Assessor_2.0/tests/compliance/regulatory-mapping-service....

638 lines
44 KiB
TypeScript

import { describe, expect, it, vi } from 'vitest';
import { AUTO_ACCEPT_COMMENT, RegulatoryMappingService } from '../../server/compliance/regulatory-mapping-service';
import { RegulatoryFindingRetrievalService } from '../../server/compliance/regulatory-finding-retrieval';
import { acceptedControlIds, REGULATORY_GPO_QUERY_VERSION, REGULATORY_MAPPING_PROMPT_VERSION, type RegulatoryMappingBatchRun, type RegulatoryMappingDecision, type RegulatoryMappingRun } from '../../src/compliance/regulatory-mapping';
import type { RegulatoryChunk, RegulatoryRetrievalRequest } from '../../src/compliance/regulatory-rag';
import { filterUnifiedResults, type UnifiedResultProjection } from '../../src/domain/unified-result';
import type { ComplianceReadPort, ComplianceStore } from '../../src/compliance/compliance-store';
type EngineRepository = ComplianceReadPort & ComplianceStore;
import { removeResultDbScopeIdentifiers } from '../../src/domain/result-db-disclosure';
import { complianceWorkFacetIndex } from '../../src/compliance/ui/compliance-work-facets';
import type { FindingRecord } from '../../src/domain/finding';
const stamp = '2026-09-15T10:00:00.000Z';
// Result-table / occurrence data that must never reach the model or the query.
const resultTableAsset = 'DC01.customer.local';
const customerPolicyValue = 'CUSTOMER\synthetic.account';
function finding(overrides: Partial<UnifiedResultProjection> = {}): UnifiedResultProjection {
return {
resultProjectionId: 'scanner-finding:occurrence-1', sourceKind: 'scanner-finding', sourceResultId: 'occurrence-1',
projectId: 'project-1', assessmentId: 'assessment-1', collectionRunId: 'run-1', scanRunId: 'run-1',
sourceTool: 'purple-knight', sourceRuleId: 'A-SmbSigning', title: 'SMB signing is not required on domain controllers',
description: 'The SMB server permits unsigned sessions, allowing relay attacks.', affectedAsset: resultTableAsset,
severityOriginal: 'high', severityNormalized: 'high', outcomeOriginal: 'fail', outcomeNormalized: 'fail',
technicalExecutionState: 'completed', resultType: 'compliance_check', isIoe: false, isDeviation: true,
lifecycleState: 'new', mappingConfidence: 1, reviewStatus: 'unreviewed', importedAt: stamp, createdAt: stamp, frameworkReferences: [], categories: [],
...overrides
};
}
function chunk(sourceStandard: 'ISO/IEC 27001' | 'ISO/IEC 27002'): RegulatoryChunk {
const reference = sourceStandard === 'ISO/IEC 27001';
return {
schemaVersion: 2, corpusId: 'iso-test', corpusVersion: 'v2', documentId: reference ? '27001-5.1' : '27002-5.1-purpose',
framework: 'ISO/IEC 27002', frameworkVersion: '2022', controlId: '5.1', annexAControlId: 'A.5.1',
controlTheme: 'organizational', sourceStandard, sourceEdition: '2022', nationalEdition: 'DIN 2024',
sectionKind: reference ? 'control' : 'purpose', sourcePageStart: 1, sourcePageEnd: 1,
retrievalRole: reference ? 'reference' : 'semantic', parserVersion: 'test', sourceSha256: reference ? '1'.repeat(64) : '2'.repeat(64),
chunkId: reference ? 'reference-5.1' : 'semantic-5.1', chunkIndex: 0, language: 'de', title: 'Synthetic control',
text: reference ? 'Synthetic normative statement.' : 'Synthetic semantic evidence.', textSha256: 'a'.repeat(64)
};
}
/** In-memory repository keyed like the global (rule-keyed) schema. */
function mockRepository(findings: UnifiedResultProjection[]) {
const byProjection = new Map(findings.map(item => [item.resultProjectionId, item]));
const runs = new Map<string, RegulatoryMappingRun>();
const batches: RegulatoryMappingBatchRun[] = [];
const decisions: RegulatoryMappingDecision[] = [];
return {
getProject: vi.fn(async (projectId: string) => findings.some(item => item.projectId === projectId) ? { id: projectId, name: 'Synthetic project' } : null),
listProjects: vi.fn(async () => [...new Set(findings.map(item => item.projectId))].map(id => ({ id, name: 'Synthetic project' }))),
listAssessments: vi.fn(async (projectId: string) => [...new Set(findings.filter(item => item.projectId === projectId).map(item => item.assessmentId).filter(Boolean))]
.map(id => ({ id: id!, projectId, label: 'Synthetic assessment', createdAt: stamp }))),
listProjectScanRuns: vi.fn(async (projectId: string) => [...new Map(findings.filter(item => item.projectId === projectId && item.scanRunId)
.map(item => [item.scanRunId!, { id: item.scanRunId!, assessmentId: item.assessmentId!, sequence: 1, startedAt: stamp }])).values()]),
queryUnifiedResults: vi.fn(async (query = {}) => {
const filtered = filterUnifiedResults(findings, query);
const offset = query.offset ?? 0;
return { total: filtered.length, items: filtered.slice(offset, offset + (query.limit ?? filtered.length)) };
}),
// Mirrors the real Result DB read: scoped to the project, returned without real scope ids.
