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
|
|
|
import { loadKtxProject, type KtxLocalProject } from './context/project/project.js';
|
|
|
|
|
import type { KtxQueryResult, KtxScanConnector } from './context/scan/types.js';
|
|
|
|
|
import type { SqlAnalysisDialect, SqlAnalysisPort } from './context/sql-analysis/ports.js';
|
2026-05-17 10:29:07 +02:00
|
|
|
import type { KtxCliIo } from './cli-runtime.js';
|
2026-05-21 02:38:18 +02:00
|
|
|
import { type KtxOutputMode, resolveOutputMode } from './io/mode.js';
|
2026-05-17 10:29:07 +02:00
|
|
|
import { createKtxCliScanConnector } from './local-scan-connectors.js';
|
|
|
|
|
import { createManagedDaemonSqlAnalysisPort } from './managed-python-http.js';
|
|
|
|
|
import { profileMark } from './startup-profile.js';
|
|
|
|
|
|
|
|
|
|
profileMark('module:sql');
|
|
|
|
|
|
2026-05-21 02:38:18 +02:00
|
|
|
type KtxSqlOutputMode = KtxOutputMode;
|
2026-05-17 10:29:07 +02:00
|
|
|
|
|
|
|
|
export type KtxSqlArgs = {
|
|
|
|
|
command: 'execute';
|
|
|
|
|
projectDir: string;
|
|
|
|
|
connectionId: string;
|
|
|
|
|
sql: string;
|
|
|
|
|
maxRows: number;
|
|
|
|
|
output?: KtxSqlOutputMode;
|
|
|
|
|
json?: boolean;
|
|
|
|
|
cliVersion: string;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
export interface KtxSqlDeps {
|
|
|
|
|
loadProject?: typeof loadKtxProject;
|
|
|
|
|
createSqlAnalysis?: () => SqlAnalysisPort;
|
|
|
|
|
createScanConnector?: typeof createKtxCliScanConnector;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
interface SqlExecutionOutput {
|
|
|
|
|
connectionId: string;
|
|
|
|
|
headers: string[];
|
|
|
|
|
headerTypes?: string[];
|
|
|
|
|
rows: unknown[][];
|
|
|
|
|
rowCount: number;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function sqlAnalysisDialectForDriver(driver: string | undefined): SqlAnalysisDialect {
|
|
|
|
|
const normalized = String(driver ?? '').trim().toLowerCase();
|
|
|
|
|
const map: Record<string, SqlAnalysisDialect> = {
|
|
|
|
|
postgres: 'postgres',
|
|
|
|
|
postgresql: 'postgres',
|
|
|
|
|
bigquery: 'bigquery',
|
|
|
|
|
snowflake: 'snowflake',
|
|
|
|
|
mysql: 'mysql',
|
|
|
|
|
sqlserver: 'tsql',
|
|
|
|
|
mssql: 'tsql',
|
|
|
|
|
sqlite: 'sqlite',
|
|
|
|
|
sqlite3: 'sqlite',
|
|
|
|
|
clickhouse: 'clickhouse',
|
|
|
|
|
redshift: 'redshift',
|
|
|
|
|
};
|
|
|
|
|
return map[normalized] ?? 'postgres';
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function formatValue(value: unknown): string {
|
|
|
|
|
if (value === null || value === undefined) return '';
|
|
|
|
|
if (typeof value === 'string') return value;
|
|
|
|
|
if (typeof value === 'number' || typeof value === 'boolean' || typeof value === 'bigint') return String(value);
|
|
|
|
|
return JSON.stringify(value);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function printJson(output: SqlExecutionOutput, io: KtxCliIo): void {
|
|
|
|
|
io.stdout.write(`${JSON.stringify(output, null, 2)}\n`);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function printPlain(output: SqlExecutionOutput, io: KtxCliIo): void {
|
|
|
|
|
io.stdout.write(`${output.headers.join('\t')}\n`);
|
|
|
|
|
for (const row of output.rows) {
|
|
|
|
|
io.stdout.write(`${row.map(formatValue).join('\t')}\n`);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function printPretty(output: SqlExecutionOutput, io: KtxCliIo): void {
|
|
|
|
|
const rows = output.rows.map((row) => row.map(formatValue));
|
|
|
|
|
const widths = output.headers.map((header, index) =>
|
|
|
|
|
Math.max(header.length, ...rows.map((row) => row[index]?.length ?? 0)),
|
|
|
|
|
);
|
|
|
|
|
const renderRow = (cells: string[]): string =>
|
|
|
|
|
