mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-16 08:25:14 +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.
68 lines
2.4 KiB
TypeScript
68 lines
2.4 KiB
TypeScript
import { execFileSync } from 'node:child_process';
|
|
import { Ajv2020 } from 'ajv/dist/2020.js';
|
|
import { describe, expect, it } from 'vitest';
|
|
|
|
import { resolvedSourceSchema } from './schemas.js';
|
|
import { toResolvedWire } from './semantic-layer.service.js';
|
|
import type { SemanticLayerSource } from './types.js';
|
|
|
|
function loadPythonSourceDefinitionSchema(): Record<string, unknown> | null {
|
|
try {
|
|
const stdout = execFileSync('uv', ['run', 'python', '-m', 'semantic_layer', 'dump-schema'], {
|
|
cwd: new URL('../../../../', import.meta.url),
|
|
encoding: 'utf8',
|
|
stdio: ['ignore', 'pipe', 'ignore'],
|
|
});
|
|
return JSON.parse(stdout) as Record<string, unknown>;
|
|
} catch {
|
|
return null;
|
|
}
|
|
}
|
|
|
|
const sourceDefinitionJsonSchema = loadPythonSourceDefinitionSchema();
|
|
|
|
const fixtures: SemanticLayerSource[] = [
|
|
{
|
|
name: 'orders',
|
|
table: 'public.orders',
|
|
grain: ['id'],
|
|
columns: [
|
|
{ name: 'id', type: 'number' },
|
|
{
|
|
name: 'status',
|
|
type: 'string',
|
|
descriptions: { dbt: 'Order lifecycle status.' },
|
|
constraints: { dbt: { not_null: true } },
|
|
enum_values: { dbt: ['placed', 'shipped'] },
|
|
tests: { dbt: [{ name: 'accepted_values', package: 'dbt' }] },
|
|
},
|
|
],
|
|
joins: [{ to: 'customers', on: 'orders.customer_id = customers.id', relationship: 'many_to_one' }],
|
|
measures: [{ name: 'order_count', expr: 'count(id)' }],
|
|
segments: [{ name: 'paid', expr: "status = 'paid'" }],
|
|
default_time_dimension: { dbt: 'created_at' },
|
|
tags: { dbt: ['mart'] },
|
|
freshness: { dbt: { loaded_at_field: 'updated_at' } },
|
|
},
|
|
{
|
|
name: 'aav_orders',
|
|
sql: 'select id, status from public.orders where status = paid',
|
|
grain: ['id'],
|
|
columns: [{ name: 'id', type: 'number' }],
|
|
joins: [],
|
|
measures: [],
|
|
},
|
|
];
|
|
|
|
describe.skipIf(sourceDefinitionJsonSchema === null)('resolved source JSON Schema contract', () => {
|
|
it('keeps TS resolved-source fixtures accepted by the Python SourceDefinition schema', () => {
|
|
const ajv = new Ajv2020({ allErrors: true, strict: false });
|
|
const validate = ajv.compile(sourceDefinitionJsonSchema as Record<string, unknown>);
|
|
|
|
for (const fixture of fixtures) {
|
|
const wire = toResolvedWire(fixture);
|
|
expect(resolvedSourceSchema.safeParse(wire).success).toBe(true);
|
|
expect(validate(wire), JSON.stringify(validate.errors, null, 2)).toBe(true);
|
|
}
|
|
});
|
|
});
|