getUnifiedResultById: vi.fn(async (id: string, projectId?: string) => {
const item = byProjection.get(id);
return item && (projectId === undefined || item.projectId === projectId) ? removeResultDbScopeIdentifiers(item) : null;
}),
getRegulatoryMappingRun: vi.fn(async (id: string) => runs.get(id) ?? null),
claimRegulatoryMappingRun: vi.fn(async (run: RegulatoryMappingRun, force: boolean) => {
const existing = runs.get(run.id);
if (existing && (['queued', 'running'].includes(existing.status) || existing.status === 'succeeded' && !force)) {
return { run: existing, claimed: false };
}
runs.set(run.id, run);
return { run, claimed: true };
}),
saveRegulatoryMappingRun: vi.fn(async (run: RegulatoryMappingRun) => { runs.set(run.id, run); return run; }),
listRegulatoryMappingRuns: vi.fn(async () => [...runs.values()]),
createRegulatoryMappingBatchRun: vi.fn(async (run: RegulatoryMappingBatchRun) => {
const existing = batches.find(item => item.projectId === run.projectId && (item.idempotencyKey === run.idempotencyKey
|| item.scopeKey === run.scopeKey && ['queued', 'running'].includes(item.status)));
if (existing) return existing;
batches.push(run);
return run;
}),
updateRegulatoryMappingBatchRun: vi.fn(async (run: RegulatoryMappingBatchRun) => {
const index = batches.findIndex(item => item.id === run.id);
if (index < 0) throw new Error('missing batch');
batches[index] = run;
return run;
}),
listRegulatoryMappingBatchRuns: vi.fn(async (projectId: string, scopeKey?: string) => batches
.filter(item => item.projectId === projectId && (!scopeKey || item.scopeKey === scopeKey))
.slice().reverse()),
createRegulatoryMappingDecision: vi.fn(async (decision: RegulatoryMappingDecision, expected?: string) => {
const run = runs.get(decision.mappingId);
if (!run || run.ruleKey !== decision.ruleKey || run.status !== 'succeeded') throw new Error('missing mapping');
if (!run.candidates.some(c => c.controlId === decision.controlId)) throw new Error('ungrounded control');
const latest = decisions.filter(d => d.ruleKey === decision.ruleKey && d.controlId === decision.controlId)
.sort((a, b) => b.createdAt.localeCompare(a.createdAt) || b.id.localeCompare(a.id))[0];
if ((expected ?? undefined) !== (latest?.id ?? undefined)) throw new Error('conflict');
const stored = { ...decision, ...(latest ? { previousDecisionId: latest.id } : {}) };
decisions.push(stored);
return stored;
}),
listRegulatoryMappingDecisions: vi.fn(async (ruleKey: string) => decisions.filter(d => d.ruleKey === ruleKey)
.sort((a, b) => b.createdAt.localeCompare(a.createdAt) || b.id.localeCompare(a.id)))
} as unknown as EngineRepository;
}
function service(repository: EngineRepository, complete: (system: string, input: string) => Promise<unknown>) {
return new RegulatoryMappingService(repository, repository, {
findingRetrieval: new RegulatoryFindingRetrievalService({ retrieve: vi.fn(async (_r: RegulatoryRetrievalRequest) => [{ score: 0.9, chunk: chunk('ISO/IEC 27002') }]) }),
index: { ensureCollection: vi.fn(), replaceDocuments: vi.fn(), searchDense: vi.fn(), list: vi.fn(async () => [chunk('ISO/IEC 27001')]) },
client: { model: 'work-model', complete: complete as never }, corpusId: 'iso-test', corpusVersion: 'v2', embeddingModel: 'bge-m3',
now: () => new Date(stamp)
});
}
describe('regulatory mapping service', () => {
it('shares one global mapping and decision across projects and sends no result-table data', async () => {
const findingB = finding({ resultProjectionId: 'scanner-finding:occurrence-2', sourceResultId: 'occurrence-2', projectId: 'project-2', affectedAsset: 'DC02.other.local' });
const repository = mockRepository([finding(), findingB]);
const complete = vi.fn(async (_system: string, _input: string) => ({ value: {
schemaVersion: 1, outcome: 'mapped', mappings: [{ controlId: '5.1', relationship: 'primary', confidence: 'high',
rationale: 'Synthetic rationale.', evidenceChunkIds: ['semantic-5.1', 'reference-5.1'] }]
}, usage: { totalTokens: 12 } }));
const svc = service(repository, complete);
await svc.start('project-1', { resultProjectionId: 'scanner-finding:occurrence-1' });
await svc.close();
// The same rule mapped once in project-1 is visible to project-2 (global sharing).
const shared = await svc.get('project-2', 'scanner-finding:occurrence-2');
expect(shared).toMatchObject({ state: 'succeeded', run: { ruleKey: 'purple-knight:A-SmbSigning', sourceTool: 'purple-knight', embeddingModel: 'bge-m3', tokenUsage: { totalTokens: 12 } } });
expect(shared.run?.result?.mappings[0].controlId).toBe('5.1');
expect(shared.run?.promptVersion).toBe(REGULATORY_MAPPING_PROMPT_VERSION);
expect(complete).toHaveBeenCalledOnce();
// The copyrighted ISO clause text is stripped from the response but still reaches the model.
expect(shared.run?.candidates.every(c => c.evidence.every(item => item.text === undefined))).toBe(true);
expect(complete.mock.calls[0][0]).toContain('governs the same security subject');
expect(complete.mock.calls[0][1]).toContain('Synthetic semantic evidence.');
expect(complete.mock.calls[0][1]).toContain('SMB signing is not required');
expect(complete.mock.calls[0][1]).not.toContain(resultTableAsset);
expect(complete.mock.calls[0][1]).not.toContain('DC02.other.local');
expect(complete.mock.calls[0][1]).not.toContain('A.5.1');
// The automatic acceptance in project-1 is visible to project-2 (global decisions), and so is a later manual decision.
