ktx/packages/cli/src/managed-python-http.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

194 lines
6.7 KiB
TypeScript

import { request as httpRequest } from 'node:http';
import { request as httpsRequest } from 'node:https';
import { URL } from 'node:url';
import { createDaemonLookerTableIdentifierParser, type KtxDaemonTableIdentifierHttpJsonRunner } from './context/ingest/adapters/looker/daemon-table-identifier-parser.js';
import type { DaemonLiveDatabaseIntrospectionOptions, KtxDaemonDatabaseHttpJsonRunner } from './context/ingest/adapters/live-database/daemon-introspection.js';
import type { LookerTableIdentifierParser } from './context/ingest/adapters/looker/mapping.js';
import { createHttpSqlAnalysisPort, type KtxSqlAnalysisHttpJsonRunner } from './context/sql-analysis/http-sql-analysis-port.js';
import type { SqlAnalysisPort } from './context/sql-analysis/ports.js';
import type { KtxCliIo } from './cli-runtime.js';
import { writePrefixedLines } from './clack.js';
import {
ensureManagedPythonCommandRuntime,
type KtxManagedPythonInstallPolicy,
type ManagedPythonCommandRuntime,
} from './managed-python-command.js';
import { startManagedPythonDaemon, type ManagedPythonDaemonStartResult } from './managed-python-daemon.js';
/** @internal */
export type ManagedPythonHttpJsonRunner = (
path: string,
payload: Record<string, unknown>,
) => Promise<Record<string, unknown>>;
type ManagedPythonHttpPostJson = (
baseUrl: string,
path: string,
payload: Record<string, unknown>,
) => Promise<Record<string, unknown>>;
export interface ManagedPythonCoreDaemonOptions {
cliVersion: string;
projectDir: string;
installPolicy: KtxManagedPythonInstallPolicy;
io: KtxCliIo;
ensureRuntime?: (options: {
cliVersion: string;
installPolicy: KtxManagedPythonInstallPolicy;
io: KtxCliIo;
feature: 'core';
}) => Promise<ManagedPythonCommandRuntime>;
startDaemon?: (options: {
cliVersion: string;
projectDir: string;
features: ['core'];
force: false;
}) => Promise<ManagedPythonDaemonStartResult>;
}
export type ManagedPythonDaemonHttpOptions =
| {
requestJson: ManagedPythonHttpJsonRunner;
}
| {
resolveBaseUrl: () => Promise<string>;
postJson?: ManagedPythonHttpPostJson;
}
| (ManagedPythonCoreDaemonOptions & {
postJson?: ManagedPythonHttpPostJson;
});
function normalizedBaseUrl(baseUrl: string): string {
return baseUrl.endsWith('/') ? baseUrl : `${baseUrl}/`;
}
function parseJsonObject(raw: string, path: string): Record<string, unknown> {
const parsed = JSON.parse(raw) as unknown;
if (!parsed || typeof parsed !== 'object' || Array.isArray(parsed)) {
throw new Error(`KTX daemon HTTP ${path} returned non-object JSON`);
}
return parsed as Record<string, unknown>;
}
async function postManagedDaemonJson(
baseUrl: string,
path: string,
payload: Record<string, unknown>,
): Promise<Record<string, unknown>> {
return await new Promise((resolve, reject) => {
const target = new URL(path.replace(/^\//, ''), normalizedBaseUrl(baseUrl));
const body = JSON.stringify(payload);
const client = target.protocol === 'https:' ? httpsRequest : httpRequest;
const request = client(
target,
{
method: 'POST',
headers: {
accept: 'application/json',
'content-type': 'application/json',
'content-length': Buffer.byteLength(body),
},
},
(response) => {
const chunks: Buffer[] = [];
response.on('data', (chunk: Buffer) => chunks.push(chunk));
response.on('end', () => {
const text = Buffer.concat(chunks).toString('utf8');
const statusCode = response.statusCode ?? 0;
if (statusCode < 200 || statusCode >= 300) {
reject(new Error(`KTX daemon HTTP ${path} failed with ${statusCode}: ${text}`));
return;
}
try {
resolve(parseJsonObject(text, path));
} catch (error) {
reject(error);
}
});
},
);
request.on('error', reject);
request.end(body);
});
}
/** @internal */
export function createManagedPythonDaemonBaseUrlResolver(
options: ManagedPythonCoreDaemonOptions,
): () => Promise<string> {
let cachedBaseUrl: string | undefined;
return async () => {
if (cachedBaseUrl) {
return cachedBaseUrl;
}
const ensureRuntime = options.ensureRuntime ?? ensureManagedPythonCommandRuntime;
const startDaemon = options.startDaemon ?? startManagedPythonDaemon;
await ensureRuntime({
cliVersion: options.cliVersion,
installPolicy: options.installPolicy,
io: options.io,
feature: 'core',
});
const daemon = await startDaemon({
cliVersion: options.cliVersion,
projectDir: options.projectDir,
features: ['core'],
force: false,
});
const verb = daemon.status === 'started' ? 'Started' : 'Using existing';
writePrefixedLines((chunk) => options.io.stderr.write(chunk), `${verb} KTX daemon: ${daemon.baseUrl}`);
cachedBaseUrl = daemon.baseUrl;
return cachedBaseUrl;
};
}
function isRequestJsonOnly(options: ManagedPythonDaemonHttpOptions): options is { requestJson: ManagedPythonHttpJsonRunner } {
return 'requestJson' in options;
}
function isResolveBaseUrlOnly(
options: ManagedPythonDaemonHttpOptions,
): options is { resolveBaseUrl: () => Promise<string>; postJson?: ManagedPythonHttpPostJson } {
return 'resolveBaseUrl' in options;
}
/** @internal */
export function createManagedDaemonHttpJsonRunner(
options: ManagedPythonDaemonHttpOptions,
): ManagedPythonHttpJsonRunner {
if (isRequestJsonOnly(options)) {
return options.requestJson;
}
const resolveBaseUrl = isResolveBaseUrlOnly(options)
? options.resolveBaseUrl
: createManagedPythonDaemonBaseUrlResolver(options);
const postJson = options.postJson ?? postManagedDaemonJson;
return async (path, payload) => postJson(await resolveBaseUrl(), path, payload);
}
export function createManagedDaemonLookerTableIdentifierParser(
options: ManagedPythonDaemonHttpOptions,
): LookerTableIdentifierParser {
return createDaemonLookerTableIdentifierParser({
baseUrl: 'http://127.0.0.1:0',
requestJson: createManagedDaemonHttpJsonRunner(options) as KtxDaemonTableIdentifierHttpJsonRunner,
});
}
export function createManagedDaemonSqlAnalysisPort(options: ManagedPythonDaemonHttpOptions): SqlAnalysisPort {
return createHttpSqlAnalysisPort({
baseUrl: 'http://127.0.0.1:0',
requestJson: createManagedDaemonHttpJsonRunner(options) as KtxSqlAnalysisHttpJsonRunner,
});
}
export function managedDaemonDatabaseIntrospectionOptions(
options: ManagedPythonDaemonHttpOptions,
): Pick<DaemonLiveDatabaseIntrospectionOptions, 'requestJson'> {
return {
requestJson: createManagedDaemonHttpJsonRunner(options) as KtxDaemonDatabaseHttpJsonRunner,
};
}