test: the patreon ingester tests run phase 3's seen-marking before counting post keys (#4436 )

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01LVjrnpQjRgHdvq95rASoiR
fix: a post record is marked seen only after it is upserted, and an hourly sweep dates the posts killed walks left undated (#4436 )
2026-09-25 11:41:16 -04:00 · 2026-09-25 11:36:17 -04:00 · 2026-09-25 10:56:08 -04:00 · 2026-09-25 10:36:32 -04:00 · 2026-09-25 10:32:41 -04:00 · 2026-09-25 10:29:05 -04:00
42 changed files with 1313 additions and 386 deletions
@@ -142,6 +142,16 @@ concurrency:
 # Deriving it per job invites the two halves to disagree: sign-extension would
 # derive dev's extension version while build-web bundled main's, and the
 # release download would 404 on a version that exists perfectly well.
+#
+# On every other trigger it is the COMMIT that fired (`github.sha`), never the
+# branch name. A branch is re-resolved by each job's checkout when that job
+# starts, so a push landing mid-run moved the later jobs onto the new tip: run
+# 7499 signed 423275a's extension, then build-web checked out 83e1382 (pushed
+# while 7499 ran), derived a version nobody had signed, and 404'd on the
+# download (#4427). The guard failed closed that time; a job without one would
+# have published a commit the run's own lanes never tested — the lanes check
+# out `github.sha` by default, so pinning here makes the publish build exactly
+# what they passed.
 # IS THIS A BASE REFRESH? Asked in five places and previously spelled five
 # ways — `github.event_name == 'schedule'` in an `if:`, `$GITHUB_EVENT_NAME` in
 # one shell, an `EVENT:` env passed into another, and a bare expression on
@@ -178,7 +188,16 @@ concurrency:
 # where a step-level `if:` needs the answer before any shell runs.
 env:
  IS_REFRESH: ${{ (github.event_name == 'schedule' || format('{0}', github.event.inputs.refresh) == 'true') && 'true' || 'false' }}
-  BUILD_REF: ${{ (github.event_name == 'schedule' || format('{0}', github.event.inputs.refresh) == 'true') && 'main' || github.ref }}
+  BUILD_REF: ${{ (github.event_name == 'schedule' || format('{0}', github.event.inputs.refresh) == 'true') && 'main' || github.sha }}
+# What the six LANES check out. Empty — the checkout default, the triggering
+# commit (or a PR's merge ref) — on every trigger but the refresh, where it is
+# `main`: the refresh publishes main, so the gate has to test main (#4430). It
+# is not BUILD_REF itself because a pull_request run's `github.sha` is a merge
+# commit the default checkout reaches through its ref, not by sha. Each job
+# still resolves `main` when it starts, so a merge to main during the ~5 min of
+# a Sunday-06:00 refresh could put the lanes and the build one commit apart;
+# the build jobs' own guards assert the branch, not the commit.
+  LANE_REF: ${{ (github.event_name == 'schedule' || format('{0}', github.event.inputs.refresh) == 'true') && 'main' || '' }}

 # Requires repo secret RELEASE_TOKEN — a Forgejo PAT with scopes:
 #   - write:package, read:package  (for docker push to git.fabledsword.com)
@@ -219,6 +238,8 @@ jobs:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    steps:
      - uses: actions/checkout@v4
+        with:
+          ref: ${{ env.LANE_REF }}
      - name: Ruff lint
        # agent/ included so the GPU-agent is linted before its image is built
        # (build.yml only `docker build`s it — this is where it gets checked).
@@ -265,6 +286,7 @@ jobs:
    steps:
      - uses: actions/checkout@v4
        with:
+          ref: ${{ env.LANE_REF }}
          # The derivation needs real history: a depth-1 clone sees one commit
          # and produces a wrong, too-low value RATHER THAN FAILING. Checking
          # that here is half the point of the lane.
@@ -320,6 +342,7 @@ jobs:
    steps:
      - uses: actions/checkout@v4
        with:
+          ref: ${{ env.LANE_REF }}
          # Full history for tests/test_artifact_identity.py, which derives
          # each artifact's revision to check the identity scheme. On a
          # depth-1 clone that derivation either fails or returns the tip sha
@@ -366,6 +389,8 @@ jobs:
        working-directory: frontend
    steps:
      - uses: actions/checkout@v4
+        with:
+          ref: ${{ env.LANE_REF }}
      # No package-lock.json is tracked yet (we don't run npm locally per
      # feedback-no-local-runs). Using `npm install` instead of `npm ci`.
      # If we want strict lockfile-based reproducibility later, commit a
@@ -395,6 +420,8 @@ jobs:
      image: node:24-bookworm-slim
    steps:
      - uses: actions/checkout@v4
+        with:
+          ref: ${{ env.LANE_REF }}
      # Not --no-save: vitest and web-ext are both real devDependencies now,
      # and the suite needs vitest resolvable from node_modules.
      - name: Install dev dependencies
@@ -497,6 +524,8 @@ jobs:
          --health-retries 10
    steps:
      - uses: actions/checkout@v4
+        with:
+          ref: ${{ env.LANE_REF }}
      - name: Integration suite (resolve service IPs, migrate, test)
        run: |
          set -eux
@@ -605,8 +634,8 @@ jobs:
      - uses: actions/checkout@v4
        with:
          # Not the triggering ref — see the `env:` block at the top. On a
-          # scheduled refresh this is `main`; on everything else it is the ref
-          # that fired, so this is a no-op on every ordinary path.
+          # scheduled refresh this is `main`; on everything else it is the
+          # commit that fired, the same one the lanes above tested.
          ref: ${{ env.BUILD_REF }}
          # Full history is load-bearing, not a convenience: the version this
          # job signs is derived from the commit TIME of the newest packaged
@@ -945,8 +974,8 @@ jobs:
      - uses: actions/checkout@v4
        with:
          # Not the triggering ref — see the `env:` block at the top. On a
-          # scheduled refresh this is `main`; on everything else it is the ref
-          # that fired, so this is a no-op on every ordinary path.
+          # scheduled refresh this is `main`; on everything else it is the
+          # commit that fired, the same one the lanes above tested.
          ref: ${{ env.BUILD_REF }}
          # Full history: this job RE-DERIVES the extension version rather than
          # being handed it, and a depth-1 clone derives a wrong, too-low value
@@ -2174,8 +2203,8 @@ jobs:
      - uses: actions/checkout@v4
        with:
          # Not the triggering ref — see the `env:` block at the top. On a
-          # scheduled refresh this is `main`; on everything else it is the ref
-          # that fired, so this is a no-op on every ordinary path.
+          # scheduled refresh this is `main`; on everything else it is the
+          # commit that fired, the same one the lanes above tested.
          ref: ${{ env.BUILD_REF }}
          # Full history: this job derives its artifact's version from the
          # commit its shipped files last changed in (milestone 313). A
@@ -22,7 +22,8 @@ through afterwards.
 - **ML tagging.** Runs image models in-container to suggest tags, group
  characters, find near-duplicates and power similarity search. Suggestions are
  reviewable — it proposes, you confirm, and it learns which proposals you keep
-  rejecting.
+  rejecting. It ships switched off: turn it on under Settings → System when
+  you want it, and it fetches its model weights then.
 - **Deduplication and provenance.** Everything that arrives is hashed and
  deduplicated by content, metadata sidecars are read wherever the source
  writes them, and every file keeps a record of where it came from.
@@ -119,9 +120,12 @@ needs every credential entered again by hand.

 A few other things are worth knowing about the first few minutes:

