mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-10 08:05:14 +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.
186 lines
5.8 KiB
TypeScript
186 lines
5.8 KiB
TypeScript
import { constants as fsConstants } from 'node:fs';
|
|
import { access, copyFile, cp, mkdir, rm, writeFile } from 'node:fs/promises';
|
|
import { tmpdir } from 'node:os';
|
|
import { join, resolve } from 'node:path';
|
|
import { fileURLToPath } from 'node:url';
|
|
import { randomBytes } from 'node:crypto';
|
|
|
|
interface DemoProjectResult {
|
|
projectDir: string;
|
|
configPath: string;
|
|
databasePath: string;
|
|
replayPath: string;
|
|
}
|
|
|
|
interface EnsureDemoProjectOptions {
|
|
projectDir: string;
|
|
force: boolean;
|
|
}
|
|
|
|
/** @internal */
|
|
export const DEMO_CONNECTION_ID = 'orbit_demo';
|
|
/** @internal */
|
|
export const DEMO_ADAPTER = 'live-database';
|
|
/** @internal */
|
|
export const DEMO_REPLAY_FILE = 'replay.memory-flow.v1.json';
|
|
|
|
const REQUIRED_PACKAGED_BASE_ASSET_PATHS = ['demo.db', 'manifest.json', DEMO_REPLAY_FILE] as const;
|
|
|
|
const REQUIRED_SEEDED_ASSET_PATHS = [
|
|
'demo.db',
|
|
'manifest.json',
|
|
DEMO_REPLAY_FILE,
|
|
join('semantic-layer', 'dbt-main', 'mart_arr_daily.yaml'),
|
|
join('semantic-layer', 'postgres-warehouse', 'mart_account_activity.yaml'),
|
|
join('wiki', 'global', 'orbit-company-overview.md'),
|
|
] as const;
|
|
|
|
function assetDir(): string {
|
|
return fileURLToPath(new URL('../assets/demo/orbit/', import.meta.url));
|
|
}
|
|
|
|
async function exists(path: string): Promise<boolean> {
|
|
try {
|
|
await access(path, fsConstants.F_OK);
|
|
return true;
|
|
} catch {
|
|
return false;
|
|
}
|
|
}
|
|
|
|
export function defaultDemoProjectDir(): string {
|
|
const suffix = randomBytes(4).toString('hex');
|
|
return join(tmpdir(), `ktx-demo-${suffix}`);
|
|
}
|
|
|
|
function demoConfig(databasePath: string): string {
|
|
return [
|
|
'connections:',
|
|
` ${DEMO_CONNECTION_ID}:`,
|
|
' driver: sqlite',
|
|
` path: ${JSON.stringify(databasePath)}`,
|
|
'storage:',
|
|
' state: sqlite',
|
|
' search: sqlite-fts5',
|
|
' git:',
|
|
' auto_commit: true',
|
|
' author: ktx <ktx@example.com>',
|
|
'llm:',
|
|
' provider:',
|
|
' backend: anthropic',
|
|
' anthropic:',
|
|
' api_key: env:ANTHROPIC_API_KEY',
|
|
' models:',
|
|
' default: claude-sonnet-4-6',
|
|
'ingest:',
|
|
' adapters:',
|
|
` - ${DEMO_ADAPTER}`,
|
|
' embeddings:',
|
|
' backend: none',
|
|
' dimensions: 8',
|
|
' workUnits:',
|
|
' stepBudget: 40',
|
|
' maxConcurrency: 1',
|
|
' failureMode: continue',
|
|
'',
|
|
].join('\n');
|
|
}
|
|
|
|
async function copyPackagedReplay(projectDir: string): Promise<string> {
|
|
const replayDir = join(projectDir, 'replays');
|
|
await mkdir(replayDir, { recursive: true });
|
|
const replayPath = join(replayDir, DEMO_REPLAY_FILE);
|
|
await copyFile(join(assetDir(), DEMO_REPLAY_FILE), replayPath);
|
|
return replayPath;
|
|
}
|
|
|
|
async function assertPackagedBaseAssetsPresent(): Promise<void> {
|
|
const missing: string[] = [];
|
|
for (const relativePath of REQUIRED_PACKAGED_BASE_ASSET_PATHS) {
|
|
if (!(await exists(join(assetDir(), relativePath)))) {
|
|
missing.push(relativePath);
|
|
}
|
|
}
|
