Files
ThothII/backend/test/catalog-description-generation.integration.test.ts
T

393 lines
15 KiB
TypeScript

import { spawnSync } from "node:child_process";
import { PostgreSqlContainer } from "@testcontainers/postgresql";
import { CamelCasePlugin, Kysely, PostgresDialect } from "kysely";
import { Pool } from "pg";
import { expect, test, vi } from "vitest";
import { buildApp } from "../src/app.js";
import type { DescriptionSourceSampler } from "../src/catalog/description-source-sampler.js";
import type { MetadataGenerationModels } from "../src/catalog/metadata-generation-models.js";
import { ModelCompletionProviderError, type ModelCompleter } from "../src/catalog/model-completer.js";
import { up as upDatabases } from "../src/catalog/migrations/001_workspace_databases.js";
import { up as upTables } from "../src/catalog/migrations/002_catalog_tables.js";
import { up as upSchemaSync } from "../src/catalog/migrations/003_catalog_schema_sync.js";
import { up as upDescriptionGeneration } from "../src/catalog/migrations/005_description_generation_runs.js";
import { up as upSensitiveDataFlag } from "../src/catalog/migrations/006_sensitive_data_flag.js";
import { up as upSensitiveSuggestionRuns } from "../src/catalog/migrations/007_sensitive_data_suggestion_runs.js";
import { up as upAiTokenUsage } from "../src/catalog/migrations/009_ai_token_usage.js";
import { up as upCanonicalModelIds } from "../src/catalog/migrations/010_canonical_model_ids.js";
import { KyselyCatalogRepository, type CatalogDatabase } from "../src/catalog/repository.js";
import { loadConfig } from "../src/config.js";
import type { WorkspaceRegistry } from "../src/workspaces/registry.js";
const dockerAvailable = spawnSync("docker", ["info"], { stdio: "ignore" }).status === 0;
async function terminalRun(app: ReturnType<typeof buildApp>, runId: string) {
for (let attempt = 0; attempt < 200; attempt += 1) {
const response = await app.inject({
method: "GET",
url: `/catalog/description-generation-runs/${runId}`,
});
const run = response.json();
if (["completed", "completed_with_errors", "cancelled", "failed", "interrupted"].includes(run.status)) {
return run;
}
await new Promise((resolve) => setTimeout(resolve, 5));
}
throw new Error(`Description Generation Run ${runId} did not finish`);
}
test.skipIf(!dockerAvailable)("Fastify persists Description Generation success and failure through PostgreSQL", async () => {
const container = await new PostgreSqlContainer("postgres:17.6-bookworm").start();
const db = new Kysely<CatalogDatabase>({
dialect: new PostgresDialect({ pool: new Pool({ connectionString: container.getConnectionUri() }) }),
plugins: [new CamelCasePlugin()],
});
let app: ReturnType<typeof buildApp> | undefined;
try {
await upDatabases(db);
await upTables(db);
await upSchemaSync(db);
await upSensitiveDataFlag(db);
await upDescriptionGeneration(db);
await upSensitiveSuggestionRuns(db);
await upAiTokenUsage(db);
await upCanonicalModelIds(db);
const repository = new KyselyCatalogRepository(db);
const database = await repository.create({
workspaceId: "psd-clinical",
engine: "postgres",
databaseName: "warehouse",
schema: "datawarehouse",
binding: { transport: "postgres_direct", host: "db.internal", port: 5432, username: "reader" },
});
await repository.applySchemaSync(database.id, database.version, "all", [], {
schemaVersion: 1,
capabilities: { tables: "available", columns: "available", relationships: "available" },
tables: [{ name: "patients", sourceComment: "Clinical patients" }],
columns: [
{
tableName: "patients",
name: "birth_date",
ordinalPosition: 1,
dataType: "date",
isNullable: true,
defaultExpression: null,
primaryKeyPosition: null,
sourceComment: "Patient date of birth",
},
{
tableName: "patients",
name: "status",
ordinalPosition: 2,
dataType: "text",
isNullable: true,
defaultExpression: null,
primaryKeyPosition: null,
sourceComment: "Patient status",
},
],
relationships: [],
});
const table = (await repository.listTables(database.id))[0]!;
const columns = await repository.listColumns(database.id, table.id);
const birthDate = columns.find((column) => column.name === "birth_date")!;
const status = columns.find((column) => column.name === "status")!;
const curatedTable = (await repository.updateTableMetadata(
database.id,
table.id,
table.version,
"Elenco curato dei pazienti.",
null,
))!;
const curatedStatus = (await repository.updateColumnMetadata(
