mirror of
https://github.com/Kaelio/ktx.git
synced 2026-07-04 10:52:13 +02:00
fix(context): merge overlay columns onto manifest columns by name (#94)
* 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.
This commit is contained in:
Andrey Avtomonov
GitHub
parent
6bc8d200ea
commit
cb8902f1e5
56 changed files with 1650 additions and 237 deletions
|
|
@ -2,13 +2,17 @@ import type { Mock } from 'vitest';
|
|||
import { beforeEach, describe, expect, it, vi } from 'vitest';
|
||||
|
||||
import {
|
||||
ColumnNameCollisionError,
|
||||
composeOverlay,
|
||||
ConflictingExcludeAndOverrideError,
|
||||
enrichColumnsFromManifest,
|
||||
findDanglingSegmentRefs,
|
||||
projectManifestEntry,
|
||||
SemanticLayerService,
|
||||
toResolvedWire,
|
||||
UnknownColumnOverrideError,
|
||||
} from './semantic-layer.service.js';
|
||||
import { sourceDefinitionSchema } from './schemas.js';
|
||||
import { resolvedSourceSchema, sourceDefinitionSchema, sourceOverlaySchema } from './schemas.js';
|
||||
import type { SemanticLayerSource } from './types.js';
|
||||
|
||||
const pythonPort = {
|
||||
|
|
@ -139,6 +143,69 @@ describe('composeOverlay', () => {
|
|||
expect(composed.measures).toHaveLength(1);
|
||||
});
|
||||
|
||||
it('applies column_overrides to same-named manifest columns', () => {
|
||||
const overlay = {
|
||||
name: 'fct_labs',
|
||||
column_overrides: [
|
||||
{ name: 'lab_order_id', descriptions: { user: 'Primary key' } },
|
||||
{ name: 'admin_user_id', descriptions: { user: 'FK to admin_users' } },
|
||||
],
|
||||
};
|
||||
const composed = composeOverlay(baseTable, overlay);
|
||||
// No duplicate columns appended — same-named overlay entries merged onto the base.
|
||||
expect(composed.columns).toHaveLength(3);
|
||||
const labOrder = composed.columns.find((c) => c.name === 'lab_order_id');
|
||||
expect(labOrder?.type).toBe('string');
|
||||
expect(labOrder?.descriptions).toEqual({ user: 'Primary key' });
|
||||
const adminUser = composed.columns.find((c) => c.name === 'admin_user_id');
|
||||
expect(adminUser?.type).toBe('string');
|
||||
expect(adminUser?.descriptions).toEqual({ user: 'FK to admin_users' });
|
||||
});
|
||||
|
||||
it('appends computed columns alongside column overrides', () => {
|
||||
const overlay = {
|
||||
name: 'fct_labs',
|
||||
column_overrides: [
|
||||
{ name: 'lab_order_id', descriptions: { user: 'PK doc' } },
|
||||
],
|
||||
columns: [
|
||||
{ name: 'is_byol', type: 'boolean', expr: "lab_type = 'byol'" },
|
||||
],
|
||||
};
|
||||
const composed = composeOverlay(baseTable, overlay);
|
||||
expect(composed.columns).toHaveLength(4);
|
||||
expect(composed.columns.find((c) => c.name === 'is_byol')?.expr).toBe("lab_type = 'byol'");
|
||||
expect(composed.columns.find((c) => c.name === 'lab_order_id')?.type).toBe('string');
|
||||
});
|
||||
|
||||
it('rejects column_overrides that target unknown manifest columns', () => {
|
||||
expect(() =>
|
||||
composeOverlay(baseTable, {
|
||||
name: 'fct_labs',
|
||||
column_overrides: [{ name: 'missing', descriptions: { user: 'Nope' } }],
|
||||
}),
|
||||
).toThrow(UnknownColumnOverrideError);
|
||||
});
|
||||
|
||||
it('rejects computed columns whose names collide with manifest columns', () => {
|
||||
expect(() =>
|
||||
composeOverlay(baseTable, {
|
||||
name: 'fct_labs',
|
||||
columns: [{ name: 'lab_order_id', type: 'string', expr: 'lab_order_id' }],
