Merge pull request 'fix(extension): Add-to-FC button on subscribed Patreon creators + v1.0.8 (#1485)' (#230) from dev into main

pg_dump + zstd in runtime image, lift Quart body cap to 1 GiB. See PR #2.

backend/app/api/gpu.py

@@ -256,7 +256,9 @@ 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 MLSettings.load(session)
+        ml = (
+            await session.execute(select(MLSettings).where(MLSettings.id == 1))
+        ).scalar_one()
         # image rows for url/mime in one shot
         ids = [j.image_record_id for j in jobs]
         imgs = {

backend/app/api/ml_admin.py

@@ -4,7 +4,6 @@ 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")
 
@@ -84,21 +83,48 @@ 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 MLSettings.load(session)
+        s = (
-    # Table-driven off _EDITABLE (which PATCH also writes) so a new settings field
+            await session.execute(select(MLSettings).where(MLSettings.id == 1))
-    # can never be silently absent from GET — the split that historically dropped
+        ).scalar_one()
-    # fields. _EDITABLE already includes *_DETECTOR_FIELDS.
+    return jsonify(
-    return jsonify({f: getattr(s, f) for f in _EDITABLE})
+        {
+            "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,
+            "process_auto_apply_enabled": s.process_auto_apply_enabled,
+            "process_auto_apply_threshold": s.process_auto_apply_threshold,
+            "process_conflict_threshold": s.process_conflict_threshold,
+            "embedder_model_name": s.embedder_model_name,
+            **{f: getattr(s, f) for f in _DETECTOR_FIELDS},
+        }
+    )
 
 
 @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 MLSettings.load(session)
+        s = (
+            await session.execute(select(MLSettings).where(MLSettings.id == 1))
+        ).scalar_one()
 
         # Merge the patch over current values, then validate the result as a
         # whole — the store-floor invariant couples three fields, so they
@@ -128,24 +154,24 @@ 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 (AUTO_APPLY_THRESHOLD_MIN <= float(p["head_auto_apply_precision"]) <= AUTO_APPLY_THRESHOLD_MAX):
+    if not (0.5 <= float(p["head_auto_apply_precision"]) <= 0.999):
-        return f"head_auto_apply_precision must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
+        return "head_auto_apply_precision must be between 0.5 and 0.999"
     if int(p["head_auto_apply_min_positives"]) < 1:
         return "head_auto_apply_min_positives must be >= 1"
-    if not (AUTO_APPLY_THRESHOLD_MIN <= float(p["ccip_match_threshold"]) <= AUTO_APPLY_THRESHOLD_MAX):
+    if not (0.5 <= float(p["ccip_match_threshold"]) <= 0.999):
-        return f"ccip_match_threshold must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
+        return "ccip_match_threshold must be between 0.5 and 0.999"
-    if not (AUTO_APPLY_THRESHOLD_MIN <= float(p["ccip_auto_apply_threshold"]) <= AUTO_APPLY_THRESHOLD_MAX):
+    if not (0.5 <= float(p["ccip_auto_apply_threshold"]) <= 0.999):
-        return f"ccip_auto_apply_threshold must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
+        return "ccip_auto_apply_threshold must be between 0.5 and 0.999"
     # Presentation chrome auto-hide (#141). Auto-apply runs high (hiding is
     # consequential); the conflict cut is a plain probability [0,1].
-    if not (AUTO_APPLY_THRESHOLD_MIN <= float(p["presentation_auto_apply_threshold"]) <= AUTO_APPLY_THRESHOLD_MAX):
+    if not (0.5 <= float(p["presentation_auto_apply_threshold"]) <= 0.999):
-        return f"presentation_auto_apply_threshold must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
+        return "presentation_auto_apply_threshold must be between 0.5 and 0.999"
     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):
+    if not (0.5 <= float(p["process_auto_apply_threshold"]) <= 0.999):
-        return f"process_auto_apply_threshold must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
+        return "process_auto_apply_threshold must be between 0.5 and 0.999"
     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

backend/app/api/settings.py

@@ -66,9 +66,34 @@ _EXTDL_TOGGLE_FIELDS = (
 async def get_import_settings():
     async with get_session() as session:
         row = await ImportSettings.load(session)
-    # Table-driven off _EDITABLE_FIELDS (which PATCH also writes) so a new field
+    return jsonify({
-    # can't be silently absent from GET.
+        "min_width": row.min_width,
-    return jsonify({f: getattr(row, f) for f in _EDITABLE_FIELDS})
+        "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,
+        "translation_min_confidence": row.translation_min_confidence,
+        "wip_title_tagging_enabled": row.wip_title_tagging_enabled,
+        "wip_soft_title_tagging_enabled": row.wip_soft_title_tagging_enabled,
+    })
 
