2026-05-10 23:12:26 +02:00
|
|
|
import { describe, expect, it, vi } from 'vitest';
|
test: split cli tests from source tree (#216)
* feat(cli): define full warehouse dialect contract
* test(cli): keep dialect edge tests focused
* fix(cli): stabilize dialect contract foundation
* refactor(connectors): own read-only query preparation
* refactor(connectors): resolve dialects through registry
* refactor(connectors): keep concrete dialect classes internal
* chore(workspace): enforce dialect import boundary
* refactor(cli): resolve relationship dialect at scan boundary
* refactor(cli): use dialect display parsing for entity details
* refactor(cli): use dialect display parsing for warehouse catalog
* refactor(cli): use dialect SQL in relationship workflows
* test(cli): verify solid dialect scan workflow closure
* test: split cli tests from source tree
* refactor(cli): standardize BigQuery scope listing
* feat(sqlite): implement connector scope listing
* test(connectors): cover required table listing
* feat(cli): add warehouse driver registry
* refactor(setup): route scope discovery through driver registry
* refactor(cli): route local query execution through driver registry
* refactor(historic-sql): route dialect support through driver registry
* refactor(cli): test warehouse connections through driver registry
* fix(cli): close driver registry type export gaps
* Improve setup daemon diagnostics
* refactor(setup): centralize rail-prefixed diagnostics + query-history fallback
Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput
into clack.ts so the setup wizard, managed daemons, and embedding/agent steps
share one rail-formatted writer. setup-databases.ts also adds a
"disable query history and retry" option when the schema-context build fails
and query history is the likely culprit, surfaced via a new
failed-query-history-unavailable status.
* fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match
The setup picker's KtxTableListEntry was a 2-level { schema, name }, so
qualifiedTableId always wrote db.name into enabled_tables. When BigQuery,
Snowflake, or SQL Server later ran fast ingest, their introspect step filtered
the scope set with scopedTableNames(scope, { catalog: projectId|database, db })
— catalog was non-null on the introspect side but null in the scope refs, so
every entry was rejected, the live-database adapter staged zero table files,
and detect() failed with 'Adapter "live-database" did not recognize fetched
source output'.
Align the picker boundary with the canonical 3-level KtxTableRef:
- Add catalog: string | null to KtxTableListEntry.
- BigQuery/Snowflake/SQL Server listTables populate catalog from the
resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null.
- qualifiedTableId emits catalog.schema.name when catalog is non-null
(resolveEnabledTables already accepts the 3-part shape) and
schemasFromEnabledTables now goes through parseDottedTableEntry so it
recovers the schema correctly from both 2-part and 3-part entries.
- Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker
reuse.
Update listTables expectations in all seven connector tests and the setup /
picker test fixtures. Add a picker regression test that covers the
catalog-bearing round-trip (save + refine).
* fix(cli): allow debug telemetry under opt-out env
2026-05-26 08:49:05 +02:00
|
|
|
import type { ToolSession } from '../../../../src/context/tools/tool-session.js';
|
|
|
|
|
import { createTouchedSlSources, hasTouchedSlSource } from '../../../../src/context/tools/touched-sl-sources.js';
|
|
|
|
|
import type { ToolContext } from '../../../../src/context/tools/base-tool.js';
|
|
|
|
|
import { SlWriteSourceTool } from '../../../../src/context/sl/tools/sl-write-source.tool.js';
|
2026-05-10 23:12:26 +02:00
|
|
|
|
|
|
|
|
function makeTool(overrides: Partial<Record<string, any>> = {}) {
|
|
|
|
|
const semanticLayerService = {
|
|
|
|
|
listManifestSourceNames: vi.fn().mockResolvedValue(['ACCOUNTS', 'ORDERS']),
|
|
|
|
|
isManifestBacked: vi.fn().mockResolvedValue(false),
|
|
|
|
|
loadSource: vi.fn().mockResolvedValue(null),
|
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.