expect(shared.decisions.map(d => ({ controlId: d.controlId, decision: d.decision }))).toEqual([{ controlId: '5.1', decision: 'accepted' }]);
await svc.decide('project-1', { resultProjectionId: 'scanner-finding:occurrence-1', controlId: '5.1', decision: 'rejected', expectedLatestDecisionId: shared.decisions[0].id });
const afterDecision = await svc.get('project-2', 'scanner-finding:occurrence-2');
const rejected = afterDecision.decisions.find(d => d.decision === 'rejected');
expect(rejected).toMatchObject({ controlId: '5.1', previousDecisionId: shared.decisions[0].id });
expect(acceptedControlIds(afterDecision.decisions)).toEqual([]);
});
it('maps a finding although the Result DB row carries no real project id, but never across projects', async () => {
const repository = mockRepository([finding()]);
const complete = vi.fn(async (_system: string, _input: string) => ({ value: {
schemaVersion: 1, outcome: 'mapped', mappings: [{ controlId: '5.1', relationship: 'primary', confidence: 'high',
rationale: 'Synthetic rationale.', evidenceChunkIds: ['semantic-5.1', 'reference-5.1'] }]
} }));
const svc = service(repository, complete);
expect((await repository.getUnifiedResultById('scanner-finding:occurrence-1'))?.projectId).toBe('scoped-project');
await expect(svc.get('project-1', 'scanner-finding:occurrence-1')).resolves.toMatchObject({ generationEnabled: true });
await svc.start('project-1', { resultProjectionId: 'scanner-finding:occurrence-1' });
await svc.close();
const automatic = (await svc.get('project-1', 'scanner-finding:occurrence-1')).decisions[0];
await expect(svc.decide('project-1', { resultProjectionId: 'scanner-finding:occurrence-1', controlId: '5.1', decision: 'rejected', expectedLatestDecisionId: automatic.id }))
.resolves.toMatchObject({ state: 'succeeded' });
await expect(svc.get('project-2', 'scanner-finding:occurrence-1')).rejects.toThrow('does not exist in this project');
await expect(svc.start('project-2', { resultProjectionId: 'scanner-finding:occurrence-1' })).rejects.toThrow('does not exist in this project');
await expect(svc.decide('project-2', { resultProjectionId: 'scanner-finding:occurrence-1', controlId: '5.1', decision: 'rejected' }))
.rejects.toThrow('does not exist in this project');
});
it('counts accepted controls once per finding for the timeslot deviations of a client', async () => {
const gpo = (id: string) => finding({ resultProjectionId: `policy-evaluation-comparison:${id}`, sourceResultId: `comparison-${id}`,
sourceKind: 'policy-evaluation', sourceTool: 'GPOs', sourceRuleId: 'registry:machine:software\policies\synthetic:mode',
policyScope: 'computer', title: 'Synthetic policy mode' });
const findings = [
finding(),
finding({ resultProjectionId: 'scanner-finding:occurrence-2', sourceResultId: 'occurrence-2' }),
finding({ resultProjectionId: 'scanner-finding:not-deviation', sourceResultId: 'not-deviation', isDeviation: false }),
finding({ resultProjectionId: 'scanner-finding:rejected', sourceResultId: 'rejected', sourceRuleId: 'A-Rejected', title: 'SMB signing is not enforced' }),
// Two baseline packages of one GPO setting are one Work record and count once.
gpo('one'), gpo('two')
];
const repository = mockRepository(findings);
const svc = service(repository, vi.fn(async () => ({ value: {
schemaVersion: 1, outcome: 'mapped', mappings: [{ controlId: '5.1', relationship: 'primary', confidence: 'high',
rationale: 'Synthetic rationale.', evidenceChunkIds: ['semantic-5.1', 'reference-5.1'] }]
} })));
for (const resultProjectionId of ['scanner-finding:occurrence-1', 'scanner-finding:rejected', 'policy-evaluation-comparison:one']) {
await svc.start('project-1', { resultProjectionId });
await svc.close();
}
const accepted = (await svc.get('project-1', 'scanner-finding:rejected')).decisions[0];
await svc.decide('project-1', { resultProjectionId: 'scanner-finding:rejected', controlId: '5.1', decision: 'rejected', expectedLatestDecisionId: accepted.id });
const overview = await svc.controlOverview('project-1', { assessmentIds: ['assessment-1'], scanRunIds: ['run-1'] });
expect(overview).toMatchObject({ version: 1, projectId: 'project-1', findingCount: 3,
controls: [{ controlId: '5.1', annexAControlId: 'A.5.1', title: 'Synthetic control', theme: 'Organizational' }] });
expect(overview.controls[0].findings.map(item => item.resultProjectionId))
.toEqual(['scanner-finding:occurrence-1', 'scanner-finding:occurrence-2', 'policy-evaluation-comparison:one']);
// Only the timeslot deviations are read, and only through the read-only port.
expect(vi.mocked(repository.queryUnifiedResults).mock.calls.at(-1)![0]).toMatchObject({ audience: 'result-db', deviation: true, projectId: 'project-1' });
// The Work filters read every mappable finding, so the status filter in Work decides what is shown.
