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.
190 lines
7.3 KiB
TypeScript
190 lines
7.3 KiB
TypeScript
import { KtxIngestEmbeddingPortAdapter } from './context/llm/embedding-port.js';
|
|
import type { KtxEmbeddingPort } from './context/core/embedding.js';
|
|
import { reindexLocalIndexes } from './context/index-sync/reindex.js';
|
|
import type { ReindexScopeResult, ReindexSummary } from './context/index-sync/types.js';
|
|
import { loadKtxProject } from './context/project/project.js';
|
|
import { Option, type Command } from '@commander-js/extra-typings';
|
|
import { cancel, intro, log, note, outro } from '@clack/prompts';
|
|
import type { KtxCliCommandContext } from './cli-program.js';
|
|
import type { KtxCliIo } from './cli-runtime.js';
|
|
import { resolveProjectEmbeddingProvider } from './embedding-resolution.js';
|
|
import { resolveOutputMode } from './io/mode.js';
|
|
import { green, red, SYMBOLS } from './io/symbols.js';
|
|
|
|
export interface KtxAdminReindexArgs {
|
|
projectDir: string;
|
|
force: boolean;
|
|
output?: 'pretty' | 'plain' | 'json';
|
|
json?: boolean;
|
|
cliVersion: string;
|
|
}
|
|
|
|
export function registerAdminReindexCommand(admin: Command, context: KtxCliCommandContext): void {
|
|
admin
|
|
.command('reindex')
|
|
.description('Sync local wiki and semantic-layer search indexes from disk')
|
|
.option('--force', 'Clear each discovered scope before rebuilding it', false)
|
|
.option('--json', 'Shortcut for --output=json (overrides --output)', false)
|
|
.addOption(
|
|
new Option('--output <mode>', 'Output mode: pretty, plain, or json').choices(['pretty', 'plain', 'json']),
|
|
)
|
|
.action(async (options: { force?: boolean; json?: boolean; output?: 'pretty' | 'plain' | 'json' }, command) => {
|
|
const runner = context.deps.adminReindex ?? runKtxAdminReindex;
|
|
const { resolveCommandProjectDir } = await import('./cli-program.js');
|
|
context.setExitCode(
|
|
await runner(
|
|
{
|
|
projectDir: resolveCommandProjectDir(command),
|
|
force: options.force === true,
|
|
json: options.json === true,
|
|
output: options.output,
|
|
cliVersion: context.packageInfo.version,
|
|
},
|
|
context.io,
|
|
),
|
|
);
|
|
});
|
|
}
|
|
|
|
function scopeKey(scope: ReindexScopeResult): string {
|
|
if (scope.kind === 'wiki') {
|
|
return scope.scope === 'user' ? `wiki/user/${scope.scopeId ?? 'local'}` : 'wiki/global';
|
|
}
|
|
return `sl/${scope.connectionId ?? scope.label}`;
|
|
}
|
|
|
|
function quotePlainValue(value: string): string {
|
|
return `"${value.replaceAll('\\', '\\\\').replaceAll('"', '\\"')}"`;
|
|
}
|
|
|
|
/** @internal */
|
|
export function reindexHasErrors(summary: ReindexSummary): boolean {
|
|
return summary.scopes.some((scope) => scope.error);
|
|
}
|
|
|
|
/** @internal */
|
|
export function renderReindexPlain(summary: ReindexSummary, io: KtxCliIo): void {
|
|
const updateKey = summary.force ? 'rebuilt' : 'updated';
|
|
for (const scope of summary.scopes) {
|
|
const cells = [
|
|
scopeKey(scope),
|
|
`scanned=${scope.scanned}`,
|
|
`${updateKey}=${scope.updated}`,
|
|
`deleted=${scope.deleted}`,
|
|
`embeddings=${summary.embeddingsAvailable ? String(scope.embeddingsRecomputed) : '-'}`,
|
|
`duration_ms=${scope.durationMs}`,
|
|
...(scope.error ? [`error=${quotePlainValue(scope.error)}`] : []),
|
|
];
|
|
io.stderr.write(`${cells.join('\t')}\n`);
|
|
}
|
|
const failed = summary.scopes.filter((scope) => scope.error).length;
|
|
io.stdout.write(
|
|
[
|
|
'reindex',
|
|
`scopes=${summary.scopes.length}`,
|
|
`scanned=${summary.totals.scanned}`,
|
|
`${updateKey}=${summary.totals.updated}`,
|
|
`deleted=${summary.totals.deleted}`,
|
|
`embeddings=${summary.embeddingsAvailable ? String(summary.totals.embeddingsRecomputed) : '-'}`,
|
|
`duration_ms=${summary.durationMs}`,
|
|
...(failed > 0 ? [`failed=${failed}`] : []),
