ktx/packages/cli/test/demo-metrics.test.ts

138 lines
5.2 KiB
TypeScript
Raw Permalink Normal View History

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 type { MemoryFlowEvent, MemoryFlowReplayInput } from '../src/context/ingest/memory-flow/types.js';
2026-05-10 23:12:26 +02:00
import { describe, expect, it } from 'vitest';
import {
buildDemoMetrics,
formatCost,
formatDuration,
formatEta,
formatTokens,
formatTokensPerSec,
progressBar,
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
} from '../src/demo-metrics.js';
2026-05-10 23:12:26 +02:00
function snapshot(events: MemoryFlowEvent[], overrides: Partial<MemoryFlowReplayInput> = {}): MemoryFlowReplayInput {
return {
runId: 'run-1',
connectionId: 'orbit_demo',
adapter: 'live-database',
status: 'running',
sourceDir: null,
syncId: 'sync-1',
errors: [],
events,
plannedWorkUnits: [],
details: { actions: [], provenance: [], transcripts: [] },
...overrides,
};
}
describe('buildDemoMetrics', () => {
it('estimates elapsed, agent steps, tool calls, and cost from event stream', () => {
const start = Date.UTC(2026, 0, 1, 0, 0, 0);
const input = snapshot(
[
{ type: 'source_acquired', adapter: 'live-database', trigger: 'demo_full', fileCount: 5, emittedAt: new Date(start).toISOString() },
{ type: 'work_unit_started', unitKey: 'orders', skills: [], stepBudget: 40, emittedAt: new Date(start + 1000).toISOString() },
{ type: 'work_unit_step', unitKey: 'orders', stepIndex: 6, stepBudget: 40, emittedAt: new Date(start + 6000).toISOString() },
],
{
plannedWorkUnits: [
{ unitKey: 'orders', rawFiles: [], peerFileCount: 0, dependencyCount: 0 },
{ unitKey: 'customers', rawFiles: [], peerFileCount: 0, dependencyCount: 0 },
],
details: {
actions: [],
provenance: [],
transcripts: [{ unitKey: 'orders', path: '/tmp/orders.jsonl', toolCallCount: 3, errorCount: 0, toolNames: ['x'] }],
},
},
);
const metrics = buildDemoMetrics(input, { now: () => start + 10_000 });
expect(metrics.elapsedMs).toBe(10_000);
expect(metrics.agentSteps).toBe(6);
expect(metrics.agentStepBudget).toBe(40);
expect(metrics.toolCalls).toBe(3);
expect(metrics.workUnitsTotal).toBe(2);
expect(metrics.estimatedTokens).toBeGreaterThan(0);
expect(metrics.estimatedCostUsd).toBeGreaterThan(0);
expect(metrics.isCostEstimated).toBe(true);
});
it('returns null ETA before the first work unit completes', () => {
const input = snapshot([{ type: 'source_acquired', adapter: 'live-database', trigger: 'x', fileCount: 1 }]);
const metrics = buildDemoMetrics(input, { now: () => Date.now() });
expect(metrics.etaMs).toBeNull();
});
it('extrapolates ETA from completed/total ratio when at least one unit finishes', () => {
const start = Date.UTC(2026, 0, 1);
const input = snapshot(
[
{ type: 'source_acquired', adapter: 'a', trigger: 't', fileCount: 1, emittedAt: new Date(start).toISOString() },
{ type: 'work_unit_started', unitKey: 'a', skills: [], stepBudget: 10, emittedAt: new Date(start + 1000).toISOString() },
{ type: 'work_unit_finished', unitKey: 'a', status: 'success', emittedAt: new Date(start + 5000).toISOString() },
],
{
plannedWorkUnits: [
{ unitKey: 'a', rawFiles: [], peerFileCount: 0, dependencyCount: 0 },
{ unitKey: 'b', rawFiles: [], peerFileCount: 0, dependencyCount: 0 },
{ unitKey: 'c', rawFiles: [], peerFileCount: 0, dependencyCount: 0 },
],
},
);
const metrics = buildDemoMetrics(input, { now: () => start + 6_000 });
expect(metrics.etaMs).toBe(12_000);
});
it('reports ETA=0 when the run is finished', () => {
const input = snapshot([], { status: 'done' });
const metrics = buildDemoMetrics(input, { now: () => Date.now() });
expect(metrics.etaMs).toBe(0);
});
});
describe('format helpers', () => {
it('formats duration in s/m/h cascades', () => {
expect(formatDuration(5_000)).toBe('5s');
expect(formatDuration(95_000)).toBe('1m35s');
expect(formatDuration(3_700_000)).toBe('1h01m');
expect(formatDuration(-1)).toBe('--');
});
it('formats ETA as estimating before any data and as duration once running', () => {
expect(formatEta(null, 'running')).toBe('estimating...');
expect(formatEta(8_000, 'running')).toBe('8s');
expect(formatEta(8_000, 'done')).toBe('done');
});
it('formats cost with sub-cent guard', () => {
expect(formatCost(0)).toBe('$0.000');
expect(formatCost(0.0005)).toBe('<$0.001');
expect(formatCost(0.012)).toBe('$0.012');
expect(formatCost(2.5)).toBe('$2.50');
});
it('formats token counts with K/M abbreviations', () => {
expect(formatTokens(0)).toBe('0');
expect(formatTokens(450)).toBe('450');
expect(formatTokens(2_300)).toBe('2.3K');
expect(formatTokens(1_500_000)).toBe('1.50M');
});
it('formats tokens per second', () => {
expect(formatTokensPerSec(0)).toBe('0/s');
expect(formatTokensPerSec(450)).toBe('450/s');
expect(formatTokensPerSec(2300)).toBe('2.3K/s');
});
it('renders a deterministic progress bar with hash and dash characters', () => {
expect(progressBar(0, 10)).toBe('----------');
expect(progressBar(0.5, 10)).toBe('#####-----');
expect(progressBar(1, 10)).toBe('##########');
expect(progressBar(1.4, 10)).toBe('##########');
});
});