mirror of
https://github.com/Kaelio/ktx.git
synced 2026-07-16 11:31:02 +02:00
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.
This commit is contained in:
Andrey Avtomonov
GitHub
parent
a1cfb03d73
commit
2366b00301
1002 changed files with 2286 additions and 12051 deletions
196
packages/cli/src/context/index-sync/reindex.test.ts
Normal file
196
packages/cli/src/context/index-sync/reindex.test.ts
Normal file
|
|
@ -0,0 +1,196 @@
|
|||
import { mkdir, mkdtemp, rm, writeFile } from 'node:fs/promises';
|
||||
import { tmpdir } from 'node:os';
|
||||
import { join } from 'node:path';
|
||||
import { afterEach, beforeEach, describe, expect, it } from 'vitest';
|
||||
import type { KtxEmbeddingPort } from '../../context/core/embedding.js';
|
||||
import { initKtxProject, loadKtxProject, type KtxLocalProject } from '../../context/project/project.js';
|
||||
import { SqliteKnowledgeIndex } from '../wiki/sqlite-knowledge-index.js';
|
||||
import { reindexLocalIndexes } from './reindex.js';
|
||||
|
||||
class FakeEmbeddingPort implements KtxEmbeddingPort {
|
||||
readonly maxBatchSize = 8;
|
||||
|
||||
async computeEmbedding(text: string): Promise<number[]> {
|
||||
return [text.length, 1];
|
||||
}
|
||||
|
||||
async computeEmbeddingsBulk(texts: string[]): Promise<number[][]> {
|
||||
return texts.map((text) => [text.length, 1]);
|
||||
}
|
||||
}
|
||||
|
||||
async function createProject(tempDir: string): Promise<KtxLocalProject> {
|
||||
await initKtxProject({ projectDir: tempDir, force: true });
|
||||
return loadKtxProject({ projectDir: tempDir });
|
||||
}
|
||||
|
||||
describe('reindexLocalIndexes', () => {
|
||||
let tempDir: string;
|
||||
|
||||
beforeEach(async () => {
|
||||
tempDir = await mkdtemp(join(tmpdir(), 'ktx-reindex-'));
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rm(tempDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
it('returns an empty summary when no wiki or semantic-layer directories exist', async () => {
|
||||
const project = await createProject(tempDir);
|
||||
await rm(join(project.projectDir, 'wiki'), { recursive: true, force: true });
|
||||
await rm(join(project.projectDir, 'semantic-layer'), { recursive: true, force: true });
|
||||
|
||||
await expect(reindexLocalIndexes(project, { force: false, embeddingService: null })).resolves.toMatchObject({
|
||||
scopes: [],
|
||||
totals: { scanned: 0, updated: 0, deleted: 0, embeddingsRecomputed: 0, embeddingsFailed: 0 },
|
||||
force: false,
|
||||
embeddingsAvailable: false,
|
||||
});
|
||||
});
|
||||
|
||||
it('discovers empty directories as zero-row scopes', async () => {
|
||||
const project = await createProject(tempDir);
|
||||
await mkdir(join(project.projectDir, 'wiki/user/local'), { recursive: true });
|
||||
await mkdir(join(project.projectDir, 'semantic-layer/warehouse'), { recursive: true });
|
||||
|
||||
const summary = await reindexLocalIndexes(project, { force: false, embeddingService: null });
|
||||
|
||||
expect(summary.scopes.map((scope) => scope.label)).toEqual(['global', 'user/local', 'warehouse']);
|
||||
expect(summary.totals.scanned).toBe(0);
|
||||
});
|
||||
|
||||
it('indexes mixed wiki and SL sources and reports totals', async () => {
|
||||
const project = await createProject(tempDir);
|
||||
await writeFile(
|
||||
join(project.projectDir, 'wiki/global/revenue.md'),
|
||||
'---\nsummary: Revenue\nusage_mode: auto\n---\n\nPaid orders.\n',
|
||||
'utf-8',
|
||||
);
|
||||
await mkdir(join(project.projectDir, 'semantic-layer/warehouse'), { recursive: true });
|
||||
await writeFile(
|
||||
join(project.projectDir, 'semantic-layer/warehouse/orders.yaml'),
|
||||
'name: orders\ntable: public.orders\ngrain: [id]\ncolumns:\n - name: id\n type: number\njoins: []\nmeasures: []\n',
|
||||
'utf-8',
|
||||
);
|
||||
|
||||
const summary = await reindexLocalIndexes(project, {
|
||||
force: false,
|
||||
embeddingService: new FakeEmbeddingPort(),
|
||||
});
|
||||
|
||||
expect(summary.scopes).toHaveLength(2);
|
||||
expect(summary.totals).toMatchObject({ scanned: 2, updated: 2, deleted: 0, embeddingsRecomputed: 2 });
|
||||
expect(summary.embeddingsAvailable).toBe(true);
|
||||
});
|
||||
|
||||