2026-05-15 02:11:04 +02:00
|
|
|
loadAllSources: vi.fn().mockResolvedValue({ sources: [], loadErrors: [] }),
|
2026-05-10 23:12:26 +02:00
|
|
|
validateWithProposedSource: vi.fn().mockResolvedValue({ errors: [], warnings: [] }),
|
|
|
|
|
writeSource: vi.fn().mockResolvedValue({ commitHash: 'c1' }),
|
|
|
|
|
deleteSource: vi.fn().mockResolvedValue(undefined),
|
|
|
|
|
readSourceFile: vi.fn().mockRejectedValue(new Error('not found')),
|
|
|
|
|
...overrides.semanticLayerService,
|
|
|
|
|
};
|
|
|
|
|
const slSearchService = {
|
|
|
|
|
indexSources: vi.fn().mockResolvedValue(undefined),
|
|
|
|
|
...overrides.slSearchService,
|
|
|
|
|
};
|
|
|
|
|
const tool = new SlWriteSourceTool({
|
|
|
|
|
semanticLayerService: semanticLayerService as never,
|
|
|
|
|
slSearchService: slSearchService as never,
|
|
|
|
|
authorResolver: { resolve: vi.fn().mockResolvedValue({ name: 'T U', email: 't@u.com' }) },
|
|
|
|
|
});
|
|
|
|
|
return { tool, semanticLayerService, slSearchService };
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
const baseContext: ToolContext = { sourceId: 's', messageId: 'm', userId: 'u' };
|
|
|
|
|
|
|
|
|
|
describe('SlWriteSourceTool — orphan overlay guard', () => {
|
|
|
|
|
it('rejects overlay YAMLs targeting a name absent from the manifest', async () => {
|
|
|
|
|
const { tool } = makeTool();
|
|
|
|
|
const result = await tool.call(
|
|
|
|
|
{
|
|
|
|
|
connectionId: '11111111-1111-1111-1111-111111111111',
|
|
|
|
|
sourceName: 'does_not_exist',
|
|
|
|
|
source: {
|
|
|
|
|
name: 'does_not_exist',
|
|
|
|
|
measures: [{ name: 'count_rows', expr: 'count(*)' }],
|
|
|
|
|
} as any,
|
|
|
|
|
} as any,
|
|
|
|
|
baseContext,
|
|
|
|
|
);
|
|
|
|
|
expect(result.structured.success).toBe(false);
|
|
|
|
|
expect(result.markdown).toMatch(/no manifest entry with that name exists/i);
|
|
|
|
|
expect(result.markdown).toMatch(/ACCOUNTS|ORDERS/);
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('SlWriteSourceTool — session gating', () => {
|
|
|
|
|
function makeSession(overrides: Partial<ToolSession> = {}): ToolSession {
|
|
|
|
|
return {
|
|
|
|
|
connectionId: '11111111-1111-1111-1111-111111111111',
|
|
|
|
|
isWorktreeScoped: true,
|
|
|
|
|
preHead: 'base',
|
|
|
|
|
touchedSlSources: createTouchedSlSources(),
|
|
|
|
|
actions: [],
|
|
|
|
|
semanticLayerService: {
|
|
|
|
|
loadSource: vi.fn().mockResolvedValue(null),
|
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.
