mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-16 08:25:14 +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.
314 lines
13 KiB
TypeScript
314 lines
13 KiB
TypeScript
/* @jsxImportSource react */
|
|
import type { MemoryFlowReplayInput } from './context/ingest/memory-flow/types.js';
|
|
import { render as renderInkTest } from 'ink-testing-library';
|
|
import React, { type ReactNode } from 'react';
|
|
import { describe, expect, it, vi } from 'vitest';
|
|
import {
|
|
MemoryFlowTuiApp,
|
|
memoryFlowCommandForInkInput,
|
|
renderMemoryFlowTui,
|
|
sanitizeMemoryFlowTuiError,
|
|
startLiveMemoryFlowTui,
|
|
type KtxMemoryFlowTuiIo,
|
|
type MemoryFlowInkInstance,
|
|
} from './memory-flow-tui.js';
|
|
|
|
function replayInput(): MemoryFlowReplayInput {
|
|
return {
|
|
runId: 'run-1', connectionId: 'warehouse', adapter: 'live-database',
|
|
status: 'done', sourceDir: null, syncId: 'sync-1', reportId: 'report-1', reportPath: 'report-1', errors: [],
|
|
plannedWorkUnits: [
|
|
{ unitKey: 'orders', rawFiles: ['orders'], peerFileCount: 0, dependencyCount: 1 },
|
|
{ unitKey: 'customers', rawFiles: ['customers'], peerFileCount: 1, dependencyCount: 0 },
|
|
],
|
|
details: {
|
|
actions: [
|
|
{ unitKey: 'orders', target: 'wiki', action: 'created', key: 'wiki/orders.md', summary: 'order lifecycle', rawFiles: ['orders'], status: 'success' },
|
|
{ unitKey: 'customers', target: 'sl', action: 'updated', key: 'orbit_demo.customers', summary: 'customer metrics', rawFiles: ['customers'], status: 'success' },
|
|
],
|
|
provenance: [{ rawPath: 'orders', artifactKind: 'wiki', artifactKey: 'wiki/orders.md', actionType: 'wiki_written' }],
|
|
transcripts: [{ unitKey: 'orders', path: '/tmp/t.jsonl', toolCallCount: 2, errorCount: 0, toolNames: ['read_raw_span', 'memory_ingest'] }],
|
|
},
|
|
events: [
|
|
{ type: 'source_acquired', adapter: 'live-database', trigger: 'manual_resync', fileCount: 2 },
|
|
{ type: 'scope_detected', fingerprint: 'scope-1' },
|
|
{ type: 'raw_snapshot_written', syncId: 'sync-1', rawFileCount: 2 },
|
|
{ type: 'diff_computed', added: 1, modified: 1, deleted: 0, unchanged: 0 },
|
|
{ type: 'chunks_planned', chunkCount: 2, workUnitCount: 2, evictionCount: 0 },
|
|
{ type: 'work_unit_started', unitKey: 'orders', skills: ['wiki_capture'], stepBudget: 40 },
|
|
{ type: 'candidate_action', unitKey: 'orders', target: 'wiki', action: 'created', key: 'wiki/orders.md' },
|
|
{ type: 'work_unit_finished', unitKey: 'orders', status: 'success' },
|
|
{ type: 'work_unit_started', unitKey: 'customers', skills: ['sl_capture'], stepBudget: 40 },
|
|
{ type: 'candidate_action', unitKey: 'customers', target: 'sl', action: 'updated', key: 'orbit_demo.customers' },
|
|
{ type: 'work_unit_finished', unitKey: 'customers', status: 'success' },
|
|
{ type: 'reconciliation_finished', conflictCount: 0, fallbackCount: 0 },
|
|
{ type: 'saved', commitSha: 'commit-one', wikiCount: 1, slCount: 1 },
|
|
{ type: 'provenance_recorded', rowCount: 1 },
|
|
{ type: 'report_created', runId: 'run-1', reportPath: 'report-1' },
|
|
],
|
|
};
|
|
}
|
|
|
|
function runningReplayInput(): MemoryFlowReplayInput {
|
|
return { ...replayInput(), status: 'running', syncId: 'pending', reportId: undefined, reportPath: undefined, plannedWorkUnits: [], events: [{ type: 'source_acquired', adapter: 'live-database', trigger: 'manual_resync', fileCount: 1 }] };
|
|
}
|
|
|
|
