mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-28 08:49:38 +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.
341 lines
12 KiB
TypeScript
341 lines
12 KiB
TypeScript
import { z } from 'zod';
|
|
import { DEFAULT_PRIORITY, resolveDescription } from '../descriptions.js';
|
|
import type { SemanticLayerService } from '../semantic-layer.service.js';
|
|
import type { SemanticLayerSource } from '../types.js';
|
|
import type { ToolContext, ToolOutput } from '../../../context/tools/base-tool.js';
|
|
import { BaseSemanticLayerTool, type BaseSemanticLayerToolDeps } from './base-semantic-layer.tool.js';
|
|
import { slToolConnectionIdSchema } from './connection-id-schema.js';
|
|
|
|
export interface SlDiscoverySettings {
|
|
maxSources: number;
|
|
minRrfScore: number;
|
|
maxDetailedSources: number;
|
|
}
|
|
|
|
const slDiscoverInputSchema = z.object({
|
|
connectionId: slToolConnectionIdSchema
|
|
.optional()
|
|
.describe('Data source connection ID (omit to discover across all data sources)'),
|
|
query: z.string().optional().describe('Search query to filter sources/columns/measures by name or description'),
|
|
sourceName: z
|
|
.string()
|
|
.optional()
|
|
.describe('Inspect a specific source in full detail (requires connectionId if multiple data sources)'),
|
|
});
|
|
|
|
type SlDiscoverInput = z.infer<typeof slDiscoverInputSchema>;
|
|
|
|
interface SlDiscoverStructured {
|
|
sources: Array<{
|
|
connectionId: string;
|
|
connectionName: string;
|
|
name: string;
|
|
description?: string;
|
|
columnCount: number;
|
|
measureCount: number;
|
|
joinCount: number;
|
|
}>;
|
|
detail?: Record<string, unknown>;
|
|
totalSources: number;
|
|
}
|
|
|
|
export class SlDiscoverTool extends BaseSemanticLayerTool<typeof slDiscoverInputSchema> {
|
|
readonly name = 'sl_discover';
|
|
|
|
constructor(
|
|
deps: BaseSemanticLayerToolDeps,
|
|
private readonly discoverySettings: SlDiscoverySettings,
|
|
) {
|
|
super(deps);
|
|
}
|
|
|
|
get description(): string {
|
|
return `<purpose>
|
|
Discover available semantic layer sources, columns, measures, and joins.
|
|
When called without a connectionId, discovers sources across ALL data sources — grouped by data source name and ID.
|
|
Use this to understand what data is available before querying through the semantic layer.
|
|
</purpose>
|
|
|
|
<when_to_use>
|
|
- Before querying: understand available sources across all data sources
|
|
- To inspect a specific source in detail (columns, joins, measures, grain) — requires connectionId when multiple data sources exist
|
|
- To search for sources related to a concept (e.g., "revenue", "customers") across all data sources
|
|
</when_to_use>`;
|
|
}
|
|
|
|
get inputSchema() {
|
|
return slDiscoverInputSchema;
|
|
}
|
|
|
|
async call(input: SlDiscoverInput, context: ToolContext): Promise<ToolOutput<SlDiscoverStructured>> {
|
|
const { query, sourceName } = input;
|
|
const semanticLayerService = context.session?.semanticLayerService ?? this.semanticLayerService;
|
|
|
|
// Resolve connectionId: use provided value, or auto-detect
|
|
let connectionId = input.connectionId;
|
|
if (!connectionId) {
|
|
const connections = await semanticLayerService.listConnectionIdsWithNames();
|
|
if (connections.length === 0) {
|
|
return {
|
|
markdown: 'No semantic layer sources found. Run a schema scan first.',
|
|
structured: { sources: [], totalSources: 0 },
|
|
};
|
|
}
|
|
if (connections.length === 1) {
|
|
connectionId = connections[0].id;
|
|
} else {
|
|
// Multiple connections — aggregate or prompt depending on operation
|
|
if (sourceName) {
|
|
const connectionList = connections
|
|
.map((c) => `- **${c.name}** (${c.connectionType}): \`${c.id}\``)
|
|
.join('\n');
|
|
return {
|
|
markdown: `Multiple data sources have semantic layer sources. Specify a connectionId to inspect source "${sourceName}":\n\n${connectionList}`,
|
|
structured: { sources: [], totalSources: 0 },
|
|
};
|
|
}
|
|
return this.discoverAcrossConnections(semanticLayerService, connections, query);
|
|
}
|
|
}
|
|
|
|
// If inspecting a specific source — show the SL interface (columns, measures, joins)
|
|
// without the raw SQL. Use `sl_read_source` to see the full YAML including SQL.
