refactor(sl): split overlay columns from column_overrides and enforce TS/Python wire contract

Overlay sources now have two distinct collections: `columns:` for computed
columns (requiring `expr` + `type`) and `column_overrides:` for metadata
patches to inherited manifest columns. Composing or loading an overlay that
mixes the two — or references an unknown column — fails with a typed error.

Introduce `ResolvedSemanticLayerSource` / `resolvedSourceSchema` /
`toResolvedWire` as the strict shape sent to the Python engine, and add a
schema contract test that diffs Zod against the Pydantic JSON schema dumped
by `python -m semantic_layer dump-schema`. `SourceDefinition` is now
`extra="forbid"` on the Python side.

`loadAllSources` surfaces per-file load errors instead of swallowing them,
so validation/query paths can report manifest shard parse failures.
This commit is contained in:
Andrey Avtomonov 2026-05-15 00:36:52 +02:00
parent 3e12a9fef4
commit f561bfa850
42 changed files with 847 additions and 193 deletions

View file

@ -148,11 +148,21 @@ class TestLoaderEdgeCases:
with open(Path(tmpdir) / "test.yaml", "w") as f:
yaml.dump(data, f)
loader = SourceLoader(tmpdir)
try:
sources = loader.load_all()
assert "test" in sources
except Exception:
pass
with pytest.raises(Exception, match="unknown_field"):
loader.load_all()
def test_source_requires_table_or_sql(self):
with tempfile.TemporaryDirectory() as tmpdir:
data = {
"name": "test",
"grain": ["id"],
"columns": [{"name": "id", "type": "number"}],
}
with open(Path(tmpdir) / "test.yaml", "w") as f:
yaml.dump(data, f)
loader = SourceLoader(tmpdir)
with pytest.raises(Exception, match="table.*sql"):
loader.load_file(Path(tmpdir) / "test.yaml")
def test_subdirectory_sources(self):
with tempfile.TemporaryDirectory() as tmpdir:

View file

@ -205,12 +205,15 @@ class TestValidateOverlay:
"descriptions": {"user": "Revenue-bearing orders"},
"grain": ["id"],
"measures": [{"name": "revenue", "expr": "sum(total)"}],
"column_overrides": [
{"name": "status", "descriptions": {"user": "Order lifecycle status"}}
],
"columns": [
{"name": "is_high_value", "expr": "total > 1000", "type": "boolean"}
],
"exclude_columns": ["status"],
}
errors = validate_overlay(data)
errors = validate_overlay(data, {"status", "total"})
assert errors == []
def test_validate_overlay_rejects_table(self):
@ -225,14 +228,13 @@ class TestValidateOverlay:
assert len(errors) == 1
assert "sql" in errors[0].lower()
def test_validate_overlay_rejects_type_without_expr(self):
def test_validate_overlay_rejects_column_without_expr(self):
data = {
"name": "orders",
"columns": [{"name": "status", "type": "string"}],
}
errors = validate_overlay(data)
assert len(errors) == 1
assert "type" in errors[0].lower()
assert "expr" in errors[0].lower()
def test_validate_overlay_allows_type_with_expr(self):
@ -243,6 +245,33 @@ class TestValidateOverlay:
errors = validate_overlay(data)
assert errors == []
def test_validate_overlay_rejects_column_override_structural_fields(self):
data = {
"name": "orders",
"column_overrides": [
{
"name": "status",
"description": "Status",
"type": "string",
"expr": "status",
}
],
}
errors = validate_overlay(data, {"status"})
assert len(errors) == 3
assert "descriptions" in errors[0]
assert "type" in errors[1]
assert "expr" in errors[2]
def test_validate_overlay_rejects_unknown_column_override(self):
data = {
"name": "orders",
"column_overrides": [{"name": "missing", "descriptions": {"user": "Nope"}}],
}
errors = validate_overlay(data, {"status"})
assert len(errors) == 1
assert "does not match" in errors[0]
# ── Two-Tier Loading Tests ─────────────────────────────────────────
@ -502,6 +531,77 @@ class TestTwoTierLoading:
assert hv.expr == "total > 1000"
assert hv.type == "boolean"
def test_overlay_column_overrides_patch_manifest_columns(self, tmp_path: Path):
schema_dir = tmp_path / "_schema"
_write_yaml(schema_dir / "public.yaml", _manifest_tables())
overlay = {
"name": "orders",
"column_overrides": [
{"name": "status", "descriptions": {"user": "Order lifecycle status"}}
],
}
_write_yaml(tmp_path / "orders.yaml", overlay)
_write_yaml(tmp_path / "customers.yaml", {"name": "customers"})
loader = SourceLoader(tmp_path)
sources = loader.load_all()
status = next(c for c in sources["orders"].columns if c.name == "status")
assert status.type == "string"
assert status.description == "Order lifecycle status"
assert status.descriptions == {"user": "Order lifecycle status"}
def test_overlay_rejects_unknown_column_override(self, tmp_path: Path):
schema_dir = tmp_path / "_schema"
_write_yaml(schema_dir / "public.yaml", _manifest_tables())
overlay = {
"name": "orders",
"column_overrides": [
{"name": "missing", "descriptions": {"user": "No such column"}}
],
}
_write_yaml(tmp_path / "orders.yaml", overlay)
_write_yaml(tmp_path / "customers.yaml", {"name": "customers"})
loader = SourceLoader(tmp_path)
with pytest.raises(ValueError, match="Column override 'missing'"):
loader.load_all()
def test_overlay_rejects_computed_column_name_collision(self, tmp_path: Path):
schema_dir = tmp_path / "_schema"
_write_yaml(schema_dir / "public.yaml", _manifest_tables())
overlay = {
"name": "orders",
"columns": [{"name": "status", "type": "string", "expr": "status"}],
}
_write_yaml(tmp_path / "orders.yaml", overlay)
_write_yaml(tmp_path / "customers.yaml", {"name": "customers"})
loader = SourceLoader(tmp_path)
with pytest.raises(ValueError, match="move it to 'column_overrides:'"):
loader.load_all()
def test_overlay_rejects_exclude_override_conflict(self, tmp_path: Path):
schema_dir = tmp_path / "_schema"
_write_yaml(schema_dir / "public.yaml", _manifest_tables())
overlay = {
"name": "orders",
"exclude_columns": ["status"],
"column_overrides": [
{"name": "status", "descriptions": {"user": "Hidden status"}}
],
}
_write_yaml(tmp_path / "orders.yaml", overlay)
_write_yaml(tmp_path / "customers.yaml", {"name": "customers"})
loader = SourceLoader(tmp_path)
with pytest.raises(ValueError, match="conflict with exclude_columns"):
loader.load_all()
def test_overlay_measures_set(self, tmp_path: Path):
schema_dir = tmp_path / "_schema"
_write_yaml(schema_dir / "public.yaml", _manifest_tables())