function packagedReplayInput(overrides: Partial<MemoryFlowReplayInput> = {}): MemoryFlowReplayInput {
|
|
return {
|
|
...replayInput(),
|
|
connectionId: 'orbit_demo',
|
|
metadata: {
|
|
schemaVersion: 1,
|
|
mode: 'seeded',
|
|
origin: 'packaged',
|
|
timing: 'prebuilt',
|
|
capturedAt: null,
|
|
sourceReportId: 'demo-seeded-report',
|
|
sourceReportPath: 'reports/seeded-demo-report.json',
|
|
fallbackReason: null,
|
|
},
|
|
...overrides,
|
|
};
|
|
}
|
|
|
|
function makeIo(): { io: KtxMemoryFlowTuiIo; stderr: () => string } {
|
|
let stderr = '';
|
|
return { io: { stdin: { isTTY: true, setRawMode: vi.fn() }, stdout: { isTTY: true, columns: 120, write: vi.fn() }, stderr: { write(chunk: string) { stderr += chunk; } } }, stderr: () => stderr };
|
|
}
|
|
|
|
function fakeInkInstance(): MemoryFlowInkInstance {
|
|
return { rerender: vi.fn(), unmount: vi.fn(), waitUntilExit: vi.fn(async () => undefined), clear: vi.fn() };
|
|
}
|
|
|
|
async function waitForInkInput(): Promise<void> { await new Promise((r) => setTimeout(r, 10)); }
|
|
|
|
function renderedAppProps(tree: ReactNode): Record<string, unknown> {
|
|
expect(React.isValidElement(tree)).toBe(true);
|
|
return (tree as React.ReactElement<Record<string, unknown>>).props;
|
|
}
|
|
|
|
describe('memoryFlowCommandForInkInput', () => {
|
|
it('maps input to commands', () => {
|
|
expect(memoryFlowCommandForInkInput('q', {})).toBe('quit');
|
|
expect(memoryFlowCommandForInkInput('c', { ctrl: true })).toBe('quit');
|
|
expect(memoryFlowCommandForInkInput('x', {})).toBeNull();
|
|
});
|
|
});
|
|
|
|
describe('sanitizeMemoryFlowTuiError', () => {
|
|
it('redacts credentials', () => {
|
|
expect(sanitizeMemoryFlowTuiError(new Error('postgres://x?api_key=y password=z'))).toBe('[redacted-url] [redacted]');
|
|
});
|
|
});
|
|
|
|
describe('MemoryFlowTuiApp', () => {
|
|
it('always shows the KTX logo', () => {
|
|
const { lastFrame } = renderInkTest(<MemoryFlowTuiApp input={replayInput()} terminalWidth={120} onExit={vi.fn()} showBoot={false} />);
|
|
expect(lastFrame()).toContain('╚███╔╝');
|
|
});
|
|
|
|
it('shows persistent HUD with source and status terminology', () => {
|
|
const { lastFrame } = renderInkTest(<MemoryFlowTuiApp input={{ ...replayInput(), connectionId: 'warehouse' }} terminalWidth={120} onExit={vi.fn()} showBoot={false} />);
|
|
const frame = lastFrame() ?? '';
|
|
expect(frame).toContain('Database (warehouse)');
|
|
expect(frame).toContain('2 tables');
|
|
expect(frame).toContain('done');
|
|
expect(frame).toContain('warehouse');
|
|
expect(frame).toContain('╭');
|
|
expect(frame).toContain('╰');
|
|
});
|
|
|
|
it('hides the internal demo connection id before packaged replay source events are visible', () => {
|
|
const { lastFrame } = renderInkTest(
|
|
<MemoryFlowTuiApp
|
|
input={packagedReplayInput({ status: 'running', events: [] })}
|
|
terminalWidth={120}
|
|
onExit={vi.fn()}
|
|
showBoot={false}
|
|
/>,
|
|
);
|
|
const frame = lastFrame() ?? '';
|
|
expect(frame).toContain('Orbit Demo');
|
|
expect(frame).not.toContain('orbit_demo');
|
|
expect(frame).not.toContain('Database (orbit_demo)');
|
|
});
|
|
|
|
it('keeps the packaged replay source label public while only one source event is visible', () => {
|
|
const { lastFrame } = renderInkTest(
|
|
<MemoryFlowTuiApp
|
|
input={packagedReplayInput({
|
|
status: 'running',
|
|
events: [{ type: 'source_acquired', adapter: 'live-database', trigger: 'demo_seeded', fileCount: 8 }],
|
|
})}
|
|
terminalWidth={120}