cells.map((cell, index) => cell.padEnd(widths[index] ?? cell.length)).join(' ').trimEnd();
|
|
|
|
|
|
|
|
|
|
if (output.headers.length > 0) {
|
|
|
|
|
io.stdout.write(`${renderRow(output.headers)}\n`);
|
|
|
|
|
io.stdout.write(`${renderRow(widths.map((width) => '-'.repeat(width)))}\n`);
|
|
|
|
|
}
|
|
|
|
|
for (const row of rows) {
|
|
|
|
|
io.stdout.write(`${renderRow(row)}\n`);
|
|
|
|
|
}
|
|
|
|
|
io.stdout.write(`\n${output.rowCount} ${output.rowCount === 1 ? 'row' : 'rows'}\n`);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function printSqlResult(output: SqlExecutionOutput, mode: KtxSqlOutputMode, io: KtxCliIo): void {
|
|
|
|
|
if (mode === 'json') {
|
|
|
|
|
printJson(output, io);
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
if (mode === 'plain') {
|
|
|
|
|
printPlain(output, io);
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
printPretty(output, io);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
async function cleanupConnector(connector: KtxScanConnector | null): Promise<void> {
|
|
|
|
|
if (connector?.cleanup) {
|
|
|
|
|
await connector.cleanup();
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function resultOutput(connectionId: string, result: KtxQueryResult): SqlExecutionOutput {
|
|
|
|
|
return {
|
|
|
|
|
connectionId,
|
|
|
|
|
headers: result.headers,
|
|
|
|
|
...(result.headerTypes ? { headerTypes: result.headerTypes } : {}),
|
|
|
|
|
rows: result.rows,
|
|
|
|
|
rowCount: result.rowCount ?? result.rows.length,
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export async function runKtxSql(args: KtxSqlArgs, io: KtxCliIo = process, deps: KtxSqlDeps = {}): Promise<number> {
|
|
|
|
|
try {
|
|
|
|
|
const project = await (deps.loadProject ?? loadKtxProject)({ projectDir: args.projectDir });
|
|
|
|
|
const connection = project.config.connections[args.connectionId];
|
|
|
|
|
if (!connection) {
|
|
|
|
|
throw new Error(`Connection "${args.connectionId}" is not configured in ktx.yaml`);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
const sqlAnalysis =
|
|
|
|
|
deps.createSqlAnalysis ??
|
|
|
|
|
(() =>
|
|
|
|
|
createManagedDaemonSqlAnalysisPort({
|
|
|
|
|
cliVersion: args.cliVersion,
|
|
|
|
|
projectDir: args.projectDir,
|
|
|
|
|
installPolicy: 'auto',
|
|
|
|
|
io,
|
|
|
|
|
}));
|
|
|
|
|
const validation = await sqlAnalysis().validateReadOnly(args.sql, sqlAnalysisDialectForDriver(connection.driver));
|
|
|
|
|
if (!validation.ok) {
|
|
|
|
|
throw new Error(validation.error ?? 'SQL is not read-only.');
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
const createScanConnector = deps.createScanConnector ?? createKtxCliScanConnector;
|
|
|
|
|
let connector: KtxScanConnector | null = null;
|
|
|
|
|
try {
|
|
|
|
|
connector = await createScanConnector(project as KtxLocalProject, args.connectionId);
|
|
|
|
|
if (!connector.capabilities.readOnlySql || !connector.executeReadOnly) {
|
|
|
|
|
throw new Error(`Connection "${args.connectionId}" does not support read-only SQL execution.`);
|
|
|
|
|
}
|
|
|
|
|
const result = await connector.executeReadOnly(
|
|
|
|
|
{
|
|
|
|
|
connectionId: args.connectionId,
|
|
|
|
|
sql: args.sql,
|
|
|
|
|
maxRows: args.maxRows,
|
|
|
|
|
},
|
|
|
|
|
{ runId: 'cli-sql' },
|
|
|
|
|
);
|
2026-05-21 02:38:18 +02:00
|
|
|
const mode = resolveOutputMode({ explicit: args.output, json: args.json, io });
|
|
|
|
|
printSqlResult(resultOutput(args.connectionId, result), mode, io);
|
2026-05-17 10:29:07 +02:00
|
|
|
return 0;
|
|
|
|
|
} finally {
|
|
|
|
|
await cleanupConnector(connector);
|
|
|
|
|
}
|
|
|
|
|
} catch (error) {
|
|
|
|
|
io.stderr.write(`${error instanceof Error ? error.message : String(error)}\n`);
|
|
|
|
|
return 1;
|
|
|
|
|
}
|
|
|
|
|
}
|