ktx/packages/cli/test/scan.test.ts

1524 lines
48 KiB
TypeScript
Raw Permalink Normal View History

import { mkdir, mkdtemp, readFile, rm, writeFile } from 'node:fs/promises';
2026-05-10 23:12:26 +02:00
import { tmpdir } from 'node:os';
import { join } from 'node:path';
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 { SourceAdapter } from '../src/context/ingest/types.js';
import { parseKtxProjectConfig, serializeKtxProjectConfig } from '../src/context/project/config.js';
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 { initKtxProject } from '../src/context/project/project.js';
import type { KtxScanReport } from '../src/context/scan/types.js';
import type { LocalScanRunResult, RunLocalScanOptions } from '../src/context/scan/local-scan.js';
2026-05-10 23:12:26 +02:00
import { afterEach, beforeEach, 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 { createCliScanProgress, runKtxScan, type KtxScanDeps } from '../src/scan.js';
2026-05-10 23:12:26 +02:00
const reportExceptionMock = vi.hoisted(() => vi.fn(async () => {}));
vi.mock('../src/telemetry/exception.js', () => ({
reportException: reportExceptionMock,
}));
2026-05-10 23:12:26 +02:00
const sqlServerExtractSchema = vi.hoisted(() =>
vi.fn(async (connectionId: string) => ({
connectionId,
extractedAt: '2026-04-29T16:00:00.000Z',
metadata: { database: 'analytics' },
tables: [
{
catalog: 'analytics',
db: 'dbo',
name: 'orders',
columns: [{ name: 'id', type: 'int', nullable: false, primaryKey: true }],
foreignKeys: [],
},
],
})),
);
const createSqlServerLiveDatabaseIntrospection = vi.hoisted(() =>
vi.fn(() => ({ extractSchema: sqlServerExtractSchema })),
);
2026-05-10 23:51:24 +02:00
const isKtxSqlServerConnectionConfig = vi.hoisted(() =>
2026-05-10 23:12:26 +02:00
vi.fn((connection: { driver?: string } | undefined) => connection?.driver === 'sqlserver'),
);
2026-05-10 23:51:24 +02:00
const KtxSqlServerScanConnector = vi.hoisted(
2026-05-10 23:12:26 +02:00
() =>
class {
readonly id: string;
readonly driver = 'sqlserver';
constructor(options: { connectionId: string }) {
this.id = `sqlserver:${options.connectionId}`;
}
},
);
const bigQueryExtractSchema = vi.hoisted(() =>
vi.fn(async (connectionId: string) => ({
connectionId,
extractedAt: '2026-04-29T17:00:00.000Z',
metadata: { project_id: 'project-1', datasets: ['analytics'] },
tables: [
{
catalog: 'project-1',
db: 'analytics',
name: 'orders',
columns: [{ name: 'id', type: 'INT64', nullable: false, primaryKey: true }],
foreignKeys: [],
},
],
})),
);
const createBigQueryLiveDatabaseIntrospection = vi.hoisted(() =>
vi.fn(() => ({ extractSchema: bigQueryExtractSchema })),
);
2026-05-10 23:51:24 +02:00
const isKtxBigQueryConnectionConfig = vi.hoisted(() =>
2026-05-10 23:12:26 +02:00
vi.fn((connection: { driver?: string } | undefined) => connection?.driver === 'bigquery'),
);
2026-05-10 23:51:24 +02:00
const KtxBigQueryScanConnector = vi.hoisted(
2026-05-10 23:12:26 +02:00
() =>
class {
readonly id: string;
readonly driver = 'bigquery';
constructor(options: { connectionId: string }) {
this.id = `bigquery:${options.connectionId}`;
}
},
);
const snowflakeExtractSchema = vi.hoisted(() =>
vi.fn(async (connectionId: string) => ({
connectionId,
extractedAt: '2026-04-29T18:00:00.000Z',
metadata: { database: 'ANALYTICS', schemas: ['PUBLIC'] },
tables: [
{
catalog: 'ANALYTICS',
db: 'PUBLIC',
name: 'ORDERS',
columns: [{ name: 'ID', type: 'NUMBER', nullable: false, primaryKey: true }],
foreignKeys: [],
},
],
})),
);
const createSnowflakeLiveDatabaseIntrospection = vi.hoisted(() =>
vi.fn(() => ({ extractSchema: snowflakeExtractSchema })),
);
2026-05-10 23:51:24 +02:00
const isKtxSnowflakeConnectionConfig = vi.hoisted(() =>
2026-05-10 23:12:26 +02:00
vi.fn((connection: { driver?: string } | undefined) => connection?.driver === 'snowflake'),
);
fix(snowflake): unblock multi-schema ingest and relationship discovery (#204) * feat(setup): drop redundant Snowflake schema prompt; fall back to free-text on listSchemas failure Snowflake setup previously asked for a single schema as free text, then ran a multiselect against the discovered schemas — two schema questions back-to-back, with the first being only a session bootstrap. The SDK's `schema` is optional, so the bootstrap step is unnecessary. - Remove the free-text Snowflake schema prompt; only pass `schema` to snowflake-sdk when one is configured. - When `listSchemas()` fails (e.g. role lacks SHOW SCHEMAS), prompt the user for a comma-separated list, persist it as `schema_names`, and use it as both the table-list filter and the multiselect default. Applies to every driver with a scope-discovery spec, not just Snowflake. - Update docs to lead with `schema_names`; keep `schema_name` as a documented single-schema shorthand. * fix(snowflake): keep introspecting when primary-key discovery is denied The PK query joins INFORMATION_SCHEMA.TABLE_CONSTRAINTS and INFORMATION_SCHEMA.KEY_COLUMN_USAGE, which require grants the connection role may not have. Previously a 'SQL compilation error: Object ANALYTICS.INFORMATION_SCHEMA.KEY_COLUMN_USAGE does not exist or not authorized' aborted the entire introspect — schemas, columns, and row counts were all discarded over a missing nice-to-have. Wrap the constraint query in try/catch, log a one-line warning per schema, and return an empty PK map. Columns end up with primaryKey=false; relationship inference still has FK and profiling to fall back on. * fix(scan): unblock relationship discovery on Snowflake Two adjacent bugs prevented the scan's relationship pipeline from producing any joins on a Snowflake warehouse: - relationship-profiling.ts fell through to a default `GROUP_CONCAT` branch for unknown drivers. Snowflake has no GROUP_CONCAT, so every per-table profile query failed with "Unknown function GROUP_CONCAT". Add an explicit Snowflake branch that uses LISTAGG with a literal '\x1f' delimiter (Snowflake requires the delimiter to be a constant, so CHR(31) is rejected). - description-generation.ts destructured `connector.sampleTable` and `connector.sampleColumn` into bare locals, losing the `this` binding when the class-method connectors (Snowflake, Postgres, MySQL) were invoked. Every sample call threw "Cannot read properties of undefined (reading 'assertConnection')" and degraded LLM descriptions to metadata-only prompts. Call the methods through the connector instead. Without these, even after the primary-key probe is allowed to fail softly, the scan ends up with 0 validated relationships and an empty `joins:` block in every shard YAML. * test(scan): cover table-ref helpers * feat(scan): plumb tableScope through live-database introspection port * feat(scan): apply tableScope during metadata fetch * feat(scan): enforce table scope at fetch boundary * feat(scan): pool Snowflake sessions and batch enrichment for faster ingest (#206) * feat(cli): add RSA key-pair auth option to Snowflake setup wizard Extends the interactive Snowflake setup flow with an authentication-method prompt (password vs RSA/JWT key-pair). The RSA branch collects a private-key path (env/file/absolute) and an optional passphrase; the resulting connection config records `authMethod: 'rsa'` with `privateKey` and `passphrase` instead of `password`. * feat(scan): pool Snowflake sessions * fix(scan): reuse structural snapshots and cleanup connectors * feat(scan): parallelize relationship profiling * feat(scan): batch table description generation * docs: document Snowflake ingest concurrency knobs * fix(scan): close Snowflake ingest perf verification gaps * fix(scan): keep batched description failure bounded * feat(scan): dispatch query-history probes by connection driver Extract historic-sql dialect resolution into a shared helper so the status-project readiness check and the local ingest factory agree on which connections enable query history and which probe to run. The status command now picks the postgres/snowflake/bigquery probe based on the connection's driver instead of always reporting against postgres, which previously caused snowflake connections with queryHistory.enabled to surface a misleading "driver is snowflake" failure. Also drops a noisy console.warn from Snowflake primary-key discovery — INFORMATION_SCHEMA.KEY_COLUMN_USAGE is commonly ungranted for read-only roles and the FK + profiling paths handle the empty PK map already. * fix(llm): allow StructuredOutput tool and raise maxTurns for generateObject The Claude Code agent SDK announces an internal pseudo-tool named StructuredOutput in the system/init message whenever outputFormat is set to { type: 'json_schema' }. The runtime's isolation check built its allowedToolIds set only from MCP tool ids and treated StructuredOutput as an unexpected host-injected tool, so every generateObject call threw "Claude Code runtime isolation failed: tools=StructuredOutput ..." and the table-descriptions and relationship-LLM-proposal enrichment stages recorded null output across the board. Whitelist StructuredOutput specifically in generateObject's allowedToolIds — the check also enforces missing_tools symmetry, so generateText and runAgentLoop, which do not see StructuredOutput, must not require it. generateObject also ran with maxTurns: 1, which the model intermittently breached when it emitted thinking text before the structured response. Raised to 5 to give the schema-bound call enough headroom without allowing unbounded loops. The existing tests now exercise the path with an init message that announces StructuredOutput so the regression cannot slip back in. * chore(scripts): add ktx-reset.sh project-cleanup helper Convenience script for repeatable ingest testing: takes a project directory and prunes everything except ktx.yaml and .ktx/secrets/, so the next ktx setup or ktx ingest run starts from a known-clean state.
2026-05-23 10:41:30 +02:00
const snowflakeConnectorInstances = vi.hoisted(() => [] as Array<{ cleanup: ReturnType<typeof vi.fn> }>);
2026-05-10 23:51:24 +02:00
const KtxSnowflakeScanConnector = vi.hoisted(
2026-05-10 23:12:26 +02:00
() =>
class {
readonly id: string;
readonly driver = 'snowflake';
fix(snowflake): unblock multi-schema ingest and relationship discovery (#204) * feat(setup): drop redundant Snowflake schema prompt; fall back to free-text on listSchemas failure Snowflake setup previously asked for a single schema as free text, then ran a multiselect against the discovered schemas — two schema questions back-to-back, with the first being only a session bootstrap. The SDK's `schema` is optional, so the bootstrap step is unnecessary. - Remove the free-text Snowflake schema prompt; only pass `schema` to snowflake-sdk when one is configured. - When `listSchemas()` fails (e.g. role lacks SHOW SCHEMAS), prompt the user for a comma-separated list, persist it as `schema_names`, and use it as both the table-list filter and the multiselect default. Applies to every driver with a scope-discovery spec, not just Snowflake. - Update docs to lead with `schema_names`; keep `schema_name` as a documented single-schema shorthand. * fix(snowflake): keep introspecting when primary-key discovery is denied The PK query joins INFORMATION_SCHEMA.TABLE_CONSTRAINTS and INFORMATION_SCHEMA.KEY_COLUMN_USAGE, which require grants the connection role may not have. Previously a 'SQL compilation error: Object ANALYTICS.INFORMATION_SCHEMA.KEY_COLUMN_USAGE does not exist or not authorized' aborted the entire introspect — schemas, columns, and row counts were all discarded over a missing nice-to-have. Wrap the constraint query in try/catch, log a one-line warning per schema, and return an empty PK map. Columns end up with primaryKey=false; relationship inference still has FK and profiling to fall back on. * fix(scan): unblock relationship discovery on Snowflake Two adjacent bugs prevented the scan's relationship pipeline from producing any joins on a Snowflake warehouse: - relationship-profiling.ts fell through to a default `GROUP_CONCAT` branch for unknown drivers. Snowflake has no GROUP_CONCAT, so every per-table profile query failed with "Unknown function GROUP_CONCAT". Add an explicit Snowflake branch that uses LISTAGG with a literal '\x1f' delimiter (Snowflake requires the delimiter to be a constant, so CHR(31) is rejected). - description-generation.ts destructured `connector.sampleTable` and `connector.sampleColumn` into bare locals, losing the `this` binding when the class-method connectors (Snowflake, Postgres, MySQL) were invoked. Every sample call threw "Cannot read properties of undefined (reading 'assertConnection')" and degraded LLM descriptions to metadata-only prompts. Call the methods through the connector instead. Without these, even after the primary-key probe is allowed to fail softly, the scan ends up with 0 validated relationships and an empty `joins:` block in every shard YAML. * test(scan): cover table-ref helpers * feat(scan): plumb tableScope through live-database introspection port * feat(scan): apply tableScope during metadata fetch * feat(scan): enforce table scope at fetch boundary * feat(scan): pool Snowflake sessions and batch enrichment for faster ingest (#206) * feat(cli): add RSA key-pair auth option to Snowflake setup wizard Extends the interactive Snowflake setup flow with an authentication-method prompt (password vs RSA/JWT key-pair). The RSA branch collects a private-key path (env/file/absolute) and an optional passphrase; the resulting connection config records `authMethod: 'rsa'` with `privateKey` and `passphrase` instead of `password`. * feat(scan): pool Snowflake sessions * fix(scan): reuse structural snapshots and cleanup connectors * feat(scan): parallelize relationship profiling * feat(scan): batch table description generation * docs: document Snowflake ingest concurrency knobs * fix(scan): close Snowflake ingest perf verification gaps * fix(scan): keep batched description failure bounded * feat(scan): dispatch query-history probes by connection driver Extract historic-sql dialect resolution into a shared helper so the status-project readiness check and the local ingest factory agree on which connections enable query history and which probe to run. The status command now picks the postgres/snowflake/bigquery probe based on the connection's driver instead of always reporting against postgres, which previously caused snowflake connections with queryHistory.enabled to surface a misleading "driver is snowflake" failure. Also drops a noisy console.warn from Snowflake primary-key discovery — INFORMATION_SCHEMA.KEY_COLUMN_USAGE is commonly ungranted for read-only roles and the FK + profiling paths handle the empty PK map already. * fix(llm): allow StructuredOutput tool and raise maxTurns for generateObject The Claude Code agent SDK announces an internal pseudo-tool named StructuredOutput in the system/init message whenever outputFormat is set to { type: 'json_schema' }. The runtime's isolation check built its allowedToolIds set only from MCP tool ids and treated StructuredOutput as an unexpected host-injected tool, so every generateObject call threw "Claude Code runtime isolation failed: tools=StructuredOutput ..." and the table-descriptions and relationship-LLM-proposal enrichment stages recorded null output across the board. Whitelist StructuredOutput specifically in generateObject's allowedToolIds — the check also enforces missing_tools symmetry, so generateText and runAgentLoop, which do not see StructuredOutput, must not require it. generateObject also ran with maxTurns: 1, which the model intermittently breached when it emitted thinking text before the structured response. Raised to 5 to give the schema-bound call enough headroom without allowing unbounded loops. The existing tests now exercise the path with an init message that announces StructuredOutput so the regression cannot slip back in. * chore(scripts): add ktx-reset.sh project-cleanup helper Convenience script for repeatable ingest testing: takes a project directory and prunes everything except ktx.yaml and .ktx/secrets/, so the next ktx setup or ktx ingest run starts from a known-clean state.