|
|
onExit={vi.fn()}
|
|
showBoot={false}
|
|
/>,
|
|
);
|
|
const frame = lastFrame() ?? '';
|
|
expect(frame).toContain('Orbit Demo');
|
|
expect(frame).not.toContain('orbit_demo');
|
|
expect(frame).not.toContain('Database (orbit_demo)');
|
|
});
|
|
|
|
it('shows a prepopulated data disclaimer for packaged demo replay cost estimates', () => {
|
|
const { lastFrame } = renderInkTest(
|
|
<MemoryFlowTuiApp
|
|
input={packagedReplayInput()}
|
|
terminalWidth={120}
|
|
onExit={vi.fn()}
|
|
showBoot={false}
|
|
/>,
|
|
);
|
|
const frame = lastFrame() ?? '';
|
|
expect(frame).toContain('$');
|
|
expect(frame).toContain('Pre-run demo: $ shown is illustrative; no money is being spent now.');
|
|
expect(frame).not.toContain('orbit_demo');
|
|
});
|
|
|
|
it('does not show the prepopulated data disclaimer for captured full replay cost estimates', () => {
|
|
const { lastFrame } = renderInkTest(
|
|
<MemoryFlowTuiApp
|
|
input={{
|
|
...replayInput(),
|
|
metadata: {
|
|
schemaVersion: 1,
|
|
mode: 'full',
|
|
origin: 'captured',
|
|
timing: 'captured',
|
|
capturedAt: '2026-05-01T00:00:00.000Z',
|
|
sourceReportId: 'report-full',
|
|
sourceReportPath: 'reports/report-full.json',
|
|
fallbackReason: null,
|
|
},
|
|
}}
|
|
terminalWidth={120}
|
|
onExit={vi.fn()}
|
|
showBoot={false}
|
|
/>,
|
|
);
|
|
expect(lastFrame()).not.toContain('Demo data is prepopulated');
|
|
});
|
|
|
|
it('shows accumulated activity feed on completion', () => {
|
|
const { lastFrame } = renderInkTest(<MemoryFlowTuiApp input={replayInput()} terminalWidth={120} onExit={vi.fn()} showBoot={false} />);
|
|
const frame = lastFrame() ?? '';
|
|
expect(frame).toContain('Connected — found 2 tables to ingest');
|
|
expect(frame).toContain('Created so far:');
|
|
expect(frame).toContain('order lifecycle');
|
|
expect(frame).toContain('customer metrics');
|
|
expect(frame).toContain('KTX finished ingesting your data');
|
|
expect(frame).toContain('ktx sl');
|
|
expect(frame).toContain('ktx wiki');
|
|
expect(frame).not.toContain('ktx serve --mcp stdio --user-id local');
|
|
expect(frame).not.toContain(['ktx', 'ask'].join(' '));
|
|
expect(frame).not.toContain(['ktx', 'mcp'].join(' '));
|
|
});
|
|
|
|
it('handles quit while running', async () => {
|
|
const onExit = vi.fn();
|
|
const { stdin } = renderInkTest(<MemoryFlowTuiApp input={runningReplayInput()} terminalWidth={120} onExit={onExit} showBoot={false} />);
|
|
stdin.write('q');
|
|
await waitForInkInput();
|
|
expect(onExit).toHaveBeenCalledTimes(1);
|
|
});
|
|
|
|
it('shows active work unit with progress', () => {
|
|
const running: MemoryFlowReplayInput = {
|
|
...runningReplayInput(),
|
|
events: [
|
|
{ type: 'source_acquired', adapter: 'live-database', trigger: 'manual_resync', fileCount: 1 },
|
|
{ type: 'diff_computed', added: 1, modified: 0, deleted: 0, unchanged: 0 },
|
|
{ type: 'chunks_planned', chunkCount: 1, workUnitCount: 1, evictionCount: 0 },
|
|
{ type: 'work_unit_started', unitKey: 'orders', skills: ['wiki_capture'], stepBudget: 40 },
|
|
],
|
|
plannedWorkUnits: [{ unitKey: 'orders', rawFiles: ['orders'], peerFileCount: 0, dependencyCount: 1 }],
|
|
};
|
|
const { lastFrame } = renderInkTest(<MemoryFlowTuiApp input={running} terminalWidth={120} onExit={vi.fn()} showBoot={false} />);
|
|
const frame = lastFrame() ?? '';
|
|
expect(frame).toContain('Ingesting — 0/1 business area done');
|
|
expect(frame).toContain('Reading table schemas, understanding relationships, creating query definitions');
