mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-13 08:15:14 +02:00
* 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.
193 lines
6.6 KiB
TypeScript
193 lines
6.6 KiB
TypeScript
import { request as httpRequest } from 'node:http';
|
|
import { request as httpsRequest } from 'node:https';
|
|
import { URL } from 'node:url';
|
|
import { createDaemonLookerTableIdentifierParser, type KtxDaemonTableIdentifierHttpJsonRunner } from './context/ingest/adapters/looker/daemon-table-identifier-parser.js';
|
|
import type { DaemonLiveDatabaseIntrospectionOptions, KtxDaemonDatabaseHttpJsonRunner } from './context/ingest/adapters/live-database/daemon-introspection.js';
|
|
import type { LookerTableIdentifierParser } from './context/ingest/adapters/looker/mapping.js';
|
|
import { createHttpSqlAnalysisPort, type KtxSqlAnalysisHttpJsonRunner } from './context/sql-analysis/http-sql-analysis-port.js';
|
|
import type { SqlAnalysisPort } from './context/sql-analysis/ports.js';
|
|
import type { KtxCliIo } from './cli-runtime.js';
|
|
import {
|
|
ensureManagedPythonCommandRuntime,
|
|
type KtxManagedPythonInstallPolicy,
|
|
type ManagedPythonCommandRuntime,
|
|
} from './managed-python-command.js';
|
|
import { startManagedPythonDaemon, type ManagedPythonDaemonStartResult } from './managed-python-daemon.js';
|
|
|
|
/** @internal */
|
|
export type ManagedPythonHttpJsonRunner = (
|
|
path: string,
|
|
payload: Record<string, unknown>,
|
|
) => Promise<Record<string, unknown>>;
|
|
|
|
type ManagedPythonHttpPostJson = (
|
|
baseUrl: string,
|
|
path: string,
|
|
payload: Record<string, unknown>,
|
|
) => Promise<Record<string, unknown>>;
|
|
|
|
export interface ManagedPythonCoreDaemonOptions {
|
|
cliVersion: string;
|
|
projectDir: string;
|
|
installPolicy: KtxManagedPythonInstallPolicy;
|
|
io: KtxCliIo;
|
|
ensureRuntime?: (options: {
|
|
cliVersion: string;
|
|
installPolicy: KtxManagedPythonInstallPolicy;
|
|
io: KtxCliIo;
|
|
feature: 'core';
|
|
}) => Promise<ManagedPythonCommandRuntime>;
|
|
startDaemon?: (options: {
|
|
cliVersion: string;
|
|
projectDir: string;
|
|
features: ['core'];
|
|
force: false;
|
|
}) => Promise<ManagedPythonDaemonStartResult>;
|
|
}
|
|
|
|
export type ManagedPythonDaemonHttpOptions =
|
|
| {
|
|
requestJson: ManagedPythonHttpJsonRunner;
|
|
}
|
|
| {
|
|
resolveBaseUrl: () => Promise<string>;
|
|
postJson?: ManagedPythonHttpPostJson;
|
|
}
|
|
| (ManagedPythonCoreDaemonOptions & {
|
|
postJson?: ManagedPythonHttpPostJson;
|
|
});
|
|
|
|
function normalizedBaseUrl(baseUrl: string): string {
|
|
return baseUrl.endsWith('/') ? baseUrl : `${baseUrl}/`;
|
|
}
|
|
|
|
function parseJsonObject(raw: string, path: string): Record<string, unknown> {
|
|
const parsed = JSON.parse(raw) as unknown;
|
|
if (!parsed || typeof parsed !== 'object' || Array.isArray(parsed)) {
|
|
throw new Error(`KTX daemon HTTP ${path} returned non-object JSON`);
|
|
}
|
|
return parsed as Record<string, unknown>;
|
|
}
|
|
|
|
async function postManagedDaemonJson(
|
|
baseUrl: string,
|
|
path: string,
|
|
payload: Record<string, unknown>,
|
|
): Promise<Record<string, unknown>> {
|
|
return await new Promise((resolve, reject) => {
|
|
const target = new URL(path.replace(/^\//, ''), normalizedBaseUrl(baseUrl));
|
|
const body = JSON.stringify(payload);
|
|
const client = target.protocol === 'https:' ? httpsRequest : httpRequest;
|
|
const request = client(
|
|
target,
|
|
{
|
|
method: 'POST',
|
|
headers: {
|
|
accept: 'application/json',
|
|
'content-type': 'application/json',
|
|
