
+    if artist_ids:
+        stmt = stmt.where(Post.artist_id.in_(artist_ids))
+    return stmt
+
+
+def _select_untranslated(session, artist_ids, limit):
+    return session.execute(
+        _untranslated_filter(select(Post), artist_ids).limit(limit)
+    ).scalars().all()
+
+
+def _count_untranslated(session, artist_ids) -> int:
+    return int(session.execute(
+        _untranslated_filter(select(func.count(Post.id)), artist_ids)
+    ).scalar_one())
+
+
+def _reset_translations(session, artist_ids) -> int:
+    """Clear the stored translation columns for scoped, already-handled posts so
+    the untranslated sweep re-runs them. Only touches rows that were translated
+    (translated_source_lang IS NOT NULL) — untranslated rows are already NULL.
+    Skips 'keep original' posts (translation_override = 'original') so that choice
+    survives a Re-translate-all (milestone 155). Returns the row count reset
+    (commits it)."""
+    stmt = (
+        update(Post)
+        .where(Post.translated_source_lang.is_not(None))
+        .where(Post.translation_override != "original")
+        .values(
+            post_title_translated=None,
+            description_translated=None,
+            translated_source_lang=None,
+            translation_engine_version=None,
+            translated_at=None,
+        )
+    )
+    if artist_ids:
+        stmt = stmt.where(Post.artist_id.in_(artist_ids))
+    n = session.execute(stmt).rowcount
+    session.commit()
+    return n
+
+
+def _translate_batch(session, posts, base_url: str, target: str, min_confidence: float):
+    """Translate each post in the chunk with a per-post commit (an interrupted
+    run keeps progress). Returns (status, translated, retry_after) where status is
+    one of "ok" / "interrupted" (unavailable/drain) / "stopped" (400) / "timeout";
+    retry_after is the server's Retry-After hint in seconds on an interrupt, else
+    None."""
+    translated = 0
+    for post in posts:
         try:
-            for post in posts:
-                translated += _translate_one(session, post, base_url, target)
-                session.commit()   # per-post → an interrupted run keeps progress
-        except ic.InterpreterUnavailable:
+            translated += _translate_one(session, post, base_url, target, min_confidence)
+            session.commit()
+        except ic.InterpreterUnavailable as e:
             session.rollback()
-            return f"interrupted (service down) — translated={translated}"
+            return "interrupted", translated, getattr(e, "retry_after", None)
         except ic.InterpreterBadRequest as e:
             session.rollback()
-            log.warning("translate_posts bad request: %s", e)
-            return f"stopped (bad request) — translated={translated}"
+            log.warning("translate bad request: %s", e)
+            return "stopped", translated, None
         except SoftTimeLimitExceeded:
-            return f"time limit — translated={translated}"
-    return f"translated={translated} scanned={len(posts)}"
+            return "timeout", translated, None
+    return "ok", translated, None
 
 
-def _translate_one(session, post, base_url: str, target: str) -> int:
-    """Translate one post's title/description in place. Returns 1 if it stored a
-    translation, 0 for passthrough/empty (which still marks the post handled)."""
+def _summary(status: str, translated: int, scanned: int) -> str:
+    if status == "interrupted":
+        return f"interrupted (service down) — translated={translated}"
+    if status == "stopped":
+        return f"stopped (bad request) — translated={translated}"
+    if status == "timeout":
+        return f"time limit — translated={translated}"
+    return f"translated={translated} scanned={scanned}"
+
+
+def _accept(
+    language: str, confidence, min_confidence: float = _DEFAULT_MIN_LATIN_CONFIDENCE,
+) -> bool:
+    """Should curator store Interpreter's translation, or keep the original?
+    Consumes ONLY Interpreter's own detection (curator does none, Scribe rule
+    133): CJK languages are trusted regardless of the reported number; a
+    latin-script detection must clear ``min_confidence`` (the operator-tunable
+    ImportSettings.translation_min_confidence). A missing confidence fails OPEN
+    (accept), so a service that omits the field never silently drops a
+    translation. Per-post ``force`` overrides bypass this entirely (see
+    ``_translate_one``)."""
+    if (language or "").split("-", 1)[0].lower() in _CJK_LANGS:
+        return True
+    if confidence is None:
+        return True
+    return confidence >= min_confidence
+
+
+def _translate_field(
+    text: str, base_url: str, target: str, min_confidence: float, force: bool = False,
+):
+    """Translate ONE field independently. Returns (translated, source_lang,
+    engine_version), or (None, None, None) when there's nothing to store — empty
+    text, already the target language, a passthrough (engine "none"), or a
+    latin-script detection the acceptance gate rejects as too low-confidence (kept
+    as the original). ``force`` (a per-post 'force' override) bypasses the
+    confidence gate so a legitimately-foreign title Interpreter is only ~0.86 sure
+    about is still stored; a genuine passthrough stores nothing regardless (there
+    is no translation to force). Per-field (not aggregate first-item) detection so
+    a non-English description still translates when the title is already English."""
+    if not text:
+        return None, None, None
+    res = ic.translate([text], base_url=base_url, target=target)
+    detected = res["detected_lang"] or target
+    if detected == target or res["engine"] == "none":
+        return None, None, None
+    # Trust only Interpreter's own detection (Scribe rule 133): keep the original
+    # when a latin-script detection doesn't clear the confidence floor, so a short
+    # English title mis-labelled as e.g. German isn't rewritten into the archive.
+    # A 'force' override skips the gate — the operator is overriding a rejection.
+    if not force and not _accept(
+        detected, res.get("detected_confidence"), min_confidence,
+    ):
+        return None, None, None
+    return res["translations"][0], detected, res["engine_version"]
+
+
+def _store_translation(post, title_res, desc_res, target: str) -> int:
+    """Apply per-field (translated, source_lang, engine_version) results to a post
+    in place. Returns 1 if a translation was stored, 0 when the post is all
+    passthrough/empty — in which case the translated columns are CLEARED and the
+    post is marked handled (translated_source_lang = target). Clearing (not just
+    leaving) matters on re-apply: a 'keep original' override, or a re-translate
+    that now rejects a previously-accepted mis-flag, must remove the stale
+    translation, not keep it."""
+    title_tr, title_lang, title_ev = title_res
+    desc_tr, desc_lang, desc_ev = desc_res
+    if title_tr is None and desc_tr is None:
+        post.post_title_translated = None
+        post.description_translated = None
+        post.translated_source_lang = target
+        post.translation_engine_version = None
+        post.translated_at = None
+        return 0
+    post.post_title_translated = title_tr
+    post.description_translated = desc_tr
+    # Source lang = whichever field was actually non-target (for a mixed post,
+    # the translated field's language, not the already-English one).
+    post.translated_source_lang = title_lang or desc_lang
+    post.translation_engine_version = title_ev or desc_ev
+    post.translated_at = datetime.now(UTC)
+    return 1
+
+
+def _translate_one(
+    session, post, base_url: str, target: str, min_confidence: float,
+) -> int:
+    """Translate a post's title/description in place, each field independently,
+    honoring the per-post override (milestone 155): 'original' keeps the original
+    (clears any stored translation, no Interpreter call); 'force' translates even
+    below the confidence floor; 'auto' (default) runs the acceptance gate. Returns
+    1 if it stored a translation, else 0 (still marks the post handled so the sweep
+    won't revisit it)."""
+    if post.translation_override == "original":
+        return _store_translation(post, (None, None, None), (None, None, None), target)
+    force = post.translation_override == "force"
     title = (post.post_title or "").strip()
     desc = (html_to_plain(post.description) if post.description else "") or ""
     desc = desc.strip()
-    fields: list[tuple[str, str]] = []
-    if title:
-        fields.append(("title", title))
-    if desc:
-        fields.append(("desc", desc))
-    if not fields:
-        post.translated_source_lang = target   # nothing to translate → handled
-        return 0
-    res = ic.translate([t for _, t in fields], base_url=base_url, target=target)
-    detected = res["detected_lang"] or target
-    if detected == target or res["engine"] == "none":
-        post.translated_source_lang = target   # already target language → handled
-        return 0
-    by_field = {f: res["translations"][i] for i, (f, _) in enumerate(fields)}
-    post.post_title_translated = by_field.get("title")
-    post.description_translated = by_field.get("desc")
-    post.translated_source_lang = detected
-    post.translation_engine_version = res["engine_version"]
-    post.translated_at = datetime.now(UTC)
-    return 1
+    title_res = _translate_field(title, base_url, target, min_confidence, force=force)
+    desc_res = _translate_field(desc, base_url, target, min_confidence, force=force)
+    return _store_translation(post, title_res, desc_res, target)

docker-compose.yml

@@ -8,6 +8,35 @@
 # run `docker compose up` from this directory and switches images to
 # local builds + DEBUG logging.
 
+# Rolling-deploy safety (Swarm / `docker stack deploy`): update one task at a
+# time, START the new task before stopping the old (zero-downtime via the ingress
+# mesh), and if the new task doesn't reach a healthy state within `monitor`, roll
+# back to the previous image automatically. `monitor` is sized above web's
+# healthcheck start_period so a broken image that never goes healthy is caught.
+# Plain `docker compose up` ignores `deploy:` (it warns + skips), so the dev
+# override is unaffected. Referenced by each long-lived service below.
+x-deploy-policy: &deploy_policy
+  update_config:
+    order: start-first
+    failure_action: rollback
+    monitor: 90s
+  rollback_config:
+    order: start-first
+  restart_policy:
+    condition: any
+    delay: 10s
+
+# Worker liveness: ping THIS container's celery node over the broker. Lenient
+# (60s interval, 3 retries, 60s start_period) so a transient broker blip never
+# false-flags a worker into a rollback. `$$HOSTNAME` → `$HOSTNAME` for the shell;
+# celery's default node name is celery@<hostname> (the container id).
+x-celery-healthcheck: &celery_healthcheck
+  test: ["CMD-SHELL", "celery -A backend.app.celery_app:celery inspect ping -d celery@$$HOSTNAME --timeout 10 >/dev/null 2>&1"]
+  interval: 60s
+  timeout: 15s
+  retries: 3
+  start_period: 60s
+
 services:
   redis:
     image: redis:7-alpine
@@ -47,6 +76,24 @@ services:
   web:
     image: git.fabledsword.com/bvandeusen/fabledcurator:dev
     command: ["web"]
+    # Graceful shutdown: give the container time to drain in-flight work on a
+    # deploy (docker SIGTERMs, then SIGKILLs after this window — default is only
+    # 10s, far too short for real jobs). Hypercorn/Celery both warm-shut-down on
+    # SIGTERM; per-lane values sized to typical task length. Anything that still
+    # outruns the window is re-queued (task_reject_on_worker_lost) and re-driven
+    # by the 5-min recovery sweeps, so a kill never corrupts. web = short HTTP
+    # requests + the occasional file download.
+    stop_grace_period: 30s
+    # Liveness for rolling deploys: /api/health is a no-DB 200 (just proves the
+    # app booted + serves HTTP after `alembic upgrade head`). start_period covers
+    # the migration + boot so a slow start isn't mis-flagged.
+    healthcheck:
+      test: ["CMD-SHELL", "python -c \"import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://localhost:8080/api/health', timeout=5).status==200 else 1)\""]
+      interval: 15s
+      timeout: 6s
+      retries: 3
+      start_period: 40s
+    deploy: *deploy_policy
     ports:
       - "${PORT:-8080}:8080"
     environment: &app_env
@@ -77,6 +124,10 @@ services:
   worker:
     image: git.fabledsword.com/bvandeusen/fabledcurator:dev
     command: ["worker"]
+    # Drain in-flight import/thumbnail/download tasks before SIGKILL on deploy.
+    stop_grace_period: 90s
+    healthcheck: *celery_healthcheck
+    deploy: *deploy_policy
     environment:
       <<: *app_env
       CELERY_QUEUES: default,import,thumbnail,download
@@ -93,6 +144,10 @@ services:
   scheduler:
     image: git.fabledsword.com/bvandeusen/fabledcurator:dev
     command: ["scheduler"]
+    # Quick maintenance/scan lane + beat — short tasks, modest drain window.
+    stop_grace_period: 60s
+    healthcheck: *celery_healthcheck
+    deploy: *deploy_policy
     environment:
       <<: *app_env
       CELERY_QUEUES: maintenance,scan
@@ -110,6 +165,12 @@ services:
   maintenance-long:
     image: git.fabledsword.com/bvandeusen/fabledcurator:dev
     command: ["worker"]
+    # Longest lane (DB backups, library audits, translation backfill) — give it
+    # the most room to finish a chunk gracefully. Chunked + idempotent, so a job
+    # that still outruns this resumes cleanly next run rather than corrupting.
+    stop_grace_period: 180s
+    healthcheck: *celery_healthcheck
+    deploy: *deploy_policy
     environment:
       <<: *app_env
       CELERY_QUEUES: maintenance_long
@@ -125,6 +186,10 @@ services:
   ml-worker:
     image: git.fabledsword.com/bvandeusen/fabledcurator-ml:dev
     command: ["ml-worker"]
+    # A single GPU inference pass can run tens of seconds — let it finish.
+    stop_grace_period: 120s
+    healthcheck: *celery_healthcheck
+    deploy: *deploy_policy
     environment:
       <<: *app_env
     volumes:

extension/background/background.js

@@ -31,6 +31,68 @@ browser.runtime.onInstalled.addListener(() => ensureInitialized());
 browser.runtime.onStartup.addListener(() => ensureInitialized());
 ensureInitialized().catch(e => console.error('init failed:', e));
 
+// ---- Extension self-update check (#1489) ----
+// Installed per-instance from the operator's FC host, so Firefox's static
+// update_url can't apply (each instance has a different host). Instead ask the
+// configured backend for the latest published version and nudge the operator to
+// reinstall the freshly-signed XPI — surfaced as a popup banner (on demand) and
+// a toolbar badge (daily). /api/extension/manifest is public and returns
+// {version, latest_url, sha256}; the XPI is served from the web root (not /api).
+
+function versionIsNewer(candidate, current) {
+  // Dotted numeric compare so 1.0.10 > 1.0.9 (a plain string compare wouldn't).
+  const a = String(candidate).split('.').map(n => parseInt(n, 10) || 0);
+  const b = String(current).split('.').map(n => parseInt(n, 10) || 0);
+  for (let i = 0; i < Math.max(a.length, b.length); i++) {
+    if ((a[i] || 0) !== (b[i] || 0)) return (a[i] || 0) > (b[i] || 0);
+  }
+  return false;
+}
+
+async function checkForUpdateInfo() {
+  await ensureInitialized();
+  if (!api.isConfigured()) return { updateAvailable: false, configured: false };
+  let info;
+  try {
+    info = await api.getExtensionManifest();
+  } catch (e) {
+    return { updateAvailable: false, error: e.message };
+  }
+  const currentVersion = browser.runtime.getManifest().version;
+  const latestVersion = info && info.version ? info.version : null;
+  // latest_url is served from the web root, not the JSON API.
+  const base = api.webRoot();
+  return {
+    updateAvailable: !!latestVersion && versionIsNewer(latestVersion, currentVersion),
+    currentVersion,
+    latestVersion,
+    xpiUrl: info && info.latest_url ? `${base}${info.latest_url}` : null,
+  };
+}
+
+async function refreshUpdateBadge() {
+  let r;
+  try { r = await checkForUpdateInfo(); } catch { return; }
+  try {
+    await browser.action.setBadgeText({ text: r.updateAvailable ? '↑' : '' });
+    if (r.updateAvailable) {
+      await browser.action.setBadgeBackgroundColor({ color: '#F4BA7A' });
+      await browser.action.setTitle({ title: `FabledCurator — update available (v${r.latestVersion})` });
+    } else {
+      await browser.action.setTitle({ title: 'FabledCurator' });
+    }
+  } catch { /* action API unavailable — non-fatal */ }
+}
+
+// Daily proactive check (needs the "alarms" permission). create() is idempotent
+// by name, so re-running it on each event-page load is safe.
+browser.alarms.create('fc-update-check', { periodInMinutes: 24 * 60, delayInMinutes: 1 });
+browser.alarms.onAlarm.addListener((alarm) => {
+  if (alarm.name === 'fc-update-check') refreshUpdateBadge();
+});
+browser.runtime.onStartup.addListener(() => refreshUpdateBadge());
+browser.runtime.onInstalled.addListener(() => refreshUpdateBadge());
+
 // ---- Discord token capture via webRequest ----
 
 browser.webRequest.onBeforeSendHeaders.addListener(
@@ -148,6 +210,21 @@ browser.webRequest.onBeforeRedirect.addListener(
   { urls: ['https://app-api.pixiv.net/web/v1/users/auth/pixiv/callback*'] },
 );
 
+// Extract → verify → upload one cookie-auth platform. Returns a structured
+// outcome so the two callers (EXPORT_COOKIES single, EXPORT_ALL_COOKIES) shape
+// their own response + skip semantics. Verifies the captured cookies are
+// actually live BEFORE uploading, so a confirmed-stale session doesn't overwrite
+// good FC-side credentials; platforms with no verify config (v.ok === null) fall
+// through to upload.
+async function exportPlatformCookies(key) {
+  const cookies = await extractCookiesForPlatform(key);
+  if (cookies.length === 0) return { status: 'empty' };
+  const v = await verifyCookiesForPlatform(key);
+  if (v.ok === false) return { status: 'stale', reason: v.reason, cookieCount: cookies.length };
+  await api.uploadCredentials(key, 'cookies', toNetscapeFormat(cookies));
+  return { status: 'ok', cookieCount: cookies.length, verified: v.ok === true };
+}
+
 // ---- Message router ----
 
 browser.runtime.onMessage.addListener(async (msg) => {
@@ -192,22 +269,14 @@ browser.runtime.onMessage.addListener(async (msg) => {
       if (!platform) return { error: `Unknown platform: ${key}` };
       try {
         if (platform.authType === 'cookies') {
-          const cookies = await extractCookiesForPlatform(key);
-          if (cookies.length === 0) return { error: 'No cookies found — log in first.' };
-          // Verify the captured cookies are actually live BEFORE
-          // uploading. Skips upload on confirmed-stale sessions so we
-          // don't overwrite FC-side credentials with garbage. Platforms
-          // without a verify config (verify.ok === null) fall through
-          // to upload as before.
-          const v = await verifyCookiesForPlatform(key);
-          if (v.ok === false) {
+          const r = await exportPlatformCookies(key);
+          if (r.status === 'empty') return { error: 'No cookies found — log in first.' };
+          if (r.status === 'stale') {
             return {
-              error: `Captured ${cookies.length} ${platform.name} cookies but they don't appear authenticated (${v.reason}). Log in again in this browser, then retry.`,
+              error: `Captured ${r.cookieCount} ${platform.name} cookies but they don't appear authenticated (${r.reason}). Log in again in this browser, then retry.`,
             };
           }
-          const data = toNetscapeFormat(cookies);
-          await api.uploadCredentials(key, 'cookies', data);
-          return { success: true, cookieCount: cookies.length, verified: v.ok === true };
+          return { success: true, cookieCount: r.cookieCount, verified: r.verified };
         }
         if (key === 'discord') {
           if (!discordToken) return { error: 'Open discord.com to capture a token first.' };
@@ -235,18 +304,10 @@ browser.runtime.onMessage.addListener(async (msg) => {
           continue;
         }
         try {
-          const cookies = await extractCookiesForPlatform(key);
-          if (cookies.length === 0) {
-            results[key] = { skipped: true, reason: 'no cookies' };
-            continue;
-          }
-          const v = await verifyCookiesForPlatform(key);
-          if (v.ok === false) {
-            results[key] = { error: `verify failed: ${v.reason}` };
-            continue;
-          }
-          await api.uploadCredentials(key, 'cookies', toNetscapeFormat(cookies));
-          results[key] = { success: true, cookieCount: cookies.length, verified: v.ok === true };
+          const r = await exportPlatformCookies(key);
+          if (r.status === 'empty') results[key] = { skipped: true, reason: 'no cookies' };
+          else if (r.status === 'stale') results[key] = { error: `verify failed: ${r.reason}` };
+          else results[key] = { success: true, cookieCount: r.cookieCount, verified: r.verified };
         } catch (e) {
           results[key] = { error: e.message };
         }
@@ -283,11 +344,9 @@ browser.runtime.onMessage.addListener(async (msg) => {
       }
 
     case 'OPEN_ARTIST_PAGE': {
-      // apiUrl is configured with the /api suffix (see
-      // options/options.html placeholder); the SPA artist route is
-      // /artist/:slug, served from the same origin. Strip /api so the
-      // browser-level URL hits the Vue router, not the JSON API.
-      const base = (api.baseUrl || '').replace(/\/+$/, '').replace(/\/api$/, '');
+      // The SPA artist route (/artist/:slug) is served from the web root, not
+      // the JSON API — see api.webRoot().
+      const base = api.webRoot();
       const slug = encodeURIComponent(msg.slug || '');
       if (!base || !slug) return { error: 'apiUrl or slug missing' };
       try {
@@ -298,6 +357,9 @@ browser.runtime.onMessage.addListener(async (msg) => {
       }
     }
 
+    case 'CHECK_UPDATE':
+      return await checkForUpdateInfo();
+
     default:
       return { error: `Unknown message type: ${msg.type}` };
   }

extension/lib/api.js

@@ -89,6 +89,19 @@ class FabledCuratorAPI {
     const qs = new URLSearchParams({ url }).toString();
     return this.request('GET', `/extension/probe?${qs}`);
   }
+  // Latest published extension version on this instance — drives the in-app
+  // update prompt. Public endpoint (no key needed, but request() sends it
+  // harmlessly). Returns {version, xpi_url, latest_url, sha256}.
+  getExtensionManifest() {
+    return this.request('GET', '/extension/manifest');
+  }
+
+  // The web/SPA root: baseUrl with the trailing slash + `/api` suffix stripped.
+  // Where the Vue router (artist pages) and the served XPI live, NOT the JSON
+  // API. Used by OPEN_ARTIST_PAGE + the self-update check.
+  webRoot() {
+    return (this.baseUrl || '').replace(/\/+$/, '').replace(/\/api$/, '');
+  }
 
   // Connection test = the cheapest read with auth.
   testConnection() {

extension/lib/platforms.js

@@ -86,7 +86,16 @@ const PLATFORMS = {
  * script to decide whether to show the floating "Add as source" button.
  */
 const PLATFORM_ARTIST_PATTERNS = {
-  patreon:       /^https?:\/\/(www\.)?patreon\.com\/(?!home$|search\b|messages\b|notifications\b|library\b|settings\b|posts\b|c\/)[^/?#]+\/?$/i,
+  // Patreon serves the same creator under three URL shapes (see backend
+  // patreon_resolver._VANITY_RE): bare `patreon.com/Atole`, `c/` prefix, and
+  // `cw/` "creator workspace" — the last is the URL you land on once you're
+  // SUBSCRIBED, which is exactly when the button matters. Match all three, and
+  // drop the single-segment end-anchor so a creator's inner page
+  // (…/cw/Atole/posts, …/Atole/membership) also injects the button. Nav pages
+  // (home/search/…/posts permalink) stay excluded. Mirrors extension_service
+  // ._PLATFORM_PATTERNS — keep in sync (operator-flagged 2026-07-13: button
+  // vanished once subscribed because the old pattern only matched the bare root).
+  patreon:       /^https?:\/\/(www\.)?patreon\.com\/(?:cw\/|c\/)?(?!(?:home|search|messages|notifications|library|settings|posts)(?:[\/?#]|$))[^/?#]+/i,
   subscribestar: /^https?:\/\/(www\.)?subscribestar\.(com|adult)\/(?!feed$|messages$|library$)[^/?#]+\/?$/i,
   hentaifoundry: /^https?:\/\/(www\.)?hentai-foundry\.com\/user\/[^/?#]+/i,
   deviantart:    /^https?:\/\/(www\.)?deviantart\.com\/(?!home$|watch\b|tag\b|browse\b)[^/?#]+\/?$/i,

extension/manifest.json

@@ -1,7 +1,7 @@
 {
   "manifest_version": 3,
   "name": "FabledCurator",
-  "version": "1.0.7",
+  "version": "1.0.9",
   "description": "Export cookies from supported platforms to FabledCurator and add creators as sources in one click.",
 