2026-05-23 10:41:30 +02:00
readonly cleanup = vi.fn(async () => undefined);
2026-05-10 23:12:26 +02:00
constructor(options: { connectionId: string }) {
this.id = `snowflake:${options.connectionId}`;
fix(snowflake): unblock multi-schema ingest and relationship discovery (#204) * feat(setup): drop redundant Snowflake schema prompt; fall back to free-text on listSchemas failure Snowflake setup previously asked for a single schema as free text, then ran a multiselect against the discovered schemas — two schema questions back-to-back, with the first being only a session bootstrap. The SDK's `schema` is optional, so the bootstrap step is unnecessary. - Remove the free-text Snowflake schema prompt; only pass `schema` to snowflake-sdk when one is configured. - When `listSchemas()` fails (e.g. role lacks SHOW SCHEMAS), prompt the user for a comma-separated list, persist it as `schema_names`, and use it as both the table-list filter and the multiselect default. Applies to every driver with a scope-discovery spec, not just Snowflake. - Update docs to lead with `schema_names`; keep `schema_name` as a documented single-schema shorthand. * fix(snowflake): keep introspecting when primary-key discovery is denied The PK query joins INFORMATION_SCHEMA.TABLE_CONSTRAINTS and INFORMATION_SCHEMA.KEY_COLUMN_USAGE, which require grants the connection role may not have. Previously a 'SQL compilation error: Object ANALYTICS.INFORMATION_SCHEMA.KEY_COLUMN_USAGE does not exist or not authorized' aborted the entire introspect — schemas, columns, and row counts were all discarded over a missing nice-to-have. Wrap the constraint query in try/catch, log a one-line warning per schema, and return an empty PK map. Columns end up with primaryKey=false; relationship inference still has FK and profiling to fall back on. * fix(scan): unblock relationship discovery on Snowflake Two adjacent bugs prevented the scan's relationship pipeline from producing any joins on a Snowflake warehouse: - relationship-profiling.ts fell through to a default `GROUP_CONCAT` branch for unknown drivers. Snowflake has no GROUP_CONCAT, so every per-table profile query failed with "Unknown function GROUP_CONCAT". Add an explicit Snowflake branch that uses LISTAGG with a literal '\x1f' delimiter (Snowflake requires the delimiter to be a constant, so CHR(31) is rejected). - description-generation.ts destructured `connector.sampleTable` and `connector.sampleColumn` into bare locals, losing the `this` binding when the class-method connectors (Snowflake, Postgres, MySQL) were invoked. Every sample call threw "Cannot read properties of undefined (reading 'assertConnection')" and degraded LLM descriptions to metadata-only prompts. Call the methods through the connector instead. Without these, even after the primary-key probe is allowed to fail softly, the scan ends up with 0 validated relationships and an empty `joins:` block in every shard YAML. * test(scan): cover table-ref helpers * feat(scan): plumb tableScope through live-database introspection port * feat(scan): apply tableScope during metadata fetch * feat(scan): enforce table scope at fetch boundary * feat(scan): pool Snowflake sessions and batch enrichment for faster ingest (#206) * feat(cli): add RSA key-pair auth option to Snowflake setup wizard Extends the interactive Snowflake setup flow with an authentication-method prompt (password vs RSA/JWT key-pair). The RSA branch collects a private-key path (env/file/absolute) and an optional passphrase; the resulting connection config records `authMethod: 'rsa'` with `privateKey` and `passphrase` instead of `password`. * feat(scan): pool Snowflake sessions * fix(scan): reuse structural snapshots and cleanup connectors * feat(scan): parallelize relationship profiling * feat(scan): batch table description generation * docs: document Snowflake ingest concurrency knobs * fix(scan): close Snowflake ingest perf verification gaps * fix(scan): keep batched description failure bounded * feat(scan): dispatch query-history probes by connection driver Extract historic-sql dialect resolution into a shared helper so the status-project readiness check and the local ingest factory agree on which connections enable query history and which probe to run. The status command now picks the postgres/snowflake/bigquery probe based on the connection's driver instead of always reporting against postgres, which previously caused snowflake connections with queryHistory.enabled to surface a misleading "driver is snowflake" failure. Also drops a noisy console.warn from Snowflake primary-key discovery — INFORMATION_SCHEMA.KEY_COLUMN_USAGE is commonly ungranted for read-only roles and the FK + profiling paths handle the empty PK map already. * fix(llm): allow StructuredOutput tool and raise maxTurns for generateObject The Claude Code agent SDK announces an internal pseudo-tool named StructuredOutput in the system/init message whenever outputFormat is set to { type: 'json_schema' }. The runtime's isolation check built its allowedToolIds set only from MCP tool ids and treated StructuredOutput as an unexpected host-injected tool, so every generateObject call threw "Claude Code runtime isolation failed: tools=StructuredOutput ..." and the table-descriptions and relationship-LLM-proposal enrichment stages recorded null output across the board. Whitelist StructuredOutput specifically in generateObject's allowedToolIds — the check also enforces missing_tools symmetry, so generateText and runAgentLoop, which do not see StructuredOutput, must not require it. generateObject also ran with maxTurns: 1, which the model intermittently breached when it emitted thinking text before the structured response. Raised to 5 to give the schema-bound call enough headroom without allowing unbounded loops. The existing tests now exercise the path with an init message that announces StructuredOutput so the regression cannot slip back in. * chore(scripts): add ktx-reset.sh project-cleanup helper Convenience script for repeatable ingest testing: takes a project directory and prunes everything except ktx.yaml and .ktx/secrets/, so the next ktx setup or ktx ingest run starts from a known-clean state.
2026-05-23 10:41:30 +02:00
snowflakeConnectorInstances.push(this);
2026-05-10 23:12:26 +02:00
}
},
);
const postgresExtractSchema = vi.hoisted(() =>
vi.fn(async (connectionId: string) => ({
connectionId,
extractedAt: '2026-04-29T12:00:00.000Z',
metadata: { database: 'analytics' },
tables: [],
})),
);
const createPostgresLiveDatabaseIntrospection = vi.hoisted(() =>
vi.fn(() => ({ extractSchema: postgresExtractSchema })),
);
2026-05-10 23:51:24 +02:00
const isKtxPostgresConnectionConfig = vi.hoisted(() =>
2026-05-10 23:12:26 +02:00
vi.fn((connection: { driver?: string } | undefined) =>
String(connection?.driver ?? '').toLowerCase() === 'postgres',
2026-05-10 23:12:26 +02:00
),
);
2026-05-10 23:51:24 +02:00
const KtxPostgresScanConnector = vi.hoisted(
2026-05-10 23:12:26 +02:00
() =>
class {
readonly id: string;
readonly driver = 'postgres';
constructor(options: { connectionId: string }) {
this.id = `postgres:${options.connectionId}`;
}
},
);
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
vi.mock('../src/connectors/sqlserver/connector.js', () => ({
2026-05-10 23:51:24 +02:00
isKtxSqlServerConnectionConfig,
KtxSqlServerScanConnector,
2026-05-10 23:12:26 +02:00
}));
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
vi.mock('../src/connectors/sqlserver/live-database-introspection.js', () => ({
chore(workspace): gate dead-code with knip production mode (#196) * refactor(workspace): relocate @ktx/llm source into packages/cli/src/llm * refactor(workspace): rewrite @ktx/llm imports to relative paths * refactor(workspace): fold internal packages into cli * chore(workspace): gate dead-code with knip production mode Turn on production-mode knip plus an autofix run in pre-commit and the `pnpm dead-code` script, document the `/** @internal */` convention for test-only exports in AGENTS.md, annotate test-only exports across the CLI with that JSDoc, and drop dead exports/wrappers the new gate surfaced (e.g. `cli-project.ts`, `lookerRuntimeSourceToFileAdapterSource`, `createLocalScanEnrichmentProvidersFromConfig`, `PGLITE_OWNER_PROCESS_BACKEND_CAPABILITIES`, stale type re-exports). Replace the loose `ignoreIssues` allowlist in `knip.json` with explicit production entries so cross-package barrel leaks are caught. * refactor(cli): delete internal barrel index.ts files The 34 `index.ts` re-export barrels inside `packages/cli/src/` were holdovers from the pre-fold multi-workspace structure. Post-fold-in they served no production purpose: external consumers go through the single package main entry, and in-repo callers mostly imported through them only because the path was short. Internally, knip flagged most barrel re-exports as production-dead (only reached via tests). This change: - Deletes every internal barrel except `packages/cli/src/index.ts` (the published package entry). - Rewrites ~270 source/test files to import each name directly from the file that defines it. - Moves `tools/warehouse-verification/index.ts` to `create-warehouse-verification-tools.ts` (the function it defined locally) and updates its single consumer. - Renames `search/backend-conformance.ts` → `.test-utils.ts` to match the existing test-helper file convention. - Deletes 13 dead test-only chains (dbt-descriptions/*, live-database/extracted-schema, live-database/structural-sync, relationship-* feedback/review chain) plus their tests and a cascading orphan integration test. - Updates test mocks that pointed at deleted barrel paths (notion-client, connector barrels in scan/local-scan-connectors tests) to mock the source files instead. - Points the maintainer benchmark script (`scripts/relationship-benchmark-report.mjs`) at source files instead of `dist/context/scan/index.js`. - Drops the barrel `!` entries from `knip.json`; adds explicit production entries only for the benchmark code reached via dist by the maintainer script. Net: 413 files changed, ~1.2k insertions, ~9.4k deletions. `pnpm run dead-code` (Biome + knip default + knip production) and `pnpm run type-check` are clean; 2277 tests pass. * refactor(workspace): rename @ktx/cli to @kaelio/ktx and pack it directly Promote the CLI workspace package to the public name `@kaelio/ktx` and drop the separate `scripts/build-public-npm-package.mjs` wrapper. The CLI package is now publishable in place (`publishConfig.access: public`, `provenance: true`), so artifact packing uses `pnpm pack` against `packages/cli/` instead of assembling a parallel package tree. Updates all workspace filter invocations, docs, tests, and release readiness checks to reference the new package name, and folds the tarball-name helper into `scripts/public-npm-release-metadata.mjs`. * docs: align "agent clients" and "data agents" terminology Replace "client agents" with "agent clients" and "database agents" with "data agents" across AGENTS.md, README.md, the docs-site copy, and the matching setup-agents test description, matching the canonical vocabulary in docs/terminology.md. Also moves packages/cli/tsconfig.json's tsBuildInfoFile from node_modules/.cache/ to dist/.tsbuildinfo so incremental builds survive node_modules reinstalls. * refactor(release): single source of truth for package version Make packages/cli/package.json the single source of truth for the @kaelio/ktx version. publicNpmPackageVersion() now reads it directly, so artifact filenames, release-readiness checks, and the Python wheel version all derive from one field. The duplicate release-policy.json.publicNpmPackageVersion is removed. Previously the two fields could drift: tarballs were named kaelio-ktx-0.4.1.tgz while internally containing @kaelio/ktx@0.0.0-private. - update-public-release-version.mjs rewrites both Python pyproject.toml files (ktx-daemon, ktx-sl) alongside the npm package.jsons, normalizing the version for PEP 440 (e.g. 0.1.0-rc.2 -> 0.1.0rc2). - semantic-release-config.cjs adds the two pyproject.toml files to @semantic-release/git assets so the release commit back to main carries every version source in lockstep. - The six "?? '0.0.0-private'" fallback literals across the CLI are replaced with "?? getKtxCliPackageInfo().version", and createDefaultKtxMcpServer makes its version arg required. - docs/release.md describes the actual commit-back model: the dev tree always reflects the most recent release; no sentinel pin to maintain. Verified: pnpm run artifacts:build now produces kaelio-ktx-0.4.1.tgz and kaelio_ktx-0.4.1-py3-none-any.whl with @kaelio/ktx@0.4.1 inside. Full type-check, dead-code, and 2287 vitests + 173 script tests pass. * refactor(cli): inject embedding provider resolution and detect sentence-transformers runtime Make resolveProjectEmbeddingProvider and runtimeIo injectable in ingest and scan command entrypoints so tests can stub them, and teach resolvePublicIngestRuntimeRequirements to flag the local-embeddings runtime feature when ktx.yaml selects sentence-transformers. * chore(cli): mark buildLocalStatsStatus and LocalStatsStatus as @internal Both symbols are consumed only by status-project.test.ts. Annotating with /** @internal */ keeps knip's production-mode check clean without changing runtime behavior. * fix(cli): use real package metadata in print-command-tree The stubbed package name embedded a forbidden product identifier that tripped the boundary check in CI. Read the metadata from package.json instead — keeps the rendered tree unchanged and removes a duplicate source of truth. * feat(cli): show embedding coverage in `ktx status`, drop duplicate disk counts Inline `(N embedded)` next to the Wiki scope counts and Semantic-layer source counts, computed with `SUM(embedding_json IS NOT NULL)` over `knowledge_pages` and `local_sl_sources`. Rename the "Knowledge" label to "Wiki" (canonical per `docs/terminology.md`) and rename the matching `localStats.knowledgePages` field to `localStats.wikiPages`. Drop `wiki=N md` and `semantic-layer=N yaml` from the Disk row — those duplicated the per-surface rows above. Disk now reports only actual byte usage (db, cache, raw-sources). The unused `wikiGlobalMarkdownCount` / `semanticLayerYamlCount` fields, the `isMarkdownEntry` / `isYamlEntry` helpers, and the `filter` arg on `summarizeDir` are removed.