 
 @settings_bp.route("/settings/import", methods=["PATCH"])

backend/app/models/ml_settings.py

@@ -10,7 +10,6 @@ from sqlalchemy import (
     Integer,
     String,
     func,
-    select,
 )
 from sqlalchemy.orm import Mapped, mapped_column
 
@@ -213,14 +212,3 @@ 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/services/ml/character_prototypes.py

@@ -150,7 +150,9 @@ 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 = MLSettings.load_sync(session)
+    settings = session.execute(
+        select(MLSettings).where(MLSettings.id == 1)
+    ).scalar_one()
     sig = _global_signature(session)
     if not full and settings.ccip_ref_signature == sig:
         return {"skipped": True, "rebuilt": 0, "removed": 0}
@@ -202,7 +204,9 @@ def retract_auto_applied_ccip(session: Session) -> int:
     n_retracted."""
     import numpy as np
 
-    settings = MLSettings.load_sync(session)
+    settings = session.execute(
+        select(MLSettings).where(MLSettings.id == 1)
+    ).scalar_one()
     if not settings.ccip_auto_apply_enabled:
         return 0
     thr = float(settings.ccip_auto_apply_threshold)

backend/app/services/ml/heads.py

@@ -23,7 +23,6 @@ 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
 
@@ -43,7 +42,6 @@ from ...models import (
 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,
@@ -63,14 +61,6 @@ 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.
@@ -88,38 +78,6 @@ _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."""
 
@@ -145,7 +103,9 @@ def start_head_training_run(session: Session, params: dict[str, Any]) -> int:
 
 
 def _settings(session: Session) -> MLSettings:
-    return MLSettings.load_sync(session)
+    return session.execute(
+        select(MLSettings).where(MLSettings.id == 1)
+    ).scalar_one()
 
 
 def _normalize_params(session: Session, params: dict[str, Any] | None) -> dict[str, Any]:
@@ -164,7 +124,7 @@ 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)), AUTO_APPLY_THRESHOLD_MIN), AUTO_APPLY_THRESHOLD_MAX)
+        precision_target = min(max(float(params.get("precision_target", s.head_auto_apply_precision)), 0.5), 0.999)
     except (TypeError, ValueError):
         precision_target = s.head_auto_apply_precision
     return {
@@ -576,7 +536,7 @@ async def score_image(
     norms[norms == 0] = 1.0
     Xn = X / norms
     Z = Xn @ heads["W"].T + heads["b"]                  # (B, H)
-    probs_bag = _sigmoid(Z, np)                         # (B, H)
+    probs_bag = 1.0 / (1.0 + np.exp(-Z))                # (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).
@@ -654,7 +614,9 @@ async def ground_applied_tag(
 
 
 async def _settings_async(session: AsyncSession) -> MLSettings:
-    return await MLSettings.load(session)
+    return (
+        await session.execute(select(MLSettings).where(MLSettings.id == 1))
+    ).scalar_one()
 
 
 # --- Earned auto-apply (sync, ml worker) ---------------------------------
@@ -725,6 +687,7 @@ 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(
@@ -741,7 +704,18 @@ def auto_apply_sweep(
     names = [r.name for r in rows]
 
     # Skip images that already carry, or have rejected, each tag.
-    skip = _applied_or_rejected(session, tag_ids)
+    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)
 
     applied = [0] * len(rows)
     scanned = 0
@@ -755,7 +729,7 @@ def auto_apply_sweep(
         if not cids:
             continue
         Xn = _l2norm(np.vstack([emb[i] for i in cids]).astype(np.float32), np)
-        probs = _sigmoid(Xn @ W.T + b, np)              # (N, H)
+        probs = 1.0 / (1.0 + np.exp(-(Xn @ W.T + b)))   # (N, H)
         scanned += len(cids)
         for h in range(len(rows)):
             tid = tag_ids[h]
@@ -866,6 +840,7 @@ def system_tag_auto_apply_sweep(
     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)
@@ -894,7 +869,18 @@ def system_tag_auto_apply_sweep(
     valued = _valued_image_ids(session)
 
