Files
support_backend/tests/integration/ai-diagnosis.test.ts
T
saqib mirandClaude Sonnet 5 82d02bcdcd feat: implement AI support agent (005) — diagnosis, tools, runbooks, verification
Real Anthropic Claude integration per explicit product decision: a
ticket's AI session diagnoses the problem via a structured-output call,
applies a DB-configurable confidence-band policy (FR-005), and on
"proceed" reasons and acts through a small permission/risk-gated tool
system (FR-011/FR-012), optionally walking a matching runbook step by
step with the application — never the model — owning the step index
(FR-015/FR-016). Resolution requires real tool evidence, never customer
claims alone (FR-018) — verifyProductResolution is a documented
fail-closed placeholder mirroring the existing malware-scanner precedent,
since no real per-product operational signal exists yet.

AISupportSession.status mirrors onto Ticket.status through 003-ticketing's
existing AI_ANALYZING/AI_TROUBLESHOOTING/AI_VERIFYING/AI_RESOLVED/
HUMAN_ESCALATION state machine, discovered during planning to have been
built anticipating this exact feature. Two circular module dependencies
(escalation<->sessions, tools<->sessions) were designed around rather than
found as bugs: escalation is a pure summary formatter with no state
dependencies of its own, and tools stays a clean leaf module with zero
dependency on ai-support/sessions. Ticket creation enqueues the first
diagnosis turn via the existing queue infrastructure (off the hot path of
the inbound SaaS integration endpoint); a human actor changing ticket
status ends the AI session via the event-bus scaffold that existed in
this codebase but had never been wired to anything.

A real Prisma limitation was found and fixed before it reached tests:
compound-unique upsert rejects null for a nullable key column, so
AIConfidencePolicy uses find-then-update/create instead, same fix class
004 already used for the same underlying limitation.

Adds 9 unit tests (confidence-band, tool-policy-gate, runbook-step-
advance) and 6 integration test files, including the two constitution-
required standing E2E scenarios. AI-independent tests were run against
real Postgres/Redis/MinIO (88 passed, 0 failed across the full suite,
including every pre-existing 002/003/004 test). The AI-dependent tests
compile and skip cleanly via describe.skipIf but were not run against a
live model — no ANTHROPIC_API_KEY was available in this session; a real
key must be supplied before this feature can actually run.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-09-02 17:44:52 +05:30

