2026-05-20 14:17:10 +02:00
|
|
|
import { describe, expect, it } from 'vitest';
|
|
|
|
|
import {
|
|
|
|
|
compareFinalizationDeclarations,
|
|
|
|
|
deriveFinalizationTouchedSources,
|
|
|
|
|
deriveFinalizationWikiPageKeys,
|
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
|
|
|
} from '../../../src/context/ingest/finalization-scope.js';
|
2026-05-20 14:17:10 +02:00
|
|
|
|
|
|
|
|
describe('deriveFinalizationWikiPageKeys', () => {
|
|
|
|
|
it('maps changed global wiki markdown paths to page keys', () => {
|
|
|
|
|
expect(
|
|
|
|
|
deriveFinalizationWikiPageKeys([
|
|
|
|
|
'wiki/global/historic-sql-orders.md',
|
|
|
|
|
'wiki/global/nested/page.md',
|
|
|
|
|
'README.md',
|
|
|
|
|
]),
|
|
|
|
|
).toEqual(['historic-sql-orders']);
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('deriveFinalizationTouchedSources', () => {
|
fix: read semantic sources safely (#284)
* fix: read semantic sources safely
* test: retarget reindex per-scope error case to a broken manifest
Reading a broken standalone source was made non-fatal in de1f1a8d (it is
surfaced for repair instead of throwing), so the reindex per-scope error
test no longer captured an error. Point it at a corrupt manifest shard,
which is the remaining fatal read failure the per-scope catch must
isolate, and assert the captured error names the offending file.
* fix(sl): decouple semantic-layer file names from warehouse naming rules
The in-file `name:` field is now the sole source identity; the filename is
a derived label that never participates in identity. This removes the
"Unsafe semantic-layer source name" failure class entirely: any warehouse
identifier (Snowflake's uppercase SIGNED_UP, EVENT$LOG, dotted names) can
be read, overlaid, edited, and deleted.
- New `source-files.ts`: one total filename derivation (safe lowercase
names verbatim; otherwise slug + sha256-hash suffix, immune to
case-insensitive-filesystem collisions) and one by-name file resolver.
- Reads resolve by name everywhere; the path-from-name fast path and
`assertSafeSourceName` are gone.
- Writes resolve-then-write: rewrites land on the file that declares the
name (human renames survive); new sources get a derived filename; a
derived path occupied by a different source fails instead of clobbering.
- `readSourceFile` returns null for missing files instead of forcing every
caller to launder IO errors; `deleteSource` distinguishes manifest-backed
sources from not-found instead of silently succeeding.
- `sl_write_source` accepts verbatim warehouse identifiers (snake_case is
now a recommendation for new sources) and rejects sourceName/source.name
mismatches; `sl_edit_source` rejects name-changing edits.
- Ingest projection commits, gate-repair allowlists, and touched-source
derivation use resolved paths / in-file names instead of interpolating
`<connId>/<name>.yaml`.
- Collapsed the five parallel path derivations and duplicated path-token
helpers onto the shared module; dropped dead service methods.
* fix(sl): resolve sources by declared name end-to-end and gate warehouse SQL with the parser-backed validator
- Key broken/renamed semantic-layer files by their recoverable in-file
name (slSourceNameForFile) so mid-edit sources stay reachable under
their real identity in reads, listings, and search
- Derive finalization touched sources from composed-source diffs and
recover deleted files' declared names from the pre-change commit
instead of parsing hash-derived filenames
- Resolve revert/rollback paths against history (listFilesAtCommit) so
human-renamed files are restored where they lived at preHead
- Validate ingest sql_execution through the daemon's sqlglot
validateReadOnly in the connection's dialect, sharing one
driver-to-dialect map (sql-analysis/dialect.ts) across MCP and ingest
- Harden the local read-only SQL backstop: accept leading comments,
reject smuggled second statements, and strip trailing
semicolons/comments before row-limit wrapping
2026-06-10 14:06:13 +02:00
|
|
|
it('resolves standalone files by the source diff, not the filename', () => {
|
|
|
|
|
// The file carries a derived label (`signed_up-<hash>.yaml`); the source it
|
|
|
|
|
// defines is the in-file `name:` (`SIGNED_UP`), visible only via the diff.