     # Skip images that already carry, or have rejected, each presentation tag.
-    skip = _applied_or_rejected(session, pres_tag_ids)
+    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)
 
     applied = [0] * len(pres)
     n_flagged = 0
@@ -909,9 +895,11 @@ def system_tag_auto_apply_sweep(
         if not cids:
             continue
         Xn = _l2norm(np.vstack([emb[i] for i in cids]).astype(np.float32), np)
-        probs = _sigmoid(Xn @ Wp.T + bp, np)                  # (N, P)
+        probs = 1.0 / (1.0 + np.exp(-(Xn @ Wp.T + bp)))       # (N, P)
         if Wc is not None:
-            max_c, arg_c = _conflict_scores(Xn, Wc, bc, np)   # (N,), (N,)
+            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)
         scanned += len(cids)
         for p in range(len(pres)):
             tid = pres_tag_ids[p]
@@ -936,12 +924,15 @@ def system_tag_auto_apply_sweep(
                 if Wc is not None and float(max_c[idx]) >= conflict_thr:
                     n_flagged += 1
                     if not dry_run:
-                        _insert_presentation_review(
+                        session.execute(
-                            session,
+                            pg_insert(PresentationReview)
-                            image_record_id=iid, tag_id=tid,
+                            .values(
-                            conflict_tag_id=conf_tag_ids[int(arg_c[idx])],
+                                image_record_id=iid, tag_id=tid,
-                            conflict_score=float(max_c[idx]),
+                                conflict_tag_id=conf_tag_ids[int(arg_c[idx])],
-                            mode=mode,
+                                conflict_score=float(max_c[idx]),
+                                mode=mode,
+                            )
+                            .on_conflict_do_nothing()
                         )
         if not dry_run:
             session.commit()
@@ -965,6 +956,7 @@ def soft_wip_conflict_audit(session: Session, dry_run: bool = False) -> dict:
     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 sqlalchemy.dialects.postgresql import insert as pg_insert
 
     from ..wip_title import WIP_TITLE_SOFT_SOURCE, resolve_wip_tag_id
 
@@ -1001,17 +993,22 @@ def soft_wip_conflict_audit(session: Session, dry_run: bool = False) -> dict:
             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)
+        cprobs = 1.0 / (1.0 + np.exp(-(Xn @ Wc.T + bc)))
+        max_c = cprobs.max(axis=1)
+        arg_c = cprobs.argmax(axis=1)
         for k in range(len(cids)):
             if float(max_c[k]) >= conflict_thr:
                 n_flagged += 1
                 if not dry_run:
-                    _insert_presentation_review(
+                    session.execute(
-                        session,
+                        pg_insert(PresentationReview)
-                        image_record_id=cids[k], tag_id=wip_id,
+                        .values(
-                        conflict_tag_id=conf_tag_ids[int(arg_c[k])],
+                            image_record_id=cids[k], tag_id=wip_id,
-                        conflict_score=float(max_c[k]),
+                            conflict_tag_id=conf_tag_ids[int(arg_c[k])],
-                        mode="process",
+                            conflict_score=float(max_c[k]),
+                            mode="process",
+                        )
+                        .on_conflict_do_nothing()
                     )
         if not dry_run:
             session.commit()
@@ -1065,7 +1062,7 @@ 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 = _sigmoid(Xn @ w + float(bias), np)
+        probs = 1.0 / (1.0 + np.exp(-(Xn @ w + float(bias))))
         below = [cids[k] for k in np.where(probs < float(thr))[0]]
         for iid in below:
             session.execute(

backend/app/services/ml/training_data.py

@@ -94,24 +94,6 @@ 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

@@ -91,46 +91,48 @@ def _sync_lookup(vanity: str, cookies_path: str | None) -> str | None:
     )
 
 
-def _campaigns_api_first(vanity: str, cookies_path: str | None) -> dict | None:
+def _lookup_via_api(vanity: str, cookies_path: str | None) -> str | 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={"filter[vanity]": vanity, "fields[campaign]": "name"},
+            params=params,
-            headers={"User-Agent": _USER_AGENT, "Accept": "application/vnd.api+json"},
+            headers=headers,
             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
-    campaign_id = first.get("id")
+    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
     if not isinstance(campaign_id, str) or not campaign_id:
         return None
     log.info("Resolved Patreon vanity=%s → campaign_id=%s", vanity, campaign_id)
@@ -142,10 +144,24 @@ 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."""
-    first = _campaigns_api_first(vanity, cookies_path)
+    jar = _load_cookie_jar(cookies_path)
-    if first is None:
+    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)
         return None
-    name = (first.get("attributes") or {}).get("name")
+    if not isinstance(data, list) or not data or not isinstance(data[0], dict):
+        return None
+    name = (data[0].get("attributes") or {}).get("name")
     return name.strip() if isinstance(name, str) and name.strip() else None
 