   "browser_specific_settings": {
@@ -22,7 +22,8 @@
     "tabs",
     "activeTab",
     "webRequest",
-    "webRequestBlocking"
+    "webRequestBlocking",
+    "alarms"
   ],
 
   "host_permissions": [

extension/package.json

@@ -1,6 +1,6 @@
 {
   "name": "fabledcurator-extension",
-  "version": "1.0.7",
+  "version": "1.0.9",
   "private": true,
   "description": "Firefox extension for FabledCurator",
   "scripts": {
@@ -10,6 +10,6 @@
     "sign":  "web-ext sign --source-dir=. --no-config-discovery --ignore-files package.json package-lock.json web-ext-artifacts node_modules README.md .gitignore --channel=unlisted --api-key=$WEB_EXT_API_KEY --api-secret=$WEB_EXT_API_SECRET"
   },
   "devDependencies": {
-    "web-ext": "^8.0.0"
+    "web-ext": "^10.0.0"
   }
 }

extension/popup/popup.css

@@ -72,6 +72,17 @@ body {
 .btn.block { display: block; width: 100%; margin-top: 8px; }
 .btn.link { background: none; color: var(--on-surface-variant); padding: 4px; }
 .btn.link:hover { color: var(--accent); }
+.btn.small { padding: 6px 12px; font-size: 13px; }
+
+/* In-app update prompt (accent-tinted so it reads as an actionable notice). */
+.update-banner {
+  display: flex; align-items: center; gap: 10px;
+  margin: 10px 10px 0; padding: 10px 12px;
+  background: rgba(244, 186, 122, 0.12);
+  border: 1px solid rgba(244, 186, 122, 0.4);
+  border-radius: 6px;
+}
+#update-text { flex: 1; font-size: 13px; }
 
 .source-row .play {
   background: none; border: none; color: var(--on-surface-variant);

extension/popup/popup.html

@@ -20,6 +20,11 @@
   </section>
 
   <section id="main-content" class="main hidden">
+    <div id="update-banner" class="update-banner hidden">
+      <span id="update-text"></span>
+      <button id="update-btn" class="btn primary small">Update</button>
+    </div>
+
     <nav class="tabs">
       <button class="tab active" data-tab="platforms">Platforms</button>
       <button class="tab" data-tab="sources">Sources</button>

extension/popup/popup.js

@@ -2,6 +2,15 @@ document.addEventListener('DOMContentLoaded', init);
 
 const CONNECTION_TEST_INTERVAL = 2 * 60 * 1000;
 
+// A centered muted note div — the loading / empty state shared by the platform
+// and sources lists.
+function mutedNote(text) {
+  const d = document.createElement('div');
+  d.style.cssText = 'text-align:center;padding:18px;color:var(--on-surface-variant);';
+  d.textContent = text;
+  return d;
+}
+
 async function init() {
   try {
     const cfg = await browser.runtime.sendMessage({ type: 'GET_CONFIG' });
@@ -14,6 +23,7 @@ async function init() {
     setupEventListeners();
     showPlatformsLoading();
     testConnectionIfNeeded();
+    checkForUpdate();
     loadPlatformStatus().catch(e => showError(`Failed to load platforms: ${e.message}`));
   } catch (e) {
     showSetupRequired();
@@ -37,10 +47,7 @@ function showSetupRequired() {
 function showPlatformsLoading() {
   const c = document.getElementById('platforms-list');
   c.textContent = '';
-  const d = document.createElement('div');
-  d.style.cssText = 'text-align:center;padding:18px;color:var(--on-surface-variant);';
-  d.textContent = 'Loading platforms…';
-  c.appendChild(d);
+  c.appendChild(mutedNote('Loading platforms…'));
 }
 
 async function testConnectionIfNeeded() {
@@ -63,6 +70,26 @@ function updateConnectionDot(connected) {
   d.title = connected ? 'Connected to FabledCurator' : 'Disconnected';
 }
 
+// Nudge to reinstall when the configured instance publishes a newer signed XPI
+// (the extension is self-hosted, so there's no Firefox auto-update). Never
+// blocks the popup — a failed check just leaves the banner hidden.
+async function checkForUpdate() {
+  try {
+    const r = await browser.runtime.sendMessage({ type: 'CHECK_UPDATE' });
+    if (r && r.updateAvailable && r.xpiUrl) showUpdateBanner(r);
+  } catch { /* non-fatal */ }
+}
+
+function showUpdateBanner(r) {
+  document.getElementById('update-text').textContent =
+    `Update available — v${r.latestVersion} (installed v${r.currentVersion})`;
+  // Opening the signed XPI triggers Firefox's native install prompt.
+  document.getElementById('update-btn').addEventListener('click', () => {
+    browser.tabs.create({ url: r.xpiUrl });
+  });
+  document.getElementById('update-banner').classList.remove('hidden');
+}
+
 async function loadPlatformStatus() {
   const status = await browser.runtime.sendMessage({ type: 'GET_PLATFORM_STATUS' });
   const c = document.getElementById('platforms-list');
@@ -162,10 +189,7 @@ async function exportAllCookies() {
 async function loadSources() {
   const c = document.getElementById('sources-list');
   c.textContent = '';
-  const d = document.createElement('div');
-  d.style.cssText = 'text-align:center;padding:18px;color:var(--on-surface-variant);';
-  d.textContent = 'Loading sources…';
-  c.appendChild(d);
+  c.appendChild(mutedNote('Loading sources…'));
   const r = await browser.runtime.sendMessage({ type: 'LIST_SOURCES' });
   c.textContent = '';
   if (r.error) {
@@ -176,10 +200,7 @@ async function loadSources() {
     return;
   }
   if (!r.sources || r.sources.length === 0) {
-    const empty = document.createElement('div');
-    empty.style.cssText = 'text-align:center;padding:18px;color:var(--on-surface-variant);';
-    empty.textContent = 'No sources yet.';
-    c.appendChild(empty);
+    c.appendChild(mutedNote('No sources yet.'));
     return;
   }
   for (const src of r.sources) c.appendChild(createSourceRow(src));

frontend/package.json

@@ -4,30 +4,28 @@
   "private": true,
   "type": "module",
   "engines": {
-    "node": ">=22"
+    "node": ">=24"
   },
   "scripts": {
     "dev": "vite",
     "build": "vite build",
     "preview": "vite preview",
-    "test:unit": "vitest run",
-    "check": "vue-tsc --noEmit"
+    "test:unit": "vitest run"
   },
   "dependencies": {
-    "vue": "^3.4.0",
-    "vue-router": "^4.3.0",
-    "pinia": "^2.1.0",
-    "vuetify": "^3.5.0",
+    "vue": "^3.5.0",
+    "vue-router": "^5.0.0",
+    "pinia": "^3.0.0",
+    "vuetify": "^4.0.0",
     "@mdi/font": "^7.4.0"
   },
   "devDependencies": {
-    "@vitejs/plugin-vue": "^5.0.0",
-    "vite": "^5.2.0",
-    "vue-tsc": "^2.0.0",
-    "vite-plugin-vuetify": "^2.0.0",
+    "@vitejs/plugin-vue": "^6.0.0",
+    "vite": "^8.0.0",
+    "vite-plugin-vuetify": "^2.1.0",
     "sass": "^1.71.0",
-    "vitest": "^2.1.0",
+    "vitest": "^4.0.0",
     "@vue/test-utils": "^2.4.0",
-    "happy-dom": "^15.0.0"
+    "happy-dom": "^20.0.0"
   }
 }

frontend/src/components/AppShell.vue

@@ -18,11 +18,11 @@ const route = useRoute()
 <style scoped>
 .fc-content {
   min-height: 100vh;
-  /* Push initial viewport content below the sticky TopNav. Without
-     this, some views' first rows / form fields / table headers can
-     end up obscured by the navbar (depending on parent overflow
-     context interacting with position: sticky). Scrolled-down content
-     still slides under the nav — the gradient-fade design is intact. */
-  padding-top: 64px;
+  /* NO padding-top: the TopNav is position:sticky, so it already reserves its
+     own space in the v-app flex column — content flows directly below it. The
+     old 64px padding-top was a leftover from a FIXED navbar and double-counted
+     that space, leaving a large empty band at the top of EVERY view (and pushing
+     the full-height calc(100vh - 64px) views down so they overflowed). Removed
+     2026-07-13. Scrolled content still slides under the sticky nav as before. */
 }
 </style>

frontend/src/components/AppSnackbar.vue

@@ -1,7 +1,7 @@
 <template>
   <v-snackbar
     v-model="show" :color="color" location="bottom right" timeout="4000"
-    multi-line elevation="4"
+    min-height="68" elevation="4"
   >
     {{ message }}
     <template #actions>

frontend/src/components/TopNav.vue

@@ -1,5 +1,5 @@
 <template>
-  <header class="fc-topnav">
+  <header ref="navEl" class="fc-topnav" :class="{ 'fc-topnav--chrome': hasStickyChrome }">
     <div class="fc-nav-left">
       <RouterLink :to="FRONT_DOOR" class="fc-brand" aria-label="FabledCurator home">
         <img src="/favicon.svg" alt="" class="fc-brand__glyph" width="22" height="22" />
@@ -64,13 +64,39 @@
 </template>
 
 <script setup>
-import { computed, onMounted } from 'vue'
+import { computed, onBeforeUnmount, onMounted, ref } from 'vue'
+import { useRoute } from 'vue-router'
 import router, { FRONT_DOOR } from '../router.js'
 import { useSystemStore } from '../stores/system.js'
 import PipelineStatusChip from './PipelineStatusChip.vue'
 
 const system = useSystemStore()
-onMounted(() => system.refreshHealth())
+
+// Publish the nav's REAL height as --fc-nav-h so full-height workspaces
+// (Explore/Subscriptions) and sticky sub-headers pin to it exactly instead of a
+// hardcoded 64px that Vuetify 4's MD3 sizing broke — the Explore breadcrumb was
+// tucking under a taller nav (#1481). ResizeObserver keeps it live as the nav
+// reflows (per-view teleported actions, mobile breakpoint, chip state changes).
+const navEl = ref(null)
+let navRO = null
+onMounted(() => {
+  system.refreshHealth()
+  if (navEl.value && 'ResizeObserver' in window) {
+    navRO = new ResizeObserver(() => {
+      const h = navEl.value?.offsetHeight
+      if (h) document.documentElement.style.setProperty('--fc-nav-h', `${h}px`)
+    })
+    navRO.observe(navEl.value)
+  }
+})
+onBeforeUnmount(() => { navRO?.disconnect() })
+
+// Views that pin a sticky sub-header (filter bar / tabs) directly under the nav
+// declare `meta.stickyChrome`. On those, the nav doesn't fade to transparent at
+// its bottom — it hands off at the shared seam alpha so the sub-header can
+// continue the SAME fade (see .fc-chrome-continues in app.css). One gradient.
+const route = useRoute()
+const hasStickyChrome = computed(() => !!route.meta?.stickyChrome)
 
 // Every route with a meta.title is a nav entry. Order by meta.navOrder —
 // router.getRoutes() does NOT guarantee declaration order, so explicit numbers
@@ -119,16 +145,35 @@ const health = computed(() => {
   align-items: center;
   gap: 1rem;
   padding: 0.75rem 1rem;
-  /* Obsidian (#14171A = 20,23,26) gradient fade — content scrolls under it. */
+  /* Obsidian (#14171A) fade — content scrolls under it. Holds high (0.92 →
+     0.84) through the top half, then eases to transparent over the bottom
+     quarter so it tails off softly instead of a straight line to a hard edge
+     (operator 2026-07-13). Shared --fc-chrome-rgb keeps it in sync with the
+     sub-header continuation. */
   background: linear-gradient(
     to bottom,
-    rgba(20, 23, 26, 0.92) 0%,
-    rgba(20, 23, 26, 0.65) 60%,
-    rgba(20, 23, 26, 0) 100%
+    rgba(var(--fc-chrome-rgb), 0.92) 0%,
+    rgba(var(--fc-chrome-rgb), 0.84) 50%,
+    rgba(var(--fc-chrome-rgb), 0.55) 75%,
+    rgba(var(--fc-chrome-rgb), 0) 100%
   );
   backdrop-filter: blur(2px);
   -webkit-backdrop-filter: blur(2px);
 }
+/* On a view with a sticky sub-header pinned beneath (meta.stickyChrome), the nav
+   stops fading at the shared seam alpha instead of going fully transparent — the
+   sub-header (.fc-chrome-continues) picks the fade up from there, so the two read
+   as one continuous gradient. Compound selector out-specifies .fc-topnav so it
+   wins regardless of Vite's production CSS ordering. --fc-chrome-* come from the
+   global :root in app.css (custom props inherit into scoped styles). */
+.fc-topnav.fc-topnav--chrome {
+  background: linear-gradient(
+    to bottom,
+    rgba(var(--fc-chrome-rgb), 0.92) 0%,
+    rgba(var(--fc-chrome-rgb), 0.84) 60%,
+    rgba(var(--fc-chrome-rgb), var(--fc-chrome-seam)) 100%
+  );
+}
 
 .fc-brand {
   display: flex;

frontend/src/components/artist/ArtistManagementTab.vue

@@ -101,6 +101,47 @@
       </v-card>
     </v-dialog>
 
+    <section class="fc-artist-mgmt__sec">
+      <h2 class="fc-h2">Translation</h2>
+      <p class="fc-muted text-body-2 mb-3">
+        Re-translate every post by {{ overview.name }} through the current
+        Interpreter model — clears the stored translations and rebuilds them.
+        Use this after switching translation models to refresh just this artist.
+      </p>
+      <div class="d-flex align-center flex-wrap" style="gap: 10px;">
+        <v-btn
+          size="small" variant="tonal" rounded="pill"
+          prepend-icon="mdi-translate"
+          :loading="retranslating" :disabled="!translationEnabled"
+          @click="confirmRetranslate = true"
+        >Re-translate posts</v-btn>
+        <span v-if="!translationEnabled" class="fc-muted text-caption">
+          Translation is off — enable it in Settings → Maintenance.
+        </span>
+      </div>
+    </section>
+
+    <!-- m146: per-artist re-translate — clears + rebuilds this artist's stored
+         translations (used after a translation-model change). -->
+    <v-dialog v-model="confirmRetranslate" max-width="440">
+      <v-card>
+        <v-card-title class="fc-h2">Re-translate {{ overview.name }}?</v-card-title>
+        <v-card-text class="text-body-2">
+          Clears the stored translation for every post by
+          <strong>{{ overview.name }}</strong> and re-runs them through your
+          current Interpreter model. Unchanged text comes back from the cache
+          instantly. Runs in the background until done.
+        </v-card-text>
+        <v-card-actions>
+          <v-spacer />
+          <v-btn variant="text" @click="confirmRetranslate = false">Cancel</v-btn>
+          <v-btn color="accent" :loading="retranslating" @click="onRetranslate">
+            Re-translate
+          </v-btn>
+        </v-card-actions>
+      </v-card>
+    </v-dialog>
+
     <section class="fc-artist-mgmt__sec">
       <h2 class="fc-h2">Danger zone</h2>
       <ArtistDangerZone
@@ -113,9 +154,11 @@
 </template>
 
 <script setup>
-import { computed, ref } from 'vue'
+import { computed, onMounted, ref } from 'vue'
 import { useRouter, RouterLink } from 'vue-router'
 
+import { useApi } from '../../composables/useApi.js'
+import { useImportStore } from '../../stores/import.js'
 import { useSourcesStore } from '../../stores/sources.js'
 import { toast } from '../../utils/toast.js'
 import ArtistDangerZone from './ArtistDangerZone.vue'
@@ -125,8 +168,38 @@ const props = defineProps({
 })
 
 const router = useRouter()
+const api = useApi()
+const importStore = useImportStore()
 const sources = useSourcesStore()
 
+// m146: per-artist re-translate. Gated on translation being enabled globally
+// (the endpoint 400s otherwise) — read the shared import settings once.
+const translationEnabled = ref(false)
+const retranslating = ref(false)
+const confirmRetranslate = ref(false)
+
+onMounted(async () => {
+  try {
+    await importStore.loadSettings()
+    translationEnabled.value = !!importStore.settings?.translation_enabled
+  } catch { /* non-fatal — the button just stays disabled */ }
+})
+
+async function onRetranslate () {
+  retranslating.value = true
+  try {
+    await api.post('/api/settings/translation/retranslate', {
+      body: { artist_id: props.overview.id },
+    })
+    confirmRetranslate.value = false
+    toast({ text: `Re-translating ${props.overview.name}…`, type: 'success' })
+  } catch (e) {
+    toast({ text: `Re-translate failed: ${e.message}`, type: 'error' })
+  } finally {
+    retranslating.value = false
+  }
+}
+
 // #130: move a source into another artist.
 const moveOpen = ref(false)
 const moveSource = ref(null)

frontend/src/components/cleanup/MinDimensionCard.vue

@@ -10,7 +10,7 @@
       filter, applied retroactively to the existing library.
     </p>
 
-    <v-row dense>
+    <v-row density="compact">
       <v-col cols="6">
         <v-text-field
           v-model.number="minW" label="Min width (px)" type="number"

frontend/src/components/cleanup/SingleColorAuditCard.vue

@@ -13,7 +13,7 @@
       cadence as the transparency audit.
     </p>
 
-    <v-row dense>
+    <v-row density="compact">
       <v-col cols="6">
         <v-text-field
           v-model.number="threshold" label="Threshold (0–1)"

frontend/src/components/common/SettingNumberField.vue

@@ -0,0 +1,56 @@
+<!--
+  Canonical settings number field (DRY pass #161): a compact numeric v-text-field
+  with a built-in clamp to [min,max] on commit. Hand-rolled identically across the
+  ML settings cards (HeadsCard x6, CropProposersCard, VideoEmbeddingCard).
+
+  The clamp is the point: the cards previously sent Number(raw) straight to the
+  API, so an out-of-range value bounced off the API's 400 validator (only
+  TranslationCard clamped). This is now the single home for that clamp.
+
+  Binds `modelValue` (v-model) and emits `change` on blur/enter AFTER clamping, so
+  the parent's save reads the already-clamped value — same as the prior
+  `v-model.number` + `@change=save` pattern.
+-->
+<template>
+  <v-text-field
+    :model-value="modelValue"
+    :label="label"
+    type="number"
+    :min="min"
+    :max="max"
+    :step="step"
+    :disabled="disabled"
+    :density="density" hide-details
+    :style="{ maxWidth }"
+    @update:model-value="v => emit('update:modelValue', v)"
+    @change="onCommit"
+  />
+</template>
+
+<script setup>
+const props = defineProps({
+  modelValue: { type: [Number, String], default: null },
+  label: { type: String, default: '' },
+  min: { type: [Number, String], default: null },
+  max: { type: [Number, String], default: null },
+  step: { type: [Number, String], default: 1 },
+  maxWidth: { type: String, default: '200px' },
+  density: { type: String, default: 'compact' },
+  disabled: { type: Boolean, default: false },
+})
+const emit = defineEmits(['update:modelValue', 'change'])
+
+function onCommit() {
+  // On blur/enter: coerce to a number and clamp to [min,max] so an out-of-range
+  // value never reaches the API. props.modelValue reflects the latest keystroke
+  // (kept in sync by the passthrough above); re-emit the clamped number, then let
+  // the parent persist.
+  let n = Number(props.modelValue)
+  if (!Number.isNaN(n)) {
+    if (props.min !== null && props.min !== '') n = Math.max(Number(props.min), n)
+    if (props.max !== null && props.max !== '') n = Math.min(Number(props.max), n)
+    if (n !== Number(props.modelValue)) emit('update:modelValue', n)
+  }
+  emit('change')
+}
+</script>

frontend/src/components/common/SettingToggleRow.vue

@@ -0,0 +1,42 @@
+<!--
+  Canonical settings toggle row (DRY pass #161): an accent icon + an uppercase
+  .fc-section-h label + a right-aligned switch. Hand-rolled identically in the
+  ML settings cards (HeadsCard x3, CropProposersCard, MLBackfillCard).
+
+  Two-way binds `modelValue` (so the parent switch state stays optimistic) AND
+  emits `change` with the new boolean, so the parent can persist + revert on
+  failure — matching the prior `v-model` + `@update:model-value=handler` pattern.
+-->
+<template>
+  <div class="d-flex align-center mb-1" style="gap: 10px;">
+    <v-icon v-if="icon" size="18" :color="iconColor">{{ icon }}</v-icon>
+    <span class="fc-section-h">{{ label }}</span>
+    <v-switch
+      :model-value="modelValue"
+      :loading="loading"
+      :disabled="disabled"
+      hide-details density="compact" color="success" class="ml-auto"
+      @update:model-value="onSwitch"
+    />
+  </div>
+</template>
+
+<script setup>
+defineProps({
+  modelValue: { type: Boolean, default: false },
+  label: { type: String, default: '' },
+  icon: { type: String, default: '' },
+  // Icon tint. Default accent; pass null for the theme default (e.g. when a row
+  // is off). null (not undefined) so the default doesn't override it.
+  iconColor: { type: String, default: 'accent' },
+  loading: { type: Boolean, default: false },
+  disabled: { type: Boolean, default: false },
+})
+const emit = defineEmits(['update:modelValue', 'change'])
+
+function onSwitch(v) {
+  const b = !!v
+  emit('update:modelValue', b)
+  emit('change', b)
+}
+</script>

frontend/src/components/common/TagPicker.vue

@@ -14,10 +14,10 @@
     @update:search="onSearch"
     @update:model-value="onPick"
   >
-    <template #item="{ props: itemProps, item }">
-      <v-list-item v-bind="itemProps" :title="item.raw.name">
+    <template #item="{ props: itemProps, internalItem }">
+      <v-list-item v-bind="itemProps" :title="internalItem.raw.name">
         <template #subtitle>
-          {{ item.raw.fandom_name ? `character · ${item.raw.fandom_name}` : item.raw.kind }}
+          {{ internalItem.raw.fandom_name ? `character · ${internalItem.raw.fandom_name}` : internalItem.raw.kind }}
         </template>
       </v-list-item>
     </template>

