ktx/packages/cli/test/knowledge.test.ts

331 lines
10 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import { mkdtemp, rm } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { stripVTControlCharacters } from 'node:util';
test: split cli tests from source tree (#216) * feat(cli): define full warehouse dialect contract * test(cli): keep dialect edge tests focused * fix(cli): stabilize dialect contract foundation * refactor(connectors): own read-only query preparation * refactor(connectors): resolve dialects through registry * refactor(connectors): keep concrete dialect classes internal * chore(workspace): enforce dialect import boundary * refactor(cli): resolve relationship dialect at scan boundary * refactor(cli): use dialect display parsing for entity details * refactor(cli): use dialect display parsing for warehouse catalog * refactor(cli): use dialect SQL in relationship workflows * test(cli): verify solid dialect scan workflow closure * test: split cli tests from source tree * refactor(cli): standardize BigQuery scope listing * feat(sqlite): implement connector scope listing * test(connectors): cover required table listing * feat(cli): add warehouse driver registry * refactor(setup): route scope discovery through driver registry * refactor(cli): route local query execution through driver registry * refactor(historic-sql): route dialect support through driver registry * refactor(cli): test warehouse connections through driver registry * fix(cli): close driver registry type export gaps * Improve setup daemon diagnostics * refactor(setup): centralize rail-prefixed diagnostics + query-history fallback Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput into clack.ts so the setup wizard, managed daemons, and embedding/agent steps share one rail-formatted writer. setup-databases.ts also adds a "disable query history and retry" option when the schema-context build fails and query history is the likely culprit, surfaced via a new failed-query-history-unavailable status. * fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match The setup picker's KtxTableListEntry was a 2-level { schema, name }, so qualifiedTableId always wrote db.name into enabled_tables. When BigQuery, Snowflake, or SQL Server later ran fast ingest, their introspect step filtered the scope set with scopedTableNames(scope, { catalog: projectId|database, db }) — catalog was non-null on the introspect side but null in the scope refs, so every entry was rejected, the live-database adapter staged zero table files, and detect() failed with 'Adapter "live-database" did not recognize fetched source output'. Align the picker boundary with the canonical 3-level KtxTableRef: - Add catalog: string | null to KtxTableListEntry. - BigQuery/Snowflake/SQL Server listTables populate catalog from the resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null. - qualifiedTableId emits catalog.schema.name when catalog is non-null (resolveEnabledTables already accepts the 3-part shape) and schemasFromEnabledTables now goes through parseDottedTableEntry so it recovers the schema correctly from both 2-part and 3-part entries. - Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker reuse. Update listTables expectations in all seven connector tests and the setup / picker test fixtures. Add a picker regression test that covers the catalog-bearing round-trip (save + refine). * fix(cli): allow debug telemetry under opt-out env
2026-05-26 08:49:05 +02:00
import { initKtxProject, loadKtxProject } from '../src/context/project/project.js';
import type { KtxEmbeddingPort } from '../src/context/core/embedding.js';
import { writeLocalKnowledgePage } from '../src/context/wiki/local-knowledge.js';
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
test: split cli tests from source tree (#216) * feat(cli): define full warehouse dialect contract * test(cli): keep dialect edge tests focused * fix(cli): stabilize dialect contract foundation * refactor(connectors): own read-only query preparation * refactor(connectors): resolve dialects through registry * refactor(connectors): keep concrete dialect classes internal * chore(workspace): enforce dialect import boundary * refactor(cli): resolve relationship dialect at scan boundary * refactor(cli): use dialect display parsing for entity details * refactor(cli): use dialect display parsing for warehouse catalog * refactor(cli): use dialect SQL in relationship workflows * test(cli): verify solid dialect scan workflow closure * test: split cli tests from source tree * refactor(cli): standardize BigQuery scope listing * feat(sqlite): implement connector scope listing * test(connectors): cover required table listing * feat(cli): add warehouse driver registry * refactor(setup): route scope discovery through driver registry * refactor(cli): route local query execution through driver registry * refactor(historic-sql): route dialect support through driver registry * refactor(cli): test warehouse connections through driver registry * fix(cli): close driver registry type export gaps * Improve setup daemon diagnostics * refactor(setup): centralize rail-prefixed diagnostics + query-history fallback Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput into clack.ts so the setup wizard, managed daemons, and embedding/agent steps share one rail-formatted writer. setup-databases.ts also adds a "disable query history and retry" option when the schema-context build fails and query history is the likely culprit, surfaced via a new failed-query-history-unavailable status. * fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match The setup picker's KtxTableListEntry was a 2-level { schema, name }, so qualifiedTableId always wrote db.name into enabled_tables. When BigQuery, Snowflake, or SQL Server later ran fast ingest, their introspect step filtered the scope set with scopedTableNames(scope, { catalog: projectId|database, db }) — catalog was non-null on the introspect side but null in the scope refs, so every entry was rejected, the live-database adapter staged zero table files, and detect() failed with 'Adapter "live-database" did not recognize fetched source output'. Align the picker boundary with the canonical 3-level KtxTableRef: - Add catalog: string | null to KtxTableListEntry. - BigQuery/Snowflake/SQL Server listTables populate catalog from the resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null. - qualifiedTableId emits catalog.schema.name when catalog is non-null (resolveEnabledTables already accepts the 3-part shape) and schemasFromEnabledTables now goes through parseDottedTableEntry so it recovers the schema correctly from both 2-part and 3-part entries. - Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker reuse. Update listTables expectations in all seven connector tests and the setup / picker test fixtures. Add a picker regression test that covers the catalog-bearing round-trip (save + refine). * fix(cli): allow debug telemetry under opt-out env
2026-05-26 08:49:05 +02:00
import { runKtxKnowledge } from '../src/knowledge.js';
2026-05-10 23:12:26 +02:00
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
function makeIo(options: { isTTY?: boolean } = {}) {
2026-05-10 23:12:26 +02:00
let stdout = '';
let stderr = '';
return {
io: {
stdout: {
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
isTTY: options.isTTY,
2026-05-10 23:12:26 +02:00
write: (chunk: string) => {
stdout += chunk;
},
},
stderr: {
write: (chunk: string) => {
stderr += chunk;
},
},
},
stdout: () => stdout,
stderr: () => stderr,
};
}
2026-05-11 22:59:45 +02:00
class FakeEmbeddingPort implements KtxEmbeddingPort {
readonly maxBatchSize = 16;
async computeEmbedding(text: string): Promise<number[]> {
const lower = text.toLowerCase();
return lower.includes('revenue') || lower.includes('arr') ? [1, 0] : [0, 1];
}
async computeEmbeddingsBulk(texts: string[]): Promise<number[][]> {
return Promise.all(texts.map((text) => this.computeEmbedding(text)));
}
}
interface WikiPageFixture {
key?: string;
summary?: string;
content?: string;
tags?: string[];
slRefs?: string[];
}
async function seedWikiPage(projectDir: string, fixture: WikiPageFixture = {}): Promise<void> {
const project = await loadKtxProject({ projectDir });
await writeLocalKnowledgePage(project, {
key: fixture.key ?? 'metrics-revenue',
scope: 'GLOBAL',
userId: 'local',
summary: fixture.summary ?? 'Revenue',
content: fixture.content ?? 'Revenue is paid order value.',
tags: fixture.tags ?? ['finance'],
refs: [],
slRefs: fixture.slRefs ?? ['orders'],
});
}
2026-05-10 23:51:24 +02:00
describe('runKtxKnowledge', () => {
2026-05-10 23:12:26 +02:00
let tempDir: string;
beforeEach(async () => {
2026-05-10 23:51:24 +02:00
tempDir = await mkdtemp(join(tmpdir(), 'ktx-cli-knowledge-'));
2026-05-10 23:12:26 +02:00
});
afterEach(async () => {
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
vi.unstubAllEnvs();
2026-05-10 23:12:26 +02:00
await rm(tempDir, { recursive: true, force: true });
});
it('lists and searches wiki pages', async () => {
2026-05-10 23:12:26 +02:00
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await seedWikiPage(projectDir);
2026-05-10 23:12:26 +02:00
const listIo = makeIo();
await expect(
runKtxKnowledge({ command: 'list', projectDir, userId: 'local', cliVersion: '0.0.0-test' }, listIo.io),
).resolves.toBe(0);
expect(listIo.stdout()).toContain('GLOBAL\tmetrics-revenue\tRevenue');