194 lines
8.3 KiB
TypeScript

import { describe, it, expect, beforeAll, afterAll } from 'vitest';
import { buildApp } from '@/app';
import { prismaClient } from '@/infrastructure/database';
import { FastifyInstance } from 'fastify';
import {
encryptCredential,
generateCredentialSecret,
issueIntegrationToken,
} from '@/modules/catalog/products';
import { sessionsService } from '@/modules/ai-support/sessions';
/**
* Covers specs/005-ai-support/quickstart.md Scenario 1 — requires a real ANTHROPIC_API_KEY
* (spec.md Assumptions: this feature integrates a real LLM provider, not a mock). Skipped
* entirely, not failed, when no real key is configured — see README's "AI Support" section for
* how to supply one locally.
*/
const hasRealApiKey = /^sk-ant-/.test(process.env.ANTHROPIC_API_KEY ?? '');
describe.skipIf(!hasRealApiKey)(
'AI diagnosis — confidence decides the outcome (User Story 1)',
() => {
let app: FastifyInstance;
const externalProductId = `TEST_AI_DIAG_PROD_${Date.now()}`;
let secret: string;
beforeAll(async () => {
app = await buildApp();
const product = await prismaClient.product.create({
data: { externalProductId, name: 'AI Diagnosis Test Product', status: 'active' },
});
secret = generateCredentialSecret();
await prismaClient.productIntegration.create({
data: {
productId: product.id,
credentialRef: encryptCredential(secret),
authMechanism: 'signed_token',
allowedScope: { tenantIds: ['tenant-1'] },
status: 'active',
rateLimitPerMinute: 1000,
rateLimitPerUserPerMinute: 1000,
},
});
// FR-006's grounding: at least one published entry must exist for a diagnosis to ever
// reach the confidence-band decision instead of escalating on "no knowledge".
await app
.inject({
method: 'POST',
url: `/admin/products/${externalProductId}/knowledge`,
payload: {
code: `KB-AITEST-${Date.now()}`,
type: 'faq',
problem: 'The application will not load past the loading screen.',
recommendedSolution: 'Clear the browser cache and reload.',
},
})
.then((r) => {
const code = r.json().data.code;
return app.inject({ method: 'PATCH', url: `/admin/knowledge/${code}/publish` });
});
});
afterAll(async () => {
const product = await prismaClient.product.findUnique({ where: { externalProductId } });
if (product) {
const tickets = await prismaClient.ticket.findMany({ where: { productId: product.id } });
const ticketIds = tickets.map((t) => t.id);
const sessions = await prismaClient.aISupportSession.findMany({
where: { ticketId: { in: ticketIds } },
});
const sessionIds = sessions.map((s) => s.id);
await prismaClient.aIKnowledgeReference.deleteMany({
where: { sessionId: { in: sessionIds } },
});
await prismaClient.aIDiagnosis.deleteMany({ where: { sessionId: { in: sessionIds } } });
await prismaClient.aIInteraction.deleteMany({ where: { sessionId: { in: sessionIds } } });
await prismaClient.aISupportSession.deleteMany({ where: { id: { in: sessionIds } } });
await prismaClient.ticketMessage.deleteMany({ where: { ticketId: { in: ticketIds } } });
await prismaClient.ticket.deleteMany({ where: { productId: product.id } });
await prismaClient.problem.deleteMany({ where: { productId: product.id } });
await prismaClient.knowledgeEntry.deleteMany({ where: { productId: product.id } });
await prismaClient.aIConfidencePolicy.deleteMany({ where: { productId: product.id } });
}
await prismaClient.productIntegration.deleteMany({
where: { product: { externalProductId } },
});
await prismaClient.product.deleteMany({ where: { externalProductId } });
await app.close();
});
async function createTicketAndRunFirstTurn(problem: string): Promise<string> {
const token = issueIntegrationToken(secret, {
externalProductId,
tenantId: 'tenant-1',
userId: 'user-1',
});
const created = await app.inject({
method: 'POST',
url: '/v1/support/requests',
headers: { authorization: `Bearer ${token}` },
payload: {
productId: externalProductId,
tenantId: 'tenant-1',
userId: 'user-1',
source: 'test',
problem,
},
});
const ticketId = created.json().data.ticketId;
// Bypass the queue — no worker runs during buildApp()-based tests, same convention as
// ticket-attachments.test.ts's malware scanner call.
await sessionsService.runFirstTurn(ticketId);
return ticketId;
}
it('records a structured diagnosis with a confidence score, grounded in retrieved knowledge', async () => {
const ticketId = await createTicketAndRunFirstTurn('The app is stuck on the loading screen.');
const response = await app.inject({ method: 'GET', url: `/tickets/${ticketId}/ai-session` });
expect(response.statusCode).toBe(200);
const body = response.json().data;
expect(body.diagnosis).not.toBeNull();
expect(typeof body.diagnosis.confidence).toBe('number');
expect(body.diagnosis.confidence).toBeGreaterThanOrEqual(0);
expect(body.diagnosis.confidence).toBeLessThanOrEqual(1);
}, 60000);
it('escalates rather than diagnosing when no knowledge exists for the product', async () => {
const noKnowledgeProduct = `TEST_AI_DIAG_NOKB_${Date.now()}`;
const product = await prismaClient.product.create({
data: { externalProductId: noKnowledgeProduct, name: 'No KB product', status: 'active' },
});
const noKbSecret = generateCredentialSecret();
await prismaClient.productIntegration.create({
data: {
productId: product.id,
credentialRef: encryptCredential(noKbSecret),
authMechanism: 'signed_token',
allowedScope: { tenantIds: ['tenant-1'] },
status: 'active',
rateLimitPerMinute: 1000,
rateLimitPerUserPerMinute: 1000,
},
});
const token = issueIntegrationToken(noKbSecret, {
externalProductId: noKnowledgeProduct,
tenantId: 'tenant-1',
userId: 'user-1',
});
const created = await app.inject({
method: 'POST',
url: '/v1/support/requests',
headers: { authorization: `Bearer ${token}` },
payload: {
productId: noKnowledgeProduct,
tenantId: 'tenant-1',
userId: 'user-1',
source: 'test',
problem: 'Something is broken.',
},
});
const ticketId = created.json().data.ticketId;
await sessionsService.runFirstTurn(ticketId);
const response = await app.inject({ method: 'GET', url: `/tickets/${ticketId}/ai-session` });
expect(response.json().data.status).toBe('escalated');
await prismaClient.aIDiagnosis.deleteMany({
where: { session: { ticketId } },
});
await prismaClient.aISupportSession.deleteMany({ where: { ticketId } });
await prismaClient.ticketMessage.deleteMany({ where: { ticketId } });
await prismaClient.ticket.deleteMany({ where: { id: ticketId } });
await prismaClient.problem.deleteMany({ where: { productId: product.id } });
await prismaClient.productIntegration.deleteMany({ where: { productId: product.id } });
await prismaClient.product.deleteMany({ where: { externalProductId: noKnowledgeProduct } });
}, 60000);
it('a low highThreshold/lowThreshold makes the same diagnosis less likely to escalate on confidence alone', async () => {
await app.inject({
method: 'PUT',
url: `/admin/products/${externalProductId}/ai-policy`,
payload: { highThreshold: 0.01, lowThreshold: 0.0, maxClarifyingQuestions: 3 },
});
const ticketId = await createTicketAndRunFirstTurn(
'The app is stuck on the loading screen again.',
);
const response = await app.inject({ method: 'GET', url: `/tickets/${ticketId}/ai-session` });
// With lowThreshold at 0, "escalate" from confidence alone is impossible — any remaining
// escalation would have to come from FR-006 (no knowledge), which doesn't apply here.
expect(response.json().data.status).not.toBe('escalated');
}, 60000);
},
);