|
if (missing.length > 0) {
|
|
throw new Error(`Packaged demo assets are incomplete: missing ${missing.join(', ')}`);
|
|
}
|
|
}
|
|
|
|
async function assertPackagedSeededAssetsPresent(): Promise<void> {
|
|
const missing: string[] = [];
|
|
for (const relativePath of REQUIRED_SEEDED_ASSET_PATHS) {
|
|
if (!(await exists(join(assetDir(), relativePath)))) {
|
|
missing.push(relativePath);
|
|
}
|
|
}
|
|
if (missing.length > 0) {
|
|
throw new Error(`Packaged seeded demo assets are incomplete: missing ${missing.join(', ')}`);
|
|
}
|
|
}
|
|
|
|
/** @internal */
|
|
export async function ensureDemoProject(options: EnsureDemoProjectOptions): Promise<DemoProjectResult> {
|
|
const projectDir = resolve(options.projectDir);
|
|
const configPath = join(projectDir, 'ktx.yaml');
|
|
if (!options.force && (await exists(configPath))) {
|
|
throw new Error(`Demo project already exists at ${projectDir}; pass --force to recreate it`);
|
|
}
|
|
|
|
await assertPackagedBaseAssetsPresent();
|
|
|
|
if (options.force) {
|
|
await rm(projectDir, { recursive: true, force: true });
|
|
}
|
|
|
|
await mkdir(projectDir, { recursive: true });
|
|
for (const relativeDir of ['reports', 'semantic-layer', 'wiki', 'replays', 'raw-sources', 'links']) {
|
|
await mkdir(join(projectDir, relativeDir), { recursive: true });
|
|
}
|
|
|
|
const databasePath = join(projectDir, 'demo.db');
|
|
await copyFile(join(assetDir(), 'demo.db'), databasePath);
|
|
await writeFile(join(projectDir, 'state.sqlite'), '', { flag: 'a' });
|
|
await copyFile(join(assetDir(), 'manifest.json'), join(projectDir, 'manifest.json'));
|
|
const replayPath = await copyPackagedReplay(projectDir);
|
|
await writeFile(configPath, demoConfig(databasePath), 'utf-8');
|
|
|
|
return { projectDir, configPath, databasePath, replayPath };
|
|
}
|
|
|
|
async function copyDirIfExists(src: string, dest: string): Promise<void> {
|
|
if (await exists(src)) {
|
|
await cp(src, dest, { recursive: true });
|
|
}
|
|
}
|
|
|
|
async function copySeededAssetDirectories(projectDir: string): Promise<void> {
|
|
const src = assetDir();
|
|
const dest = resolve(projectDir);
|
|
|
|
await Promise.all([
|
|
copyDirIfExists(join(src, 'semantic-layer'), join(dest, 'semantic-layer')),
|
|
copyDirIfExists(join(src, 'wiki'), join(dest, 'wiki')),
|
|
copyDirIfExists(join(src, 'raw-sources'), join(dest, 'raw-sources')),
|
|
copyDirIfExists(join(src, 'links'), join(dest, 'links')),
|
|
copyDirIfExists(join(src, 'reports'), join(dest, 'reports')),
|
|
]);
|
|
}
|
|
|
|
export async function ensureSeededDemoProject(options: EnsureDemoProjectOptions): Promise<DemoProjectResult> {
|
|
await assertPackagedSeededAssetsPresent();
|
|
const projectDir = resolve(options.projectDir);
|
|
const result = await ensureDemoProject(options).catch((error) => {
|
|
if (!options.force && error instanceof Error && error.message.includes('Demo project already exists')) {
|
|
return {
|
|
projectDir,
|
|
configPath: join(projectDir, 'ktx.yaml'),
|
|
databasePath: join(projectDir, 'demo.db'),
|
|
replayPath: join(projectDir, 'replays', DEMO_REPLAY_FILE),
|
|
};
|
|
}
|
|
throw error;
|
|
});
|
|
|
|
await copySeededAssetDirectories(result.projectDir);
|
|
return result;
|
|
}
|