const assignments = await svc.controlAssignments('project-1', { assessmentIds: ['assessment-1'], scanRunIds: ['run-1'] });
expect(assignments.findingCount).toBe(4);
expect(assignments.controls[0].findings.map(item => item.resultProjectionId)).toContain('scanner-finding:not-deviation');
expect(vi.mocked(repository.queryUnifiedResults).mock.calls.at(-1)?.[0]?.deviation).toBeUndefined();
await expect(svc.controlOverview('project-1', { assessmentIds: [], scanRunIds: [] })).rejects.toThrow('timeslot scope is required');
await expect(svc.controlOverview('project-1', { assessmentIds: ['foreign-assessment'], scanRunIds: [] })).rejects.toThrow('outside this project');
});
it('reports every batch and single finding mapping globally, marked by where it came from, on the Client Info overview only', async () => {
const repository = mockRepository([finding(),
finding({ assessmentId: 'assessment-3', scanRunId: 'run-3', resultProjectionId: 'scanner-finding:earlier', sourceResultId: 'earlier',
sourceRuleId: 'C-Earlier', title: 'Earlier synthetic check' }),
finding({ projectId: 'project-2', assessmentId: 'assessment-2', scanRunId: 'run-2',
resultProjectionId: 'scanner-finding:other', sourceResultId: 'other', sourceRuleId: 'B-Other', title: 'Other synthetic check' })]);
const svc = service(repository, vi.fn(async () => ({ value: { schemaVersion: 1, outcome: 'mapped', mappings: [{ controlId: '5.1',
relationship: 'primary', confidence: 'high', rationale: 'Synthetic rationale.', evidenceChunkIds: ['semantic-5.1', 'reference-5.1'] }] } })));
const scope = { assessmentIds: ['assessment-1'], scanRunIds: ['run-1'] };
const run = async (action: Promise<unknown>) => { await action; await svc.close(); };
await run(svc.startBatch('project-1', { ...scope, filters: {}, idempotencyKey: 'regulatory-batch-dummy-manual' }));
await run(svc.startBatch('project-1', { ...scope, filters: { deviation: true }, idempotencyKey: 'auto:run-1' }));
await run(svc.startBatch('project-1', { assessmentIds: ['assessment-3'], scanRunIds: ['run-3'], filters: {}, idempotencyKey: 'regulatory-batch-dummy-earlier' }));
await run(svc.startBatch('project-2', { assessmentIds: ['assessment-2'], scanRunIds: ['run-2'], filters: {}, idempotencyKey: 'regulatory-batch-dummy-other' }));
// Single mappings from the Finding Reader carry the timeslot they were started in.
await run(svc.start('project-1', { resultProjectionId: 'scanner-finding:occurrence-1', origin: scope }));
await run(svc.start('project-1', { resultProjectionId: 'scanner-finding:earlier', origin: { assessmentIds: ['assessment-3'], scanRunIds: ['run-3'] } }));
await run(svc.start('project-2', { resultProjectionId: 'scanner-finding:other', origin: { assessmentIds: ['assessment-2'], scanRunIds: ['run-2'] } }));
const overview = await svc.controlOverview('project-1', scope);
expect(overview.mappingHistory?.map(entry => [entry.kind, entry.scope, entry.trigger]).sort()).toEqual([
['batch', 'other-client', 'manual'], ['batch', 'other-timeslot', 'manual'], ['batch', 'timeslot', 'automatic'], ['batch', 'timeslot', 'manual'],
['single', 'other-client', 'manual'], ['single', 'other-timeslot', 'manual'], ['single', 'timeslot', 'manual']]);
// The automatic batch reused the rule the first one mapped.
const automatic = overview.mappingHistory!.find(entry => entry.trigger === 'automatic')!;
expect(automatic.counts).toEqual({ findings: 1, sentToModel: 0, reused: 1, succeeded: 0, failed: 0 });
const single = overview.mappingHistory!.find(entry => entry.kind === 'single' && entry.scope === 'timeslot')!;
expect(single).toMatchObject({ status: 'completed', counts: { sentToModel: 1, reused: 0, succeeded: 1, failed: 0 } });
expect(single.counts.findings).toBeUndefined();
// Content-free: no client, rule, scope id, filter or key leaves the engine with an entry.
expect(Object.keys(single).sort()).toEqual(['completedAt', 'counts', 'createdAt', 'id', 'kind', 'scope', 'status', 'trigger']);
expect(Object.keys(automatic).sort()).toEqual(['completedAt', 'counts', 'createdAt', 'id', 'kind', 'scope', 'status', 'trigger']);
// The stored origin is hashed: runs are global and exported with every client, so no id is kept.
const stored = JSON.stringify(await repository.listRegulatoryMappingRuns());
for (const id of ['project-1', 'project-2', 'assessment-1', 'assessment-2', 'assessment-3', 'run-1', 'run-2', 'run-3']) {
expect(stored).not.toContain(`"${id}"`);
}
expect((await svc.controlAssignments('project-1', scope)).mappingHistory).toBeUndefined();
});
it('marks a single mapping without a usable origin as unknown, or as the client only', async () => {
const repository = mockRepository([finding()]);
const svc = service(repository, vi.fn(async () => ({ value: { schemaVersion: 1, outcome: 'mapped', mappings: [{ controlId: '5.1',
relationship: 'primary', confidence: 'high', rationale: 'Synthetic rationale.', evidenceChunkIds: ['semantic-5.1', 'reference-5.1'] }] } })));
const scope = { assessmentIds: ['assessment-1'], scanRunIds: ['run-1'] };
// A foreign timeslot is not recorded; the client still is.
await svc.start('project-1', { resultProjectionId: 'scanner-finding:occurrence-1', origin: { assessmentIds: ['foreign-assessment'], scanRunIds: [] } });
await svc.close();
expect((await svc.controlOverview('project-1', scope)).mappingHistory?.map(entry => entry.scope)).toEqual(['other-timeslot']);
// A run without origin, as recorded before this change, is unknown.
const [stored] = await repository.listRegulatoryMappingRuns();
const { origin: _origin, ...withoutOrigin } = stored;
await repository.saveRegulatoryMappingRun(withoutOrigin);
expect((await svc.controlOverview('project-1', scope)).mappingHistory?.map(entry => entry.scope)).toEqual(['unknown']);
});
it('counts a GPO setting once and gives Work its setting ID although the Result DB withholds it', async () => {
// Internal comparisons carry the setting ID; the Result DB rows of the same comparisons do not.
const comparison = (id: string, settingId: string, title: string, policyScope: 'computer' | 'user') => finding({
resultProjectionId: `policy-evaluation-comparison:${id}`, sourceResultId: `comparison-${id}`, sourceKind: 'policy-evaluation',
sourceTool: 'GPOs', sourceRuleId: settingId, policyScope, title });
const findings = [
// Three baseline packages of one setting, a second setting, the same title in the other scope and
// a different setting that shares the first setting's title.
