ktx/packages/cli/test/llm/model-provider.test.ts

325 lines
12 KiB
TypeScript
Raw Permalink Normal View History

import { devToolsMiddleware as defaultDevToolsMiddleware } from '@ai-sdk/devtools';
import { wrapLanguageModel as defaultWrapLanguageModel, type LanguageModel } from 'ai';
2026-05-10 23:12:26 +02:00
import { 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 { createKtxLlmProvider, type KtxLlmProviderFactoryDeps } from '../../src/llm/model-provider.js';
2026-05-10 23:12:26 +02:00
const languageModel = (modelId: string, provider = 'test'): LanguageModel => ({ modelId, provider }) as LanguageModel;
const devtoolsMiddleware = (): ReturnType<typeof defaultDevToolsMiddleware> => ({ specificationVersion: 'v3' });
const wrapWith = (model: LanguageModel) =>
vi.fn((_options: Parameters<typeof defaultWrapLanguageModel>[0]) => model as ReturnType<typeof defaultWrapLanguageModel>);
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
describe('createKtxLlmProvider', () => {
it('wraps language models with DevTools middleware when explicitly enabled', () => {
const anthropicModel = languageModel('claude-sonnet-4-6', 'anthropic');
const wrappedModel = languageModel('claude-sonnet-4-6', 'anthropic-devtools');
const middleware = devtoolsMiddleware();
const wrapLanguageModel = wrapWith(wrappedModel);
const devToolsMiddleware = vi.fn(devtoolsMiddleware);
const provider = createKtxLlmProvider(
{
backend: 'anthropic',
anthropic: { apiKey: 'test-anthropic-key' }, // pragma: allowlist secret
modelSlots: { default: 'claude-sonnet-4-6' },
promptCaching: { enabled: false },
},
{
createAnthropic: vi.fn(() => vi.fn(() => anthropicModel)),
devtoolsEnabled: true,
wrapLanguageModel,
devToolsMiddleware,
} satisfies KtxLlmProviderFactoryDeps,
);
expect(provider.getModel('default')).toBe(wrappedModel);
expect(devToolsMiddleware).toHaveBeenCalledTimes(1);
expect(wrapLanguageModel).toHaveBeenCalledWith({
model: anthropicModel,
middleware,
modelId: 'claude-sonnet-4-6',
providerId: 'anthropic',
});
});
it('does not wrap language models by default', () => {
const anthropicModel = languageModel('claude-sonnet-4-6', 'anthropic');
const wrapLanguageModel = vi.fn(defaultWrapLanguageModel);
const devToolsMiddleware = vi.fn(defaultDevToolsMiddleware);
const provider = createKtxLlmProvider(
{
backend: 'anthropic',
anthropic: { apiKey: 'test-anthropic-key' }, // pragma: allowlist secret
modelSlots: { default: 'claude-sonnet-4-6' },
promptCaching: { enabled: false },
},
{
createAnthropic: vi.fn(() => vi.fn(() => anthropicModel)),
devtoolsEnabled: false,
wrapLanguageModel,
devToolsMiddleware,
} satisfies KtxLlmProviderFactoryDeps,
);
expect(provider.getModel('default')).toBe(anthropicModel);
expect(wrapLanguageModel).not.toHaveBeenCalled();
expect(devToolsMiddleware).not.toHaveBeenCalled();
});
it('wraps language models when KTX_AI_DEVTOOLS_ENABLED is true', () => {
const originalEnv = process.env.KTX_AI_DEVTOOLS_ENABLED;
process.env.KTX_AI_DEVTOOLS_ENABLED = 'true';
try {
const gatewayModel = languageModel('anthropic/claude-sonnet-4-6', 'gateway');
const wrappedModel = languageModel('anthropic/claude-sonnet-4-6', 'gateway-devtools');
const wrapLanguageModel = wrapWith(wrappedModel);
const provider = createKtxLlmProvider(
{
backend: 'gateway',
gateway: { baseURL: 'https://gateway.test/v1' },
modelSlots: { default: 'anthropic/claude-sonnet-4-6' },
promptCaching: { enabled: false },
},
{
createGateway: vi.fn(() => vi.fn(() => gatewayModel)),
wrapLanguageModel,
devToolsMiddleware: vi.fn(devtoolsMiddleware),
} satisfies KtxLlmProviderFactoryDeps,