- **The ML worker downloads its model weights on first boot**, several GB from
-  HuggingFace into `./models`. Until that finishes, tagging is queued rather
-  than broken. It is idempotent — a restart resumes rather than refetches.
+- **ML tagging starts switched off, and nothing is downloaded at boot.** Give
+  the ML lane a slot under **Settings → System** and it fetches its model
+  weights then — several GB from HuggingFace into `./models`, shown as a job
+  under **Settings → Activity** that you can watch and retry. Until it
+  finishes, tagging is queued rather than broken, and the fetch only takes
+  what is missing, so turning the lane off and on again does not refetch.
 - **The gallery starts empty**, and that is the expected state. Add a creator
  under **Subscriptions** and it fills as posts come down.
 - **If you already have a library on disk**, there is no screen that imports
@@ -0,0 +1,78 @@
+"""Retire the sketch/doodle WIP title tier — its tags, its review flags, its toggle.
+
+Milestone 430, #4428. The soft tier (#1474) tagged `wip` on any post titled
+sketch / doodle / scribble. Measured on the operator's library it was 6,096 of
+8,876 wip tags, and its conflict audit filled the Gallery's review strip with
+2,086 cards, because most finished art scores >= 0.5 on some content head. A
+"sketch" is usually finished work, so the operator retired it (2026-09-25).
+
+Data:
+
+* A soft tag the operator stood behind is kept and relabelled `manual`: one they
+  confirmed (tag_positive_confirmation), or one whose review flag they resolved
+  while leaving the tag on (the strip's "Keep tag").
+* Every other `wip_title_soft` row is deleted.
+* Unresolved review flags whose tag is no longer on the image are deleted: the
+  question they ask no longer applies. That is the audit's cards, and any older
+  orphan the same way.
+
+Then `import_settings.wip_soft_title_tagging_enabled` is dropped. The downgrade
+restores the column only; deleted tags are not recreated.
+
+Revision ID: 0112
+Revises: 0111
+Create Date: 2026-09-25
+
+"""
+import sqlalchemy as sa
+from alembic import op
+
+revision = "0112"
+down_revision = "0111"
+branch_labels = None
+depends_on = None
+
+
+def retire_soft_wip_tags(conn) -> None:
+    """The data half, on a plain connection, so a test can run it directly."""
+    conn.execute(sa.text("""
+        UPDATE image_tag it SET source = 'manual'
+        WHERE it.source = 'wip_title_soft'
+          AND (
+            EXISTS (
+              SELECT 1 FROM tag_positive_confirmation c
+              WHERE c.image_record_id = it.image_record_id AND c.tag_id = it.tag_id
+            )
+            OR EXISTS (
+              SELECT 1 FROM presentation_review pr
+              WHERE pr.image_record_id = it.image_record_id AND pr.tag_id = it.tag_id
+                AND pr.resolved_at IS NOT NULL
+            )
+          )
+    """))
+    conn.execute(sa.text("DELETE FROM image_tag WHERE source = 'wip_title_soft'"))
+    conn.execute(sa.text("""
+        DELETE FROM presentation_review pr
+        WHERE pr.resolved_at IS NULL
+          AND NOT EXISTS (
+            SELECT 1 FROM image_tag it
+            WHERE it.image_record_id = pr.image_record_id AND it.tag_id = pr.tag_id
+          )
+    """))
+
+
+def upgrade():
+    retire_soft_wip_tags(op.get_bind())
+    op.drop_column("import_settings", "wip_soft_title_tagging_enabled")
+
+
+def downgrade():
+    op.add_column(
+        "import_settings",
+        sa.Column(
+            "wip_soft_title_tagging_enabled",
+            sa.Boolean(),
+            nullable=False,
+            server_default=sa.text("false"),
+        ),
+    )
@@ -0,0 +1,60 @@
+"""Re-date images whose post's date arrived after they were linked.
+
+#4431. The native ingesters import a post's media before its record, and the
+date travels in the record (`_post.json`). Every natively downloaded image was
+therefore linked to an undated post and kept its download time in both gallery
+date columns, while the post itself was dated correctly. The importer now
+re-dates a post's images when its record lands; this repairs the images that
+landed before that.
+
+Both columns get back the rules the importer keeps:
+
+* `effective_date` is the primary post's date (left alone when that post has
+  none, as the importer does);
+* `earliest_post_date` is the earliest dated post the image is linked to.
+
+Only rows that differ are written. The downgrade does nothing: the old values
+were download times that no one chose.
+
+Revision ID: 0113
+Revises: 0112
+Create Date: 2026-09-25
+
+"""
+import sqlalchemy as sa
+from alembic import op
+
+revision = "0113"
+down_revision = "0112"
+branch_labels = None
+depends_on = None
+
+
+def redate_images(conn) -> None:
+    """The data step, on a plain connection, so a test can run it directly."""
+    conn.execute(sa.text("""
+        UPDATE image_record ir SET effective_date = p.post_date
+        FROM post p
+        WHERE p.id = ir.primary_post_id
+          AND p.post_date IS NOT NULL
+          AND ir.effective_date IS DISTINCT FROM p.post_date
+    """))
+    conn.execute(sa.text("""
+        UPDATE image_record ir SET earliest_post_date = m.earliest
+        FROM (
+          SELECT ip.image_record_id, MIN(p.post_date) AS earliest
+          FROM image_provenance ip JOIN post p ON p.id = ip.post_id
+          WHERE p.post_date IS NOT NULL
+          GROUP BY ip.image_record_id
+        ) m
+        WHERE m.image_record_id = ir.id
+          AND ir.earliest_post_date IS DISTINCT FROM m.earliest
+    """))
+
+
+def upgrade():
+    redate_images(op.get_bind())
+
+
+def downgrade():
+    pass
@@ -0,0 +1,79 @@
+"""Fold the undated shell posts a misfiled attachment created into the real post.
+
+#4435. A non-image file (an archive, a pdf) downloaded for one of an artist's
+Discord channels was filed under the artist's FIRST Discord source: the
+attachment path looked the source up by (artist, platform), which takes the
+lowest id. That created an undated, url-less post there holding only the
+attachment, and the message's real post record then created the dated post
+under the right source. The importer now uses the source it was downloading
+for; this repairs the pairs it left.
+
+A shell is folded only when all of this holds:
+
+* it has no date and no url, and nothing synthesized it;
+* another post of the same artist, platform and external id HAS a date;
+* no image is linked to the shell (it held an attachment and nothing else).
+
+Its attachments move to the dated post, dropping any the dated post already
+has (same sha256, which the per-post unique forbids twice), and the shell is
+deleted. A shell with no dated twin is left alone: which channel it belongs to
+is not recorded anywhere but the file name. The downgrade does nothing.
+
+Revision ID: 0114
+Revises: 0113
+Create Date: 2026-09-25
+
+"""
+import sqlalchemy as sa
+from alembic import op
+
+revision = "0114"
+down_revision = "0113"
+branch_labels = None
+depends_on = None
+
+_PAIRS = """
+    SELECT DISTINCT ON (shell.id) shell.id AS shell_id, real.id AS real_id
+    FROM post shell
+    JOIN source ss ON ss.id = shell.source_id
+    JOIN post real
+      ON real.artist_id = shell.artist_id
+     AND real.external_post_id = shell.external_post_id
+     AND real.id <> shell.id
+     AND real.post_date IS NOT NULL
+    JOIN source rs ON rs.id = real.source_id AND rs.platform = ss.platform
+    WHERE shell.post_date IS NULL
+      AND shell.post_url IS NULL
+      AND shell.synthesized_by IS NULL
+      AND NOT EXISTS (SELECT 1 FROM image_provenance ip WHERE ip.post_id = shell.id)
+    ORDER BY shell.id, real.id
+"""
+
+
+def fold_misfiled_attachment_posts(conn) -> int:
+    """The data step, on a plain connection, so a test can run it directly.
+    Returns how many shells were folded."""
+    pairs = conn.execute(sa.text(_PAIRS)).all()
+    for shell_id, real_id in pairs:
+        conn.execute(sa.text("""
+            DELETE FROM post_attachment pa
+            WHERE pa.post_id = :shell
+              AND EXISTS (
+                SELECT 1 FROM post_attachment keep
+                WHERE keep.post_id = :real AND keep.sha256 = pa.sha256
+              )
+        """), {"shell": shell_id, "real": real_id})
+        conn.execute(
+            sa.text("UPDATE post_attachment SET post_id = :real WHERE post_id = :shell"),
+            {"shell": shell_id, "real": real_id},
+        )
+        conn.execute(sa.text("DELETE FROM post WHERE id = :shell"), {"shell": shell_id})
+    return len(pairs)
+
+
+def upgrade() -> None:
+    fold_misfiled_attachment_posts(op.get_bind())
+
+
+def downgrade() -> None:
+    pass
@@ -57,7 +57,6 @@ _EDITABLE_FIELDS = (
    "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.
@@ -196,12 +195,6 @@ async def update_import_settings():
        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)
@@ -152,6 +152,8 @@ async def list_runs():
      queue=<name>     filter to one queue
      status=<status>  filter to one status (running/ok/error/timeout/retry)
      task=<substr>    case-insensitive substring match on task_name
+      celery_task_id=<id>  exactly one run — how a page follows a job it
+                           started without having to know its lane
      limit=<int>      default 50, max 200
      before_id=<int>  cursor for keyset pagination

@@ -167,6 +169,7 @@ async def list_runs():
    queue = request.args.get("queue")
    status = request.args.get("status")
    task = request.args.get("task")
+    celery_task_id = request.args.get("celery_task_id")
    before_id_raw = request.args.get("before_id")
    before_id = int(before_id_raw) if before_id_raw else None

@@ -176,6 +179,8 @@ async def list_runs():
            stmt = stmt.where(TaskRun.queue == queue)
        if status:
            stmt = stmt.where(TaskRun.status == status)
+        if celery_task_id:
+            stmt = stmt.where(TaskRun.celery_task_id == celery_task_id)
        if task:
            # Task names contain literal underscores (download_source,
            # vacuum_analyze) — escape LIKE wildcards so a search for
@@ -69,6 +69,8 @@ def make_celery() -> Celery:
            # up behind it (2026-09-24: 7 waiting, "all workers busy for 18
            # minutes"). An exact name wins over the glob above.
            "backend.app.tasks.maintenance.backfill_phash": {"queue": "maintenance_long"},
+            # Walks a folder tree per artist with undated posts (#4436).
+            "backend.app.tasks.maintenance.date_posts_from_records": {"queue": "maintenance_long"},
            "backend.app.tasks.backup.*": {"queue": "maintenance_long"},
            "backend.app.tasks.admin.*": {"queue": "maintenance_long"},
            "backend.app.tasks.library_audit.*": {"queue": "maintenance_long"},
@@ -156,6 +158,11 @@ def make_celery() -> Celery:
                "schedule": 86400.0,  # daily — sweep .part/.partial left by a
                # download/import killed mid-write (graceful-shutdown fallout)
            },
+            "date-posts-from-records-hourly": {
+                "task": "backend.app.tasks.maintenance.date_posts_from_records",
+                "schedule": 3600.0,  # an empty query once every native post is
+                # dated; otherwise upserts the _post.json a killed walk left (#4436)
+            },
            "backfill-phash-daily": {
                "task": "backend.app.tasks.maintenance.backfill_phash",
                "schedule": 86400.0,  # daily — NULL-only, so a no-op once the
@@ -223,11 +230,6 @@ def make_celery() -> Celery:
                "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
@@ -18,11 +18,18 @@ dark for that interval. Monitoring NEVER breaks the thing it's
 monitoring.
 """

+import functools
 import logging
 from datetime import UTC, datetime

 from celery.exceptions import SoftTimeLimitExceeded
-from celery.signals import task_failure, task_postrun, task_prerun, task_retry
+from celery.signals import (
+    task_failure,
+    task_postrun,
+    task_prerun,
+    task_retry,
+    worker_ready,
+)

 from .models import TaskRun
 from .tasks._sync_engine import sync_session_factory
@@ -53,42 +60,29 @@ _INT32_MIN = -2_147_483_648


 def _queue_for(task) -> str:
-    """Reverse the task→queue routing from celery_app.task_routes.
-    Keep in sync if task_routes is reordered.
+    """The queue Celery routes this task to — asked of the router itself.

-    Audit 2026-06-02: backup/admin/library_audit prefixes were
-    missing here even though task_routes sent all three to
-    'maintenance'. The TaskRun.queue column then lied for those
-    rows (claimed 'default') so per-queue dashboard filters and
-    per-queue threshold overrides silently missed them.
+    This was a hand-kept copy of `celery_app.task_routes`, and it drifted
+    twice (the 2026-06-02 audit, then #4432). Long-lane jobs were recorded as
+    `maintenance`, and translation and gpu_queue runs as `default`, where the
+    5-minute stall sweep failed healthy 35-minute translation runs. The router
+    answers from the same table the broker uses, so the two cannot disagree.
    """
    name = getattr(task, "name", "") or ""
-    if name.startswith("backend.app.tasks.import_file."):
-        return "import"
-    if name.startswith("backend.app.tasks.ml."):
-        return "ml"
-    if name.startswith("backend.app.tasks.thumbnail."):
-        return "thumbnail"
-    if name.startswith((
-        "backend.app.tasks.download.",
-        # External file-host fetches share the download lane (celery_app
-        # routes external.* → download). Mirror it here or TaskRun.queue
-        # lies 'default' for them, so per-queue dashboard filters and the
-        # per-queue threshold override miss them — the same gap the
-        # 2026-06-02 audit fixed for backup/admin/library_audit.
-        "backend.app.tasks.external.",
-    )):
-        return "download"
-    if name.startswith("backend.app.tasks.scan."):
-        return "scan"
-    if name.startswith((
-        "backend.app.tasks.maintenance.",
-        "backend.app.tasks.backup.",
-        "backend.app.tasks.admin.",
-        "backend.app.tasks.library_audit.",
-    )):
-        return "maintenance"
-    return "default"
+    app = getattr(task, "app", None)
+    if app is None:
+        from .celery_app import celery as app
+    return _routed_queue(app, name)
+
+
+@functools.lru_cache(maxsize=1024)
+def _routed_queue(app, name: str) -> str:
+    try:
+        queue = app.amqp.router.route({}, name).get("queue")
+    except Exception:  # noqa: BLE001 — monitoring never breaks the task
+        log.warning("task_run: could not resolve the queue for %s", name)
+        return "default"
+    return getattr(queue, "name", None) or (queue if isinstance(queue, str) else "default")