|
|
if (sourceName) {
|
|
const { sources } = await semanticLayerService.loadAllSources(connectionId);
|
|
const source = sources.find((s) => s.name === sourceName);
|
|
if (!source) {
|
|
return {
|
|
markdown: `Source **${sourceName}** not found for this connection.`,
|
|
structured: { sources: [], totalSources: 0 },
|
|
};
|
|
}
|
|
|
|
const parts: string[] = [];
|
|
this.appendSourceDetail(parts, source);
|
|
|
|
if (source.grain?.length) {
|
|
parts.push(`Grain: ${source.grain.join(', ')}`);
|
|
}
|
|
|
|
return {
|
|
markdown: parts.join('\n'),
|
|
structured: {
|
|
sources: [
|
|
{
|
|
connectionId,
|
|
connectionName: connectionId,
|
|
name: source.name,
|
|
description:
|
|
resolveDescription(source.descriptions, { priority: DEFAULT_PRIORITY }) ?? undefined,
|
|
columnCount: source.columns.length,
|
|
measureCount: source.measures.length,
|
|
joinCount: source.joins.length,
|
|
},
|
|
],
|
|
totalSources: 1,
|
|
},
|
|
};
|
|
}
|
|
|
|
// Single connection: list all sources
|
|
const connections = await semanticLayerService.listConnectionIdsWithNames();
|
|
const connInfo = connections.find((c) => c.id === connectionId);
|
|
return this.discoverForConnection(semanticLayerService, connectionId, connInfo?.name ?? connectionId, query);
|
|
}
|
|
|
|
private async discoverAcrossConnections(
|
|
semanticLayerService: SemanticLayerService,
|
|
connections: Array<{ id: string; name: string; connectionType: string }>,
|
|
query?: string,
|
|
): Promise<ToolOutput<SlDiscoverStructured>> {
|
|
// Load sources from all connections in parallel
|
|
const results = await Promise.all(
|
|
connections.map(async (conn) => {
|
|
const { sources } = await semanticLayerService.loadAllSources(conn.id);
|
|
let filtered = sources;
|
|
if (query) {
|
|
filtered = await this.filterByQuery(conn.id, sources, query);
|
|
}
|
|
return { conn, sources: filtered };
|
|
}),
|
|
);
|
|
|
|
const allSummaries: SlDiscoverStructured['sources'] = [];
|
|
const parts: string[] = [];
|
|
let totalSources = 0;
|
|
|
|
for (const { conn, sources } of results) {
|
|
if (sources.length === 0) {
|
|
continue;
|
|
}
|
|
totalSources += sources.length;
|
|
|
|
parts.push(`## ${conn.name} (${conn.connectionType}) — \`${conn.id}\``);
|
|
parts.push('');
|
|
|
|
const config = { priority: DEFAULT_PRIORITY };
|
|
for (const s of sources) {
|
|
allSummaries.push({
|
|
connectionId: conn.id,
|
|
connectionName: conn.name,
|
|
name: s.name,
|
|
description: resolveDescription(s.descriptions, config) ?? undefined,
|
|
columnCount: (s.columns ?? []).length,
|
|
measureCount: (s.measures ?? []).length,
|
|
joinCount: (s.joins ?? []).length,
|
|
});
|
|
}
|
|
|
|
this.appendTieredSources(parts, sources, !!query);
|
|
}
|
|
|
|
if (totalSources === 0) {
|
|
return {
|
|
markdown: query
|
|
? `No semantic layer sources found matching "${query}".`
|
|
: 'No semantic layer sources found. Run a schema scan first, or create sources with sl_write_source.',
|
|
structured: { sources: [], totalSources: 0 },
|
|
};
|
|
}
|
|
|
|
const header = `**${totalSources} source(s) found across ${results.filter((r) => r.sources.length > 0).length} data source(s)**${query ? ` matching "${query}"` : ''}:\n`;
|
|
parts.unshift(header);
|
|
|
|
return {
|
|
markdown: parts.join('\n'),
|
|
structured: { sources: allSummaries, totalSources },
|
|
};
|
|
}
|
|
|
|
private async discoverForConnection(
|
|
semanticLayerService: SemanticLayerService,
|
|
connectionId: string,
|
|
connectionName: string,
|
|
query?: string,
|
|
): Promise<ToolOutput<SlDiscoverStructured>> {
|
|
const { sources } = await semanticLayerService.loadAllSources(connectionId);
|
|
|
|
if (sources.length === 0) {
|
|
return {
|
|
markdown: 'No semantic layer sources found. Run a schema scan first, or create sources with sl_write_source.',
|
|
structured: { sources: [], totalSources: 0 },
|
|
};
|
|
}
|
|
|
|
const filtered = query ? await this.filterByQuery(connectionId, sources, query) : sources;
|
|
|
|
const config = { priority: DEFAULT_PRIORITY };
|
|
const summaries = filtered.map((s) => ({
|
|
connectionId,
|
|
connectionName,
|
|
name: s.name,
|
|
description: resolveDescription(s.descriptions, config) ?? undefined,
|
|