|
||||
}),
|
||||
).toThrow(ColumnNameCollisionError);
|
||||
});
|
||||
|
||||
it('rejects exclude/override conflicts before applying exclusions', () => {
|
||||
expect(() =>
|
||||
composeOverlay(baseTable, {
|
||||
name: 'fct_labs',
|
||||
exclude_columns: ['lab_order_id'],
|
||||
column_overrides: [{ name: 'lab_order_id', descriptions: { user: 'Hidden PK' } }],
|
||||
}),
|
||||
).toThrow(ConflictingExcludeAndOverrideError);
|
||||
});
|
||||
|
||||
it('merges overlay descriptions (plural) with base descriptions keyed by source', () => {
|
||||
const baseWithDescriptions: SemanticLayerSource = {
|
||||
...baseTable,
|
||||
|
|
@ -418,6 +485,62 @@ describe('sourceDefinitionSchema', () => {
|
|||
});
|
||||
});
|
||||
|
||||
describe('sourceOverlaySchema', () => {
|
||||
it('accepts column_overrides and keeps columns computed-only', () => {
|
||||
const result = sourceOverlaySchema.safeParse({
|
||||
name: 'orders',
|
||||
column_overrides: [{ name: 'status', descriptions: { user: 'Lifecycle status' } }],
|
||||
columns: [{ name: 'is_paid', type: 'boolean', expr: "status = 'paid'" }],
|
||||
});
|
||||
expect(result.success).toBe(true);
|
||||
});
|
||||
|
||||
it('rejects typeless overlay columns and singular description on overrides', () => {
|
||||
const result = sourceOverlaySchema.safeParse({
|
||||
name: 'orders',
|
||||
column_overrides: [{ name: 'status', description: 'Lifecycle status' }],
|
||||
columns: [{ name: 'status', descriptions: { user: 'Lifecycle status' } }],
|
||||
});
|
||||
expect(result.success).toBe(false);
|
||||
if (!result.success) {
|
||||
const paths = result.error.issues.map((issue) => issue.path.join('.'));
|
||||
expect(paths).toContain('column_overrides.0');
|
||||
expect(paths).toContain('columns.0.type');
|
||||
expect(paths).toContain('columns.0.expr');
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('toResolvedWire', () => {
|
||||
it('strips TS-only authoring and provenance fields before the Python boundary', () => {
|
||||
const wire = toResolvedWire({
|
||||
name: 'orders',
|
||||
table: 'public.orders',
|
||||
inherits_columns_from: 'orders',
|
||||
grain: ['id'],
|
||||
columns: [{ name: 'id', type: 'string' }],
|
||||
joins: [{ to: 'customers', on: 'orders.customer_id = customers.id', relationship: 'many_to_one', source: 'formal' }],
|
||||
measures: [],
|
||||
usage: {
|
||||
narrative: 'Frequently queried orders.',
|
||||
frequencyTier: 'high',
|
||||
commonFilters: ['status'],
|
||||
commonJoins: [],
|
||||
},
|
||||
});
|
||||
|
||||
expect(wire).toEqual({
|
||||
name: 'orders',
|
||||
table: 'public.orders',
|
||||
grain: ['id'],
|
||||
columns: [{ name: 'id', type: 'string' }],
|
||||
joins: [{ to: 'customers', on: 'orders.customer_id = customers.id', relationship: 'many_to_one' }],
|
||||
measures: [],
|
||||
});
|
||||
expect(resolvedSourceSchema.parse(wire)).toEqual(wire);
|
||||
});
|
||||
});
|
||||
|
||||
describe('projectManifestEntry', () => {
|
||||
it('projects manifest usage onto the semantic-layer source', () => {
|
||||
const source = projectManifestEntry('orders', {
|
||||
|
|
@ -537,7 +660,8 @@ describe('loadAllSources — standalone enrichment via inherits_columns_from', (
|
|||
].join('\n'),
|
||||
});
|
||||
|
||||
const sources = await service.loadAllSources('conn-1');
|
||||
const { sources, loadErrors } = await service.loadAllSources('conn-1');