frontend/src/components/gallery/GalleryFilterBar.vue

@@ -1,5 +1,5 @@
 <template>
-  <div class="fc-filterbar-wrap">
+  <div class="fc-filterbar-wrap fc-chrome-continues">
    <div class="fc-filterbar">
     <v-autocomplete
       v-model="selected"
@@ -13,14 +13,14 @@
       @update:search="onSearch"
       @update:model-value="onPick"
     >
-      <template #item="{ props: itemProps, item }">
-        <v-list-item v-bind="itemProps" :title="item.raw.name">
+      <template #item="{ props: itemProps, internalItem }">
+        <v-list-item v-bind="itemProps" :title="internalItem.raw.name">
           <template #prepend>
-            <v-icon size="small">{{ iconFor(item.raw) }}</v-icon>
+            <v-icon size="small">{{ iconFor(internalItem.raw) }}</v-icon>
           </template>
           <template #subtitle>
-            {{ item.raw.kind === 'artist' ? 'artist'
-              : (item.raw.fandom_name ? `character · ${item.raw.fandom_name}` : item.raw.kind) }}
+            {{ internalItem.raw.kind === 'artist' ? 'artist'
+              : (internalItem.raw.fandom_name ? `character · ${internalItem.raw.fandom_name}` : internalItem.raw.kind) }}
           </template>
         </v-list-item>
       </template>
@@ -306,27 +306,17 @@ function pushFilter(mutate) {
    frosted block pinned directly under the 64px TopNav and continuous with it. */
 .fc-filterbar-wrap {
   position: sticky;
-  top: 64px;
+  top: var(--fc-nav-h, 64px); /* pins at the nav's real measured bottom (#1481) */
   z-index: 5;
   /* Attach to the TopNav: cancel the v-container's top padding (pt-2 = 8px)
      so the bar sits flush at 64px even at scroll 0 — without this it detaches
      and a gap shows through when scrolled to the top. */
   margin-top: -8px;
   margin-bottom: 12px;
-  /* EXACT same gradiated obsidian (#14171A = 20,23,26) frost as the TopNav so
-     the two read as one continuous piece of chrome — images scroll visibly
-     under both. The nav's gradient fades to transparent at ITS bottom; this
-     bar re-darkens at its top, so a faint seam (the page/image showing through
-     the nav's transparent edge) separates them when scrolled to the very top,
-     while under-scroll they frost as one. */
-  background: linear-gradient(
-    to bottom,
-    rgba(20, 23, 26, 0.92) 0%,
-    rgba(20, 23, 26, 0.65) 60%,
-    rgba(20, 23, 26, 0) 100%
-  );
-  backdrop-filter: blur(2px);
-  -webkit-backdrop-filter: blur(2px);
+  /* The frost itself (obsidian fade + blur) is the shared .fc-chrome-continues
+     primitive: it CONTINUES the TopNav's fade from the seam alpha to transparent
+     rather than re-darkening, so the nav + bar read as one gradient (operator
+     2026-07-13). This block only owns the sticky positioning now. */
 }
 .fc-filterbar {
   display: flex;
@@ -341,6 +331,20 @@ function pushFilter(mutate) {
 .fc-filterbar-wrap :deep(.v-btn-group) {
   background-color: rgba(20, 23, 26, 0.72);
 }
+/* Media toggle (All / Images / Videos) as ONE cohesive segmented control.
+   FC's global VBtn { rounded: 'pill' } default made Vuetify 4 pill-round each
+   SEGMENT individually, so the rounded ends collided at the joins — the shapes
+   landed awkwardly on the button edges (operator 2026-07-13). Square the inner
+   segments (over the pill utility's !important) and clip the group to a single
+   8px outline (matches the chips/tiles rounding elsewhere in the app). Radius
+   only — no height change, so the bar height and nav offset are untouched. */
+.fc-filterbar-wrap :deep(.v-btn-toggle) {
+  border-radius: 8px;
+  overflow: hidden;
+}
+.fc-filterbar-wrap :deep(.v-btn-toggle .v-btn) {
+  border-radius: 0 !important;
+}
 .fc-filterbar__search { max-width: 320px; min-width: 200px; }
 .fc-filterbar__chips { display: flex; align-items: center; gap: 6px; flex-wrap: wrap; }
 /* The tag chips' bodies toggle include/exclude — signal they're clickable. */

frontend/src/components/gallery/HiddenReviewStrip.vue

@@ -1,14 +1,15 @@
 <template>
-  <!-- Auto-hidden chrome that ALSO looked like real content — surfaced PROACTIVELY
-       atop the gallery whenever there's something to review (NOT gated on the
-       Show-hidden toggle, so misfires can't go unnoticed), most-concerning first,
-       with keep / un-hide (#141). Renders nothing when there's nothing to review. -->
-  <section v-if="items.length" class="fc-review" aria-label="Hidden images to review">
+  <!-- System-tag auto-applies (chrome hides / process WIP tags) that ALSO looked
+       like real content — surfaced PROACTIVELY atop the gallery whenever there's
+       something to review (NOT gated on the Show-hidden toggle, so misfires can't
+       go unnoticed), most-concerning first, with keep / remove (#141, #1464).
+       Renders nothing when there's nothing to review. -->
+  <section v-if="items.length" class="fc-review" aria-label="Auto-tagged images to review">
     <div class="fc-review__head">
       <v-icon size="18" color="warning">mdi-alert-outline</v-icon>
       <span class="fc-review__title">
-        {{ items.length }} auto-hidden {{ items.length === 1 ? 'image' : 'images' }}
-        may be real content — review before they stay hidden
+        {{ items.length }} auto-tagged {{ items.length === 1 ? 'image' : 'images' }}
+        may be real content — review
       </span>
     </div>
     <div class="fc-review__cards">
@@ -26,16 +27,16 @@
           >
             also looks like <strong>{{ it.conflict_name || 'content' }}</strong>
           </div>
-          <div class="fc-review-card__tag">hidden as {{ it.tag_name }}</div>
+          <div class="fc-review-card__tag">{{ tagLine(it) }}</div>
           <div class="fc-review-card__acts">
             <button
               type="button" class="fc-review-btn fc-review-btn--keep"
               :disabled="busy.includes(keyOf(it))" @click="resolve(it, 'keep')"
-            >Keep hidden</button>
+            >{{ keepLabel(it) }}</button>
             <button
               type="button" class="fc-review-btn fc-review-btn--unhide"
               :disabled="busy.includes(keyOf(it))" @click="resolve(it, 'unhide')"
-            >Un-hide</button>
+            >{{ removeLabel(it) }}</button>
           </div>
         </div>
       </div>
@@ -54,6 +55,11 @@ const items = ref([])
 const busy = ref([])
 
 function keyOf(it) { return `${it.image_id}:${it.tag_id}` }
+// Chrome flags hide the image (keep-hidden / un-hide); process flags leave it
+// visible and just tagged (keep-tag / remove-tag). Same endpoints, different words.
+function tagLine(it) { return (it.mode === 'process' ? 'auto-tagged ' : 'hidden as ') + it.tag_name }
+function keepLabel(it) { return it.mode === 'process' ? 'Keep tag' : 'Keep hidden' }
+function removeLabel(it) { return it.mode === 'process' ? 'Remove tag' : 'Un-hide' }
 
 async function load() {
   // Fetched unconditionally on mount — the strip prompts for pending misfires
@@ -71,7 +77,8 @@ async function resolve(it, action) {
     await api.post(`/api/gallery/hidden-review/${it.image_id}/${it.tag_id}/${action}`)
     items.value = items.value.filter((x) => keyOf(x) !== k)
     if (action === 'unhide') {
-      toast({ text: `Un-hidden — “${it.tag_name}” removed; it'll train the head`, type: 'success' })
+      const verb = it.mode === 'process' ? 'Removed' : 'Un-hidden'
+      toast({ text: `${verb} — “${it.tag_name}” removed; it'll train the head`, type: 'success' })
     }
   } catch (e) {
     toast({

frontend/src/components/modal/AliasPickerDialog.vue

@@ -1,72 +0,0 @@
-<template>
-  <v-card>
-    <v-card-title>Treat as alias for…</v-card-title>
-    <v-card-text>
-      <p class="text-caption mb-2">
-        Pick the existing tag the model's prediction should map to. All
-        future predictions of this name will resolve to your tag.
-      </p>
-      <v-autocomplete
-        v-model="selectedId"
-        v-model:menu="menuOpen"
-        :items="results"
-        :item-title="(t) => t.fandom_name ? `${t.name} — ${t.fandom_name}` : t.name"
-        :item-value="(t) => t.id"
-        :loading="loading"
-        label="Canonical tag"
-        no-filter clearable density="compact"
-        @update:search="onSearch"
-        @keydown.enter.capture="onEnter"
-      />
-    </v-card-text>
-    <v-card-actions>
-      <v-spacer />
-      <v-btn @click="$emit('cancel')">Cancel</v-btn>
-      <v-btn
-        color="primary" rounded="pill" :disabled="!selectedId"
-        @click="$emit('confirm', selectedId)"
-      >Use this tag</v-btn>
-    </v-card-actions>
-  </v-card>
-</template>
-
-<script setup>
-import { ref } from 'vue'
-import { useApi } from '../../composables/useApi.js'
-import { useAcceptOnEnter } from '../../composables/useAcceptOnEnter.js'
-
-const props = defineProps({ category: { type: String, required: true } })
-const emit = defineEmits(['confirm', 'cancel'])
-
-const api = useApi()
-const results = ref([])
-const loading = ref(false)
-const selectedId = ref(null)
-let debounce = null
-
-// Enter on the closed dropdown confirms the selection instead of re-opening it.
-const { menuOpen, onEnter } = useAcceptOnEnter(() => {
-  if (selectedId.value != null) emit('confirm', selectedId.value)
-})
-
-function onSearch(q) {
-  if (debounce) clearTimeout(debounce)
-  debounce = setTimeout(async () => {
-    const query = (q || '').trim()
-    if (!query) { results.value = []; return }
-    loading.value = true
-    try {
-      // Scope the autocomplete to the prediction's category where it
-      // maps to a tag kind. Only 'character' surfaces as both a
-      // suggestion category and a tag kind now ('artist' + 'copyright'
-      // retired); other categories search unscoped.
-      const kind = props.category === 'character' ? 'character' : null
-      const params = { q: query, limit: 20 }
-      if (kind) params.kind = kind
-      results.value = await api.get('/api/tags/autocomplete', { params })
-    } finally {
-      loading.value = false
-    }
-  }, 200)
-}
-</script>

frontend/src/components/modal/SuggestionItem.vue

@@ -11,10 +11,6 @@
       {{ suggestion.display_name }}
       <span v-if="suggestion.rejected" class="fc-suggestion__rejected-tag"
         title="You rejected this for this image — un-reject to recover">rejected</span>
-      <span v-else-if="suggestion.creates_new_tag" class="fc-suggestion__new"
-        title="No matching tag yet — accepting creates it">+ new</span>
-      <span v-else-if="suggestion.via_alias" class="fc-suggestion__alias"
-        :title="`Mapped from the tagger's “${suggestion.raw_name}” via an alias`">alias</span>
     </span>
     <span class="fc-suggestion__score">{{ scorePct }}</span>
     <!-- Green ✓ / red ✗ pair (operator-asked 2026-06-28) mirrors the eval
@@ -46,40 +42,14 @@
         @click="$emit('dismiss', suggestion)"
       ><v-icon size="16">mdi-close</v-icon></button>
     </div>
-    <!-- Modal-safe kebab is baked into KebabMenu (this row lives in the
-         teleported image modal — #711). Only rendered when an alias action
-         applies — dismiss now lives on the red ✗, so a centroid hit with no
-         alias option has no menu. -->
-    <KebabMenu
-      v-if="hasMenu"
-      class="fc-suggestion__menu" size="small" variant="outlined"
-      :label="`More actions for ${suggestion.display_name}`"
-    >
-      <!-- Alias is a tagger-prediction remap, so only offer it for tagger
-           suggestions with a raw model key that aren't already aliased.
-           Centroid hits (raw_name null) have nothing to alias. -->
-      <v-list-item
-        v-if="suggestion.raw_name && !suggestion.via_alias"
-        @click="$emit('alias', suggestion)"
-      >
-        <v-list-item-title>Treat as alias for…</v-list-item-title>
-      </v-list-item>
-      <v-list-item
-        v-if="suggestion.via_alias"
-        @click="$emit('remove-alias', suggestion)"
-      >
-        <v-list-item-title>Remove alias</v-list-item-title>
-      </v-list-item>
-    </KebabMenu>
   </div>
 </template>
 
 <script setup>
 import { computed, inject } from 'vue'
-import KebabMenu from '../common/KebabMenu.vue'
 
 const props = defineProps({ suggestion: { type: Object, required: true } })
-defineEmits(['accept', 'alias', 'remove-alias', 'dismiss', 'undismiss'])
+defineEmits(['accept', 'dismiss', 'undismiss'])
 
 // #1206: on hover, tell the image viewer which crop produced this suggestion so
 // it highlights that region. Provided by ImageViewer/Explore; a no-op elsewhere.
@@ -92,12 +62,6 @@ function onLeave () {
 }
 
 const scorePct = computed(() => `${Math.round(props.suggestion.score * 100)}%`)
-// Kebab now only carries alias actions: show it when this suggestion can be
-// aliased (raw model key, not yet aliased) or is already aliased (so it can be
-// un-aliased). Centroid hits (no raw_name, no alias) have an empty menu → hide.
-const hasMenu = computed(() =>
-  Boolean(props.suggestion.raw_name) || Boolean(props.suggestion.via_alias)
-)
 </script>
 
 <style scoped>
@@ -119,26 +83,6 @@ const hasMenu = computed(() =>
   color: rgb(var(--v-theme-on-surface));
   overflow: hidden; text-overflow: ellipsis; white-space: nowrap;
 }
-.fc-suggestion__new {
-  display: inline-block;
-  font-size: 10px; font-weight: 600;
-  color: rgb(var(--v-theme-accent));
-  background: rgba(var(--v-theme-accent), 0.12);
-  border: 1px solid rgb(var(--v-theme-accent), 0.4);
-  padding: 1px 6px; border-radius: 999px;
-  margin-left: 6px;
-  text-transform: uppercase; letter-spacing: 0.04em;
-}
-.fc-suggestion__alias {
-  display: inline-block;
-  font-size: 10px; font-weight: 600;
-  color: rgb(var(--v-theme-on-surface-variant));
-  background: rgb(var(--v-theme-surface-light));
-  border: 1px solid rgb(var(--v-theme-surface-light));
-  padding: 1px 6px; border-radius: 999px;
-  margin-left: 6px;
-  text-transform: uppercase; letter-spacing: 0.04em;
-}
 .fc-suggestion__score {
   flex: 0 0 auto; min-width: 38px; text-align: right;
   font-size: 11px;
@@ -166,10 +110,6 @@ const hasMenu = computed(() =>
   background: transparent; color: rgb(var(--v-theme-on-surface-variant));
   border: 1px solid rgb(var(--v-theme-on-surface-variant), 0.5);
 }
-.fc-suggestion__menu {
-  flex: 0 0 auto;
-}
-
 /* Rejected state: the row stays put (recovery), dimmed + red-edged so it
    reads as "handled, negative" without shouting over live suggestions. */
 .fc-suggestion--rejected {

frontend/src/components/modal/SuggestionsCategoryGroup.vue

@@ -26,8 +26,6 @@
         v-for="(s, i) in items" :key="`${s.display_name}-${i}`"
         :suggestion="s"
         @accept="$emit('accept', $event)"
-        @alias="$emit('alias', $event)"
-        @remove-alias="$emit('remove-alias', $event)"
         @dismiss="$emit('dismiss', $event)"
         @undismiss="$emit('undismiss', $event)"
       />
@@ -45,7 +43,7 @@ const props = defineProps({
   collapsible: { type: Boolean, default: false },
   defaultOpen: { type: Boolean, default: true }
 })
-defineEmits(['accept', 'alias', 'remove-alias', 'dismiss', 'undismiss', 'reject-all'])
+defineEmits(['accept', 'dismiss', 'undismiss', 'reject-all'])
 
 // Still-unhandled suggestions (not yet rejected) — how many "Reject rest" clears.
 const rejectableCount = computed(() => props.items.filter((s) => !s.rejected).length)

frontend/src/components/modal/SuggestionsPanel.vue

@@ -20,48 +20,39 @@
            first, so false positives are easy to spot and reject (reject-to-train
            for these heads). Small set — collapsible, open by default. -->
       <SuggestionsCategoryGroup
-        v-if="store.byCategory.system && store.byCategory.system.length"
-        label="System" :items="store.byCategory.system"
+        v-if="store.aboveByCategory.system && store.aboveByCategory.system.length"
+        label="System" :items="store.aboveByCategory.system"
         collapsible :default-open="true"
-        @accept="onAccept" @alias="onAlias" @remove-alias="onRemoveAlias"
+        @accept="onAccept"
         @dismiss="onDismiss" @undismiss="onUndismiss"
         @reject-all="onRejectAll('system')"
       />
       <SuggestionsCategoryGroup
         v-for="cat in peopleCats" :key="cat"
-        v-show="store.byCategory[cat] && store.byCategory[cat].length"
-        :label="labelFor(cat)" :items="store.byCategory[cat] || []"
-        @accept="onAccept" @alias="onAlias" @remove-alias="onRemoveAlias"
+        v-show="store.aboveByCategory[cat] && store.aboveByCategory[cat].length"
+        :label="labelFor(cat)" :items="store.aboveByCategory[cat] || []"
+        @accept="onAccept"
         @dismiss="onDismiss" @undismiss="onUndismiss"
         @reject-all="onRejectAll(cat)"
       />
       <SuggestionsCategoryGroup
-        v-if="store.byCategory.general && store.byCategory.general.length"
-        label="General" :items="store.byCategory.general"
+        v-if="store.aboveByCategory.general && store.aboveByCategory.general.length"
+        label="General" :items="store.aboveByCategory.general"
         collapsible :default-open="true"
-        @accept="onAccept" @alias="onAlias" @remove-alias="onRemoveAlias"
+        @accept="onAccept"
         @dismiss="onDismiss" @undismiss="onUndismiss"
         @reject-all="onRejectAll('general')"
       />
     </div>
-
-    <v-dialog v-model="aliasDialog" max-width="480">
-      <AliasPickerDialog
-        v-if="aliasTarget"
-        :category="aliasTarget.category"
-        @confirm="onAliasConfirm" @cancel="aliasDialog = false"
-      />
-    </v-dialog>
   </section>
 </template>
 
 <script setup>
 import { toast } from '../../utils/toast.js'
-import { computed, ref, watch } from 'vue'
+import { computed, watch } from 'vue'
 import { useSuggestionsStore, CATEGORY_LABELS } from '../../stores/suggestions.js'
 import { useModalStore } from '../../stores/modal.js'
 import SuggestionsCategoryGroup from './SuggestionsCategoryGroup.vue'
-import AliasPickerDialog from './AliasPickerDialog.vue'
 
 const props = defineProps({
   imageId: { type: Number, required: true },
@@ -100,13 +91,14 @@ const peopleCats = ['character']
 function labelFor(c) { return CATEGORY_LABELS[c] || c }
 
 const isEmpty = computed(() =>
-  Object.values(store.byCategory).every(list => !list || list.length === 0)
+  Object.values(store.aboveByCategory).every(list => !list || list.length === 0)
 )
 
 watch(() => props.imageId, (id) => {
   if (id == null) return
-  store.load(id)        // panel: curated, ≥ threshold
-  store.loadAll(id)     // dropdown: full prediction set (low-confidence included)
+  // One fetch (min=0) backs both surfaces: the panel reads aboveByCategory, the
+  // typed tag-input dropdown reads the full set. No second request.
+  store.load(id)
 }, { immediate: true })
 
 // After a successful accept/alias-accept, refresh the modal's current
@@ -125,31 +117,6 @@ async function onAccept(s) {
     toast({ text: `Accept failed: ${e.message}`, type: 'error' })
   }
 }
-
-const aliasDialog = ref(false)
-const aliasTarget = ref(null)
-function onAlias(s) { aliasTarget.value = s; aliasDialog.value = true }
-async function onAliasConfirm(canonicalTagId) {
-  try {
-    await store.aliasAccept(aliasTarget.value, canonicalTagId)
-    aliasDialog.value = false
-    await host.reloadTags()
-    emit('accepted')
-  } catch (e) {
-    toast({ text: `Alias failed: ${e.message}`, type: 'error' })
-  }
-}
-
-// Undo the model-key→tag mapping behind an aliased suggestion. The store
-// reloads suggestions so the prediction reverts to its raw form; the applied
-// canonical tag (if any) stays, so no tag-rail reload is needed.
-async function onRemoveAlias(s) {
-  try {
-    await store.removeAlias(s)
-  } catch (e) {
-    toast({ text: `Remove alias failed: ${e.message}`, type: 'error' })
-  }
-}
 </script>
 
 <style scoped>

frontend/src/components/modal/TagAutocomplete.vue

@@ -17,7 +17,14 @@
       density="compact" class="fc-tag-autocomplete__list"
     >
       <template v-for="(row, idx) in rows" :key="row.key">
-        <!-- Existing tag match (server autocomplete). -->
+        <!-- One unified row per DB tag (server autocomplete). Every suggestion is
+             a canonical tag now, so when the model ALSO scored this tag for the
+             image the row just carries its confidence (🔧 %) in place of the
+             redundant kind label — the coloured leading icon already shows kind.
+             That means a searched tag that's also a suggestion shows its % on ONE
+             row, with no dedup and no flicker. Picking it emits pick-existing;
+             TagPanel.findPending routes a matching suggestion through accept() so
+             the acceptance is still recorded + it drops from the panel. -->
         <v-list-item
           v-if="row.type === 'hit'"
           :active="idx === highlight" @click="onPickRow(row)"
@@ -32,32 +39,18 @@
             <span v-if="row.hit.fandom_name" class="text-caption">— {{ row.hit.fandom_name }}</span>
           </v-list-item-title>
           <template #append>
-            <span class="text-caption">{{ row.hit.kind }}</span>
-          </template>
-        </v-list-item>
-
-        <!-- ML suggestion for THIS image that matches the typed query. Picking
-             it routes through the same accept path as the Suggestions panel, so
-             it's recorded + drops out of the panel (operator-asked 2026-06-07). -->
-        <v-list-item
-          v-else-if="row.type === 'suggestion'"
-          :active="idx === highlight" @click="onPickRow(row)"
-          class="fc-tag-autocomplete__sugg"
-        >
-          <template #prepend>
-            <v-icon size="small" :color="store.colorFor(row.sugg.category)">
-              {{ iconFor(row.sugg.category) }}
-            </v-icon>
-          </template>
-          <v-list-item-title>
-            {{ row.sugg.display_name }}
-            <span v-if="row.sugg.creates_new_tag" class="text-caption">— new</span>
-          </v-list-item-title>
-          <template #append>
-            <span class="fc-tag-autocomplete__sugg-tag">
+            <span
+              v-if="row.sugg"
+              class="fc-tag-autocomplete__sugg-tag"
+              :class="{ 'fc-tag-autocomplete__sugg-tag--below': !row.sugg.above_threshold }"
+              :title="row.sugg.above_threshold
+                ? 'The model suggests this tag for this image'
+                : 'The model scored this tag below its suggest threshold'"
+            >
               <v-icon size="x-small">mdi-auto-fix</v-icon>
               {{ scorePct(row.sugg) }}
             </span>
+            <span v-else class="text-caption">{{ row.hit.kind }}</span>
           </template>
         </v-list-item>
 
@@ -100,11 +93,10 @@ import { useSuggestionsStore } from '../../stores/suggestions.js'
 import { useInflightToken } from '../../composables/useInflightToken.js'
 import FandomPicker from './FandomPicker.vue'
 
-const emit = defineEmits(['pick-existing', 'pick-new', 'accept-suggestion', 'cancel'])
-// The host surface's applied tags (host.current?.tags). Both dropdown sections
-// filter against this so a just-added tag drops out of the search the moment
-// the chip rail updates, not after the next modal refresh (operator-asked
-// 2026-07-03).
+const emit = defineEmits(['pick-existing', 'pick-new', 'cancel'])
+// The host surface's applied tags (host.current?.tags). The dropdown filters
+// against this so a just-added tag drops out of the search the moment the chip
+// rail updates, not after the next modal refresh (operator-asked 2026-07-03).
 const props = defineProps({
   appliedTags: { type: Array, default: () => [] },
 })
@@ -238,9 +230,6 @@ const createLabel = computed(() =>
 function scorePct (s) { return `${Math.round(s.score * 100)}%` }
 
 const appliedIds = computed(() => new Set(props.appliedTags.map(t => t.id)))
-const appliedNames = computed(() =>
-  new Set(props.appliedTags.map(t => `${t.kind}:${(t.name || '').toLowerCase()}`)),
-)
 
 // Server matches minus the image's applied tags. allowCreate/sameNameCharExists
 // keep reading the RAW hits — they reason about the tag universe (does this tag
@@ -249,49 +238,29 @@ const visibleHits = computed(() =>
   hits.value.filter(h => !appliedIds.value.has(h.id)),
 )
 
-// This image's suggestions that match the typed query, minus any the server
-// autocomplete already returned (same name+kind) so a tag never shows twice.
-// Sources the FULL prediction set (allByCategory, down to the store floor) — NOT
-// the threshold-filtered panel list — so a low-confidence action/feature the
-// model saw can be typed and accepted in canonical formatting instead of being
-// hand-entered as a custom tag (operator-asked 2026-06-09). The typed query is
-// the only filter; the threshold no longer hides anything here.
-const suggestionHits = computed(() => {
-  const q = parsedName.value.toLowerCase()
-  if (!q) return []
-  const seen = new Set(visibleHits.value.map(h => `${h.kind}:${h.name.toLowerCase()}`))
-  const out = []
-  for (const list of Object.values(suggestions.allByCategory)) {
+// This image's suggestions keyed by canonical tag id, so a matching DB-tag row
+// can show the model's confidence inline. Every suggestion is a canonical tag
+// now (tagging-v2), so the id is the join key — no name/kind matching, no dedup,
+// no flicker. Rejected suggestions are excluded: a dismissed tag shouldn't
+// advertise a score in the type-to-add dropdown (un-reject lives in the panel).
+const suggByTagId = computed(() => {
+  const m = new Map()
+  for (const list of Object.values(suggestions.byCategory)) {
     for (const s of list || []) {
-      // Rejected suggestions now stay in allByCategory (flagged) so the panel
-      // can show + un-reject them; keep them OUT of the type-to-add dropdown,
-      // whose job is finding a tag to ADD (un-reject lives in the panel).
       if (s.rejected) continue
-      // Already on the image (matched by canonical id or name+kind): nothing
-      // to add. Covers the window between an add and the next suggestions
-      // fetch, where the stale row would otherwise still be pickable.
-      if (s.canonical_tag_id != null && appliedIds.value.has(s.canonical_tag_id)) continue
-      const key = `${s.category}:${s.display_name.toLowerCase()}`
-      if (appliedNames.value.has(key)) continue
-      if (!s.display_name.toLowerCase().includes(q)) continue
-      if (seen.has(key)) continue
-      seen.add(key)
-      out.push(s)
+      if (s.canonical_tag_id != null) m.set(s.canonical_tag_id, s)
     }
   }
-  // Best matches first; cap generously so a specific typed query surfaces its
-  // matches even when many predictions exist, while the list stays scrollable.
-  out.sort((a, b) => b.score - a.score)
-  return out.slice(0, 20)
+  return m
 })
 
 // One ordered list backing both the rendered dropdown and keyboard nav, so the
-// highlight index maps 1:1 to a row regardless of which section it's in.
+// highlight index maps 1:1 to a row. Each hit is annotated with its suggestion
+// (score) when the model scored that tag for this image.
 const rows = computed(() => {
-  const r = visibleHits.value.map(h => ({ type: 'hit', key: `h${h.id}`, hit: h }))
-  for (const s of suggestionHits.value) {
-    r.push({ type: 'suggestion', key: `s${s.category}:${s.display_name}`, sugg: s })
-  }
+  const r = visibleHits.value.map(h => ({
+    type: 'hit', key: `h${h.id}`, hit: h, sugg: suggByTagId.value.get(h.id) || null,
+  }))
   if (allowCreate.value) r.push({ type: 'create', key: 'create' })
   return r
 })
@@ -313,16 +282,9 @@ function moveHighlight (delta) {
 // Dispatch a chosen dropdown row by its type.
 function onPickRow (row) {
   if (row.type === 'hit') { emit('pick-existing', row.hit); reset() }
-  else if (row.type === 'suggestion') { onPickSuggestion(row.sugg) }
   else { onCreate() }
 }
 
-// Picking an ML suggestion hands it to the parent, which runs the same accept
-// flow as the Suggestions panel (creates the tag if raw, records acceptance,
-// drops it from the panel). reset() clears the query; the panel-drop makes it
-// fall out of suggestionHits reactively.
-function onPickSuggestion (s) { emit('accept-suggestion', s); reset() }
-
 function onCreate () {
   const name = parsedName.value
   const kind = parsedKind.value
@@ -389,14 +351,16 @@ function reset () { query.value = ''; hits.value = []; highlight.value = 0 }
   border: 1px solid rgb(var(--v-theme-surface-light));
   border-radius: 6px;
 }
-/* Mark ML-suggestion rows so they read as distinct from typed/known matches. */
-.fc-tag-autocomplete__sugg {
-  border-left: 2px solid rgb(var(--v-theme-accent), 0.5);
-}
+/* The model-confidence badge on a row whose tag the model also scored. Accent
+   when above the head's suggest threshold; muted when below (a low-confidence
+   match you can still type + pick). */
 .fc-tag-autocomplete__sugg-tag {
   display: inline-flex; align-items: center; gap: 2px;
   font-size: 11px;
   font-family: 'JetBrains Mono', monospace;
   color: rgb(var(--v-theme-accent));
 }
+.fc-tag-autocomplete__sugg-tag--below {
+  color: rgb(var(--v-theme-on-surface-variant));
+}
 </style>

frontend/src/components/modal/TagChip.vue

@@ -1,7 +1,7 @@
 <template>
   <span class="fc-tag-chip" @mouseenter="onEnter" @mouseleave="onLeave">
     <v-chip
-      size="small" :closable="!unconfirmedAuto"
+      size="default" :closable="!unconfirmedAuto"
       :color="store.colorFor(tag.kind)" variant="tonal"
       class="fc-tag-chip__nav"
       role="link"
@@ -9,7 +9,7 @@
       @click="$emit('navigate', tag)"
       @click:close="$emit('remove', tag.id)"
     >
-      <v-icon start size="x-small">{{ iconFor(tag.kind) }}</v-icon>
+      <v-icon start size="small">{{ iconFor(tag.kind) }}</v-icon>
       <span class="fc-tag-chip__name">{{ tag.name }}</span><v-icon
         v-if="tag.is_system" end size="x-small" class="fc-tag-chip__system"
         title="System tag — tagged items are excluded from training other concepts"
@@ -27,13 +27,13 @@
           :title="`Yes — keep “${tag.name}” (trains the model, won't be retracted)`"
           :aria-label="`Confirm ${tag.name}`"
           @click.stop="$emit('confirm', tag)"
-        ><v-icon size="13">mdi-check</v-icon></button>
+        ><v-icon size="15">mdi-check</v-icon></button>
         <button
           type="button" class="fc-tag-chip__no"
           :title="`No — remove “${tag.name}”`"
           :aria-label="`Reject ${tag.name}`"
           @click.stop="$emit('remove', tag.id)"
-        ><v-icon size="13">mdi-close</v-icon></button>
+        ><v-icon size="15">mdi-close</v-icon></button>
       </span>
     </v-chip>
     <!-- Modal-safe kebab is baked into KebabMenu (this chip lives in the
@@ -143,7 +143,19 @@ function iconFor (k) { return KIND_ICONS[k] || 'mdi-tag' }
    chip's hover title. */
 .fc-tag-chip { display: inline-flex; align-items: center; gap: 1px; max-width: 100%; min-width: 0; }
 .fc-tag-chip__nav { max-width: 100%; min-width: 0; }
+/* Tonal chips (esp. character = info) wash out against the dark rail — the fill
+   is intentionally faint. Give every tag chip a thin border in its OWN kind
+   colour (currentColor = the tonal chip's themed foreground) so the edge reads
+   clearly without touching the fill (operator-asked 2026-07-08). Theme-aware:
+   currentColor tracks the kind colour in either light or dark. */
+.fc-tag-chip__nav { border: thin solid color-mix(in srgb, currentColor 55%, transparent); }
 .fc-tag-chip__nav :deep(.v-chip__content) { min-width: 0; overflow: hidden; }
+/* The bigger size=default chip widens Vuetify's negative start-margin on the
+   leading kind-icon, pulling it LEFT of the content box above — where that
+   overflow:hidden then clips the icon's left edge as a vertical slice
+   (operator-flagged 2026-07-08). Zero the pull so the icon sits inside the clip
+   box; the chip's own 12px padding keeps a comfortable left inset. */
+.fc-tag-chip__nav :deep(.v-icon--start) { margin-inline-start: 0; }
 .fc-tag-chip__name {
   overflow: hidden; text-overflow: ellipsis; white-space: nowrap;
   min-width: 0; flex: 0 1 auto;
@@ -159,23 +171,27 @@ function iconFor (k) { return KIND_ICONS[k] || 'mdi-tag' }
 .fc-tag-chip__kebab { opacity: 0.7; }
 .fc-tag-chip:hover .fc-tag-chip__kebab { opacity: 1; }
 .fc-tag-chip__fandom { opacity: 0.7; font-size: 0.85em; }
-/* Provisional auto-tag: a compact green ✓ / red ✗ pair in place of the ✕. The
-   yes/no is obvious enough on its own, so there's no "auto" label (operator-asked
+/* Provisional auto-tag: a green ✓ / red ✗ pair in place of the ✕. The yes/no is
+   obvious enough on its own, so there's no "auto" label (operator-asked
    2026-07-07). flex:0 0 auto keeps it visible while the name ellipsis-truncates. */
 .fc-tag-chip__verdict {
-  flex: 0 0 auto; display: inline-flex; align-items: center; gap: 1px;
-  margin-left: 3px;
+  flex: 0 0 auto; display: inline-flex; align-items: center; gap: 3px;
+  margin-left: 5px;
 }
+/* Solid-filled (white glyph on a full success/error circle) so accept/reject
+   stay well-defined even on a muted tonal chip — e.g. character (info) — instead
+   of a faint icon that only lit up on hover. Mirrors the Suggestions rail's
+   verdict buttons so the affordance reads identically (operator-asked 2026-07-08). */
 .fc-tag-chip__yes, .fc-tag-chip__no {
   display: inline-flex; align-items: center; justify-content: center;
-  width: 18px; height: 18px; padding: 0; border: none; border-radius: 50%;
-  background: transparent; cursor: pointer; transition: background 0.1s;
+  width: 22px; height: 22px; padding: 0; border: none; border-radius: 50%;
+  color: #fff; cursor: pointer; opacity: 0.92;
+  transition: transform 0.1s, opacity 0.1s;
 }
-.fc-tag-chip__yes { color: rgb(var(--v-theme-success)); }
-.fc-tag-chip__no { color: rgb(var(--v-theme-error)); }
-.fc-tag-chip__yes:hover { background: rgb(var(--v-theme-success), 0.16); }
-.fc-tag-chip__no:hover { background: rgb(var(--v-theme-error), 0.16); }
+.fc-tag-chip__yes { background: rgb(var(--v-theme-success)); }
+.fc-tag-chip__no { background: rgb(var(--v-theme-error)); }
+.fc-tag-chip__yes:hover, .fc-tag-chip__no:hover { opacity: 1; transform: scale(1.1); }
 .fc-tag-chip__yes:focus-visible, .fc-tag-chip__no:focus-visible {
-  outline: 2px solid rgb(var(--v-theme-accent)); outline-offset: 1px;
+  outline: 2px solid rgb(var(--v-theme-accent)); outline-offset: 2px;
 }
 </style>

frontend/src/components/modal/TagPanel.vue

@@ -17,7 +17,6 @@
       ref="tagInputRef"
       :applied-tags="host.current?.tags || []"
       @pick-existing="onPickExisting" @pick-new="onPickNew"
-      @accept-suggestion="onAcceptSuggestion"
     />
 
     <v-alert v-if="errorMsg" type="error" variant="tonal" class="mt-2" closable>
@@ -134,7 +133,6 @@ async function onRemove(tagId) {
     // until the next modal open (operator-asked 2026-07-03).
     if (host.currentImageId != null) {
       suggestions.load(host.currentImageId)
-      suggestions.loadAll(host.currentImageId)
     }
     focusTagInput()
   }
@@ -178,18 +176,6 @@ async function onPickNew(payload) {
   }
   catch (e) { errorMsg.value = e.message }
 }
-// A suggestion picked from the autocomplete dropdown runs the SAME path as the
-// Suggestions panel's Accept: the store creates the tag if it's raw, records the
-// acceptance, and drops it from the panel; then we refresh the chip rail.
-async function onAcceptSuggestion(s) {
-  errorMsg.value = null
-  try {
-    await suggestions.accept(s)
-    await host.reloadTags()
-    focusTagInput()
-  } catch (e) { errorMsg.value = e.message }
-}
-
 const renameDialog = ref(false)
 const renameTarget = ref(null)
 

frontend/src/components/posts/PostCard.vue

@@ -70,6 +70,14 @@
           @click.stop="showOriginal = !showOriginal"
         >{{ showOriginal ? 'Show translation' : `Show original${sourceLangLabel}` }}</button>
 
+        <!-- Per-post translation override (#155): force a skipped translation on,
+             or keep the original for a confidently mis-flagged title. Only where
+             there's text to translate. -->
+        <PostTranslationControl
+          v-if="post.post_title || post.description_plain"
+          :post="post"
+        />
+
         <!-- Faithful (semantic) body render once expanded: backend-sanitized
              HTML (headings, lists, links, inline images). Collapsed and the
              no-detail fallback stay plain text. -->
@@ -136,6 +144,7 @@ import { useModalStore } from '../../stores/modal.js'
 import { usePostsStore } from '../../stores/posts.js'
 import { toPlainText } from '../../utils/htmlSanitize.js'
 import PostSeriesMenu from './PostSeriesMenu.vue'
+import PostTranslationControl from './PostTranslationControl.vue'
 
 const props = defineProps({
   post: { type: Object, required: true },

frontend/src/components/posts/PostTranslationControl.vue

@@ -0,0 +1,102 @@
+<template>
+  <!-- Sticky per-post translation override (#155). Quiet inline control under the
+       post title: force a skipped legit-foreign title on, or knock a wrongly
+       mis-translated one back to the original. The choice sticks through a
+       Re-translate-all. -->
+  <div class="fc-post-tx">
+    <span class="fc-post-tx__label">Translation:</span>
+    <v-menu :disabled="busy">
+      <template #activator="{ props: menuProps }">
+        <button
+          type="button" class="fc-post-tx__btn" v-bind="menuProps" :disabled="busy"
+          :aria-label="`Translation handling: ${currentLabel}`"
+        >
+          {{ currentLabel }}
+          <v-icon size="14">mdi-menu-down</v-icon>
+        </button>
+      </template>
+      <v-list density="compact" min-width="240" class="fc-post-tx__list">
+        <v-list-item
+          v-for="opt in OPTIONS" :key="opt.value"
+          :active="opt.value === current" @click="choose(opt.value)"
+        >
+          <template #prepend>
+            <v-icon size="small">{{ opt.icon }}</v-icon>
+          </template>
+          <v-list-item-title>{{ opt.label }}</v-list-item-title>
+          <v-list-item-subtitle>{{ opt.help }}</v-list-item-subtitle>
+        </v-list-item>
+      </v-list>
+    </v-menu>
+    <v-progress-circular v-if="busy" indeterminate size="13" width="2" />
+  </div>
+</template>
+
+<script setup>
+import { computed, ref } from 'vue'
+
+import { usePostsStore } from '../../stores/posts.js'
+import { toast } from '../../utils/toast.js'
+
+const props = defineProps({ post: { type: Object, required: true } })
+const posts = usePostsStore()
+const busy = ref(false)
+
+const OPTIONS = [
+  { value: 'auto', label: 'Auto', icon: 'mdi-cog-outline',
+    help: 'Translate only when confident enough' },
+  { value: 'force', label: 'Force translate', icon: 'mdi-translate',
+    help: 'Always translate, even at low confidence' },
+  { value: 'original', label: 'Keep original', icon: 'mdi-translate-off',
+    help: 'Never translate — keep the original text' },
+]
+
+const current = computed(() => props.post.translation_override || 'auto')
+const currentLabel = computed(
+  () => (OPTIONS.find((o) => o.value === current.value) || OPTIONS[0]).label,
+)
+
+async function choose (value) {
+  if (value === current.value || busy.value) return
+  busy.value = true
+  try {
+    const res = await posts.applyTranslationOverride(props.post.id, value)
+    if (res.applied === 'queued') {
+      toast({
+        text: 'Saved — this post will translate on the next sweep (service offline).',
+        type: 'info',
+      })
+    }
+  } catch (e) {
+    toast({ text: `Couldn't update translation: ${e.message}`, type: 'error' })
+  } finally {
+    busy.value = false
+  }
+}
+</script>
+
+<style scoped>
+.fc-post-tx {
+  display: inline-flex; align-items: center; gap: 6px;
+  margin: 2px 0 6px;
+}
+.fc-post-tx__label {
+  font-size: 0.72rem;
+  color: rgb(var(--v-theme-on-surface-variant));
+}
+.fc-post-tx__btn {
+  display: inline-flex; align-items: center; gap: 1px;
+  padding: 0; background: none; border: 0; cursor: pointer;
+  font-size: 0.72rem; font-weight: 700;
+  color: rgb(var(--v-theme-on-surface-variant));
+}
+.fc-post-tx__btn:hover { color: rgb(var(--v-theme-accent)); }
+.fc-post-tx__btn:focus-visible {
+  outline: 2px solid rgb(var(--v-theme-accent)); outline-offset: 1px;
+  border-radius: 2px;
+}
+.fc-post-tx__btn:disabled { cursor: default; opacity: 0.6; }
+.fc-post-tx__list :deep(.v-list-item-subtitle) {
+  font-size: 0.7rem;
+}
+</style>

frontend/src/components/settings/CropProposersCard.vue

@@ -15,28 +15,23 @@
     </p>
 
     <div v-for="p in proposers" :key="p.key" class="fc-proposer">
-      <div class="d-flex align-center mb-1" style="gap: 10px;">
-        <v-icon size="18" :color="p.on ? 'accent' : undefined">{{ p.icon }}</v-icon>
-        <span class="fc-section-h">{{ p.label }}</span>
-        <v-switch
-          v-model="p.on" :loading="busy" hide-details density="compact"
-          color="success" class="ml-auto"
-          @update:model-value="v => saveToggle(p, v)"
-        />
-      </div>
+      <SettingToggleRow
+        v-model="p.on" :loading="busy" :icon="p.icon"
+        :icon-color="p.on ? 'accent' : null" :label="p.label"
+        @change="v => saveToggle(p, v)"
+      />
       <p class="fc-muted text-body-2 mb-2">{{ p.help }}</p>
       <div class="d-flex flex-wrap mb-4" style="gap: 12px;">
         <v-text-field
           v-model="p.weights" label="Weights" density="compact" hide-details
           style="min-width: 300px; flex: 1;" :disabled="busy || !p.on"
           placeholder="name | URL | hf_repo::file"
-          @change="save({ [`detector_${p.key}_weights`]: p.weights })"
+          @change="saveField({ [`detector_${p.key}_weights`]: p.weights })"
         />
-        <v-text-field
-          v-model.number="p.conf" label="Confidence" type="number"
-          min="0" max="1" step="0.05" density="compact" hide-details
-          style="max-width: 140px;" :disabled="busy || !p.on"
-          @change="save({ [`detector_${p.key}_conf`]: Number(p.conf) })"
+        <SettingNumberField
+          v-model="p.conf" label="Confidence" :min="0" :max="1" :step="0.05"
+          max-width="140px" :disabled="busy || !p.on"
+          @change="saveField({ [`detector_${p.key}_conf`]: Number(p.conf) })"
         />
       </div>
     </div>
@@ -48,12 +43,12 @@
         storage. Dedupe IoU drops near-duplicate crops before embedding.
       </p>
       <div class="d-flex flex-wrap" style="gap: 12px;">
-        <v-text-field
+        <SettingNumberField
           v-for="c in caps" :key="c.key"
-          v-model.number="c.val" :label="c.label" type="number"
-          :min="c.min" :max="c.max" :step="c.step || 1" density="compact"
-          hide-details style="max-width: 165px;" :disabled="busy"
-          @change="save({ [c.key]: Number(c.val) })"
+          v-model="c.val" :label="c.label"
+          :min="c.min" :max="c.max" :step="c.step || 1"
+          max-width="165px" :disabled="busy"
+          @change="saveField({ [c.key]: Number(c.val) })"
         />
       </div>
     </div>
@@ -61,14 +56,16 @@
 </template>
 
 <script setup>
-import { toast } from '../../utils/toast.js'
 import { onMounted, ref } from 'vue'
 
 import MaintenanceTile from '../common/MaintenanceTile.vue'
+import SettingNumberField from '../common/SettingNumberField.vue'
+import SettingToggleRow from '../common/SettingToggleRow.vue'
+import { useSettingSave } from '../../composables/useSettingSave.js'
 import { useMLStore } from '../../stores/ml.js'
 
 const mlSettings = useMLStore()
-const busy = ref(false)
+const { busy, save } = useSettingSave(mlSettings.patchSettings)
 const proposers = ref([])
 const caps = ref([])
 
@@ -111,31 +108,20 @@ onMounted(async () => {
   caps.value = CAP_DEFS.map(c => ({ ...c, val: s[c.key] ?? 0 }))
 })
 
-async function save(patch, revert) {
-  busy.value = true
-  try {
-    await mlSettings.patchSettings(patch)
-    toast({ text: 'Saved', type: 'success' })
-  } catch (e) {
-    if (revert) revert()
-    toast({ text: `Could not save: ${e.message}`, type: 'error' })
-  } finally {
-    busy.value = false
-  }
+// Field @change → persist with a "Saved" confirmation. SettingNumberField has
+// already clamped numeric values to their [min,max] before this fires.
+function saveField(patch) {
+  save(patch, { successMessage: 'Saved' })
 }
 
-function saveToggle (p, v) {
+async function saveToggle(p, v) {
   // Revert the switch on failure so it never lies about the persisted state.
-  save({ [`detector_${p.key}_enabled`]: !!v }, () => { p.on = !v })
+  const ok = await save({ [`detector_${p.key}_enabled`]: !!v }, { successMessage: 'Saved' })
+  if (!ok) p.on = !v
 }
 </script>
 
 <style scoped>
-.fc-muted { color: rgb(var(--v-theme-on-surface-variant)); }
-.fc-section-h {
-  font-size: 13px; font-weight: 700; letter-spacing: 0.03em;
-  text-transform: uppercase; color: rgb(var(--v-theme-on-surface));
-}
 .fc-proposer {
   border-top: 1px solid rgb(var(--v-theme-surface-light)); padding-top: 14px;
 }

frontend/src/components/settings/DangerZoneCard.vue

@@ -112,7 +112,6 @@ async function onCommit() {
 </script>
 
 <style scoped>
-.fc-muted { color: rgb(var(--v-theme-on-surface-variant)); }
 .fc-code {
   background: rgb(var(--v-theme-surface-light));
   border-radius: 4px; padding: 2px 8px;

frontend/src/components/settings/DbMaintenanceCard.vue

@@ -42,7 +42,7 @@
           </tr>
         </tbody>
       </v-table>
-      <p v-else class="text-caption mt-3" style="opacity: 0.6;">
+      <p v-else class="text-caption mt-3 fc-muted">
         No table statistics yet.
       </p>
   </MaintenanceTile>

frontend/src/components/settings/DownloadsActivityPanel.vue

@@ -72,6 +72,5 @@ onUnmounted(() => { if (pollId) clearInterval(pollId) })
 </script>
 