 

backend/app/tasks/maintenance.py

@@ -776,62 +776,89 @@ 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."""
-    return _recover_stalled_runs(
+    SessionLocal = _sync_session_factory()
-        HeadTrainingRun,
+    now = datetime.now(UTC)
-        stall_minutes=HEAD_TRAINING_STALL_THRESHOLD_MINUTES,
+    cutoff = now - timedelta(minutes=HEAD_TRAINING_STALL_THRESHOLD_MINUTES)
-        keep_runs=HEAD_TRAINING_KEEP_RUNS,
+    with SessionLocal() as session:
-        label="recover_stalled_head_training_runs",
+        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
 
 
 @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."""
-    return _recover_stalled_runs(
+    SessionLocal = _sync_session_factory()
-        HeadAutoApplyRun,
+    now = datetime.now(UTC)
-        stall_minutes=HEAD_AUTO_APPLY_STALL_THRESHOLD_MINUTES,
+    cutoff = now - timedelta(minutes=HEAD_AUTO_APPLY_STALL_THRESHOLD_MINUTES)
-        keep_runs=HEAD_AUTO_APPLY_KEEP_RUNS,
+    with SessionLocal() as session:
-        label="recover_stalled_head_auto_apply_runs",
+        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
 
 
 # Keep ~6 months of daily head-metric snapshots (enough to see tuning trends).

backend/app/tasks/ml.py

@@ -105,7 +105,9 @@ 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 = MLSettings.load_sync(session)
+            settings = session.execute(
+                select(MLSettings).where(MLSettings.id == 1)
+            ).scalar_one()
 
             src = Path(record.path)
             is_vid = _is_video(src)
@@ -486,10 +488,15 @@ 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
+    from ..models import ImageRegion, MLSettings, Tag, TagKind, TagSuggestionRejection
     from ..models.tag import image_tag
-    from ..services.ml.ccip import _FIGURE_KINDS
+
-    from ..services.ml.training_data import _applied_or_rejected, _l2norm
+    fig = ("face", "figure")
+
+    def _l2(m):
+        n = np.linalg.norm(m, axis=1, keepdims=True)
+        n[n == 0] = 1.0
+        return m / n
 
     SessionLocal = _sync_session_factory()
     with SessionLocal() as session:
@@ -514,7 +521,7 @@ def scheduled_ccip_auto_apply() -> str:
             )
             .join(Tag, Tag.id == image_tag.c.tag_id)
             .where(Tag.kind == TagKind.character)
-            .where(ImageRegion.kind.in_(_FIGURE_KINDS))
+            .where(ImageRegion.kind.in_(fig))
             .where(ImageRegion.ccip_embedding.is_not(None))
             .where(ImageRegion.image_record_id.in_(single))
         ).all()
@@ -525,16 +532,29 @@ def scheduled_ccip_auto_apply() -> str:
         for tid, vec in ref_rows:
             by_char.setdefault(tid, []).append(vec)
         ref_tags = list(by_char)
-        mats = [_l2norm(np.asarray(by_char[t], dtype=np.float32), np) for t in ref_tags]
+        mats = [_l2(np.asarray(by_char[t], dtype=np.float32)) for t in ref_tags]
         allref = np.vstack(mats)                                  # (total, 768)
         seg = np.cumsum([0] + [len(m) for m in mats])[:-1]        # per-char start
 
         # Per character: images that already carry OR rejected the tag — skip.
-        skip = _applied_or_rejected(session, ref_tags)
+        skip = {t: set() for t in ref_tags}
+        for t in ref_tags:
+            for (iid,) in session.execute(
+                sa_select(image_tag.c.image_record_id).where(
+                    image_tag.c.tag_id == t
+                )
+            ):
+                skip[t].add(iid)
+            for (iid,) in session.execute(
+                sa_select(TagSuggestionRejection.image_record_id).where(
+                    TagSuggestionRejection.tag_id == t
+                )
+            ):
+                skip[t].add(iid)
 
         img_ids = list(session.execute(
             sa_select(ImageRegion.image_record_id)
-            .where(ImageRegion.kind.in_(_FIGURE_KINDS), ImageRegion.ccip_embedding.is_not(None))
+            .where(ImageRegion.kind.in_(fig), ImageRegion.ccip_embedding.is_not(None))
             .distinct()
         ).scalars())
 
