feat: protect sensitive catalog samples

This commit is contained in:
Codex
2026-08-30 12:14:23 +02:00
parent 6278ee9d81
commit 0736983bc5
28 changed files with 1162 additions and 128 deletions
@@ -141,6 +141,83 @@ async function waitForTerminalRun(app: ReturnType<typeof buildApp>, runId: strin
throw new Error(`Description Generation Run ${runId} did not finish`);
}
test("suggests sensitive flags from structural metadata without persisting them", async () => {
const modelCompleter = {
complete: vi.fn(async () => JSON.stringify({
suggestions: [{ columnId: expect.any(String), sensitive: true }],
})),
};
const { app, repository, database, column } = await setup(modelCompleter);
modelCompleter.complete.mockResolvedValueOnce(JSON.stringify({
suggestions: [{ columnId: column.id, sensitive: true }],
}));
try {
const response = await app.inject({
method: "POST",
url: `/catalog/databases/${database.id}/sensitive-data-suggestions`,
payload: { modelId: configuredModel.id },
});
expect(response.statusCode).toBe(200);
expect(response.json()).toEqual({
suggestions: [{ columnId: column.id, sensitive: true }],
});
expect(await repository.getColumn(database.id, column.tableId, column.id))
.toMatchObject({ sensitive: false });
const request = modelCompleter.complete.mock.calls[0]![0] as ModelCompletionRequest;
const prompt = request.messages.map((message) => message.content).join("\n");
expect(prompt).toContain("patients");
expect(prompt).toContain("birth_date");
expect(prompt).toContain("date");
expect(prompt).not.toContain("Patient date of birth");
expect(prompt).not.toContain("test-provider-secret");
} finally {
await app.close();
}
});
test.each(["malformed", "incomplete", "duplicate"] as const)(
"fails safely when sensitive-data suggestions are %s",
async (kind) => {
const modelCompleter: ModelCompleter = {
complete: vi.fn(async () => "unused"),
};
const { app, repository, database, column } = await setup(modelCompleter);
const rawResponse = kind === "malformed"
? "RAW_PROVIDER_RESPONSE_DO_NOT_EXPOSE_{"
: kind === "incomplete"
? JSON.stringify({ suggestions: [] })
: JSON.stringify({
suggestions: [
{ columnId: column.id, sensitive: true },
{ columnId: column.id, sensitive: true },
],
});
vi.mocked(modelCompleter.complete).mockResolvedValueOnce(rawResponse);
try {
const response = await app.inject({
method: "POST",
url: `/catalog/databases/${database.id}/sensitive-data-suggestions`,
payload: { modelId: configuredModel.id },
});
expect(response.statusCode).toBe(502);
expect(response.json()).toEqual({
code: "sensitive_data_suggestion_failed",
message: "Sensitive-data suggestions could not be prepared.",
});
expect(response.body).not.toContain(rawResponse);
expect(await repository.getColumn(database.id, column.tableId, column.id))
.toMatchObject({ sensitive: false });
} finally {
await app.close();
}
},
);
interface SseFrame {
id?: string;
event?: string;
@@ -398,6 +475,102 @@ test("keeps real source samples transient across the Fastify API and application
}
});
test("never exposes a protected source value to the model, persistence, logs, or browser APIs", async () => {
let selectedColumnId = "";
const protectedValue = "PROTECTED_SOURCE_VALUE_8f4c2a";
const modelCompleter: ModelCompleter = {
complete: vi.fn(async () => JSON.stringify({
results: [{
targetId: selectedColumnId,
outcome: "generated",
description: "Data di nascita del paziente.",
}],
})),
};
const descriptionSourceSampler: DescriptionSourceSampler = {
sample: vi.fn(async (_database, targets) => [{
targetId: targets[0]!.targetId,
tableName: targets[0]!.tableName,
rows: [{ fields: [{ name: "birth_date", value: protectedValue }] }],
representativeValues: [{ column: "birth_date", values: [protectedValue] }],
}]),
};
const { app, repository, database, table, column } = await setup(
modelCompleter,
{},
"it",