columnCount: (s.columns ?? []).length,
|
|
measureCount: (s.measures ?? []).length,
|
|
joinCount: (s.joins ?? []).length,
|
|
}));
|
|
|
|
const parts: string[] = [`**${filtered.length} source(s) found**${query ? ` matching "${query}"` : ''}:\n`];
|
|
|
|
this.appendTieredSources(parts, filtered, !!query);
|
|
|
|
return {
|
|
markdown: parts.join('\n'),
|
|
structured: { sources: summaries, totalSources: filtered.length },
|
|
};
|
|
}
|
|
|
|
private async filterByQuery(
|
|
connectionId: string,
|
|
sources: SemanticLayerSource[],
|
|
query: string,
|
|
): Promise<SemanticLayerSource[]> {
|
|
const config = this.discoverySettings;
|
|
const searchResults = await this.slSearchService.search(connectionId, query, config.maxSources, config.minRrfScore);
|
|
if (searchResults.length > 0) {
|
|
const rankedNames = new Set(searchResults.map((r) => r.sourceName));
|
|
const nameOrder = new Map(searchResults.map((r, i) => [r.sourceName, i]));
|
|
return sources
|
|
.filter((s) => rankedNames.has(s.name))
|
|
.sort((a, b) => (nameOrder.get(a.name) ?? 0) - (nameOrder.get(b.name) ?? 0));
|
|
}
|
|
return this.fallbackTermMatch(sources, query);
|
|
}
|
|
|
|
private fallbackTermMatch(sources: SemanticLayerSource[], query: string): SemanticLayerSource[] {
|
|
const config = { priority: DEFAULT_PRIORITY };
|
|
const terms = query.toLowerCase().split(/\s+/).filter(Boolean);
|
|
const scored = sources
|
|
.map((s) => {
|
|
const searchText = [
|
|
s.name,
|
|
resolveDescription(s.descriptions, config) ?? '',
|
|
...s.columns.map((c) => `${c.name} ${resolveDescription(c.descriptions, config) ?? ''}`),
|
|
...s.measures.map((m) => `${m.name} ${m.description ?? ''}`),
|
|
]
|
|
.join(' ')
|
|
.toLowerCase();
|
|
const matchCount = terms.filter((term) => searchText.includes(term)).length;
|
|
return { source: s, matchCount };
|
|
})
|
|
.filter((x) => x.matchCount > 0)
|
|
.sort((a, b) => b.matchCount - a.matchCount);
|
|
return scored.map((x) => x.source);
|
|
}
|
|
|
|
/**
|
|
* Render sources in two tiers:
|
|
* - Top N (ranked by relevance when query is present) get full detail
|
|
* - Remaining sources get a one-liner with name, description, and measure count
|
|
*/
|
|
private appendTieredSources(parts: string[], sources: SemanticLayerSource[], hasQuery: boolean): void {
|
|
const maxDetailed = this.discoverySettings.maxDetailedSources;
|
|
const detailLimit = hasQuery ? maxDetailed : 0;
|
|
const detailed = sources.slice(0, detailLimit);
|
|
const rest = sources.slice(detailLimit);
|
|
|
|
for (const s of detailed) {
|
|
this.appendSourceDetail(parts, s);
|
|
}
|
|
|
|
if (rest.length > 0) {
|
|
if (detailed.length > 0) {
|
|
parts.push('**Other sources** (pass `sourceName` to inspect):');
|
|
}
|
|
const defaultConfig = { priority: DEFAULT_PRIORITY };
|
|
for (const s of rest) {
|
|
const resolvedDesc = resolveDescription(s.descriptions, defaultConfig);
|
|
const desc = resolvedDesc ? ` — ${resolvedDesc}` : '';
|
|
const stats = [s.measures.length > 0 ? `${s.measures.length} measures` : null, `${s.columns.length} cols`]
|
|
.filter(Boolean)
|
|
.join(', ');
|
|
parts.push(`- **${s.name}**${desc} (${stats})`);
|
|
}
|
|
parts.push('');
|
|
}
|
|
}
|
|
|
|
/** Full detail for a single source: metadata, measures, joins, all public columns. */
|
|
private appendSourceDetail(parts: string[], s: SemanticLayerSource): void {
|
|
const detailDesc = resolveDescription(s.descriptions, { priority: DEFAULT_PRIORITY });
|
|
parts.push(`### ${s.name}${detailDesc ? ` — ${detailDesc}` : ''}`);
|
|
parts.push(
|
|
`Type: ${s.sql ? 'sql' : 'table'} | Columns: ${s.columns.length} | Measures: ${s.measures.length} | Joins: ${s.joins.length}`,
|
|
);
|
|
|
|
if (s.measures.length > 0) {
|
|
parts.push(`Measures: ${s.measures.map((m) => `\`${m.name}\` (${m.expr})`).join(', ')}`);
|
|
}
|
|
|
|
if (s.joins.length > 0) {
|
|
parts.push(`Joins: ${s.joins.map((j) => `→ ${j.to} (${j.relationship})`).join(', ')}`);
|
|
}
|
|
|
|
const publicCols = s.columns.filter((c) => c.visibility !== 'hidden');
|
|
if (publicCols.length > 0) {
|
|
parts.push(`Columns: ${publicCols.map((c) => `\`${s.name}.${c.name}\` (${c.type})`).join(', ')}`);
|
|
}
|
|
|
|
parts.push('');
|
|
}
|
|
}
|