Fix review issues: tags validation, size nullability, type annotation, hash mismatch check, and add tag histogram tests

- Remove contradictory min_length=1 from CreateFromHashBody.tags default
- Restore size field to int|None=None for proper null semantics
- Add Union type annotation to _build_asset_response result param
- Add hash mismatch validation on idempotent upload path (409 HASH_MISMATCH)
- Add unit tests for list_tag_histogram service function

Amp-Thread-ID: https://ampcode.com/threads/T-019cd993-f43c-704e-b3d7-6cfc3d4d4a80
Co-authored-by: Amp <amp@ampcode.com>

app/assets/api/routes.py

@@ -13,6 +13,7 @@ from pydantic import ValidationError
 import folder_paths
 from app import user_manager
 from app.assets.api import schemas_in, schemas_out
+from app.assets.services import schemas
 from app.assets.api.schemas_in import (
     AssetValidationError,
     UploadError,
@@ -123,7 +124,7 @@ def _validate_sort_field(requested: str | None) -> str:
     return "created_at"
 
 
-def _build_asset_response(result) -> schemas_out.Asset:
+def _build_asset_response(result: schemas.AssetDetailResult | schemas.UploadResult) -> schemas_out.Asset:
     """Build an Asset response from a service result."""
     preview_url = None
     if result.ref.preview_id:
@@ -132,7 +133,7 @@ def _build_asset_response(result) -> schemas_out.Asset:
         id=result.ref.id,
         name=result.ref.name,
         asset_hash=result.asset.hash if result.asset else None,
-        size=int(result.asset.size_bytes) if result.asset else 0,
+        size=int(result.asset.size_bytes) if result.asset else None,
         mime_type=result.asset.mime_type if result.asset else None,
         tags=result.tags,
         preview_url=preview_url,
@@ -386,6 +387,14 @@ async def upload_asset(request: web.Request) -> web.Response:
                 owner_id=owner_id,
             )
             if existing:
+                # Validate that uploaded content matches existing asset
+                if spec.hash and existing.asset and existing.asset.hash != spec.hash:
+                    delete_temp_file_if_exists(parsed.tmp_path)
+                    return _build_error_response(
+                        409,
+                        "HASH_MISMATCH",
+                        "Uploaded file hash does not match existing asset.",
+                    )
                 delete_temp_file_if_exists(parsed.tmp_path)
                 asset = _build_asset_response(existing)
                 payload_out = schemas_out.AssetCreated(

app/assets/api/schemas_in.py

@@ -121,7 +121,7 @@ class CreateFromHashBody(BaseModel):
 
     hash: str
     name: str | None = None
-    tags: list[str] = Field(default_factory=list, min_length=1)
+    tags: list[str] = Field(default_factory=list)
     user_metadata: dict[str, Any] = Field(default_factory=dict)
     mime_type: str | None = None
 

app/assets/api/schemas_out.py

@@ -8,7 +8,7 @@ class Asset(BaseModel):
     id: str
     name: str
     asset_hash: str | None = None
-    size: int = 0
+    size: int | None = None
     mime_type: str | None = None
     tags: list[str] = Field(default_factory=list)
     preview_url: str | None = None