comparison('a1', 'gpo-policy-identity-aaaa', 'Synthetic · Mode', 'computer'),
comparison('a2', 'gpo-policy-identity-aaaa', 'Synthetic · Mode', 'computer'),
comparison('a3', 'gpo-policy-identity-aaaa', 'Synthetic · Mode', 'computer'),
comparison('b1', 'gpo-policy-identity-bbbb', 'Security Options · SyntheticKey', 'computer'),
comparison('b2', 'gpo-policy-identity-bbbb', 'Security Options · SyntheticKey', 'computer'),
comparison('c1', 'gpo-policy-identity-cccc', 'Synthetic · Mode', 'user'),
comparison('d1', 'gpo-policy-identity-dddd', 'Synthetic · Mode', 'computer')
];
const repository = mockRepository(findings);
const internal = vi.mocked(repository.queryUnifiedResults).getMockImplementation()!;
vi.mocked(repository.queryUnifiedResults).mockImplementation(async (query = {}) => {
const page = await internal(query);
return query.audience === 'internal-analysis' ? page
: { ...page, items: page.items.map(item => ({ ...item, sourceRuleId: undefined })) };
});
const svc = service(repository, vi.fn(async () => ({ value: {
schemaVersion: 1, outcome: 'mapped', mappings: [{ controlId: '5.1', relationship: 'primary', confidence: 'high',
rationale: 'Synthetic rationale.', evidenceChunkIds: ['semantic-5.1', 'reference-5.1'] }]
} })));
const scope = { assessmentIds: ['assessment-1'], scanRunIds: ['run-1'], filters: { deviation: true } };
await svc.startBatch('project-1', { ...scope, idempotencyKey: 'batch-gpo-settings' });
await svc.close();
// Mapping stays one global rule per disclosed title; counting follows the Work settings.
expect((await svc.getBatch('project-1', scope)).run?.counts)
.toMatchObject({ filteredResultCount: 7, eligibleFindingCount: 4, distinctRuleCount: 2 });
const overview = await svc.controlOverview('project-1', { assessmentIds: ['assessment-1'], scanRunIds: ['run-1'] });
expect(overview.findingCount).toBe(4);
expect(overview.controls[0].findings.map(item => `${item.policyScope}:${item.sourceRuleId}`).sort()).toEqual([
'computer:gpo-policy-identity-aaaa', 'computer:gpo-policy-identity-bbbb',
'computer:gpo-policy-identity-dddd', 'user:gpo-policy-identity-cccc']);
// The internal read is limited to GPO comparisons of the same timeslot.
const internalQueries = vi.mocked(repository.queryUnifiedResults).mock.calls.map(call => call[0] ?? {})
.filter(query => query.audience === 'internal-analysis');
expect(internalQueries.length).toBeGreaterThan(0);
expect(internalQueries.every(query => query.projectId === 'project-1' && query.sourceKind?.join() === 'policy-evaluation'
&& query.assessmentIds?.join() === 'assessment-1' && query.scanRunIds?.join() === 'run-1')).toBe(true);
// The Work ISO filter finds the rolled-up GPO setting by scope and setting ID.
const workSetting = { id: `gpo-work-setting:${encodeURIComponent(JSON.stringify(['project-1', 'aggregation-1', 'computer', 'gpo-policy-identity-aaaa']))}` } as FindingRecord;
expect(complianceWorkFacetIndex(overview).facets[0].valuesFor!(workSetting)).toEqual(['5.1']);
});
it('accepts the first two proposals automatically, keeps existing decisions and accepts nothing without a proposal', async () => {
const semantic = (controlId: string): RegulatoryChunk => ({ ...chunk('ISO/IEC 27002'), controlId, annexAControlId: `A.${controlId}`,
documentId: `27002-${controlId}`, chunkId: `semantic-${controlId}` });
const proposal = (controlId: string) => ({ controlId, relationship: 'supporting', confidence: 'medium', rationale: 'Synthetic rationale.',
evidenceChunkIds: [`semantic-${controlId}`] });
const build = (repository: EngineRepository, value: unknown) => new RegulatoryMappingService(repository, repository, {
findingRetrieval: new RegulatoryFindingRetrievalService({ retrieve: vi.fn(async (_r: RegulatoryRetrievalRequest) =>
['8.20', '5.15', '5.1'].map((controlId, index) => ({ score: 0.9 - index / 10, chunk: semantic(controlId) }))) }),
index: { ensureCollection: vi.fn(), replaceDocuments: vi.fn(), searchDense: vi.fn(), list: vi.fn(async () => [chunk('ISO/IEC 27001')]) },
client: { model: 'work-model', complete: vi.fn(async () => ({ value })) as never }, corpusId: 'iso-test', corpusVersion: 'v2',
embeddingModel: 'bge-m3', now: () => new Date(stamp)
});
const accepted = async (svc: RegulatoryMappingService) => acceptedControlIds((await svc.get('project-1', 'scanner-finding:occurrence-1')).decisions).sort();
const mapped = (...controls: string[]) => ({ schemaVersion: 1, outcome: 'mapped', mappings: controls.map(proposal) });
// Three proposals: the first two in the model's order are accepted, the third stays undecided.
const three = build(mockRepository([finding()]), mapped('5.15', '8.20', '5.1'));
await three.start('project-1', { resultProjectionId: 'scanner-finding:occurrence-1' });
await three.close();
expect(await accepted(three)).toEqual(['5.15', '8.20']);
expect((await three.get('project-1', 'scanner-finding:occurrence-1')).decisions.every(item => item.comment === AUTO_ACCEPT_COMMENT)).toBe(true);
// A single proposal is accepted alone.