descriptionSourceSampler,
);
selectedColumnId = column.id;
await repository.updateColumnMetadata(
database.id,
table.id,
column.id,
column.version,
column.description,
column.generatedDescription,
true,
);
const logSpies = [
vi.spyOn(app.log, "info"),
vi.spyOn(app.log, "warn"),
vi.spyOn(app.log, "error"),
];
try {
const start = await app.inject({
method: "POST",
url: `/catalog/databases/${database.id}/description-generation-runs`,
payload: {
modelId: configuredModel.id,
scope: "selected_columns",
targetIds: [column.id],
},
});
expect(start.statusCode).toBe(202);
await waitForTerminalRun(app, start.json().id);
expect(descriptionSourceSampler.sample).toHaveBeenCalledWith(
expect.anything(),
[expect.objectContaining({ targetId: column.id, columnNames: [] })],
expect.any(AbortSignal),
);
const completionRequest = vi.mocked(modelCompleter.complete).mock.calls[0]![0];
const providerPayload = JSON.stringify(completionRequest.messages);
expect(providerPayload).not.toContain(protectedValue);
expect(providerPayload).toContain("1981-01-01");
const apiResponses = await Promise.all([
app.inject({ method: "GET", url: `/catalog/description-generation-runs/${start.json().id}` }),
app.inject({
method: "GET",
url: `/catalog/description-generation-runs/${start.json().id}/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.every((response) => response.statusCode === 200)).toBe(true);
expect(apiResponses.map((response) => response.body).join("\n")).not.toContain(protectedValue);
const persisted = JSON.stringify({
run: await repository.getDescriptionGenerationRun(start.json().id),
events: await repository.listDescriptionGenerationEvents(start.json().id),
database: await repository.get(database.id),
table: await repository.getTable(database.id, table.id),
column: await repository.getColumn(database.id, table.id, column.id),
});
expect(persisted).not.toContain(protectedValue);
expect(JSON.stringify(logSpies.flatMap((spy) => spy.mock.calls))).not.toContain(protectedValue);
} finally {
for (const spy of logSpies) spy.mockRestore();
await app.close();
}
});
test("wires the production sampler to the same injected CatalogPostgresAccess instance", async () => {
let selectedColumnId = "";
const sampleSecret = "PRODUCTION_WIRING_SAMPLE_f2986a";
@@ -222,7 +222,7 @@ test("adds only bounded transient source samples to the model request", async ()
tables: [{ name: "patients", sourceComment: null }],
columns: [{
tableName: "patients",
name: "status",
name: "patient_email",
ordinalPosition: 1,
dataType: "text",
isNullable: true,
@@ -243,9 +243,18 @@ test("adds only bounded transient source samples to the model request", async ()
});
const table = (await repository.listTables(database.id))[0]!;
const columns = await repository.listColumns(database.id, table.id);
const column = columns.find((candidate) => candidate.name === "status")!;
const column = columns.find((candidate) => candidate.name === "patient_email")!;
const ward = columns.find((candidate) => candidate.name === "ward")!;
const sampleSecret = "ONLY_IN_TRANSIENT_SAMPLE_7f29c8";
await repository.updateColumnMetadata(
database.id,
table.id,
column.id,
column.version,
column.description,
column.generatedDescription,
true,
);
const sampleSecret = "real.patient@hospital.invalid";
const sourceSampler: DescriptionSourceSampler = {
sample: vi.fn(async () => [{
targetId: column.id,
@@ -265,11 +274,14 @@ test("adds only bounded transient source samples to the model request", async ()
rows: [
{ fields: [{ name: ward.name, value: "row-4" }] },
{ fields: [{ name: ward.name, value: "row-5" }] },
{ fields: [{ name: ward.name, value: "row-6-must-be-omitted" }] },
{ fields: [{ name: ward.name, value: "row-6" }] },
{ fields: [{ name: ward.name, value: "row-7" }] },
{ fields: [{ name: ward.name, value: "row-8" }] },