it('does not report unchanged lexical-only rows as updated on repeated runs', async () => {
|
||||
const project = await createProject(tempDir);
|
||||
await writeFile(
|
||||
join(project.projectDir, 'wiki/global/revenue.md'),
|
||||
'---\nsummary: Revenue\nusage_mode: auto\n---\n\nPaid orders.\n',
|
||||
'utf-8',
|
||||
);
|
||||
await mkdir(join(project.projectDir, 'semantic-layer/warehouse'), { recursive: true });
|
||||
await writeFile(
|
||||
join(project.projectDir, 'semantic-layer/warehouse/orders.yaml'),
|
||||
'name: orders\ntable: public.orders\ngrain: [id]\ncolumns:\n - name: id\n type: number\njoins: []\nmeasures: []\n',
|
||||
'utf-8',
|
||||
);
|
||||
|
||||
const first = await reindexLocalIndexes(project, { force: false, embeddingService: null });
|
||||
expect(first.totals).toMatchObject({
|
||||
scanned: 2,
|
||||
updated: 2,
|
||||
deleted: 0,
|
||||
embeddingsRecomputed: 0,
|
||||
embeddingsFailed: 0,
|
||||
});
|
||||
|
||||
const second = await reindexLocalIndexes(project, { force: false, embeddingService: null });
|
||||
|
||||
expect(second.totals).toMatchObject({
|
||||
scanned: 2,
|
||||
updated: 0,
|
||||
deleted: 0,
|
||||
embeddingsRecomputed: 0,
|
||||
embeddingsFailed: 0,
|
||||
});
|
||||
expect(second.scopes.map((scope) => [scope.label, scope.updated])).toEqual([
|
||||
['global', 0],
|
||||
['warehouse', 0],
|
||||
]);
|
||||
});
|
||||
|
||||
it('force clears stale rows before rebuilding each discovered scope', async () => {
|
||||
const project = await createProject(tempDir);
|
||||
const wikiIndex = new SqliteKnowledgeIndex({ dbPath: join(project.projectDir, '.ktx/db.sqlite') });
|
||||
wikiIndex.sync([
|
||||
{
|
||||
path: 'wiki/global/stale.md',
|
||||
key: 'stale',
|
||||
scope: 'GLOBAL',
|
||||
scopeId: null,
|
||||
summary: 'Stale',
|
||||
content: 'Stale content',
|
||||
tags: [],
|
||||
embedding: [1, 0],
|
||||
},
|
||||
]);
|
||||
await writeFile(
|
||||
join(project.projectDir, 'wiki/global/revenue.md'),
|
||||
'---\nsummary: Revenue\nusage_mode: auto\n---\n\nPaid orders.\n',
|
||||
'utf-8',
|
||||
);
|
||||
|
||||
const summary = await reindexLocalIndexes(project, {
|
||||
force: true,
|
||||
embeddingService: new FakeEmbeddingPort(),
|
||||
});
|
||||
|
||||
expect(summary.force).toBe(true);
|
||||
expect(summary.totals).toMatchObject({ scanned: 1, updated: 1, deleted: 0 });
|
||||
expect(wikiIndex.search('Stale', 10)).toEqual([]);
|
||||
});
|
||||
|
||||
it('captures a per-scope error and continues other scopes', async () => {
|
||||
const project = await createProject(tempDir);
|
||||
await writeFile(
|
||||
join(project.projectDir, 'wiki/global/revenue.md'),
|
||||
'---\nsummary: Revenue\nusage_mode: auto\n---\n\nPaid orders.\n',
|
||||
'utf-8',
|
||||
);
|
||||
await mkdir(join(project.projectDir, 'semantic-layer/warehouse'), { recursive: true });
|
||||
await writeFile(join(project.projectDir, 'semantic-layer/warehouse/broken.yaml'), 'not: [valid', 'utf-8');
|
||||
|
||||
const summary = await reindexLocalIndexes(project, { force: false, embeddingService: null });
|
||||
|
||||
expect(summary.scopes.find((scope) => scope.label === 'global')?.error).toBeUndefined();
|
||||
expect(summary.scopes.find((scope) => scope.label === 'warehouse')?.error).toContain('YAML');
|
||||
});
|
||||
|
||||
it('marks a scope errored when configured embeddings fail', async () => {
|
||||
const project = await createProject(tempDir);
|
||||
await writeFile(
|
||||
join(project.projectDir, 'wiki/global/revenue.md'),
|
||||
'---\nsummary: Revenue\nusage_mode: auto\n---\n\nPaid orders.\n',
|
||||
'utf-8',
|
||||
);
|
||||
const embeddingService: KtxEmbeddingPort = {
|
||||
maxBatchSize: 8,
|
||||
async computeEmbedding() {
|
||||
throw new Error('embedding provider unavailable');
|
||||
},
|
||||
async computeEmbeddingsBulk() {
|
||||
throw new Error('embedding provider unavailable');
|
||||
},
|
||||
};
|
||||
|
||||
const summary = await reindexLocalIndexes(project, { force: false, embeddingService });
|
||||
|
||||
expect(summary.scopes[0]).toMatchObject({
|
||||
label: 'global',
|
||||
embeddingsFailed: 1,
|
||||
error: '1 embedding recomputation failed',
|
||||
});
|
||||
});
|
||||
});
|
||||
Loading…
Add table
Add a link
Reference in a new issue