2026-05-15 02:11:04 +02:00
|
|
|
loadAllSources: vi.fn().mockResolvedValue({ sources: [], loadErrors: [] }),
|
2026-05-10 23:12:26 +02:00
|
|
|
validateWithProposedSource: vi.fn().mockResolvedValue({ errors: [], warnings: [] }),
|
|
|
|
|
writeSource: vi.fn().mockResolvedValue({ commitHash: 'c1' }),
|
|
|
|
|
deleteSource: vi.fn().mockResolvedValue(undefined),
|
|
|
|
|
listManifestSourceNames: vi.fn().mockResolvedValue([]),
|
|
|
|
|
isManifestBacked: vi.fn().mockResolvedValue(false),
|
|
|
|
|
readSourceFile: vi.fn().mockRejectedValue(new Error('not found')),
|
|
|
|
|
findManifestEntryByTableRef: vi.fn().mockResolvedValue(null),
|
|
|
|
|
} as any,
|
|
|
|
|
wikiService: {} as any,
|
|
|
|
|
configService: {} as any,
|
|
|
|
|
gitService: {} as any,
|
|
|
|
|
...overrides,
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
it('skips slSearchService.indexSources when session is worktree-scoped', async () => {
|
|
|
|
|
const { tool, slSearchService } = makeTool();
|
|
|
|
|
const session = makeSession();
|
|
|
|
|
const context: ToolContext = { ...baseContext, session };
|
|
|
|
|
const result = await tool.call(
|
|
|
|
|
{
|
|
|
|
|
connectionId: session.connectionId,
|
|
|
|
|
sourceName: 'my_source',
|
|
|
|
|
source: {
|
|
|
|
|
name: 'my_source',
|
|
|
|
|
sql: 'select 1 as id',
|
|
|
|
|
grain: ['id'],
|
|
|
|
|
columns: [{ name: 'id', type: 'string' }],
|
|
|
|
|
measures: [],
|
|
|
|
|
joins: [],
|
|
|
|
|
} as any,
|
|
|
|
|
} as any,
|
|
|
|
|
context,
|
|
|
|
|
);
|
|
|
|
|
expect(result.structured.success).toBe(true);
|
|
|
|
|
expect(slSearchService.indexSources).not.toHaveBeenCalled();
|
|
|
|
|
expect(hasTouchedSlSource(session.touchedSlSources, session.connectionId!, 'my_source')).toBe(true);
|
|
|
|
|
expect(session.actions).toContainEqual(expect.objectContaining({ target: 'sl', key: 'my_source' }));
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('records cross-connection SL writes with targetConnectionId', async () => {
|
|
|
|
|
const { tool } = makeTool();
|
|
|
|
|
const session = makeSession({ connectionId: '11111111-1111-4111-8111-111111111111' });
|
|
|
|
|
const warehouseConnectionId = '22222222-2222-4222-8222-222222222222';
|
|
|
|
|
const context: ToolContext = { ...baseContext, session };
|
|
|
|
|
|
|
|
|
|
const result = await tool.call(
|
|
|
|
|
{
|
|
|
|
|
connectionId: warehouseConnectionId,
|
|
|
|
|
sourceName: 'mapped_orders',
|
|
|
|
|
source: {
|
|
|
|
|
name: 'mapped_orders',
|
|
|
|
|
table: 'public.orders',
|
|
|
|
|
grain: ['id'],
|
|
|
|
|
columns: [{ name: 'id', type: 'string' }],
|
|
|
|
|
measures: [],
|
|
|
|
|
joins: [],
|
|
|
|
|
} as any,
|
|
|
|
|
} as any,
|
|
|
|
|
context,
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
expect(result.structured.success).toBe(true);
|
|
|
|
|
expect(hasTouchedSlSource(session.touchedSlSources, warehouseConnectionId, 'mapped_orders')).toBe(true);
|
|
|
|
|
expect(session.actions).toContainEqual(
|
|
|
|
|
expect.objectContaining({
|
|
|
|
|
target: 'sl',
|
|
|
|
|
key: 'mapped_orders',
|
|
|
|
|
targetConnectionId: warehouseConnectionId,
|
|
|
|
|
}),
|
|
|
|
|
);
|
|
|
|
|
});
|
|
|
|
|
|
2026-05-18 13:38:06 +02:00
|
|
|
it('rejects session-scoped writes outside allowed target connections', async () => {
|
|
|
|
|
const { tool } = makeTool();
|
|
|
|
|
const session = makeSession({
|
|
|
|
|
allowedConnectionNames: new Set(['warehouse']),
|
|
|
|
|
});
|
|
|
|
|
const context: ToolContext = { ...baseContext, session };
|
|
|
|
|
|
|
|
|
|
const result = await tool.call(
|
|
|
|
|
{
|
|
|
|
|
connectionId: 'finance',
|
|
|
|
|
sourceName: 'finance_orders',
|
|
|
|
|
source: {
|
|
|
|
|
name: 'finance_orders',
|
|
|
|
|
table: 'public.orders',
|
|
|
|
|
grain: ['id'],
|
|
|
|