 def _target_id_from_args(args) -> int | None:
@@ -225,3 +219,43 @@ def _on_retry(sender=None, request=None, reason=None, einfo=None, **_):
        error_message=str(reason) if reason else None,
        retry_count=getattr(request, "retries", 0),
    )
+
+
+def _consumed_queues(consumer) -> set[str]:
+    """The queue names this worker process consumes (its `-Q`), or empty when
+    they can't be read — which makes the boot hook below a no-op, not a guess."""
+    try:
+        return {q.name for q in consumer.task_consumer.queues}
+    except Exception:  # noqa: BLE001 — shape varies across celery versions
+        return set()
+
+
+@worker_ready.connect
+def _on_worker_ready(sender=None, **_):
+    """The download lane clears what its previous process left behind (#4433).
+
+    A restart SIGKILLs any walk that outlives the stop grace, so its event is
+    never finalized and its platform lock is never released. Both used to wait
+    out timers — a 30-min stall sweep that then blamed the source, and a 27-min
+    lock TTL that stalled every other source on the platform. Only the process
+    consuming `download` does this; the other lanes booting beside it must not.
+    Best-effort: a failure here is logged and the worker still starts.
+    """
+    if "download" not in _consumed_queues(sender):
+        return
+    booted_at = datetime.now(UTC)
+    try:
+        from .services.download_recovery import interrupt_orphaned_download_events
+        from .services.platform_lock import release_all_platform_locks
+
+        with sync_session_factory()() as session:
+            closed = interrupt_orphaned_download_events(session, booted_at=booted_at)
+            session.commit()
+        released = release_all_platform_locks()
+        if closed or released:
+            log.info(
+                "download lane boot: closed %d orphaned download event(s) as "
+                "interrupted, released %d platform lock(s)", closed, released,
+            )
+    except Exception:  # noqa: BLE001 — never block the worker from starting
+        log.exception("download lane boot recovery failed")
@@ -238,13 +238,6 @@ class ImportSettings(Base):
    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:
@@ -0,0 +1,57 @@
+"""Closing the download runs a worker restart orphaned (#4433).
+
+Its own module, importing nothing but the model, because its caller is the
+worker boot hook in `celery_signals` — which every download task imports via
+`celery_app`. Living in `tasks.maintenance` put the whole maintenance import
+graph, the membership roster included, on the fetch path, which
+`test_gated_reason` forbids.
+"""
+from __future__ import annotations
+
+from datetime import UTC, datetime
+
+from sqlalchemy import literal, update
+from sqlalchemy.dialects.postgresql import JSONB
+
+from ..models import DownloadEvent
+
+DOWNLOAD_INTERRUPTED_MESSAGE = (
+    "interrupted by a worker restart — the next check picks it up where it left off"
+)
+
+
+def interrupt_orphaned_download_events(session, *, booted_at: datetime) -> int:
+    """Close the download events a restart orphaned, without blaming the source.
+
+    Called when the download lane comes up (#4433). Anything still
+    pending/running from before this boot belongs to the previous process:
+    a walk that outlived the 90s stop grace was SIGKILLed, and a queued or
+    serialize-deferred task is held unacked until Redis redelivers it about an
+    hour later. Left alone, the 30-min stall sweep would error each one and
+    bump `consecutive_failures`, backing the source off as if the platform had
+    failed.
+
+    Instead they end as `skipped` (terminal, not a failure) and the source is
+    not touched: `last_checked_at` keeps its old value, so the next tick finds
+    it due and the walk resumes from its checkpoint. A redelivered message
+    that arrives later finds no pending event and opens a fresh one.
+
+    An event promoted to running after the boot has `started_at` reset to its
+    real start (download_service), so it is never caught here. Does NOT commit.
+    """
+    now = datetime.now(UTC)
+    result = session.execute(
+        update(DownloadEvent)
+        .where(DownloadEvent.status.in_(["pending", "running"]))
+        .where(DownloadEvent.started_at < booted_at)
+        .values(
+            status="skipped",
+            finished_at=now,
+            error=DOWNLOAD_INTERRUPTED_MESSAGE,
+            metadata_=DownloadEvent.metadata_.op("||")(
+                literal({"error_type": "interrupted"}, JSONB)
+            ),
+        )
+        .returning(DownloadEvent.id)
+    )
+    return len(result.all())
@@ -49,10 +49,8 @@ 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,
 )
@@ -428,11 +426,19 @@ class Importer:
        return self._upsert_artist(name) if name else None

    def _post_for_sidecar(
-        self, source: Path, artist: Artist | None
+        self, source: Path, artist: Artist | None,
+        *, source_row: Source | None = None,
    ) -> Post | None:
        """If a sidecar sits next to `source`, ensure its Source+Post
        exist (idempotent) and return the Post — so attachments can link
-        to the same Post the per-member _apply_sidecar will reuse."""
+        to the same Post the per-member _apply_sidecar will reuse.
+
+        `source_row` is the subscription being downloaded, when there is one,
+        and wins over the (artist, platform) lookup — as it does in
+        `upsert_post_record`. The lookup takes the artist's FIRST source on the
+        platform, which is right only while an artist has one: a Discord artist
+        has one per channel, and every non-image file from a later channel was
+        filed under the first as an undated second post (#4435)."""
        sc = find_sidecar(source)
        if sc is None or artist is None:
            return None
@@ -444,10 +450,13 @@ class Importer:
            log.warning("sidecar parse failed for %s: %s", sc, exc)
            return None
        sd = parse_sidecar(data)
-        platform = sd.platform or "unknown"
-        src = self._lookup_source_for_sidecar(
-            artist_id=artist.id, platform=platform,
-        )
+        if source_row is not None:
+            src = source_row
+        else:
+            platform = sd.platform or "unknown"
+            src = self._lookup_source_for_sidecar(
+                artist_id=artist.id, platform=platform,
+            )
        epid = sd.external_post_id or sc.stem
        return self._find_or_create_post(
            source_id=src.id if src else None,
@@ -545,7 +554,7 @@ class Importer:
            # nothing silently vanishes, matching extract_archive's
            # fail-soft contract.
            artist_use = artist if artist is not None else self._resolve_artist(source)
-            post = self._post_for_sidecar(source, artist_use)
+            post = self._post_for_sidecar(source, artist_use, source_row=source_row)
            self._capture_attachment(
                source, post=post, artist=artist_use, resolved=True,
            )
@@ -554,7 +563,7 @@ class Importer:
            return ImportResult(status="attached", error=reason)

        artist_use = artist if artist is not None else self._resolve_artist(source)
-        post = self._post_for_sidecar(source, artist_use)
+        post = self._post_for_sidecar(source, artist_use, source_row=source_row)
        member_ids: list[int] = []
        # Every member image touched (new + superseded + deduped), so the
        # from_attachment_id stamp below covers files that already existed in the
@@ -1040,9 +1049,7 @@ class Importer:
        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):
+        if not self.settings.wip_title_tagging_enabled:
            return
        if record.primary_post_id is None:
            return
@@ -1050,21 +1057,14 @@ class Importer:
            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:
+            if not matches_wip_title(title):
                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
+                self.session, [record.id], self._wip_tag_id, source=WIP_TITLE_SOURCE
            )
        except Exception as exc:  # noqa: BLE001 — a tag must never fail an import
            log.warning(
@@ -1141,9 +1141,51 @@ class Importer:
        if post.artist_id is None:
            post.artist_id = artist.id
        self._apply_post_fields(post, sd)
+        self._redate_post_images(post)
        self.session.commit()
        return True

+    def _redate_post_images(self, post: Post) -> None:
+        """Carry a post's date onto the images already linked to it (#4431).
+
+        The native ingesters import a post's media BEFORE its record: the
+        per-media sidecar holds only the image identity (post-first, #856), and
+        the date arrives with `_post.json`. So `_attach_provenance` links each
+        image to a post that has no date yet, and the image keeps its download
+        time. This runs when the record lands, and applies the same two rules
+        `_attach_provenance` applies: `effective_date` is the PRIMARY post's
+        date, and `earliest_post_date` is the earliest date across every post
+        the image is linked to. Only rows that differ are written."""
+        if post.post_date is None:
+            return
+        self.session.flush()
+        self.session.execute(
+            update(ImageRecord)
+            .where(ImageRecord.primary_post_id == post.id)
+            .where(ImageRecord.effective_date.is_distinct_from(post.post_date))
+            .values(effective_date=post.post_date)
+            .execution_options(synchronize_session=False)
+        )
+        linked = select(ImageProvenance.image_record_id).where(
+            ImageProvenance.post_id == post.id
+        )
+        earliest = (
+            select(func.min(Post.post_date))
+            .select_from(ImageProvenance)
+            .join(Post, Post.id == ImageProvenance.post_id)
+            .where(ImageProvenance.image_record_id == ImageRecord.id)
+            .where(Post.post_date.is_not(None))
+            .correlate(ImageRecord)
+            .scalar_subquery()
+        )
+        self.session.execute(
+            update(ImageRecord)
+            .where(ImageRecord.id.in_(linked))
+            .where(ImageRecord.earliest_post_date.is_distinct_from(earliest))
+            .values(earliest_post_date=earliest)
+            .execution_options(synchronize_session=False)
+        )
+
    def attach_in_place(
        self,
        path: Path,
@@ -1187,7 +1229,10 @@ class Importer:
                path, artist=artist, source_row=source,
            )
        if not is_supported(path):
-            post = self._post_for_sidecar(path, artist) if artist else None
+            post = (
+                self._post_for_sidecar(path, artist, source_row=source)
+                if artist else None
+            )
            return self._capture_attachment(
                path, post=post, artist=artist, resolved=True,
            )
@@ -289,6 +289,11 @@ class Ingester:
        # Media handed to phase 3 for import. Marked seen by phase 3 once the
        # import has run (`mark_seen_after_import`), not here — see there.
        fetched: list[tuple[str, str]] = []
+        # Post-record keys written this walk. Marked with the media, after
+        # phase 3 has upserted the records — marking them at write time left a
+        # walk killed before phase 3 with posts the ledger calls recorded that
+        # the database never dated, and no later tick walks back to them (#4436).
+        recorded: list[tuple[str, str]] = []
        downloaded = 0
        errors = 0
        quarantined = 0
@@ -342,7 +347,9 @@ class Ingester:
                written_paths=written,
                post_record_paths=list(post_records),
                relink_source_paths=list(relink),
-                mark_seen_after_import=lambda: self._mark_seen(source_id, fetched),
+                mark_seen_after_import=lambda: self._mark_seen(
+                    source_id, fetched + recorded,
+                ),
                stdout="\n".join(log_lines),
                stderr="",
                return_code=return_code,
@@ -511,7 +518,7 @@ class Ingester:
                                    posts_with_body += 1
                            if rec.path is not None:
                                post_records.append(str(rec.path))
-                                self._mark_seen(source_id, [(pkey, ppid)])
+                                recorded.append((pkey, ppid))
                            # Per-post handling line in the run stdout (the existing
                            # "Raw stdout" panel) — the downloader already read the
                            # post; we only format its outcome here. post_type beside
@@ -97,8 +97,8 @@ def _sigmoid(z, np):

 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?"."""
+    probability and WHICH head produced it — the system-tag sweep's guard-2 asks
+    "does this ALSO look like real content?"."""
    cprobs = _sigmoid(Xn @ Wc.T + bc, np)
    return cprobs.max(axis=1), cprobs.argmax(axis=1)

@@ -106,10 +106,9 @@ def _conflict_scores(Xn, Wc, bc, np):
 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."""
+    """Single-source the ring-loud PresentationReview row shape, so every writer of
+    the (image_record_id, tag_id) composite PK agrees on columns and `mode` — a
+    divergent `mode` would be a silent first-writer-wins bug."""
    session.execute(
        pg_insert(PresentationReview)
        .values(
@@ -963,68 +962,6 @@ def system_tag_auto_apply_sweep(
    }


-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
@@ -32,11 +32,8 @@ from ...models.tag import image_tag
 # `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",
 )