{ fields: [{ name: ward.name, value: "row-9-must-be-omitted" }] },
],
representativeValues: [{
column: ward.name,
values: ["ward-1", "ward-2", "ward-3-must-be-omitted"],
values: ["ward-1", "ward-2", "ward-3", "ward-4", "ward-5", "ward-6-must-be-omitted"],
}],
}]),
};
@@ -321,7 +333,7 @@ test("adds only bounded transient source samples to the model request", async ()
expect(sourceSampler.sample).toHaveBeenCalledWith(
expect.objectContaining({ id: database.id, binding: database.binding }),
[
{ targetId: column.id, tableName: table.name, columnNames: [column.name] },
{ targetId: column.id, tableName: table.name, columnNames: [] },
{ targetId: ward.id, tableName: table.name, columnNames: [ward.name] },
],
expect.any(AbortSignal),
@@ -338,21 +350,29 @@ test("adds only bounded transient source samples to the model request", async ()
targetContext.sourceSample?.representativeValues.flatMap((entry) => entry.values) ?? []
),
);
expect(sampledRows).toHaveLength(5);
expect(representativeValues).toHaveLength(5);
expect(context.targets[0].sourceSample.rows).toHaveLength(3);
expect(context.targets[1].sourceSample.rows).toHaveLength(2);
expect(sampledRows).toHaveLength(10);
expect(representativeValues).toHaveLength(10);
expect(context.targets[0].sourceSample.rows).toHaveLength(5);
expect(context.targets[1].sourceSample.rows).toHaveLength(5);
expect(context.targets[0].sourceSample.representativeValues).toEqual([{
column: column.name,
values: [sampleSecret, "two", "three"],
values: [
"marta.rossi@example.com",
"luca.bianchi@example.com",
"elena.conti@example.com",
"paolo.romano@example.com",
"giulia.ferrari@example.com",
],
}]);
expect(context.targets[1].sourceSample.representativeValues).toEqual([{
column: ward.name,
values: ["ward-1", "ward-2"],
values: ["ward-1", "ward-2", "ward-3", "ward-4", "ward-5"],
}]);
expect(userMessage).toContain(sampleSecret);
expect(userMessage).not.toContain(sampleSecret);
expect(userMessage).not.toMatch(/synthetic|fake|fittizi/i);
expect(userMessage).toContain("marta.rossi@example.com");
expect(userMessage).not.toMatch(
/row-6-must-be-omitted|ward-3-must-be-omitted/,
/row-9-must-be-omitted|ward-6-must-be-omitted/,
);
const persisted = JSON.stringify({
@@ -366,6 +386,173 @@ test("adds only bounded transient source samples to the model request", async ()
expect(persisted).not.toContain(sampleSecret);
});
test("gives every sensitive column synthetic context without consuming the real sample budget", async () => {
const repository = new MemoryCatalogRepository();
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: null }],
columns: [{
tableName: "patients",
name: "patient_email",
ordinalPosition: 1,
dataType: "text",
isNullable: true,
defaultExpression: null,
primaryKeyPosition: null,
sourceComment: null,
}, {
tableName: "patients",
name: "patient_phone",
ordinalPosition: 2,
dataType: "text",
isNullable: true,
defaultExpression: null,
primaryKeyPosition: null,
sourceComment: null,
}, {
tableName: "patients",
name: "ward",
ordinalPosition: 3,
dataType: "text",
isNullable: true,
defaultExpression: null,
primaryKeyPosition: null,
sourceComment: null,
}],
relationships: [],
});
const table = (await repository.listTables(database.id))[0]!;
const columns = await repository.listColumns(database.id, table.id);
const email = columns.find((column) => column.name === "patient_email")!;
const phone = columns.find((column) => column.name === "patient_phone")!;
const ward = columns.find((column) => column.name === "ward")!;
for (const column of [email, phone]) {
await repository.updateColumnMetadata(
database.id,
table.id,
column.id,
column.version,
column.description,
column.generatedDescription,
true,
);
}
const wardValues = ["ward-a", "ward-b", "ward-c", "ward-d", "ward-e"];
const sourceSampler: DescriptionSourceSampler = {
sample: vi.fn(async (_database, targets) => targets.map((target) => {