|
columns: [{ name: 'id', type: 'string' }],
|
|
|
|
|
measures: [],
|
|
|
|
|
joins: [],
|
|
|
|
|
} as any,
|
|
|
|
|
} as any,
|
|
|
|
|
context,
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
expect(result.structured.success).toBe(false);
|
|
|
|
|
expect(result.markdown).toContain('connectionId "finance" is outside this ingest session');
|
|
|
|
|
expect(session.actions).toEqual([]);
|
|
|
|
|
});
|
|
|
|
|
|
2026-05-10 23:12:26 +02:00
|
|
|
it('indexes normally when no session is present', async () => {
|
|
|
|
|
const { tool, slSearchService } = makeTool();
|
|
|
|
|
const result = await tool.call(
|
|
|
|
|
{
|
|
|
|
|
connectionId: '11111111-1111-1111-1111-111111111111',
|
|
|
|
|
sourceName: 'my_source',
|
|
|
|
|
source: {
|
|
|
|
|
name: 'my_source',
|
|
|
|
|
sql: 'select 1 as id',
|
|
|
|
|
grain: ['id'],
|
|
|
|
|
columns: [{ name: 'id', type: 'string' }],
|
|
|
|
|
measures: [],
|
|
|
|
|
joins: [],
|
|
|
|
|
} as any,
|
|
|
|
|
} as any,
|
|
|
|
|
baseContext,
|
|
|
|
|
);
|
|
|
|
|
expect(result.structured.success).toBe(true);
|
|
|
|
|
expect(slSearchService.indexSources).toHaveBeenCalledTimes(1);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('uses session.semanticLayerService when session is present', async () => {
|
|
|
|
|
const { tool } = makeTool();
|
|
|
|
|
const session = makeSession();
|
|
|
|
|
const context: ToolContext = { ...baseContext, session };
|
|
|
|
|
await tool.call(
|
|
|
|
|
{
|
|
|
|
|
connectionId: session.connectionId,
|
|
|
|
|
sourceName: 'my_source',
|
|
|
|
|
source: {
|
|
|
|
|
name: 'my_source',
|
|
|
|
|
sql: 'select 1 as id',
|
|
|
|
|
grain: ['id'],
|
|
|
|
|
columns: [{ name: 'id', type: 'string' }],
|
|
|
|
|
measures: [],
|
|
|
|
|
joins: [],
|
|
|
|
|
} as any,
|
|
|
|
|
} as any,
|
|
|
|
|
context,
|
|
|
|
|
);
|
|
|
|
|
expect((session.semanticLayerService as any).writeSource).toHaveBeenCalled();
|
|
|
|
|
});
|
2026-05-11 00:31:15 -07:00
|
|
|
|
2026-05-13 15:55:00 +02:00
|
|
|
it('writes source and column description maps', async () => {
|
2026-05-11 00:31:15 -07:00
|
|
|
const { tool, semanticLayerService } = makeTool();
|
|
|
|
|
const result = await tool.call(
|
|
|
|
|
{
|
|
|
|
|
connectionId: '11111111-1111-1111-1111-111111111111',
|
|
|
|
|
sourceName: 'orders',
|
|
|
|
|
source: {
|
|
|
|
|
name: 'orders',
|
2026-05-13 15:55:00 +02:00
|
|
|
descriptions: { user: 'Finance orders used for invoice reconciliation.' },
|
2026-05-11 00:31:15 -07:00
|
|
|
table: 'public.orders',
|
|
|
|
|
grain: ['id'],
|
2026-05-13 15:55:00 +02:00
|
|
|
columns: [{ name: 'id', type: 'string', descriptions: { user: 'Stable order identifier.' } }],
|
2026-05-11 00:31:15 -07:00
|
|
|
measures: [],
|
|
|
|
|
joins: [],
|
|
|
|
|
} as any,
|
|
|
|
|
} as any,
|
|
|
|
|
baseContext,
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
expect(result.structured.success).toBe(true);
|
|
|
|
|
expect(semanticLayerService.writeSource).toHaveBeenCalledWith(
|
|
|
|
|
expect.any(String),
|
|
|
|
|
expect.objectContaining({
|
|
|
|
|
descriptions: { user: 'Finance orders used for invoice reconciliation.' },
|
|
|
|
|
columns: [expect.objectContaining({ descriptions: { user: 'Stable order identifier.' } })],
|
|
|
|
|
}),
|
|
|
|
|
expect.any(String),
|
|
|
|
|
expect.any(String),
|
|
|
|
|
expect.any(String),
|
|
|
|
|
);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('fills missing descriptions for ingest-written overlays and columns', async () => {
|
|
|
|
|
const session = makeSession({
|
|
|
|
|
ingest: { runId: 'run-1', jobId: 'job-1', syncId: 'sync-1', sourceKey: 'metabase' },
|
|
|
|
|
semanticLayerService: {
|
|
|
|
|
loadSource: vi.fn().mockResolvedValue(null),
|
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.