@@ -60,3 +60,22 @@ def platform_lock(platform: str, *, ttl_seconds: int):
    except redis.RedisError as exc:  # pragma: no cover - broker outage
        log.warning("platform_lock unavailable for %s: %s", platform, exc)
        return None
+
+
+def release_all_platform_locks() -> int:
+    """Drop every serialized platform's lock. Returns how many were held.
+
+    Only for the download lane's boot (#4433). A worker that restarts mid-walk
+    is SIGKILLed past its stop grace, so its `finally` never releases the lock,
+    and the TTL keeps every other source on that platform bouncing for up to
+    27 minutes after the new worker is ready. At boot no walk of ours can be
+    running, so a held lock names a dead one. Assumes one download consumer —
+    the only shape FC deploys; a second replica booting would free a live
+    walk's lock (not corrupt it: the walk runs on, a second walk may overlap it).
+    """
+    try:
+        client = _redis()
+        return int(client.delete(*(f"{_LOCK_PREFIX}{p}" for p in SERIALIZED_PLATFORMS)))
+    except redis.RedisError as exc:  # pragma: no cover - broker outage
+        log.warning("could not release platform locks at boot: %s", exc)
+        return 0
@@ -0,0 +1,86 @@
+"""Date the posts whose record reached the disk but never the database (#4436).
+
+A native walk writes each post's record (`_post.json`, or Discord's
+`<day>_<message id>_post.json`) as it goes, and phase 3 upserts those records
+after the walk — which is when the post, and through it its images, get their
+date. Until #4436 the walk marked a record's post key seen at write time, so a
+walk killed before phase 3 (a restart, a stall) left the post undated with the
+ledger saying it was done, and no later tick walked back that far to fix it.
+
+The record files are still on disk. This finds each undated native post's
+record under its artist's folder and upserts it with the post's OWN source —
+never the (artist, platform) lookup, which picks the artist's first source and
+would misfile a Discord channel's post (#4435). Idempotent: a post that is
+already dated is never looked at, and upserting a record twice changes nothing.
+"""
+from __future__ import annotations
+
+import json
+import logging
+from collections import defaultdict
+from pathlib import Path
+
+from sqlalchemy import select
+from sqlalchemy.orm import Session
+
+from ..models import Artist, Post, Source
+from ..utils.sidecar import parse_sidecar
+from .download_backends import NATIVE_INGESTER_PLATFORMS
+
+log = logging.getLogger(__name__)
+
+
+def _is_record(path: Path) -> bool:
+    return path.name == "_post.json" or path.name.endswith("_post.json")
+
+
+def _record_id(path: Path) -> str | None:
+    try:
+        data = json.loads(path.read_text("utf-8"))
+    except (OSError, ValueError):
+        return None
+    if not isinstance(data, dict):
+        return None
+    return parse_sidecar(data).external_post_id
+
+
+def date_posts_from_records(session: Session, importer, images_root: Path) -> dict:
+    """Upsert the on-disk record of every undated native post. Returns counts."""
+    rows = session.execute(
+        select(Post.external_post_id, Post.source_id, Post.artist_id, Source.platform)
+        .join(Source, Source.id == Post.source_id)
+        .where(
+            Post.post_date.is_(None),
+            Post.synthesized_by.is_(None),
+            Source.platform.in_(NATIVE_INGESTER_PLATFORMS),
+        )
+    ).all()
+    wanted: dict[tuple[int, str], dict[str, int]] = defaultdict(dict)
+    for epid, source_id, artist_id, platform in rows:
+        wanted[(artist_id, platform)][epid] = source_id
+
+    summary = {"undated": len(rows), "dated": 0, "no_record": 0}
+    for (artist_id, platform), by_epid in wanted.items():
+        artist = session.get(Artist, artist_id)
+        root = Path(images_root) / artist.slug / platform if artist else None
+        if root is None or not root.is_dir():
+            summary["no_record"] += len(by_epid)
+            continue
+        found = 0
+        for record in root.rglob("*post.json"):
+            if not _is_record(record):
+                continue
+            epid = _record_id(record)
+            source_id = by_epid.pop(epid, None) if epid else None
+            if source_id is None:
+                continue
+            source = session.get(Source, source_id)
+            if importer.upsert_post_record(record, artist=artist, source=source):
+                found += 1
+            if not by_epid:
+                break
+        summary["dated"] += found
+        summary["no_record"] += len(by_epid)
+    if summary["undated"]:
+        log.info("date_posts_from_records: %s", summary)
+    return summary
@@ -27,13 +27,10 @@ from .image_tag_apply import insert_image_tags

 # 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.
+# Only the artist's own "WIP"/"work in progress" label counts — high-precision, so it
+# trains the wip head. A sketch/doodle/scribble tier (#1474) was retired in milestone
+# 430: a "sketch" is usually finished art, and its 6k tags flooded the review strip.
 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
@@ -45,20 +42,10 @@ _WIP_RE = re.compile(
    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
+# Coarse SQL prefilter for the backfill sweep — narrows 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.
+# It MUST stay a SUPERSET of the 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).
@@ -66,19 +53,12 @@ _INSERT_CHUNK = 5000


 def matches_wip_title(title: str | None) -> bool:
-    """True when a post title explicitly marks it work-in-progress (HARD tier)."""
+    """True when a post title explicitly marks it work-in-progress."""
    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(
@@ -137,7 +137,13 @@ IMPORT_BATCH_KEEP_DAYS = 30
 #   (the import queue itself stays at the 5-min default for single
 #   files); time_limit=2100.
 QUEUE_STUCK_THRESHOLD_MINUTES: dict[str, int] = {
-    "ml": 25,
+    # ml: the scheduled auto-apply sweeps and refresh_character_prototypes run
+    # to a 35-min hard limit (2100s); 25 swept them mid-run (#4432). The two
+    # 65-min jobs have their own entries below.
+    "ml": 40,
+    # import: import_media_file's hard limit is 6 min (360s), one past the
+    # 5-min default this queue fell to (#4432).
+    "import": 10,
    # download_source legitimately walks 5-25 min (Patreon/gallery-dl
    # deep creators); its hard time_limit is DOWNLOAD_HARD_TIME_LIMIT
    # (1500s = 25m). The 5-min default flagged healthy in-flight walks as
@@ -154,6 +160,12 @@ QUEUE_STUCK_THRESHOLD_MINUTES: dict[str, int] = {
    # overrides below cover the outliers (backups, library audit).
    "maintenance": 75,
    "scan": 75,
+    # The long lane (#4432). Until TaskRun.queue asked the router, nothing was
+    # recorded here: these runs read as `maintenance` (75) or, for
+    # translation, `default` (5 — which failed healthy 35-min runs). The
+    # longest task without its own entry below is the admin family at a
+    # 40-min hard limit; 45 = 40 + 5.
+    "maintenance_long": 45,
 }
 TASK_STUCK_THRESHOLD_MINUTES: dict[str, int] = {
    "backend.app.tasks.import_file.import_archive_file": 40,
@@ -179,6 +191,10 @@ TASK_STUCK_THRESHOLD_MINUTES: dict[str, int] = {
    # external-fetch entry above — without an override a healthy in-flight walk
    # is swept 'RecoverySweep' at the bare 5-min default. 30 = 25 + 5.
    "backend.app.tasks.admin.reclaim_orphaned_attachments_task": 30,
+    # Head training and the manual head apply run to 65 min (3900s) — past the
+    # ml queue's threshold (#4432). 70 = 65 + 5.
+    "backend.app.tasks.ml.train_heads": 70,
+    "backend.app.tasks.ml.apply_head_tags": 70,
 }


@@ -715,6 +731,32 @@ def recover_stalled_download_events() -> int:
        return events_recovered


+@celery.task(
+    name="backend.app.tasks.maintenance.date_posts_from_records",
+    soft_time_limit=1500,
+    time_limit=1800,
+)
+def date_posts_from_records() -> dict:
+    """Date undated native posts from the records their walk left on disk
+    (#4436). Hourly and self-limiting: once every post is dated it is one
+    empty query."""
+    from ..services.importer import Importer
+    from ..services.post_record_repair import date_posts_from_records as _repair
+    from ..services.thumbnailer import Thumbnailer
+
+    images_root = IMAGES_ROOT
+    SessionLocal = _sync_session_factory()
+    with SessionLocal() as session:
+        importer = Importer(
+            session=session,
+            images_root=images_root,
+            import_root=images_root,
+            thumbnailer=Thumbnailer(images_root=images_root),
+            settings=ImportSettings.load_sync(session),
+        )
+        return _repair(session, importer, images_root)
+
+
@celery.task(name="backend.app.tasks.maintenance.recover_stalled_backup_runs")
 def recover_stalled_backup_runs() -> int:
    """Flip BackupRun rows stuck in running/restoring past the hard limit
@@ -1041,8 +1083,7 @@ def cleanup_old_download_events() -> int:

 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
+    `tag_id` (stamped `source`) to their images (#1458). 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
@@ -1082,26 +1123,17 @@ def _backfill_wip_tier(session, tag_id, prefilter, matcher, source) -> int:
 )
 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.
+    images — the operator-triggered back-catalogue catch-up (task #1458). New
+    imports are tagged live by the importer; this covers the existing library.
+    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,
    )
@@ -1114,16 +1146,10 @@ def backfill_wip_title_tags() -> int:
                "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
@@ -620,24 +620,6 @@ def scheduled_process_auto_apply() -> str:
    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
@@ -180,7 +180,10 @@ per `docs/process.md`'s "add deps to the image when used by >1 project".
    BUILD_REF` that every checkout in the file takes, rather than per job —
    otherwise `sign-extension` would derive dev's extension version while
    `build-web` bundled main's, and the release download would 404 on a version
-    that exists perfectly well. Every job then ASSERTS its checkout is `main`
+    that exists perfectly well. On every other trigger `BUILD_REF` is the
+    triggering COMMIT (`github.sha`), not the branch: a branch is re-resolved
+    per job, so a push landing mid-run used to move the publishing jobs onto a
+    commit the run's lanes never tested (run 7499, #4427). Every job then ASSERTS its checkout is `main`
    before doing anything, because `env` inside `with:` is not a context this
    runner is known to evaluate — if it silently resolved to empty, checkout
    would fall back to the triggering ref and the refresh would publish dev's
@@ -2,14 +2,14 @@
  <!-- 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).
+       go unnoticed), most-concerning first (#141, #1464). Each card asks one
+       question — is this image a <tag>? — and its buttons answer it (#4424).
       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-tagged {{ items.length === 1 ? 'image' : 'images' }}
-        may be real content — review
+        {{ items.length }} {{ items.length === 1 ? 'auto-tag' : 'auto-tags' }} to check
      </span>
    </div>
    <div class="fc-review__cards">
@@ -21,22 +21,23 @@
          class="fc-review-card__thumb" loading="lazy"
        >
        <div class="fc-review-card__body">
+          <div class="fc-review-card__question">{{ question(it) }}</div>
          <div
-            class="fc-review-card__conflict"
-            :title="`Scored ${Math.round(it.conflict_score * 100)}% on “${it.conflict_name || 'a content tag'}”`"
+            class="fc-review-card__reason"
+            :title="reasonTitle(it)"
          >
-            also looks like <strong>{{ it.conflict_name || 'content' }}</strong>
+            also {{ Math.round(it.conflict_score * 100) }}%
+            <strong>{{ it.conflict_name || 'content' }}</strong>
          </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')"
-            >{{ keepLabel(it) }}</button>
+            >Is {{ withArticle(it) }}</button>
            <button
              type="button" class="fc-review-btn fc-review-btn--unhide"
              :disabled="busy.includes(keyOf(it))" @click="resolve(it, 'unhide')"
-            >{{ removeLabel(it) }}</button>
+            >Is not {{ withArticle(it) }}</button>
          </div>
        </div>
      </div>
@@ -55,11 +56,18 @@ 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' }
+// The card asks whether the image IS the auto-applied system tag, and the buttons
+// answer that (operator, #4424: "is a <tag>" / "is not a <tag>"). "Is" keeps the
+// tag ('keep'); "Is not" removes it, un-hiding a chrome image ('unhide'). The
+// content tag it also scored on is the reason it was flagged, not the question.
+function noun(it) { return it.tag_name === 'wip' ? 'WIP' : it.tag_name }
+function withArticle(it) { return (/^[aeiou]/i.test(noun(it)) ? 'an ' : 'a ') + noun(it) }
+function question(it) { return `Is this ${withArticle(it)}?` }
+function reasonTitle(it) {
+  const hidden = it.mode === 'process' ? '' : ' It is hidden from the gallery until you answer.'
+  return `Auto-tagged “${it.tag_name}”, but it also scored ${Math.round(it.conflict_score * 100)}% `
+    + `on “${it.conflict_name || 'a content tag'}”, so it may be finished art.${hidden}`
+}