2026-05-21 15:28:58 +02:00
createSqlServerLiveDatabaseIntrospection,
}));
2026-05-10 23:12:26 +02:00
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
vi.mock('../src/connectors/bigquery/connector.js', () => ({
2026-05-10 23:51:24 +02:00
isKtxBigQueryConnectionConfig,
KtxBigQueryScanConnector,
2026-05-10 23:12:26 +02:00
}));
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
vi.mock('../src/connectors/bigquery/live-database-introspection.js', () => ({
chore(workspace): gate dead-code with knip production mode (#196) * refactor(workspace): relocate @ktx/llm source into packages/cli/src/llm * refactor(workspace): rewrite @ktx/llm imports to relative paths * refactor(workspace): fold internal packages into cli * chore(workspace): gate dead-code with knip production mode Turn on production-mode knip plus an autofix run in pre-commit and the `pnpm dead-code` script, document the `/** @internal */` convention for test-only exports in AGENTS.md, annotate test-only exports across the CLI with that JSDoc, and drop dead exports/wrappers the new gate surfaced (e.g. `cli-project.ts`, `lookerRuntimeSourceToFileAdapterSource`, `createLocalScanEnrichmentProvidersFromConfig`, `PGLITE_OWNER_PROCESS_BACKEND_CAPABILITIES`, stale type re-exports). Replace the loose `ignoreIssues` allowlist in `knip.json` with explicit production entries so cross-package barrel leaks are caught. * refactor(cli): delete internal barrel index.ts files The 34 `index.ts` re-export barrels inside `packages/cli/src/` were holdovers from the pre-fold multi-workspace structure. Post-fold-in they served no production purpose: external consumers go through the single package main entry, and in-repo callers mostly imported through them only because the path was short. Internally, knip flagged most barrel re-exports as production-dead (only reached via tests). This change: - Deletes every internal barrel except `packages/cli/src/index.ts` (the published package entry). - Rewrites ~270 source/test files to import each name directly from the file that defines it. - Moves `tools/warehouse-verification/index.ts` to `create-warehouse-verification-tools.ts` (the function it defined locally) and updates its single consumer. - Renames `search/backend-conformance.ts` → `.test-utils.ts` to match the existing test-helper file convention. - Deletes 13 dead test-only chains (dbt-descriptions/*, live-database/extracted-schema, live-database/structural-sync, relationship-* feedback/review chain) plus their tests and a cascading orphan integration test. - Updates test mocks that pointed at deleted barrel paths (notion-client, connector barrels in scan/local-scan-connectors tests) to mock the source files instead. - Points the maintainer benchmark script (`scripts/relationship-benchmark-report.mjs`) at source files instead of `dist/context/scan/index.js`. - Drops the barrel `!` entries from `knip.json`; adds explicit production entries only for the benchmark code reached via dist by the maintainer script. Net: 413 files changed, ~1.2k insertions, ~9.4k deletions. `pnpm run dead-code` (Biome + knip default + knip production) and `pnpm run type-check` are clean; 2277 tests pass. * refactor(workspace): rename @ktx/cli to @kaelio/ktx and pack it directly Promote the CLI workspace package to the public name `@kaelio/ktx` and drop the separate `scripts/build-public-npm-package.mjs` wrapper. The CLI package is now publishable in place (`publishConfig.access: public`, `provenance: true`), so artifact packing uses `pnpm pack` against `packages/cli/` instead of assembling a parallel package tree. Updates all workspace filter invocations, docs, tests, and release readiness checks to reference the new package name, and folds the tarball-name helper into `scripts/public-npm-release-metadata.mjs`. * docs: align "agent clients" and "data agents" terminology Replace "client agents" with "agent clients" and "database agents" with "data agents" across AGENTS.md, README.md, the docs-site copy, and the matching setup-agents test description, matching the canonical vocabulary in docs/terminology.md. Also moves packages/cli/tsconfig.json's tsBuildInfoFile from node_modules/.cache/ to dist/.tsbuildinfo so incremental builds survive node_modules reinstalls. * refactor(release): single source of truth for package version Make packages/cli/package.json the single source of truth for the @kaelio/ktx version. publicNpmPackageVersion() now reads it directly, so artifact filenames, release-readiness checks, and the Python wheel version all derive from one field. The duplicate release-policy.json.publicNpmPackageVersion is removed. Previously the two fields could drift: tarballs were named kaelio-ktx-0.4.1.tgz while internally containing @kaelio/ktx@0.0.0-private. - update-public-release-version.mjs rewrites both Python pyproject.toml files (ktx-daemon, ktx-sl) alongside the npm package.jsons, normalizing the version for PEP 440 (e.g. 0.1.0-rc.2 -> 0.1.0rc2). - semantic-release-config.cjs adds the two pyproject.toml files to @semantic-release/git assets so the release commit back to main carries every version source in lockstep. - The six "?? '0.0.0-private'" fallback literals across the CLI are replaced with "?? getKtxCliPackageInfo().version", and createDefaultKtxMcpServer makes its version arg required. - docs/release.md describes the actual commit-back model: the dev tree always reflects the most recent release; no sentinel pin to maintain. Verified: pnpm run artifacts:build now produces kaelio-ktx-0.4.1.tgz and kaelio_ktx-0.4.1-py3-none-any.whl with @kaelio/ktx@0.4.1 inside. Full type-check, dead-code, and 2287 vitests + 173 script tests pass. * refactor(cli): inject embedding provider resolution and detect sentence-transformers runtime Make resolveProjectEmbeddingProvider and runtimeIo injectable in ingest and scan command entrypoints so tests can stub them, and teach resolvePublicIngestRuntimeRequirements to flag the local-embeddings runtime feature when ktx.yaml selects sentence-transformers. * chore(cli): mark buildLocalStatsStatus and LocalStatsStatus as @internal Both symbols are consumed only by status-project.test.ts. Annotating with /** @internal */ keeps knip's production-mode check clean without changing runtime behavior. * fix(cli): use real package metadata in print-command-tree The stubbed package name embedded a forbidden product identifier that tripped the boundary check in CI. Read the metadata from package.json instead — keeps the rendered tree unchanged and removes a duplicate source of truth. * feat(cli): show embedding coverage in `ktx status`, drop duplicate disk counts Inline `(N embedded)` next to the Wiki scope counts and Semantic-layer source counts, computed with `SUM(embedding_json IS NOT NULL)` over `knowledge_pages` and `local_sl_sources`. Rename the "Knowledge" label to "Wiki" (canonical per `docs/terminology.md`) and rename the matching `localStats.knowledgePages` field to `localStats.wikiPages`. Drop `wiki=N md` and `semantic-layer=N yaml` from the Disk row — those duplicated the per-surface rows above. Disk now reports only actual byte usage (db, cache, raw-sources). The unused `wikiGlobalMarkdownCount` / `semanticLayerYamlCount` fields, the `isMarkdownEntry` / `isYamlEntry` helpers, and the `filter` arg on `summarizeDir` are removed.
2026-05-21 15:28:58 +02:00
createBigQueryLiveDatabaseIntrospection,
}));
2026-05-10 23:12:26 +02:00
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
vi.mock('../src/connectors/snowflake/connector.js', () => ({
2026-05-10 23:51:24 +02:00
isKtxSnowflakeConnectionConfig,
KtxSnowflakeScanConnector,
2026-05-10 23:12:26 +02:00
}));
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
vi.mock('../src/connectors/snowflake/live-database-introspection.js', () => ({
chore(workspace): gate dead-code with knip production mode (#196) * refactor(workspace): relocate @ktx/llm source into packages/cli/src/llm * refactor(workspace): rewrite @ktx/llm imports to relative paths * refactor(workspace): fold internal packages into cli * chore(workspace): gate dead-code with knip production mode Turn on production-mode knip plus an autofix run in pre-commit and the `pnpm dead-code` script, document the `/** @internal */` convention for test-only exports in AGENTS.md, annotate test-only exports across the CLI with that JSDoc, and drop dead exports/wrappers the new gate surfaced (e.g. `cli-project.ts`, `lookerRuntimeSourceToFileAdapterSource`, `createLocalScanEnrichmentProvidersFromConfig`, `PGLITE_OWNER_PROCESS_BACKEND_CAPABILITIES`, stale type re-exports). Replace the loose `ignoreIssues` allowlist in `knip.json` with explicit production entries so cross-package barrel leaks are caught. * refactor(cli): delete internal barrel index.ts files The 34 `index.ts` re-export barrels inside `packages/cli/src/` were holdovers from the pre-fold multi-workspace structure. Post-fold-in they served no production purpose: external consumers go through the single package main entry, and in-repo callers mostly imported through them only because the path was short. Internally, knip flagged most barrel re-exports as production-dead (only reached via tests). This change: - Deletes every internal barrel except `packages/cli/src/index.ts` (the published package entry). - Rewrites ~270 source/test files to import each name directly from the file that defines it. - Moves `tools/warehouse-verification/index.ts` to `create-warehouse-verification-tools.ts` (the function it defined locally) and updates its single consumer. - Renames `search/backend-conformance.ts` → `.test-utils.ts` to match the existing test-helper file convention. - Deletes 13 dead test-only chains (dbt-descriptions/*, live-database/extracted-schema, live-database/structural-sync, relationship-* feedback/review chain) plus their tests and a cascading orphan integration test. - Updates test mocks that pointed at deleted barrel paths (notion-client, connector barrels in scan/local-scan-connectors tests) to mock the source files instead. - Points the maintainer benchmark script (`scripts/relationship-benchmark-report.mjs`) at source files instead of `dist/context/scan/index.js`. - Drops the barrel `!` entries from `knip.json`; adds explicit production entries only for the benchmark code reached via dist by the maintainer script. Net: 413 files changed, ~1.2k insertions, ~9.4k deletions. `pnpm run dead-code` (Biome + knip default + knip production) and `pnpm run type-check` are clean; 2277 tests pass. * refactor(workspace): rename @ktx/cli to @kaelio/ktx and pack it directly Promote the CLI workspace package to the public name `@kaelio/ktx` and drop the separate `scripts/build-public-npm-package.mjs` wrapper. The CLI package is now publishable in place (`publishConfig.access: public`, `provenance: true`), so artifact packing uses `pnpm pack` against `packages/cli/` instead of assembling a parallel package tree. Updates all workspace filter invocations, docs, tests, and release readiness checks to reference the new package name, and folds the tarball-name helper into `scripts/public-npm-release-metadata.mjs`. * docs: align "agent clients" and "data agents" terminology Replace "client agents" with "agent clients" and "database agents" with "data agents" across AGENTS.md, README.md, the docs-site copy, and the matching setup-agents test description, matching the canonical vocabulary in docs/terminology.md. Also moves packages/cli/tsconfig.json's tsBuildInfoFile from node_modules/.cache/ to dist/.tsbuildinfo so incremental builds survive node_modules reinstalls. * refactor(release): single source of truth for package version Make packages/cli/package.json the single source of truth for the @kaelio/ktx version. publicNpmPackageVersion() now reads it directly, so artifact filenames, release-readiness checks, and the Python wheel version all derive from one field. The duplicate release-policy.json.publicNpmPackageVersion is removed. Previously the two fields could drift: tarballs were named kaelio-ktx-0.4.1.tgz while internally containing @kaelio/ktx@0.0.0-private. - update-public-release-version.mjs rewrites both Python pyproject.toml files (ktx-daemon, ktx-sl) alongside the npm package.jsons, normalizing the version for PEP 440 (e.g. 0.1.0-rc.2 -> 0.1.0rc2). - semantic-release-config.cjs adds the two pyproject.toml files to @semantic-release/git assets so the release commit back to main carries every version source in lockstep. - The six "?? '0.0.0-private'" fallback literals across the CLI are replaced with "?? getKtxCliPackageInfo().version", and createDefaultKtxMcpServer makes its version arg required. - docs/release.md describes the actual commit-back model: the dev tree always reflects the most recent release; no sentinel pin to maintain. Verified: pnpm run artifacts:build now produces kaelio-ktx-0.4.1.tgz and kaelio_ktx-0.4.1-py3-none-any.whl with @kaelio/ktx@0.4.1 inside. Full type-check, dead-code, and 2287 vitests + 173 script tests pass. * refactor(cli): inject embedding provider resolution and detect sentence-transformers runtime Make resolveProjectEmbeddingProvider and runtimeIo injectable in ingest and scan command entrypoints so tests can stub them, and teach resolvePublicIngestRuntimeRequirements to flag the local-embeddings runtime feature when ktx.yaml selects sentence-transformers. * chore(cli): mark buildLocalStatsStatus and LocalStatsStatus as @internal Both symbols are consumed only by status-project.test.ts. Annotating with /** @internal */ keeps knip's production-mode check clean without changing runtime behavior. * fix(cli): use real package metadata in print-command-tree The stubbed package name embedded a forbidden product identifier that tripped the boundary check in CI. Read the metadata from package.json instead — keeps the rendered tree unchanged and removes a duplicate source of truth. * feat(cli): show embedding coverage in `ktx status`, drop duplicate disk counts Inline `(N embedded)` next to the Wiki scope counts and Semantic-layer source counts, computed with `SUM(embedding_json IS NOT NULL)` over `knowledge_pages` and `local_sl_sources`. Rename the "Knowledge" label to "Wiki" (canonical per `docs/terminology.md`) and rename the matching `localStats.knowledgePages` field to `localStats.wikiPages`. Drop `wiki=N md` and `semantic-layer=N yaml` from the Disk row — those duplicated the per-surface rows above. Disk now reports only actual byte usage (db, cache, raw-sources). The unused `wikiGlobalMarkdownCount` / `semanticLayerYamlCount` fields, the `isMarkdownEntry` / `isYamlEntry` helpers, and the `filter` arg on `summarizeDir` are removed.