2026-05-10 23:12:26 +02:00
const searchIo = makeIo();
await expect(
runKtxKnowledge(
{ command: 'search', projectDir, query: 'paid order', userId: 'local', cliVersion: '0.0.0-test' },
searchIo.io,
),
2026-05-10 23:12:26 +02:00
).resolves.toBe(0);
expect(searchIo.stdout()).toContain('metrics-revenue');
});
feat(cli): shell completion for commands, flags, and entity names (#244) * feat(completion): complete known argument values * fix(completion): hide Commander-hidden subcommands from completions Replace the `__`-prefix name heuristic with Commander's `_hidden` flag so internal subcommands registered with { hidden: true } (e.g. `mcp serve-internal`) are excluded from completions, mirroring `ktx --help`. * test: cover wiki and sl read command routing * test: cover raw wiki and sl reads * feat: add wiki read command * feat: add sl read command * feat: complete read command entity names * docs: document wiki and sl read commands * test: include read commands in command tree * feat(sl): read and validate unique sources by name * feat(sl): make read and validate connection id optional * fix(completion): dedupe semantic source names * docs(sl): document connection-optional read and validate * fix(sl): require connection id for query command * docs(sl): clarify query connection requirement * fix(completion): don't resolve option values as subcommands resolveCommand skipped flag tokens but not the value consumed by a value-taking option in the `--flag value` form, so a connection id like `query` was matched as the `sl query` subcommand and yielded no `sl` completions. Track value-taking options and skip their consumed value before matching subcommands. * test(telemetry): assert first-run notice via TELEMETRY_NOTICE constant CI (which tests this branch merged with main) failed because #243 changed the first-run notice wording in identity.ts (dropped "anonymous") but left this test grepping for the old literal 'ktx collects anonymous usage data', so indexOf returned -1. Assert against the exported TELEMETRY_NOTICE constant instead so the test tracks the source of truth and cannot drift when the notice text changes again.
2026-05-31 23:44:33 +02:00
it('reads a wiki page as raw markdown with frontmatter', async () => {
const projectDir = join(tempDir, 'read-project');
await initKtxProject({ projectDir });
await seedWikiPage(projectDir, {
key: 'metrics-revenue',
summary: 'Revenue',
content: 'Revenue is paid order value.',
tags: ['finance'],
slRefs: ['orders'],
});
const readIo = makeIo();
await expect(
runKtxKnowledge({ command: 'read', projectDir, key: 'metrics-revenue', userId: 'local' }, readIo.io),
).resolves.toBe(0);
expect(readIo.stdout()).toContain('---\n');
expect(readIo.stdout()).toContain('summary: Revenue');
expect(readIo.stdout()).toContain('tags:');
expect(readIo.stdout()).toContain('- finance');
expect(readIo.stdout()).toContain('sl_refs:');
expect(readIo.stdout()).toContain('- orders');
expect(readIo.stdout()).toContain('usage_mode: auto');
expect(readIo.stdout()).toContain('Revenue is paid order value.');
expect(readIo.stderr()).toBe('');
});
it('reports a clear error when a wiki page key is missing', async () => {
const projectDir = join(tempDir, 'missing-read-project');
await initKtxProject({ projectDir });
const readIo = makeIo();
await expect(
runKtxKnowledge({ command: 'read', projectDir, key: 'missing-page', userId: 'local' }, readIo.io),
).resolves.toBe(1);
expect(readIo.stdout()).toBe('');
expect(readIo.stderr()).toBe("No wiki page found for key 'missing-page'\n");
});
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
it('emits debug telemetry for wiki search without query text', async () => {
vi.stubEnv('KTX_TELEMETRY_DEBUG', '1');
vi.stubEnv('CI', '');
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await seedWikiPage(projectDir);
const searchIo = makeIo({ isTTY: true });
await expect(
runKtxKnowledge(
{ command: 'search', projectDir, query: 'revenue recognition', userId: 'local', cliVersion: '0.0.0-test' },
searchIo.io,
),
).resolves.toBe(0);
expect(searchIo.stderr()).toContain('"event":"wiki_query_completed"');
expect(searchIo.stderr()).toContain('"queryLength"');
expect(searchIo.stderr()).not.toContain('revenue recognition');
});
it('prints wiki search rank badges in pretty output', async () => {
const projectDir = join(tempDir, 'rank-project');
await initKtxProject({ projectDir });
await seedWikiPage(projectDir);
const searchIo = makeIo();
await expect(
runKtxKnowledge(
{
command: 'search',
projectDir,
query: 'paid order',
userId: 'local',
output: 'pretty',
cliVersion: '0.0.0-test',
},
searchIo.io,
),
).resolves.toBe(0);