|
|
|
|
|
const result = deriveFinalizationTouchedSources({
|
|
|
|
|
changedPaths: ['semantic-layer/warehouse/signed_up-1a2b3c4d.yaml'],
|
|
|
|
|
beforeSourcesByConnection: new Map([['warehouse', []]]),
|
|
|
|
|
afterSourcesByConnection: new Map([
|
|
|
|
|
['warehouse', [{ name: 'SIGNED_UP', grain: [], columns: [], joins: [], measures: [] }]],
|
|
|
|
|
]),
|
|
|
|
|
});
|
|
|
|
|
expect(result).toEqual({
|
|
|
|
|
touchedSources: [{ connectionId: 'warehouse', sourceName: 'SIGNED_UP' }],
|
|
|
|
|
unresolvedPaths: [],
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('resolves deleted standalone files by the name that disappeared', () => {
|
|
|
|
|
const result = deriveFinalizationTouchedSources({
|
|
|
|
|
changedPaths: ['semantic-layer/warehouse/signed_up-1a2b3c4d.yaml'],
|
|
|
|
|
beforeSourcesByConnection: new Map([
|
|
|
|
|
['warehouse', [{ name: 'SIGNED_UP', grain: [], columns: [], joins: [], measures: [] }]],
|
|
|
|
|
]),
|
|
|
|
|
afterSourcesByConnection: new Map([['warehouse', []]]),
|
|
|
|
|
});
|
|
|
|
|
expect(result).toEqual({
|
|
|
|
|
touchedSources: [{ connectionId: 'warehouse', sourceName: 'SIGNED_UP' }],
|
|
|
|
|
unresolvedPaths: [],
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('flags standalone changes that produce no source diff', () => {
|
|
|
|
|
const result = deriveFinalizationTouchedSources({
|
2026-05-20 14:17:10 +02:00
|
|
|
changedPaths: ['semantic-layer/warehouse/orders.yaml'],
|
|
|
|
|
beforeSourcesByConnection: new Map(),
|
|
|
|
|
afterSourcesByConnection: new Map(),
|
|
|
|
|
});
|
|
|
|
|
expect(result).toEqual({
|
fix: read semantic sources safely (#284)
* fix: read semantic sources safely
* test: retarget reindex per-scope error case to a broken manifest
Reading a broken standalone source was made non-fatal in de1f1a8d (it is
surfaced for repair instead of throwing), so the reindex per-scope error
test no longer captured an error. Point it at a corrupt manifest shard,
which is the remaining fatal read failure the per-scope catch must
isolate, and assert the captured error names the offending file.
* fix(sl): decouple semantic-layer file names from warehouse naming rules
The in-file `name:` field is now the sole source identity; the filename is
a derived label that never participates in identity. This removes the
"Unsafe semantic-layer source name" failure class entirely: any warehouse
identifier (Snowflake's uppercase SIGNED_UP, EVENT$LOG, dotted names) can
be read, overlaid, edited, and deleted.
- New `source-files.ts`: one total filename derivation (safe lowercase
names verbatim; otherwise slug + sha256-hash suffix, immune to
case-insensitive-filesystem collisions) and one by-name file resolver.
- Reads resolve by name everywhere; the path-from-name fast path and
`assertSafeSourceName` are gone.
- Writes resolve-then-write: rewrites land on the file that declares the
name (human renames survive); new sources get a derived filename; a
derived path occupied by a different source fails instead of clobbering.
- `readSourceFile` returns null for missing files instead of forcing every
caller to launder IO errors; `deleteSource` distinguishes manifest-backed
sources from not-found instead of silently succeeding.
- `sl_write_source` accepts verbatim warehouse identifiers (snake_case is
now a recommendation for new sources) and rejects sourceName/source.name
mismatches; `sl_edit_source` rejects name-changing edits.
- Ingest projection commits, gate-repair allowlists, and touched-source
derivation use resolved paths / in-file names instead of interpolating
`<connId>/<name>.yaml`.
- Collapsed the five parallel path derivations and duplicated path-token
helpers onto the shared module; dropped dead service methods.