|
||||
expect(loadErrors).toEqual([]);
|
||||
|
||||
expect(sources[0]).toMatchObject({
|
||||
name: 'orders',
|
||||
|
|
@ -601,7 +725,8 @@ describe('loadAllSources — standalone enrichment via inherits_columns_from', (
|
|||
return Promise.reject(new Error(`Unexpected readFile: ${path}`));
|
||||
});
|
||||
|
||||
const sources = await service.loadAllSources('conn-1');
|
||||
const { sources, loadErrors } = await service.loadAllSources('conn-1');
|
||||
expect(loadErrors).toEqual([]);
|
||||
const aav = sources.find((s) => s.name === 'aav_consignments');
|
||||
expect(aav).toBeDefined();
|
||||
expect(aav?.columns).toEqual([
|
||||
|
|
@ -646,7 +771,8 @@ describe('loadAllSources — standalone enrichment via inherits_columns_from', (
|
|||
});
|
||||
});
|
||||
|
||||
const sources = await service.loadAllSources('conn-1');
|
||||
const { sources, loadErrors } = await service.loadAllSources('conn-1');
|
||||
expect(loadErrors).toEqual([]);
|
||||
const aav = sources.find((s) => s.name === 'aav_consignments');
|
||||
expect(aav?.columns[0].type).toBe('string');
|
||||
});
|
||||
|
|
@ -670,7 +796,8 @@ describe('loadAllSources — standalone enrichment via inherits_columns_from', (
|
|||
].join('\n'),
|
||||
});
|
||||
|
||||
const sources = await service.loadAllSources('conn-1');
|
||||
const { sources, loadErrors } = await service.loadAllSources('conn-1');
|
||||
expect(loadErrors).toEqual([]);
|
||||
const aav = sources.find((s) => s.name === 'aav_consignments');
|
||||
expect(aav?.columns).toEqual([{ name: 'FOO', type: 'string' }]);
|
||||
});
|
||||
|
|
@ -693,7 +820,8 @@ describe('loadAllSources — standalone enrichment via inherits_columns_from', (
|
|||
].join('\n'),
|
||||
});
|
||||
|
||||
const sources = await service.loadAllSources('conn-1');
|
||||
const { sources, loadErrors } = await service.loadAllSources('conn-1');
|
||||
expect(loadErrors).toEqual([]);
|
||||
|
||||
expect(sources[0]).toMatchObject({
|
||||
name: 'orders',
|
||||
|
|
@ -701,6 +829,33 @@ describe('loadAllSources — standalone enrichment via inherits_columns_from', (
|
|||
columns: [{ name: 'id', type: 'string', descriptions: { user: 'Stable order identifier.' } }],
|
||||
});
|
||||
});
|
||||
|
||||
it('reports file-attributed errors for legacy overlay column patches', async () => {
|
||||
const schemaPath = 'semantic-layer/conn-1/_schema/marts.yaml';
|
||||
const overlayPath = 'semantic-layer/conn-1/orders.yaml';
|
||||
configService.listFiles.mockResolvedValue({ files: [schemaPath, overlayPath] });
|
||||
configService.readFile.mockImplementation((path: string) => {
|
||||
if (path === schemaPath) {
|
||||
return Promise.resolve({
|
||||
content: [
|
||||
'tables:',
|
||||
' orders:',
|
||||
' table: public.orders',
|
||||
' columns:',
|
||||
' - { name: id, type: string, pk: true }',
|
||||
].join('\n'),
|
||||
});
|
||||
}
|
||||
return Promise.resolve({
|
||||
content: ['name: orders', 'columns:', ' - name: id', ' descriptions: { user: "Stable id." }'].join('\n'),
|
||||
});
|
||||
});
|
||||
|
||||
const { loadErrors } = await service.loadAllSources('conn-1');
|
||||
|
||||
expect(loadErrors.join('\n')).toContain(overlayPath);
|
||||
expect(loadErrors.join('\n')).toContain("move it to 'column_overrides:'");
|
||||
});
|
||||
});
|
||||
|
||||
describe('validateWithProposedSource', () => {
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue