ktx/packages/cli/src/context/sl/tools/sl-discover.tool.ts
Andrey Avtomonov 2366b00301
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

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('');
}
}