2026-05-21 15:28:58 +02:00
createSnowflakeLiveDatabaseIntrospection,
}));
2026-05-10 23:12:26 +02:00
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
vi.mock('../src/connectors/postgres/connector.js', () => ({
2026-05-10 23:51:24 +02:00
isKtxPostgresConnectionConfig,
KtxPostgresScanConnector,
2026-05-10 23:12:26 +02:00
}));
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
vi.mock('../src/connectors/postgres/live-database-introspection.js', () => ({
chore(workspace): gate dead-code with knip production mode (#196) * refactor(workspace): relocate @ktx/llm source into packages/cli/src/llm * refactor(workspace): rewrite @ktx/llm imports to relative paths * refactor(workspace): fold internal packages into cli * chore(workspace): gate dead-code with knip production mode Turn on production-mode knip plus an autofix run in pre-commit and the `pnpm dead-code` script, document the `/** @internal */` convention for test-only exports in AGENTS.md, annotate test-only exports across the CLI with that JSDoc, and drop dead exports/wrappers the new gate surfaced (e.g. `cli-project.ts`, `lookerRuntimeSourceToFileAdapterSource`, `createLocalScanEnrichmentProvidersFromConfig`, `PGLITE_OWNER_PROCESS_BACKEND_CAPABILITIES`, stale type re-exports). Replace the loose `ignoreIssues` allowlist in `knip.json` with explicit production entries so cross-package barrel leaks are caught. * refactor(cli): delete internal barrel index.ts files The 34 `index.ts` re-export barrels inside `packages/cli/src/` were holdovers from the pre-fold multi-workspace structure. Post-fold-in they served no production purpose: external consumers go through the single package main entry, and in-repo callers mostly imported through them only because the path was short. Internally, knip flagged most barrel re-exports as production-dead (only reached via tests). This change: - Deletes every internal barrel except `packages/cli/src/index.ts` (the published package entry). - Rewrites ~270 source/test files to import each name directly from the file that defines it. - Moves `tools/warehouse-verification/index.ts` to `create-warehouse-verification-tools.ts` (the function it defined locally) and updates its single consumer. - Renames `search/backend-conformance.ts` → `.test-utils.ts` to match the existing test-helper file convention. - Deletes 13 dead test-only chains (dbt-descriptions/*, live-database/extracted-schema, live-database/structural-sync, relationship-* feedback/review chain) plus their tests and a cascading orphan integration test. - Updates test mocks that pointed at deleted barrel paths (notion-client, connector barrels in scan/local-scan-connectors tests) to mock the source files instead. - Points the maintainer benchmark script (`scripts/relationship-benchmark-report.mjs`) at source files instead of `dist/context/scan/index.js`. - Drops the barrel `!` entries from `knip.json`; adds explicit production entries only for the benchmark code reached via dist by the maintainer script. Net: 413 files changed, ~1.2k insertions, ~9.4k deletions. `pnpm run dead-code` (Biome + knip default + knip production) and `pnpm run type-check` are clean; 2277 tests pass. * refactor(workspace): rename @ktx/cli to @kaelio/ktx and pack it directly Promote the CLI workspace package to the public name `@kaelio/ktx` and drop the separate `scripts/build-public-npm-package.mjs` wrapper. The CLI package is now publishable in place (`publishConfig.access: public`, `provenance: true`), so artifact packing uses `pnpm pack` against `packages/cli/` instead of assembling a parallel package tree. Updates all workspace filter invocations, docs, tests, and release readiness checks to reference the new package name, and folds the tarball-name helper into `scripts/public-npm-release-metadata.mjs`. * docs: align "agent clients" and "data agents" terminology Replace "client agents" with "agent clients" and "database agents" with "data agents" across AGENTS.md, README.md, the docs-site copy, and the matching setup-agents test description, matching the canonical vocabulary in docs/terminology.md. Also moves packages/cli/tsconfig.json's tsBuildInfoFile from node_modules/.cache/ to dist/.tsbuildinfo so incremental builds survive node_modules reinstalls. * refactor(release): single source of truth for package version Make packages/cli/package.json the single source of truth for the @kaelio/ktx version. publicNpmPackageVersion() now reads it directly, so artifact filenames, release-readiness checks, and the Python wheel version all derive from one field. The duplicate release-policy.json.publicNpmPackageVersion is removed. Previously the two fields could drift: tarballs were named kaelio-ktx-0.4.1.tgz while internally containing @kaelio/ktx@0.0.0-private. - update-public-release-version.mjs rewrites both Python pyproject.toml files (ktx-daemon, ktx-sl) alongside the npm package.jsons, normalizing the version for PEP 440 (e.g. 0.1.0-rc.2 -> 0.1.0rc2). - semantic-release-config.cjs adds the two pyproject.toml files to @semantic-release/git assets so the release commit back to main carries every version source in lockstep. - The six "?? '0.0.0-private'" fallback literals across the CLI are replaced with "?? getKtxCliPackageInfo().version", and createDefaultKtxMcpServer makes its version arg required. - docs/release.md describes the actual commit-back model: the dev tree always reflects the most recent release; no sentinel pin to maintain. Verified: pnpm run artifacts:build now produces kaelio-ktx-0.4.1.tgz and kaelio_ktx-0.4.1-py3-none-any.whl with @kaelio/ktx@0.4.1 inside. Full type-check, dead-code, and 2287 vitests + 173 script tests pass. * refactor(cli): inject embedding provider resolution and detect sentence-transformers runtime Make resolveProjectEmbeddingProvider and runtimeIo injectable in ingest and scan command entrypoints so tests can stub them, and teach resolvePublicIngestRuntimeRequirements to flag the local-embeddings runtime feature when ktx.yaml selects sentence-transformers. * chore(cli): mark buildLocalStatsStatus and LocalStatsStatus as @internal Both symbols are consumed only by status-project.test.ts. Annotating with /** @internal */ keeps knip's production-mode check clean without changing runtime behavior. * fix(cli): use real package metadata in print-command-tree The stubbed package name embedded a forbidden product identifier that tripped the boundary check in CI. Read the metadata from package.json instead — keeps the rendered tree unchanged and removes a duplicate source of truth. * feat(cli): show embedding coverage in `ktx status`, drop duplicate disk counts Inline `(N embedded)` next to the Wiki scope counts and Semantic-layer source counts, computed with `SUM(embedding_json IS NOT NULL)` over `knowledge_pages` and `local_sl_sources`. Rename the "Knowledge" label to "Wiki" (canonical per `docs/terminology.md`) and rename the matching `localStats.knowledgePages` field to `localStats.wikiPages`. Drop `wiki=N md` and `semantic-layer=N yaml` from the Disk row — those duplicated the per-surface rows above. Disk now reports only actual byte usage (db, cache, raw-sources). The unused `wikiGlobalMarkdownCount` / `semanticLayerYamlCount` fields, the `isMarkdownEntry` / `isYamlEntry` helpers, and the `filter` arg on `summarizeDir` are removed.
2026-05-21 15:28:58 +02:00
createPostgresLiveDatabaseIntrospection,
}));
2026-05-10 23:12:26 +02:00
function makeIo(options: { isTTY?: boolean } = {}) {
let stdout = '';
let stderr = '';
return {
io: {
stdout: {
isTTY: options.isTTY,
write: (chunk: string) => {
stdout += chunk;
},
},
stderr: {
write: (chunk: string) => {
stderr += chunk;
},
},
},
stdout: () => stdout,
stderr: () => stderr,
};
}
function fakeLiveDatabaseAdapter(
createIntrospection: (options: { connections: unknown }) => {
extractSchema: (connectionId: string) => Promise<unknown>;
},
): SourceAdapter {
return {
source: 'live-database',
skillNames: [],
async detect() {
return true;
},
async fetch(_pullConfig: unknown, stagedDir: string, ctx: { connectionId: string }) {
await mkdir(stagedDir, { recursive: true });
const schema = await createIntrospection({ connections: {} }).extractSchema(ctx.connectionId);
await writeFile(
join(stagedDir, 'connection.json'),
JSON.stringify({ connectionId: ctx.connectionId, schema }, null, 2),
'utf-8',
);
},
async chunk() {
return { workUnits: [] };
},
};
}
2026-05-10 23:51:24 +02:00
const report: KtxScanReport = {
2026-05-10 23:12:26 +02:00
connectionId: 'warehouse',
driver: 'postgres',
syncId: 'sync-1',
runId: 'scan-run-1',
trigger: 'cli',
mode: 'structural',
dryRun: false,
artifactPaths: {
rawSourcesDir: 'raw-sources/warehouse/live-database/sync-1',
reportPath: 'raw-sources/warehouse/live-database/sync-1/scan-report.json',
manifestShards: [],
enrichmentArtifacts: [],
},
diffSummary: {
tablesAdded: 1,
tablesModified: 0,
tablesDeleted: 0,
tablesUnchanged: 0,
columnsAdded: 0,
columnsModified: 0,
columnsDeleted: 0,
},
manifestShardsWritten: 0,
structuralSyncStats: {
tablesCreated: 0,
tablesUpdated: 0,
tablesDeleted: 0,
columnsCreated: 0,
columnsUpdated: 0,
columnsDeleted: 0,
},
enrichment: {
dataDictionary: 'skipped',
tableDescriptions: 'skipped',
columnDescriptions: 'skipped',
embeddings: 'skipped',
deterministicRelationships: 'skipped',
llmRelationshipValidation: 'skipped',
statisticalValidation: 'skipped',
},
capabilityGaps: [],
warnings: [],
relationships: { accepted: 0, review: 0, rejected: 0, skipped: 0 },
enrichmentState: {
resumedStages: [],
completedStages: [],
failedStages: [],
},
createdAt: '2026-04-29T09:00:00.000Z',
};
2026-05-10 23:51:24 +02:00
const reportWithAttention: KtxScanReport = {
2026-05-10 23:12:26 +02:00
...report,
mode: 'relationships',
diffSummary: {
tablesAdded: 3,
tablesModified: 2,
tablesDeleted: 0,
tablesUnchanged: 13,
columnsAdded: 18,
columnsModified: 5,
columnsDeleted: 0,
},
capabilityGaps: ['columnStats'],
warnings: [
{
code: 'connector_capability_missing',
message: 'ktx scan connector is missing optional capability: columnStats',
2026-05-10 23:12:26 +02:00
recoverable: true,
metadata: { capability: 'columnStats' },
},
{
code: 'relationship_validation_failed',
message: 'Could not validate relationship orders.customer_id -> customers.id',
table: 'orders',
column: 'customer_id',
recoverable: true,
},
],
relationships: { accepted: 7, review: 3, rejected: 2, skipped: 4 },
enrichmentState: {
resumedStages: ['relationships'],
completedStages: ['descriptions', 'relationships'],
failedStages: [],
},
artifactPaths: {
...report.artifactPaths,
manifestShards: ['raw-sources/warehouse/live-database/sync-1/_schema/shard-000.json'],
enrichmentArtifacts: ['raw-sources/warehouse/live-database/sync-1/_enrichment/relationships.json'],
},
};
2026-05-10 23:51:24 +02:00
describe('runKtxScan', () => {
2026-05-10 23:12:26 +02:00
let tempDir: string;
const noLocalIngestAdapters = () => [];
2026-05-10 23:12:26 +02:00
beforeEach(async () => {
2026-05-10 23:51:24 +02:00
tempDir = await mkdtemp(join(tmpdir(), 'ktx-cli-scan-'));
reportExceptionMock.mockClear();
2026-05-10 23:12:26 +02:00
});
afterEach(async () => {
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
vi.unstubAllEnvs();
2026-05-10 23:12:26 +02:00
await rm(tempDir, { recursive: true, force: true });
});
it('runs structural scans and prints a dev-friendly plain summary', async () => {
await initKtxProject({ projectDir: tempDir });
2026-05-10 23:12:26 +02:00
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report,
}),
);
const io = makeIo();
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
databaseIntrospectionUrl: 'http://127.0.0.1:8765',
},
io.io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
2026-05-10 23:12:26 +02:00
),
).resolves.toBe(0);
expect(runLocalScan).toHaveBeenCalledWith(
expect.objectContaining({
connectionId: 'warehouse',
mode: 'structural',
databaseIntrospectionUrl: 'http://127.0.0.1:8765',
connector: undefined,
}),
);
expect(io.stdout()).toContain('ktx scan completed\n');
2026-05-10 23:12:26 +02:00
expect(io.stdout()).toContain('Run: scan-run-1');
expect(io.stdout()).toContain('Mode: structural');
expect(io.stdout()).toContain('What changed\n');
expect(io.stdout()).toContain('New tables: 1\n');
expect(io.stdout()).toContain('Changed tables: 0\n');
expect(io.stdout()).toContain('Removed tables: 0\n');
expect(io.stdout()).toContain('Unchanged tables: 0\n');
expect(io.stdout()).toContain('Needs attention\n None\n');
expect(io.stdout()).toContain('Artifacts\n');
expect(io.stdout()).toContain('Report: raw-sources/warehouse/live-database/sync-1/scan-report.json');
expect(io.stdout()).toContain('Next:\n');
expect(io.stdout()).toContain('ktx status --project-dir ');
expect(io.stdout()).not.toContain('ktx admin scan status');
expect(io.stdout()).not.toContain('ktx admin scan report');
2026-05-10 23:12:26 +02:00
expect(io.stdout()).not.toContain('\u001b[');
expect(io.stdout()).not.toContain('✓');
expect(io.stdout()).not.toContain('+1');
expect(io.stdout()).not.toContain('/~');
});
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
it('emits debug telemetry for completed scans without project paths', async () => {
vi.stubEnv('KTX_TELEMETRY_DEBUG', '1');
vi.stubEnv('CI', '');
await initKtxProject({ projectDir: tempDir });
const runLocalScan = vi.fn(
async (): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report,
}),
);
const io = makeIo({ isTTY: true });
const code = await runKtxScan(
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
databaseIntrospectionUrl: 'http://127.0.0.1:8765',
},
io.io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
);
expect(code).toBe(0);
expect(io.stderr()).toContain('"event":"scan_completed"');
expect(io.stderr()).toContain('"tableCount"');
expect(io.stderr()).not.toContain(tempDir);
});
it('records the raw errorDetail in scan_completed telemetry when the scan throws', async () => {
vi.stubEnv('KTX_TELEMETRY_DEBUG', '1');
vi.stubEnv('CI', '');
vi.stubEnv('ANTHROPIC_API_KEY', 'anthropic-callsite-secret'); // pragma: allowlist secret
vi.stubEnv('DATABASE_URL', 'postgres://svc:scan-db-password@db.example.test/analytics'); // pragma: allowlist secret
await initKtxProject({ projectDir: tempDir });
const config = parseKtxProjectConfig(await readFile(join(tempDir, 'ktx.yaml'), 'utf-8'));
await writeFile(
join(tempDir, 'ktx.yaml'),
serializeKtxProjectConfig({
...config,
connections: {
warehouse: { driver: 'postgres', url: 'env:DATABASE_URL' },
},
llm: {
...config.llm,
provider: {
backend: 'anthropic',
anthropic: { api_key: 'env:ANTHROPIC_API_KEY' }, // pragma: allowlist secret
},
models: { default: 'claude-sonnet-4-6' },
},
}),
'utf-8',
);
const runLocalScan = vi.fn(async (): Promise<LocalScanRunResult> => {
const error = new Error('introspection timed out');
(error as { code?: unknown }).code = 'ETIMEDOUT';
throw error;
});
const io = makeIo({ isTTY: true });
const code = await runKtxScan(
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
databaseIntrospectionUrl: 'http://127.0.0.1:8765',
