mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-07 07:55:13 +02:00
* fix(context): merge overlay columns onto manifest columns by name composeOverlay was appending overlay columns to the manifest column list, producing duplicate entries when dbt/metabase overlays declared a column just to attach descriptions. The duplicates carried no `type`, so the pydantic SourceDefinition rejected them at semantic-query time and broke `ktx sl query` for every overlay-backed measure. Now overlay columns match base columns by name (case-insensitive): same-name entries merge onto the manifest (overlay fields win, type/role fall back to the base, descriptions merge per source key) and only new names append. * 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. * fix(context): make scan description generation resilient and quiet A transient sampleTable failure during ingest used to take out every table in a connection: generateTableDescription returned a hardcoded 'Table not found' string into descriptions.ai, and KtxDescriptionGenerator was constructed without a logger, so the failure left no trail anywhere. - sampleTable / sampleColumn calls retry 3x with 200/400/800ms backoff, honouring KtxScanContext.signal via a new KtxAbortedError. - On retry exhaustion or missing capability, table generation falls back to a metadata-only prompt built from column name / native type / comment / rawDescriptions. The column path follows the same rule -- call the LLM when any of samples or rawDescriptions are available; skip only when both are absent. - Logger is now threaded from KtxScanContext into the generator. Failures emit structured KtxScanWarning entries (new description_fallback_used code, plus existing sampling_failed / enrichment_failed / connector_capability_missing). ktx scan groups warnings by code so a batch of identical failures collapses to one summary line plus sample. - Returns null on failure instead of the 'Table not found' sentinel; the manifest writer's existing guard already skips empty descriptions, so schema YAML no longer carries misleading text. SCAN_MANAGED_DESCRIPTION_KEYS already strips stale 'ai' on merge, so existing YAML clears on next run. Also suppress AI SDK v6 'system in messages' warning: pull system messages out of KtxMessageBuilder.wrapSimple's output via a new splitKtxSystemMessages helper and pass them top-level to generateText (preserves cacheControl providerOptions on the SystemModelMessage). Agent-runner's local splitSystemPromptMessages dedupes onto the shared helper. * test(docs): align examples-docs assertions with revamped docs PR #103 (setup/guide doc revamp) reworded several CLI examples and connection labels; the assertions in scripts/examples-docs.test.mjs still referenced the pre-revamp wording and were failing in CI on main. Update the regexes to match the post-revamp content: - drop the `--json` flag from the sl-query example expectation - move the `Driver:` / `Status: ok` probe to the connection reference, which is where that output now lives (driver id is lowercase `postgres`, not the display name `PostgreSQL`) - drop the obsolete `Install \`uv\`...` troubleshooting line - accept `<connectionId>` everywhere; the docs no longer use the hyphenated `<connection-id>` form - match the `warehouse` connection id used in the quickstart instead of the `postgres-warehouse` id only used in the README and setup ref * fix(sl): skip TS/Python schema contract test when uv is unavailable The TypeScript checks CI job does not install uv or Python, so the module-level `execFileSync('uv', ...)` in schemas.contract.test.ts threw ENOENT and failed the suite. Wrap the schema dump in a try/catch and guard the describe block with `describe.skipIf` so the test skips in environments without uv. Local dev and any CI job that has uv on PATH still runs the cross-language contract assertion.
181 lines
6.5 KiB
Python
181 lines
6.5 KiB
Python
import pytest
|
|
from pathlib import Path
|
|
import tempfile
|
|
|
|
import yaml
|
|
|
|
from semantic_layer.loader import SourceLoader
|
|
from semantic_layer.models import SourceDefinition
|
|
|
|
SOURCES_DIR = Path(__file__).parent.parent / "sources" / "ecommerce"
|
|
|
|
|
|
class TestSourceLoader:
|
|
def test_load_all_ecommerce(self, ecommerce_sources):
|
|
assert len(ecommerce_sources) == 6
|
|
assert set(ecommerce_sources.keys()) == {
|
|
"customers",
|
|
"orders",
|
|
"regions",
|
|
"products",
|
|
"order_items",
|
|
"churn_risk",
|
|
}
|
|
|
|
def test_orders_source(self, ecommerce_sources):