@@ -546,7 +566,7 @@ 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_(_FIGURE_KINDS),
+                    ImageRegion.kind.in_(fig),
                     ImageRegion.ccip_embedding.is_not(None),
                 )
             ).all()
@@ -554,7 +574,7 @@ 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 = _l2norm(np.asarray(vecs, dtype=np.float32), np)  # (nq, 768)
+                q = _l2(np.asarray(vecs, dtype=np.float32))      # (nq, 768)
                 colmax = (q @ allref.T).max(axis=0)              # (total,)
                 charmax = np.maximum.reduceat(colmax, seg)       # (n_chars,)
                 for ci in np.where(charmax >= thr)[0]:

extension/background/background.js

@@ -31,69 +31,6 @@ 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; strip the /api suffix off baseUrl
-  // (same transform as OPEN_ARTIST_PAGE).
-  const base = (api.baseUrl || '').replace(/\/+$/, '').replace(/\/api$/, '');
-  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(
@@ -361,9 +298,6 @@ browser.runtime.onMessage.addListener(async (msg) => {
       }
     }
 
-    case 'CHECK_UPDATE':
-      return await checkForUpdateInfo();
-
     default:
       return { error: `Unknown message type: ${msg.type}` };
   }

extension/lib/api.js

@@ -89,12 +89,6 @@ 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');
-  }
 
   // Connection test = the cheapest read with auth.
   testConnection() {

extension/manifest.json

@@ -1,7 +1,7 @@
 {
   "manifest_version": 3,
   "name": "FabledCurator",
-  "version": "1.0.9",
+  "version": "1.0.8",
   "description": "Export cookies from supported platforms to FabledCurator and add creators as sources in one click.",
 
   "browser_specific_settings": {
@@ -22,8 +22,7 @@
     "tabs",
     "activeTab",
     "webRequest",
-    "webRequestBlocking",
+    "webRequestBlocking"
-    "alarms"
   ],
 
   "host_permissions": [

extension/package.json

@@ -1,6 +1,6 @@
 {
   "name": "fabledcurator-extension",
-  "version": "1.0.9",
+  "version": "1.0.8",
   "private": true,
   "description": "Firefox extension for FabledCurator",
   "scripts": {

extension/popup/popup.css

@@ -72,17 +72,6 @@ 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

@@ -20,11 +20,6 @@
   </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

@@ -14,7 +14,6 @@ async function init() {
     setupEventListeners();
     showPlatformsLoading();
     testConnectionIfNeeded();
-    checkForUpdate();
     loadPlatformStatus().catch(e => showError(`Failed to load platforms: ${e.message}`));
   } catch (e) {
     showSetupRequired();
@@ -64,26 +63,6 @@ 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');