* fix(sl): resolve sources by declared name end-to-end and gate warehouse SQL with the parser-backed validator
- Key broken/renamed semantic-layer files by their recoverable in-file
name (slSourceNameForFile) so mid-edit sources stay reachable under
their real identity in reads, listings, and search
- Derive finalization touched sources from composed-source diffs and
recover deleted files' declared names from the pre-change commit
instead of parsing hash-derived filenames
- Resolve revert/rollback paths against history (listFilesAtCommit) so
human-renamed files are restored where they lived at preHead
- Validate ingest sql_execution through the daemon's sqlglot
validateReadOnly in the connection's dialect, sharing one
driver-to-dialect map (sql-analysis/dialect.ts) across MCP and ingest
- Harden the local read-only SQL backstop: accept leading comments,
reject smuggled second statements, and strip trailing
semicolons/comments before row-limit wrapping
2026-06-10 14:06:13 +02:00
|
|
|
touchedSources: [],
|
|
|
|
|
unresolvedPaths: ['semantic-layer/warehouse/orders.yaml'],
|
2026-05-20 14:17:10 +02:00
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
fix: read semantic sources safely (#284)
* fix: read semantic sources safely
* test: retarget reindex per-scope error case to a broken manifest
Reading a broken standalone source was made non-fatal in de1f1a8d (it is
surfaced for repair instead of throwing), so the reindex per-scope error
test no longer captured an error. Point it at a corrupt manifest shard,
which is the remaining fatal read failure the per-scope catch must
isolate, and assert the captured error names the offending file.
* fix(sl): decouple semantic-layer file names from warehouse naming rules
The in-file `name:` field is now the sole source identity; the filename is
a derived label that never participates in identity. This removes the
"Unsafe semantic-layer source name" failure class entirely: any warehouse
identifier (Snowflake's uppercase SIGNED_UP, EVENT$LOG, dotted names) can
be read, overlaid, edited, and deleted.
- New `source-files.ts`: one total filename derivation (safe lowercase
names verbatim; otherwise slug + sha256-hash suffix, immune to
case-insensitive-filesystem collisions) and one by-name file resolver.
- Reads resolve by name everywhere; the path-from-name fast path and
`assertSafeSourceName` are gone.
- Writes resolve-then-write: rewrites land on the file that declares the
name (human renames survive); new sources get a derived filename; a
derived path occupied by a different source fails instead of clobbering.
- `readSourceFile` returns null for missing files instead of forcing every
caller to launder IO errors; `deleteSource` distinguishes manifest-backed
sources from not-found instead of silently succeeding.
- `sl_write_source` accepts verbatim warehouse identifiers (snake_case is
now a recommendation for new sources) and rejects sourceName/source.name
mismatches; `sl_edit_source` rejects name-changing edits.
- Ingest projection commits, gate-repair allowlists, and touched-source
derivation use resolved paths / in-file names instead of interpolating
`<connId>/<name>.yaml`.
- Collapsed the five parallel path derivations and duplicated path-token
helpers onto the shared module; dropped dead service methods.
* fix(sl): resolve sources by declared name end-to-end and gate warehouse SQL with the parser-backed validator
- Key broken/renamed semantic-layer files by their recoverable in-file
name (slSourceNameForFile) so mid-edit sources stay reachable under
their real identity in reads, listings, and search
- Derive finalization touched sources from composed-source diffs and
recover deleted files' declared names from the pre-change commit
instead of parsing hash-derived filenames
- Resolve revert/rollback paths against history (listFilesAtCommit) so
human-renamed files are restored where they lived at preHead
- Validate ingest sql_execution through the daemon's sqlglot
validateReadOnly in the connection's dialect, sharing one
driver-to-dialect map (sql-analysis/dialect.ts) across MCP and ingest
- Harden the local read-only SQL backstop: accept leading comments,
reject smuggled second statements, and strip trailing
semicolons/comments before row-limit wrapping
2026-06-10 14:06:13 +02:00
|
|
|
it('resolves aggregate _schema changes by comparing loaded source snapshots', () => {
|
2026-05-20 14:17:10 +02:00
|
|
|
const beforeSourcesByConnection = new Map([
|
|
|
|
|
[
|
|
|
|
|
'warehouse',
|
|
|
|
|
[
|
|
|
|
|
{
|
|
|
|
|
name: 'orders',
|
|
|
|
|
grain: ['order_id'],
|
|
|
|
|
columns: [{ name: 'order_id', type: 'string' }],
|
|
|
|
|
joins: [],
|
|
|
|
|
measures: [],
|
|
|
|
|
usage: {
|
|
|
|
|
narrative: 'old',
|
|
|
|
|