|
|
orders = ecommerce_sources["orders"]
|
|
assert orders.is_table_source
|
|
assert orders.table == "public.orders"
|
|
assert orders.grain == ["id"]
|
|
assert len(orders.columns) == 6
|
|
assert len(orders.measures) == 5
|
|
assert len(orders.joins) == 1
|
|
assert orders.joins[0].to == "customers"
|
|
assert orders.joins[0].relationship == "many_to_one"
|
|
|
|
def test_churn_risk_sql_source(self, ecommerce_sources):
|
|
churn = ecommerce_sources["churn_risk"]
|
|
assert churn.is_sql_source
|
|
assert churn.sql is not None
|
|
assert "calculate_churn_score" in churn.sql
|
|
assert churn.grain == ["customer_id"]
|
|
assert len(churn.measures) == 1
|
|
assert churn.measures[0].name == "avg_risk"
|
|
|
|
def test_regions_no_joins(self, ecommerce_sources):
|
|
regions = ecommerce_sources["regions"]
|
|
assert regions.joins == []
|
|
assert regions.measures == []
|
|
|
|
def test_order_items_bridge(self, ecommerce_sources):
|
|
oi = ecommerce_sources["order_items"]
|
|
assert len(oi.joins) == 2
|
|
targets = {j.to for j in oi.joins}
|
|
assert targets == {"orders", "products"}
|
|
|
|
def test_revenue_measure_has_filter(self, ecommerce_sources):
|
|
orders = ecommerce_sources["orders"]
|
|
revenue = next(m for m in orders.measures if m.name == "revenue")
|
|
assert revenue.filter == "status != 'refunded'"
|
|
assert revenue.expr == "sum(amount)"
|
|
|
|
def test_load_single_file(self):
|
|
loader = SourceLoader(SOURCES_DIR)
|
|
src = loader.load_file(SOURCES_DIR / "regions.yaml")
|
|
assert src.name == "regions"
|
|
assert isinstance(src, SourceDefinition)
|
|
|
|
def test_invalid_join_target(self):
|
|
with tempfile.TemporaryDirectory() as tmpdir:
|
|
data = {
|
|
"name": "bad_source",
|
|
"table": "t",
|
|
"grain": ["id"],
|
|
"columns": [{"name": "id", "type": "number"}],
|
|
"joins": [
|
|
{
|
|
"to": "nonexistent",
|
|
"on": "id = nonexistent.id",
|
|
"relationship": "many_to_one",
|
|
}
|
|
],
|
|
}
|
|
path = Path(tmpdir) / "bad.yaml"
|
|
with open(path, "w") as f:
|
|
yaml.dump(data, f)
|
|
|
|
loader = SourceLoader(tmpdir)
|
|
with pytest.raises(ValueError, match="nonexistent"):
|
|
loader.load_all()
|
|
|
|
def test_duplicate_source_name(self):
|
|
with tempfile.TemporaryDirectory() as tmpdir:
|
|
data = {
|
|
"name": "dupe",
|
|
"table": "t",
|
|
"grain": ["id"],
|
|
"columns": [{"name": "id", "type": "number"}],
|
|
}
|
|
for fname in ["a.yaml", "b.yaml"]:
|
|
with open(Path(tmpdir) / fname, "w") as f:
|
|
yaml.dump(data, f)
|
|
|
|
loader = SourceLoader(tmpdir)
|
|
with pytest.raises(ValueError, match="Duplicate source name"):
|
|
loader.load_all()
|
|
|
|
def test_source_description_loads(self, ecommerce_sources):
|
|
churn = ecommerce_sources["churn_risk"]
|
|
assert churn.description is not None
|
|
assert "churn" in churn.description.lower()
|
|
|
|
def test_column_role_loads(self, ecommerce_sources):
|
|
orders = ecommerce_sources["orders"]
|
|
time_col = next(c for c in orders.columns if c.name == "created_at")
|
|
assert time_col.role == "time"
|
|
|
|
def test_source_without_description(self, ecommerce_sources):
|
|
regions = ecommerce_sources["regions"]
|
|
assert regions.description is None
|
|
|
|
|
|
# ── From test_edge_cases.py ──────────────────────────────────────────
|
|
|
|
|
|
class TestLoaderEdgeCases:
|
|
def test_empty_directory(self):
|
|
with tempfile.TemporaryDirectory() as tmpdir:
|
|
loader = SourceLoader(tmpdir)
|
|
sources = loader.load_all()
|
|
assert sources == {}
|
|
|
|
def test_non_yaml_files_ignored(self):
|
|
with tempfile.TemporaryDirectory() as tmpdir:
|
|
(Path(tmpdir) / "readme.txt").write_text("not a yaml file")
|
|
loader = SourceLoader(tmpdir)
|
|
sources = loader.load_all()
|
|
assert sources == {}
|
|
|
|
def test_yaml_with_extra_fields(self):
|
|
with tempfile.TemporaryDirectory() as tmpdir:
|
|
data = {
|
|
"name": "test",
|
|
"table": "t",
|
|
"grain": ["id"],
|
|
"columns": [{"name": "id", "type": "number"}],
|
|
"unknown_field": "should be rejected",
|
|
}
|
|
with open(Path(tmpdir) / "test.yaml", "w") as f:
|
|
yaml.dump(data, f)
|
|
loader = SourceLoader(tmpdir)
|
|
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:
|
|
subdir = Path(tmpdir) / "sub"
|
|
subdir.mkdir()
|
|
data = {
|
|
"name": "nested",
|
|
"table": "t",
|
|
"grain": ["id"],
|
|
"columns": [{"name": "id", "type": "number"}],
|
|
}
|
|
with open(subdir / "nested.yaml", "w") as f:
|
|
yaml.dump(data, f)
|
|
loader = SourceLoader(tmpdir)
|
|
sources = loader.load_all()
|
|
assert "nested" in sources
|