);
expect(provider.getModel('default')).toBe(wrappedModel);
expect(wrapLanguageModel).toHaveBeenCalledTimes(1);
} finally {
if (originalEnv === undefined) {
delete process.env.KTX_AI_DEVTOOLS_ENABLED;
} else {
process.env.KTX_AI_DEVTOOLS_ENABLED = originalEnv;
}
}
});
it('does not wrap language models in production even when enabled', () => {
const originalNodeEnv = process.env.NODE_ENV;
process.env.NODE_ENV = 'production';
try {
const anthropicModel = languageModel('claude-sonnet-4-6', 'anthropic');
const wrapLanguageModel = vi.fn(defaultWrapLanguageModel);
const devToolsMiddleware = vi.fn(defaultDevToolsMiddleware);
const provider = createKtxLlmProvider(
{
backend: 'anthropic',
anthropic: { apiKey: 'test-anthropic-key' }, // pragma: allowlist secret
modelSlots: { default: 'claude-sonnet-4-6' },
promptCaching: { enabled: false },
},
{
createAnthropic: vi.fn(() => vi.fn(() => anthropicModel)),
devtoolsEnabled: true,
wrapLanguageModel,
devToolsMiddleware,
} satisfies KtxLlmProviderFactoryDeps,
);
expect(provider.getModel('default')).toBe(anthropicModel);
expect(wrapLanguageModel).not.toHaveBeenCalled();
expect(devToolsMiddleware).not.toHaveBeenCalled();
} finally {
if (originalNodeEnv === undefined) {
delete process.env.NODE_ENV;
} else {
process.env.NODE_ENV = originalNodeEnv;
}
}
});
2026-05-10 23:12:26 +02:00
it('uses direct Anthropic with both beta headers', () => {
const anthropicModel = languageModel('claude-sonnet-4-6', 'anthropic');
const anthropic = vi.fn(() => anthropicModel);
const createAnthropic = vi.fn(() => anthropic);
2026-05-10 23:51:24 +02:00
const provider = createKtxLlmProvider(
2026-05-10 23:12:26 +02:00
{
backend: 'anthropic',
anthropic: { apiKey: 'test-anthropic-key', baseURL: 'https://anthropic.test' }, // pragma: allowlist secret
modelSlots: { default: 'claude-sonnet-4-6' },
promptCaching: { enabled: false },
},
{ createAnthropic, devtoolsEnabled: false },
2026-05-10 23:12:26 +02:00
);
expect(provider.getModel('default')).toBe(anthropicModel);
expect(createAnthropic).toHaveBeenCalledWith({
apiKey: 'test-anthropic-key', // pragma: allowlist secret
baseURL: 'https://anthropic.test',
headers: {
'anthropic-beta': 'interleaved-thinking-2025-05-14,extended-cache-ttl-2025-04-11',
},
});
expect(anthropic).toHaveBeenCalledWith('claude-sonnet-4-6');
});
it('uses Vertex Anthropic without the direct-Anthropic beta header', () => {
const vertexModel = languageModel('claude-sonnet-4-6', 'vertex');
const vertex = vi.fn(() => vertexModel);
const createVertexAnthropic = vi.fn(() => vertex);
2026-05-10 23:51:24 +02:00
const provider = createKtxLlmProvider(
2026-05-10 23:12:26 +02:00
{
backend: 'vertex',
2026-05-10 23:51:24 +02:00
vertex: { project: 'ktx-test', location: 'us-east5' },
2026-05-10 23:12:26 +02:00
modelSlots: { default: 'claude-sonnet-4-6' },
promptCaching: { enabled: false },
},
{ createVertexAnthropic, devtoolsEnabled: false },
2026-05-10 23:12:26 +02:00
);
expect(provider.getModel('default')).toBe(vertexModel);
2026-05-10 23:51:24 +02:00
expect(createVertexAnthropic).toHaveBeenCalledWith({ project: 'ktx-test', location: 'us-east5' });
2026-05-10 23:12:26 +02:00
expect(vertex).toHaveBeenCalledWith('claude-sonnet-4-6');
});
it('uses Gateway and supports role fallback to default', () => {
const gatewayModel = languageModel('anthropic/claude-sonnet-4-6', 'gateway');
const gateway = vi.fn(() => gatewayModel);
const createGateway = vi.fn(() => gateway);
2026-05-10 23:51:24 +02:00
const provider = createKtxLlmProvider(
2026-05-10 23:12:26 +02:00
{
backend: 'gateway',