tests/test_ml_dry_helpers.py

@@ -1,59 +0,0 @@
-"""Shared ML helpers extracted in the DRY pass (milestone #161). These pin the
-single sources the auto-apply sweeps now trust, so a future edit can't silently
-drift them: `_applied_or_rejected` is the skip-set used by auto_apply_sweep,
-system_tag_auto_apply_sweep (heads.py) and scheduled_ccip_auto_apply (tasks/ml.py);
-`_sigmoid` is the head score→prob transform used at every scoring site."""
-import pytest
-
-from backend.app.models import ImageRecord, Tag, TagKind, TagSuggestionRejection
-from backend.app.models.tag import image_tag
-from backend.app.services.ml.training_data import _applied_or_rejected
-
-
-def test_sigmoid_matches_naive_form():
-    import numpy as np
-
-    from backend.app.services.ml.heads import _sigmoid
-
-    z = np.array([-3.0, -0.5, 0.0, 1.5, 12.0], dtype=np.float32)
-    assert np.allclose(_sigmoid(z, np), 1.0 / (1.0 + np.exp(-z)))
-    assert float(_sigmoid(np.array([0.0]), np)[0]) == pytest.approx(0.5)
-
-
-@pytest.mark.integration
-def test_applied_or_rejected_unions_applied_any_source_and_rejected(db_sync):
-    a = Tag(name="dry-helper-a", kind=TagKind.general)
-    b = Tag(name="dry-helper-b", kind=TagKind.general)
-    db_sync.add_all([a, b])
-    db_sync.flush()
-
-    imgs = []
-    for i in range(5):
-        img = ImageRecord(
-            path=f"/images/dryhelp{i}.jpg", sha256=f"{i:064d}", size_bytes=1,
-            mime="image/jpeg", width=1, height=1, origin="imported_filesystem",
-            integrity_status="unknown", siglip_embedding=[0.0] * 1152,
-        )
-        db_sync.add(img)
-        imgs.append(img)
-    db_sync.flush()
-
-    # tag a: applied manually (img0), applied by an AUTO source (img1), rejected (img2).
-    db_sync.execute(image_tag.insert().values(
-        image_record_id=imgs[0].id, tag_id=a.id, source="manual"))
-    db_sync.execute(image_tag.insert().values(
-        image_record_id=imgs[1].id, tag_id=a.id, source="head_auto"))
-    db_sync.add(TagSuggestionRejection(image_record_id=imgs[2].id, tag_id=a.id))
-    # tag b: applied to img3 only.
-    db_sync.execute(image_tag.insert().values(
-        image_record_id=imgs[3].id, tag_id=b.id, source="manual"))
-    db_sync.flush()
-
-    skip = _applied_or_rejected(db_sync, [a.id, b.id])
-
-    # Applied-under-ANY-source (manual + head_auto) ∪ rejected, kept per-tag; the
-    # untouched image (img4) appears under neither tag.
-    assert skip[a.id] == {imgs[0].id, imgs[1].id, imgs[2].id}
-    assert skip[b.id] == {imgs[3].id}
-    assert imgs[4].id not in skip[a.id]
-    assert imgs[4].id not in skip[b.id]

tests/test_recover_stalled_head_runs.py

@@ -1,63 +0,0 @@
-"""recover_stalled_head_training_runs + recover_stalled_head_auto_apply_runs share
-one helper (_recover_stalled_runs, DRY pass #161). These pin BOTH wrappers so the
-shared source stays correct: a 'running' row with no progress past the stall
-threshold flips to 'error'; a fresh 'running' row is left alone."""
-from datetime import UTC, datetime, timedelta
-
-import pytest
-from sqlalchemy import select
-
-from backend.app.models import HeadAutoApplyRun, HeadTrainingRun
-
-pytestmark = pytest.mark.integration
-
-
-def test_recover_stalled_head_training_runs_flips_stalled_keeps_fresh(db_sync):
-    from backend.app.tasks.maintenance import recover_stalled_head_training_runs
-
-    stale = HeadTrainingRun(
-        params={}, status="running",
-        last_progress_at=datetime.now(UTC) - timedelta(days=1),
-    )
-    fresh = HeadTrainingRun(
-        params={}, status="running", last_progress_at=datetime.now(UTC),
-    )
-    db_sync.add_all([stale, fresh])
-    db_sync.commit()
-    stale_id, fresh_id = stale.id, fresh.id
-
-    assert recover_stalled_head_training_runs.apply().get() == 1
-
-    db_sync.expire_all()
-    assert db_sync.execute(
-        select(HeadTrainingRun.status).where(HeadTrainingRun.id == stale_id)
-    ).scalar_one() == "error"
-    assert db_sync.execute(
-        select(HeadTrainingRun.status).where(HeadTrainingRun.id == fresh_id)
-    ).scalar_one() == "running"
-
-
-def test_recover_stalled_head_auto_apply_runs_flips_stalled_keeps_fresh(db_sync):
-    from backend.app.tasks.maintenance import recover_stalled_head_auto_apply_runs
-
-    stale = HeadAutoApplyRun(
-        dry_run=False, params={}, status="running",
-        last_progress_at=datetime.now(UTC) - timedelta(days=1),
-    )
-    fresh = HeadAutoApplyRun(
-        dry_run=False, params={}, status="running",
-        last_progress_at=datetime.now(UTC),
-    )
-    db_sync.add_all([stale, fresh])
-    db_sync.commit()
-    stale_id, fresh_id = stale.id, fresh.id
-
-    assert recover_stalled_head_auto_apply_runs.apply().get() == 1
-
-    db_sync.expire_all()
-    assert db_sync.execute(
-        select(HeadAutoApplyRun.status).where(HeadAutoApplyRun.id == stale_id)
-    ).scalar_one() == "error"
-    assert db_sync.execute(
-        select(HeadAutoApplyRun.status).where(HeadAutoApplyRun.id == fresh_id)
-    ).scalar_one() == "running"