'content-length': Buffer.byteLength(body),
|
|
},
|
|
},
|
|
(response) => {
|
|
const chunks: Buffer[] = [];
|
|
response.on('data', (chunk: Buffer) => chunks.push(chunk));
|
|
response.on('end', () => {
|
|
const text = Buffer.concat(chunks).toString('utf8');
|
|
const statusCode = response.statusCode ?? 0;
|
|
if (statusCode < 200 || statusCode >= 300) {
|
|
reject(new Error(`KTX daemon HTTP ${path} failed with ${statusCode}: ${text}`));
|
|
return;
|
|
}
|
|
try {
|
|
resolve(parseJsonObject(text, path));
|
|
} catch (error) {
|
|
reject(error);
|
|
}
|
|
});
|
|
},
|
|
);
|
|
request.on('error', reject);
|
|
request.end(body);
|
|
});
|
|
}
|
|
|
|
/** @internal */
|
|
export function createManagedPythonDaemonBaseUrlResolver(
|
|
options: ManagedPythonCoreDaemonOptions,
|
|
): () => Promise<string> {
|
|
let cachedBaseUrl: string | undefined;
|
|
|
|
return async () => {
|
|
if (cachedBaseUrl) {
|
|
return cachedBaseUrl;
|
|
}
|
|
|
|
const ensureRuntime = options.ensureRuntime ?? ensureManagedPythonCommandRuntime;
|
|
const startDaemon = options.startDaemon ?? startManagedPythonDaemon;
|
|
await ensureRuntime({
|
|
cliVersion: options.cliVersion,
|
|
installPolicy: options.installPolicy,
|
|
io: options.io,
|
|
feature: 'core',
|
|
});
|
|
const daemon = await startDaemon({
|
|
cliVersion: options.cliVersion,
|
|
projectDir: options.projectDir,
|
|
features: ['core'],
|
|
force: false,
|
|
});
|
|
const verb = daemon.status === 'started' ? 'Started' : 'Using existing';
|
|
options.io.stderr.write(`${verb} KTX daemon: ${daemon.baseUrl}\n`);
|
|
cachedBaseUrl = daemon.baseUrl;
|
|
return cachedBaseUrl;
|
|
};
|
|
}
|
|
|
|
function isRequestJsonOnly(options: ManagedPythonDaemonHttpOptions): options is { requestJson: ManagedPythonHttpJsonRunner } {
|
|
return 'requestJson' in options;
|
|
}
|
|
|
|
function isResolveBaseUrlOnly(
|
|
options: ManagedPythonDaemonHttpOptions,
|
|
): options is { resolveBaseUrl: () => Promise<string>; postJson?: ManagedPythonHttpPostJson } {
|
|
return 'resolveBaseUrl' in options;
|
|
}
|
|
|
|
/** @internal */
|
|
export function createManagedDaemonHttpJsonRunner(
|
|
options: ManagedPythonDaemonHttpOptions,
|
|
): ManagedPythonHttpJsonRunner {
|
|
if (isRequestJsonOnly(options)) {
|
|
return options.requestJson;
|
|
}
|
|
const resolveBaseUrl = isResolveBaseUrlOnly(options)
|
|
? options.resolveBaseUrl
|
|
: createManagedPythonDaemonBaseUrlResolver(options);
|
|
const postJson = options.postJson ?? postManagedDaemonJson;
|
|
|
|
return async (path, payload) => postJson(await resolveBaseUrl(), path, payload);
|
|
}
|
|
|
|
export function createManagedDaemonLookerTableIdentifierParser(
|
|
options: ManagedPythonDaemonHttpOptions,
|
|
): LookerTableIdentifierParser {
|
|
return createDaemonLookerTableIdentifierParser({
|
|
baseUrl: 'http://127.0.0.1:0',
|
|
requestJson: createManagedDaemonHttpJsonRunner(options) as KtxDaemonTableIdentifierHttpJsonRunner,
|
|
});
|
|
}
|
|
|
|
export function createManagedDaemonSqlAnalysisPort(options: ManagedPythonDaemonHttpOptions): SqlAnalysisPort {
|
|
return createHttpSqlAnalysisPort({
|
|
baseUrl: 'http://127.0.0.1:0',
|
|
requestJson: createManagedDaemonHttpJsonRunner(options) as KtxSqlAnalysisHttpJsonRunner,
|
|
});
|
|
}
|
|
|
|
export function managedDaemonDatabaseIntrospectionOptions(
|
|
options: ManagedPythonDaemonHttpOptions,
|
|
): Pick<DaemonLiveDatabaseIntrospectionOptions, 'requestJson'> {
|
|
return {
|
|
requestJson: createManagedDaemonHttpJsonRunner(options) as KtxDaemonDatabaseHttpJsonRunner,
|
|
};
|
|
}
|