 async function load() {
  // Fetched unconditionally on mount — the strip prompts for pending misfires
@@ -77,14 +85,11 @@ async function resolve(it, action) {
    await api.post(`/api/gallery/hidden-review/${it.image_id}/${it.tag_id}/${action}`)
    items.value = items.value.filter((x) => keyOf(x) !== k)
    if (action === 'unhide') {
-      const verb = it.mode === 'process' ? 'Removed' : 'Un-hidden'
-      toast({ text: `${verb} — “${it.tag_name}” removed; it'll train the head`, type: 'success' })
+      const shown = it.mode === 'process' ? '' : ', back in the gallery'
+      toast({ text: `Not ${withArticle(it)} — “${it.tag_name}” removed${shown}; the tagger learns from it`, type: 'success' })
    }
  } catch (e) {
-    toast({
-      text: `Could not ${action === 'keep' ? 'keep hidden' : 'un-hide'}: ${e.message}`,
-      type: 'error',
-    })
+    toast({ text: `Could not save your answer: ${e.message}`, type: 'error' })
  } finally {
    busy.value = busy.value.filter((x) => x !== k)
  }
@@ -112,7 +117,7 @@ onMounted(load)
  display: flex; gap: 10px; overflow-x: auto; padding-bottom: 4px;
 }
 .fc-review-card {
-  flex: 0 0 auto; width: 150px;
+  flex: 0 0 auto; width: 170px;
  display: flex; flex-direction: column;
  border: 1px solid rgb(var(--v-theme-surface-light));
  border-radius: 6px; overflow: hidden;
@@ -123,16 +128,16 @@ onMounted(load)
  background: rgb(var(--v-theme-surface-light));
 }
 .fc-review-card__body { padding: 6px 8px; }
-.fc-review-card__conflict {
-  font-size: 11px; color: rgb(var(--v-theme-on-surface));
+.fc-review-card__question {
+  font-size: 12px; font-weight: 600; color: rgb(var(--v-theme-on-surface));
  overflow: hidden; text-overflow: ellipsis; white-space: nowrap;
 }
-.fc-review-card__conflict strong { color: rgb(var(--v-theme-warning)); }
-.fc-review-card__tag {
+.fc-review-card__reason {
  font-size: 10px; color: rgb(var(--v-theme-on-surface-variant));
  margin: 1px 0 6px;
  overflow: hidden; text-overflow: ellipsis; white-space: nowrap;
 }
+.fc-review-card__reason strong { color: rgb(var(--v-theme-warning)); font-weight: 600; }
 .fc-review-card__acts { display: flex; gap: 4px; }
 .fc-review-btn {
  flex: 1; font-size: 11px; padding: 3px 4px; border-radius: 4px;
@@ -17,7 +17,7 @@
        <v-icon start>mdi-folder-zip-outline</v-icon> Re-extract archives now
      </v-btn>
      <span v-if="queued" class="ml-3 text-caption text-success">Queued ✓</span>
-      <QueueStatusBar queue="maintenance" queue-label="Maintenance" />
+      <QueueStatusBar queue="maintenance_long" queue-label="Long maintenance" />
  </MaintenanceTile>
 </template>

@@ -103,17 +103,6 @@
          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"
@@ -156,7 +145,6 @@ const local = reactive({
  skip_single_color: false, single_color_threshold: 0.95,
  phash_threshold: 24,
  wip_title_tagging_enabled: true,
-  wip_soft_title_tagging_enabled: false,
 })

 watch(() => store.settings, (s) => { if (s) Object.assign(local, s) }, { immediate: true })
@@ -18,7 +18,7 @@
        <v-icon start>mdi-file-remove-outline</v-icon> Repair missing-file records
      </v-btn>
      <span v-if="queued" class="ml-3 text-caption text-success">Queued ✓</span>
-      <QueueStatusBar queue="maintenance" queue-label="Maintenance" />
+      <QueueStatusBar queue="maintenance_long" queue-label="Long maintenance" />
  </MaintenanceTile>
 </template>

@@ -41,7 +41,7 @@ const props = defineProps({

 const QUEUE_NAMES = [
  'default', 'import', 'thumbnail', 'ml',
-  'download', 'scan', 'maintenance',
+  'download', 'scan', 'maintenance', 'maintenance_long',
 ]

 function formatDepth(name) {
@@ -119,7 +119,7 @@ export const useAdminStore = defineStore('admin', () => {
  // --- Task progress polling (taps FC-3i activity dashboard) --------

  /**
-   * Polls /api/system/activity/runs?queue=maintenance every 3s,
+   * Polls /api/system/activity/runs?celery_task_id=<id> every 3s,
   * resolves when a task_run row with the given celery task_id
   * reaches a terminal status (ok / error / timeout). Returns the
   * row. Times out after 30 min by default.
@@ -129,7 +129,9 @@ export const useAdminStore = defineStore('admin', () => {
    while (Date.now() < deadline) {
      const body = await api.get(
        '/api/system/activity/runs',
-        { params: { queue: 'maintenance', limit: 20 } },
+        // By id, not by lane: these jobs run on `maintenance_long`, and a
+        // lane filter here is one more copy of the routing table (#4432).
+        { params: { celery_task_id: taskId, limit: 1 } },
      )
      const row = (body.runs || []).find(r => r.celery_task_id === taskId)
      if (row && ['ok', 'error', 'timeout'].includes(row.status)) {
@@ -210,8 +210,8 @@ def render(
        )

    parts.append(
-        f"Built from `{short}`. The rollback unit is the immutable `:c-` tag "
-        f"(rule 145) — these three move together:\n\n```\n"
+        f"Built from `{short}`. To roll back to this release, pull these "
+        f"immutable `:c-` tags — the images move together:\n\n```\n"
        + "\n".join(f"{image}:c-{short}" for image in IMAGES)
        + "\n```"
    )
@@ -221,10 +221,10 @@ def render(
        # truncated to MAX_COMMITS, which is 200 lines of internal build-out
        # presented to someone who has never seen this project.
        parts.append(
-            "---\n\n_First release under rule 148's `vYYYY.MM.DD.HHMM` shape, so "
-            "there is no predecessor to diff against and no changelog to derive. "
-            "The description above is README.md's, quoted at publish time. Later "
-            "releases carry the commits since the previous one._"
+            "---\n\n_The first release, so there is no earlier one to diff "
+            "against and no changelog to derive. The description above is "
+            "README.md's, quoted at publish time. Later releases carry the "
+            "commits since the previous one._"
        )
        return "\n\n".join(parts)

@@ -257,8 +257,8 @@ def cross_checks(tag: str, sha: str) -> list[str]:

    if not RULE_148.match(tag):
        notes.append(
-            f"`{tag}` is not rule 148's `vYYYY.MM.DD.HHMM` shape. Published "
-            f"anyway — the old `v26.*` tags predate the rule."
+            f"`{tag}` is not the `vYYYY.MM.DD.HHMM` release-tag shape. "
+            f"Published anyway — the old `v26.*` tags predate it."
        )
    else:
        derived = artifact_version("web")
@@ -295,3 +295,11 @@ async def test_failures_only_within_24h_window(client, _seed_failures):
    body = await resp.get_json()
    ids = {r["error_type"] for r in body["recent"]}
    assert "OldError" not in ids
+
+
+@pytest.mark.asyncio
+async def test_runs_filter_by_celery_task_id(client, _seed_runs):
+    # How a page follows a job it started, without knowing its lane (#4432).
+    resp = await client.get("/api/system/activity/runs?celery_task_id=tid-3")
+    body = await resp.get_json()
+    assert [r["celery_task_id"] for r in body["runs"]] == ["tid-3"]
@@ -2,6 +2,8 @@
 `maintenance_long` lane so a 30-min backup or a multi-chunk audit can't starve
 the quick recovery sweeps / vacuum on the concurrency-1 `maintenance` lane
 (operator-flagged 2026-06-07)."""
+import pytest
+
 from backend.app.celery_app import celery


@@ -20,23 +22,65 @@ def test_quick_maintenance_stays_on_maintenance():
    assert routes["backend.app.tasks.maintenance.*"]["queue"] == "maintenance"


-def test_queue_for_mirrors_external_to_download():
-    """celery_signals._queue_for is a hand-maintained mirror of task_routes
-    that stamps TaskRun.queue. external.* routes to the download lane, so the
-    mirror must agree — else TaskRun.queue lies 'default' for external fetches
-    and per-queue dashboard filters / threshold overrides miss them
-    (operator-flagged 2026-06-17)."""
+@pytest.mark.parametrize(("name", "queue"), [
+    ("backend.app.tasks.external.fetch_external_link", "download"),
+    # The rows #4432 found recorded on the wrong lane:
+    ("backend.app.tasks.translation.translate_posts", "maintenance_long"),
+    ("backend.app.tasks.gpu_queue.enqueue_gpu_backfill", "maintenance"),
+    ("backend.app.tasks.maintenance.backfill_phash", "maintenance_long"),
+    ("backend.app.tasks.maintenance.date_posts_from_records", "maintenance_long"),
+    ("backend.app.tasks.admin.normalize_tags_task", "maintenance_long"),
+    ("backend.app.tasks.backup.backup_db_task", "maintenance_long"),
+    ("backend.app.tasks.maintenance.vacuum_analyze", "maintenance"),
+    ("backend.app.tasks.not_routed.anything", "default"),
+])
+def test_task_run_records_the_queue_the_router_sends_to(name, queue):
+    """TaskRun.queue comes from the router, not a copy of task_routes (#4432):
+    the stall sweep's per-queue thresholds and the System activity filters both
+    key off it."""
    from backend.app.celery_signals import _queue_for

    class _T:
-        name = "backend.app.tasks.external.fetch_external_link"
+        pass

-    assert _queue_for(_T()) == "download"
-    assert (
-        celery.conf.task_routes["backend.app.tasks.external.*"]["queue"]
-        == "download"
+    t = _T()
+    t.name = name
+    t.app = celery
+    assert _queue_for(t) == queue
+
+
+def test_no_task_outlives_its_stall_threshold():
+    """A task whose hard time limit is longer than the stall sweep's threshold
+    for it gets failed 'RecoverySweep' while it is still healthy — the class
+    #4432 found on the ml, import and long-maintenance lanes. The threshold is
+    resolved the way recover_stalled_task_runs resolves it: task-name override,
+    then queue, then the default."""
+    from backend.app.celery_signals import _queue_for
+    from backend.app.tasks.maintenance import (
+        QUEUE_STUCK_THRESHOLD_MINUTES,
+        STUCK_THRESHOLD_MINUTES,
+        TASK_STUCK_THRESHOLD_MINUTES,
    )