const one = build(mockRepository([finding()]), mapped('8.20'));
await one.start('project-1', { resultProjectionId: 'scanner-finding:occurrence-1' });
await one.close();
expect(await accepted(one)).toEqual(['8.20']);
// Regenerating never overrides a manual reject; a still undecided first proposal is accepted.
const automatic = (await three.get('project-1', 'scanner-finding:occurrence-1')).decisions.find(item => item.controlId === '5.15')!;
await three.decide('project-1', { resultProjectionId: 'scanner-finding:occurrence-1', controlId: '5.15', decision: 'rejected', expectedLatestDecisionId: automatic.id });
await three.start('project-1', { resultProjectionId: 'scanner-finding:occurrence-1' });
await three.close();
expect(await accepted(three)).toEqual(['8.20']);
// Without a proposal nothing is accepted.
const none = build(mockRepository([finding()]), { schemaVersion: 1, outcome: 'no_relevant_control', mappings: [], reason: 'Synthetic refusal.' });
await none.start('project-1', { resultProjectionId: 'scanner-finding:occurrence-1' });
await none.close();
expect((await none.get('project-1', 'scanner-finding:occurrence-1')).decisions).toEqual([]);
});
it('keeps a control decided by an earlier run reviewable after a new pipeline version stops retrieving it', async () => {
const semantic = (controlId: string): RegulatoryChunk => ({ ...chunk('ISO/IEC 27002'), controlId, annexAControlId: `A.${controlId}`,
documentId: `27002-${controlId}`, chunkId: `semantic-${controlId}` });
const repository = mockRepository([finding()]);
const build = (corpusVersion: string, controlId: string) => new RegulatoryMappingService(repository, repository, {
findingRetrieval: new RegulatoryFindingRetrievalService({ retrieve: vi.fn(async (_r: RegulatoryRetrievalRequest) => [{ score: 0.9, chunk: semantic(controlId) }]) }),
index: { ensureCollection: vi.fn(), replaceDocuments: vi.fn(), searchDense: vi.fn(), list: vi.fn(async () => [chunk('ISO/IEC 27001')]) },
client: { model: 'work-model', complete: vi.fn(async () => ({ value: { schemaVersion: 1, outcome: 'mapped', mappings: [{ controlId,
relationship: 'primary', confidence: 'high', rationale: 'Synthetic rationale.', evidenceChunkIds: [`semantic-${controlId}`] }] } })) as never },
corpusId: 'iso-test', corpusVersion, embeddingModel: 'bge-m3', now: () => new Date(stamp)
});
const older = build('v1', '8.3');
await older.start('project-1', { resultProjectionId: 'scanner-finding:occurrence-1' });
await older.close();
const current = build('v2', '8.2');
await current.start('project-1', { resultProjectionId: 'scanner-finding:occurrence-1' });
await current.close();
const response = await current.get('project-1', 'scanner-finding:occurrence-1');
expect(acceptedControlIds(response.decisions).sort()).toEqual(['8.2', '8.3']);
expect(response.run?.candidates.map(item => item.controlId)).toEqual(['8.2']);
expect(response.earlierControls).toEqual([{ controlId: '8.3', annexAControlId: 'A.8.3', title: semantic('8.3').title }]);
// Rejecting the earlier control is grounded by the older run that retrieved it.
const earlier = response.decisions.find(item => item.controlId === '8.3')!;
const rejected = await current.decide('project-1', { resultProjectionId: 'scanner-finding:occurrence-1', controlId: '8.3', decision: 'rejected', expectedLatestDecisionId: earlier.id });
expect(acceptedControlIds(rejected.decisions)).toEqual(['8.2']);
expect(rejected.decisions.find(item => item.controlId === '8.3' && item.previousDecisionId === earlier.id)).toMatchObject({ decision: 'rejected', mappingId: earlier.mappingId });
});
it('keeps a saved mapping readable when the retrieval index is unavailable', async () => {
const repository = mockRepository([finding()]);
const complete = vi.fn(async (_system: string, _input: string) => ({ value: {
schemaVersion: 1, outcome: 'mapped', mappings: [{ controlId: '5.1', relationship: 'primary', confidence: 'high',
rationale: 'Synthetic rationale.', evidenceChunkIds: ['semantic-5.1', 'reference-5.1'] }]
} }));
const online = service(repository, complete);
await online.start('project-1', { resultProjectionId: 'scanner-finding:occurrence-1' });
await online.close();
const offline = new RegulatoryMappingService(repository, repository, {
findingRetrieval: {} as never,
index: { list: vi.fn(async () => { throw new Error('Index unavailable'); }) } as never,
client: { model: 'work-model', complete } as never,
corpusId: 'iso-test', corpusVersion: 'v2', embeddingModel: 'bge-m3'
});
const response = await offline.get('project-1', 'scanner-finding:occurrence-1');
expect(response).toMatchObject({ generationEnabled: false, state: 'succeeded', run: { status: 'succeeded' } });
expect(response.run?.result?.mappings[0].controlId).toBe('5.1');
expect(response.run?.candidates.every(candidate => candidate.evidence.every(item => item.text === undefined))).toBe(true);
});
it('drops one ungrounded evidence id but keeps the otherwise-valid mapping', async () => {
const { svc } = await runWith({
schemaVersion: 1, outcome: 'mapped', mappings: [{ controlId: '5.1', relationship: 'primary', confidence: 'high',
rationale: 'Synthetic rationale.', evidenceChunkIds: ['semantic-5.1', 'not-a-supplied-chunk'] }]
});
const completed = await svc.get('project-1', 'scanner-finding:occurrence-1');
expect(completed.run?.status).toBe('succeeded');
expect(completed.run?.result?.mappings[0].evidenceChunkIds).toEqual(['semantic-5.1']);
expect(completed.run?.errorCode).toBeUndefined();
});
it('fails safely with a structural detail when the model maps to an unknown control', async () => {
const { svc } = await runWith({
schemaVersion: 1, outcome: 'mapped', mappings: [{ controlId: 'A.5.1', relationship: 'primary', confidence: 'high',
rationale: 'Synthetic rationale.', evidenceChunkIds: ['semantic-5.1'] }]
});
const completed = await svc.get('project-1', 'scanner-finding:occurrence-1');
expect(completed.run?.status).toBe('failed');
expect(completed.run?.errorCode).toBe('regulatory_mapping_invalid_output');
expect(completed.run?.errorDetail).toContain('unknown candidate control');
expect(completed.run?.errorDetail).not.toContain(resultTableAsset);
});
it('maps the complete filtered timeslot including GPO comparisons, excludes context rows and deduplicates global rules', async () => {
const findings = [
finding(),
finding({ resultProjectionId: 'scanner-finding:occurrence-2', sourceResultId: 'occurrence-2' }),
finding({ resultProjectionId: 'scanner-finding:occurrence-3', sourceResultId: 'occurrence-3', sourceRuleId: 'A-Second', title: 'Second synthetic check' }),
finding({ resultProjectionId: 'policy-observation:one', sourceResultId: 'policy-one', sourceKind: 'policy-observation', sourceRuleId: undefined }),
// Two baseline packages of one GPO setting share one global rule.