if (target.columnNames.length === 0) {
return {
targetId: target.targetId,
tableName: target.tableName,
rows: [],
representativeValues: [],
};
}
const columnName = target.columnNames[0]!;
return {
targetId: target.targetId,
tableName: target.tableName,
rows: wardValues.map((value) => ({ fields: [{ name: columnName, value }] })),
representativeValues: [{ column: columnName, values: wardValues }],
};
})),
};
const completer: ModelCompleter = {
complete: vi.fn(async (request) => {
const context = JSON.parse(request.messages[1]!.content.split("\n").slice(1).join("\n"));
return JSON.stringify({
results: context.targets.map((target: { targetId: string }) => ({
targetId: target.targetId,
outcome: "generated",
description: "Descrizione generata.",
})),
});
}),
};
const models: MetadataGenerationModels = {
catalog: () => ({ models: [{ id: "openai-mini", label: "OpenAI Mini" }], default: "openai-mini" }),
resolve: () => ({
id: "openai-mini",
provider: "openai",
model: "gpt-4.1-mini",
apiKeyEnv: "OPENAI_API_KEY",
apiKey: "test-provider-secret",
}),
};
const worker = new DescriptionGenerationWorker(
repository,
{
read: vi.fn(async () => ({
workspace: { workspace: { language: "it" } },
revision: {},
})),
} as unknown as WorkspaceRegistry,
models,
completer,
new CatalogOperationCoordinator(),
sourceSampler,
);
const run = await worker.start(
database.id,
"openai-mini",
"selected_columns",
[email.id, phone.id, ward.id],
);
await worker.waitForRun(run.id);
expect(sourceSampler.sample).toHaveBeenCalledWith(
expect.objectContaining({ id: database.id }),
[
{ targetId: email.id, tableName: table.name, columnNames: [] },
{ targetId: phone.id, tableName: table.name, columnNames: [] },
{ targetId: ward.id, tableName: table.name, columnNames: [ward.name] },
],
expect.any(AbortSignal),
);
const request = vi.mocked(completer.complete).mock.calls[0]![0] as ModelCompletionRequest;
const context = JSON.parse(request.messages[1]!.content.split("\n").slice(1).join("\n"));
const targets = new Map(
context.targets.map((target: { targetId: string }) => [target.targetId, target]),
);
expect(targets.get(email.id)).toMatchObject({
sourceSample: {
rows: expect.arrayContaining([
{ fields: [{ name: email.name, value: "marta.rossi@example.com" }] },
]),
representativeValues: [{
column: email.name,
values: expect.arrayContaining(["marta.rossi@example.com"]),
}],
},
});
expect(targets.get(phone.id)).toMatchObject({
sourceSample: {
rows: expect.arrayContaining([
{ fields: [{ name: phone.name, value: "+39 02 5550 1001" }] },
]),
representativeValues: [{
column: phone.name,
values: expect.arrayContaining(["+39 02 5550 1001"]),
}],
},
});
expect(targets.get(ward.id)).toMatchObject({
sourceSample: {
rows: wardValues.map((value) => ({ fields: [{ name: ward.name, value }] })),
representativeValues: [{ column: ward.name, values: wardValues }],
},
});
});
test("continues metadata-only with one safe warning when source sampling is unavailable", async () => {
const repository = new MemoryCatalogRepository();
const database = await repository.create({
@@ -11,6 +11,7 @@ import { up as upDatabases } from "../src/catalog/migrations/001_workspace_datab
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 { KyselyCatalogRepository, type CatalogDatabase } from "../src/catalog/repository.js";
import { loadConfig } from "../src/config.js";
import type { WorkspaceRegistry } from "../src/workspaces/registry.js";
@@ -43,6 +44,7 @@ test.skipIf(!dockerAvailable)("Fastify persists Description Generation success a
await upDatabases(db);
await upTables(db);
await upSchemaSync(db);
await upSensitiveDataFlag(db);
await upDescriptionGeneration(db);
const repository = new KyselyCatalogRepository(db);
const database = await repository.create({
