fix(importer): Source = one per (artist, platform), not one per post — filesystem importer's sidecar paths now reuse the artist's existing subscription Source (or create one synthetic anchor with enabled=False) instead of fabricating a new Source per post URL. Alembic 0022 consolidates existing per-post Sources to canonical (prefers campaign URL; falls back to sidecar:<platform>:<slug>) and re-parents Posts + ImageProvenance, merging Post collisions.

Operator-flagged 2026-05-26: Atole artist detail page showed 406 Sources where 1 was right.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

alembic/versions/0022_source_per_artist_platform.py

@@ -0,0 +1,181 @@
+"""source-collapse: one Source per (artist, platform) — consolidate junk per-post Sources
+
+Revision ID: 0022
+Revises: 0021
+Create Date: 2026-05-26
+
+Closes the operator-flagged 2026-05-26 issue where the filesystem importer
+called _find_or_create_source(url=sd.post_url), creating one Source row per
+imported post URL. Operator's Atole artist had 406 Source rows where there
+should have been 1 (the /cw/Atole subscription Source).
+
+Source represents a subscription feed (one per artist+platform — the
+gallery-dl URL polled by the FC-3 downloader). Posts hang off it. The
+filesystem importer was misusing Source as a per-post key.
+
+Migration steps per (artist_id, platform) group with >1 Source:
+  1. Pick canonical — prefer a URL NOT matching '/posts/<id>$' (real
+     campaign URL like /cw/Atole); else min(id).
+  2. Reparent Posts and ImageProvenance off the other Sources onto canonical.
+  3. Merge any Posts that collide on (canonical_source_id, external_post_id)
+     by repointing ImageProvenance + ImageRecord.primary_post_id to the
+     earliest Post, dedupe ImageProvenance, delete the loser Posts.
+  4. Delete the orphan Source rows.
+  5. If the canonical Source's URL still looks like a per-post URL (no
+     campaign URL existed among candidates), rewrite it to
+     'sidecar:<platform>:<artist_slug>' so the artist detail page shows
+     something readable.
+"""
+from typing import Sequence, Union
+
+from alembic import op
+from sqlalchemy import text
+
+revision: str = "0022"
+down_revision: Union[str, None] = "0021"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+_POST_URL_RE = r"/posts/[^/]+$"
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+
+    # Find (artist_id, platform) groups with > 1 Source row.
+    groups = conn.execute(text("""
+        SELECT artist_id, platform
+        FROM source
+        GROUP BY artist_id, platform
+        HAVING COUNT(*) > 1
+    """)).fetchall()
+
+    for artist_id, platform in groups:
+        rows = conn.execute(
+            text("""
+                SELECT id, url FROM source
+                WHERE artist_id = :a AND platform = :p
+                ORDER BY id ASC
+            """),
+            {"a": artist_id, "p": platform},
+        ).fetchall()
+
+        # Canonical: first row whose URL doesn't look like a per-post URL;
+        # else min(id).
+        canonical_id = None
+        for sid, url in rows:
+            if not _matches_post_url(url):
+                canonical_id = sid
+                break
+        if canonical_id is None:
+            canonical_id = rows[0][0]
+
+        other_ids = [sid for sid, _ in rows if sid != canonical_id]
+        if not other_ids:
+            continue
+
+        # Reparent Posts off the other Sources.
+        conn.execute(
+            text("""
+                UPDATE post SET source_id = :canonical
+                WHERE source_id = ANY(:others)
+            """),
+            {"canonical": canonical_id, "others": other_ids},
+        )
+        # Reparent ImageProvenance.source_id similarly (denormalized FK).