|
|
expect(frame).toContain('╚███╔╝');
|
|
});
|
|
|
|
it('describes multi-source ingestion as building the context layer', () => {
|
|
const running: MemoryFlowReplayInput = {
|
|
...runningReplayInput(),
|
|
adapter: 'multi-source',
|
|
events: [
|
|
{ type: 'source_acquired', adapter: 'live-database', trigger: 'manual_resync', fileCount: 8 },
|
|
{ type: 'source_acquired', adapter: 'dbt-descriptions', trigger: 'manual_resync', fileCount: 3 },
|
|
{ type: 'diff_computed', added: 11, modified: 0, deleted: 0, unchanged: 0 },
|
|
{ type: 'chunks_planned', chunkCount: 1, workUnitCount: 1, evictionCount: 0 },
|
|
{ type: 'work_unit_started', unitKey: 'orders', skills: ['wiki_capture'], stepBudget: 40 },
|
|
],
|
|
plannedWorkUnits: [{ unitKey: 'orders', rawFiles: ['orders'], peerFileCount: 0, dependencyCount: 1 }],
|
|
};
|
|
|
|
const { lastFrame } = renderInkTest(<MemoryFlowTuiApp input={running} terminalWidth={120} onExit={vi.fn()} showBoot={false} />);
|
|
const frame = lastFrame() ?? '';
|
|
expect(frame).toContain('Ingesting warehouse, dbt, BI, and docs into a unified context layer');
|
|
expect(frame).not.toContain('unified semantic layer');
|
|
});
|
|
|
|
it('hides completion while running', () => {
|
|
const { lastFrame } = renderInkTest(<MemoryFlowTuiApp input={runningReplayInput()} terminalWidth={120} onExit={vi.fn()} showBoot={false} />);
|
|
expect(lastFrame()).not.toContain('KTX finished ingesting');
|
|
});
|
|
});
|
|
|
|
describe('startLiveMemoryFlowTui', () => {
|
|
it('starts and updates', async () => {
|
|
const { io } = makeIo();
|
|
const instance = fakeInkInstance();
|
|
const live = await startLiveMemoryFlowTui(runningReplayInput(), io, { renderInk: () => instance });
|
|
expect(live).not.toBeNull();
|
|
live?.update(replayInput());
|
|
expect(instance.rerender).toHaveBeenCalledTimes(1);
|
|
live?.close();
|
|
expect(instance.unmount).toHaveBeenCalledTimes(1);
|
|
});
|
|
|
|
it('redacts errors', async () => {
|
|
const { io, stderr } = makeIo();
|
|
await expect(startLiveMemoryFlowTui(runningReplayInput(), io, { renderInk: () => { throw new Error('postgres://x?token=y'); } })).resolves.toBeNull();
|
|
expect(stderr()).toContain('[redacted-url]');
|
|
});
|
|
});
|
|
|
|
describe('renderMemoryFlowTui', () => {
|
|
it('renders and returns true', async () => {
|
|
const { io } = makeIo();
|
|
const instance = fakeInkInstance();
|
|
await expect(renderMemoryFlowTui(replayInput(), io, { renderInk: () => instance })).resolves.toBe(true);
|
|
});
|
|
|
|
it('scales event timing with the speed multiplier while keeping animations normal speed', async () => {
|
|
const { io } = makeIo();
|
|
const instance = fakeInkInstance();
|
|
let renderedTree: ReactNode = null;
|
|
|
|
await expect(
|
|
renderMemoryFlowTui(replayInput(), io, {
|
|
speedMultiplier: 0.125,
|
|
renderInk: (tree) => {
|
|
renderedTree = tree;
|
|
return instance;
|
|
},
|
|
}),
|
|
).resolves.toBe(true);
|
|
|
|
expect(renderedAppProps(renderedTree)).toMatchObject({
|
|
paceMsPerEvent: 1440,
|
|
frameMs: 140,
|
|
completionFrameMs: 80,
|
|
completionHoldMs: 1000,
|
|
});
|
|
});
|
|
|
|
it('redacts errors', async () => {
|
|
const { io, stderr } = makeIo();
|
|
await expect(renderMemoryFlowTui(replayInput(), io, { renderInk: () => { throw new Error('postgres://x?token=y'); } })).resolves.toBe(false);
|
|
expect(stderr()).toContain('[redacted-url]');
|
|
});
|
|
});
|