},
io.io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
);
expect(code).toBe(1);
expect(io.stderr()).toContain('"event":"scan_completed"');
expect(io.stderr()).toContain('"outcome":"error"');
expect(io.stderr()).toContain('"errorDetail":"ETIMEDOUT: introspection timed out"');
expect(reportExceptionMock).toHaveBeenCalledWith(
expect.objectContaining({
context: expect.objectContaining({ source: 'scan run', handled: true, fatal: false }),
projectDir: tempDir,
redactionSecrets: expect.arrayContaining([
'anthropic-callsite-secret',
'postgres://svc:scan-db-password@db.example.test/analytics', // pragma: allowlist secret
'scan-db-password',
]),
}),
);
});
it('passes ktx daemon options to local ingest adapters when no explicit daemon URL is set', async () => {
await initKtxProject({ projectDir: tempDir });
feat: npm-managed Python runtime for @kaelio/ktx (#7) * docs: add npm managed python runtime design * build: add bundled python runtime wheel builder * build: make local embedding dependencies optional * build: bundle python runtime wheel in cli artifacts * build: track bundled python runtime release artifact * test: verify bundled python runtime wheel * docs: add plan for bundled python runtime wheel * test: cover managed python runtime lifecycle * feat: add managed python runtime installer * feat: add runtime command runner * feat: expose runtime management commands * test: verify managed python runtime commands * docs: add plan for managed python runtime installer * feat: add managed python command helper * feat: use managed runtime for sl query compute * feat: route sl query managed runtime policy * docs: add plan for managed runtime sl query integration * feat: add managed runtime daemon metadata * feat: manage python daemon lifecycle * feat: add runtime daemon start stop commands * fix: verify managed runtime daemon lifecycle * docs: add plan for managed runtime daemon lifecycle * feat: add managed local embeddings config marker * feat: add managed local embeddings daemon helper * feat: use managed runtime for local embedding setup * feat: pass managed runtime policy through setup * docs: add plan for managed local embeddings runtime * feat: read CLI package metadata dynamically * feat: assemble public kaelio ktx npm package * feat: release one public kaelio ktx npm artifact * test: cover public kaelio ktx package invocations * chore: verify public kaelio ktx package artifacts * docs: add plan for public kaelio ktx npm package * test: verify managed runtime in public package smoke * test: finalize managed runtime release smoke * docs: add plan for managed runtime release smoke * test: specify local embeddings release smoke * feat: add local embeddings runtime smoke * chore: register local embeddings smoke * fix: verify local embeddings smoke * fix: restore artifact smoke python env helper * docs: add plan for managed local embeddings release smoke * refactor: share managed runtime install policy parsing * feat: use managed runtime for agent semantic queries * feat: use managed runtime for MCP semantic compute * docs: add plan for managed agent and MCP semantic runtime * feat(cli): add managed daemon HTTP helpers * feat(cli): route local adapters through managed daemon * feat(cli): use managed daemon for ingest helpers * feat(cli): pass managed daemon options to scan * feat(context): pass MCP ingest pull config options * feat(cli): pass managed daemon options to serve ingest * test: verify managed local ingest daemon runtime * docs: add plan for managed local ingest daemon runtime * docs: align managed runtime examples * docs: add plan for managed runtime docs cleanup * test: cover published package runtime smoke commands * test: validate published package smoke outputs * docs: add plan for published package runtime smoke * build: stamp public npm package version * release: add npm public release policy * release: add guarded npm publish script * release: document public npm release handoff * docs: add plan for public npm release handoff * test: cover managed runtime prune in package smoke * docs: document managed runtime prune * docs: add plan for managed runtime prune smoke and docs * chore: encode uv runtime prerequisite policy * fix: clarify missing uv runtime error * docs: document uv runtime prerequisite * docs: add plan for uv runtime prerequisite contract * refactor: limit release artifacts to public package runtime * chore: align release policy with bundled runtime wheel * docs: describe single public runtime artifact surface * test: verify single public runtime artifact contract * docs: add plan for single public runtime artifact cleanup * fix: align local embeddings smoke with public version * docs: add plan for local embeddings smoke public version * release: soft-launch as @kaelio/ktx@0.1.0-rc.0 on next tag Publish target moves to the pre-release version 0.1.0-rc.0 under the next dist-tag so npm install @kaelio/ktx (which resolves to latest) does not pick up the soft-launch build. Users opt in via @kaelio/ktx@next. * Fix release script boundary checks * Remove PostHog from public package bundle
2026-05-11 15:50:34 +02:00
const createLocalIngestAdapters = vi.fn(() => []);
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report,
}),
);
const io = makeIo();
const runtimeIo = makeIo({ isTTY: true });
feat: npm-managed Python runtime for @kaelio/ktx (#7) * docs: add npm managed python runtime design * build: add bundled python runtime wheel builder * build: make local embedding dependencies optional * build: bundle python runtime wheel in cli artifacts * build: track bundled python runtime release artifact * test: verify bundled python runtime wheel * docs: add plan for bundled python runtime wheel * test: cover managed python runtime lifecycle * feat: add managed python runtime installer * feat: add runtime command runner * feat: expose runtime management commands * test: verify managed python runtime commands * docs: add plan for managed python runtime installer * feat: add managed python command helper * feat: use managed runtime for sl query compute * feat: route sl query managed runtime policy * docs: add plan for managed runtime sl query integration * feat: add managed runtime daemon metadata * feat: manage python daemon lifecycle * feat: add runtime daemon start stop commands * fix: verify managed runtime daemon lifecycle * docs: add plan for managed runtime daemon lifecycle * feat: add managed local embeddings config marker * feat: add managed local embeddings daemon helper * feat: use managed runtime for local embedding setup * feat: pass managed runtime policy through setup * docs: add plan for managed local embeddings runtime * feat: read CLI package metadata dynamically * feat: assemble public kaelio ktx npm package * feat: release one public kaelio ktx npm artifact * test: cover public kaelio ktx package invocations * chore: verify public kaelio ktx package artifacts * docs: add plan for public kaelio ktx npm package * test: verify managed runtime in public package smoke * test: finalize managed runtime release smoke * docs: add plan for managed runtime release smoke * test: specify local embeddings release smoke * feat: add local embeddings runtime smoke * chore: register local embeddings smoke * fix: verify local embeddings smoke * fix: restore artifact smoke python env helper * docs: add plan for managed local embeddings release smoke * refactor: share managed runtime install policy parsing * feat: use managed runtime for agent semantic queries * feat: use managed runtime for MCP semantic compute * docs: add plan for managed agent and MCP semantic runtime * feat(cli): add managed daemon HTTP helpers * feat(cli): route local adapters through managed daemon * feat(cli): use managed daemon for ingest helpers * feat(cli): pass managed daemon options to scan * feat(context): pass MCP ingest pull config options * feat(cli): pass managed daemon options to serve ingest * test: verify managed local ingest daemon runtime * docs: add plan for managed local ingest daemon runtime * docs: align managed runtime examples * docs: add plan for managed runtime docs cleanup * test: cover published package runtime smoke commands * test: validate published package smoke outputs * docs: add plan for published package runtime smoke * build: stamp public npm package version * release: add npm public release policy * release: add guarded npm publish script * release: document public npm release handoff * docs: add plan for public npm release handoff * test: cover managed runtime prune in package smoke * docs: document managed runtime prune * docs: add plan for managed runtime prune smoke and docs * chore: encode uv runtime prerequisite policy * fix: clarify missing uv runtime error * docs: document uv runtime prerequisite * docs: add plan for uv runtime prerequisite contract * refactor: limit release artifacts to public package runtime * chore: align release policy with bundled runtime wheel * docs: describe single public runtime artifact surface * test: verify single public runtime artifact contract * docs: add plan for single public runtime artifact cleanup * fix: align local embeddings smoke with public version * docs: add plan for local embeddings smoke public version * release: soft-launch as @kaelio/ktx@0.1.0-rc.0 on next tag Publish target moves to the pre-release version 0.1.0-rc.0 under the next dist-tag so npm install @kaelio/ktx (which resolves to latest) does not pick up the soft-launch build. Users opt in via @kaelio/ktx@next. * Fix release script boundary checks * Remove PostHog from public package bundle
2026-05-11 15:50:34 +02:00
await expect(
runKtxScan(
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
cliVersion: '0.2.0',
runtimeInstallPolicy: 'auto',
},
io.io,
{ runLocalScan, createLocalIngestAdapters, runtimeIo: runtimeIo.io } as KtxScanDeps & {
runtimeIo: typeof runtimeIo.io;
},
feat: npm-managed Python runtime for @kaelio/ktx (#7) * docs: add npm managed python runtime design * build: add bundled python runtime wheel builder * build: make local embedding dependencies optional * build: bundle python runtime wheel in cli artifacts * build: track bundled python runtime release artifact * test: verify bundled python runtime wheel * docs: add plan for bundled python runtime wheel * test: cover managed python runtime lifecycle * feat: add managed python runtime installer * feat: add runtime command runner * feat: expose runtime management commands * test: verify managed python runtime commands * docs: add plan for managed python runtime installer * feat: add managed python command helper * feat: use managed runtime for sl query compute * feat: route sl query managed runtime policy * docs: add plan for managed runtime sl query integration * feat: add managed runtime daemon metadata * feat: manage python daemon lifecycle * feat: add runtime daemon start stop commands * fix: verify managed runtime daemon lifecycle * docs: add plan for managed runtime daemon lifecycle * feat: add managed local embeddings config marker * feat: add managed local embeddings daemon helper * feat: use managed runtime for local embedding setup * feat: pass managed runtime policy through setup * docs: add plan for managed local embeddings runtime * feat: read CLI package metadata dynamically * feat: assemble public kaelio ktx npm package * feat: release one public kaelio ktx npm artifact * test: cover public kaelio ktx package invocations * chore: verify public kaelio ktx package artifacts * docs: add plan for public kaelio ktx npm package * test: verify managed runtime in public package smoke * test: finalize managed runtime release smoke * docs: add plan for managed runtime release smoke * test: specify local embeddings release smoke * feat: add local embeddings runtime smoke * chore: register local embeddings smoke * fix: verify local embeddings smoke * fix: restore artifact smoke python env helper * docs: add plan for managed local embeddings release smoke * refactor: share managed runtime install policy parsing * feat: use managed runtime for agent semantic queries * feat: use managed runtime for MCP semantic compute * docs: add plan for managed agent and MCP semantic runtime * feat(cli): add managed daemon HTTP helpers * feat(cli): route local adapters through managed daemon * feat(cli): use managed daemon for ingest helpers * feat(cli): pass managed daemon options to scan * feat(context): pass MCP ingest pull config options * feat(cli): pass managed daemon options to serve ingest * test: verify managed local ingest daemon runtime * docs: add plan for managed local ingest daemon runtime * docs: align managed runtime examples * docs: add plan for managed runtime docs cleanup * test: cover published package runtime smoke commands * test: validate published package smoke outputs * docs: add plan for published package runtime smoke * build: stamp public npm package version * release: add npm public release policy * release: add guarded npm publish script * release: document public npm release handoff * docs: add plan for public npm release handoff * test: cover managed runtime prune in package smoke * docs: document managed runtime prune * docs: add plan for managed runtime prune smoke and docs * chore: encode uv runtime prerequisite policy * fix: clarify missing uv runtime error * docs: document uv runtime prerequisite * docs: add plan for uv runtime prerequisite contract * refactor: limit release artifacts to public package runtime * chore: align release policy with bundled runtime wheel * docs: describe single public runtime artifact surface * test: verify single public runtime artifact contract * docs: add plan for single public runtime artifact cleanup * fix: align local embeddings smoke with public version * docs: add plan for local embeddings smoke public version * release: soft-launch as @kaelio/ktx@0.1.0-rc.0 on next tag Publish target moves to the pre-release version 0.1.0-rc.0 under the next dist-tag so npm install @kaelio/ktx (which resolves to latest) does not pick up the soft-launch build. Users opt in via @kaelio/ktx@next. * Fix release script boundary checks * Remove PostHog from public package bundle
2026-05-11 15:50:34 +02:00
),
).resolves.toBe(0);
expect(createLocalIngestAdapters).toHaveBeenCalledWith(expect.objectContaining({ projectDir: tempDir }), {
managedDaemon: {
cliVersion: '0.2.0',
projectDir: tempDir,