2026-05-15 02:11:04 +02:00
|
|
|
loadAllSources: vi.fn().mockResolvedValue({ sources: [], loadErrors: [] }),
|
2026-05-11 00:31:15 -07:00
|
|
|
validateWithProposedSource: vi.fn().mockResolvedValue({ errors: [], warnings: [] }),
|
|
|
|
|
writeSource: vi.fn().mockResolvedValue({ commitHash: 'c1' }),
|
|
|
|
|
deleteSource: vi.fn().mockResolvedValue(undefined),
|
|
|
|
|
listManifestSourceNames: vi.fn().mockResolvedValue(['mart_account_segments']),
|
|
|
|
|
isManifestBacked: vi.fn().mockResolvedValue(false),
|
|
|
|
|
readSourceFile: vi.fn().mockRejectedValue(new Error('not found')),
|
|
|
|
|
findManifestEntryByTableRef: vi.fn().mockResolvedValue(null),
|
|
|
|
|
} as any,
|
|
|
|
|
});
|
|
|
|
|
const { tool } = makeTool();
|
|
|
|
|
|
|
|
|
|
const result = await tool.call(
|
|
|
|
|
{
|
|
|
|
|
connectionId: session.connectionId,
|
|
|
|
|
sourceName: 'mart_account_segments',
|
|
|
|
|
source: {
|
|
|
|
|
name: 'mart_account_segments',
|
|
|
|
|
columns: [{ name: 'is_large_contract', type: 'boolean', expr: 'contract_arr_cents >= 20000000' }],
|
|
|
|
|
measures: [{ name: 'account_count', expr: 'count(account_id)' }],
|
|
|
|
|
} as any,
|
|
|
|
|
} as any,
|
|
|
|
|
{ ...baseContext, session },
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
expect(result.structured.success).toBe(true);
|
|
|
|
|
expect((session.semanticLayerService as any).writeSource).toHaveBeenCalledWith(
|
|
|
|
|
expect.any(String),
|
|
|
|
|
expect.objectContaining({
|
|
|
|
|
descriptions: {
|
|
|
|
|
ktx: expect.stringContaining('mart_account_segments'),
|
|
|
|
|
},
|
|
|
|
|
columns: [
|
|
|
|
|
expect.objectContaining({
|
|
|
|
|
descriptions: {
|
|
|
|
|
ktx: expect.stringContaining('is large contract'),
|
|
|
|
|
},
|
|
|
|
|
}),
|
|
|
|
|
],
|
|
|
|
|
}),
|
|
|
|
|
expect.any(String),
|
|
|
|
|
expect.any(String),
|
|
|
|
|
expect.any(String),
|
|
|
|
|
);
|
|
|
|
|
});
|
2026-05-10 23:12:26 +02:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('SlWriteSourceTool — disconnected-components warning in markdown', () => {
|
|
|
|
|
it('surfaces validation warnings (including disconnected-components) in the markdown body', async () => {
|
|
|
|
|
const { tool } = makeTool({
|
|
|
|
|
semanticLayerService: {
|
|
|
|
|
validateWithProposedSource: vi.fn().mockResolvedValue({
|
|
|
|
|
errors: [],
|
|
|
|
|
warnings: ['orders: disconnected-components — no join path to ACCOUNTS'],
|
|
|
|
|
}),
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
const result = await tool.call(
|
|
|
|
|
{
|
|
|
|
|
connectionId: '11111111-1111-1111-1111-111111111111',