+        conn.execute(
+            text("""
+                UPDATE image_provenance SET source_id = :canonical
+                WHERE source_id = ANY(:others)
+            """),
+            {"canonical": canonical_id, "others": other_ids},
+        )
+
+        # Merge any Posts colliding on (canonical, external_post_id) after
+        # reparent. In practice within a single (artist, platform) group
+        # these should be rare — each gallery-dl post has a unique id — but
+        # safe to handle.
+        post_collisions = conn.execute(
+            text("""
+                SELECT external_post_id, ARRAY_AGG(id ORDER BY id) AS ids
+                FROM post
+                WHERE source_id = :canonical
+                GROUP BY external_post_id
+                HAVING COUNT(*) > 1
+            """),
+            {"canonical": canonical_id},
+        ).fetchall()
+        for _epid, post_ids in post_collisions:
+            keep = post_ids[0]
+            drops = post_ids[1:]
+            conn.execute(
+                text("""
+                    UPDATE image_provenance SET post_id = :keep
+                    WHERE post_id = ANY(:drops)
+                """),
+                {"keep": keep, "drops": drops},
+            )
+            conn.execute(
+                text("""
+                    UPDATE image_record SET primary_post_id = :keep
+                    WHERE primary_post_id = ANY(:drops)
+                """),
+                {"keep": keep, "drops": drops},
+            )
+            # Repointed provenance rows may now collide on
+            # uq_image_provenance_image_post (alembic 0021). Same dedupe
+            # pattern: keep min(id) per (image_record_id, post_id).
+            conn.execute(text("""
+                DELETE FROM image_provenance ip1
+                USING image_provenance ip2
+                WHERE ip1.image_record_id = ip2.image_record_id
+                  AND ip1.post_id = ip2.post_id
+                  AND ip1.id > ip2.id
+            """))
+            conn.execute(
+                text("DELETE FROM post WHERE id = ANY(:drops)"),
+                {"drops": drops},
+            )
+
+        # Drop the orphan Sources.
+        conn.execute(
+            text("DELETE FROM source WHERE id = ANY(:others)"),
+            {"others": other_ids},
+        )
+
+        # If the canonical's URL still looks per-post (no campaign URL
+        # existed among the candidates), rewrite to a synthetic anchor so
+        # the artist detail page renders something readable.
+        canonical_url = conn.execute(
+            text("SELECT url FROM source WHERE id = :id"),
+            {"id": canonical_id},
+        ).scalar_one()
+        if _matches_post_url(canonical_url):
+            slug = conn.execute(
+                text("SELECT slug FROM artist WHERE id = :id"),
+                {"id": artist_id},
+            ).scalar_one()
+            conn.execute(
+                text("""
+                    UPDATE source
+                    SET url = :new_url, enabled = false
+                    WHERE id = :id
+                """),
+                {
+                    "id": canonical_id,
+                    "new_url": f"sidecar:{platform}:{slug}",
+                },
+            )
+
+
+def downgrade() -> None:
+    # Lossy migration — orphan Sources deleted, Posts reparented, Posts
+    # merged. No safe downgrade. If you need to roll back the schema
+    # invariant, fork from 0021 and re-run filesystem imports.
+    pass
+
+
+def _matches_post_url(url: str) -> bool:
+    """True if url ends with /posts/<token> (gallery-dl-style per-post URL)."""
+    import re
+    return bool(re.search(_POST_URL_RE, url or ""))