gateway: { apiKey: 'gateway-key', baseURL: 'https://gateway.test/v1' }, // pragma: allowlist secret
modelSlots: { default: 'anthropic/claude-sonnet-4-6' },
promptCaching: { enabled: false },
},
{ createGateway, devtoolsEnabled: false },
2026-05-10 23:12:26 +02:00
);
expect(provider.getModel('curator')).toBe(gatewayModel);
expect(createGateway).toHaveBeenCalledWith({
apiKey: 'gateway-key', // pragma: allowlist secret
baseURL: 'https://gateway.test/v1',
headers: {
'anthropic-beta': 'interleaved-thinking-2025-05-14,extended-cache-ttl-2025-04-11',
},
2026-05-10 23:12:26 +02:00
});
expect(gateway).toHaveBeenCalledWith('anthropic/claude-sonnet-4-6');
});
it('uses explicit role overrides before default', () => {
const anthropic = vi.fn((modelId: string) => languageModel(modelId, 'anthropic'));
2026-05-10 23:51:24 +02:00
const provider = createKtxLlmProvider(
2026-05-10 23:12:26 +02:00
{
backend: 'anthropic',
anthropic: { apiKey: 'test-anthropic-key' }, // pragma: allowlist secret
modelSlots: {
default: 'claude-sonnet-4-6',
triage: 'claude-haiku-4-5',
repair: 'claude-opus-4-7',
},
promptCaching: { enabled: false },
},
{ createAnthropic: vi.fn(() => anthropic) },
);
expect((provider.getModel('triage') as { modelId: string }).modelId).toBe('claude-haiku-4-5');
expect((provider.getModel('repair') as { modelId: string }).modelId).toBe('claude-opus-4-7');
expect((provider.getModel('reconcile') as { modelId: string }).modelId).toBe('claude-sonnet-4-6');
});
it('emits cache markers only when enabled and the model speaks Anthropic protocol', () => {
2026-05-10 23:51:24 +02:00
const provider = createKtxLlmProvider(
2026-05-10 23:12:26 +02:00
{
backend: 'gateway',
gateway: { baseURL: 'https://gateway.test/v1' },
modelSlots: { default: 'anthropic/claude-sonnet-4-6' },
promptCaching: { enabled: true },
},
{ createGateway: vi.fn(() => vi.fn((modelId: string) => languageModel(modelId, 'gateway'))) },
);
expect(provider.cacheMarker('1h', 'anthropic/claude-sonnet-4-6')).toEqual({
anthropic: { cacheControl: { type: 'ephemeral', ttl: '1h' } },
});
expect(provider.cacheMarker('1h', 'gpt-5')).toBeUndefined();
});
it('returns Anthropic thinking provider options', () => {
2026-05-10 23:51:24 +02:00
const provider = createKtxLlmProvider(
2026-05-10 23:12:26 +02:00
{
backend: 'anthropic',
anthropic: { apiKey: 'test-anthropic-key' }, // pragma: allowlist secret
modelSlots: { default: 'claude-sonnet-4-6' },
promptCaching: { enabled: false },
},
{ createAnthropic: vi.fn(() => vi.fn((modelId: string) => languageModel(modelId, 'anthropic'))) },
);
expect(provider.thinkingProviderOptions('default', 12000)).toEqual({
anthropic: {
thinking: { type: 'enabled', budgetTokens: 12000 },
},
});
});
it('defaults prompt caching to enabled with canonical TTLs', () => {
2026-05-10 23:51:24 +02:00
const provider = createKtxLlmProvider(
2026-05-10 23:12:26 +02:00
{
backend: 'gateway',
gateway: { baseURL: 'https://gateway.test/v1' },
modelSlots: { default: 'anthropic/claude-sonnet-4-6' },
},
{ createGateway: vi.fn(() => vi.fn((modelId: string) => languageModel(modelId, 'gateway'))) },
);
expect(provider.promptCachingConfig()).toEqual({
enabled: true,
systemTtl: '1h',
toolsTtl: '1h',
historyTtl: '5m',
cacheSystem: true,
cacheTools: true,
cacheHistory: true,
vertexFallbackTo5m: false,
});
expect(provider.cacheMarker('1h', 'anthropic/claude-sonnet-4-6')).toEqual({
anthropic: { cacheControl: { type: 'ephemeral', ttl: '1h' } },
});
});
it('preserves explicit prompt caching opt-out', () => {
2026-05-10 23:51:24 +02:00
const provider = createKtxLlmProvider(
2026-05-10 23:12:26 +02:00
{