|
|
|
|
|
sourceName: 'orders',
|
|
|
|
|
source: {
|
|
|
|
|
name: 'orders',
|
|
|
|
|
sql: 'select 1 as id',
|
|
|
|
|
grain: ['id'],
|
|
|
|
|
columns: [{ name: 'id', type: 'string' }],
|
|
|
|
|
measures: [],
|
|
|
|
|
joins: [],
|
|
|
|
|
} as any,
|
|
|
|
|
} as any,
|
|
|
|
|
baseContext,
|
|
|
|
|
);
|
|
|
|
|
expect(result.markdown).toMatch(/disconnected-components/i);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('renders per-source warnings prominently when the just-written source becomes a singleton component', async () => {
|
|
|
|
|
const { tool } = makeTool({
|
|
|
|
|
semanticLayerService: {
|
|
|
|
|
validateWithProposedSource: vi.fn().mockResolvedValue({
|
|
|
|
|
errors: [],
|
|
|
|
|
warnings: ['Model has 2 disconnected components.'],
|
|
|
|
|
perSourceWarnings: {
|
|
|
|
|
foo: ["Source 'foo' is now a singleton component (no joins to any other source)."],
|
|
|
|
|
},
|
|
|
|
|
}),
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const result = await tool.call(
|
|
|
|
|
{
|
|
|
|
|
connectionId: '11111111-1111-1111-1111-111111111111',
|
|
|
|
|
sourceName: 'foo',
|
|
|
|
|
source: {
|
|
|
|
|
name: 'foo',
|
|
|
|
|
sql: 'select 1 as id',
|
|
|
|
|
grain: ['id'],
|
|
|
|
|
columns: [{ name: 'id', type: 'string' }],
|
|
|
|
|
measures: [],
|
|
|
|
|
joins: [],
|
|
|
|
|
} as any,
|
|
|
|
|
} as any,
|
|
|
|
|
baseContext,
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
expect(result.markdown).toMatch(/Action required/i);
|
|
|
|
|
expect(result.markdown).toContain("Source 'foo' is now a singleton component");
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('SlWriteSourceTool — standalone shadow guard', () => {
|
|
|
|
|
it('rejects standalone YAMLs that shadow a manifest entry', async () => {
|
|
|
|
|
const { tool } = makeTool({
|
|
|
|
|
semanticLayerService: {
|
|
|
|
|
isManifestBacked: vi.fn().mockResolvedValue(true),
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
const result = await tool.call(
|
|
|
|
|
{
|
|
|
|
|
connectionId: '11111111-1111-1111-1111-111111111111',
|
|
|
|
|
sourceName: 'ACCOUNTS',
|
|
|
|
|
source: {
|
|
|
|
|
name: 'ACCOUNTS',
|
|
|
|
|
table: 'raw.accounts',
|
|
|
|
|
grain: ['id'],
|
|
|
|
|
columns: [{ name: 'id', type: 'string' }],
|
|
|
|
|
measures: [],
|
|
|
|
|
joins: [],
|
|
|
|
|
} as any,
|
|
|
|
|
} as any,
|
|
|
|
|
baseContext,
|
|
|
|
|
);
|
|
|
|
|
expect(result.structured.success).toBe(false);
|
|
|
|
|
expect(result.markdown).toMatch(/shadows an existing manifest entry|already exists/i);
|
|
|
|
|
});
|
|
|
|
|
});
|