fix(migrators): tag_apply phase 4 now covers deviantart + pixiv (was silently dropping IR PostMetadata from those platforms)

_PLATFORM_PROFILE_URL had only patreon/subscribestar/hentaifoundry but
FC's extension_service.py recognizes 5 platforms. Any IR PostMetadata
with platform=deviantart or pixiv fell through _profile_url returning
None and the entry was silently skipped — explaining operator's
2026-05-25 finding that IR-migrated images had tags but no provenance
for the deviantart + pixiv subscriptions.

Pixiv caveat noted in comment: real profile URL takes numeric user_id
(https://www.pixiv.net/users/12345) but IR's PostMetadata.artist
stores display name. We slug the name and use it as if it were the id
so the artist->post->image linkage survives migration; the resulting
Source.url won't resolve in a browser and operator can fix via
Settings -> Subscriptions later if they want.

To recover existing IR-migrated state: re-run /api/migrate/tag_apply
on the existing manifest. Phase 4 is idempotent; new posts get
inserted only for the previously-skipped platforms.

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

backend/app/services/migrators/tag_apply.py

@@ -37,13 +37,25 @@ from ...utils.slug import slugify
 from .ir_ingest import manifest_path
 
 # Per-platform artist-profile URL — used as Source.url when restoring
-# IR PostMetadata into FC. Keep this table in sync with
+# IR PostMetadata into FC. Must cover every platform that
-# backend/app/services/extension_service.py:_PLATFORM_PATTERNS and
+# backend/app/services/extension_service.py:_PLATFORM_PATTERNS
-# extension/lib/platforms.js.
+# recognizes; an entry missing here silently drops ALL PostMetadata for
+# that platform during phase 4 (operator hit this 2026-05-25:
+# DeviantArt + Pixiv posts in the IR migration produced empty
+# ImageProvenance because they fell through this table).
+#
+# Pixiv caveat: the real profile URL takes a numeric user_id
+# (https://www.pixiv.net/users/12345), but IR's PostMetadata.artist
+# stores the display name not the id. We use the slugified name here
+# so we preserve the artist→post→image linkage; the resulting Source.url
+# won't resolve in a browser and the operator may want to manually fix
+# it via Settings → Subscriptions once the migration lands.
 _PLATFORM_PROFILE_URL = {
     "patreon":       "https://www.patreon.com/{slug}",
     "subscribestar": "https://www.subscribestar.com/{slug}",
     "hentaifoundry": "https://www.hentai-foundry.com/user/{slug}",
+    "deviantart":    "https://www.deviantart.com/{slug}",
+    "pixiv":         "https://www.pixiv.net/users/{slug}",
 }
 
 

tests/test_tag_apply.py

@@ -281,6 +281,42 @@ async def test_image_posts_unknown_platform_skipped(db, tmp_path):
     assert src_count == 0
 
 
+@pytest.mark.parametrize("platform,expected_url", [
+    ("deviantart", "https://www.deviantart.com/maewix"),
+    ("pixiv",      "https://www.pixiv.net/users/maewix"),
+])
+@pytest.mark.asyncio
+async def test_image_posts_extended_platforms_create_source(
+    db, tmp_path, platform, expected_url,
+):
+    """Regression for 2026-05-25 operator-reported bug: phase 4's
+    _PLATFORM_PROFILE_URL had only patreon/subscribestar/hentaifoundry,
+    silently dropping deviantart + pixiv PostMetadata from the IR migration."""
+    sha = f"{platform[0]}" * 64
+    await _seed_image(db, sha, suffix=f"_{platform}")
+    await db.commit()
+
+    _write_manifest(tmp_path, image_posts=[
+        {**_POST_ENTRY, "platform": platform, "image_sha256s": [sha]},
+    ])
+
+    result = await tag_apply.apply_async(db, images_root=tmp_path, dry_run=False)
+    assert result["counts"]["rows_inserted"] >= 1
+
+    src_url = (await db.execute(
+        select(Source.url).where(Source.platform == platform)
+    )).scalar_one()
+    assert src_url == expected_url
+
+    # ImageProvenance row was created.
+    prov_count = (await db.execute(
+        select(func.count(ImageProvenance.id))
+        .join(Source, Source.id == ImageProvenance.source_id)
+        .where(Source.platform == platform)
+    )).scalar_one()
+    assert prov_count == 1
+
+
 @pytest.mark.asyncio
 async def test_image_posts_dry_run_makes_no_writes(db, tmp_path):
     sha = "2" * 64