frequencyTier: 'low' as const,
|
|
|
|
|
commonFilters: [],
|
|
|
|
|
commonJoins: [],
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
],
|
|
|
|
|
],
|
|
|
|
|
]);
|
|
|
|
|
const afterSourcesByConnection = new Map([
|
|
|
|
|
[
|
|
|
|
|
'warehouse',
|
|
|
|
|
[
|
|
|
|
|
{
|
|
|
|
|
name: 'orders',
|
|
|
|
|
grain: ['order_id'],
|
|
|
|
|
columns: [{ name: 'order_id', type: 'string' }],
|
|
|
|
|
joins: [],
|
|
|
|
|
measures: [],
|
|
|
|
|
usage: {
|
|
|
|
|
narrative: 'new',
|
|
|
|
|
frequencyTier: 'high' as const,
|
|
|
|
|
commonFilters: [],
|
|
|
|
|
commonJoins: [],
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
],
|
|
|
|
|
],
|
|
|
|
|
]);
|
|
|
|
|
|
fix: read semantic sources safely (#284)
* fix: read semantic sources safely
* test: retarget reindex per-scope error case to a broken manifest
Reading a broken standalone source was made non-fatal in de1f1a8d (it is
surfaced for repair instead of throwing), so the reindex per-scope error
test no longer captured an error. Point it at a corrupt manifest shard,
which is the remaining fatal read failure the per-scope catch must
isolate, and assert the captured error names the offending file.
* fix(sl): decouple semantic-layer file names from warehouse naming rules
The in-file `name:` field is now the sole source identity; the filename is
a derived label that never participates in identity. This removes the
"Unsafe semantic-layer source name" failure class entirely: any warehouse
identifier (Snowflake's uppercase SIGNED_UP, EVENT$LOG, dotted names) can
be read, overlaid, edited, and deleted.
- New `source-files.ts`: one total filename derivation (safe lowercase
names verbatim; otherwise slug + sha256-hash suffix, immune to
case-insensitive-filesystem collisions) and one by-name file resolver.
- Reads resolve by name everywhere; the path-from-name fast path and
`assertSafeSourceName` are gone.
- Writes resolve-then-write: rewrites land on the file that declares the
name (human renames survive); new sources get a derived filename; a
derived path occupied by a different source fails instead of clobbering.
- `readSourceFile` returns null for missing files instead of forcing every
caller to launder IO errors; `deleteSource` distinguishes manifest-backed
sources from not-found instead of silently succeeding.
- `sl_write_source` accepts verbatim warehouse identifiers (snake_case is
now a recommendation for new sources) and rejects sourceName/source.name
mismatches; `sl_edit_source` rejects name-changing edits.
- Ingest projection commits, gate-repair allowlists, and touched-source
derivation use resolved paths / in-file names instead of interpolating
`<connId>/<name>.yaml`.
- Collapsed the five parallel path derivations and duplicated path-token
helpers onto the shared module; dropped dead service methods.
* fix(sl): resolve sources by declared name end-to-end and gate warehouse SQL with the parser-backed validator
- Key broken/renamed semantic-layer files by their recoverable in-file
name (slSourceNameForFile) so mid-edit sources stay reachable under
their real identity in reads, listings, and search
- Derive finalization touched sources from composed-source diffs and
recover deleted files' declared names from the pre-change commit
instead of parsing hash-derived filenames
- Resolve revert/rollback paths against history (listFilesAtCommit) so
human-renamed files are restored where they lived at preHead
- Validate ingest sql_execution through the daemon's sqlglot
validateReadOnly in the connection's dialect, sharing one
driver-to-dialect map (sql-analysis/dialect.ts) across MCP and ingest
- Harden the local read-only SQL backstop: accept leading comments,
reject smuggled second statements, and strip trailing
semicolons/comments before row-limit wrapping
2026-06-10 14:06:13 +02:00
|
|
|
const result = deriveFinalizationTouchedSources({
|
2026-05-20 14:17:10 +02:00
|
|
|
changedPaths: ['semantic-layer/warehouse/_schema/public.yaml'],
|
|
|
|
|
beforeSourcesByConnection,
|
|
|
|
|
afterSourcesByConnection,
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(result).toEqual({
|
|
|
|
|
touchedSources: [{ connectionId: 'warehouse', sourceName: 'orders' }],
|
|
|
|
|
unresolvedPaths: [],
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
fix: read semantic sources safely (#284)
* fix: read semantic sources safely
* test: retarget reindex per-scope error case to a broken manifest
Reading a broken standalone source was made non-fatal in de1f1a8d (it is
surfaced for repair instead of throwing), so the reindex per-scope error
test no longer captured an error. Point it at a corrupt manifest shard,
which is the remaining fatal read failure the per-scope catch must
isolate, and assert the captured error names the offending file.