feat: npm-managed Python runtime for @kaelio/ktx (#7) * docs: add npm managed python runtime design * build: add bundled python runtime wheel builder * build: make local embedding dependencies optional * build: bundle python runtime wheel in cli artifacts * build: track bundled python runtime release artifact * test: verify bundled python runtime wheel * docs: add plan for bundled python runtime wheel * test: cover managed python runtime lifecycle * feat: add managed python runtime installer * feat: add runtime command runner * feat: expose runtime management commands * test: verify managed python runtime commands * docs: add plan for managed python runtime installer * feat: add managed python command helper * feat: use managed runtime for sl query compute * feat: route sl query managed runtime policy * docs: add plan for managed runtime sl query integration * feat: add managed runtime daemon metadata * feat: manage python daemon lifecycle * feat: add runtime daemon start stop commands * fix: verify managed runtime daemon lifecycle * docs: add plan for managed runtime daemon lifecycle * feat: add managed local embeddings config marker * feat: add managed local embeddings daemon helper * feat: use managed runtime for local embedding setup * feat: pass managed runtime policy through setup * docs: add plan for managed local embeddings runtime * feat: read CLI package metadata dynamically * feat: assemble public kaelio ktx npm package * feat: release one public kaelio ktx npm artifact * test: cover public kaelio ktx package invocations * chore: verify public kaelio ktx package artifacts * docs: add plan for public kaelio ktx npm package * test: verify managed runtime in public package smoke * test: finalize managed runtime release smoke * docs: add plan for managed runtime release smoke * test: specify local embeddings release smoke * feat: add local embeddings runtime smoke * chore: register local embeddings smoke * fix: verify local embeddings smoke * fix: restore artifact smoke python env helper * docs: add plan for managed local embeddings release smoke * refactor: share managed runtime install policy parsing * feat: use managed runtime for agent semantic queries * feat: use managed runtime for MCP semantic compute * docs: add plan for managed agent and MCP semantic runtime * feat(cli): add managed daemon HTTP helpers * feat(cli): route local adapters through managed daemon * feat(cli): use managed daemon for ingest helpers * feat(cli): pass managed daemon options to scan * feat(context): pass MCP ingest pull config options * feat(cli): pass managed daemon options to serve ingest * test: verify managed local ingest daemon runtime * docs: add plan for managed local ingest daemon runtime * docs: align managed runtime examples * docs: add plan for managed runtime docs cleanup * test: cover published package runtime smoke commands * test: validate published package smoke outputs * docs: add plan for published package runtime smoke * build: stamp public npm package version * release: add npm public release policy * release: add guarded npm publish script * release: document public npm release handoff * docs: add plan for public npm release handoff * test: cover managed runtime prune in package smoke * docs: document managed runtime prune * docs: add plan for managed runtime prune smoke and docs * chore: encode uv runtime prerequisite policy * fix: clarify missing uv runtime error * docs: document uv runtime prerequisite * docs: add plan for uv runtime prerequisite contract * refactor: limit release artifacts to public package runtime * chore: align release policy with bundled runtime wheel * docs: describe single public runtime artifact surface * test: verify single public runtime artifact contract * docs: add plan for single public runtime artifact cleanup * fix: align local embeddings smoke with public version * docs: add plan for local embeddings smoke public version * release: soft-launch as @kaelio/ktx@0.1.0-rc.0 on next tag Publish target moves to the pre-release version 0.1.0-rc.0 under the next dist-tag so npm install @kaelio/ktx (which resolves to latest) does not pick up the soft-launch build. Users opt in via @kaelio/ktx@next. * Fix release script boundary checks * Remove PostHog from public package bundle
2026-05-11 15:50:34 +02:00
installPolicy: 'auto',
io: runtimeIo.io,
feat: npm-managed Python runtime for @kaelio/ktx (#7) * docs: add npm managed python runtime design * build: add bundled python runtime wheel builder * build: make local embedding dependencies optional * build: bundle python runtime wheel in cli artifacts * build: track bundled python runtime release artifact * test: verify bundled python runtime wheel * docs: add plan for bundled python runtime wheel * test: cover managed python runtime lifecycle * feat: add managed python runtime installer * feat: add runtime command runner * feat: expose runtime management commands * test: verify managed python runtime commands * docs: add plan for managed python runtime installer * feat: add managed python command helper * feat: use managed runtime for sl query compute * feat: route sl query managed runtime policy * docs: add plan for managed runtime sl query integration * feat: add managed runtime daemon metadata * feat: manage python daemon lifecycle * feat: add runtime daemon start stop commands * fix: verify managed runtime daemon lifecycle * docs: add plan for managed runtime daemon lifecycle * feat: add managed local embeddings config marker * feat: add managed local embeddings daemon helper * feat: use managed runtime for local embedding setup * feat: pass managed runtime policy through setup * docs: add plan for managed local embeddings runtime * feat: read CLI package metadata dynamically * feat: assemble public kaelio ktx npm package * feat: release one public kaelio ktx npm artifact * test: cover public kaelio ktx package invocations * chore: verify public kaelio ktx package artifacts * docs: add plan for public kaelio ktx npm package * test: verify managed runtime in public package smoke * test: finalize managed runtime release smoke * docs: add plan for managed runtime release smoke * test: specify local embeddings release smoke * feat: add local embeddings runtime smoke * chore: register local embeddings smoke * fix: verify local embeddings smoke * fix: restore artifact smoke python env helper * docs: add plan for managed local embeddings release smoke * refactor: share managed runtime install policy parsing * feat: use managed runtime for agent semantic queries * feat: use managed runtime for MCP semantic compute * docs: add plan for managed agent and MCP semantic runtime * feat(cli): add managed daemon HTTP helpers * feat(cli): route local adapters through managed daemon * feat(cli): use managed daemon for ingest helpers * feat(cli): pass managed daemon options to scan * feat(context): pass MCP ingest pull config options * feat(cli): pass managed daemon options to serve ingest * test: verify managed local ingest daemon runtime * docs: add plan for managed local ingest daemon runtime * docs: align managed runtime examples * docs: add plan for managed runtime docs cleanup * test: cover published package runtime smoke commands * test: validate published package smoke outputs * docs: add plan for published package runtime smoke * build: stamp public npm package version * release: add npm public release policy * release: add guarded npm publish script * release: document public npm release handoff * docs: add plan for public npm release handoff * test: cover managed runtime prune in package smoke * docs: document managed runtime prune * docs: add plan for managed runtime prune smoke and docs * chore: encode uv runtime prerequisite policy * fix: clarify missing uv runtime error * docs: document uv runtime prerequisite * docs: add plan for uv runtime prerequisite contract * refactor: limit release artifacts to public package runtime * chore: align release policy with bundled runtime wheel * docs: describe single public runtime artifact surface * test: verify single public runtime artifact contract * docs: add plan for single public runtime artifact cleanup * fix: align local embeddings smoke with public version * docs: add plan for local embeddings smoke public version * release: soft-launch as @kaelio/ktx@0.1.0-rc.0 on next tag Publish target moves to the pre-release version 0.1.0-rc.0 under the next dist-tag so npm install @kaelio/ktx (which resolves to latest) does not pick up the soft-launch build. Users opt in via @kaelio/ktx@next. * Fix release script boundary checks * Remove PostHog from public package bundle
2026-05-11 15:50:34 +02:00
},
});
});
chore(workspace): gate dead-code with knip production mode (#196) * refactor(workspace): relocate @ktx/llm source into packages/cli/src/llm * refactor(workspace): rewrite @ktx/llm imports to relative paths * refactor(workspace): fold internal packages into cli * chore(workspace): gate dead-code with knip production mode Turn on production-mode knip plus an autofix run in pre-commit and the `pnpm dead-code` script, document the `/** @internal */` convention for test-only exports in AGENTS.md, annotate test-only exports across the CLI with that JSDoc, and drop dead exports/wrappers the new gate surfaced (e.g. `cli-project.ts`, `lookerRuntimeSourceToFileAdapterSource`, `createLocalScanEnrichmentProvidersFromConfig`, `PGLITE_OWNER_PROCESS_BACKEND_CAPABILITIES`, stale type re-exports). Replace the loose `ignoreIssues` allowlist in `knip.json` with explicit production entries so cross-package barrel leaks are caught. * refactor(cli): delete internal barrel index.ts files The 34 `index.ts` re-export barrels inside `packages/cli/src/` were holdovers from the pre-fold multi-workspace structure. Post-fold-in they served no production purpose: external consumers go through the single package main entry, and in-repo callers mostly imported through them only because the path was short. Internally, knip flagged most barrel re-exports as production-dead (only reached via tests). This change: - Deletes every internal barrel except `packages/cli/src/index.ts` (the published package entry). - Rewrites ~270 source/test files to import each name directly from the file that defines it. - Moves `tools/warehouse-verification/index.ts` to `create-warehouse-verification-tools.ts` (the function it defined locally) and updates its single consumer. - Renames `search/backend-conformance.ts` → `.test-utils.ts` to match the existing test-helper file convention. - Deletes 13 dead test-only chains (dbt-descriptions/*, live-database/extracted-schema, live-database/structural-sync, relationship-* feedback/review chain) plus their tests and a cascading orphan integration test. - Updates test mocks that pointed at deleted barrel paths (notion-client, connector barrels in scan/local-scan-connectors tests) to mock the source files instead. - Points the maintainer benchmark script (`scripts/relationship-benchmark-report.mjs`) at source files instead of `dist/context/scan/index.js`. - Drops the barrel `!` entries from `knip.json`; adds explicit production entries only for the benchmark code reached via dist by the maintainer script. Net: 413 files changed, ~1.2k insertions, ~9.4k deletions. `pnpm run dead-code` (Biome + knip default + knip production) and `pnpm run type-check` are clean; 2277 tests pass. * refactor(workspace): rename @ktx/cli to @kaelio/ktx and pack it directly Promote the CLI workspace package to the public name `@kaelio/ktx` and drop the separate `scripts/build-public-npm-package.mjs` wrapper. The CLI package is now publishable in place (`publishConfig.access: public`, `provenance: true`), so artifact packing uses `pnpm pack` against `packages/cli/` instead of assembling a parallel package tree. Updates all workspace filter invocations, docs, tests, and release readiness checks to reference the new package name, and folds the tarball-name helper into `scripts/public-npm-release-metadata.mjs`. * docs: align "agent clients" and "data agents" terminology Replace "client agents" with "agent clients" and "database agents" with "data agents" across AGENTS.md, README.md, the docs-site copy, and the matching setup-agents test description, matching the canonical vocabulary in docs/terminology.md. Also moves packages/cli/tsconfig.json's tsBuildInfoFile from node_modules/.cache/ to dist/.tsbuildinfo so incremental builds survive node_modules reinstalls. * refactor(release): single source of truth for package version Make packages/cli/package.json the single source of truth for the @kaelio/ktx version. publicNpmPackageVersion() now reads it directly, so artifact filenames, release-readiness checks, and the Python wheel version all derive from one field. The duplicate release-policy.json.publicNpmPackageVersion is removed. Previously the two fields could drift: tarballs were named kaelio-ktx-0.4.1.tgz while internally containing @kaelio/ktx@0.0.0-private. - update-public-release-version.mjs rewrites both Python pyproject.toml files (ktx-daemon, ktx-sl) alongside the npm package.jsons, normalizing the version for PEP 440 (e.g. 0.1.0-rc.2 -> 0.1.0rc2). - semantic-release-config.cjs adds the two pyproject.toml files to @semantic-release/git assets so the release commit back to main carries every version source in lockstep. - The six "?? '0.0.0-private'" fallback literals across the CLI are replaced with "?? getKtxCliPackageInfo().version", and createDefaultKtxMcpServer makes its version arg required. - docs/release.md describes the actual commit-back model: the dev tree always reflects the most recent release; no sentinel pin to maintain. Verified: pnpm run artifacts:build now produces kaelio-ktx-0.4.1.tgz and kaelio_ktx-0.4.1-py3-none-any.whl with @kaelio/ktx@0.4.1 inside. Full type-check, dead-code, and 2287 vitests + 173 script tests pass. * refactor(cli): inject embedding provider resolution and detect sentence-transformers runtime Make resolveProjectEmbeddingProvider and runtimeIo injectable in ingest and scan command entrypoints so tests can stub them, and teach resolvePublicIngestRuntimeRequirements to flag the local-embeddings runtime feature when ktx.yaml selects sentence-transformers. * chore(cli): mark buildLocalStatsStatus and LocalStatsStatus as @internal Both symbols are consumed only by status-project.test.ts. Annotating with /** @internal */ keeps knip's production-mode check clean without changing runtime behavior. * fix(cli): use real package metadata in print-command-tree The stubbed package name embedded a forbidden product identifier that tripped the boundary check in CI. Read the metadata from package.json instead — keeps the rendered tree unchanged and removes a duplicate source of truth. * feat(cli): show embedding coverage in `ktx status`, drop duplicate disk counts Inline `(N embedded)` next to the Wiki scope counts and Semantic-layer source counts, computed with `SUM(embedding_json IS NOT NULL)` over `knowledge_pages` and `local_sl_sources`. Rename the "Knowledge" label to "Wiki" (canonical per `docs/terminology.md`) and rename the matching `localStats.knowledgePages` field to `localStats.wikiPages`. Drop `wiki=N md` and `semantic-layer=N yaml` from the Disk row — those duplicated the per-surface rows above. Disk now reports only actual byte usage (db, cache, raw-sources). The unused `wikiGlobalMarkdownCount` / `semanticLayerYamlCount` fields, the `isMarkdownEntry` / `isYamlEntry` helpers, and the `filter` arg on `summarizeDir` are removed.