database.id,
table.id,
status.id,
status.version,
"Stato curato del paziente.",
null,
))!;
let call = 0;
const modelCompleter: ModelCompleter = {
complete: vi.fn(async () => {
call += 1;
if (call === 1) {
return JSON.stringify({ results: [
{
targetId: birthDate.id,
outcome: "generated",
description: "Data di nascita del paziente.",
},
{ targetId: status.id, outcome: "non_generatable" },
] });
}
if (call === 2) {
return JSON.stringify({ results: [{
targetId: table.id,
outcome: "generated",
description: "Elenco dei pazienti e dei loro dati clinici.",
}] });
}
if (call === 5) {
return JSON.stringify({ results: [
{
targetId: birthDate.id,
outcome: "generated",
description: "Descrizione rigenerata della data di nascita.",
},
{
targetId: status.id,
outcome: "generated",
description: "Descrizione rigenerata dello stato.",
},
] });
}
if (call === 6) {
return JSON.stringify({ results: [{
targetId: table.id,
outcome: "generated",
description: "Descrizione rigenerata della tabella pazienti.",
}] });
}
if (call === 7) {
return JSON.stringify({ results: [{
targetId: birthDate.id,
outcome: "generated",
description: "Descrizione recuperata della data di nascita.",
}] });
}
throw new ModelCompletionProviderError();
}),
};
const models: MetadataGenerationModels = {
catalog: () => ({ models: [{ id: "openai/gpt-4.1-mini", label: "OpenAI Mini" }], default: "openai/gpt-4.1-mini" }),
resolve: () => ({
id: "openai/gpt-4.1-mini",
provider: "openai",
model: "gpt-4.1-mini",
apiKeyEnv: "OPENAI_API_KEY",
apiKey: "test-provider-secret",
}),
};
const registry = {
list: vi.fn(async () => []),
read: vi.fn(async () => ({
workspace: { workspace: { language: "it" } },
revision: {},
})),
} as unknown as WorkspaceRegistry;
const persistedSampleSecret = "POSTGRES_TRANSIENT_SAMPLE_6a0d7b";
const descriptionSourceSampler: DescriptionSourceSampler = {
sample: vi.fn(async (_database, targets) => targets.map((target) => ({
targetId: target.targetId,
tableName: target.tableName,
rows: [{
fields: target.columnNames.slice(0, 1).map((name) => ({
name,
value: persistedSampleSecret,
})),
}],
representativeValues: target.columnNames.slice(0, 1).map((column) => ({
column,
values: [persistedSampleSecret],
})),
}))),
};
app = buildApp(loadConfig({ NODE_ENV: "test", THT_HARNESS_DIR: "/missing" }), {
thtRunner: {} as never,
workspaceRegistry: registry,
workspaceDiagnoser: vi.fn(),
catalogRepository: repository,
metadataGenerationModels: models,
modelCompleter,
descriptionSourceSampler,
});
const successfulStart = await app.inject({
method: "POST",
url: `/catalog/databases/${database.id}/description-generation-runs`,
payload: {
modelId: "openai/gpt-4.1-mini",
scope: "selected_columns",
targetIds: [status.id, birthDate.id],
},
});
expect(successfulStart.statusCode, successfulStart.body).toBe(202);
expect(await terminalRun(app, successfulStart.json().id)).toMatchObject({
status: "completed",
total: 2,
processed: 2,
generated: 1,
nonGeneratable: 1,
failed: 0,
});
expect(await repository.getColumn(database.id, table.id, birthDate.id)).toMatchObject({
generatedDescription: "Data di nascita del paziente.",
version: birthDate.version + 1,
});
const generatedStatus = (await repository.getColumn(database.id, table.id, status.id))!;
expect(generatedStatus).toMatchObject({
description: "Stato curato del paziente.",
generatedDescription: "Non generabile",
version: curatedStatus.version + 1,
});
const tableStart = await app.inject({
method: "POST",
url: `/catalog/databases/${database.id}/description-generation-runs`,
payload: { modelId: "openai/gpt-4.1-mini", scope: "selected_tables", targetIds: [table.id] },
});
expect(tableStart.statusCode).toBe(202);
expect(await terminalRun(app, tableStart.json().id)).toMatchObject({
scope: "selected_tables",
status: "completed",
processed: 1,
generated: 1,
nonGeneratable: 0,
failed: 0,
});
expect(await repository.getTable(database.id, table.id)).toMatchObject({
description: "Elenco curato dei pazienti.",
generatedDescription: "Elenco dei pazienti e dei loro dati clinici.",
version: curatedTable.version + 1,
});
const failedStart = await app.inject({
method: "POST",
url: `/catalog/databases/${database.id}/description-generation-runs`,
payload: { modelId: "openai/gpt-4.1-mini", scope: "selected_columns", targetIds: [status.id] },
});
expect(failedStart.statusCode).toBe(202);