 <style scoped>
-.fc-muted { color: rgb(var(--v-theme-on-surface-variant)); }
 .fc-bad { color: rgb(var(--v-theme-error)); }
 </style>

frontend/src/components/settings/GpuActivityPanel.vue

@@ -95,7 +95,6 @@ onUnmounted(() => { if (pollId) clearInterval(pollId) })
 </script>
 
 <style scoped>
-.fc-muted { color: rgb(var(--v-theme-on-surface-variant)); }
 .fc-cells { display: flex; gap: 28px; }
 .fc-cell__n {
   font-size: 20px; font-weight: 700; line-height: 1.1;
@@ -105,6 +104,5 @@ onUnmounted(() => { if (pollId) clearInterval(pollId) })
   font-size: 11px; text-transform: uppercase; letter-spacing: 0.04em;
   color: rgb(var(--v-theme-on-surface-variant));
 }
-.fc-good { color: rgb(var(--v-theme-success)); }
 .fc-bad { color: rgb(var(--v-theme-error)); }
 </style>

frontend/src/components/settings/GpuAgentCard.vue

@@ -367,11 +367,6 @@ async function onReprocess() {
 </script>
 
 <style scoped>
-.fc-muted { color: rgb(var(--v-theme-on-surface-variant)); }
-.fc-section-h {
-  font-size: 13px; font-weight: 700; letter-spacing: 0.03em;
-  text-transform: uppercase; color: rgb(var(--v-theme-on-surface));
-}
 .fc-token {
   display: flex; align-items: center; gap: 4px;
   background: rgb(var(--v-theme-surface-light)); border-radius: 6px;
@@ -390,6 +385,4 @@ async function onReprocess() {
   font-size: 11px; text-transform: uppercase; letter-spacing: 0.04em;
   color: rgb(var(--v-theme-on-surface-variant));
 }
-.fc-good { color: rgb(var(--v-theme-success)); }
-.fc-weak { color: rgb(var(--v-theme-error)); }
 </style>

frontend/src/components/settings/GpuTriageCard.vue

@@ -155,11 +155,6 @@ async function onRecover(it) {
 </script>
 
 <style scoped>
-.fc-muted { color: rgb(var(--v-theme-on-surface-variant)); }
-.fc-section-h {
-  font-size: 13px; font-weight: 700; letter-spacing: 0.03em;
-  text-transform: uppercase; color: rgb(var(--v-theme-on-surface));
-}
 .fc-queue { display: flex; gap: 24px; }
 .fc-q__n {
   font-size: 20px; font-weight: 700; line-height: 1.1;
@@ -169,8 +164,6 @@ async function onRecover(it) {
   font-size: 11px; text-transform: uppercase; letter-spacing: 0.04em;
   color: rgb(var(--v-theme-on-surface-variant));
 }
-.fc-good { color: rgb(var(--v-theme-success)); }
-.fc-weak { color: rgb(var(--v-theme-error)); }
 .fc-defect {
   display: flex; align-items: center; gap: 12px;
   background: rgb(var(--v-theme-surface-light)); border-radius: 8px;

frontend/src/components/settings/HeadsCard.vue

@@ -95,14 +95,10 @@
 
     <!-- Earned auto-apply -->
     <div class="fc-auto mt-6">
-      <div class="d-flex align-center mb-1" style="gap: 10px;">
-        <v-icon size="18" color="accent">mdi-lightning-bolt</v-icon>
-        <span class="fc-section-h">Auto-apply</span>
-        <v-switch
-          v-model="autoEnabled" :loading="settingBusy" hide-details density="compact"
-          color="success" class="ml-auto" @update:model-value="onToggleAuto"
-        />
-      </div>
+      <SettingToggleRow
+        v-model="autoEnabled" :loading="settingBusy"
+        icon="mdi-lightning-bolt" label="Auto-apply" @change="onToggleAuto"
+      />
       <p class="fc-muted text-body-2 mb-3">
         Graduated heads (⚡, with ≥ {{ autoMinPosInput }} examples) apply their tag
         on their own where they clear {{ Math.round((autoPrecisionInput || 0) * 100) }}%
@@ -111,17 +107,14 @@
       </p>
 
       <div class="d-flex mb-3" style="gap: 12px;">
-        <v-text-field
-          v-model.number="autoPrecisionInput" label="Precision target"
-          type="number" min="0.5" max="0.999" step="0.01" density="compact"
-          hide-details style="max-width: 200px;" :disabled="settingBusy"
+        <SettingNumberField
+          v-model="autoPrecisionInput" label="Precision target"
+          :min="0.5" :max="0.999" :step="0.01" :disabled="settingBusy"
           @change="onSaveSettings"
         />
-        <v-text-field
-          v-model.number="autoMinPosInput" label="Min examples to fire"
-          type="number" min="1" density="compact" hide-details
-          style="max-width: 200px;" :disabled="settingBusy"
-          @change="onSaveSettings"
+        <SettingNumberField
+          v-model="autoMinPosInput" label="Min examples to fire"
+          :min="1" :disabled="settingBusy" @change="onSaveSettings"
         />
       </div>
 
@@ -161,40 +154,65 @@
 
     <!-- Presentation chrome auto-hide (#141) -->
     <div class="fc-auto mt-6">
-      <div class="d-flex align-center mb-1" style="gap: 10px;">
-        <v-icon size="18" color="accent">mdi-image-off-outline</v-icon>
-        <span class="fc-section-h">Hide presentation chrome</span>
-        <v-switch
-          v-model="presentationEnabled" :loading="settingBusy" hide-details
-          density="compact" color="success" class="ml-auto"
-          @update:model-value="onTogglePresentation"
-        />
-      </div>
+      <SettingToggleRow
+        v-model="presentationEnabled" :loading="settingBusy"
+        icon="mdi-image-off-outline" label="Hide presentation chrome"
+        @change="onTogglePresentation"
+      />
       <p class="fc-muted text-body-2 mb-3">
-        Auto-hide banners and editor screenshots from the gallery once a head has
-        learned them (≥ {{ minPositives }} examples) and clears
+        Auto-hide <code>banner</code> chrome from the gallery once a head has
+        learned it (≥ {{ minPositives }} examples) and clears
         {{ Math.round((presentationThresholdInput || 0) * 100) }}% confidence.
-        <code>wip</code> is never auto-hidden. If a hidden image also looks like
-        real content (≥ {{ Math.round((presentationConflictInput || 0) * 100) }}%
-        on a content tag), it's flagged in the Hidden view instead of buried.
-        Every auto-hide is reversible.
+        (<code>wip</code> and <code>editor screenshot</code> are handled by the
+        process auto-tagger below.) If a hidden image also looks like real content
+        (≥ {{ Math.round((presentationConflictInput || 0) * 100) }}% on a content
+        tag), it's flagged for review instead of buried. Every auto-hide is reversible.
       </p>
       <div class="d-flex mb-3" style="gap: 12px;">
-        <v-text-field
-          v-model.number="presentationThresholdInput" label="Hide confidence"
-          type="number" min="0.5" max="0.999" step="0.01" density="compact"
-          hide-details style="max-width: 200px;" :disabled="settingBusy"
+        <SettingNumberField
+          v-model="presentationThresholdInput" label="Hide confidence"
+          :min="0.5" :max="0.999" :step="0.01" :disabled="settingBusy"
           @change="onSavePresentation"
         />
-        <v-text-field
-          v-model.number="presentationConflictInput" label="Flag if content ≥"
-          type="number" min="0" max="1" step="0.05" density="compact"
-          hide-details style="max-width: 200px;" :disabled="settingBusy"
+        <SettingNumberField
+          v-model="presentationConflictInput" label="Flag if content ≥"
+          :min="0" :max="1" :step="0.05" :disabled="settingBusy"
           @change="onSavePresentation"
         />
       </div>
     </div>
 
+    <!-- Process auto-tagging (#1464): wip / editor screenshot -->
+    <div class="fc-auto mt-6">
+      <SettingToggleRow
+        v-model="processEnabled" :loading="settingBusy"
+        icon="mdi-progress-wrench" label="Auto-tag work-in-progress"
+        @change="onToggleProcess"
+      />
+      <p class="fc-muted text-body-2 mb-3">
+        Auto-tag <code>wip</code> and <code>editor screenshot</code> process art
+        once a head has learned them (≥ {{ minPositives }} examples) and clears
+        {{ Math.round((processThresholdInput || 0) * 100) }}% confidence. These stay
+        <strong>visible</strong> in the gallery — the tag just keeps them out of
+        training and the Explore rabbit-hole. Off by default. If a tagged image also
+        looks like real content (≥ {{ Math.round((processConflictInput || 0) * 100) }}%
+        on a content tag), it's flagged for review. Learns only from your titles +
+        manual tags, never its own guesses — so it can't run away. Every tag reversible.
+      </p>
+      <div class="d-flex mb-3" style="gap: 12px;">
+        <SettingNumberField
+          v-model="processThresholdInput" label="Tag confidence"
+          :min="0.5" :max="0.999" :step="0.01" :disabled="settingBusy"
+          @change="onSaveProcess"
+        />
+        <SettingNumberField
+          v-model="processConflictInput" label="Flag if content ≥"
+          :min="0" :max="1" :step="0.05" :disabled="settingBusy"
+          @change="onSaveProcess"
+        />
+      </div>
+    </div>
+
     <!-- Performance / tuning -->
     <div v-if="metricsConcepts.length" class="mt-5">
       <div class="fc-section-h mb-1">How auto-apply is landing</div>
@@ -219,7 +237,7 @@
               <td class="fc-r fc-mono">{{ c.n_auto_applied }}</td>
               <td class="fc-r fc-mono">{{ c.n_misfires }}</td>
               <td class="fc-r fc-mono" :class="rateClass(c.misfire_rate)">
-                {{ ratePct(c.misfire_rate) }}
+                {{ pct(c.misfire_rate) }}
               </td>
               <td class="fc-r fc-mono">{{ c.n_underfires }}</td>
             </tr>
@@ -235,6 +253,9 @@ import { toast } from '../../utils/toast.js'
 import { computed, onMounted, onUnmounted, ref } from 'vue'
 
 import MaintenanceTile from '../common/MaintenanceTile.vue'
+import SettingNumberField from '../common/SettingNumberField.vue'
+import SettingToggleRow from '../common/SettingToggleRow.vue'
+import { useSettingSave } from '../../composables/useSettingSave.js'
 import { useHeadsStore } from '../../stores/heads.js'
 import { useMLStore } from '../../stores/ml.js'
 
@@ -248,7 +269,9 @@ let pollTimer = null
 const autoEnabled = ref(false)
 const autoPrecisionInput = ref(0.97)
 const autoMinPosInput = ref(30)
-const settingBusy = ref(false)
+// Shared settings-save flow (busy + toast + revert); `settingBusy` gates the
+// toggles/fields, `save` returns ok/false for the optimistic-switch revert.
+const { busy: settingBusy, save } = useSettingSave(mlSettings.patchSettings)
 const autoBusy = ref(false)
 const autoStatus = ref(null)
 const metricsData = ref(null)
@@ -258,6 +281,9 @@ let autoTimer = null
 const presentationEnabled = ref(true)
 const presentationThresholdInput = ref(0.90)
 const presentationConflictInput = ref(0.50)
+const processEnabled = ref(false)
+const processThresholdInput = ref(0.90)
+const processConflictInput = ref(0.50)
 
 const autoRunning = computed(() => autoStatus.value?.running_id != null)
 const lastSweep = computed(() =>
@@ -292,6 +318,9 @@ onMounted(async () => {
     presentationEnabled.value = s.presentation_auto_apply_enabled ?? true
     presentationThresholdInput.value = s.presentation_auto_apply_threshold ?? 0.90
     presentationConflictInput.value = s.presentation_conflict_threshold ?? 0.50
+    processEnabled.value = s.process_auto_apply_enabled ?? false
+    processThresholdInput.value = s.process_auto_apply_threshold ?? 0.90
+    processConflictInput.value = s.process_conflict_threshold ?? 0.50
   } catch { /* non-fatal */ }
   await refresh()
   if (running.value) startPoll()
@@ -352,55 +381,39 @@ function startAutoPoll() {
 function stopAutoPoll() { if (autoTimer) { clearInterval(autoTimer); autoTimer = null } }
 
 async function onToggleAuto(val) {
-  settingBusy.value = true
-  try {
-    await mlSettings.patchSettings({ head_auto_apply_enabled: !!val })
-    toast({ text: val ? 'Auto-apply on' : 'Auto-apply off', type: 'success' })
-  } catch (e) {
-    autoEnabled.value = !val   // revert the switch
-    toast({ text: `Could not update: ${e.message}`, type: 'error' })
-  } finally {
-    settingBusy.value = false
-  }
+  const ok = await save({ head_auto_apply_enabled: !!val },
+    { successMessage: val ? 'Auto-apply on' : 'Auto-apply off', errorPrefix: 'Could not update' })
+  if (!ok) autoEnabled.value = !val   // revert the switch
 }
 async function onSaveSettings() {
-  settingBusy.value = true
-  try {
-    await mlSettings.patchSettings({
-      head_auto_apply_precision: Number(autoPrecisionInput.value),
-      head_auto_apply_min_positives: Number(autoMinPosInput.value),
-    })
-  } catch (e) {
-    toast({ text: `Could not save: ${e.message}`, type: 'error' })
-  } finally {
-    settingBusy.value = false
-  }
+  await save({
+    head_auto_apply_precision: Number(autoPrecisionInput.value),
+    head_auto_apply_min_positives: Number(autoMinPosInput.value),
+  })
 }
 
 async function onTogglePresentation(val) {
-  settingBusy.value = true
-  try {
-    await mlSettings.patchSettings({ presentation_auto_apply_enabled: !!val })
-    toast({ text: val ? 'Chrome auto-hide on' : 'Chrome auto-hide off', type: 'success' })
-  } catch (e) {
-    presentationEnabled.value = !val   // revert the switch
-    toast({ text: `Could not update: ${e.message}`, type: 'error' })
-  } finally {
-    settingBusy.value = false
-  }
+  const ok = await save({ presentation_auto_apply_enabled: !!val },
+    { successMessage: val ? 'Chrome auto-hide on' : 'Chrome auto-hide off', errorPrefix: 'Could not update' })
+  if (!ok) presentationEnabled.value = !val   // revert the switch
 }
 async function onSavePresentation() {
-  settingBusy.value = true
-  try {
-    await mlSettings.patchSettings({
-      presentation_auto_apply_threshold: Number(presentationThresholdInput.value),
-      presentation_conflict_threshold: Number(presentationConflictInput.value),
-    })
-  } catch (e) {
-    toast({ text: `Could not save: ${e.message}`, type: 'error' })
-  } finally {
-    settingBusy.value = false
-  }
+  await save({
+    presentation_auto_apply_threshold: Number(presentationThresholdInput.value),
+    presentation_conflict_threshold: Number(presentationConflictInput.value),
+  })
+}
+
+async function onToggleProcess(val) {
+  const ok = await save({ process_auto_apply_enabled: !!val },
+    { successMessage: val ? 'WIP auto-tag on' : 'WIP auto-tag off', errorPrefix: 'Could not update' })
+  if (!ok) processEnabled.value = !val   // revert the switch
+}
+async function onSaveProcess() {
+  await save({
+    process_auto_apply_threshold: Number(processThresholdInput.value),
+    process_conflict_threshold: Number(processConflictInput.value),
+  })
 }
 function onPreview() { startSweep(true) }
 function onApplyNow() { startSweep(false) }
@@ -426,7 +439,6 @@ function sweepConcepts(run) {
     .sort((a, b) => b.applied - a.applied)
 }
 function sweepTotal(run) { return run?.n_applied ?? 0 }
-function ratePct(x) { return x == null ? '—' : `${Math.round(x * 100)}%` }
 function rateClass(x) {
   if (x == null) return ''
   if (x <= 0.03) return 'fc-good'
@@ -457,12 +469,6 @@ function relTime(iso) {
 </script>
 
 <style scoped>
-.fc-muted { color: rgb(var(--v-theme-on-surface-variant)); }
-
-.fc-section-h {
-  font-size: 13px; font-weight: 700; letter-spacing: 0.03em;
-  text-transform: uppercase; color: rgb(var(--v-theme-on-surface));
-}
 .fc-auto {
   border-top: 1px solid rgb(var(--v-theme-surface-light)); padding-top: 16px;
 }
@@ -519,7 +525,5 @@ function relTime(iso) {
   background: rgb(var(--v-theme-surface-light));
   padding: 1px 6px; border-radius: 999px;
 }
-.fc-good { color: rgb(var(--v-theme-success)); }
 .fc-ok { color: rgb(var(--v-theme-on-surface)); }
-.fc-weak { color: rgb(var(--v-theme-error)); }
 </style>

frontend/src/components/settings/ImportFiltersForm.vue

@@ -15,7 +15,7 @@
           being dropped as duplicates;</strong> raise it to collapse more
           look-alikes. Applies to new imports.
         </div>
-        <v-row align="center" no-gutters>
+        <v-row no-gutters class="align-center">
           <v-col cols="12" sm="9">
             <v-slider
               v-model="local.phash_threshold"
@@ -79,6 +79,46 @@
         </v-col>
       </v-row>
 
+      <v-divider class="my-5" />
+
+      <!-- Title-based WIP auto-tagging (task #1458). The switch gates the LIVE
+           import hook; the button runs the one-off back-catalogue scan (an
+           explicit action — it is deliberately not a scheduled sweep so it can't
+           silently re-apply a WIP tag you removed by hand). -->
+      <div class="fc-wip">
+        <div class="fc-wip__title">WIP auto-tagging</div>
+        <v-switch
+          v-model="local.wip_title_tagging_enabled"
+          label="Tag work-in-progress from post titles"
+          density="compact" hide-details color="primary" @change="save"
+        />
+        <div class="fc-help mb-3">
+          When a post's title says <strong>“WIP”</strong> or
+          <strong>“work in progress”</strong>, new imports get the
+          <code>wip</code> tag automatically — keeping unfinished pieces out of
+          the Explore browse. Applies to new imports; run the scan below to catch
+          posts already in your library.
+        </div>
+        <v-switch
+          v-model="local.wip_soft_title_tagging_enabled"
+          label="Also tag “sketch” / “doodle” titles (lower precision)"
+          density="compact" hide-details color="primary" @change="save"
+        />
+        <div class="fc-help mb-3">
+          Extends the above to softer cues (<code>sketch</code>, <code>doodle</code>,
+          <code>scribble</code>). These stay <strong>visible</strong> and never train
+          the tagging model — a daily audit flags any that actually look like finished
+          art for review. Off by default.
+        </div>
+        <v-btn
+          variant="tonal" color="primary" size="small"
+          :loading="store.wipScanBusy" prepend-icon="mdi-magnify"
+          @click="store.scanWipTitles()"
+        >
+          Scan existing posts for WIP titles
+        </v-btn>
+      </div>
+
       <v-alert v-if="store.settingsError" type="error" variant="tonal" class="mt-2" closable>
         {{ store.settingsError }}
       </v-alert>
@@ -109,6 +149,8 @@ const local = reactive({
   skip_transparent: false, transparency_threshold: 0.9,
   skip_single_color: false, single_color_threshold: 0.95,
   phash_threshold: 10,
+  wip_title_tagging_enabled: true,
+  wip_soft_title_tagging_enabled: false,
 })
 
 watch(() => store.settings, (s) => { if (s) Object.assign(local, s) }, { immediate: true })
@@ -124,11 +166,18 @@ async function save() {
   color: rgb(var(--v-theme-on-surface-variant));
   margin-top: 2px;
 }
-.fc-phash__title {
+.fc-phash__title,
+.fc-wip__title {
   font-size: 0.95rem;
   font-weight: 600;
   color: rgb(var(--v-theme-on-surface));
 }
+.fc-wip code {
+  font-size: 0.85em;
+  padding: 1px 4px;
+  border-radius: 3px;
+  background: rgb(var(--v-theme-surface-variant));
+}
 /* Headroom so the tick labels (Exact/Strict/Default/Loose) aren't clipped. */
 .fc-phash__slider { margin-bottom: 18px; }
 </style>

frontend/src/components/settings/MLBackfillCard.vue

@@ -39,13 +39,14 @@
 import { toast } from '../../utils/toast.js'
 import { onMounted, ref } from 'vue'
 import { useMLStore } from '../../stores/ml.js'
+import { useSettingSave } from '../../composables/useSettingSave.js'
 import MaintenanceTile from '../common/MaintenanceTile.vue'
 import QueueStatusBar from './QueueStatusBar.vue'
 const store = useMLStore()
+const { busy: saving, save } = useSettingSave(store.patchSettings)
 const busy = ref(false)
 const done = ref(false)
 const enabled = ref(true)
-const saving = ref(false)
 onMounted(async () => {
   try {
     await store.loadSettings()
@@ -55,21 +56,12 @@ onMounted(async () => {
   } catch { /* non-fatal */ }
 })
 async function onToggle() {
-  saving.value = true
-  try {
-    await store.patchSettings({ cpu_embed_enabled: enabled.value })
-    toast({
-      text: enabled.value
-        ? 'CPU embedding on — imports queue embeds for the ml-worker'
-        : 'CPU embedding off — the GPU embed backfill owns whole-image embeds',
-      type: 'success',
-    })
-  } catch (e) {
-    toast({ text: `Could not save: ${e.message}`, type: 'error' })
-    enabled.value = !enabled.value
-  } finally {
-    saving.value = false
-  }
+  const ok = await save({ cpu_embed_enabled: enabled.value }, {
+    successMessage: enabled.value
+      ? 'CPU embedding on — imports queue embeds for the ml-worker'
+      : 'CPU embedding off — the GPU embed backfill owns whole-image embeds',
+  })
+  if (!ok) enabled.value = !enabled.value
 }
 async function run() {
   busy.value = true
@@ -80,5 +72,4 @@ async function run() {
 </script>
 