+    celery.loader.import_default_modules()
+    checked = 0
+    too_short = []
+    for name, task in sorted(celery.tasks.items()):
+        if name.startswith("celery."):
+            continue
+        limit = getattr(task, "time_limit", None)
+        if not limit:
+            continue
+        threshold = TASK_STUCK_THRESHOLD_MINUTES.get(
+            name,
+            QUEUE_STUCK_THRESHOLD_MINUTES.get(_queue_for(task), STUCK_THRESHOLD_MINUTES),
+        )
+        checked += 1
+        if limit / 60 > threshold:
+            too_short.append(f"{name}: limit {limit / 60:.0f} min > sweep {threshold} min")
+    assert checked > 20, "the task registry did not load — this guard checked nothing"
+    assert not too_short, "\n".join(too_short)
+

 def test_backfill_phash_runs_on_the_long_lane():
    """It lives in maintenance.py, so the quick-lane glob matches it too —
@@ -0,0 +1,71 @@
+"""#4433: only the process consuming `download` clears a restart's leftovers.
+
+The consolidated container boots four lanes side by side. If the scheduler or
+ml lane ran this too, a lane restarting on its own (supervisord restarts a
+crashed program) would close the events of walks that are still running.
+"""
+from __future__ import annotations
+
+from types import SimpleNamespace
+
+import pytest
+
+from backend.app import celery_signals
+
+
+def _consumer(*queues: str):
+    return SimpleNamespace(
+        task_consumer=SimpleNamespace(queues=[SimpleNamespace(name=q) for q in queues])
+    )
+
+
+@pytest.fixture
+def calls(monkeypatch):
+    seen: list[str] = []
+
+    class _Session:
+        def __enter__(self):
+            return self
+
+        def __exit__(self, *exc):
+            return False
+
+        def commit(self):
+            seen.append("commit")
+
+    monkeypatch.setattr(celery_signals, "sync_session_factory", lambda: _Session)
+    monkeypatch.setattr(
+        "backend.app.services.download_recovery.interrupt_orphaned_download_events",
+        lambda session, *, booted_at: seen.append("interrupt") or 0,
+    )
+    monkeypatch.setattr(
+        "backend.app.services.platform_lock.release_all_platform_locks",
+        lambda: seen.append("release") or 0,
+    )
+    return seen
+
+
+def test_the_download_lane_clears_orphans_and_locks(calls):
+    celery_signals._on_worker_ready(sender=_consumer("default", "download", "import"))
+    assert calls == ["interrupt", "commit", "release"]
+
+
+@pytest.mark.parametrize("queues", [("maintenance", "scan"), ("ml",), ("maintenance_long",)])
+def test_other_lanes_leave_downloads_alone(calls, queues):
+    celery_signals._on_worker_ready(sender=_consumer(*queues))
+    assert calls == []
+
+
+def test_unreadable_queues_do_nothing_rather_than_guess(calls):
+    celery_signals._on_worker_ready(sender=SimpleNamespace())
+    assert calls == []
+
+
+def test_a_failure_does_not_stop_the_worker_starting(monkeypatch, calls):
+    def boom(session, *, booted_at):
+        raise RuntimeError("db down")
+
+    monkeypatch.setattr(
+        "backend.app.services.download_recovery.interrupt_orphaned_download_events", boom
+    )
+    celery_signals._on_worker_ready(sender=_consumer("download"))  # must not raise
@@ -0,0 +1,106 @@
+"""Migration 0114 (#4435): the undated shell post a misfiled attachment made on
+the artist's first Discord source is folded into the real, dated post."""
+import importlib.util
+from datetime import UTC, datetime
+from pathlib import Path
+
+import pytest
+from sqlalchemy import select
+
+from backend.app.models import (
+    Artist,
+    ImageProvenance,
+    Post,
+    PostAttachment,
+    Source,
+)
+from tests.factories import make_image as _img
+
+pytestmark = pytest.mark.integration
+
+_MIGRATION = (
+    Path(__file__).resolve().parents[1]
+    / "alembic" / "versions" / "0114_fold_misfiled_attachment_posts.py"
+)
+
+
+def _fold():
+    spec = importlib.util.spec_from_file_location("m0114", _MIGRATION)
+    mod = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(mod)
+    return mod.fold_misfiled_attachment_posts
+
+
+def _source(db, artist, channel):
+    s = Source(
+        artist_id=artist.id, platform="discord",
+        url=f"https://discord.com/channels/1/{channel}",
+    )
+    db.add(s)
+    db.flush()
+    return s
+
+
+def _post(db, artist, source, epid, when=None):
+    p = Post(
+        artist_id=artist.id, source_id=source.id, external_post_id=epid,
+        post_date=when,
+        post_url=f"https://discord.com/channels/1/x/{epid}" if when else None,
+    )
+    db.add(p)
+    db.flush()
+    return p
+
+
+def _attach(db, post, sha, name):
+    db.add(PostAttachment(
+        post_id=post.id, artist_id=post.artist_id, sha256=sha,
+        path=f"/att/{sha}", original_filename=name, ext=".rar", size_bytes=1,
+    ))
+    db.flush()
+
+
+def test_shells_fold_into_their_dated_twin_and_nothing_else_moves(db_sync):
+    sent = datetime(2024, 12, 26, 1, 42, tzinfo=UTC)
+    artist = Artist(name="Yellow", slug="yellow")
+    db_sync.add(artist)
+    db_sync.flush()
+    first = _source(db_sync, artist, 100)
+    second = _source(db_sync, artist, 200)
+
+    # The #4435 shape: shell on the first source, real post on the second.
+    shell = _post(db_sync, artist, first, "555")
+    real = _post(db_sync, artist, second, "555", sent)
+    _attach(db_sync, shell, "a" * 64, "pack.rar")
+    # A shell whose attachment the real post already has: dropped, not doubled.
+    shell2 = _post(db_sync, artist, first, "556")
+    real2 = _post(db_sync, artist, second, "556", sent)
+    _attach(db_sync, shell2, "b" * 64, "same.rar")
+    _attach(db_sync, real2, "b" * 64, "same.rar")
+    # Left alone: no dated twin, and an undated post that holds an image.
+    lonely = _post(db_sync, artist, first, "557")
+    _attach(db_sync, lonely, "c" * 64, "lonely.rar")
+    with_image = _post(db_sync, artist, first, "558")
+    _post(db_sync, artist, second, "558", sent)
+    img = _img(db_sync, "d" * 64)
+    db_sync.add(ImageProvenance(image_record_id=img.id, post_id=with_image.id))
+    db_sync.flush()
+    shell_id, shell2_id = shell.id, shell2.id
+
+    folded = _fold()(db_sync.connection())
+    db_sync.expire_all()
+
+    assert folded == 2
+    assert db_sync.get(Post, shell_id) is None
+    assert db_sync.get(Post, shell2_id) is None
+    owners = dict(db_sync.execute(
+        select(PostAttachment.original_filename, PostAttachment.post_id)
+    ).all())
+    assert owners["pack.rar"] == real.id
+    assert owners["lonely.rar"] == lonely.id
+    kept = db_sync.execute(
+        select(PostAttachment.id).where(PostAttachment.post_id == real2.id)
+    ).scalars().all()
+    assert len(kept) == 1
+    assert db_sync.get(Post, lonely.id) is not None
+    assert db_sync.get(Post, with_image.id) is not None
@@ -435,3 +435,48 @@ def test_attach_in_place_non_media_routes_to_attachment(importer, db_sync):
    ).scalar_one()
    assert row.ext == ".txt"
    assert row.artist_id == artist.id
+
+
+def test_a_non_media_file_lands_on_the_source_being_downloaded(importer, db_sync):
+    """#4435: a Discord artist has one source per channel. A non-media file
+    downloaded for the SECOND channel was filed under the artist's first
+    Discord source (the (artist, platform) lookup takes the lowest id), as an
+    undated shell post; the real post record then made a second post under
+    the right source. The attachment must follow the source it was fetched for."""
+    from backend.app.models import Post, PostAttachment, Source
+
+    images_root = importer.images_root
+    artist = Artist(name="Yara", slug="yara")
+    db_sync.add(artist)
+    db_sync.flush()
+    first = Source(
+        artist_id=artist.id, platform="discord",
+        url="https://discord.com/channels/1/100",
+    )
+    second = Source(
+        artist_id=artist.id, platform="discord",
+        url="https://discord.com/channels/1/200",
+    )
+    db_sync.add_all([first, second])
+    db_sync.flush()
+
+    rar = images_root / "yara" / "discord" / "rewards" / "20241226_555_01_pack.rar"
+    rar.parent.mkdir(parents=True, exist_ok=True)
+    rar.write_bytes(b"not a real archive, so it is kept as an attachment")
+    rar.with_suffix(rar.suffix + ".json").write_text(
+        '{"category": "discord", "id": "555", "message_id": "555"}'
+    )
+
+    result = importer.attach_in_place(rar, artist=artist, source=second)
+    assert result.status == "attached"
+
+    owner = db_sync.execute(
+        select(Post.source_id, Post.external_post_id)
+        .join(PostAttachment, PostAttachment.post_id == Post.id)
+        .where(PostAttachment.original_filename == rar.name)
+    ).one()
+    assert owner.source_id == second.id
+    assert owner.external_post_id == "555"
+    assert db_sync.execute(
+        select(func.count()).select_from(Post).where(Post.source_id == first.id)
+    ).scalar_one() == 0
@@ -335,26 +335,30 @@ def test_recover_stalled_task_runs_ml_queue_uses_longer_threshold(db_sync):
    """ml-queue tasks (embed_image video branch) legitimately run
    past the default 5-min threshold. The sweep must NOT flag an
    ml-queue task that's only been running 10 min — the override
-    threshold (25 min via QUEUE_STUCK_THRESHOLD_MINUTES) protects
-    in-flight video tagging. Operator-flagged 2026-05-28 after
-    image 6288 (mp4) was marked failed at the 5-min tick mid-run."""
+    threshold (QUEUE_STUCK_THRESHOLD_MINUTES["ml"]) protects in-flight
+    video tagging. Operator-flagged 2026-05-28 after image 6288 (mp4)
+    was marked failed at the 5-min tick mid-run. Read from the table
+    rather than restated: the value moved 25 -> 40 in #4432."""
    from sqlalchemy import select

    from backend.app.models import TaskRun
-    from backend.app.tasks.maintenance import recover_stalled_task_runs
+    from backend.app.tasks.maintenance import (
+        QUEUE_STUCK_THRESHOLD_MINUTES,
+        recover_stalled_task_runs,
+    )

+    ml_threshold = QUEUE_STUCK_THRESHOLD_MINUTES["ml"]
    now = datetime.now(UTC)
    # 10-min-old ml-queue row: stale by the default 5-min rule but
-    # fresh by the 25-min ml override. Must survive the sweep.
+    # fresh by the ml override. Must survive the sweep.
    ml_fresh_id = _make_task_run(
        db_sync, status="running", queue="ml",
        started_at=now - timedelta(minutes=10),
    )
-    # 30-min-old ml-queue row: past even the ml override. Must be
-    # flagged.
+    # Past even the ml override. Must be flagged.
    ml_stale_id = _make_task_run(
        db_sync, status="running", queue="ml",
-        started_at=now - timedelta(minutes=30),
+        started_at=now - timedelta(minutes=ml_threshold + 5),
    )
    db_sync.commit()

@@ -431,9 +435,10 @@ def test_download_stuck_threshold_exceeds_hard_time_limit():
 def test_recover_stalled_task_runs_archive_task_uses_longer_threshold(db_sync):
    """import_archive_file shares the 'import' queue with fast
    single-file import_media_file, so it gets a per-task-name override
-    (40 min) while the import queue stays at the 5-min default. A
-    10-min-old archive task-run must survive; a 50-min-old one is
-    flagged. Operator-flagged 2026-05-28."""
+    (40 min) while the import queue keeps its short threshold (10 min
+    since #4432; import_media_file's hard limit is 6). A 10-min-old
+    archive task-run must survive; a 50-min-old one is flagged.
+    Operator-flagged 2026-05-28."""
    from sqlalchemy import select

    from backend.app.models import TaskRun
@@ -441,12 +446,12 @@ def test_recover_stalled_task_runs_archive_task_uses_longer_threshold(db_sync):

    archive_name = "backend.app.tasks.import_file.import_archive_file"
    now = datetime.now(UTC)
-    # Fast single-file import on the same queue, 10 min old → flagged
-    # by the default 5-min rule.
+    # Fast single-file import on the same queue, 15 min old → flagged
+    # by the import queue's 10-min threshold.
    media_id = _make_task_run(
        db_sync, status="running", queue="import",
        task_name="backend.app.tasks.import_file.import_media_file",
-        started_at=now - timedelta(minutes=10),
+        started_at=now - timedelta(minutes=15),
    )
    # Archive on the same queue, 10 min old → survives (40-min override).
    archive_fresh_id = _make_task_run(
@@ -713,6 +718,57 @@ def test_recover_stalled_download_skips_fresh(db_sync):
    assert failures == 0