const failedRun = await terminalRun(app, failedStart.json().id);
expect(failedRun).toMatchObject({
status: "completed_with_errors",
processed: 1,
generated: 0,
failed: 1,
errorSummary: "Description generation completed with errors.",
});
expect(await repository.getColumn(database.id, table.id, status.id)).toMatchObject({
description: "Stato curato del paziente.",
generatedDescription: "Non generabile",
version: generatedStatus.version,
});
const events = await app.inject({
method: "GET",
url: `/catalog/description-generation-runs/${failedRun.id}/events-list`,
});
expect(events.statusCode).toBe(200);
expect(events.json().find((event: { level: string }) => event.level === "error")).toEqual(expect.objectContaining({
level: "error",
message: `The model provider request failed. Affected Catalog Column target: ${status.id}.`,
}));
expect(events.body).not.toMatch(/test-provider-secret|gpt-4\.1-mini|raw provider/i);
const allStart = await app.inject({
method: "POST",
url: `/catalog/databases/${database.id}/description-generation-runs`,
payload: { modelId: "openai/gpt-4.1-mini", scope: "all" },
});
expect(allStart.statusCode).toBe(202);
const allRun = await terminalRun(app, allStart.json().id);
expect(allRun).toMatchObject({
scope: "all",
status: "completed",
total: 3,
processed: 3,
generated: 3,
nonGeneratable: 0,
failed: 0,
});
expect(await repository.getColumn(database.id, table.id, birthDate.id)).toMatchObject({
generatedDescription: "Descrizione rigenerata della data di nascita.",
});
expect(await repository.getColumn(database.id, table.id, status.id)).toMatchObject({
generatedDescription: "Descrizione rigenerata dello stato.",
});
expect(await repository.getTable(database.id, table.id)).toMatchObject({
generatedDescription: "Descrizione rigenerata della tabella pazienti.",
});
const allEvents = await app.inject({
method: "GET",
url: `/catalog/description-generation-runs/${allRun.id}/events-list`,
});
expect(allEvents.json()[0]).toEqual(expect.objectContaining({
message: "Description generation queued (scope: all).",
}));
const regeneratedBirthDate = (await repository.getColumn(
database.id, table.id, birthDate.id,
))!;
await repository.updateColumnMetadata(
database.id,
table.id,
birthDate.id,
regeneratedBirthDate.version,
regeneratedBirthDate.description,
" ",
);
const missingStart = await app.inject({
method: "POST",
url: `/catalog/databases/${database.id}/description-generation-runs`,
payload: { modelId: "openai/gpt-4.1-mini", scope: "missing" },
});
expect(missingStart.statusCode).toBe(202);
expect(await terminalRun(app, missingStart.json().id)).toMatchObject({
scope: "missing",
status: "completed",
total: 1,
processed: 1,
generated: 1,
nonGeneratable: 0,
failed: 0,
});
expect(await repository.getColumn(database.id, table.id, birthDate.id)).toMatchObject({
generatedDescription: "Descrizione recuperata della data di nascita.",
});
expect(modelCompleter.complete).toHaveBeenCalledTimes(7);
expect(JSON.stringify(vi.mocked(modelCompleter.complete).mock.calls)).toContain(persistedSampleSecret);
const runIds = [
successfulStart.json().id,
tableStart.json().id,
failedStart.json().id,
allStart.json().id,
missingStart.json().id,
];
const durableState = JSON.stringify({
runs: await Promise.all(runIds.map(async (runId) => (
await repository.getDescriptionGenerationRun(runId)
))),
events: await Promise.all(runIds.map(async (runId) => (
await repository.listDescriptionGenerationEvents(runId)
))),
database: await repository.get(database.id),
table: await repository.getTable(database.id, table.id),
columns: await repository.listColumns(database.id, table.id),
});
expect(durableState).not.toContain(persistedSampleSecret);
const apiResponses = await Promise.all([
...runIds.flatMap((runId) => [
app!.inject({ method: "GET", url: `/catalog/description-generation-runs/${runId}` }),
app!.inject({
method: "GET",
url: `/catalog/description-generation-runs/${runId}/events-list`,
}),
]),
app.inject({ method: "GET", url: `/catalog/databases/${database.id}` }),
app.inject({ method: "GET", url: `/catalog/databases/${database.id}/tables` }),
app.inject({
method: "GET",
url: `/catalog/databases/${database.id}/tables/${table.id}/columns`,
}),
]);
expect(apiResponses.map((response) => response.body).join("\n")).not.toContain(
persistedSampleSecret,
);
} finally {
if (app) await app.close();
await db.destroy();
await container.stop();
}
}, 60_000);