 <style scoped>
-.fc-muted { color: rgb(var(--v-theme-on-surface-variant)); }
 </style>

frontend/src/components/settings/MaintenancePanel.vue

@@ -24,6 +24,7 @@
         the CPU fallback.
       </p>
       <div class="fc-tile-stack">
+        <VideoEmbeddingCard />
         <GpuAgentCard />
         <GpuTriageCard />
         <MLBackfillCard />
@@ -36,7 +37,6 @@
         Suggestion thresholds, trained heads and tag aliases.
       </p>
       <div class="fc-tile-stack">
-        <MLThresholdSliders />
         <CropProposersCard />
         <HeadsCard />
         <AliasTable />
@@ -77,7 +77,7 @@ import ArchiveReextractCard from './ArchiveReextractCard.vue'
 import MissingFileRepairCard from './MissingFileRepairCard.vue'
 import GpuTriageCard from './GpuTriageCard.vue'
 import DbMaintenanceCard from './DbMaintenanceCard.vue'
-import MLThresholdSliders from './MLThresholdSliders.vue'
+import VideoEmbeddingCard from './VideoEmbeddingCard.vue'
 import CropProposersCard from './CropProposersCard.vue'
 import HeadsCard from './HeadsCard.vue'
 import GpuAgentCard from './GpuAgentCard.vue'

frontend/src/components/settings/SystemStatsCards.vue

@@ -1,5 +1,5 @@
 <template>
-  <v-row dense>
+  <v-row density="compact">
     <v-col v-for="card in cards" :key="card.label" cols="12" sm="6" md="4" lg="3" xl="2">
       <v-card class="fc-stat">
         <v-card-text>

frontend/src/components/settings/TranslationCard.vue

@@ -28,6 +28,21 @@
       @change="onSave"
     />
 
+    <!-- Acceptance floor (#155): latin-script translations below this Interpreter
+         confidence are kept as the original. Per-post overrides handle exceptions. -->
+    <v-text-field
+      v-model.number="minConfidence" label="Acceptance confidence"
+      type="number" min="0" max="1" step="0.01" density="compact"
+      hide-details style="max-width: 200px;" class="mb-1" :disabled="busy"
+      @change="onSaveConfidence"
+    />
+    <div class="fc-muted text-caption mb-3">
+      Latin-script titles Interpreter is less than this sure about (0–1) are kept
+      as the original; CJK is always translated. Default 0.90 — raise it to reject
+      more mis-detections, lower it to translate more. Per-post controls in the
+      posts feed override this either way.
+    </div>
+
     <div class="d-flex align-center flex-wrap mb-3" style="gap: 8px;">
       <v-icon size="12" :color="statusColor">mdi-circle</v-icon>
       <span class="fc-muted text-body-2">{{ statusText }}</span>
@@ -47,21 +62,123 @@
         prepend-icon="mdi-translate" :loading="running"
         :disabled="!enabled || !baseUrl" @click="onRun"
       >Translate now</v-btn>
-      <span v-if="status" class="fc-muted text-caption">
+      <v-btn
+        size="small" variant="tonal" rounded="pill"
+        prepend-icon="mdi-refresh" :loading="retranslating"
+        :disabled="!enabled || !baseUrl" @click="confirmAll = true"
+      >Re-translate all</v-btn>
+      <span
+        v-if="status && status.active"
+        class="fc-muted text-caption d-inline-flex align-center" style="gap: 6px;"
+      >
+        <v-progress-circular indeterminate size="12" width="2" color="accent" />
+        Translating… {{ status.untranslated_count }} remaining
+      </span>
+      <span v-else-if="status" class="fc-muted text-caption">
         {{ status.untranslated_count }}
         post{{ status.untranslated_count === 1 ? '' : 's' }} awaiting translation
       </span>
     </div>
+    <p
+      v-if="status && status.last_run && ['error', 'timeout'].includes(status.last_run.status)"
+      class="text-caption text-error mt-1 mb-0"
+    >
+      Last translation run ended with “{{ status.last_run.status }}”. It resumes on
+      the next sweep; check the Interpreter connection if it persists.
+    </p>
+    <p class="fc-muted text-caption mt-2 mb-0">
+      Use <strong>Re-translate all</strong> after switching the Interpreter model —
+      it clears every stored translation and re-runs it through the new model
+      (unchanged text is served from cache, so it's cheap). To refresh just one
+      artist, use the Re-translate button on that artist's page.
+    </p>
+
+    <v-divider class="my-3" />
+
+    <!-- Diagnostic probe (task #1376): paste text → what Interpreter DETECTS
+         (language + confidence) and returns, without saving. Used to see why a
+         short/abbreviation-heavy English title gets mis-detected, and to pick a
+         detection-confidence / min-length guard from real numbers. -->
+    <div class="mb-1">
+      <span class="fc-section-h">Test translation</span>
+      <p class="fc-muted text-caption mt-1 mb-2">
+        Paste a title or snippet to see what Interpreter detects and returns —
+        handy for checking why a short string is mis-detected. Nothing is saved.
+      </p>
+    </div>
+    <v-textarea
+      v-model="probeText" label="Text to test" rows="2" auto-grow
+      density="compact" hide-details class="mb-2" :disabled="!baseUrl"
+    />
+    <div class="d-flex align-center flex-wrap mb-2" style="gap: 8px;">
+      <v-btn
+        size="small" variant="tonal" rounded="pill" prepend-icon="mdi-magnify"
+        :loading="probing" :disabled="!baseUrl || !probeText.trim()"
+        @click="onProbe"
+      >Test translation</v-btn>
+    </div>
+    <v-sheet
+      v-if="probeResult" rounded class="pa-3 mb-1 text-body-2"
+      color="rgba(var(--v-theme-accent), 0.06)"
+    >
+      <div class="d-flex flex-wrap" style="gap: 4px 16px;">
+        <span>
+          <span class="fc-muted">Detected:</span>
+          <strong>{{ probeResult.detected_lang || '—' }}</strong>
+        </span>
+        <span v-if="probeResult.detected_confidence != null">
+          <span class="fc-muted">Confidence:</span>
+          <strong>{{ fmtConf(probeResult.detected_confidence) }}</strong>
+        </span>
+        <span>
+          <span class="fc-muted">Engine:</span>
+          {{ probeResult.engine || '—' }}<template
+            v-if="probeResult.engine_version"
+          > ({{ probeResult.engine_version }})</template>
+        </span>
+        <span><span class="fc-muted">Target:</span> {{ probeResult.target }}</span>
+      </div>
+      <v-divider class="my-2" />
+      <div class="fc-muted mb-1">
+        Result<template v-if="probeResult.detected_lang === probeResult.target">
+          — already {{ probeResult.target }}, so the sweep leaves it as-is</template>:
+      </div>
+      <p class="mb-0" style="white-space: pre-wrap;">{{
+        probeResult.translated || '(no change)'
+      }}</p>
+    </v-sheet>
 
     <v-alert
       v-if="err" type="error" variant="tonal" density="compact"
       class="mt-3" closable @click:close="err = null"
     >{{ err }}</v-alert>
+
+    <!-- m146: re-translate-everything is a bigger hammer than 'Translate now'
+         (it clears + rebuilds all translations), so it asks first. -->
+    <v-dialog v-model="confirmAll" max-width="440">
+      <v-card>
+        <v-card-title>Re-translate everything?</v-card-title>
+        <v-card-text class="text-body-2">
+          This clears the stored translation for <strong>every</strong> post and
+          re-runs them through your current Interpreter model. Text that hasn't
+          changed comes back from the cache instantly; anything the new model
+          translates differently is refreshed. It runs in the background until
+          done.
+        </v-card-text>
+        <v-card-actions>
+          <v-spacer />
+          <v-btn variant="text" @click="confirmAll = false">Cancel</v-btn>
+          <v-btn
+            color="accent" :loading="retranslating" @click="onRetranslateAll"
+          >Re-translate all</v-btn>
+        </v-card-actions>
+      </v-card>
+    </v-dialog>
   </MaintenanceTile>
 </template>
 
 <script setup>
-import { computed, onMounted, ref } from 'vue'
+import { computed, onMounted, onUnmounted, ref } from 'vue'
 import { toast } from '../../utils/toast.js'
 import { useApi } from '../../composables/useApi.js'
 import { useImportStore } from '../../stores/import.js'
@@ -73,13 +190,27 @@ const store = useImportStore()
 const enabled = ref(false)
 const baseUrl = ref('')
 const targetLang = ref('en')
+const minConfidence = ref(0.9)
 const busy = ref(false)
 const running = ref(false)
+const retranslating = ref(false)
+const confirmAll = ref(false)
 const testing = ref(false)
 const testResult = ref(null)   // null = not tested this session; true/false = last result
 const status = ref(null)
 const err = ref(null)
 
+// #1376 "Test translation" probe: paste text → detected lang/confidence + result.
+const probeText = ref('')
+const probing = ref(false)
+const probeResult = ref(null)
+
+// Confidence scale is Interpreter-defined (0–100 or 0–1) — show it as-is, just
+// trimmed to 2 decimals, so the operator reads the true number.
+function fmtConf (c) {
+  return c == null ? '' : Math.round(c * 100) / 100
+}
+
 const statusColor = computed(() => {
   if (!enabled.value || !baseUrl.value) return 'grey'
   return status.value?.healthy ? 'success' : 'error'
@@ -91,10 +222,16 @@ const statusText = computed(() => {
   return status.value.healthy ? 'Interpreter reachable' : 'Interpreter unreachable'
 })
 
+let pollTimer = null
 async function loadStatus() {
   try { status.value = await api.get('/api/settings/translation/status') }
   catch { status.value = null }
+  // Poll live while a sweep is running so the remaining count ticks down; stop
+  // when idle (a fresh trigger restarts it via its own setTimeout(loadStatus)).
+  clearTimeout(pollTimer)
+  if (status.value?.active) pollTimer = setTimeout(loadStatus, 3000)
 }
+onUnmounted(() => clearTimeout(pollTimer))
 
 async function onTest() {
   // Ping /v1/health for the CURRENTLY-typed URL (not the saved one), so a new
@@ -115,6 +252,21 @@ async function onTest() {
   }
 }
 
+async function onProbe () {
+  probing.value = true
+  err.value = null
+  probeResult.value = null
+  try {
+    probeResult.value = await api.post('/api/settings/translation/probe', {
+      body: { text: probeText.value.trim() },
+    })
+  } catch (e) {
+    err.value = e.message
+  } finally {
+    probing.value = false
+  }
+}
+
 onMounted(async () => {
   try {
     await store.loadSettings()
@@ -122,6 +274,7 @@ onMounted(async () => {
     enabled.value = !!s.translation_enabled
     baseUrl.value = s.interpreter_base_url || ''
     targetLang.value = s.translation_target_lang || 'en'
+    minConfidence.value = s.translation_min_confidence ?? 0.9
   } catch { /* non-fatal */ }
   await loadStatus()
 })
@@ -146,6 +299,14 @@ async function onSave() {
   })
   await loadStatus()
 }
+async function onSaveConfidence() {
+  // Clamp to [0, 1] so a stray value never bounces off the API 400.
+  let v = Number(minConfidence.value)
+  if (!Number.isFinite(v)) v = 0.9
+  v = Math.min(1, Math.max(0, v))
+  minConfidence.value = v
+  await save({ translation_min_confidence: v })
+}
 async function onRun() {
   running.value = true
   err.value = null
@@ -159,4 +320,18 @@ async function onRun() {
     setTimeout(loadStatus, 1500)   // let the sweep make a dent, then refresh
   }
 }
+async function onRetranslateAll() {
+  retranslating.value = true
+  err.value = null
+  try {
+    await api.post('/api/settings/translation/retranslate', { body: { all: true } })
+    confirmAll.value = false
+    toast({ text: 'Re-translating all posts…', type: 'success' })
+  } catch (e) {
+    err.value = e.message
+  } finally {
+    retranslating.value = false
+    setTimeout(loadStatus, 1500)   // reset spikes the untranslated count — refresh it
+  }
+}
 </script>

frontend/src/components/settings/VideoEmbeddingCard.vue

@@ -12,17 +12,17 @@
       </div>
       <v-row>
         <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"
+          <SettingNumberField
+            v-model="local.video_frame_interval_seconds"
+            label="Frame interval (s)" :min="0.5" :step="0.5"
+            density="comfortable" max-width="none" @change="onSave"
           />
         </v-col>
         <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"
+          <SettingNumberField
+            v-model="local.video_max_frames"
+            label="Max frames" :min="1" :step="1"
+            density="comfortable" max-width="none" @change="onSave"
           />
         </v-col>
       </v-row>
@@ -32,21 +32,23 @@
 </template>
 
 <script setup>
-import { toast } from '../../utils/toast.js'
 import { reactive, watch } from 'vue'
 import { useMLStore } from '../../stores/ml.js'
 import MaintenanceTile from '../common/MaintenanceTile.vue'
+import SettingNumberField from '../common/SettingNumberField.vue'
+import { useSettingSave } from '../../composables/useSettingSave.js'
 
 const store = useMLStore()
+const { save } = useSettingSave(store.patchSettings)
 const local = reactive({})
 watch(() => store.settings, (s) => { if (s) Object.assign(local, s) }, { immediate: true })
 
-async function save() {
-  const patch = {
-    video_frame_interval_seconds: local.video_frame_interval_seconds,
-    video_max_frames: local.video_max_frames
-  }
-  try { await store.patchSettings(patch) }
-  catch (e) { toast({ text: e.message, type: 'error' }) }
+// SettingNumberField clamps interval to ≥0.5 and max-frames to ≥1 before this
+// fires, so an out-of-range value never reaches the API.
+function onSave() {
+  save({
+    video_frame_interval_seconds: Number(local.video_frame_interval_seconds),
+    video_max_frames: Number(local.video_max_frames),
+  })
 }
 </script>

frontend/src/composables/useSettingSave.js

@@ -0,0 +1,33 @@
+import { ref } from 'vue'
+import { toast } from '../utils/toast.js'
+
+// The shared "persist a settings patch" flow for the ML settings cards. Flips a
+// busy flag, calls the store's patch (which rethrows on failure), toasts
+// success/error, and returns true/false so a toggle handler can revert its
+// optimistic switch on failure. Centralises the try/catch/toast the cards each
+// hand-rolled (HeadsCard x6, CropProposersCard, MLBackfillCard) — and where the
+// threshold-clamp drifted; the clamp now lives in <SettingNumberField>.
+//
+// Pass the store's patch fn, e.g. useSettingSave(ml.patchSettings).
+export function useSettingSave(patchFn) {
+  const busy = ref(false)
+
+  // opts.successMessage — toast on success (toggles announce their new state;
+  // silent field-saves omit it). opts.errorPrefix — the failure toast prefix
+  // ("Could not save" default; toggles used "Could not update").
+  async function save(patch, { successMessage = '', errorPrefix = 'Could not save' } = {}) {
+    busy.value = true
+    try {
+      await patchFn(patch)
+      if (successMessage) toast({ text: successMessage, type: 'success' })
+      return true
+    } catch (e) {
+      toast({ text: `${errorPrefix}: ${e.message}`, type: 'error' })
+      return false
+    } finally {
+      busy.value = false
+    }
+  }
+
+  return { busy, save }
+}

frontend/src/router.js

@@ -20,7 +20,7 @@ const routes = [
 
   // FC-2: image backbone
   { path: '/showcase', name: 'showcase', component: ShowcaseView, meta: { title: 'Showcase', navOrder: 10 } },
-  { path: '/gallery',  name: 'gallery',  component: GalleryView,  meta: { title: 'Gallery', navOrder: 20  } },
+  { path: '/gallery',  name: 'gallery',  component: GalleryView,  meta: { title: 'Gallery', navOrder: 20, stickyChrome: true } },
   // Explore: a 3-pane tagging workspace — walk an image's visual neighbours
   // (left) while tagging the focused image (center viewer + modal-parity tag
   // rail). Optional anchor param — the bare /explore nav entry SEEDS a random
@@ -29,11 +29,11 @@ const routes = [
   // Browse hub (operator-asked 2026-06-09): Posts / Artists / Tags as tabs —
   // the three "browse the library by an axis" surfaces. One nav entry; the old
   // standalone paths redirect into the matching tab (below).
-  { path: '/browse', name: 'browse', component: BrowseView, meta: { title: 'Browse', navOrder: 30 } },
+  { path: '/browse', name: 'browse', component: BrowseView, meta: { title: 'Browse', navOrder: 30, stickyChrome: true } },
   // Artist detail — no meta.title (reached by clicking an artist, not nav).
   { path: '/artist/:slug', name: 'artist', component: ArtistView },
   // Series browse — a nav entry (meta.title).
-  { path: '/series', name: 'series', component: SeriesView, meta: { title: 'Series', navOrder: 40 } },
+  { path: '/series', name: 'series', component: SeriesView, meta: { title: 'Series', navOrder: 40, stickyChrome: true } },
   // Series management — no meta.title (reached from a series card/tag).
   { path: '/series/:tagId', name: 'series-manage', component: SeriesManageView },
   // Series reader — immersive (no top nav, no meta.title).
@@ -41,10 +41,10 @@ const routes = [
 
   // FC-3: subscription backbone — purely management (sources/downloads),
   // distinct from the Browse hub.
-  { path: '/subscriptions', name: 'subscriptions', component: SubscriptionsView, meta: { title: 'Subscriptions', navOrder: 50 } },
+  { path: '/subscriptions', name: 'subscriptions', component: SubscriptionsView, meta: { title: 'Subscriptions', navOrder: 50, stickyChrome: true } },
 
   // Settings — config, pinned to the right of the nav (TopNav special-cases it).
-  { path: '/settings', name: 'settings', component: SettingsView, meta: { title: 'Settings' } },
+  { path: '/settings', name: 'settings', component: SettingsView, meta: { title: 'Settings', stickyChrome: true } },
 
   // The old standalone paths now redirect into the Browse hub, preserving any
   // deep-link query (e.g. /posts?post_id=N → /browse?tab=posts&post_id=N). The

frontend/src/stores/explore.js

@@ -25,6 +25,10 @@ export const useExploreStore = defineStore('explore', () => {
   const cursor = ref(-1)
   const loading = ref(false)
   const error = ref(null)
+  // Reach (#1476): how far the walk reaches past the anchor's immediate cluster.
+  // 0 = nearest (can get stuck in a dense signature); ~0.4 default mixes in
+  // mid-far escape routes so the walk diversifies without hitting "Random image".
+  const reach = ref(0.4)
 
   const inflight = useInflightToken()
 
@@ -44,7 +48,15 @@ export const useExploreStore = defineStore('explore', () => {
       // empty and let the view explain why (anchor.has_embedding === false).
       if (detail.has_embedding) {
         const body = await api.get('/api/gallery/similar', {
-          params: { similar_to: numId, limit: NEIGHBOR_LIMIT },
+          // exclude_wip: keep work-in-progress out of the Explore rabbit-hole
+          // (the gallery's own "similar" button still shows it) — operator 2026-07-08.
+          // reach + exclude_ids (#1476): reach past the dense cluster + never re-serve
+          // an already-walked image, so the walk keeps moving instead of getting stuck.
+          params: {
+            similar_to: numId, limit: NEIGHBOR_LIMIT, exclude_wip: 1,
+            reach: reach.value,
+            exclude_ids: breadcrumb.value.map((c) => c.id).join(','),
+          },
         })
         if (!t.isCurrent()) return
         neighbors.value = body.images || []
@@ -111,6 +123,14 @@ export const useExploreStore = defineStore('explore', () => {
     loading.value = false
   }
 
+  // Change how far the walk reaches and re-fetch the current anchor's neighbours
+  // with the new setting (the anchor + trail are unchanged — only the grid varies).
+  function setReach (v) {
+    reach.value = Math.max(0, Math.min(1, Number(v)))
+    const id = anchor.value?.id
+    if (id != null) anchorOn(id)
+  }
+
   // --- TagPanel "host" surface ---------------------------------------------
   // The anchor IS the current image (same /api/gallery/image/<id> payload the
   // modal uses), so these mirror the modal store's tag-CRUD, targeting the
@@ -187,8 +207,8 @@ export const useExploreStore = defineStore('explore', () => {
   function close () {}
 
   return {
-    anchor, neighbors, breadcrumb, cursor, loading, error, NEIGHBOR_LIMIT,
-    anchorOn, reset, backTarget, forwardTarget,
+    anchor, neighbors, breadcrumb, cursor, loading, error, NEIGHBOR_LIMIT, reach,
+    anchorOn, reset, backTarget, forwardTarget, setReach,
     // host surface
     current, currentImageId,
     reloadTags, addExistingTag, removeTag, createAndAdd, close,

frontend/src/stores/import.js

@@ -16,6 +16,7 @@ export const useImportStore = defineStore('import', () => {
   const settings = ref(null)
   const settingsLoading = ref(false)
   const settingsError = ref(null)
+  const wipScanBusy = ref(false)
 
   async function loadSettings() {
     settingsLoading.value = true
@@ -40,8 +41,25 @@ export const useImportStore = defineStore('import', () => {
     }
   }
 
+  // Enqueue the back-catalogue WIP-title scan (task #1458). New imports are
+  // tagged live; this catches posts already in the library. Fire-and-forget —
+  // the sweep runs on the maintenance worker and its run shows in Activity.
+  async function scanWipTitles() {
+    wipScanBusy.value = true
+    try {
+      const r = await api.post('/api/settings/wip-title/scan')
+      toast({ text: 'Scanning existing posts for WIP titles…', type: 'success' })
+      return r
+    } catch (e) {
+      toast({ text: `WIP scan failed: ${e.message}`, type: 'error' })
+      throw e
+    } finally {
+      wipScanBusy.value = false
+    }
+  }
+
   return {
-    settings, settingsLoading, settingsError,
-    loadSettings, patchSettings,
+    settings, settingsLoading, settingsError, wipScanBusy,
+    loadSettings, patchSettings, scanWipTitles,
   }
 })

frontend/src/stores/posts.js

@@ -71,6 +71,24 @@ export const usePostsStore = defineStore('posts', () => {
     return await api.get(`/api/posts/${id}`)
   }
 
+  // Set a post's sticky translation override (auto/force/original, #155) and
+  // patch the loaded item in place with the endpoint's result (it translates /
+  // clears immediately when the service is up), so the card reflects the change
+  // without a feed reload.
+  async function applyTranslationOverride(postId, override) {
+    const res = await api.post(`/api/posts/${postId}/translation-override`, {
+      body: { override },
+    })
+    const item = items.value.find((p) => p.id === postId)
+    if (item) {
+      item.translation_override = res.translation_override
+      item.post_title_translated = res.post_title_translated
+      item.description_translated = res.description_translated
+      item.translated_source_lang = res.translated_source_lang
+    }
+    return res
+  }
+
   // Filter overlay for the around/older/newer (in-context anchored)
   // path. Keep this distinct from `filters.value` (the down-only feed)
   // so a normal-feed filter change doesn't leak into an active anchored
@@ -168,7 +186,7 @@ export const usePostsStore = defineStore('posts', () => {
   return {
     items, cursor, loading, done, error, filters,
     cursorOlder, cursorNewer, doneOlder, doneNewer, anchorId,
-    loadInitial, loadMore, getPostFull,
+    loadInitial, loadMore, getPostFull, applyTranslationOverride,
     loadAround, loadOlder, loadNewer,
   }
 })

frontend/src/stores/suggestions.js

@@ -1,6 +1,6 @@
 import { defineStore } from 'pinia'
 import { toast } from '../utils/toast.js'
-import { ref } from 'vue'
+import { computed, ref } from 'vue'
 import { useApi } from '../composables/useApi.js'
 import { useAsyncAction } from '../composables/useAsyncAction.js'
 import { useInflightToken } from '../composables/useInflightToken.js'
@@ -18,182 +18,112 @@ export const CATEGORY_LABELS = {
 
 export const useSuggestionsStore = defineStore('suggestions', () => {
   const api = useApi()
-  const byCategory = ref({})       // { category: [suggestion, ...] } — panel (≥ threshold)
-  // The typed tag-input dropdown searches the model's FULL prediction set for
-  // the image (min=0, down to the store floor) so low-confidence actions/
-  // features can be picked in canonical formatting (operator-asked 2026-06-09).
-  const allByCategory = ref({})
+  // ONE source of truth per image: every trained head scored for this image
+  // (min=0), each row carrying above_threshold. The Suggestions PANEL renders
+  // aboveByCategory; the typed tag-input dropdown reads the full set and
+  // annotates matching DB-tag rows with their score. A single fetch backs both —
+  // every suggestion is a canonical tag now (tagging-v2, #114), so there is no
+  // raw-prediction / create-new / alias-remap path to reconcile.
+  const byCategory = ref({})
   const { loading, error, run } = useAsyncAction({ errorAs: 'message' })
   let currentImageId = null
-  const inflightAll = useInflightToken()
-  // Audit 2026-06-02: this store had no inflight guard — a late
-  // /suggestions response from a prior image could overwrite
-  // byCategory while currentImageId pointed at a new one, and
-  // accept() dereferenced currentImageId AFTER an awaited POST so
-  // the subsequent /suggestions/accept could apply A's chosen tag
-  // to image B (and push it to the allowlist). Both fixed below
-  // by capturing imageId at call-time and gating writes on the token.
+  // Audit 2026-06-02: without an inflight guard a late /suggestions response from
+  // a prior image could overwrite byCategory while currentImageId points at a new
+  // one, and accept() could apply image A's tag to image B. Both guarded below by
+  // capturing imageId at call-time and gating writes on the token.
   const inflight = useInflightToken()
 
