ktx/packages/cli/test/llm/message-builder.test.ts
Andrey Avtomonov 56985b7e09
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

146 lines
5.5 KiB
TypeScript

import type { ModelMessage } from 'ai';
import { describe, expect, it } from 'vitest';
import { KtxMessageBuilder, splitKtxSystemMessages } from '../../src/llm/message-builder.js';
import { createKtxLlmProvider } from '../../src/llm/model-provider.js';
function makeBuilder(overrides: Parameters<typeof createKtxLlmProvider>[0]['promptCaching'] = {}) {
const provider = createKtxLlmProvider({
backend: 'gateway',
gateway: { baseURL: 'https://gateway.test' },
modelSlots: { default: 'anthropic/claude-sonnet-4-6' },
promptCaching: { enabled: true, ...overrides },
});
return new KtxMessageBuilder(provider);
}
describe('KtxMessageBuilder.build', () => {
it('caches static system, last sorted tool, and last history message', () => {
const builder = makeBuilder();
const out = builder.build({
parts: { staticSystem: 'STATIC', dynamicSystem: 'DYNAMIC' },
history: [
{ role: 'user', content: 'first' },
{ role: 'assistant', content: [{ type: 'text', text: 'reply A' }, { type: 'text', text: 'reply B' }] } as ModelMessage,
],
currentMessage: { role: 'user', content: 'now' },
tools: {
zoo: { description: 'z' },
apple: { description: 'a' },
},
model: 'anthropic/claude-sonnet-4-6',
});
expect(out.messages[0]).toMatchObject({
role: 'system',
content: 'STATIC',
providerOptions: { anthropic: { cacheControl: { type: 'ephemeral', ttl: '1h' } } },
});
expect(out.messages[1]).toMatchObject({ role: 'system', content: 'DYNAMIC' });
expect((out.messages[1] as { providerOptions?: unknown }).providerOptions).toBeUndefined();
expect((out.messages[3] as { content: Array<{ providerOptions?: unknown }> }).content[1].providerOptions).toEqual({
anthropic: { cacheControl: { type: 'ephemeral', ttl: '5m' } },
});
expect(Object.keys(out.tools)).toEqual(['apple', 'zoo']);
expect((out.tools.zoo as { providerOptions?: unknown }).providerOptions).toEqual({
anthropic: { cacheControl: { type: 'ephemeral', ttl: '1h' } },
});
});
it('wraps leading user context onto currentMessage as a system reminder part', () => {
const builder = makeBuilder();
const out = builder.build({
parts: { staticSystem: 'STATIC', leadingUserContext: 'current_date: 2026-05-04' },
history: [],
currentMessage: { role: 'user', content: 'question' },
tools: {},
model: 'anthropic/claude-sonnet-4-6',
});
expect(out.messages[out.messages.length - 1]).toMatchObject({
role: 'user',
content: [
{ type: 'text', text: '<system-reminder>\ncurrent_date: 2026-05-04\n</system-reminder>' },
{ type: 'text', text: 'question' },
],
});
});
it('omits cache markers for non-Anthropic protocol models', () => {
const builder = makeBuilder();
const out = builder.wrapSimple({
system: 'SYS',
messages: [{ role: 'user', content: 'q' }],
tools: { z: {} },
model: 'gpt-5',
});
expect((out.messages[0] as { providerOptions?: unknown }).providerOptions).toBeUndefined();
expect((out.tools.z as { providerOptions?: unknown }).providerOptions).toBeUndefined();
});
it('clamps every TTL to 5m for Vertex when vertexFallbackTo5m is enabled', () => {
const provider = createKtxLlmProvider({
backend: 'vertex',
vertex: { project: 'ktx-test', location: 'us-east5' },
modelSlots: { default: 'claude-sonnet-4-6' },
promptCaching: {
enabled: true,
systemTtl: '1h',
toolsTtl: '1h',
historyTtl: '1h',
vertexFallbackTo5m: true,
},
});
const builder = new KtxMessageBuilder(provider);
const out = builder.build({
parts: { staticSystem: 'STATIC' },
history: [{ role: 'user', content: 'history' }],
currentMessage: { role: 'user', content: 'now' },
tools: { z: {} },
model: 'claude-sonnet-4-6',
});
expect((out.messages[0] as { providerOptions: any }).providerOptions.anthropic.cacheControl.ttl).toBe('5m');
expect((out.messages[1] as { content: Array<{ providerOptions: any }> }).content[0].providerOptions.anthropic.cacheControl.ttl).toBe(
'5m',
);
expect((out.tools.z as { providerOptions: any }).providerOptions.anthropic.cacheControl.ttl).toBe('5m');
});
});
describe('splitKtxSystemMessages', () => {
it('returns undefined system when no system messages are present', () => {
const split = splitKtxSystemMessages([
{ role: 'user', content: 'hello' },
{ role: 'assistant', content: 'hi' },
]);
expect(split.system).toBeUndefined();
expect(split.messages).toHaveLength(2);
});
it('returns a single system message object when one system message is present, preserving providerOptions', () => {
const systemMessage = {
role: 'system' as const,
content: 'You are helpful.',
providerOptions: { anthropic: { cacheControl: { type: 'ephemeral' } } },
};
const split = splitKtxSystemMessages([systemMessage, { role: 'user', content: 'hello' }]);
expect(split.system).toBe(systemMessage);
expect(split.messages).toEqual([{ role: 'user', content: 'hello' }]);
});
it('returns an array of system messages when multiple are present, in order', () => {
const split = splitKtxSystemMessages([
{ role: 'system', content: 'cached' },
{ role: 'system', content: 'fresh' },
{ role: 'user', content: 'hello' },
]);
expect(Array.isArray(split.system)).toBe(true);
expect(split.system).toHaveLength(2);
expect(split.messages).toEqual([{ role: 'user', content: 'hello' }]);
});
});