@@ -92,6 +92,34 @@ test("samples at most five source rows and five distinct non-null examples in a
expect(end).toHaveBeenCalledOnce();
});
test("does not issue a SELECT when a protected target has no source columns", async () => {
const query = vi.fn(async () => ({ rows: [] }));
const end = vi.fn(async () => undefined);
const access: CatalogPostgresAccess = {
connect: vi.fn(async () => ({ query, end }) as CatalogDatabaseClient),
};
const sampler = new PostgresDescriptionSourceSampler(access);
const samples = await sampler.sample(database, [{
targetId: target.targetId,
tableName: target.tableName,
columnNames: [],
}], new AbortController().signal);
expect(samples).toEqual([{
targetId: target.targetId,
tableName: target.tableName,
rows: [],
representativeValues: [],
}]);
expect(query.mock.calls).toEqual([
["BEGIN TRANSACTION READ ONLY", []],
["ROLLBACK", []],
]);
expect(query.mock.calls.some(([sql]) => String(sql).startsWith("SELECT"))).toBe(false);
expect(end).toHaveBeenCalledOnce();
});
test("rolls back and closes the source connection when sampling fails", async () => {
const query = vi.fn(async (sql: string) => {
if (sql.startsWith("SELECT")) throw new Error("distinctive-source-secret");
@@ -10,6 +10,7 @@ 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 upRuntimeSequencePrivileges } from "../src/catalog/migrations/004_catalog_runtime_sequence_privileges.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";
const dockerAvailable = spawnSync("docker", ["info"], { stdio: "ignore" }).status === 0;
@@ -23,6 +24,7 @@ test.skipIf(!dockerAvailable)("PostgreSQL migration enforces one database per wo
await upDatabases(db);
await upTables(db);
await upSchemaSync(db);
await upSensitiveDataFlag(db);
await sql`CREATE ROLE thothii_catalog_runtime`.execute(db);
await upRuntimeSequencePrivileges(db);
const sequencePrivilege = await sql<{ allowed: boolean }>`
@@ -75,11 +77,47 @@ test.skipIf(!dockerAvailable)("PostgreSQL migration enforces one database per wo
};
expect(await repository.applySchemaSync(created.id, 1, "columns", [], fullColumnsSnapshot))
.toMatchObject({ created: 4, deleted: 0 });
expect((await repository.listColumns(created.id, patients.id)).map((column) => column.name))
.toEqual(["id", "name"]);
expect((await repository.listColumns(created.id, patients.id)).map((column) => ({
name: column.name,
sensitive: column.sensitive,
}))).toEqual([
{ name: "id", sensitive: false },
{ name: "name", sensitive: false },
]);
expect((await repository.listColumns(created.id, visits.id)).map((column) => column.name))
.toEqual(["id", "patient_id"]);
const patientName = (await repository.listColumns(created.id, patients.id))
.find((column) => column.name === "name")!;
expect(await repository.updateColumnMetadata(
created.id,
patients.id,
patientName.id,
patientName.version,
patientName.description,
patientName.generatedDescription,
true,
)).toMatchObject({ sensitive: true });
const refreshedColumnsSnapshot: ObservedSchemaSnapshot = {
...fullColumnsSnapshot,
schemaVersion: 2,
columns: fullColumnsSnapshot.columns.map((column) => column.tableName === "patients"
&& column.name === "name"
? { ...column, sourceComment: "Sensitive patient name" }
: column),
};
expect(await repository.applySchemaSync(
created.id,
1,
"columns",
[patients.id],
refreshedColumnsSnapshot,
)).toMatchObject({ updated: 1 });
expect(await repository.getColumn(created.id, patients.id, patientName.id)).toMatchObject({
sensitive: true,
sourceComment: "Sensitive patient name",
});
const reducedColumnsSnapshot: ObservedSchemaSnapshot = {
...fullColumnsSnapshot,
columns: fullColumnsSnapshot.columns.filter((column) => column.name === "id"),
@@ -135,6 +173,7 @@ test.skipIf(!dockerAvailable)("PostgreSQL repository performs scoped metadata cl
await upDatabases(db);
await upTables(db);
await upSchemaSync(db);
await upSensitiveDataFlag(db);