backend: 'anthropic',
anthropic: { apiKey: 'test-anthropic-key' }, // pragma: allowlist secret
modelSlots: { default: 'claude-sonnet-4-6' },
promptCaching: { enabled: false },
},
{ createAnthropic: vi.fn(() => vi.fn((modelId: string) => languageModel(modelId, 'anthropic'))) },
);
expect(provider.promptCachingConfig().enabled).toBe(false);
expect(provider.cacheMarker('1h', 'claude-sonnet-4-6')).toBeUndefined();
});
feat: add claude-code llm backend with runtime port (#115) * docs: revise claude-code ingest backend spec * docs: keep claude-code spec focused on ingest * docs: expand claude-code spec to full llm parity * Refine claude-code backend spec after adversarial review iteration 1 * Refine claude-code backend spec after adversarial review iteration 2 * Refine claude-code backend spec after adversarial review iteration 3 * feat: recognize claude-code llm backend * feat: add ktx llm runtime port * feat: add claude-code llm runtime * feat: route non-agent llm calls through runtime * feat: run ingest agents through llm runtime * feat: support claude-code setup and status * test: verify claude-code backend runtime * docs: add claude-code backend v1 runtime plan * fix: close claude-code runtime isolation checks * fix: warn on claude-code prompt caching during setup * chore: verify claude-code v1 closure * docs: add claude-code backend v1 isolation closure plan * fix: update claude-code ingest setup guidance * docs: add claude-code backend v1 ingest guidance closure plan * docs: align claude-code isolation spec with sdk metadata * test: cover claude-code host discovery metadata * fix: tolerate claude-code host discovery metadata * docs: clarify claude-code host discovery metadata * docs: add claude-code auth-probe isolation fix plan * chore: prepare kaelio ktx rc1 release * chore: add semantic release workflow * fix: unblock ci checks * chore(release): 0.1.0-rc.1 * feat: add Claude Code model selection to setup * fix: keep git maintenance attached in local repos
2026-05-16 12:06:34 +02:00
it('throws instead of falling through when an unsupported LLM backend is passed to the AI SDK provider factory', () => {
expect(() =>
createKtxLlmProvider({
backend: 'claude-code',
modelSlots: { default: 'sonnet' },
promptCaching: { enabled: false },
}),
).toThrow('claude-code is not an AI SDK LanguageModel backend');
});
feat: add codex llm backend for ktx runtime work (#253) * feat: add codex sdk runner foundation * feat: parse codex runtime events * feat: expose codex runtime mcp tools * feat: add codex llm runtime * feat: wire codex llm backend * test: avoid Array.fromAsync in codex runner test * docs: document codex llm backend * fix: tighten codex runtime config ownership * fix: use codex sdk env and thread options * fix: parse codex sdk event shapes * test: add codex backend live smoke * docs: clarify codex backend isolation * fix: drive codex loop metrics from mcp events * fix: enforce codex local step budget * docs: disclose codex isolation limits * fix: count all codex agent steps and stream step callbacks live The agent-loop step budget only counted completed mcp_tool_call items, so built-in command_execution steps (which the public Codex SDK/CLI surface can still expose) never decremented the budget, letting ingest/reconciliation run past stepBudget until Codex stopped on its own. onStepFinish was also replayed only after the whole stream drained, so live work_unit_step / reconciliation progress appeared stuck until the Codex process exited. collectEvents is now the single live step accumulator: it counts every