Files
ThothII/backend/test/catalog-sensitivity-analysis.test.ts

266 lines
8.1 KiB
TypeScript

import { expect, test, vi } from "vitest";
import {
SensitivityAnalysisInterruptedError,
SensitivityAnalysisService,
} from "../src/catalog/sensitivity-analysis-service.js";
import { SensitivityAnalysisRunner } from "../src/catalog/sensitivity-analysis-runner.js";
import type { SensitivityClassifier } from "../src/catalog/sensitivity-classifier.js";
import type {
CatalogColumn,
CatalogRepository,
CatalogTable,
SensitivityAnalysisRun,
WorkspaceDatabase,
} from "../src/catalog/types.js";
const database = {
id: "11111111-1111-4111-8111-111111111111",
workspaceId: "psd-clinical",
engine: "postgres",
databaseName: "warehouse",
schema: "public",
version: 1,
createdAt: "2026-09-02T08:00:00Z",
updatedAt: "2026-09-02T08:00:00Z",
connectionStatus: "reachable",
binding: { transport: "postgres_direct", host: "db.internal", port: 5432, username: "reader" },
} satisfies WorkspaceDatabase;
function catalogTable(id: string, name: string): CatalogTable {
return {
id,
databaseId: database.id,
name,
sourceComment: null,
description: null,
generatedDescription: null,
lastSyncedDatabaseVersion: 1,
lastSyncedAt: "2026-09-02T08:00:00Z",
version: 1,
createdAt: "2026-09-02T08:00:00Z",
updatedAt: "2026-09-02T08:00:00Z",
};
}
function catalogColumn(id: string, tableId: string, name: string): CatalogColumn {
return {
id,
tableId,
name,
ordinalPosition: 1,
dataType: "text",
isNullable: true,
defaultExpression: null,
primaryKeyPosition: null,
isPrimaryKey: false,
isForeignKey: false,
foreignKeyCount: 0,
sourceComment: null,
description: null,
generatedDescription: null,
sensitive: false,
lastSyncedDatabaseVersion: 1,
lastSyncedAt: "2026-09-02T08:00:00Z",
version: 1,
createdAt: "2026-09-02T08:00:00Z",
updatedAt: "2026-09-02T08:00:00Z",
};
}
const running: SensitivityAnalysisRun = {
id: "22222222-2222-4222-8222-222222222222",
databaseId: database.id,
scope: "all",
engine: "local",
modelId: null,
policyVersion: "sensitivity-v4",
status: "running",
total: 0,
suggestedSensitive: 0,
suggestedNonSensitive: 0,
unknown: 0,
inputTokens: 0,
cacheReadTokens: 0,
outputTokens: 0,
createdAt: "2026-09-02T08:00:00Z",
startedAt: "2026-09-02T08:00:00Z",
updatedAt: "2026-09-02T08:00:00Z",
finishedAt: null,
errorSummary: null,
};
test("stops catalog selection when the request expires during a catalog read", async () => {
const controller = new AbortController();
const listTables = vi.fn();
const repository = {
get: vi.fn(async () => {
controller.abort();
return database;
}),
listTables,
} as unknown as CatalogRepository;
const classifier = { assess: vi.fn() } as unknown as SensitivityClassifier;
const analysis = new SensitivityAnalysisService(repository, classifier);
await expect(analysis.analyze(
database.id,
"all",
[],
controller.signal,
)).rejects.toBeInstanceOf(SensitivityAnalysisInterruptedError);
expect(listTables).not.toHaveBeenCalled();
expect(classifier.assess).not.toHaveBeenCalled();
});
test("classifies all selected tables in one breadth-first run and reports coverage", async () => {
const firstTable = catalogTable("33333333-3333-4333-8333-333333333333", "patients");
const secondTable = catalogTable("44444444-4444-4444-8444-444444444444", "encounters");
const firstColumn = catalogColumn(
"55555555-5555-4555-8555-555555555555",
firstTable.id,
"status",
);
const secondColumn = catalogColumn(
"66666666-6666-4666-8666-666666666666",
secondTable.id,
"note",
);
const repository = {
get: vi.fn(async () => database),
listTables: vi.fn(async () => [firstTable, secondTable]),
listColumns: vi.fn(async (_databaseId: string, tableId: string) => (
tableId === firstTable.id ? [firstColumn] : [secondColumn]
)),
} as unknown as CatalogRepository;
const assess = vi.fn(async (
_targets,
