backend/app/domains/products/diff.py

@@ -44,6 +44,7 @@ class CatalogImage:
     source_url: str
     position: int
     alt_text: str | None
+    status: str = "pending"
 
 
 @dataclass

backend/app/domains/products/repo.py

@@ -91,7 +91,7 @@ def load_catalog(conn: psycopg.Connection, storefront_id: int) -> dict[str, Cata
             )
         )
     for row in conn.execute(
-        "SELECT i.product_id, i.id, i.source_url, i.position, i.alt_text"
+        "SELECT i.product_id, i.id, i.source_url, i.position, i.alt_text, i.status"
         " FROM product_image i"
         " JOIN product p ON p.id = i.product_id"
         " WHERE p.storefront_id = %s"
@@ -99,7 +99,8 @@ def load_catalog(conn: psycopg.Connection, storefront_id: int) -> dict[str, Cata
         (storefront_id,),
     ):
         by_id[row[0]].images.append(
-            CatalogImage(id=row[1], source_url=row[2], position=row[3], alt_text=row[4])
+            CatalogImage(id=row[1], source_url=row[2], position=row[3],
+                         alt_text=row[4], status=row[5])
         )
     return catalog
 

backend/app/domains/products/serialize.py

@@ -14,6 +14,7 @@ from collections.abc import Iterable, Iterator
 from decimal import Decimal
 
 from .diff import CatalogProduct
+from .hosted import EXPORT_RENDITION, image_url
 from .models import (
     IMAGE_COLUMNS,
     OPTION_VALUE_COLUMNS,
@@ -51,14 +52,14 @@ def _cell(value: object) -> str:
     return str(value)
 
 
-def catalog_to_csv(products: Iterable[CatalogProduct]) -> Iterator[str]:
+def catalog_to_csv(products: Iterable[CatalogProduct], base_url: str = "") -> Iterator[str]:
     """Stream canonical CSV text, header first, one product block at a time."""
     buf = io.StringIO()
     writer = csv.writer(buf)
     writer.writerow(HEADER)
     yield _drain(buf)
     for product in products:
-        for row in _product_rows(product):
+        for row in _product_rows(product, base_url):
             writer.writerow([row.get(col, "") for col in HEADER])
         yield _drain(buf)
 
@@ -70,7 +71,7 @@ def _drain(buf: io.StringIO) -> str:
     return text
 
 
-def _product_rows(product: CatalogProduct) -> list[dict[str, str]]:
+def _product_rows(product: CatalogProduct, base_url: str = "") -> list[dict[str, str]]:
     """The product's CSV rows (§6.5.1 grammar): product fields + option names on
     the first row; one variant per row; images interleaved; image-only rows when
     a product has more images than variants."""
@@ -90,12 +91,17 @@ def _product_rows(product: CatalogProduct) -> list[dict[str, str]]:
         if i < len(product.variants):
             _write_variant(row, product, product.variants[i])
         if i < len(product.images):
-            _write_image(row, product.images[i])
+            _write_image(row, product.images[i], base_url)
         rows.append(row)
     return rows
 
 
-def _write_image(row: dict[str, str], image) -> None:
+def _write_image(row: dict[str, str], image, base_url: str) -> None:
+    # Fetched images export the platform-hosted URL (INV-12/16); everything
+    # else keeps the original source_url so nothing is lost (§6.5.5).
+    if image.status == "fetched":
+        row["Image Src"] = image_url(base_url, image.id, EXPORT_RENDITION)
+    else:
         row["Image Src"] = image.source_url
     row["Image Position"] = str(image.position)
     if image.alt_text is not None:

backend/app/domains/products/service.py

@@ -12,7 +12,7 @@ from datetime import datetime, timezone
 
 import psycopg
 
-from app.platform import telemetry
+from app.platform import config, telemetry
 
 from . import codec, diff, repo, serialize, validate
 from .errors import (
@@ -242,7 +242,7 @@ def export_catalog(
         raise EmptyCatalog()
 
     def _stream() -> Iterator[str]:
-        yield from serialize.catalog_to_csv(snapshot)
+        yield from serialize.catalog_to_csv(snapshot, base_url=config.public_base_url())
         telemetry.emit(
             "catalog_exported",
             storefront_id=storefront_id,

backend/tests/test_products_serialize.py

@@ -104,6 +104,24 @@ def test_more_images_than_variants_emits_image_only_rows():
     assert [r["Image Src"] for r in rows] == ["https://x/a.jpg", "https://x/b.jpg", "https://x/c.jpg"]
 
 
+def test_fetched_image_serializes_hosted_detail_url():
+    product = CatalogProduct(
+        id=1, handle="lamp", title="Lamp", option_names=(None, None, None),
+        fields={"title": "Lamp", "status": "active"},
+        variants=[CatalogVariant(id=1, options=(None, None, None), position=1, fields={})],
+        images=[
+            CatalogImage(id=55, source_url="https://m.example/a.png", position=1,
+                         alt_text=None, status="fetched"),
+            CatalogImage(id=56, source_url="https://m.example/b.png", position=2,
+                         alt_text=None, status="failed"),
+        ],
+    )
+    rows = list(serialize._product_rows(product, base_url="https://shop.test"))
+    srcs = [r.get("Image Src") for r in rows if r.get("Image Src")]
+    assert "https://shop.test/api/products/images/55/detail" in srcs  # fetched -> hosted
+    assert "https://m.example/b.png" in srcs                          # failed -> source kept
+
+
 import random
 
 from app.domains.products import codec, diff, validate