const repository = new KyselyCatalogRepository(db);
const database = await repository.create({
workspaceId: "cleanup-test",
@@ -212,6 +251,7 @@ test.skipIf(!dockerAvailable)("PostgreSQL repository atomically consolidates sel
await upDatabases(db);
await upTables(db);
await upSchemaSync(db);
await upSensitiveDataFlag(db);
const repository = new KyselyCatalogRepository(db);
const database = await repository.create({
workspaceId: "consolidation-test",
@@ -310,6 +350,7 @@ test.skipIf(!dockerAvailable)("PostgreSQL repository persists globally exclusive
await upDatabases(db);
await upTables(db);
await upSchemaSync(db);
await upSensitiveDataFlag(db);
await upDescriptionGeneration(db);
const repository = new KyselyCatalogRepository(db);
const firstDatabase = await repository.create({
+17 -3
View File
@@ -234,16 +234,30 @@ test("keeps generated descriptions editable and preserves them across synchroniz
});
expect(editedTable.json()).toMatchObject({ description: null, generatedDescription: "Generated table draft" });
const idColumn = (await repository.listColumns(database.id, patients.id))[0];
expect(idColumn.sensitive).toBe(false);
const editedColumn = await app.inject({
method: "PATCH", url: `/catalog/databases/${database.id}/tables/${patients.id}/columns/${idColumn.id}`,
payload: { version: idColumn.version, description: "Reviewed key", generatedDescription: "Generated key draft" },
payload: {
version: idColumn.version,
description: "Reviewed key",
generatedDescription: "Generated key draft",
sensitive: true,
},
});
expect(editedColumn.json()).toMatchObject({
description: "Reviewed key",
generatedDescription: "Generated key draft",
sensitive: true,
});
expect(editedColumn.json()).toMatchObject({ description: "Reviewed key", generatedDescription: "Generated key draft" });
const second = await app.inject({ method: "POST", url: `/catalog/databases/${database.id}/sync-runs`, payload: { version: database.version, scope: "all", tableIds: [] } });
await waitFor(repository, second.json().id, "succeeded");
expect(await repository.getTable(database.id, patients.id)).toMatchObject({ generatedDescription: "Generated table draft" });
expect(await repository.getColumn(database.id, patients.id, idColumn.id)).toMatchObject({ description: "Reviewed key", generatedDescription: "Generated key draft" });
expect(await repository.getColumn(database.id, patients.id, idColumn.id)).toMatchObject({
description: "Reviewed key",
generatedDescription: "Generated key draft",
sensitive: true,
});
});
test("consolidates non-empty generated table descriptions and reports skipped selections", async () => {
@@ -0,0 +1,29 @@
import { expect, test } from "vitest";
import { syntheticSampleValue } from "../src/catalog/synthetic-sample-value.js";
test.each([
["text[]", "tags", 1, "{tags_001,tags_002}"],
["json", "payload", 2, '{"example":"payload_002","sequence":2}'],
["jsonb", "attributes", 3, '{"example":"attributes_003","sequence":3}'],
["inet", "client_ip", 4, "192.0.2.4"],
["cidr", "network", 5, "192.0.2.0/24"],
["time without time zone", "opening_time", 6, "10:30:06"],
["interval", "duration", 7, "7 days 07:00:00"],
["bytea", "digest", 8, "\\x00000008"],
] as const)(
"creates a deterministic PostgreSQL-shaped value for %s",
(dataType, name, index, expected) => {
const column = { name, dataType };
expect(syntheticSampleValue(column, index)).toBe(expected);
expect(syntheticSampleValue(column, index)).toBe(expected);
},
);
test("uses the PostgreSQL type before birth-related name hints", () => {
expect(syntheticSampleValue({ name: "birth_year", dataType: "integer" }, 2)).toBe(1002);
expect(syntheticSampleValue({ name: "birth_date", dataType: "date" }, 2))
.toBe("1982-01-02");
expect(syntheticSampleValue({ name: "birth_recorded_at", dataType: "timestamp" }, 2))
.toBe("2024-01-02T10:30:00.000Z");
});