* fix(sl): decouple semantic-layer file names from warehouse naming rules
The in-file `name:` field is now the sole source identity; the filename is
a derived label that never participates in identity. This removes the
"Unsafe semantic-layer source name" failure class entirely: any warehouse
identifier (Snowflake's uppercase SIGNED_UP, EVENT$LOG, dotted names) can
be read, overlaid, edited, and deleted.
- New `source-files.ts`: one total filename derivation (safe lowercase
names verbatim; otherwise slug + sha256-hash suffix, immune to
case-insensitive-filesystem collisions) and one by-name file resolver.
- Reads resolve by name everywhere; the path-from-name fast path and
`assertSafeSourceName` are gone.
- Writes resolve-then-write: rewrites land on the file that declares the
name (human renames survive); new sources get a derived filename; a
derived path occupied by a different source fails instead of clobbering.
- `readSourceFile` returns null for missing files instead of forcing every
caller to launder IO errors; `deleteSource` distinguishes manifest-backed
sources from not-found instead of silently succeeding.
- `sl_write_source` accepts verbatim warehouse identifiers (snake_case is
now a recommendation for new sources) and rejects sourceName/source.name
mismatches; `sl_edit_source` rejects name-changing edits.
- Ingest projection commits, gate-repair allowlists, and touched-source
derivation use resolved paths / in-file names instead of interpolating
`<connId>/<name>.yaml`.
- Collapsed the five parallel path derivations and duplicated path-token
helpers onto the shared module; dropped dead service methods.
* fix(sl): resolve sources by declared name end-to-end and gate warehouse SQL with the parser-backed validator
- Key broken/renamed semantic-layer files by their recoverable in-file
name (slSourceNameForFile) so mid-edit sources stay reachable under
their real identity in reads, listings, and search
- Derive finalization touched sources from composed-source diffs and
recover deleted files' declared names from the pre-change commit
instead of parsing hash-derived filenames
- Resolve revert/rollback paths against history (listFilesAtCommit) so
human-renamed files are restored where they lived at preHead
- Validate ingest sql_execution through the daemon's sqlglot
validateReadOnly in the connection's dialect, sharing one
driver-to-dialect map (sql-analysis/dialect.ts) across MCP and ingest
- Harden the local read-only SQL backstop: accept leading comments,
reject smuggled second statements, and strip trailing
semicolons/comments before row-limit wrapping
2026-06-10 14:06:13 +02:00
|
|
|
it('flags aggregate _schema changes that cannot be resolved to logical sources', () => {
|
2026-05-20 14:17:10 +02:00
|
|
|
const beforeSourcesByConnection = new Map([['warehouse', []]]);
|
|
|
|
|
const afterSourcesByConnection = new Map([['warehouse', []]]);
|
|
|
|
|
|
fix: read semantic sources safely (#284)
* fix: read semantic sources safely
* test: retarget reindex per-scope error case to a broken manifest
Reading a broken standalone source was made non-fatal in de1f1a8d (it is
surfaced for repair instead of throwing), so the reindex per-scope error
test no longer captured an error. Point it at a corrupt manifest shard,
which is the remaining fatal read failure the per-scope catch must
isolate, and assert the captured error names the offending file.