...['one', 'two'].map(id => finding({ resultProjectionId: `policy-evaluation-comparison:${id}`, sourceResultId: `comparison-${id}`,
sourceKind: 'policy-evaluation', sourceTool: 'GPOs', sourceRuleId: 'registry:machine:software\policies\synthetic:mode',
title: 'Synthetic policy mode', policyActualValue: { principals: [customerPolicyValue] } })),
finding({ resultProjectionId: 'scanner-finding:unsupported', sourceResultId: 'unsupported', sourceRuleId: 'A-Unsupported', title: '' }),
finding({ resultProjectionId: 'scanner-finding:not-deviation', sourceResultId: 'not-deviation', sourceRuleId: 'A-Ignored', isDeviation: false })
];
const repository = mockRepository(findings);
const complete = vi.fn(async (_system: string, _input: string) => ({ value: {
schemaVersion: 1, outcome: 'mapped', mappings: [{ controlId: '5.1', relationship: 'primary', confidence: 'high',
rationale: 'Synthetic rationale.', evidenceChunkIds: ['semantic-5.1', 'reference-5.1'] }]
} }));
const svc = service(repository, complete);
await svc.startBatch('project-1', {
assessmentIds: ['assessment-1'], scanRunIds: ['run-1'], filters: { deviation: true, affectedAsset: resultTableAsset },
idempotencyKey: 'batch-filtered-1'
});
await svc.close();
const response = await svc.getBatch('project-1', {
assessmentIds: ['assessment-1'], scanRunIds: ['run-1'], filters: { deviation: true, affectedAsset: resultTableAsset }
});
expect(response.run).toMatchObject({ status: 'completed', counts: {
filteredResultCount: 7,
excludedNonScannerCount: 1,
// The two baseline comparisons of one GPO setting are one eligible finding, like its Work record.
eligibleFindingCount: 4,
unsupportedFindingCount: 1,
distinctRuleCount: 3,
scheduledRuleCount: 3,
succeededRuleCount: 3,
failedRuleCount: 0
} });
expect(complete).toHaveBeenCalledTimes(3);
expect(complete.mock.calls.every(call => !String(call[1]).includes(resultTableAsset) && !String(call[1]).includes('synthetic.account'))).toBe(true);
});
it('maps a single GPO baseline comparison under its technical setting and refuses a raw observation', async () => {
const gpo = finding({ resultProjectionId: 'policy-evaluation-comparison:one', sourceResultId: 'comparison-one',
sourceKind: 'policy-evaluation', sourceTool: 'GPOs', sourceRuleId: 'registry:machine:software\policies\synthetic:mode',
title: 'Synthetic policy mode', policyActualValue: { principals: [customerPolicyValue] } });
const observation = finding({ resultProjectionId: 'policy-observation:one', sourceResultId: 'observation-one', sourceKind: 'policy-observation' });
const complete = vi.fn(async (_system: string, _input: string) => ({ value: {
schemaVersion: 1, outcome: 'mapped', mappings: [{ controlId: '5.1', relationship: 'primary', confidence: 'high',
rationale: 'Synthetic rationale.', evidenceChunkIds: ['semantic-5.1', 'reference-5.1'] }]
} }));
const svc = service(mockRepository([gpo, observation]), complete);
await svc.start('project-1', { resultProjectionId: gpo.resultProjectionId });
await svc.close();
const mapped = await svc.get('project-1', gpo.resultProjectionId);
expect(mapped).toMatchObject({ generationEnabled: true, state: 'succeeded', run: { ruleKey: 'GPOs:registry:machine:software\policies\synthetic:mode' } });
// The stored identity tuple must differ per GPO query version, or a version bump collides with the older row.