_signal,
_nerBudget,
onActivity?: (message: string) => void | Promise<void>,
) => {
await onActivity?.("Scanning source data: pass 1 of 3, table batch 1 of 1.");
return [
{
columnId: firstColumn.id,
assessment: "non_sensitive" as const,
proposedSensitive: false,
evidence: [{ kind: "coverage" as const, ruleId: "coverage.sampled_1000" }],
observedValues: 1_000,
coverage: "sampled" as const,
},
{
columnId: secondColumn.id,
assessment: "sensitive" as const,
proposedSensitive: true,
evidence: [{ kind: "content" as const, ruleId: "pii.email" }],
observedValues: 12,
coverage: "sampled" as const,
},
];
});
const classifier = { assess } as unknown as SensitivityClassifier;
const onPrepared = vi.fn();
const onProgress = vi.fn();
const onActivity = vi.fn();
const suggestions = await new SensitivityAnalysisService(repository, classifier).analyze(
database.id,
"all",
[],
new AbortController().signal,
onPrepared,
onProgress,
onActivity,
);
expect(assess).toHaveBeenCalledOnce();
expect(assess.mock.calls[0]![0]).toEqual([
{ database, table: firstTable, columns: [firstColumn] },
{ database, table: secondTable, columns: [secondColumn] },
]);
expect(onPrepared).toHaveBeenCalledWith(2);
expect(onActivity).toHaveBeenCalledWith(
"Scanning source data: pass 1 of 3, table batch 1 of 1.",
);
expect(onProgress.mock.calls.map(([processed]) => processed)).toEqual([1, 2]);
expect(suggestions).toEqual([
expect.objectContaining({ columnId: firstColumn.id, sensitive: false, coverage: "sampled" }),
expect.objectContaining({ columnId: secondColumn.id, sensitive: true, coverage: "sampled" }),
]);
});
test("persists classifier activity in the running analysis event log", async () => {
let persisted = running;
const appendEvent = vi.fn(async () => undefined);
const repository = {
get: vi.fn(async () => database),
createSensitivityAnalysisRun: vi.fn(async () => running),
getSensitivityAnalysisRun: vi.fn(async () => persisted),
updateSensitivityAnalysisRun: vi.fn(async (
_runId: string,
changes: Partial<SensitivityAnalysisRun>,
) => {
persisted = { ...persisted, ...changes };
return persisted;
}),
appendSensitivityAnalysisEvent: appendEvent,
} as unknown as CatalogRepository;
const analysis = {
analyze: vi.fn(async (
_databaseId,
_scope,
_targetIds,
_signal,
onPrepared,
_onProgress,
onActivity,
) => {
await onPrepared?.(0);
await onActivity?.("Scanning source data: pass 1 of 3, table batch 1 of 1.");
return [];
}),
} as unknown as SensitivityAnalysisService;
await new SensitivityAnalysisRunner(repository, analysis).run(
database.id,
"all",
[],
new AbortController().signal,
);
expect(appendEvent).toHaveBeenCalledWith(
running.id,
"info",
"Scanning source data: pass 1 of 3, table batch 1 of 1.",
);
});
test("marks a created run interrupted if the request deadline expires during persistence", async () => {
const controller = new AbortController();
const update = vi.fn(async (_runId: string, changes: Partial<SensitivityAnalysisRun>) => ({
...running,
...changes,
}));
const repository = {
get: vi.fn(async () => database),
createSensitivityAnalysisRun: vi.fn(async () => {
controller.abort();
return running;
}),
updateSensitivityAnalysisRun: update,
appendSensitivityAnalysisEvent: vi.fn(async () => undefined),
} as unknown as CatalogRepository;
const analysis = { analyze: vi.fn() } as unknown as SensitivityAnalysisService;
const runner = new SensitivityAnalysisRunner(repository, analysis);
await expect(runner.run(database.id, "all", [], controller.signal))
.rejects.toBeInstanceOf(SensitivityAnalysisInterruptedError);
expect(analysis.analyze).not.toHaveBeenCalled();
expect(update).toHaveBeenCalledWith(running.id, expect.objectContaining({
status: "interrupted",
total: 0,
unknown: 0,
errorSummary: "Local sensitivity analysis was interrupted before completion.",
}));
});