|
|
].join('\t') + '\n',
|
|
);
|
|
}
|
|
|
|
/** @internal */
|
|
export function renderReindexJson(summary: ReindexSummary, io: KtxCliIo): void {
|
|
io.stdout.write(`${JSON.stringify({ kind: 'reindex', data: summary, meta: { command: 'admin reindex' } }, null, 2)}\n`);
|
|
}
|
|
|
|
function noun(scope: ReindexScopeResult): string {
|
|
return scope.kind === 'wiki' ? 'pages' : 'sources';
|
|
}
|
|
|
|
function formatScopeLine(scope: ReindexScopeResult, force: boolean, embeddingsAvailable: boolean): string {
|
|
if (scope.error) {
|
|
return `${scope.kind === 'wiki' ? 'Wiki' : 'SL'}: ${scope.label} ${SYMBOLS.emDash} failed: ${scope.error}`;
|
|
}
|
|
const changedLabel = force ? 'rebuilt' : 'updated';
|
|
const parts = [`${scope.scanned} ${noun(scope)}`];
|
|
if (scope.updated > 0) {
|
|
parts.push(`${scope.updated} ${changedLabel}`);
|
|
} else {
|
|
parts.push('unchanged');
|
|
}
|
|
if (!force && scope.deleted > 0) {
|
|
parts.push(`${scope.deleted} deleted`);
|
|
}
|
|
if (embeddingsAvailable) {
|
|
parts.push(`${scope.embeddingsRecomputed} embeddings recomputed`);
|
|
}
|
|
parts.push(`${scope.durationMs}ms`);
|
|
return `${scope.kind === 'wiki' ? 'Wiki' : 'SL'}: ${scope.label} ${SYMBOLS.emDash} ${parts.join(` ${SYMBOLS.middot} `)}`;
|
|
}
|
|
|
|
function renderReindexPretty(summary: ReindexSummary, io: KtxCliIo): void {
|
|
intro(summary.force ? 'ktx admin reindex --force' : 'ktx admin reindex');
|
|
if (!summary.embeddingsAvailable) {
|
|
log.warn(`Embeddings: not configured ${SYMBOLS.emDash} indexing lexical only`);
|
|
}
|
|
for (const scope of summary.scopes) {
|
|
const line = formatScopeLine(scope, summary.force, summary.embeddingsAvailable);
|
|
if (scope.error) {
|
|
log.error(red(line));
|
|
} else {
|
|
log.success(green(line));
|
|
}
|
|
}
|
|
const failed = summary.scopes.filter((scope) => scope.error).length;
|
|
note(
|
|
[
|
|
`scopes ${summary.scopes.length}`,
|
|
`scanned ${summary.totals.scanned}`,
|
|
`${summary.force ? 'rebuilt' : 'updated'} ${summary.totals.updated}`,
|
|
`deleted ${summary.totals.deleted}`,
|
|
`embeddings ${summary.embeddingsAvailable ? summary.totals.embeddingsRecomputed : SYMBOLS.emDash}`,
|
|
`index ${summary.dbPath}`,
|
|
...(failed > 0 ? [`failed ${failed}`] : []),
|
|
].join('\n'),
|
|
'Summary',
|
|
);
|
|
if (failed > 0) {
|
|
cancel(`reindex completed with ${failed} error${failed === 1 ? '' : 's'}`);
|
|
} else {
|
|
outro(`Done in ${(summary.durationMs / 1000).toFixed(1)}s`);
|
|
}
|
|
void io;
|
|
}
|
|
|
|
async function runKtxAdminReindex(args: KtxAdminReindexArgs, io: KtxCliIo = process): Promise<number> {
|
|
try {
|
|
const project = await loadKtxProject({ projectDir: args.projectDir });
|
|
const resolution = await resolveProjectEmbeddingProvider(project, {
|
|
mode: 'use-if-running',
|
|
cliVersion: args.cliVersion,
|
|
io,
|
|
});
|
|
const embeddingService: KtxEmbeddingPort | null =
|
|
resolution.kind === 'configured' || resolution.kind === 'managed-running' || resolution.kind === 'managed-started'
|
|
? new KtxIngestEmbeddingPortAdapter(resolution.provider)
|
|
: null;
|
|
const summary = await reindexLocalIndexes(project, { force: args.force, embeddingService });
|
|
const mode = resolveOutputMode({ explicit: args.output, json: args.json, io });
|
|
|
|
if (!summary.embeddingsAvailable && mode === 'plain') {
|
|
io.stderr.write(`Embeddings: not configured ${SYMBOLS.emDash} indexing lexical only\n`);
|
|
}
|
|
|
|
if (mode === 'json') {
|
|
renderReindexJson(summary, io);
|
|
} else if (mode === 'plain') {
|
|
renderReindexPlain(summary, io);
|
|
} else {
|
|
renderReindexPretty(summary, io);
|
|
}
|
|
return reindexHasErrors(summary) ? 1 : 0;
|
|
} catch (error) {
|
|
io.stderr.write(`${error instanceof Error ? error.message : String(error)}\n`);
|
|
return 1;
|
|
}
|
|
}
|