backend/app/services/importer.py

@@ -247,6 +247,62 @@ class Importer:
                 )
             ).scalar_one()
 
+    def _source_for_sidecar(
+        self, *, artist_id: int, platform: str, artist_slug: str,
+    ) -> Source:
+        """Filesystem-import sidecar Source resolver.
+
+        Source represents a subscription feed (one per artist+platform — the
+        gallery-dl URL polled by the FC-3 downloader). The filesystem importer
+        used to call _find_or_create_source(url=sd.post_url), which created
+        one Source row per post URL — 100s of junk Sources per artist, all
+        with enabled=True, polluting the artist detail page and tricking the
+        subscription checker into trying to poll patreon post URLs as feeds.
+        Operator-flagged 2026-05-26.
+
+        New behaviour: if any Source row exists for (artist_id, platform),
+        reuse it regardless of its URL — the artist's real subscription Source
+        (created by the downloader / extension / UI) is the canonical
+        attachment point for filesystem-imported posts. If none exists, create
+        ONE synthetic anchor with url='sidecar:<platform>:<artist_slug>' and
+        enabled=False (so the subscription checker doesn't poll it).
+        """
+        existing = self.session.execute(
+            select(Source)
+            .where(
+                Source.artist_id == artist_id,
+                Source.platform == platform,
+            )
+            .order_by(Source.id.asc())
+            .limit(1)
+        ).scalar_one_or_none()
+        if existing is not None:
+            return existing
+        synthetic_url = f"sidecar:{platform}:{artist_slug}"
+        sp = self.session.begin_nested()
+        try:
+            row = Source(
+                artist_id=artist_id,
+                platform=platform,
+                url=synthetic_url,
+                enabled=False,
+            )
+            self.session.add(row)
+            self.session.flush()
+            sp.commit()
+            return row
+        except IntegrityError:
+            sp.rollback()
+            return self.session.execute(
+                select(Source)
+                .where(
+                    Source.artist_id == artist_id,
+                    Source.platform == platform,
+                )
+                .order_by(Source.id.asc())
+                .limit(1)
+            ).scalar_one()
+
     def _find_or_create_post(
         self, *, source_id: int, external_post_id: str,
     ) -> Post:
@@ -315,9 +371,8 @@ class Importer:
             return None
         sd = parse_sidecar(data)
         platform = sd.platform or "unknown"
-        url = sd.post_url or f"sidecar:{platform}"
+        src = self._source_for_sidecar(
-        src = self._find_or_create_source(
+            artist_id=artist.id, platform=platform, artist_slug=artist.slug,
-            artist_id=artist.id, platform=platform, url=url,
         )
         epid = sd.external_post_id or sc.stem
         return self._find_or_create_post(
@@ -763,9 +818,9 @@ class Importer:
             src = explicit_source
         else:
             platform = sd.platform or "unknown"
-            url = sd.post_url or f"sidecar:{platform}"
+            src = self._source_for_sidecar(
-            src = self._find_or_create_source(
+                artist_id=artist.id, platform=platform,
-                artist_id=artist.id, platform=platform, url=url,
+                artist_slug=artist.slug,
             )
 
         epid = sd.external_post_id or sc.stem

tests/test_importer_upsert_helpers.py

@@ -145,3 +145,68 @@ def test_find_or_create_source_recovers_from_integrity_error(
         artist_id=artist_row.id, platform="patreon", url=canonical_url,
     )
     assert recovered.id == pre_existing.id
+
+
+def test_source_for_sidecar_reuses_existing_subscription(
+    importer, artist_row, db_sync,
+):
+    """The filesystem-import sidecar resolver should attach to whatever
+    Source already exists for (artist, platform) — the canonical subscription
+    Source — regardless of its URL. Without this, every imported post
+    spawned its own Source row.
+    """
+    canonical = Source(
+        artist_id=artist_row.id, platform="patreon",
+        url="https://www.patreon.com/cw/testartist", enabled=True,
+    )
+    db_sync.add(canonical)
+    db_sync.flush()
+
+    resolved = importer._source_for_sidecar(
+        artist_id=artist_row.id, platform="patreon",
+        artist_slug=artist_row.slug,
+    )
+    assert resolved.id == canonical.id
+
+
+def test_source_for_sidecar_creates_synthetic_anchor_when_none_exists(
+    importer, artist_row, db_sync,
+):
+    """No subscription Source for this (artist, platform) yet. The helper
+    creates one synthetic anchor (enabled=False, url='sidecar:<plat>:<slug>')
+    so subsequent imports reuse it instead of spawning per-post Sources.
+    """
+    resolved = importer._source_for_sidecar(
+        artist_id=artist_row.id, platform="pixiv",
+        artist_slug=artist_row.slug,
+    )
+    assert resolved.url == f"sidecar:pixiv:{artist_row.slug}"
+    assert resolved.enabled is False
+    assert resolved.artist_id == artist_row.id
+    assert resolved.platform == "pixiv"
+
+    # Second call returns the same row (no new Source spawned).
+    again = importer._source_for_sidecar(
+        artist_id=artist_row.id, platform="pixiv",
+        artist_slug=artist_row.slug,
+    )
+    assert again.id == resolved.id
+
+
+def test_source_for_sidecar_distinct_platforms_distinct_anchors(
+    importer, artist_row, db_sync,
+):
+    """One synthetic anchor per (artist, platform). Different platforms get
+    different anchors even when no campaign Source exists for either.
+    """
+    p = importer._source_for_sidecar(
+        artist_id=artist_row.id, platform="patreon",
+        artist_slug=artist_row.slug,
+    )
+    x = importer._source_for_sidecar(
+        artist_id=artist_row.id, platform="pixiv",
+        artist_slug=artist_row.slug,
+    )
+    assert p.id != x.id
+    assert p.platform == "patreon"
+    assert x.platform == "pixiv"