ktx/packages/cli/src/context/scan/local-structural-artifacts.ts

126 lines
4.5 KiB
TypeScript
Raw Normal View History

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.
2026-05-21 15:28:58 +02:00
import type { KtxLocalProject } from '../../context/project/project.js';
2026-05-10 23:12:26 +02:00
import type {
2026-05-10 23:51:24 +02:00
KtxConnectionDriver,
KtxSchemaColumn,
KtxSchemaForeignKey,
KtxSchemaSnapshot,
KtxSchemaTable,
2026-05-10 23:12:26 +02:00
} from './types.js';
export interface ReadLocalScanStructuralSnapshotInput {
2026-05-10 23:51:24 +02:00
project: KtxLocalProject;
2026-05-10 23:12:26 +02:00
connectionId: string;
2026-05-10 23:51:24 +02:00
driver: KtxConnectionDriver;
2026-05-10 23:12:26 +02:00
rawSourcesDir: string;
extractedAtFallback: string;
}
interface LiveDatabaseConnectionArtifact {
connectionId?: unknown;
extractedAt?: unknown;
metadata?: unknown;
scope?: unknown;
}
function isRecord(value: unknown): value is Record<string, unknown> {
return typeof value === 'object' && value !== null && !Array.isArray(value);
}
function metadataRecord(value: unknown): Record<string, unknown> {
return isRecord(value) ? value : {};
}
function optionalStringOrNull(value: unknown): string | null | undefined {
if (value === undefined) {
return undefined;
}
return typeof value === 'string' ? value : null;
}
2026-05-10 23:51:24 +02:00
function parseColumn(rawColumn: unknown, path: string): KtxSchemaColumn {
2026-05-10 23:12:26 +02:00
if (
!isRecord(rawColumn) ||
typeof rawColumn.name !== 'string' ||
typeof rawColumn.nativeType !== 'string' ||
typeof rawColumn.normalizedType !== 'string' ||
(rawColumn.dimensionType !== 'time' &&
rawColumn.dimensionType !== 'string' &&
rawColumn.dimensionType !== 'number' &&
rawColumn.dimensionType !== 'boolean')
) {
2026-05-10 23:51:24 +02:00
throw new Error(`Invalid KTX schema column artifact: ${path}`);
2026-05-10 23:12:26 +02:00
}
return {
name: rawColumn.name,
nativeType: rawColumn.nativeType,
normalizedType: rawColumn.normalizedType,
dimensionType: rawColumn.dimensionType,
nullable: rawColumn.nullable === true,
primaryKey: rawColumn.primaryKey === true,
comment: optionalStringOrNull(rawColumn.comment) ?? null,
};
}
2026-05-10 23:51:24 +02:00
function parseForeignKey(rawForeignKey: unknown, path: string): KtxSchemaForeignKey {
2026-05-10 23:12:26 +02:00
if (
!isRecord(rawForeignKey) ||
typeof rawForeignKey.fromColumn !== 'string' ||
typeof rawForeignKey.toTable !== 'string' ||
typeof rawForeignKey.toColumn !== 'string'
) {
2026-05-10 23:51:24 +02:00
throw new Error(`Invalid KTX schema foreign key artifact: ${path}`);
2026-05-10 23:12:26 +02:00
}
return {
fromColumn: rawForeignKey.fromColumn,
toCatalog: optionalStringOrNull(rawForeignKey.toCatalog) ?? null,
toDb: optionalStringOrNull(rawForeignKey.toDb) ?? null,
toTable: rawForeignKey.toTable,
toColumn: rawForeignKey.toColumn,
constraintName: optionalStringOrNull(rawForeignKey.constraintName) ?? null,
};
}
2026-05-10 23:51:24 +02:00
function parseTable(raw: string, path: string): KtxSchemaTable {
2026-05-10 23:12:26 +02:00
const parsed = JSON.parse(raw) as unknown;
if (!isRecord(parsed) || typeof parsed.name !== 'string' || !Array.isArray(parsed.columns)) {
2026-05-10 23:51:24 +02:00
throw new Error(`Invalid KTX schema table artifact: ${path}`);
2026-05-10 23:12:26 +02:00
}
return {
catalog: optionalStringOrNull(parsed.catalog) ?? null,
db: optionalStringOrNull(parsed.db) ?? null,
name: parsed.name,
kind:
parsed.kind === 'view' || parsed.kind === 'external' || parsed.kind === 'event_stream' ? parsed.kind : 'table',
comment: optionalStringOrNull(parsed.comment) ?? null,
estimatedRows: typeof parsed.estimatedRows === 'number' ? parsed.estimatedRows : null,
columns: parsed.columns.map((column) => parseColumn(column, path)),
foreignKeys: Array.isArray(parsed.foreignKeys)
? parsed.foreignKeys.map((foreignKey) => parseForeignKey(foreignKey, path))
: [],
};
}
export async function readLocalScanStructuralSnapshot(
input: ReadLocalScanStructuralSnapshotInput,
2026-05-10 23:51:24 +02:00
): Promise<KtxSchemaSnapshot> {
2026-05-10 23:12:26 +02:00
const connectionRaw = await input.project.fileStore.readFile(`${input.rawSourcesDir}/connection.json`);
const connection = JSON.parse(connectionRaw.content) as LiveDatabaseConnectionArtifact;
const listedTables = await input.project.fileStore.listFiles(`${input.rawSourcesDir}/tables`);
const tablePaths = listedTables.files.filter((path) => path.endsWith('.json')).sort();
2026-05-10 23:51:24 +02:00
const tables: KtxSchemaTable[] = [];
2026-05-10 23:12:26 +02:00
for (const path of tablePaths) {
const tableRaw = await input.project.fileStore.readFile(path);
tables.push(parseTable(tableRaw.content, path));
}
return {
connectionId: typeof connection.connectionId === 'string' ? connection.connectionId : input.connectionId,
driver: input.driver,
extractedAt: typeof connection.extractedAt === 'string' ? connection.extractedAt : input.extractedAtFallback,
scope: isRecord(connection.scope) ? connection.scope : {},
metadata: metadataRecord(connection.metadata),
tables,
};
}