expect(mapped.run?.promptVersion).toBe(`${REGULATORY_MAPPING_PROMPT_VERSION}+${REGULATORY_GPO_QUERY_VERSION}`);
expect(complete).toHaveBeenCalledTimes(1);
expect(String(complete.mock.calls[0][1])).not.toContain('synthetic.account');
expect(await svc.get('project-1', observation.resultProjectionId)).toMatchObject({ generationEnabled: false, state: 'unsupported' });
await expect(svc.start('project-1', { resultProjectionId: observation.resultProjectionId })).rejects.toThrow('GPO baseline comparisons');
});
it('bounds concurrent mapping completions across a batch', async () => {
const findings = Array.from({ length: 5 }, (_, index) => finding({
resultProjectionId: `scanner-finding:occurrence-${index}`,
sourceResultId: `occurrence-${index}`,
sourceRuleId: `A-Rule-${index}`,
title: `Synthetic check ${index}`
}));
let active = 0;
let maximum = 0;
const complete = vi.fn(async () => {
active += 1;
maximum = Math.max(maximum, active);
await new Promise(resolve => setTimeout(resolve, 5));
active -= 1;
return { value: { schemaVersion: 1, outcome: 'no_relevant_control', reason: 'Synthetic.', mappings: [] } };
});
const svc = service(mockRepository(findings), complete);
await svc.startBatch('project-1', {
assessmentIds: ['assessment-1'], scanRunIds: ['run-1'], filters: { deviation: true }, idempotencyKey: 'batch-concurrency-1'
});
await svc.close();
expect(complete).toHaveBeenCalledTimes(5);
expect(maximum).toBe(2);
});
it('reads every server page independently of loaded rows', async () => {
const findings = Array.from({ length: 501 }, (_, index) => finding({
resultProjectionId: `scanner-finding:occurrence-${index}`,
sourceResultId: `occurrence-${index}`
}));
const repository = mockRepository(findings);
const complete = vi.fn(async () => ({ value: {
schemaVersion: 1, outcome: 'no_relevant_control', reason: 'Synthetic.', mappings: []
} }));
const svc = service(repository, complete);
await svc.startBatch('project-1', {
assessmentIds: ['assessment-1'], scanRunIds: ['run-1'], filters: { deviation: true }, idempotencyKey: 'batch-many-pages-1'
});
await svc.close();
const response = await svc.getBatch('project-1', {
assessmentIds: ['assessment-1'], scanRunIds: ['run-1'], filters: { deviation: true }
});
expect(response.run?.counts).toMatchObject({ filteredResultCount: 501, eligibleFindingCount: 501, distinctRuleCount: 1 });
expect(repository.queryUnifiedResults).toHaveBeenCalledTimes(2);
expect(complete).toHaveBeenCalledOnce();
});
it('fails the batch safely when the filtered total changes between pages', async () => {
const findings = Array.from({ length: 501 }, (_, index) => finding({
resultProjectionId: `scanner-finding:occurrence-${index}`,
sourceResultId: `occurrence-${index}`
}));
const repository = mockRepository(findings);
let page = 0;
vi.mocked(repository.queryUnifiedResults).mockImplementation(async (query = {}) => {
page += 1;
const offset = query.offset ?? 0;
return { total: page === 1 ? 501 : 500, items: findings.slice(offset, offset + (query.limit ?? findings.length)) };
});
const complete = vi.fn();
const svc = service(repository, complete);
await svc.startBatch('project-1', {
assessmentIds: ['assessment-1'], scanRunIds: ['run-1'], filters: { deviation: true }, idempotencyKey: 'batch-changing-total-1'
});
await svc.close();
const response = await svc.getBatch('project-1', {
assessmentIds: ['assessment-1'], scanRunIds: ['run-1'], filters: { deviation: true }
});
expect(response.run).toMatchObject({ status: 'failed', errorCode: 'regulatory_mapping_batch_scope_changed' });
expect(complete).not.toHaveBeenCalled();
});
it('completes with partial failures, then reuses success and retries only the failed rule', async () => {
const findings = [finding(), finding({
resultProjectionId: 'scanner-finding:occurrence-2', sourceResultId: 'occurrence-2', sourceRuleId: 'A-Second', title: 'Second synthetic check'
})];
let secondAttempts = 0;
const complete = vi.fn(async (_system: string, input: string) => {
if (input.includes('Second synthetic check') && ++secondAttempts === 1) throw new Error('synthetic provider failure');
return { value: { schemaVersion: 1, outcome: 'no_relevant_control', reason: 'Synthetic.', mappings: [] } };
});
const svc = service(mockRepository(findings), complete);
const scope = { assessmentIds: ['assessment-1'], scanRunIds: ['run-1'], filters: { deviation: true } };
await svc.startBatch('project-1', { ...scope, idempotencyKey: 'batch-partial-1' });
await svc.close();
expect((await svc.getBatch('project-1', scope)).run).toMatchObject({
status: 'completed', counts: { scheduledRuleCount: 2, succeededRuleCount: 1, failedRuleCount: 1 }
});
await svc.startBatch('project-1', { ...scope, idempotencyKey: 'batch-partial-2' });
await svc.close();
expect((await svc.getBatch('project-1', scope)).run).toMatchObject({
status: 'completed', counts: {
distinctRuleCount: 2, reusedSucceededRuleCount: 1, scheduledRuleCount: 1, succeededRuleCount: 1, failedRuleCount: 0
}
});
expect(complete).toHaveBeenCalledTimes(3);
});
it('reuses an active single-finding mapping without a duplicate model call', async () => {
let release!: () => void;
const gate = new Promise<void>(resolve => { release = resolve; });
const complete = vi.fn(async () => {
await gate;
return { value: { schemaVersion: 1, outcome: 'no_relevant_control', reason: 'Synthetic.', mappings: [] } };
});
const svc = service(mockRepository([finding()]), complete);
await svc.start('project-1', { resultProjectionId: 'scanner-finding:occurrence-1' });
const scope = { assessmentIds: ['assessment-1'], scanRunIds: ['run-1'], filters: { deviation: true } };
await svc.startBatch('project-1', { ...scope, idempotencyKey: 'batch-active-reuse-1' });
release();
await svc.close();
expect((await svc.getBatch('project-1', scope)).run?.counts).toMatchObject({
distinctRuleCount: 1, reusedActiveRuleCount: 1, scheduledRuleCount: 0
});
expect(complete).toHaveBeenCalledOnce();
});
});
async function runWith(value: unknown): Promise<{ svc: RegulatoryMappingService }> {
const repository = mockRepository([finding()]);
const svc = service(repository, vi.fn(async () => ({ value })));
await svc.start('project-1', { resultProjectionId: 'scanner-finding:occurrence-1' });
await svc.close();
return { svc };
}