2026-05-21 15:28:58 +02:00
it('uses runtime IO when resolving managed embedding runtime', async () => {
await initKtxProject({ projectDir: tempDir });
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report,
}),
);
const resolveEmbeddingProvider = vi.fn(async () => ({ kind: 'disabled' as const }));
const io = makeIo();
const runtimeIo = makeIo({ isTTY: true });
await expect(
runKtxScan(
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
cliVersion: '0.2.0',
runtimeInstallPolicy: 'auto',
},
io.io,
{
runLocalScan,
createLocalIngestAdapters: noLocalIngestAdapters,
runtimeIo: runtimeIo.io,
resolveEmbeddingProvider,
},
),
).resolves.toBe(0);
expect(resolveEmbeddingProvider).toHaveBeenCalledWith(
expect.anything(),
expect.objectContaining({
installPolicy: 'auto',
io: runtimeIo.io,
}),
);
});
2026-05-10 23:12:26 +02:00
it('explains warnings, capability gaps, and relationships in human scan summaries', async () => {
await initKtxProject({ projectDir: tempDir });
2026-05-10 23:12:26 +02:00
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'relationships',
dryRun: false,
syncId: 'sync-1',
report: reportWithAttention,
}),
);
const io = makeIo();
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
2026-05-10 23:12:26 +02:00
),
).resolves.toBe(0);
expect(io.stdout()).toContain('Semantic layer comparison found 5 changes across 18 tables');
expect(io.stdout()).toContain('New columns: 18');
expect(io.stdout()).toContain('Changed columns: 5');
expect(io.stdout()).toContain('Relationships\n');
expect(io.stdout()).toContain('Accepted: 7');
expect(io.stdout()).toContain('Review: 3');
expect(io.stdout()).toContain('Rejected: 2');
expect(io.stdout()).toContain('Skipped: 4');
expect(io.stdout()).toContain('Needs attention\n');
expect(io.stdout()).toContain('2 warnings');
expect(io.stdout()).toContain('1 capability gap');
expect(io.stdout()).toContain('columnStats is unavailable; relationship confidence may be lower.');
expect(io.stdout()).toContain(
'relationship_validation_failed: orders.customer_id: Could not validate relationship orders.customer_id -> customers.id',
);
expect(io.stdout()).not.toContain('+3');
expect(io.stdout()).not.toContain('~2');
expect(io.stdout()).not.toContain('=13');
});
it('prints review-only relationship summaries and validation capability warnings', async () => {
await initKtxProject({ projectDir: tempDir });
2026-05-10 23:51:24 +02:00
const reviewOnlyReport: KtxScanReport = {
2026-05-10 23:12:26 +02:00
...reportWithAttention,
capabilityGaps: [],
warnings: [
{
code: 'connector_capability_missing',
message: 'ktx scan connector cannot run read-only SQL relationship validation',
2026-05-10 23:12:26 +02:00
recoverable: true,
metadata: { capability: 'readOnlySql' },
},
],
relationships: { accepted: 0, review: 12, rejected: 44, skipped: 0 },
};
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-review',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'relationships',
dryRun: false,
syncId: 'sync-review',
report: reviewOnlyReport,
}),
);
const io = makeIo();
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
2026-05-10 23:12:26 +02:00
),
).resolves.toBe(0);
expect(io.stdout()).toContain('Relationships');
expect(io.stdout()).toContain('Accepted: 0');
expect(io.stdout()).toContain('Review: 12');
expect(io.stdout()).toContain('Rejected: 44');
expect(io.stdout()).toContain(
'connector_capability_missing: ktx scan connector cannot run read-only SQL relationship validation',
2026-05-10 23:12:26 +02:00
);
});
it('passes a scan progress port and prints TTY progress messages', async () => {
await initKtxProject({ projectDir: tempDir });
2026-05-10 23:12:26 +02:00
const runLocalScan = vi.fn(async (input: RunLocalScanOptions): Promise<LocalScanRunResult> => {
await input.progress?.update(0.15, 'Inspecting database schema');
await input.progress?.update(0.55, 'Semantic layer comparison found 5 changes across 18 tables');
return {
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'relationships',
dryRun: false,
syncId: 'sync-1',
report: reportWithAttention,
};
});
const io = makeIo({ isTTY: true });
const previousCi = process.env.CI;
delete process.env.CI;
try {
2026-05-10 23:51:24 +02:00
const exitCode = await runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
2026-05-10 23:12:26 +02:00
);
expect({ exitCode, stderr: io.stderr() }).toEqual({ exitCode: 0, stderr: '' });
} finally {
if (previousCi === undefined) {
delete process.env.CI;
} else {
process.env.CI = previousCi;
}
}
expect(runLocalScan.mock.calls[0]?.[0].progress).toBeDefined();
expect(io.stdout()).toContain('[15%] Inspecting database schema');
expect(io.stdout()).toContain('[55%] Semantic layer comparison found 5 changes across 18 tables');
});
it('uses injected structured progress without requiring TTY progress output', async () => {
await initKtxProject({ projectDir: tempDir });
const progressEvents: Array<{ progress: number; message?: string; transient?: boolean }> = [];
const structuredProgress = {
async update(progress: number, message?: string, options?: { transient?: boolean }) {
progressEvents.push({
progress,
...(message !== undefined ? { message } : {}),
...(options?.transient !== undefined ? { transient: options.transient } : {}),
});
},
startPhase() {
return structuredProgress;
},
};
const runLocalScan = vi.fn(async (input: RunLocalScanOptions): Promise<LocalScanRunResult> => {
await input.progress?.update(0.42, 'Generating descriptions 4/10 tables', { transient: true });
return {
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report,
};
});
const io = makeIo();
await expect(
runKtxScan(
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters, progress: structuredProgress },
),
).resolves.toBe(0);
expect(progressEvents).toContainEqual({
progress: 0.42,
message: 'Generating descriptions 4/10 tables',
transient: true,
});
expect(io.stdout()).not.toContain('[42%] Generating descriptions 4/10 tables');
});
2026-05-10 23:12:26 +02:00
it('updates transient TTY progress messages in place', async () => {
const io = makeIo({ isTTY: true });
const previousCi = process.env.CI;
delete process.env.CI;
try {
const progress = createCliScanProgress(io.io);
await progress.update(0.84, 'Generating descriptions 1/35 tables', { transient: true });
await progress.update(0.85, 'Generating descriptions 2/35 tables', { transient: true });
await progress.update(0.9, 'Building embeddings 1/4 batches');
} finally {
if (previousCi === undefined) {
delete process.env.CI;
} else {
process.env.CI = previousCi;
}
}
expect(io.stdout()).toContain('\r[84%] Generating descriptions 1/35 tables');
expect(io.stdout()).toContain('\r[85%] Generating descriptions 2/35 tables');
expect(io.stdout()).toContain('\n[90%] Building embeddings 1/4 batches\n');
});
it('scales nested progress phases by the parent phase weight', async () => {
const io = makeIo({ isTTY: true });
const previousCi = process.env.CI;
delete process.env.CI;
try {
const progress = createCliScanProgress(io.io);
await progress.update(0.82, 'Enriching schema metadata');
const enrichmentProgress = progress.startPhase(0.18);
await enrichmentProgress.update(0.05, 'Loaded schema snapshot with 56 tables');
const descriptionProgress = enrichmentProgress.startPhase(0.45);
await descriptionProgress.update(37 / 56, 'Generating descriptions 37/56 tables', { transient: true });
await descriptionProgress.update(1, 'Generated descriptions for 56 tables');
} finally {
if (previousCi === undefined) {
delete process.env.CI;
} else {
process.env.CI = previousCi;
}
}
expect(io.stdout()).toContain('\r[88%] Generating descriptions 37/56 tables');
expect(io.stdout()).toContain('\n[91%] Generated descriptions for 56 tables\n');
expect(io.stdout()).not.toContain('[100%] Generating descriptions 37/56 tables');
});
2026-05-10 23:12:26 +02:00
it('flushes transient TTY progress messages before printing scan failures', async () => {
await initKtxProject({ projectDir: tempDir });
2026-05-10 23:12:26 +02:00
const runLocalScan = vi.fn(async (input: RunLocalScanOptions): Promise<LocalScanRunResult> => {
await input.progress?.update(0.42, 'Generating descriptions 3/35 tables', { transient: true });
throw new Error('scan failed');
});
const io = makeIo({ isTTY: true });
const previousCi = process.env.CI;
delete process.env.CI;
try {
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{ runLocalScan, createLocalIngestAdapters: () => [] },
),
).resolves.toBe(1);
} finally {
if (previousCi === undefined) {
delete process.env.CI;
} else {
process.env.CI = previousCi;
}
}
expect(io.stdout()).toContain('\r[42%] Generating descriptions 3/35 tables\u001b[K\n');
expect(io.stderr()).toBe('scan failed\n');
});
it('does not print live progress messages for non-TTY output', async () => {
await initKtxProject({ projectDir: tempDir });
2026-05-10 23:12:26 +02:00
const runLocalScan = vi.fn(async (input: RunLocalScanOptions): Promise<LocalScanRunResult> => {
await input.progress?.update(0.15, 'Inspecting database schema');
return {
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report,
};
});
const io = makeIo();
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
2026-05-10 23:12:26 +02:00
),
).resolves.toBe(0);
expect(io.stdout()).not.toContain('[15%]');
expect(io.stdout()).not.toContain('Inspecting database schema');
});
it('uses terminal-aware visual styling only for TTY output', async () => {
await initKtxProject({ projectDir: tempDir });
2026-05-10 23:12:26 +02:00
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report,
}),
);
const io = makeIo({ isTTY: true });
const previousNoColor = process.env.NO_COLOR;
const previousCi = process.env.CI;
const previousTerm = process.env.TERM;
delete process.env.NO_COLOR;
delete process.env.CI;
process.env.TERM = 'xterm-256color';
try {
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
2026-05-10 23:12:26 +02:00
),
).resolves.toBe(0);
} finally {
if (previousNoColor === undefined) {
delete process.env.NO_COLOR;
} else {
process.env.NO_COLOR = previousNoColor;
}
if (previousCi === undefined) {
delete process.env.CI;
} else {
process.env.CI = previousCi;
}
if (previousTerm === undefined) {
delete process.env.TERM;
} else {
process.env.TERM = previousTerm;
}
}
expect(io.stdout()).toContain('✓');
expect(io.stdout()).toContain('ktx scan completed');
2026-05-10 23:12:26 +02:00
expect(io.stdout()).toContain('\u001b[');
});
it('honors NO_COLOR for TTY scan summaries', async () => {
await initKtxProject({ projectDir: tempDir });
2026-05-10 23:12:26 +02:00
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report,
}),
);
const io = makeIo({ isTTY: true });
const previousNoColor = process.env.NO_COLOR;
process.env.NO_COLOR = '1';
try {
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
2026-05-10 23:12:26 +02:00
),
).resolves.toBe(0);
} finally {
if (previousNoColor === undefined) {
delete process.env.NO_COLOR;
} else {
process.env.NO_COLOR = previousNoColor;
}
}
expect(io.stdout()).toContain('ktx scan completed');
2026-05-10 23:12:26 +02:00
expect(io.stdout()).not.toContain('\u001b[');
});
it('passes native CLI adapters into local scan runs for mysql configs', async () => {
2026-05-10 23:51:24 +02:00
const tempProject = await mkdtemp(join(tmpdir(), 'ktx-scan-cli-native-'));
await initKtxProject({ projectDir: tempProject });
2026-05-10 23:12:26 +02:00
await writeFile(
2026-05-10 23:51:24 +02:00
join(tempProject, 'ktx.yaml'),
2026-05-10 23:12:26 +02:00
[
'connections:',
' warehouse:',
' driver: mysql',
' url: env:MYSQL_URL',
'',
].join('\n'),
'utf-8',
);
const io = makeIo();
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report,
}),
);
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempProject,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
2026-05-10 23:12:26 +02:00
),
).resolves.toBe(0);
expect(runLocalScan).toHaveBeenCalledWith(expect.objectContaining({ adapters: expect.any(Array) }));
await rm(tempProject, { recursive: true, force: true });
});
it('creates a native connector for standalone relationship scans', async () => {
2026-05-10 23:51:24 +02:00
const tempProject = await mkdtemp(join(tmpdir(), 'ktx-scan-cli-relationships-'));
await initKtxProject({ projectDir: tempProject });
2026-05-10 23:12:26 +02:00
await writeFile(
2026-05-10 23:51:24 +02:00
join(tempProject, 'ktx.yaml'),
2026-05-10 23:12:26 +02:00
[
'connections:',
' warehouse:',
' driver: sqlite',
' path: warehouse.db',
'',
].join('\n'),
'utf-8',
);
const io = makeIo();
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'relationships',
dryRun: false,
syncId: 'sync-1',
report: { ...report, mode: 'relationships' },
}),
);
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempProject,
connectionId: 'warehouse',
mode: 'relationships',
detectRelationships: true,
dryRun: false,
},
io.io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
2026-05-10 23:12:26 +02:00
),
).resolves.toBe(0);
expect(runLocalScan).toHaveBeenCalledWith(
expect.objectContaining({
mode: 'relationships',
detectRelationships: true,
connector: expect.objectContaining({ driver: 'sqlite' }),
}),
);
await rm(tempProject, { recursive: true, force: true });
});
fix(snowflake): unblock multi-schema ingest and relationship discovery (#204) * feat(setup): drop redundant Snowflake schema prompt; fall back to free-text on listSchemas failure Snowflake setup previously asked for a single schema as free text, then ran a multiselect against the discovered schemas — two schema questions back-to-back, with the first being only a session bootstrap. The SDK's `schema` is optional, so the bootstrap step is unnecessary. - Remove the free-text Snowflake schema prompt; only pass `schema` to snowflake-sdk when one is configured. - When `listSchemas()` fails (e.g. role lacks SHOW SCHEMAS), prompt the user for a comma-separated list, persist it as `schema_names`, and use it as both the table-list filter and the multiselect default. Applies to every driver with a scope-discovery spec, not just Snowflake. - Update docs to lead with `schema_names`; keep `schema_name` as a documented single-schema shorthand. * fix(snowflake): keep introspecting when primary-key discovery is denied The PK query joins INFORMATION_SCHEMA.TABLE_CONSTRAINTS and INFORMATION_SCHEMA.KEY_COLUMN_USAGE, which require grants the connection role may not have. Previously a 'SQL compilation error: Object ANALYTICS.INFORMATION_SCHEMA.KEY_COLUMN_USAGE does not exist or not authorized' aborted the entire introspect — schemas, columns, and row counts were all discarded over a missing nice-to-have. Wrap the constraint query in try/catch, log a one-line warning per schema, and return an empty PK map. Columns end up with primaryKey=false; relationship inference still has FK and profiling to fall back on. * fix(scan): unblock relationship discovery on Snowflake Two adjacent bugs prevented the scan's relationship pipeline from producing any joins on a Snowflake warehouse: - relationship-profiling.ts fell through to a default `GROUP_CONCAT` branch for unknown drivers. Snowflake has no GROUP_CONCAT, so every per-table profile query failed with "Unknown function GROUP_CONCAT". Add an explicit Snowflake branch that uses LISTAGG with a literal '\x1f' delimiter (Snowflake requires the delimiter to be a constant, so CHR(31) is rejected). - description-generation.ts destructured `connector.sampleTable` and `connector.sampleColumn` into bare locals, losing the `this` binding when the class-method connectors (Snowflake, Postgres, MySQL) were invoked. Every sample call threw "Cannot read properties of undefined (reading 'assertConnection')" and degraded LLM descriptions to metadata-only prompts. Call the methods through the connector instead. Without these, even after the primary-key probe is allowed to fail softly, the scan ends up with 0 validated relationships and an empty `joins:` block in every shard YAML. * test(scan): cover table-ref helpers * feat(scan): plumb tableScope through live-database introspection port * feat(scan): apply tableScope during metadata fetch * feat(scan): enforce table scope at fetch boundary * feat(scan): pool Snowflake sessions and batch enrichment for faster ingest (#206) * feat(cli): add RSA key-pair auth option to Snowflake setup wizard Extends the interactive Snowflake setup flow with an authentication-method prompt (password vs RSA/JWT key-pair). The RSA branch collects a private-key path (env/file/absolute) and an optional passphrase; the resulting connection config records `authMethod: 'rsa'` with `privateKey` and `passphrase` instead of `password`. * feat(scan): pool Snowflake sessions * fix(scan): reuse structural snapshots and cleanup connectors * feat(scan): parallelize relationship profiling * feat(scan): batch table description generation * docs: document Snowflake ingest concurrency knobs * fix(scan): close Snowflake ingest perf verification gaps * fix(scan): keep batched description failure bounded * feat(scan): dispatch query-history probes by connection driver Extract historic-sql dialect resolution into a shared helper so the status-project readiness check and the local ingest factory agree on which connections enable query history and which probe to run. The status command now picks the postgres/snowflake/bigquery probe based on the connection's driver instead of always reporting against postgres, which previously caused snowflake connections with queryHistory.enabled to surface a misleading "driver is snowflake" failure. Also drops a noisy console.warn from Snowflake primary-key discovery — INFORMATION_SCHEMA.KEY_COLUMN_USAGE is commonly ungranted for read-only roles and the FK + profiling paths handle the empty PK map already. * fix(llm): allow StructuredOutput tool and raise maxTurns for generateObject The Claude Code agent SDK announces an internal pseudo-tool named StructuredOutput in the system/init message whenever outputFormat is set to { type: 'json_schema' }. The runtime's isolation check built its allowedToolIds set only from MCP tool ids and treated StructuredOutput as an unexpected host-injected tool, so every generateObject call threw "Claude Code runtime isolation failed: tools=StructuredOutput ..." and the table-descriptions and relationship-LLM-proposal enrichment stages recorded null output across the board. Whitelist StructuredOutput specifically in generateObject's allowedToolIds — the check also enforces missing_tools symmetry, so generateText and runAgentLoop, which do not see StructuredOutput, must not require it. generateObject also ran with maxTurns: 1, which the model intermittently breached when it emitted thinking text before the structured response. Raised to 5 to give the schema-bound call enough headroom without allowing unbounded loops. The existing tests now exercise the path with an init message that announces StructuredOutput so the regression cannot slip back in. * chore(scripts): add ktx-reset.sh project-cleanup helper Convenience script for repeatable ingest testing: takes a project directory and prunes everything except ktx.yaml and .ktx/secrets/, so the next ktx setup or ktx ingest run starts from a known-clean state.