completed agent-action item via a shared isCompletedAgentStep predicate (command_execution, mcp_tool_call, file_change, web_search), fires onStepFinish as each step completes, and enforces the budget on that broader count. A no-tool turn still counts as one step. toolFailures stays MCP-specific, since a non-zero command exit is normal agent exploration, not a loop failure. * test: align ingest llm-guard assertions with codex backend The skip-llm ingest guard message now lists codex as a valid backend and mentions a Claude Code/Codex session plus a codex setup hint, but this slow suite test still asserted the pre-codex wording. Update it to match the production message (already covered by the local-bundle-runtime unit test) and add the codex setup-line assertion. * fix: treat codex error:null tool calls as success The Codex SDK serializes error: null on successful mcp_tool_call items, so the failure check (item.error !== undefined) flagged every successful tool call as failed with the empty-payload default "Codex turn failed". This killed every ingest work unit under the codex backend before it could produce a patch. Key on status === 'failed' (authoritative, always set) and only treat a populated error object as a failure. Add a regression test built from a verbatim real-SDK event capture. * fix: default codex backend to gpt-5.5 and report real probe errors The previous default gpt-5.3-codex is an API-key-only model that the OpenAI API rejects under ChatGPT-account (subscription) auth, so codex status/setup failed with a misleading "authentication is not usable" message even though auth was fine. - Default codex model is now gpt-5.5 (works on both subscription and API-key auth); the curated setup picker offers gpt-5.5 / gpt-5.4 / gpt-5.4-mini and keeps free-form entry for account-specific ids (e.g. gpt-5.3-codex-spark). - runCodexAuthProbe now distinguishes "model not available" from an auth failure and surfaces the real API error: collectEvents retains stream events when the SDK throws on a non-zero exit, and the API error JSON envelope is unwrapped to its human-readable message. - The Codex isolation warning now renders inside the clack setup frame. - Docs updated to gpt-5.5 with a note that *-codex ids require API-key auth. * fix: require llm.models.default in status and match codex probe remediation Status reported a project ready when a non-none LLM backend was configured without llm.models.default, but the runtime (resolveModelSlots) hard-requires it, so ingest/scan/memory threw after `ktx status` said the project was usable. buildLlmStatus now fails for any non-none backend missing models.default and no longer invents a fallback model for claude-code/codex. Codex probe failures now carry a category-matched fix: a model-access failure steers the user at llm.models.default instead of the auth/install remediation. runCodexAuthProbe returns the fix and status consumes it; the message stays self-sufficient so setup output is unchanged. Docs: README now lists the codex backend and local Codex auth; ktx-setup.mdx states --llm-model only accepts codex/default or gpt-*/codex-* ids. Repaired four doctor fixtures that configured a backend without models.default (the now-correctly-blocked config) and added coverage for the new behavior.
2026-06-02 13:57:11 +02:00
it('rejects codex as an AI SDK LanguageModel backend', () => {
expect(() =>
createKtxLlmProvider({
backend: 'codex',
modelSlots: { default: 'gpt-5.3-codex' },
}),
).toThrow('codex is not an AI SDK LanguageModel backend');
});
2026-05-10 23:12:26 +02:00
});