+  // The curated above-threshold subset the Suggestions panel shows. A rejected
+  // row that still scores above its cut stays (flagged) so the rejection is
+  // visible + reversible; below-threshold rows live only in the dropdown.
+  const aboveByCategory = computed(() => {
+    const out = {}
+    for (const [cat, list] of Object.entries(byCategory.value)) {
+      const kept = (list || []).filter(s => s.above_threshold)
+      if (kept.length) out[cat] = kept
+    }
+    return out
+  })
+
   async function load(imageId) {
-    // Cancel any in-flight load from the previous image so its late
-    // response can't overwrite this image's byCategory.
+    // Cancel any in-flight load from the previous image so its late response
+    // can't overwrite this image's list.
     inflight.cancel()
     currentImageId = imageId
     byCategory.value = {}  // cleared upfront so it stays empty on error
     const t = inflight.claim()
     await run(async () => {
-      const body = await api.get(`/api/images/${imageId}/suggestions`)
+      // min=0 → every head, each flagged above_threshold; the panel + the typed
+      // dropdown are both derived from this one payload.
+      const body = await api.get(`/api/images/${imageId}/suggestions`, {
+        params: { min: 0 },
+      })
       if (!t.isCurrent()) return
       byCategory.value = body.by_category || {}
     })
   }
 
-  // Load the full prediction set for the dropdown (separate inflight guard so a
-  // late response from a prior image can't overwrite the current one's list).
-  async function loadAll(imageId) {
-    inflightAll.cancel()
-    allByCategory.value = {}
-    const t = inflightAll.claim()
-    try {
-      const body = await api.get(`/api/images/${imageId}/suggestions`, {
-        params: { min: 0 },
-      })
-      if (!t.isCurrent()) return
-      allByCategory.value = body.by_category || {}
-    } catch {
-      // Dropdown is best-effort — the panel surfaces load errors.
-    }
-  }
-
-  // A stable identity for a suggestion across the two lists (panel vs dropdown
-  // are separate fetches, so object identity differs): tag id when known, else
-  // the raw display key.
+  // A stable identity for a suggestion across the panel + dropdown surfaces:
+  // its canonical tag id (every suggestion has one now).
   function _keyOf(s) {
-    return s.canonical_tag_id != null
-      ? `id:${s.canonical_tag_id}`
-      : `raw:${s.category}:${(s.display_name || '').toLowerCase()}`
+    return `id:${s.canonical_tag_id}`
   }
 
-  // Drop an accepted/dismissed suggestion from BOTH the panel list and the
-  // dropdown's full list so it can't reappear in either surface.
+  // Drop an accepted suggestion from the list so it can't reappear.
   function _dropEverywhere(suggestion) {
     const key = _keyOf(suggestion)
-    const cat = suggestion.category
-    for (const map of [byCategory.value, allByCategory.value]) {
-      const list = map[cat]
-      if (list) map[cat] = list.filter(s => _keyOf(s) !== key)
-    }
+    const list = byCategory.value[suggestion.category]
+    if (list) byCategory.value[suggestion.category] = list.filter(s => _keyOf(s) !== key)
   }
 
-  // Flip the `rejected` flag on the matching suggestion in BOTH lists in place,
-  // so a reject/un-reject shows immediately without dropping the row (visible,
+  // Flip the `rejected` flag on the matching suggestion in place, so a
+  // reject/un-reject shows immediately without dropping the row (visible,
   // reversible rejection — misclick recovery, operator-asked 2026-06-27).
   function _setRejectedEverywhere(suggestion, value) {
     const key = _keyOf(suggestion)
-    const cat = suggestion.category
-    for (const map of [byCategory.value, allByCategory.value]) {
-      for (const s of map[cat] || []) {
-        if (_keyOf(s) === key) s.rejected = value
-      }
+    for (const s of byCategory.value[suggestion.category] || []) {
+      if (_keyOf(s) === key) s.rejected = value
     }
   }
 
-  // opts.tagId: the tag's known id, when the caller already created/resolved
-  // it (TagPanel's manual-add-matches-suggestion path). Passed separately —
-  // NOT spread onto the suggestion — because _dropEverywhere keys off the
-  // suggestion object, and mutating canonical_tag_id on a raw suggestion
-  // would stop it matching its own row in the lists.
+  // opts.tagId: the tag's known id when the caller already resolved it (TagPanel's
+  // manual-add-matches-suggestion path). Passed separately — NOT spread onto the
+  // suggestion — because _dropEverywhere keys off the suggestion object.
   async function accept(suggestion, { tagId: knownTagId = null } = {}) {
-    // Capture imageId so a mid-flight prev/next can't reroute the
-    // accept POST to a different image AND push the tag to that
-    // image's allowlist.
+    // Capture imageId so a mid-flight prev/next can't reroute the accept POST to
+    // a different image.
     const imageId = currentImageId
     if (imageId == null) return
-    // Raw tags (creates_new_tag) have no canonical_tag_id; the backend's
-    // accept endpoint needs a tag_id, so for raw tags we create the tag
-    // first via the existing /api/tags endpoint, then accept by id.
-    let tagId = knownTagId ?? suggestion.canonical_tag_id
-    if (tagId == null) {
-      const created = await api.post('/api/tags', {
-        body: { name: suggestion.display_name, kind: suggestion.category }
-      })
-      tagId = created.id
-    }
+    const tagId = knownTagId ?? suggestion.canonical_tag_id
     await api.post(`/api/images/${imageId}/suggestions/accept`, {
       body: { tag_id: tagId }
     })
-    // Only drop from THIS image's category list — if the user navigated,
-    // the new image has its own suggestions and this drop would corrupt them.
+    // Only drop from THIS image's list — if the user navigated, the new image
+    // has its own suggestions and this drop would corrupt them.
     if (currentImageId === imageId) {
       _dropEverywhere(suggestion)
     }
     _acceptToast('Tagged', suggestion.display_name)
   }
 
-  // One non-blocking toast for accept/alias. The accepted tag is applied to this
-  // image and feeds head training; head auto-apply handles propagation (earned),
-  // so there's no instant fan-out to project.
+  // One non-blocking toast for accept. The accepted tag is applied to this image
+  // and feeds head training; head auto-apply handles propagation (earned).
   function _acceptToast(verb, displayName) {
     toast({ text: `${verb}: ${displayName}`, type: 'success' })
   }
 
-  async function aliasAccept(suggestion, canonicalTagId) {
-    const imageId = currentImageId
-    if (imageId == null) return
-    // The alias MUST be stored under the raw model key — resolution looks up the
-    // raw prediction key, not the normalized display name. Sending display_name
-    // (the old bug) stored an alias that never resolved, so the prediction kept
-    // reappearing unaliased. raw_name is null only for centroid hits, which
-    // can't be aliased (the UI hides the action for them).
-    const aliasString = suggestion.raw_name ?? suggestion.display_name
-    await api.post(`/api/images/${imageId}/suggestions/alias`, {
-      body: {
-        alias_string: aliasString,
-        alias_category: suggestion.category,
-        canonical_tag_id: canonicalTagId
-      }
-    })
-    if (currentImageId === imageId) {
-      _dropEverywhere(suggestion)
-    }
-    _acceptToast('Aliased & tagged', suggestion.display_name)
-  }
-
-  // Remove the alias behind an aliased suggestion (the raw prediction reverts to
-  // its unaliased form on reload). The canonical tag stays applied if it was
-  // accepted — this only undoes the model-key→tag mapping.
-  async function removeAlias(suggestion) {
-    const imageId = currentImageId
-    if (imageId == null || suggestion.raw_name == null) return
-    await api.delete(
-      `/api/aliases/${encodeURIComponent(suggestion.raw_name)}/${encodeURIComponent(suggestion.category)}`
-    )
-    if (currentImageId === imageId) {
-      await load(imageId)
-      await loadAll(imageId)
-    }
-    toast({ text: `Alias removed: ${suggestion.display_name}`, type: 'success' })
-  }
-
-  // Find a live (non-rejected) pending suggestion matching a manually-picked
-  // tag — by canonical id when known, else by (kind, name). Manually adding a
-  // tag the model also suggested must be indistinguishable from accepting the
-  // suggestion (recorded + dropped from the panel), so TagPanel routes matches
-  // through accept() (operator-asked 2026-07-03). Searches the full dropdown
-  // set first, then the panel list (loadAll is best-effort and can be empty).
+  // Find a live (non-rejected) suggestion matching a manually-picked tag — by
+  // canonical id when known, else by (kind, name). Manually adding a tag the
+  // model also suggested must be indistinguishable from accepting the suggestion
+  // (recorded + dropped from the panel), so TagPanel routes matches through
+  // accept() (operator-asked 2026-07-03).
   function findPending(kind, name, tagId = null) {
     const lname = (name || '').toLowerCase()
-    for (const map of [allByCategory.value, byCategory.value]) {
-      for (const list of Object.values(map)) {
-        for (const s of list || []) {
-          if (s.rejected) continue
-          if (tagId != null && s.canonical_tag_id === tagId) return s
-          if (
-            s.category === kind &&
-            (s.display_name || '').toLowerCase() === lname
-          ) return s
-        }
+    for (const list of Object.values(byCategory.value)) {
+      for (const s of list || []) {
+        if (s.rejected) continue
+        if (tagId != null && s.canonical_tag_id === tagId) return s
+        if (s.category === kind && (s.display_name || '').toLowerCase() === lname) return s
       }
     }
     return null
@@ -202,14 +132,8 @@ export const useSuggestionsStore = defineStore('suggestions', () => {
   async function dismiss(suggestion) {
     const imageId = currentImageId
     if (imageId == null) return
-    // Dismiss needs a tag_id. Raw tags (creates_new_tag) have none, so there's
-    // nothing to persist a rejection against — drop them client-side as before.
     // Canonical tags persist a rejection and STAY in the list flagged rejected,
     // so the operator can see it and one-click un-reject (misclick recovery).
-    if (suggestion.canonical_tag_id == null) {
-      if (currentImageId === imageId) _dropEverywhere(suggestion)
-      return
-    }
     await api.post(`/api/images/${imageId}/suggestions/dismiss`, {
       body: { tag_id: suggestion.canonical_tag_id }
     })
@@ -218,33 +142,31 @@ export const useSuggestionsStore = defineStore('suggestions', () => {
     }
   }
 
-  // Reject every still-unhandled suggestion in a category in one go ("confirm
-  // the good ones, reject the rest" — operator-asked 2026-07-06). Canonical tags
-  // persist a rejection and STAY flagged rejected (reversible, one-click
-  // un-reject); raw creates-new-tag rows drop client-side. Dispatched in parallel
-  // so a big section clears fast.
+  // Reject every still-unhandled VISIBLE (above-threshold) suggestion in a
+  // category in one go ("confirm the good ones, reject the rest" — operator-asked
+  // 2026-07-06). Only touches what the panel shows, not the low-confidence tail
+  // the dropdown carries. Dispatched in parallel so a big section clears fast.
   async function dismissRemaining(category) {
     const imageId = currentImageId
     if (imageId == null) return
-    const targets = (byCategory.value[category] || []).filter((s) => !s.rejected)
+    const targets = (byCategory.value[category] || []).filter(
+      (s) => s.above_threshold && !s.rejected
+    )
     if (!targets.length) return
-    const canon = targets.filter((s) => s.canonical_tag_id != null)
-    const raw = targets.filter((s) => s.canonical_tag_id == null)
-    await Promise.all(canon.map((s) =>
+    await Promise.all(targets.map((s) =>
       api.post(`/api/images/${imageId}/suggestions/dismiss`, {
         body: { tag_id: s.canonical_tag_id },
       })
     ))
     if (currentImageId === imageId) {
-      canon.forEach((s) => _setRejectedEverywhere(s, true))
-      raw.forEach((s) => _dropEverywhere(s))
+      targets.forEach((s) => _setRejectedEverywhere(s, true))
     }
   }
 
   // Undo a per-image dismissal — the suggestion reverts to a live row.
   async function undismiss(suggestion) {
     const imageId = currentImageId
-    if (imageId == null || suggestion.canonical_tag_id == null) return
+    if (imageId == null) return
     await api.post(`/api/images/${imageId}/suggestions/undismiss`, {
       body: { tag_id: suggestion.canonical_tag_id }
     })
@@ -254,8 +176,7 @@ export const useSuggestionsStore = defineStore('suggestions', () => {
   }
 
   return {
-    byCategory, allByCategory, loading, error,
-    load, loadAll, accept, aliasAccept, removeAlias, dismiss, dismissRemaining,
-    undismiss, findPending
+    byCategory, aboveByCategory, loading, error,
+    load, accept, dismiss, dismissRemaining, undismiss, findPending
   }
 })

frontend/src/styles/app.css

@@ -39,3 +39,91 @@
    deliberately not used here. `.fc-muted` is a custom class Vuetify never
    emits, so no specificity/reorder fight — no !important needed. */
 .fc-muted { color: rgb(var(--v-theme-on-surface-variant)); }
+
+/* Section sub-heading in settings cards (DRY pass #161): was redefined
+   identically in 4 cards, and TranslationCard used the class with NO local def
+   so its section headers rendered unstyled. Now one global utility. */
+.fc-section-h {
+  font-size: 13px; font-weight: 700; letter-spacing: 0.03em;
+  text-transform: uppercase; color: rgb(var(--v-theme-on-surface));
+}
+
+/* Status text colours (DRY pass #161): fc-good = success, fc-weak = error,
+   consolidated from the GPU / heads cards. fc-ok is intentionally NOT global —
+   it means on-surface in HeadsCard but success in QueuesTable. */
+.fc-good { color: rgb(var(--v-theme-success)); }
+.fc-weak { color: rgb(var(--v-theme-error)); }
+
+/* Vuetify 4 dropped its global CSS reset (normalisation moved into each
+   component). FC's layouts assumed the reset zeroed margins on text elements, so
+   restore just that — the "minimal reset" from the v4 upgrade guide — inside
+   Vuetify's own reset layer, which is low precedence so component + app styles
+   still win over it. Batch-4 Vuetify 3→4 (#1449). */
+@layer vuetify-core.reset {
+  ul, ol, figure, details, summary { padding: 0; margin: 0; }
+  h1, h2, h3, h4, h5, h6, p { margin: 0; }
+}
+
+/* Active-tab indicator (operator-flagged 2026-07-13 in the Vuetify-4 review): v4's
+   MD3 v-tab "slider" underline renders wider than the tab and floats below it. The
+   active tab's TEXT is already accent-coloured (color="accent"), so drop the slider
+   and mark the active tab with a subtle accent fill + rounded top — a clean,
+   unambiguous highlight app-wide (Subscriptions / Browse / Settings / Series). */
+.v-tab__slider { display: none !important; }
+.v-tab[aria-selected="true"],
+.v-tab.v-tab--selected {
+  background: rgb(var(--v-theme-accent) / 0.12);
+  border-radius: 8px 8px 0 0;
+}
+
+/* --- Continuous chrome fade (operator-asked 2026-07-13: "group the sub-nav as
+   part of the nav and use a single gradient in them"). ------------------------
+   The TopNav and any sticky sub-header pinned directly beneath it (Gallery's
+   filter bar, the Browse/Series/Settings/Subscriptions tabs bars) used to each
+   paint their OWN dark-to-transparent gradient (or a solid band), so the fade
+   read as happening TWICE — dark, fade out, then dark again. Instead the two
+   share ONE obsidian fade: the nav paints the TOP half (opaque → the seam
+   alpha) and the sub-header paints the CONTINUATION (seam alpha → transparent)
+   over its own height. Both reference --fc-chrome-seam, so the alphas meet
+   exactly at the 64px boundary — no re-darkening, no doubling, one gradient.
+
+   --fc-chrome-seam is the single knob: raise it for a heavier sub-header (more
+   legible tabs/controls over scrolling content), lower it for a lighter fade. */
+:root {
+  --fc-chrome-rgb: 20, 23, 26;   /* obsidian #14171A — matches the TopNav */
+  /* Alpha where the nav hands off to the sub-header — also the "hold" level of
+     the fade. The chrome stays fairly opaque (0.92 → this) through the bulk of
+     its height, then drops to transparent in a small eased section at the very
+     bottom (see the multi-stop gradients), so it reads as a slow falloff that
+     tails off softly rather than a straight line to a hard edge (operator
+     2026-07-13). Raise for heavier/​more-legible chrome, lower for a lighter fade. */
+  --fc-chrome-seam: 0.68;
+  /* Actual TopNav height, measured live (ResizeObserver in TopNav.vue) and used
+     by full-height workspaces (Explore/Subscriptions: calc(100vh - var)) and by
+     every sticky sub-header pinned beneath the nav (top: var). This was a
+     hardcoded 64px in ~6 places; Vuetify 4's MD3 sizing made the real nav a
+     different height, so the Explore workspace overflowed and its breadcrumb
+     tucked under the nav (#1481). This fallback is only used pre-measure. */
+  --fc-nav-h: 64px;
+}
+/* Applied to a sticky sub-header so it continues the nav's fade instead of
+   restarting it. Percentage stops so the fade always spans the element's height
+   (survives the filter bar's expanding refine panel). The blur keeps tabs and
+   controls legible as the fill thins toward transparent — the solid-surface
+   bars it replaces had none, so it must live here. */
+.fc-chrome-continues {
+  /* Continues the nav's fade: HOLDS near the seam alpha through the first ~55%
+     (subtle), then eases down to transparent over the last ~45% with an
+     intermediate stop so the tail is soft — no hard line at the bottom edge
+     (operator 2026-07-13). Percentage stops keep the shape spanning the
+     element's height (survives the filter bar's expanding refine panel). */
+  background: linear-gradient(
+    to bottom,
+    rgba(var(--fc-chrome-rgb), var(--fc-chrome-seam)) 0%,
+    rgba(var(--fc-chrome-rgb), 0.60) 55%,
+    rgba(var(--fc-chrome-rgb), 0.28) 82%,
+    rgba(var(--fc-chrome-rgb), 0) 100%
+  );
+  backdrop-filter: blur(2px);
+  -webkit-backdrop-filter: blur(2px);
+}

frontend/src/views/BrowseView.vue

@@ -7,7 +7,7 @@
          switcher and the search stay reachable no matter how far you scroll.
          Background uses the theme surface token so content scrolls cleanly
          under it (matches SettingsView's sticky tabs). -->
-    <div class="fc-browse__head">
+    <div class="fc-browse__head fc-chrome-continues">
       <v-container fluid class="py-0">
         <!-- Tabs and search share one row: the axis switcher on the left, the
              search field + active-scope chips on the right (operator-asked
@@ -154,9 +154,10 @@ function clearFilter(key) {
 <style scoped>
 .fc-browse__head {
   position: sticky;
-  top: 64px; /* directly under AppShell's 64px sticky TopNav */
+  top: var(--fc-nav-h, 64px); /* pins at the nav's real measured bottom (#1481) */
   z-index: 4;
-  background: rgb(var(--v-theme-surface));
+  /* Background is the shared .fc-chrome-continues fade — it continues the nav's
+     gradient instead of a solid surface band (operator 2026-07-13). */
 }
 .fc-browse__bar {
   display: flex;

frontend/src/views/ExploreView.vue

@@ -31,6 +31,20 @@
           <img :src="c.thumbnail_url" alt="" loading="lazy" />
         </button>
         <div class="fc-ex__trail-actions">
+          <!-- Reach (#1476): how far each step reaches past the anchor's cluster.
+               Raise it to break out of a dense signature without hitting Random. -->
+          <div
+            class="fc-ex__reach"
+            title="How far each step reaches — raise it to escape a dense cluster without going fully random"
+          >
+            <v-icon size="16" color="accent">mdi-map-marker-distance</v-icon>
+            <v-slider
+              :model-value="store.reach" @end="store.setReach"
+              :min="0" :max="1" :step="0.2" hide-details density="compact"
+              color="accent" class="fc-ex__reach-slider"
+            />
+            <span class="fc-muted fc-ex__reach-label">{{ reachLabel }}</span>
+          </div>
           <!-- Active retrain right where you tag: fold the +/- you just gave
                into the heads without a trip to Settings (the nightly beat is the
                passive cadence). -->
@@ -153,6 +167,12 @@ const modal = useModalStore()
 
 const anchorId = computed(() => route.params.imageId || null)
 const isVideo = computed(() => !!store.anchor?.mime?.startsWith('video/'))
+const reachLabel = computed(() => {
+  const r = store.reach
+  if (r <= 0.15) return 'Near'
+  if (r <= 0.55) return 'Varied'
+  return 'Far'
+})
 
 // #1206: hovering a suggestion in the rail highlights the crop it came from on
 // the anchor image (same provide/inject as the modal viewer).
@@ -264,12 +284,14 @@ onUnmounted(() => {
 </script>
 
 <style scoped>
-.fc-muted { color: rgb(var(--v-theme-on-surface-variant)); }
 
-/* Full-height workspace under the sticky top nav. */
+/* Full-height workspace under the sticky top nav. --fc-nav-h is the nav's REAL
+   measured height (set by TopNav) — a hardcoded 64px here overflowed the
+   viewport under Vuetify 4's taller nav and tucked the breadcrumb under it
+   (#1481). Panes scroll internally, so an exact fit keeps everything on screen. */
 .fc-ex {
   display: flex; flex-direction: column;
-  height: calc(100vh - 64px);
+  height: calc(100vh - var(--fc-nav-h, 64px));
   min-height: 0;
 }
 
@@ -296,6 +318,14 @@ onUnmounted(() => {
 .fc-ex__trail-actions {
   margin-left: auto; display: flex; align-items: center; gap: 4px; flex: 0 0 auto;
 }
+.fc-ex__reach {
+  display: flex; align-items: center; gap: 6px;
+  margin-right: 8px;
+}
+.fc-ex__reach-slider { width: 96px; }
+.fc-ex__reach-label {
+  font-size: 12px; min-width: 44px; text-align: left;
+}
 
 /* The three panes fill the remaining height; each scrolls on its own.
    grid-template-rows: minmax(0, 1fr) BOUNDS the single row to the container

frontend/src/views/SeriesView.vue

@@ -4,7 +4,7 @@
          the 64px TopNav (operator-asked 2026-06-12), so the axis switcher and
          search/sort stay reachable on a long grid. The controls can't sit
          inside v-window (it clips sticky children), so they're hoisted here. -->
-    <div class="fc-series__head">
+    <div class="fc-series__head fc-chrome-continues">
       <v-tabs v-model="tab" density="compact">
         <v-tab value="browse">Browse</v-tab>
         <v-tab value="suggestions">
@@ -294,12 +294,13 @@ onMounted(() => {
 
