feat: add ArtifactRepository with batch DB operations

Add optimized database operations for artifact storage:
- Atomic upserts using ON CONFLICT for artifact creation
- Batch inserts for dependencies to eliminate N+1 queries
- Joined queries for cached URL lookups
- All methods include comprehensive unit tests

backend/tests/unit/test_db_utils.py

@@ -0,0 +1,167 @@
+"""Tests for database utility functions."""
+import pytest
+from unittest.mock import MagicMock, patch
+
+
+class TestArtifactRepository:
+    """Tests for ArtifactRepository."""
+
+    def test_batch_dependency_values_formatting(self):
+        """batch_upsert_dependencies should format values correctly."""
+        from backend.app.db_utils import ArtifactRepository
+
+        deps = [
+            ("_pypi", "numpy", ">=1.21.0"),
+            ("_pypi", "requests", "*"),
+            ("myproject", "mylib", "==1.0.0"),
+        ]
+
+        values = ArtifactRepository._format_dependency_values("abc123", deps)
+
+        assert len(values) == 3
+        assert values[0] == {
+            "artifact_id": "abc123",
+            "dependency_project": "_pypi",
+            "dependency_package": "numpy",
+            "version_constraint": ">=1.21.0",
+        }
+        assert values[2]["dependency_project"] == "myproject"
+
+    def test_empty_dependencies_returns_empty_list(self):
+        """Empty dependency list should return empty values."""
+        from backend.app.db_utils import ArtifactRepository
+
+        values = ArtifactRepository._format_dependency_values("abc123", [])
+
+        assert values == []
+
+    def test_format_dependency_values_preserves_special_characters(self):
+        """Version constraints with special characters should be preserved."""
+        from backend.app.db_utils import ArtifactRepository
+
+        deps = [
+            ("_pypi", "package-name", ">=1.0.0,<2.0.0"),
+            ("_pypi", "another_pkg", "~=1.4.2"),
+        ]
+
+        values = ArtifactRepository._format_dependency_values("hash123", deps)
+
+        assert values[0]["version_constraint"] == ">=1.0.0,<2.0.0"
+        assert values[1]["version_constraint"] == "~=1.4.2"
+
+    def test_batch_upsert_dependencies_returns_zero_for_empty(self):
+        """batch_upsert_dependencies should return 0 for empty list without DB call."""
+        from backend.app.db_utils import ArtifactRepository
+
+        mock_db = MagicMock()
+        repo = ArtifactRepository(mock_db)
+
+        result = repo.batch_upsert_dependencies("abc123", [])
+
+        assert result == 0
+        # Verify no DB operations were performed
+        mock_db.execute.assert_not_called()
+
+    def test_get_or_create_artifact_builds_correct_statement(self):
+        """get_or_create_artifact should use ON CONFLICT DO UPDATE."""
+        from backend.app.db_utils import ArtifactRepository
+        from backend.app.models import Artifact
+
+        mock_db = MagicMock()
+        mock_result = MagicMock()
+        mock_artifact = MagicMock()
+        mock_artifact.ref_count = 1
+        mock_result.scalar_one.return_value = mock_artifact
+        mock_db.execute.return_value = mock_result
+
+        repo = ArtifactRepository(mock_db)
+        artifact, created = repo.get_or_create_artifact(
+            sha256="abc123def456",
+            size=1024,
+            filename="test.whl",
+            content_type="application/zip",
+        )
+
+        assert mock_db.execute.called
+        assert created is True
+        assert artifact == mock_artifact
+
+    def test_get_or_create_artifact_existing_not_created(self):
+        """get_or_create_artifact should return created=False for existing artifact."""
+        from backend.app.db_utils import ArtifactRepository
+
+        mock_db = MagicMock()
+        mock_result = MagicMock()
+        mock_artifact = MagicMock()
+        mock_artifact.ref_count = 5  # Existing artifact with ref_count > 1
+        mock_result.scalar_one.return_value = mock_artifact
+        mock_db.execute.return_value = mock_result
+
+        repo = ArtifactRepository(mock_db)
+        artifact, created = repo.get_or_create_artifact(
+            sha256="abc123def456",
+            size=1024,
+            filename="test.whl",
+        )
+
+        assert created is False
+
+    def test_get_cached_url_with_artifact_returns_tuple(self):
+        """get_cached_url_with_artifact should return (CachedUrl, Artifact) tuple."""
+        from backend.app.db_utils import ArtifactRepository
+
+        mock_db = MagicMock()
+        mock_cached_url = MagicMock()
+        mock_artifact = MagicMock()
+        mock_db.query.return_value.join.return_value.filter.return_value.first.return_value = (
+            mock_cached_url,
+            mock_artifact,
+        )
+
+        repo = ArtifactRepository(mock_db)
+        result = repo.get_cached_url_with_artifact("url_hash_123")
+
+        assert result == (mock_cached_url, mock_artifact)
+
+    def test_get_cached_url_with_artifact_returns_none_when_not_found(self):
+        """get_cached_url_with_artifact should return None when URL not cached."""
+        from backend.app.db_utils import ArtifactRepository
+
+        mock_db = MagicMock()
+        mock_db.query.return_value.join.return_value.filter.return_value.first.return_value = None
+
+        repo = ArtifactRepository(mock_db)
+        result = repo.get_cached_url_with_artifact("nonexistent_hash")
+
+        assert result is None
+
+    def test_get_artifact_dependencies_returns_list(self):
+        """get_artifact_dependencies should return list of dependencies."""
+        from backend.app.db_utils import ArtifactRepository
+
+        mock_db = MagicMock()
+        mock_dep1 = MagicMock()
+        mock_dep2 = MagicMock()
+        mock_db.query.return_value.filter.return_value.all.return_value = [
+            mock_dep1,
+            mock_dep2,
+        ]
+
+        repo = ArtifactRepository(mock_db)
+        result = repo.get_artifact_dependencies("artifact_hash_123")
+
+        assert len(result) == 2
+        assert result[0] == mock_dep1
+        assert result[1] == mock_dep2
+
+    def test_get_artifact_dependencies_returns_empty_list(self):
+        """get_artifact_dependencies should return empty list when no dependencies."""
+        from backend.app.db_utils import ArtifactRepository
+
+        mock_db = MagicMock()
+        mock_db.query.return_value.filter.return_value.all.return_value = []
+
+        repo = ArtifactRepository(mock_db)
+        result = repo.get_artifact_dependencies("artifact_without_deps")
+
+        assert result == []