+def test_download_lane_boot_closes_pre_boot_events_without_blaming_the_source(db_sync):
+    """#4433: a restart SIGKILLs a walk past its stop grace and strands queued
+    ones. At the download lane's boot, everything pending/running from before
+    it ends as `skipped`/interrupted — and the source is left as it was, so it
+    is due on the next tick instead of backed off as a failure."""
+    from sqlalchemy import select
+
+    from backend.app.models import DownloadEvent, Source
+    from backend.app.services.download_recovery import (
+        DOWNLOAD_INTERRUPTED_MESSAGE,
+        interrupt_orphaned_download_events,
+    )
+
+    sid = _make_source(db_sync, slug="rebooted")
+    booted_at = datetime.now(UTC)
+    before = booted_at - timedelta(minutes=5)
+    walking = DownloadEvent(
+        source_id=sid, status="running", started_at=before,
+        metadata_={"live": {"downloaded": 3}},
+    )
+    queued = DownloadEvent(source_id=sid, status="pending", started_at=before)
+    finished = DownloadEvent(source_id=sid, status="ok", started_at=before)
+    # Promoted to running after the boot: download_service resets started_at.
+    fresh = DownloadEvent(
+        source_id=sid, status="running", started_at=booted_at + timedelta(seconds=5),
+    )
+    db_sync.add_all([walking, queued, finished, fresh])
+    db_sync.commit()
+
+    closed = interrupt_orphaned_download_events(db_sync, booted_at=booted_at)
+    db_sync.commit()
+
+    assert closed == 2
+    db_sync.expire_all()
+    for ev in (walking, queued):
+        assert ev.status == "skipped"
+        assert ev.error == DOWNLOAD_INTERRUPTED_MESSAGE
+        assert ev.finished_at is not None
+        assert ev.metadata_["error_type"] == "interrupted"
+    assert walking.metadata_["live"] == {"downloaded": 3}
+    assert finished.status == "ok"
+    assert fresh.status == "running"
+    src = db_sync.execute(
+        select(Source.consecutive_failures, Source.last_error, Source.last_checked_at)
+        .where(Source.id == sid)
+    ).one()
+    assert src.consecutive_failures == 0
+    assert src.last_error is None
+    assert src.last_checked_at is None
+
+
 def test_recover_stalled_download_flips_stale_pending(db_sync):
    """A 2-hour-old pending event flips to error AND the source is bumped
    (consecutive_failures, last_error, last_checked_at) so the next scan
@@ -239,8 +239,8 @@ async def test_tick_downloads_unseen_and_marks_seen(source_id, sync_engine, tmp_
    # plan #704: structured run_stats carry the real counts.
    assert result.run_stats["downloaded_count"] == 2
    assert result.posts_processed == 1
-    # The media wait for phase 3 to import them; only the post key is in yet.
-    assert _count_ledger(sync_engine, source_id) == 1
+    # The media and the post record both wait for phase 3 to import them (#4436).
+    assert _count_ledger(sync_engine, source_id) == 0
    result.mark_seen_after_import()
    # 2 media keys + 1 synthetic post key (body/links recaptured per post).
    assert _count_ledger(sync_engine, source_id) == 3
@@ -648,8 +648,10 @@ async def test_recovery_tier2_disk_still_skips(source_id, sync_engine, tmp_path)
    assert result.files_downloaded == 0
    assert downloader.download_calls == 0
    assert result.written_paths == []
-    # Disk-skip reconciles the media key + the synthetic post key (recovery
-    # recaptures the body/links per post) = 2.
+    # Disk-skip reconciles the media key at once; the synthetic post key
+    # (recovery recaptures the body/links per post) waits for phase 3 (#4436).
+    assert _count_ledger(sync_engine, source_id) == 1
+    result.mark_seen_after_import()
    assert _count_ledger(sync_engine, source_id) == 2


@@ -943,8 +945,10 @@ async def test_a_run_that_dies_before_import_leaves_its_media_unmarked(
                    _FakeDownloader(tmp_path))
    ing.run(source_id=source_id, campaign_id="c1", artist_slug="ingest",
            url="https://patreon.com/ingest", mode="tick")
-    # Phase 3 never ran, so `mark_seen_after_import` never did: only the post key.
-    assert _count_ledger(sync_engine, source_id) == 1
+    # Phase 3 never ran, so `mark_seen_after_import` never did: neither the
+    # media nor the post record is marked (#4436 — the record, marked at write
+    # time, left the post undated for good once the run died before phase 3).
+    assert _count_ledger(sync_engine, source_id) == 0

    # The next walk finds the file on disk with no record, and imports it.
    ing2 = _ingester(sync_engine, tmp_path, _FakeClient([(None, [("p1", [m1])])]),
@@ -954,6 +958,7 @@ async def test_a_run_that_dies_before_import_leaves_its_media_unmarked(
    assert result.written_paths == [str(tmp_path / "p1_1.jpg")]
    assert result.files_downloaded == 0          # not fetched again
    assert "on disk but never imported: p1_1.jpg" in result.stdout
+    assert len(result.post_record_paths) == 1    # the record is written again
    result.mark_seen_after_import()
    assert _count_ledger(sync_engine, source_id) == 2

@@ -1200,7 +1205,10 @@ async def test_tick_captures_media_less_post_once(source_id, sync_engine, tmp_pa
    assert result.success is True
    assert len(result.post_record_paths) == 1
    assert downloader.post_records == 1
-    # The synthetic `post:ptext` key was marked seen (gates re-capture).
+    # The synthetic `post:ptext` key is marked once phase 3 has upserted the
+    # record (#4436), and then gates re-capture.
+    assert _count_ledger(sync_engine, source_id) == 0
+    result.mark_seen_after_import()
    assert _count_ledger(sync_engine, source_id) == 1

    # Second walk: already recorded → gated, no re-write, no new ledger row.
@@ -1540,6 +1548,7 @@ async def test_revisits_do_not_feed_the_body_drift_canary(
        url="https://patreon.com/ingest", mode="tick", revisit_days=30,
    )
    assert first.success is True
+    first.mark_seen_after_import()  # phase 3 ran

    # Second walk: every post is a revisit, and every body comes back empty.
    client2 = _FakeClient([(None, posts)], published=published, empty_body=True)
@@ -126,53 +126,17 @@ def test_process_sweep_flags_conflict_with_process_mode(db_sync):


 def test_process_auto_source_never_trains_head(db_sync):
-    # The runaway break: provisional wip tags (process sweep 'process_auto', soft
-    # title 'wip_title_soft') are NOT training positives; a HARD title-heuristic /
-    # manual one IS. So the head learns only from trusted labels, never its own
-    # output or the low-precision sketch/doodle tier (#1464 + #1474).
+    # The runaway break: provisional wip tags (process sweep 'process_auto') are NOT
+    # training positives; a title-heuristic / manual one IS. So the head learns only
+    # from trusted labels, never its own output (#1464).
    wip = _system_tag(db_sync, "wip")
    auto_img = _img(db_sync, "f" * 64, _emb(0))
-    soft_img = _img(db_sync, "9" * 64, _emb(2))
    title_img = _img(db_sync, "0" * 64, _emb(1))
    db_sync.execute(image_tag.insert().values(
        image_record_id=auto_img.id, tag_id=wip.id, source="process_auto"))
-    db_sync.execute(image_tag.insert().values(
-        image_record_id=soft_img.id, tag_id=wip.id, source="wip_title_soft"))
    db_sync.execute(image_tag.insert().values(
        image_record_id=title_img.id, tag_id=wip.id, source="wip_title"))
    db_sync.commit()
    positives = set(_ids_with_tag(db_sync, wip.id))
    assert title_img.id in positives       # trusted HARD label trains the head
    assert auto_img.id not in positives    # its own auto-applied output does NOT
-    assert soft_img.id not in positives    # low-precision soft tier does NOT
-
-
-def test_soft_wip_conflict_audit_flags_ring_loud(db_sync):
-    # A soft-tagged image (sketch/doodle title) that ALSO scores high on a content
-    # head is probably finished art mis-tagged — flagged for review; a quiet one is not.
-    from backend.app.services.ml.heads import soft_wip_conflict_audit
-
-    s = db_sync.execute(select(MLSettings).where(MLSettings.id == 1)).scalar_one()
-    s.process_conflict_threshold = 0.6
-    wip = _system_tag(db_sync, "wip")
-    content = Tag(name="looksreal", kind=TagKind.general)
-    db_sync.add(content)
-    db_sync.flush()
-    _head(db_sync, content.id, 0, weight=1.0)   # sigmoid(1)=0.73 > 0.6 conflict
-    ring = _img(db_sync, "1" * 64, _emb(0))      # scores on the content head
-    quiet = _img(db_sync, "2" * 64, _emb(5))     # orthogonal → 0.5 < 0.6
-    for img in (ring, quiet):
-        db_sync.execute(image_tag.insert().values(
-            image_record_id=img.id, tag_id=wip.id, source="wip_title_soft"))
-    db_sync.commit()
-
-    res = soft_wip_conflict_audit(db_sync)
-    assert res["n_flagged"] == 1
-    flag = db_sync.execute(
-        select(PresentationReview).where(PresentationReview.image_record_id == ring.id)
-    ).scalar_one()
-    assert flag.mode == "process"
-    assert flag.conflict_tag_id == content.id
-    assert db_sync.execute(
-        select(PresentationReview).where(PresentationReview.image_record_id == quiet.id)
-    ).scalar_one_or_none() is None
@@ -0,0 +1,70 @@
+"""Migration 0113 (#4431): images linked to a post before its date arrived get
+the post's date back. Runs the migration's data step against real rows."""
+import importlib.util
+from datetime import UTC, datetime
+from pathlib import Path
+
+import pytest
+
+from backend.app.models import Artist, ImageProvenance, ImageRecord, Post
+from tests.factories import make_image as _img
+
+pytestmark = pytest.mark.integration
+
+_MIGRATION = (
+    Path(__file__).resolve().parents[1]
+    / "alembic" / "versions" / "0113_redate_native_images.py"
+)
+
+
+def _redate():
+    spec = importlib.util.spec_from_file_location("m0113", _MIGRATION)
+    mod = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(mod)
+    return mod.redate_images
+
+
+def _post(db, artist, epid, when):
+    p = Post(artist_id=artist.id, external_post_id=epid, post_date=when)
+    db.add(p)
+    db.flush()
+    return p
+
+
+def _link(db, img, post, *, primary):
+    db.add(ImageProvenance(image_record_id=img.id, post_id=post.id))
+    if primary:
+        img.primary_post_id = post.id
+    db.flush()
+
+
+def test_redate_images_from_their_posts(db_sync):
+    sent = datetime(2024, 3, 1, 18, 30, tzinfo=UTC)
+    earlier = datetime(2023, 1, 5, tzinfo=UTC)
+    artist = Artist(name="Alice", slug="alice")
+    db_sync.add(artist)
+    db_sync.flush()
+    undated = _post(db_sync, artist, "u1", None)
+    dated = _post(db_sync, artist, "d1", sent)
+    repost = _post(db_sync, artist, "r1", earlier)
+
+    stale = _img(db_sync, "a" * 64)          # primary post dated, image not
+    reposted = _img(db_sync, "b" * 64)       # also in an earlier post
+    orphan = _img(db_sync, "c" * 64)         # only an undated post
+    _link(db_sync, stale, dated, primary=True)
+    _link(db_sync, reposted, dated, primary=True)
+    _link(db_sync, reposted, repost, primary=False)
+    _link(db_sync, orphan, undated, primary=True)
+    orphan_before = orphan.effective_date
+
+    _redate()(db_sync.connection())
+    db_sync.expire_all()
+
+    stale = db_sync.get(ImageRecord, stale.id)
+    reposted = db_sync.get(ImageRecord, reposted.id)
+    orphan = db_sync.get(ImageRecord, orphan.id)
+    assert stale.effective_date == sent
+    assert stale.earliest_post_date == sent
+    assert reposted.effective_date == sent             # the primary post's date
+    assert reposted.earliest_post_date == earlier      # the earliest post's date
+    assert orphan.effective_date == orphan_before      # no date to take
@@ -14,6 +14,7 @@ re-implementation of it.
 """
 from __future__ import annotations