const stdout = stripVTControlCharacters(searchIo.stdout());
expect(stdout).toMatch(/#1\s+metrics-revenue/);
expect(stdout).not.toContain('%');
});
it('prints wiki list and search as public JSON envelopes', async () => {
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await seedWikiPage(projectDir);
const listIo = makeIo();
await expect(
runKtxKnowledge(
{ command: 'list', projectDir, userId: 'local', json: true, cliVersion: '0.0.0-test' },
listIo.io,
),
).resolves.toBe(0);
expect(JSON.parse(listIo.stdout())).toMatchObject({
kind: 'list',
data: { items: [expect.objectContaining({ key: 'metrics-revenue', summary: 'Revenue' })] },
meta: { command: 'wiki list' },
});
const searchIo = makeIo();
await expect(
runKtxKnowledge(
{
command: 'search',
projectDir,
query: 'paid order',
userId: 'local',
json: true,
limit: 5,
cliVersion: '0.0.0-test',
},
searchIo.io,
),
).resolves.toBe(0);
expect(JSON.parse(searchIo.stdout())).toMatchObject({
kind: 'list',
data: { items: [expect.objectContaining({ key: 'metrics-revenue', summary: 'Revenue' })] },
meta: { command: 'wiki search' },
});
2026-05-10 23:12:26 +02:00
});
it('explains empty search results for a project without wiki pages', async () => {
const projectDir = join(tempDir, 'empty-project');
await initKtxProject({ projectDir });
2026-05-10 23:12:26 +02:00
const searchIo = makeIo();
await expect(
runKtxKnowledge(
{ command: 'search', projectDir, query: 'revenue', userId: 'local', cliVersion: '0.0.0-test' },
searchIo.io,
),
2026-05-10 23:12:26 +02:00
).resolves.toBe(0);
expect(searchIo.stdout()).toBe('');
expect(searchIo.stderr()).toContain('No local wiki pages found');
feat: merge ingest and scan * docs: add CLI component reuse guidance * docs: add unified ingest ux design * Refine unified ingest UX design after adversarial review iteration 1 * Refine unified ingest UX design after adversarial review iteration 2 * Refine unified ingest UX design after adversarial review iteration 3 * feat(cli): route public connection ingest command * feat(cli): hide standalone scan from public help * feat(cli): plan public ingest depth and query history * feat(cli): execute public database ingest facets * feat(ingest): read connection query history config * fix(cli): use public ingest wording * fix(config): stop generating ingest adapter allow lists * docs: document public ingest command * test: align ingest surface expectations * docs: add unified ingest public CLI surface plan * feat(cli): preflight deep public ingest readiness * feat(setup): store query history in connection context * feat(setup): store database context depth * feat(setup): verify context readiness by database depth * fix(setup): keep context build foreground only * fix(config): reject reserved ingest connection ids * test: close unified ingest v1 expectations * docs: add unified ingest v1 closure plan * fix(ingest): bypass adapter allow-list for public source ingest * fix(ingest): honor query history window intent * fix(ingest): hide scan internals from public database ingest * feat(ingest): use foreground view for interactive public ingest * fix(setup): use schema context and query history wording * test(cli): verify unified ingest public output * docs: add unified ingest v1 public output closure plan * fix(setup): forward query history flags * fix(setup): prompt for postgres query history * fix(status): report query history readiness * fix(ingest): remove legacy public guidance * fix(ingest): polish foreground retry copy * docs(examples): use unified query history wording * chore(ingest): finish public query history cleanup * docs: add unified ingest v1 query history status cleanup plan * test(docs): cover unified ingest public docs * docs: align ingest CLI reference with unified UX * docs: update context build guides for unified ingest * docs: update setup and primary source ingest wording * docs: stop advertising adapter-backed example ingest * docs: close unified ingest public docs gaps * docs: add unified ingest v1 docs site closure plan * fix: render unified ingest foreground warnings * fix: explain query history schema order * fix: add public ingest retry guidance * fix: align setup next steps with unified ingest * fix: remove scan wording from demo progress * test: verify unified ingest ux closure * docs: add unified ingest v1 foreground and retry closure plan * fix(cli): preserve query-history pull config in public ingest * fix(cli): omit hidden commands from docs command tree * test(cli): close unified ingest final public surface checks * docs: add unified ingest v1 final public surface closure plan * fix(cli): use public source labels in ingest reports * fix(cli): suppress low-level public ingest output * test(cli): verify