feat(catalog): preserve and display dataset value scores

backend/app/catalog/contracts.py

@@ -37,7 +37,7 @@ class CatalogFilters(Scope):
     field_type: str | None = None
     coverage_min: float | None = Field(default=None, ge=0, le=1)
     sort: Literal[
-        "id", "name", "category", "field_count", "coverage", "user_count", "alpha_count", "field_type"
+        "id", "name", "category", "field_count", "coverage", "user_count", "alpha_count", "field_type", "value_score"
     ] = "name"
     direction: Literal["asc", "desc"] = "asc"
     limit: int = Field(default=25, ge=1, le=100)
@@ -80,6 +80,7 @@ class EntryOutput(BaseModel):
     category: str | None
     subcategory: str | None
     field_type: str | None
+    value_score: float | None = None
     coverage: float | None
     user_count: int | None
     alpha_count: int | None

backend/app/catalog/sync.py

@@ -55,6 +55,7 @@ def normalize(raw, dataset_id):
         subcategory=label(raw.get("subcategory")),
         field_type=label(raw.get("type")) if dataset_id else None,
         coverage=coverage,
+        value_score=number(raw.get("valueScore")) if not dataset_id else None,
         user_count=number(raw.get("userCount"), True),
         alpha_count=number(raw.get("alphaCount"), True),
         field_count=number(raw.get("fieldCount"), True),

backend/app/models.py

@@ -357,6 +357,7 @@ class CatalogEntry(Base):
     subcategory: Mapped[str | None] = mapped_column(String(200))
     field_type: Mapped[str | None] = mapped_column(String(100))
     coverage: Mapped[float | None] = mapped_column(Float)
+    value_score: Mapped[float | None] = mapped_column(Float)
     user_count: Mapped[int | None] = mapped_column(Integer)
     alpha_count: Mapped[int | None] = mapped_column(Integer)
     field_count: Mapped[int | None] = mapped_column(Integer)

backend/migrations/versions/0009_dataset_value_score.py

@@ -0,0 +1,17 @@
+"""Preserve the upstream dataset value score; old snapshots remain unknown."""
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = "0009"
+down_revision = "0008"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    op.add_column("catalog_entries", sa.Column("value_score", sa.Float(), nullable=True))
+
+
+def downgrade():
+    op.drop_column("catalog_entries", "value_score")

backend/tests/catalog_fake.py

@@ -37,6 +37,7 @@ def catalog_response(request, fields=None):
                 "category": {"name": "基本面"},
                 "subcategory": {"name": "财务报表"},
                 "fieldCount": 123,
+                "valueScore": 2.0,
                 "description": "合成数据，仅用于验收",
             },
             {
@@ -45,6 +46,7 @@ def catalog_response(request, fields=None):
                 "category": {"name": "新闻"},
                 "subcategory": {"name": "情绪"},
                 "fieldCount": 3,
+                "valueScore": 0.0,
             },
             {"id": "TEST_UNKNOWN", "name": "TEST 未分类", "fieldCount": 0},
         ]

backend/tests/test_catalog.py

@@ -279,3 +279,17 @@ async def test_dynamic_platform_scopes_and_validation(catalog):
     runner.client.disconnect()
     assert (await client.get(BASE + "/scopes")).status_code == 409
     assert (await search(client))["total"] == 0
+
+
+async def test_dataset_value_score_survives_sync_and_sorts_null_last(catalog):
+    client, _, _ = catalog
+    assert (await sync(catalog))["status"] == "completed"
+    rows = (await search(client, sort="value_score", direction="desc"))["items"]
+    assert [(row["id"], row["value_score"]) for row in rows] == [
+        ("TEST_FIN", 2.0), ("TEST_NEWS", 0.0), ("TEST_UNKNOWN", None)
+    ]
+    rows = (await search(client, sort="value_score", direction="asc"))["items"]
+    assert [row["value_score"] for row in rows] == [0.0, 2.0, None]
+    assert (await search(client, "/datasets/TEST_FIN"))["value_score"] == 2.0
+    assert (await search(client, "/datasets/TEST_NEWS"))["value_score"] == 0.0
+    assert (await search(client, "/datasets/TEST_UNKNOWN"))["value_score"] is None