 <style scoped>
 /* Sticky header (tabs + active-tab controls) pinned under the 64px TopNav, so
-   content scrolls cleanly beneath it. Surface bg matches SettingsView. */
+   content scrolls cleanly beneath it. Background is the shared
+   .fc-chrome-continues fade — continues the nav's gradient rather than a solid
+   band (operator 2026-07-13). */
 .fc-series__head {
   position: sticky;
-  top: 64px;
+  top: var(--fc-nav-h, 64px); /* pins at the nav's real measured bottom (#1481) */
   z-index: 4;
-  background: rgb(var(--v-theme-surface));
   padding-bottom: 12px;
 }
 .fc-series-browse__controls {

frontend/src/views/SettingsView.vue

@@ -7,13 +7,11 @@
     <!-- Sticky tabs: operator-flagged 2026-05-25 — long Import / Maintenance
          panels pushed the tab strip out of the viewport, forcing a scroll-
          to-top just to change tab. AppShell's TopNav is 64px sticky, so the
-         tab strip lives directly under it. Background uses the theme surface
-         token so it visually merges with the page rather than the
-         translucent v-tabs default. -->
+         tab strip lives directly under it. The .fc-chrome-continues fade
+         continues the nav's gradient across the strip (operator 2026-07-13). -->
     <v-tabs
-      v-model="tab" color="accent" class="mb-4"
-      style="position: sticky; top: 64px; z-index: 4;
-             background: rgb(var(--v-theme-surface));"
+      v-model="tab" color="accent" class="mb-4 fc-chrome-continues"
+      style="position: sticky; top: var(--fc-nav-h, 64px); z-index: 4;"
     >
       <v-tab value="overview">Overview</v-tab>
       <v-tab value="activity">Activity</v-tab>

frontend/src/views/SubscriptionsView.vue

@@ -5,7 +5,7 @@
       align-tabs="start"
       color="accent"
       density="compact"
-      class="fc-subs-tabs"
+      class="fc-subs-tabs fc-chrome-continues"
     >
       <v-tab value="subscriptions">
         <v-icon start>mdi-account-multiple-check</v-icon>
@@ -55,15 +55,18 @@ const { tab } = useTabQuery(VALID_TABS, 'subscriptions')
   /* Fixed-height hub: the tabs (and each tab's sticky control bar) stay
      put while ONLY the tab content scrolls — previously the whole view
      scrolled instead of just the subscription list (operator-flagged
-     2026-05-28). 64px = the TopNav height (AppShell .fc-content pad-top). */
-  height: calc(100vh - 64px);
+     2026-05-28). --fc-nav-h = the TopNav's real measured height (#1481). */
+  height: calc(100vh - var(--fc-nav-h, 64px));
   display: flex;
   flex-direction: column;
   overflow: hidden;
 }
 .fc-subs-tabs {
   flex: 0 0 auto;
-  border-bottom: 1px solid rgb(var(--v-theme-on-surface-variant) / 0.18);
+  /* Cancel the shell's pt-2 so the tabs sit flush under the 64px nav, letting
+     the .fc-chrome-continues fade read as one gradient with it (operator
+     2026-07-13). The fade replaces the old border-bottom separator. */
+  margin-top: -8px;
 }
 .fc-subs-window {
   flex: 1 1 auto;

frontend/src/views/TagsView.vue

@@ -349,7 +349,6 @@ async function onDeleteTagConfirm() {
 .fc-tags__sentinel {
   display: flex; justify-content: center; padding: 32px 0; min-height: 60px;
 }
-.fc-muted { color: rgb(var(--v-theme-on-surface-variant)); }
 .fc-merge-preview {
   padding: 10px 12px;
   border: 1px solid rgba(var(--v-theme-on-surface), 0.12);

frontend/test/suggestions.spec.js

@@ -16,25 +16,44 @@ function stubFetch(handler) {
   })
 }
 
+// Every suggestion is a canonical DB tag now (tagging-v2): a real id, flagged
+// above/below its head's suggest threshold. No raw / creates-new / alias cases.
 const sugg = (over = {}) => ({
   canonical_tag_id: 7,
   display_name: 'Ichigo',
   category: 'character',
   score: 0.9,
   source: 'head',
-  creates_new_tag: false,
+  above_threshold: true,
   rejected: false,
   ...over,
 })
 
-// Seed the store through its own load/loadAll so currentImageId is set the
-// way the panel sets it (accept() derives the image from it).
+// Seed the store through its single load() so currentImageId is set the way the
+// panel sets it (accept() derives the image from it).
 async function seed(store, byCategory) {
   stubFetch(() => ({ status: 200, body: { by_category: byCategory } }))
   await store.load(1)
-  await store.loadAll(1)
 }
 
+describe('suggestions store: load derives aboveByCategory', () => {
+  beforeEach(() => setActivePinia(createPinia()))
+  afterEach(() => vi.restoreAllMocks())
+
+  it('one fetch backs both surfaces: byCategory is the full set, aboveByCategory the panel subset', async () => {
+    const s = useSuggestionsStore()
+    await seed(s, {
+      general: [
+        sugg({ canonical_tag_id: 1, display_name: 'sword', category: 'general' }),
+        sugg({ canonical_tag_id: 2, display_name: 'faint', category: 'general', above_threshold: false }),
+      ],
+    })
+    expect(s.byCategory.general).toHaveLength(2)          // dropdown sees all
+    expect(s.aboveByCategory.general).toHaveLength(1)      // panel sees above-threshold only
+    expect(s.aboveByCategory.general[0].display_name).toBe('sword')
+  })
+})
+
 describe('suggestions store: findPending (manual add == accept, 2026-07-03)', () => {
   beforeEach(() => setActivePinia(createPinia()))
   afterEach(() => vi.restoreAllMocks())
@@ -45,15 +64,12 @@ describe('suggestions store: findPending (manual add == accept, 2026-07-03)', ()
     expect(s.findPending('general', 'unrelated', 7)?.display_name).toBe('Ichigo')
   })
 
-  it('matches raw suggestions by kind + name, case-insensitively', async () => {
+  it('matches by kind + name, case-insensitively', async () => {
     const s = useSuggestionsStore()
     await seed(s, {
-      general: [sugg({
-        canonical_tag_id: null, display_name: 'Holding Sword',
-        category: 'general', creates_new_tag: true,
-      })],
+      general: [sugg({ canonical_tag_id: 12, display_name: 'Holding Sword', category: 'general' })],
     })
-    expect(s.findPending('general', 'holding sword')).toBeTruthy()
+    expect(s.findPending('general', 'holding sword')?.canonical_tag_id).toBe(12)
     // Kind must match: same name under another kind is a different tag.
     expect(s.findPending('character', 'holding sword')).toBeNull()
   })
@@ -66,37 +82,31 @@ describe('suggestions store: findPending (manual add == accept, 2026-07-03)', ()
   })
 })
 
-describe('suggestions store: accept with a known tag id', () => {
+describe('suggestions store: accept', () => {
   beforeEach(() => setActivePinia(createPinia()))
   afterEach(() => vi.restoreAllMocks())
 
-  it('POSTs only the accept endpoint (no tag create) and drops the row', async () => {
+  it('POSTs only the accept endpoint (canonical id) and drops the row', async () => {
     const s = useSuggestionsStore()
     await seed(s, { character: [sugg()] })
     const calls = []
     stubFetch((url, init) => {
-      calls.push({ url, method: init?.method })
+      calls.push({ url, method: init?.method, body: init?.body })
       return { status: 200, body: { accepted: true, tag_id: 7 } }
     })
-    await s.accept(s.byCategory.character[0], { tagId: 7 })
+    await s.accept(s.byCategory.character[0])
     expect(calls).toHaveLength(1)
     expect(calls[0].url).toContain('/api/images/1/suggestions/accept')
+    expect(JSON.parse(calls[0].body)).toEqual({ tag_id: 7 })
     expect(s.byCategory.character).toHaveLength(0)
-    expect(s.allByCategory.character).toHaveLength(0)
   })
 
-  it('a RAW suggestion accepted with a known tagId skips create AND still drops its row', async () => {
-    // TagPanel's manual-create path: the tag was just created by
-    // host.createAndAdd, so accept must not create again — and the drop must
-    // key off the original raw suggestion object, not the resolved id
-    // (regression: spreading canonical_tag_id onto the suggestion changed its
-    // identity key and left the panel row behind).
+  it('honors a known tagId and still drops the row by the suggestion identity', async () => {
+    // TagPanel's manual-add-matches-suggestion path passes the resolved tag id;
+    // accept sends exactly it and drops the original suggestion row (which keys
+    // off the suggestion object, not the passed id).
     const s = useSuggestionsStore()
-    const raw = sugg({
-      canonical_tag_id: null, display_name: 'Holding Sword',
-      category: 'general', creates_new_tag: true,
-    })
-    await seed(s, { general: [raw] })
+    await seed(s, { general: [sugg({ canonical_tag_id: 12, display_name: 'Holding Sword', category: 'general' })] })
     const calls = []
     stubFetch((url, init) => {
       calls.push({ url, body: init?.body })
@@ -107,6 +117,5 @@ describe('suggestions store: accept with a known tag id', () => {
     expect(calls[0].url).toContain('/api/images/1/suggestions/accept')
     expect(JSON.parse(calls[0].body)).toEqual({ tag_id: 42 })
     expect(s.byCategory.general).toHaveLength(0)
-    expect(s.allByCategory.general).toHaveLength(0)
   })
 })

renovate.json

@@ -0,0 +1,19 @@
+{
+  "$schema": "https://docs.renovatebot.com/renovate-schema.json",
+  "extends": [
+    "config:recommended"
+  ],
+  "packageRules": [
+    {
+      "description": "Bundle the interlocking frontend build/test toolchain into ONE PR. vite, vitest, @vitejs/plugin-vue, happy-dom and @vue/test-utils are version-coupled — a lone major bump red-fails the build/tests until its peers land, so they must move together.",
+      "matchPackageNames": [
+        "vite",
+        "vitest",
+        "@vitejs/plugin-vue",
+        "happy-dom",
+        "@vue/test-utils"
+      ],
+      "groupName": "frontend build/test toolchain"
+    }
+  ]
+}

requirements.txt

@@ -7,14 +7,14 @@ sqlalchemy[asyncio]>=2.0,<2.1
 asyncpg>=0.31,<0.32
 psycopg[binary]>=3.3,<3.4
 alembic>=1.18,<1.19
-pgvector>=0.4,<0.5
+pgvector>=0.5,<0.6
 
 # Task queue
 celery>=5.6,<5.7
 redis>=7.4,<8.0
 
 # Crypto for credential storage (lands in FC-3, but pinned now for stability)
-cryptography>=48,<49
+cryptography>=49,<50
 
 # Image handling (lands in FC-2)
 pillow>=12,<13
@@ -30,10 +30,10 @@ yt-dlp>=2025.1
 
 # Utilities
 python-dotenv>=1.2,<2.0
-structlog>=25.5,<26.0
+structlog>=26.1,<26.2
 
 # HTML sanitization for scraped post descriptions (FC-2d provenance)
-nh3>=0.2,<0.3
+nh3>=0.3,<0.4
 
 # Archive extraction (FC-2d-iii filesystem-import aid)
 rarfile>=4.2,<5
@@ -42,4 +42,4 @@ py7zr>=1,<2
 # Google Drive fetcher for off-platform file-host links (external downloads,
 # #830). Handles Drive's confirm-token + virus-scan interstitial. mega.nz uses
 # the `megatools` binary instead (Debian apt pkg in the runtime image, not pip).
-gdown>=5,<6
+gdown>=6,<7

tests/test_api_posts.py

@@ -184,6 +184,68 @@ async def test_rejects_bad_direction(client):
     assert (await resp.get_json())["error"] == "invalid_direction"
 
 
+@pytest.mark.asyncio
+async def test_translation_override_rejects_bad_value(client, seeded_post):
+    _, _, post = seeded_post
+    resp = await client.post(
+        f"/api/posts/{post.id}/translation-override", json={"override": "nope"}
+    )
+    assert resp.status_code == 400
+    assert (await resp.get_json())["error"] == "invalid_override"
+
+
+@pytest.mark.asyncio
+async def test_translation_override_404_for_unknown(client):
+    resp = await client.post(
+        "/api/posts/999999/translation-override", json={"override": "original"}
+    )
+    assert resp.status_code == 404
+
+
+@pytest.mark.asyncio
+async def test_translation_override_original_clears_and_keeps(client, db, seeded_post):
+    # 'keep original' clears a stored translation immediately (no Interpreter) and
+    # marks the post handled (== target). Asserts on the response, which reflects
+    # the endpoint's own committed session.
+    _, _, post = seeded_post
+    post.post_title_translated = "STALE"
+    post.description_translated = "STALE"
+    post.translated_source_lang = "de"
+    await db.commit()
+    resp = await client.post(
+        f"/api/posts/{post.id}/translation-override", json={"override": "original"}
+    )
+    assert resp.status_code == 200
+    body = await resp.get_json()
+    assert body["translation_override"] == "original"
+    assert body["applied"] == "cleared"
+    assert body["post_title_translated"] is None
+    assert body["translated_source_lang"] == "en"
+
+
+@pytest.mark.asyncio
+async def test_translation_override_force_queues_when_disabled(client, seeded_post):
+    # Translation disabled (default) → can't translate inline; the override is
+    # saved and the post is queued (columns NULLed) for the next sweep.
+    _, _, post = seeded_post
+    resp = await client.post(
+        f"/api/posts/{post.id}/translation-override", json={"override": "force"}
+    )
+    assert resp.status_code == 200
+    body = await resp.get_json()
+    assert body["translation_override"] == "force"
+    assert body["applied"] == "queued"
+    assert body["translated_source_lang"] is None
+
+
+@pytest.mark.asyncio
+async def test_list_exposes_translation_override(client, seeded_post):
+    resp = await client.get("/api/posts")
+    assert resp.status_code == 200
+    body = await resp.get_json()
+    assert body["items"][0]["translation_override"] == "auto"   # default
+
+
 @pytest.mark.asyncio
 async def test_detail_returns_uncapped_thumbnails(client, db):
     """Feed query caps thumbnails at 6 for previews; detail endpoint

tests/test_api_settings.py

@@ -53,6 +53,26 @@ async def test_translation_settings_defaults_and_patch(client):
         "/api/settings/import", json={"interpreter_base_url": 123})).status_code == 400
 
 
+@pytest.mark.asyncio
+async def test_translation_min_confidence_default_and_patch(client):
+    # #155: the latin-script acceptance floor is an operator-tunable setting,
+    # default 0.9 (stricter than the old hardcoded 0.8).
+    body = await (await client.get("/api/settings/import")).get_json()
+    assert body["translation_min_confidence"] == 0.9
+
+    ok = await client.patch(
+        "/api/settings/import", json={"translation_min_confidence": 0.95}
+    )
+    assert ok.status_code == 200
+    assert (await ok.get_json())["translation_min_confidence"] == 0.95
+
+    # Out-of-range + wrong-type are rejected.
+    assert (await client.patch(
+        "/api/settings/import", json={"translation_min_confidence": 1.5})).status_code == 400
+    assert (await client.patch(
+        "/api/settings/import", json={"translation_min_confidence": "high"})).status_code == 400
+
+
 @pytest.mark.asyncio
 async def test_translation_status_defaults(client):
     # Off + no URL → no network health call, healthy False (#143).
@@ -61,6 +81,34 @@ async def test_translation_status_defaults(client):
     assert body["base_url_set"] is False
     assert body["healthy"] is False
     assert "untranslated_count" in body
+    assert body["active"] is False      # no sweep running
+    assert body["last_run"] is None
+
+
+@pytest.mark.asyncio
+async def test_translation_status_reports_active_and_last_run(client, db):
+    # A running translate/retranslate TaskRun → active True; the most recent
+    # finished one → last_run (task basename + status).
+    from datetime import UTC, datetime
+
+    from backend.app.models import TaskRun
+
+    db.add(TaskRun(
+        celery_task_id="r-run", queue="maintenance_long",
+        task_name="backend.app.tasks.translation.retranslate_posts",
+        started_at=datetime.now(UTC), status="running",
+    ))
+    db.add(TaskRun(
+        celery_task_id="r-done", queue="maintenance_long",
+        task_name="backend.app.tasks.translation.translate_posts",
+        started_at=datetime.now(UTC), finished_at=datetime.now(UTC),
+        status="success",
+    ))
+    await db.commit()
+    body = await (await client.get("/api/settings/translation/status")).get_json()
+    assert body["active"] is True
+    assert body["last_run"]["task"] == "translate_posts"
+    assert body["last_run"]["status"] == "success"
 
 
 @pytest.mark.asyncio
@@ -85,9 +133,10 @@ async def test_translation_test_connection(client, monkeypatch):
 
 @pytest.mark.asyncio
 async def test_translation_run_enqueues_when_configured(client, monkeypatch):
+    sink = {}
     monkeypatch.setattr(
         "backend.app.tasks.translation.translate_posts.delay",
-        lambda *a, **k: type("R", (), {"id": "t1"})(),
+        lambda *a, **k: sink.update(k) or type("R", (), {"id": "t1"})(),
     )
     await client.patch("/api/settings/import", json={
         "translation_enabled": True, "interpreter_base_url": "http://i.lan",
@@ -95,6 +144,108 @@ async def test_translation_run_enqueues_when_configured(client, monkeypatch):
     resp = await client.post("/api/settings/translation/run")
     assert resp.status_code == 202
     assert (await resp.get_json())["celery_task_id"] == "t1"
+    assert sink["drain"] is True   # "Translate now" chases the whole backlog
+
+
+@pytest.mark.asyncio
+async def test_translation_probe_requires_text(client):
+    resp = await client.post(
+        "/api/settings/translation/probe", json={"text": "  "})
+    assert resp.status_code == 400
+
+
+@pytest.mark.asyncio
+async def test_translation_probe_requires_base_url(client):
+    # Text given but no Interpreter URL saved → nothing to probe against.
+    resp = await client.post(
+        "/api/settings/translation/probe", json={"text": "hello"})
+    assert resp.status_code == 400
+
+
+@pytest.mark.asyncio
+async def test_translation_probe_returns_detection(client, monkeypatch):
+    # The diagnostic surfaces detected language + confidence + result, unsaved.
+    monkeypatch.setattr(
+        "backend.app.api.settings.ic.translate",
+        lambda texts, **k: {
+            "translations": ["Work in Progress"],
+            "detected_lang": "de", "detected_confidence": 71.5,
+            "engine": "llm", "engine_version": "v1",
+        },
+    )
+    await client.patch("/api/settings/import", json={
+        "translation_enabled": True, "interpreter_base_url": "http://i.lan",
+    })
+    resp = await client.post(
+        "/api/settings/translation/probe", json={"text": "WIP"})
+    assert resp.status_code == 200
+    body = await resp.get_json()
+    assert body["detected_lang"] == "de"
+    assert body["detected_confidence"] == 71.5
+    assert body["translated"] == "Work in Progress"
+    assert body["target"] == "en"
+
+
+def _fake_retranslate(monkeypatch, sink):
+    # Record the kwargs the endpoint enqueues with, return a fake AsyncResult.
+    monkeypatch.setattr(
+        "backend.app.tasks.translation.retranslate_posts.delay",
+        lambda *a, **k: sink.update(k) or type("R", (), {"id": "r1"})(),
+    )
+
+
+@pytest.mark.asyncio
+async def test_translation_retranslate_requires_config(client):
+    # Disabled → 400 even with an explicit scope (no reset is enqueued).
+    resp = await client.post(
+        "/api/settings/translation/retranslate", json={"all": True})
+    assert resp.status_code == 400
+
+
+@pytest.mark.asyncio
+async def test_translation_retranslate_requires_target(client, monkeypatch):
+    # 'all' must be explicit: an empty body is a 400, so a stray call can't
+    # wipe every translation.
+    _fake_retranslate(monkeypatch, {})
+    await client.patch("/api/settings/import", json={
+        "translation_enabled": True, "interpreter_base_url": "http://i.lan",
+    })
+    resp = await client.post("/api/settings/translation/retranslate")
+    assert resp.status_code == 400
+
+
+@pytest.mark.asyncio
+async def test_translation_retranslate_artist_scope(client, monkeypatch):
+    sink = {}
+    _fake_retranslate(monkeypatch, sink)
+    await client.patch("/api/settings/import", json={
+        "translation_enabled": True, "interpreter_base_url": "http://i.lan",
+    })
+    resp = await client.post(
+        "/api/settings/translation/retranslate", json={"artist_id": 7})
+    assert resp.status_code == 202
+    assert (await resp.get_json())["celery_task_id"] == "r1"
+    assert sink["artist_ids"] == [7]
+
+
+@pytest.mark.asyncio
+async def test_translation_retranslate_all_scope(client, monkeypatch):
+    sink = {}
+    _fake_retranslate(monkeypatch, sink)
+    await client.patch("/api/settings/import", json={
+        "translation_enabled": True, "interpreter_base_url": "http://i.lan",
+    })
+    resp = await client.post(
+        "/api/settings/translation/retranslate", json={"all": True})
+    assert resp.status_code == 202
+    assert sink["artist_ids"] is None
+
+
+@pytest.mark.asyncio
+async def test_translation_retranslate_bad_artist_id(client):
+    resp = await client.post(
+        "/api/settings/translation/retranslate", json={"artist_id": "abc"})
+    assert resp.status_code == 400
 
 
 @pytest.mark.asyncio

tests/test_api_suggestions.py

@@ -52,6 +52,7 @@ async def test_get_suggestions(client, db):
     general = body["by_category"].get("general", [])
     s2 = next(x for x in general if x["canonical_tag_id"] == tag.id)
     assert s2["source"] == "head"
+    assert s2["above_threshold"] is True   # ~0.73 clears the 0.5 suggest cut
 
 
 @pytest.mark.asyncio
@@ -114,12 +115,3 @@ async def test_undismiss_reverses_rejection(client, db):
         f"/api/images/{img.id}/suggestions/undismiss", json={"tag_id": tag.id}
     )
     assert resp2.status_code == 204
-
-
-@pytest.mark.asyncio
-async def test_alias_requires_fields(client, db):
-    img = await _img(db)
-    resp = await client.post(
-        f"/api/images/{img.id}/suggestions/alias", json={"alias_string": "x"}
-    )
-    assert resp.status_code == 400

tests/test_extension_url_derive.py

@@ -0,0 +1,65 @@
+"""Unit tests for ExtensionService._derive — the URL → (platform, slug)
+parser that gates the browser extension's "Add as source" button and pulls
+the creator slug on probe/add.
+
+Regression cover for #1485: Patreon serves the same creator under three URL
+shapes — bare `patreon.com/Atole`, `c/`, and `cw/` (the "creator workspace"
+URL you land on once SUBSCRIBED). The button used to vanish while subscribed
+because the pattern only matched the bare root and excluded `c/`.
+
+_derive is pure URL parsing (no DB / no async), so a session-less instance is
+fine to exercise directly.
+"""
+
+import pytest
+
+from backend.app.services.extension_service import (
+    ExtensionService,
+    InvalidUrlError,
+    UnknownPlatformError,
+)
+
+_svc = ExtensionService(None)
+
+
+@pytest.mark.parametrize(
+    "url, slug",
+    [
+        # All three Patreon creator prefixes resolve to the same vanity slug.
+        ("https://www.patreon.com/Atole", "Atole"),
+        ("https://www.patreon.com/c/Atole", "Atole"),
+        ("https://www.patreon.com/cw/Atole", "Atole"),  # subscribed-view URL
+        # A creator's inner page still derives the slug (trailing sub-path).
+        ("https://www.patreon.com/cw/Atole/posts", "Atole"),
+        ("https://www.patreon.com/Atole/membership", "Atole"),
+        ("https://patreon.com/c/Atole", "Atole"),  # bare host, no www
+    ],
+)
+def test_derive_patreon_creator_urls(url, slug):
+    platform, got = _svc._derive(url)
+    assert platform == "patreon"
+    assert got == slug
+
+
+@pytest.mark.parametrize(
+    "url",
+    [
+        # Patreon's own nav pages must never read as a creator slug.
+        "https://www.patreon.com/home",
+        "https://www.patreon.com/settings",
+        "https://www.patreon.com/search",
+        "https://www.patreon.com/messages",
+        "https://www.patreon.com/library",
+        "https://www.patreon.com/notifications",
+        "https://www.patreon.com/posts/12345",       # post permalink
+        "https://www.patreon.com/settings/billing",  # nav sub-page
+    ],
+)
+def test_derive_patreon_nav_pages_rejected(url):
+    with pytest.raises(UnknownPlatformError):
+        _svc._derive(url)
+
+
+def test_derive_rejects_missing_scheme():
+    with pytest.raises(InvalidUrlError):
+        _svc._derive("patreon.com/Atole")