feat(provenance): ProvenanceService.for_image (peer provenance rows)

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

backend/app/services/provenance_service.py

@@ -0,0 +1,67 @@
+"""Read-only provenance queries.
+
+Provenance is its own system, intentionally separate from the tag/ML
+system (see project_provenance_separation). This service joins
+ImageProvenance -> Post/Source/Artist and returns plain dicts. It never
+mutates and never imports tag/ML modules.
+"""
+
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from ..models import Artist, ImageProvenance, ImageRecord, Post, Source
+from ..utils.html_sanitize import sanitize_post_html
+
+
+def _post_dict(p: Post) -> dict:
+    return {
+        "id": p.id,
+        "external_post_id": p.external_post_id,
+        "url": p.post_url,
+        "title": p.post_title,
+        "date": p.post_date.isoformat() if p.post_date else None,
+        "description_html": sanitize_post_html(p.description),
+        "attachment_count": p.attachment_count,
+    }
+
+
+def _source_dict(s: Source) -> dict:
+    return {"id": s.id, "platform": s.platform, "url": s.url}
+
+
+def _artist_dict(a: Artist) -> dict:
+    return {"id": a.id, "name": a.name, "slug": a.slug}
+
+
+class ProvenanceService:
+    def __init__(self, session: AsyncSession):
+        self.session = session
+
+    async def for_image(self, image_id: int) -> dict | None:
+        rec = await self.session.get(ImageRecord, image_id)
+        if rec is None:
+            return None
+        stmt = (
+            select(ImageProvenance, Post, Source, Artist)
+            .join(Post, Post.id == ImageProvenance.post_id)
+            .join(Source, Source.id == ImageProvenance.source_id)
+            .join(Artist, Artist.id == Source.artist_id)
+            .where(ImageProvenance.image_record_id == image_id)
+            .order_by(ImageProvenance.captured_at.asc(),
+                      ImageProvenance.id.asc())
+        )
+        rows = (await self.session.execute(stmt)).all()
+        return {
+            "image_id": image_id,
+            "provenance": [
+                {
+                    "provenance_id": ip.id,
+                    "captured_at": ip.captured_at.isoformat()
+                    if ip.captured_at else None,
+                    "post": _post_dict(post),
+                    "source": _source_dict(src),
+                    "artist": _artist_dict(art),
+                }
+                for ip, post, src, art in rows
+            ],
+        }