+import re
 import subprocess
 from pathlib import Path

@@ -162,6 +163,15 @@ def test_the_first_release_describes_the_product_instead_of_diffing(shaped_histo
    assert not [ln for ln in body.split("\n") if ln.startswith("- work landing")]


+@pytest.mark.parametrize("tag", ["v2026.08.28.2208", "v2026.08.29.1000"])
+def test_the_release_page_cites_no_internal_rule_numbers(shaped_history, tag):
+    """The release page is read by strangers. "rule 145" names a record in the
+    operator's own notes, which a reader cannot open — say what the rule means
+    instead. Covers the first-release overview and the changelog body."""
+    body = body_of(notes(tag, cwd=shaped_history))
+    assert not re.search(r"\brule\s+\d+", body, re.IGNORECASE), body
+
+
 def test_the_overview_is_readmes_words_not_a_second_copy(shaped_history):
    """Two hand-maintained descriptions of one product drift and nothing
    catches it. The release page quotes README.md so there is one source."""
@@ -0,0 +1,90 @@
+"""Migration 0112 (milestone 430, #4428): retiring the sketch/doodle WIP title tier.
+
+Runs the migration's data step against real rows. The soft tags the operator stood
+behind (confirmed, or kept through the review strip) survive as `manual`; the rest go,
+and so do the unresolved review cards whose tag went with them. Hard title tags and
+their flags are untouched.
+"""
+import importlib.util
+from datetime import UTC, datetime
+from pathlib import Path
+
+import pytest
+from sqlalchemy import select
+
+from backend.app.models import PresentationReview, TagPositiveConfirmation
+from backend.app.models.tag import image_tag
+from backend.app.services.wip_title import resolve_wip_tag_id
+from tests.factories import make_image as _img
+
+pytestmark = pytest.mark.integration
+
+_MIGRATION = (
+    Path(__file__).resolve().parents[1]
+    / "alembic" / "versions" / "0112_retire_soft_wip_title.py"
+)
+
+
+def _retire():
+    spec = importlib.util.spec_from_file_location("m0112", _MIGRATION)
+    mod = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(mod)
+    return mod.retire_soft_wip_tags
+
+
+def _source(db, image_id, tag_id):
+    return db.execute(
+        select(image_tag.c.source)
+        .where(image_tag.c.image_record_id == image_id)
+        .where(image_tag.c.tag_id == tag_id)
+    ).scalar_one_or_none()
+
+
+def _review(db, image_id, tag_id):
+    return db.execute(
+        select(PresentationReview)
+        .where(PresentationReview.image_record_id == image_id)
+        .where(PresentationReview.tag_id == tag_id)
+    ).scalar_one_or_none()
+
+
+def _flag(db, image_id, tag_id, *, resolved):
+    db.add(PresentationReview(
+        image_record_id=image_id, tag_id=tag_id, conflict_score=0.8, mode="process",
+        resolved_at=datetime.now(UTC) if resolved else None,
+    ))
+
+
+def test_retire_soft_wip_keeps_human_judged_and_clears_the_rest(db_sync):
+    wip = resolve_wip_tag_id(db_sync)
+    plain = _img(db_sync, "a" * 64)       # soft, never looked at → removed
+    confirmed = _img(db_sync, "b" * 64)   # soft + confirmed → kept as manual
+    kept = _img(db_sync, "c" * 64)        # soft + "Keep tag" in the strip → manual
+    pending = _img(db_sync, "d" * 64)     # soft + open card → tag and card removed
+    hard = _img(db_sync, "e" * 64)        # hard title tag + open card → untouched
+    for img in (plain, confirmed, kept, pending):
+        db_sync.execute(image_tag.insert().values(
+            image_record_id=img.id, tag_id=wip, source="wip_title_soft"))
+    db_sync.execute(image_tag.insert().values(
+        image_record_id=hard.id, tag_id=wip, source="wip_title"))
+    db_sync.add(TagPositiveConfirmation(image_record_id=confirmed.id, tag_id=wip))
+    _flag(db_sync, kept.id, wip, resolved=True)
+    _flag(db_sync, pending.id, wip, resolved=False)
+    _flag(db_sync, hard.id, wip, resolved=False)
+    db_sync.flush()
+
+    _retire()(db_sync.connection())
+    db_sync.expire_all()
+
+    assert _source(db_sync, plain.id, wip) is None
+    assert _source(db_sync, confirmed.id, wip) == "manual"
+    assert _source(db_sync, kept.id, wip) == "manual"
+    assert _source(db_sync, pending.id, wip) is None
+    assert _source(db_sync, hard.id, wip) == "wip_title"
+
+    assert _review(db_sync, pending.id, wip) is None
+    assert _review(db_sync, kept.id, wip) is not None     # resolved history stays
+    assert _review(db_sync, hard.id, wip) is not None     # its tag is still on
+    assert db_sync.execute(
+        select(image_tag.c.image_record_id).where(image_tag.c.source == "wip_title_soft")
+    ).first() is None
@@ -382,3 +382,84 @@ def test_external_links_not_duplicated_on_reimport(importer, import_layout):
    assert importer.session.execute(
        select(func.count()).select_from(ExternalLink)
    ).scalar_one() == 1
+
+
+def test_post_record_redates_images_linked_before_it(importer, import_layout):
+    """#4431: the native ingesters import a message's media before its record,
+    and only the record carries the date. The images start on their download
+    time; when the record lands they take the post's date."""
+    import_root, _ = import_layout
+    artist = Artist(name="Alice", slug="alice")
+    importer.session.add(artist)
+    importer.session.flush()
+    m = import_root / "Alice" / "20240301_123_01_art.jpg"
+    _split(m, "v")
+    _sidecar(m, {"category": "discord", "message_id": "123"})
+    r = importer.import_one(m)
+    assert r.status == "imported"
+    rec = importer.session.get(ImageRecord, r.image_id)
+    post = importer.session.execute(select(Post)).scalar_one()
+    assert post.post_date is None
+    download_time = rec.effective_date
+
+    sc = import_root / "Alice" / "20240301_123_post.json"
+    sc.write_text(json.dumps({
+        "category": "discord", "message_id": "123", "message": "",
+        "date": "2024-03-01T18:30:00.000000+00:00",
+    }))
+    assert importer.upsert_post_record(sc, artist=artist) is True
+    importer.session.expire_all()
+    rec = importer.session.get(ImageRecord, r.image_id)
+    post = importer.session.execute(select(Post)).scalar_one()
+    assert post.post_date is not None
+    assert post.post_date != download_time
+    assert rec.effective_date == post.post_date
+    assert rec.earliest_post_date == post.post_date
+
+
+def test_an_undated_post_is_dated_from_the_record_its_walk_left_on_disk(
+    importer, import_layout,
+):
+    """#4436: a walk killed before phase 3 wrote the message's record to disk
+    but never upserted it, and marked it seen, so no later tick fixed it. The
+    repair finds the record under the artist's folder and dates the post — and
+    its images — under the post's own source."""
+    from backend.app.services.post_record_repair import date_posts_from_records
+
+    import_root, images_root = import_layout
+    artist = Artist(name="Alice", slug="alice")
+    importer.session.add(artist)
+    importer.session.flush()
+    importer.session.add(Source(
+        artist_id=artist.id, platform="discord",
+        url="https://discord.com/channels/1/100",
+    ))
+    importer.session.flush()
+    m = import_root / "Alice" / "20240301_123_01_art.jpg"
+    _split(m, "v")
+    _sidecar(m, {"category": "discord", "message_id": "123"})
+    r = importer.import_one(m)
+    assert r.status == "imported"
+    post = importer.session.execute(select(Post)).scalar_one()
+    assert post.post_date is None and post.source_id is not None
+
+    channel = images_root / "alice" / "discord" / "rewards"
+    channel.mkdir(parents=True)
+    (channel / "20240301_123_post.json").write_text(json.dumps({
+        "category": "discord", "message_id": "123", "message": "",
+        "date": "2024-03-01T18:30:00.000000+00:00",
+    }))
+    (channel / "20240301_999_post.json").write_text("not json")  # skipped, not fatal
+
+    summary = date_posts_from_records(importer.session, importer, images_root)
+
+    assert summary == {"undated": 1, "dated": 1, "no_record": 0}
+    importer.session.expire_all()
+    post = importer.session.execute(select(Post)).scalar_one()
+    rec = importer.session.get(ImageRecord, r.image_id)
+    assert post.post_date is not None
+    assert rec.earliest_post_date == post.post_date
+    # Nothing left undated: the next sweep is an empty query.
+    assert date_posts_from_records(importer.session, importer, images_root) == {
+        "undated": 0, "dated": 0, "no_record": 0,
+    }
@@ -8,7 +8,7 @@ negative cases (substrings like ``swipe`` / ``wiped``) are the load-bearing ones
 """
 import pytest

-from backend.app.services.wip_title import matches_soft_wip_title, matches_wip_title
+from backend.app.services.wip_title import matches_wip_title


@pytest.mark.parametrize("title", [
@@ -48,29 +48,3 @@ def test_matches_positive(title):
 ])
 def test_matches_negative(title):
    assert matches_wip_title(title) is False
-
-
-@pytest.mark.parametrize("title", [
-    "quick sketch",
-    "Nami sketch",
-    "morning doodle",
-    "some doodles",
-    "sketches from today",
-    "a little scribble",
-    "SKETCH",
-])
-def test_soft_matches_positive(title):
-    assert matches_soft_wip_title(title) is True
-
-
-@pytest.mark.parametrize("title", [
-    None,
-    "",
-    "sketchbook tour",              # 'sketch' inside sketchbook — must NOT match
-    "kadoodle mascot",              # 'doodle' mid-word
-    "the final piece",
-    "WIP",                          # a HARD cue is not a SOFT cue
-    "prescribed colours",           # 'scrib' inside prescribed — must NOT match
-])
-def test_soft_matches_negative(title):
-    assert matches_soft_wip_title(title) is False
@@ -10,7 +10,6 @@ from backend.app.celery_app import celery
 from backend.app.models import Artist, ImageProvenance, ImageRecord, Post, Source
 from backend.app.models.tag import image_tag
 from backend.app.services.wip_title import (
-    WIP_TITLE_SOFT_SOURCE,
    apply_wip_image_tags,
    resolve_wip_tag_id,
 )
@@ -108,14 +107,3 @@ def test_backfill_tags_only_wip_titled_posts(db_sync):

    # Idempotent: a second sweep finds the tag already present and applies nothing.
    assert backfill_wip_title_tags.apply().get() == 0
-
-
-def test_apply_soft_source_stamps_wip_title_soft(db_sync):
-    # The soft tier (#1474) stamps a distinct provisional source.
-    tag_id = resolve_wip_tag_id(db_sync)
-    rec = _img(db_sync)
-    db_sync.commit()
-    assert apply_wip_image_tags(
-        db_sync, [rec.id], tag_id, source=WIP_TITLE_SOFT_SOURCE
-    ) == 1
-    assert _wip_source(db_sync, rec.id, tag_id) == "wip_title_soft"