unified ingest public plain output * docs: add unified ingest v1 public plain output closure plan * fix(cli): add public ingest copy sanitizers * fix(cli): sanitize public ingest progress copy * fix(cli): rename setup schema scope prompt * docs(plan): add progress copy closure; test: align setup back-nav fixture Adds the iter9 plan and updates the setup back-navigation test fixture to pass disableQueryHistory plus listSchemas/listTables stubs that the unified ingest setup step now requires. * docs(plan): add final ux labels plan with narrowed label scans * fix(cli): aggregate unsupported query-history warnings * fix(cli): align setup database labels * test(cli): fix setup database test type-check * fix(cli): remove primary-source wording from setup output * test(cli): verify unified ingest setup closure * docs(plan): add unified ingest v1 verification copy closure plan * fix(cli): remove top-level scan command * fix(cli): remove legacy ingest and wiki commands * Merge scan into ingest flow * feat(cli): split ingest progress into per-phase rows, rename work units to tasks Each database target in the unified ingest dashboard now renders one row per real subprocess (Schema, then Query history when enabled) instead of a single combined bar. Each phase has its own monotonic 0-100% bar so the progress never snaps back to zero when historic-sql starts after scan completes. Completed phases keep their final bar, summary, and elapsed time visible as an inline audit trail; queued and skipped phases are shown explicitly. Also rename user-facing "work units" / "Failed work units" to "tasks" / "Failed tasks" in ingest output and parseIngestSummary. The parser still accepts the legacy "Work units:" wording in captured output for backward compat. Internal memory-flow event names and type fields are left alone. * Fix test harness failures * Fix CI smoke checks --------- Co-authored-by: Andrey Avtomonov <7889985+andreybavt@users.noreply.github.com>
2026-05-14 01:43:06 +02:00
expect(searchIo.stderr()).toContain('ktx ingest <connectionId>');
2026-05-10 23:12:26 +02:00
});
2026-05-11 22:59:45 +02:00
it('uses configured embeddings for semantic wiki search', async () => {
const projectDir = join(tempDir, 'semantic-project');
await initKtxProject({ projectDir });
await seedWikiPage(projectDir, {
key: 'active-contract-arr-open-tickets',
summary: 'Active Contract ARR Ranked by Open Support Ticket Count',
content: 'Accounts ranked by annual recurring contract value and support ticket load.',
tags: ['historic-sql'],
slRefs: [],
});
2026-05-11 22:59:45 +02:00
const searchIo = makeIo();
await expect(
runKtxKnowledge(
{ command: 'search', projectDir, query: 'revenue', userId: 'local', cliVersion: '0.0.0-test' },
2026-05-11 22:59:45 +02:00
searchIo.io,
{ embeddingService: new FakeEmbeddingPort() },
),
).resolves.toBe(0);
expect(searchIo.stdout()).toContain('active-contract-arr-open-tickets');
2026-05-11 22:59:45 +02:00
expect(searchIo.stderr()).toBe('');
});
it('routes wiki search through resolveEmbeddingProvider when no embeddingService is injected', async () => {
const projectDir = join(tempDir, 'resolver-project');
await initKtxProject({ projectDir });
const search = vi.fn(async () => []);
const searchIo = makeIo();
await expect(
runKtxKnowledge(
{
command: 'search',
projectDir,
query: 'income',
userId: 'local',
cliVersion: '0.5.0',
},
searchIo.io,
{
resolveEmbeddingProvider: async () => ({
kind: 'managed-running',
provider: { id: 'fake' } as never,
baseUrl: 'http://127.0.0.1:51234',
}),
searchLocalKnowledgePages: search,
},
),
).resolves.toBe(0);
expect(search).toHaveBeenCalledWith(
expect.anything(),
expect.objectContaining({ embeddingService: expect.any(Object) }),
);
});
it('writes wiki search lane diagnostics to stderr when debug is enabled', async () => {
const projectDir = join(tempDir, 'debug-project');
await initKtxProject({ projectDir });
await seedWikiPage(projectDir);
const searchIo = makeIo();
await expect(
runKtxKnowledge(
{
command: 'search',
projectDir,
query: 'paid order',
userId: 'local',
json: true,
debug: true,
cliVersion: '0.0.0-test',
},
searchIo.io,
{ embeddingService: new FakeEmbeddingPort() },
),
).resolves.toBe(0);
expect(JSON.parse(searchIo.stdout())).toMatchObject({
kind: 'list',
data: { items: [expect.objectContaining({ key: 'metrics-revenue' })] },
meta: { command: 'wiki search' },
});
expect(searchIo.stderr()).toContain('[debug] wiki search mode=sqlite-fts5');
expect(searchIo.stderr()).toContain('embedding=configured');
expect(searchIo.stderr()).toContain('lane=lexical status=available');
expect(searchIo.stderr()).toContain('lane=semantic status=available');
});
2026-05-10 23:12:26 +02:00
});