2026-05-23 10:41:30 +02:00
it('cleans up a constructed scan connector after an enriched scan succeeds', async () => {
await initKtxProject({ projectDir: tempDir });
await writeFile(
join(tempDir, 'ktx.yaml'),
[
'connections:',
' warehouse:',
' driver: snowflake',
' account: acct',
' warehouse: WH',
' database: ANALYTICS',
' schema_name: PUBLIC',
' username: reader',
' password: env:SNOWFLAKE_PASSWORD',
'',
].join('\n'),
'utf-8',
);
snowflakeConnectorInstances.length = 0;
const runLocalScan = vi.fn(async (): Promise<LocalScanRunResult> => ({
runId: 'scan-run-cleanup',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'enriched',
dryRun: false,
syncId: 'sync-1',
report: { ...report, mode: 'enriched' },
}));
await expect(
runKtxScan(
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'enriched',
detectRelationships: false,
dryRun: false,
},
makeIo().io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
),
).resolves.toBe(0);
expect(snowflakeConnectorInstances[0]?.cleanup).toHaveBeenCalledTimes(1);
});
it('cleans up a constructed scan connector after runLocalScan throws', async () => {
await initKtxProject({ projectDir: tempDir });
await writeFile(
join(tempDir, 'ktx.yaml'),
[
'connections:',
' warehouse:',
' driver: snowflake',
' account: acct',
' warehouse: WH',
' database: ANALYTICS',
' schema_name: PUBLIC',
' username: reader',
' password: env:SNOWFLAKE_PASSWORD',
'',
].join('\n'),
'utf-8',
);
snowflakeConnectorInstances.length = 0;
const runLocalScan = vi.fn(async () => {
throw new Error('scan failed');
});
await expect(
runKtxScan(
{
command: 'run',
projectDir: tempDir,
connectionId: 'warehouse',
mode: 'relationships',
detectRelationships: true,
dryRun: false,
},
makeIo().io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
),
).resolves.toBe(1);
expect(snowflakeConnectorInstances[0]?.cleanup).toHaveBeenCalledTimes(1);
});
2026-05-10 23:12:26 +02:00
it('routes standalone postgres scans through the native connector before daemon fallback', async () => {
2026-05-10 23:51:24 +02:00
const tempProject = await mkdtemp(join(tmpdir(), 'ktx-scan-cli-native-postgres-'));
await initKtxProject({ projectDir: tempProject });
2026-05-10 23:12:26 +02:00
await writeFile(
2026-05-10 23:51:24 +02:00
join(tempProject, 'ktx.yaml'),
2026-05-10 23:12:26 +02:00
[
'connections:',
' warehouse:',
' driver: postgres',
' host: db.example.test',
' database: analytics',
' username: reader',
' password: env:POSTGRES_PASSWORD',
'',
].join('\n'),
'utf-8',
);
const io = makeIo();
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report,
}),
);
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempProject,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{
runLocalScan,
createLocalIngestAdapters: () => [fakeLiveDatabaseAdapter(createPostgresLiveDatabaseIntrospection)],
},
2026-05-10 23:12:26 +02:00
),
).resolves.toBe(0);
expect(runLocalScan).toHaveBeenCalledWith(expect.objectContaining({ adapters: expect.any(Array) }));
const scanOptions = runLocalScan.mock.calls[0]?.[0];
const liveDatabase = scanOptions?.adapters?.find((adapter) => adapter.source === 'live-database');
if (!liveDatabase?.fetch) {
throw new Error('Expected scan adapters to include a fetch-capable live-database adapter');
}
const stagedDir = join(tempProject, 'postgres-staged');
await liveDatabase.fetch(undefined, stagedDir, { connectionId: 'warehouse', sourceKey: 'live-database' });
expect(createPostgresLiveDatabaseIntrospection).toHaveBeenCalledWith({ connections: expect.any(Object) });
expect(postgresExtractSchema).toHaveBeenCalledWith('warehouse');
await expect(readFile(join(stagedDir, 'connection.json'), 'utf-8')).resolves.toContain(
'"connectionId": "warehouse"',
);
await rm(tempProject, { recursive: true, force: true });
});
it('passes native CLI adapters into local scan runs for clickhouse configs', async () => {
2026-05-10 23:51:24 +02:00
const tempProject = await mkdtemp(join(tmpdir(), 'ktx-scan-cli-native-clickhouse-'));
await initKtxProject({ projectDir: tempProject });
2026-05-10 23:12:26 +02:00
await writeFile(
2026-05-10 23:51:24 +02:00
join(tempProject, 'ktx.yaml'),
2026-05-10 23:12:26 +02:00
[
'connections:',
' warehouse:',
' driver: clickhouse',
' host: env:CLICKHOUSE_HOST',
' database: analytics',
' username: reader',
' password: env:CLICKHOUSE_PASSWORD',
'',
].join('\n'),
'utf-8',
);
const io = makeIo();
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report: { ...report, driver: 'clickhouse' },
}),
);
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempProject,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{ runLocalScan, createLocalIngestAdapters: noLocalIngestAdapters },
2026-05-10 23:12:26 +02:00
),
).resolves.toBe(0);
expect(runLocalScan).toHaveBeenCalledWith(expect.objectContaining({ adapters: expect.any(Array) }));
await rm(tempProject, { recursive: true, force: true });
});
it('passes native CLI adapters into local scan runs for sqlserver configs', async () => {
2026-05-10 23:51:24 +02:00
const tempProject = await mkdtemp(join(tmpdir(), 'ktx-scan-cli-native-sqlserver-'));
await initKtxProject({ projectDir: tempProject });
2026-05-10 23:12:26 +02:00
await writeFile(
2026-05-10 23:51:24 +02:00
join(tempProject, 'ktx.yaml'),
2026-05-10 23:12:26 +02:00
[
'connections:',
' warehouse:',
' driver: sqlserver',
' host: env:SQLSERVER_HOST',
' database: analytics',
' username: reader',
' schema: dbo',
'',
].join('\n'),
'utf-8',
);
const io = makeIo();
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report: { ...report, driver: 'sqlserver' },
}),
);
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempProject,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{
runLocalScan,
createLocalIngestAdapters: () => [fakeLiveDatabaseAdapter(createSqlServerLiveDatabaseIntrospection)],
},
2026-05-10 23:12:26 +02:00
),
).resolves.toBe(0);
expect(runLocalScan).toHaveBeenCalledWith(expect.objectContaining({ adapters: expect.any(Array) }));
const scanOptions = runLocalScan.mock.calls[0]?.[0];
const liveDatabase = scanOptions?.adapters?.find((adapter) => adapter.source === 'live-database');
if (!liveDatabase?.fetch) {
throw new Error('Expected scan adapters to include a fetch-capable live-database adapter');
}
const stagedDir = join(tempProject, 'sqlserver-staged');
await liveDatabase.fetch(undefined, stagedDir, { connectionId: 'warehouse', sourceKey: 'live-database' });
expect(createSqlServerLiveDatabaseIntrospection).toHaveBeenCalledWith({ connections: expect.any(Object) });
expect(sqlServerExtractSchema).toHaveBeenCalledWith('warehouse');
await expect(readFile(join(stagedDir, 'connection.json'), 'utf-8')).resolves.toContain(
'"connectionId": "warehouse"',
);
await rm(tempProject, { recursive: true, force: true });
});
it('passes native CLI adapters into local scan runs for bigquery configs', async () => {
2026-05-10 23:51:24 +02:00
const tempProject = await mkdtemp(join(tmpdir(), 'ktx-scan-cli-native-bigquery-'));
await initKtxProject({ projectDir: tempProject });
2026-05-10 23:12:26 +02:00
await writeFile(
2026-05-10 23:51:24 +02:00
join(tempProject, 'ktx.yaml'),
2026-05-10 23:12:26 +02:00
[
'connections:',
' warehouse:',
' driver: bigquery',
' dataset_id: analytics',
' credentials_json: env:BIGQUERY_CREDENTIALS_JSON',
' location: US',
'',
].join('\n'),
'utf-8',
);
const io = makeIo();
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report: { ...report, driver: 'bigquery' },
}),
);
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempProject,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{
runLocalScan,
createLocalIngestAdapters: () => [fakeLiveDatabaseAdapter(createBigQueryLiveDatabaseIntrospection)],
},
2026-05-10 23:12:26 +02:00
),
).resolves.toBe(0);
expect(runLocalScan).toHaveBeenCalledWith(expect.objectContaining({ adapters: expect.any(Array) }));
const scanOptions = runLocalScan.mock.calls[0]?.[0];
const liveDatabase = scanOptions?.adapters?.find((adapter) => adapter.source === 'live-database');
if (!liveDatabase?.fetch) {
throw new Error('Expected scan adapters to include a fetch-capable live-database adapter');
}
const stagedDir = join(tempProject, 'bigquery-staged');
await liveDatabase.fetch(undefined, stagedDir, { connectionId: 'warehouse', sourceKey: 'live-database' });
expect(createBigQueryLiveDatabaseIntrospection).toHaveBeenCalledWith({ connections: expect.any(Object) });
expect(bigQueryExtractSchema).toHaveBeenCalledWith('warehouse');
await expect(readFile(join(stagedDir, 'connection.json'), 'utf-8')).resolves.toContain(
'"connectionId": "warehouse"',
);
await rm(tempProject, { recursive: true, force: true });
});
it('passes native CLI adapters into local scan runs for snowflake configs', async () => {
2026-05-10 23:51:24 +02:00
const tempProject = await mkdtemp(join(tmpdir(), 'ktx-scan-cli-native-snowflake-'));
await initKtxProject({ projectDir: tempProject });
2026-05-10 23:12:26 +02:00
await writeFile(
2026-05-10 23:51:24 +02:00
join(tempProject, 'ktx.yaml'),
2026-05-10 23:12:26 +02:00
[
'connections:',
' warehouse:',
' driver: snowflake',
' authMethod: password',
' account: env:SNOWFLAKE_ACCOUNT',
' warehouse: WH',
' database: ANALYTICS',
' schema_name: PUBLIC',
' username: reader',
'',
].join('\n'),
'utf-8',
);
const io = makeIo();
const runLocalScan = vi.fn(
async (_input: RunLocalScanOptions): Promise<LocalScanRunResult> => ({
runId: 'scan-run-1',
status: 'done',
done: true,
connectionId: 'warehouse',
mode: 'structural',
dryRun: false,
syncId: 'sync-1',
report: { ...report, driver: 'snowflake' },
}),
);
await expect(
2026-05-10 23:51:24 +02:00
runKtxScan(
2026-05-10 23:12:26 +02:00
{
command: 'run',
projectDir: tempProject,
connectionId: 'warehouse',
mode: 'structural',
detectRelationships: false,
dryRun: false,
},
io.io,
{
runLocalScan,
createLocalIngestAdapters: () => [fakeLiveDatabaseAdapter(createSnowflakeLiveDatabaseIntrospection)],
},
2026-05-10 23:12:26 +02:00
),
).resolves.toBe(0);
expect(runLocalScan).toHaveBeenCalledWith(expect.objectContaining({ adapters: expect.any(Array) }));
const scanOptions = runLocalScan.mock.calls[0]?.[0];
const liveDatabase = scanOptions?.adapters?.find((adapter) => adapter.source === 'live-database');
if (!liveDatabase?.fetch) {
throw new Error('Expected scan adapters to include a fetch-capable live-database adapter');
}
const stagedDir = join(tempProject, 'snowflake-staged');
await liveDatabase.fetch(undefined, stagedDir, { connectionId: 'warehouse', sourceKey: 'live-database' });
expect(createSnowflakeLiveDatabaseIntrospection).toHaveBeenCalledWith({ connections: expect.any(Object) });
expect(snowflakeExtractSchema).toHaveBeenCalledWith('warehouse');
await expect(readFile(join(stagedDir, 'connection.json'), 'utf-8')).resolves.toContain(
'"connectionId": "warehouse"',
);
await rm(tempProject, { recursive: true, force: true });
});
});