mirror of
https://github.com/Kaelio/ktx.git
synced 2026-07-04 10:52:13 +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.
151 lines
5.2 KiB
TypeScript
151 lines
5.2 KiB
TypeScript
import type { SearchBackendCapabilities, SearchLaneStatus } from './types.js';
|
|
|
|
export interface SearchBackendConformanceLane {
|
|
lane: string;
|
|
status: SearchLaneStatus;
|
|
reason?: string;
|
|
}
|
|
|
|
export interface SearchBackendConformanceDictionaryMatch {
|
|
column: string;
|
|
values: readonly string[];
|
|
overflowCount?: number;
|
|
}
|
|
|
|
export interface SearchBackendConformanceResult {
|
|
id: string;
|
|
score: number;
|
|
matchReasons: readonly string[];
|
|
lanes?: readonly SearchBackendConformanceLane[];
|
|
dictionaryMatches?: readonly SearchBackendConformanceDictionaryMatch[];
|
|
}
|
|
|
|
export interface ExpectedSearchBackendConformanceLane {
|
|
status: SearchLaneStatus;
|
|
reason?: string;
|
|
}
|
|
|
|
export interface AssertSearchBackendConformanceCaseInput {
|
|
backendName: string;
|
|
surface: string;
|
|
caseName: string;
|
|
results: readonly SearchBackendConformanceResult[];
|
|
expectedTopIds: readonly string[];
|
|
expectedReasonsById?: Record<string, readonly string[]>;
|
|
expectedLanes?: Record<string, ExpectedSearchBackendConformanceLane>;
|
|
expectedDictionaryMatchesById?: Record<string, readonly SearchBackendConformanceDictionaryMatch[]>;
|
|
}
|
|
|
|
export interface AssertSearchBackendCapabilitiesInput {
|
|
backendName: string;
|
|
capabilities: SearchBackendCapabilities;
|
|
expected: Partial<SearchBackendCapabilities>;
|
|
}
|
|
|
|
function caseLabel(
|
|
input: Pick<AssertSearchBackendConformanceCaseInput, 'backendName' | 'surface' | 'caseName'>,
|
|
): string {
|
|
return `${input.backendName} ${input.surface} conformance case "${input.caseName}"`;
|
|
}
|
|
|
|
function fail(label: string, failures: string[]): never {
|
|
throw new Error([`${label} failed:`, ...failures.map((failure) => `- ${failure}`)].join('\n'));
|
|
}
|
|
|
|
function dictionaryMatchKey(match: SearchBackendConformanceDictionaryMatch): string {
|
|
const values = [...match.values].sort((left, right) => left.localeCompare(right)).join(',');
|
|
return `${match.column}:${values}:${match.overflowCount ?? 0}`;
|
|
}
|
|
|
|
function dictionaryMatchKeys(matches: readonly SearchBackendConformanceDictionaryMatch[] | undefined): string[] {
|
|
return (matches ?? []).map(dictionaryMatchKey).sort((left, right) => left.localeCompare(right));
|
|
}
|
|
|
|
export function assertSearchBackendConformanceCase(input: AssertSearchBackendConformanceCaseInput): void {
|
|
const label = caseLabel(input);
|
|
const failures: string[] = [];
|
|
const topResults = input.results.slice(0, input.expectedTopIds.length);
|
|
|
|
input.expectedTopIds.forEach((expectedId, index) => {
|
|
const actualId = topResults[index]?.id;
|
|
if (actualId !== expectedId) {
|
|
failures.push(`expected result ${index + 1} to be ${expectedId}, got ${actualId ?? '<missing>'}`);
|
|
}
|
|
});
|
|
|
|
const byId = new Map(input.results.map((result) => [result.id, result]));
|
|
|
|
for (const expectedId of input.expectedTopIds) {
|
|
const result = byId.get(expectedId);
|
|
if (!result) {
|
|
continue;
|
|
}
|
|
if (!Number.isFinite(result.score) || result.score <= 0) {
|
|
failures.push(`expected ${expectedId} to have a positive finite score, got ${result.score}`);
|
|
}
|
|
}
|
|
|
|
for (const [id, expectedReasons] of Object.entries(input.expectedReasonsById ?? {})) {
|
|
const result = byId.get(id);
|
|
if (!result) {
|
|
failures.push(`expected reasons for ${id}, but the result was missing`);
|
|
continue;
|
|
}
|
|
for (const reason of expectedReasons) {
|
|
if (!result.matchReasons.includes(reason)) {
|
|
failures.push(`expected ${id} to include match reason ${reason}, got [${result.matchReasons.join(', ')}]`);
|
|
}
|
|
}
|
|
}
|
|
|
|
const allLanes = input.results.flatMap((result) => result.lanes ?? []);
|
|
for (const [lane, expected] of Object.entries(input.expectedLanes ?? {})) {
|
|
const actual = allLanes.find((entry) => entry.lane === lane);
|
|
if (!actual) {
|
|
failures.push(`expected lane ${lane} to be reported`);
|
|
continue;
|
|
}
|
|
if (actual.status !== expected.status) {
|
|
failures.push(`expected lane ${lane} status ${expected.status}, got ${actual.status}`);
|
|
}
|
|
if (expected.reason !== undefined && actual.reason !== expected.reason) {
|
|
failures.push(`expected lane ${lane} reason ${expected.reason}, got ${actual.reason ?? '<missing>'}`);
|
|
}
|
|
}
|
|
|
|
for (const [id, expectedMatches] of Object.entries(input.expectedDictionaryMatchesById ?? {})) {
|
|
const result = byId.get(id);
|
|
if (!result) {
|
|
failures.push(`expected dictionary matches for ${id}, but the result was missing`);
|
|
continue;
|
|
}
|
|
|
|
const actualKeys = dictionaryMatchKeys(result.dictionaryMatches);
|
|
for (const expectedKey of dictionaryMatchKeys(expectedMatches)) {
|
|
if (!actualKeys.includes(expectedKey)) {
|
|
failures.push(`expected ${id} dictionary evidence ${expectedKey}, got [${actualKeys.join(', ')}]`);
|
|
}
|
|
}
|
|
}
|
|
|
|
if (failures.length > 0) {
|
|
fail(label, failures);
|
|
}
|
|
}
|
|
|
|
export function assertSearchBackendCapabilities(input: AssertSearchBackendCapabilitiesInput): void {
|
|
const failures: string[] = [];
|
|
|
|
for (const [capability, expected] of Object.entries(input.expected) as Array<
|
|
[keyof SearchBackendCapabilities, boolean]
|
|
>) {
|
|
const actual = input.capabilities[capability];
|
|
if (actual !== expected) {
|
|
failures.push(`expected ${capability}=${expected}, got ${actual}`);
|
|
}
|
|
}
|
|
|
|
if (failures.length > 0) {
|
|
fail(`${input.backendName} search backend capabilities`, failures);
|
|
}
|
|
}
|