tests-unit/assets_test/services/test_tag_histogram.py

@@ -0,0 +1,123 @@
+"""Tests for list_tag_histogram service function."""
+from sqlalchemy.orm import Session
+
+from app.assets.database.models import Asset, AssetReference
+from app.assets.database.queries import ensure_tags_exist, add_tags_to_reference
+from app.assets.helpers import get_utc_now
+from app.assets.services.tagging import list_tag_histogram
+
+
+def _make_asset(session: Session, hash_val: str = "blake3:test") -> Asset:
+    asset = Asset(hash=hash_val, size_bytes=1024)
+    session.add(asset)
+    session.flush()
+    return asset
+
+
+def _make_reference(
+    session: Session,
+    asset: Asset,
+    name: str = "test",
+    owner_id: str = "",
+) -> AssetReference:
+    now = get_utc_now()
+    ref = AssetReference(
+        owner_id=owner_id,
+        name=name,
+        asset_id=asset.id,
+        created_at=now,
+        updated_at=now,
+        last_access_time=now,
+    )
+    session.add(ref)
+    session.flush()
+    return ref
+
+
+class TestListTagHistogram:
+    def test_returns_counts_for_all_tags(self, mock_create_session, session: Session):
+        ensure_tags_exist(session, ["alpha", "beta"])
+        a1 = _make_asset(session, "blake3:aaa")
+        r1 = _make_reference(session, a1, name="r1")
+        add_tags_to_reference(session, reference_id=r1.id, tags=["alpha", "beta"])
+
+        a2 = _make_asset(session, "blake3:bbb")
+        r2 = _make_reference(session, a2, name="r2")
+        add_tags_to_reference(session, reference_id=r2.id, tags=["alpha"])
+        session.commit()
+
+        result = list_tag_histogram()
+
+        assert result["alpha"] == 2
+        assert result["beta"] == 1
+
+    def test_empty_when_no_assets(self, mock_create_session, session: Session):
+        ensure_tags_exist(session, ["unused"])
+        session.commit()
+
+        result = list_tag_histogram()
+
+        assert result == {}
+
+    def test_include_tags_filter(self, mock_create_session, session: Session):
+        ensure_tags_exist(session, ["models", "loras", "input"])
+        a1 = _make_asset(session, "blake3:aaa")
+        r1 = _make_reference(session, a1, name="r1")
+        add_tags_to_reference(session, reference_id=r1.id, tags=["models", "loras"])
+
+        a2 = _make_asset(session, "blake3:bbb")
+        r2 = _make_reference(session, a2, name="r2")
+        add_tags_to_reference(session, reference_id=r2.id, tags=["input"])
+        session.commit()
+
+        result = list_tag_histogram(include_tags=["models"])
+
+        # Only r1 has "models", so only its tags appear
+        assert "models" in result
+        assert "loras" in result
+        assert "input" not in result
+
+    def test_exclude_tags_filter(self, mock_create_session, session: Session):
+        ensure_tags_exist(session, ["models", "loras", "input"])
+        a1 = _make_asset(session, "blake3:aaa")
+        r1 = _make_reference(session, a1, name="r1")
+        add_tags_to_reference(session, reference_id=r1.id, tags=["models", "loras"])
+
+        a2 = _make_asset(session, "blake3:bbb")
+        r2 = _make_reference(session, a2, name="r2")
+        add_tags_to_reference(session, reference_id=r2.id, tags=["input"])
+        session.commit()
+
+        result = list_tag_histogram(exclude_tags=["models"])
+
+        # r1 excluded, only r2's tags remain
+        assert "input" in result
+        assert "loras" not in result
+
+    def test_name_contains_filter(self, mock_create_session, session: Session):
+        ensure_tags_exist(session, ["alpha", "beta"])
+        a1 = _make_asset(session, "blake3:aaa")
+        r1 = _make_reference(session, a1, name="my_model.safetensors")
+        add_tags_to_reference(session, reference_id=r1.id, tags=["alpha"])
+
+        a2 = _make_asset(session, "blake3:bbb")
+        r2 = _make_reference(session, a2, name="picture.png")
+        add_tags_to_reference(session, reference_id=r2.id, tags=["beta"])
+        session.commit()
+
+        result = list_tag_histogram(name_contains="model")
+
+        assert "alpha" in result
+        assert "beta" not in result
+
+    def test_limit_caps_results(self, mock_create_session, session: Session):
+        tags = [f"tag{i}" for i in range(10)]
+        ensure_tags_exist(session, tags)
+        a = _make_asset(session, "blake3:aaa")
+        r = _make_reference(session, a, name="r1")
+        add_tags_to_reference(session, reference_id=r.id, tags=tags)
+        session.commit()
+
+        result = list_tag_histogram(limit=3)
+
+        assert len(result) == 3