* fix(sl): decouple semantic-layer file names from warehouse naming rules
The in-file `name:` field is now the sole source identity; the filename is
a derived label that never participates in identity. This removes the
"Unsafe semantic-layer source name" failure class entirely: any warehouse
identifier (Snowflake's uppercase SIGNED_UP, EVENT$LOG, dotted names) can
be read, overlaid, edited, and deleted.
- New `source-files.ts`: one total filename derivation (safe lowercase
names verbatim; otherwise slug + sha256-hash suffix, immune to
case-insensitive-filesystem collisions) and one by-name file resolver.
- Reads resolve by name everywhere; the path-from-name fast path and
`assertSafeSourceName` are gone.
- Writes resolve-then-write: rewrites land on the file that declares the
name (human renames survive); new sources get a derived filename; a
derived path occupied by a different source fails instead of clobbering.
- `readSourceFile` returns null for missing files instead of forcing every
caller to launder IO errors; `deleteSource` distinguishes manifest-backed
sources from not-found instead of silently succeeding.
- `sl_write_source` accepts verbatim warehouse identifiers (snake_case is
now a recommendation for new sources) and rejects sourceName/source.name
mismatches; `sl_edit_source` rejects name-changing edits.
- Ingest projection commits, gate-repair allowlists, and touched-source
derivation use resolved paths / in-file names instead of interpolating
`<connId>/<name>.yaml`.
- Collapsed the five parallel path derivations and duplicated path-token
helpers onto the shared module; dropped dead service methods.
* fix(sl): resolve sources by declared name end-to-end and gate warehouse SQL with the parser-backed validator
- Key broken/renamed semantic-layer files by their recoverable in-file
name (slSourceNameForFile) so mid-edit sources stay reachable under
their real identity in reads, listings, and search
- Derive finalization touched sources from composed-source diffs and
recover deleted files' declared names from the pre-change commit
instead of parsing hash-derived filenames
- Resolve revert/rollback paths against history (listFilesAtCommit) so
human-renamed files are restored where they lived at preHead
- Validate ingest sql_execution through the daemon's sqlglot
validateReadOnly in the connection's dialect, sharing one
driver-to-dialect map (sql-analysis/dialect.ts) across MCP and ingest
- Harden the local read-only SQL backstop: accept leading comments,
reject smuggled second statements, and strip trailing
semicolons/comments before row-limit wrapping
2026-06-10 14:06:13 +02:00
|
|
|
const result = deriveFinalizationTouchedSources({
|
2026-05-20 14:17:10 +02:00
|
|
|
changedPaths: ['semantic-layer/warehouse/_schema/public.yaml'],
|
|
|
|
|
beforeSourcesByConnection,
|
|
|
|
|
afterSourcesByConnection,
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(result).toEqual({
|
|
|
|
|
touchedSources: [],
|
|
|
|
|
unresolvedPaths: ['semantic-layer/warehouse/_schema/public.yaml'],
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('compareFinalizationDeclarations', () => {
|
|
|
|
|
it('reports missing and extra adapter declarations', () => {
|
|
|
|
|
expect(
|
|
|
|
|
compareFinalizationDeclarations({
|
|
|
|
|
declaredTouchedSources: [{ connectionId: 'warehouse', sourceName: 'orders' }],
|
|
|
|
|
derivedTouchedSources: [{ connectionId: 'warehouse', sourceName: 'customers' }],
|
|
|
|
|
declaredChangedWikiPageKeys: ['orders'],
|
|
|
|
|
derivedChangedWikiPageKeys: ['orders', 'patterns'],
|
|
|
|
|
}),
|
|
|
|
|
).toEqual([
|
|
|
|
|
{
|
|
|
|
|
artifactKind: 'sl',
|
|
|
|
|
key: 'warehouse:customers',
|
|
|
|
|
direction: 'missing_from_adapter_declaration',
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
artifactKind: 'sl',
|
|
|
|
|
key: 'warehouse:orders',
|
|
|
|
|
direction: 'extra_in_adapter_declaration',
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
artifactKind: 'wiki',
|
|
|
|
|
key: 'patterns',
|
|
|
|
|
direction: 'missing_from_adapter_declaration',
|
|
|
|
|
},
|
|
|
|
|
]);
|
|
|
|
|
});
|
|
|
|
|
});
|