Files
accounted/app/api/agent/ask/__tests__/route.test.ts
T
ff4425d10e feat(agent): let the single-call assistant read the ledger via read-only MCP tools (#1767)
The /chat assistant (audit Option A / rip) shipped in #1759 reading only the
company name + entity type, so it answered "jag har ingen bokföringsdata" to
every figures question ("vad är min största utgiftspost?"). It now behaves like
an MCP client: it answers over a bounded, READ-only tool loop across the same
MCP read tools the old streaming assistant had, plus an always-on company
snapshot as the backstop.

Provider-agnostic by construction, so it still runs on a local model:
- lib/ai generateText gains optional `tools` + `maxSteps`. The OpenAI-compatible
  service forwards them to the Vercel AI SDK (stopWhen: stepCountIs), which runs
  the loop; the Anthropic-family service hand-rolls a small loop against
  messages.create. Kept on the raw Anthropic SDK: no new deps, and the no-tools
  path is byte-identical, so hosted extraction/composer/etc. are unchanged.
- lib/agent/ask/ledger-tools.ts: the read slice of general.help's whitelist
  (income statement, VAT, ledgers, query_journal, reskontror, lists…) from
  agentToolRegistry, dispatched with the agent_chat actor run-turn uses. Write/
  staging + memory-write tools are excluded; readOnlyHint/destructiveHint are
  re-checked. Empty in a core-only build → snapshot-only, graceful.
- lib/agent/ask/snapshot.ts: a compact company_settings + deadlines block so a
  model that can't/won't call tools still answers status questions. Never carries
  figures (those come from the live tools).
- ask-service attaches tools + snapshot when a userId is present and uses a
  tool-aware system prompt; the route calls ensureInitialized() so the registry
  is populated and threads userId/conversationId through.

Works on Bedrock and on any local model with function-calling (Qwen). Tests:
the anthropic hand-rolled loop (tool call → result → answer, is_error handling,
step-budget forced answer), openai tool forwarding, the read-only adapter
filter, the snapshot format, and the ask-service wiring. 457 agent+ai tests
green, lint/guards clean.

Co-authored-by: Jakob Wennberg <311770904+jakobwennberg-oss@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-20 21:18:21 +02:00

166 lines
7.5 KiB
TypeScript

import { describe, it, expect, vi, beforeEach } from 'vitest'
import { NextResponse } from 'next/server'
import { createMockRequest, parseJsonResponse } from '@/tests/helpers'
vi.mock('@/lib/init', () => ({ ensureInitialized: vi.fn() }))
const requireAuthMock = vi.fn()
vi.mock('@/lib/auth/require-auth', () => ({ requireAuth: () => requireAuthMock() }))
vi.mock('@/lib/company/context', () => ({ getActiveCompanyId: vi.fn().mockResolvedValue('company-1') }))
const checkRate = vi.fn()
vi.mock('@/lib/rate-limits/agent', () => ({
checkAgentRateLimit: () => checkRate(),
agentRateLimitResponseBody: () => ({ error: 'För många förfrågningar.' }),
}))
vi.mock('@/lib/sandbox/guard', () => ({ guardSandbox: vi.fn().mockResolvedValue(null) }))
const requireCapability = vi.fn()
vi.mock('@/lib/entitlements/has-capability', () => ({ requireCapability: () => requireCapability() }))
vi.mock('@/lib/entitlements/keys', () => ({ CAPABILITY: { ai: 'ai' } }))
const aiStatus = vi.fn()
vi.mock('@/lib/ai', () => ({ getAiStatus: () => aiStatus() }))
const answer = vi.fn()
vi.mock('@/lib/agent/ask/ask-service', () => ({ answerAssistantQuestion: (...a: unknown[]) => answer(...a) }))
const resolveConv = vi.fn()
const persistUser = vi.fn()
const persistAssistant = vi.fn()
vi.mock('@/lib/agent/ask/persist', () => ({
resolveChatConversation: (...a: unknown[]) => resolveConv(...a),
persistUserTurn: (...a: unknown[]) => persistUser(...a),
persistAssistantTurn: (...a: unknown[]) => persistAssistant(...a),
}))
import { POST } from '../route'
const membershipChain = { select: () => membershipChain, eq: () => membershipChain, maybeSingle: async () => ({ data: { user_id: 'user-1' } }) }
const supabase = { from: () => membershipChain }
beforeEach(() => {
vi.clearAllMocks()
requireAuthMock.mockResolvedValue({ user: { id: 'user-1' }, supabase, error: null })
checkRate.mockResolvedValue({ ok: true })
requireCapability.mockResolvedValue(null)
aiStatus.mockReturnValue({ configured: true, assistantAvailable: false, provider: 'openai-compatible' })
answer.mockResolvedValue({ answer: 'Svar', model: 'qwen3.8' })
resolveConv.mockResolvedValue({ ok: true, conversationId: 'conv-9', created: true })
persistUser.mockResolvedValue(undefined)
persistAssistant.mockResolvedValue(undefined)
})
const body = (o: Record<string, unknown> = {}) => ({ question: 'Hur gick juli?', ...o })
describe('POST /api/agent/ask', () => {
it('401 when unauthenticated', async () => {
requireAuthMock.mockResolvedValue({ user: null, supabase, error: NextResponse.json({ error: 'x' }, { status: 401 }) })
expect((await POST(createMockRequest('/api/agent/ask', { method: 'POST', body: body() }))).status).toBe(401)
})
it('429 when rate limited', async () => {
checkRate.mockResolvedValue({ ok: false })
expect((await POST(createMockRequest('/x', { method: 'POST', body: body() }))).status).toBe(429)
})
it('400 on an empty question', async () => {
expect((await POST(createMockRequest('/x', { method: 'POST', body: { question: '' } }))).status).toBe(400)
})
it('403 when the company lacks the ai capability (paywall)', async () => {
requireCapability.mockResolvedValue(NextResponse.json({ error: 'pay' }, { status: 403 }))
expect((await POST(createMockRequest('/x', { method: 'POST', body: body() }))).status).toBe(403)
})
// The key behaviour: this endpoint runs on ANY configured backend, so it is
// available even when the streaming chat (assistantAvailable) is not, e.g.
// on a local OpenAI-compatible model.
it('answers on an openai-compatible backend where the streaming chat would 503', async () => {
const res = await POST(createMockRequest('/x', { method: 'POST', body: body({ context: 'Resultat juli: +12 000' }) }))
const { status, body: b } = await parseJsonResponse<{ data: { answer: string; model: string } }>(res)
expect(status).toBe(200)
expect(b.data).toEqual({ answer: 'Svar', model: 'qwen3.8' })
expect(answer).toHaveBeenCalledWith(expect.objectContaining({ companyId: 'company-1', question: 'Hur gick juli?', pageContext: 'Resultat juli: +12 000' }))
})
it('503 ai_unconfigured when no backend is configured at all', async () => {
aiStatus.mockReturnValue({ configured: false })
const res = await POST(createMockRequest('/x', { method: 'POST', body: body() }))
const { status, body: b } = await parseJsonResponse<{ code: string }>(res)
expect(status).toBe(503)
expect(b.code).toBe('ai_unconfigured')
expect(answer).not.toHaveBeenCalled()
})
it('stateless (no persist): never touches the conversation tables', async () => {
await POST(createMockRequest('/x', { method: 'POST', body: body() }))
expect(resolveConv).not.toHaveBeenCalled()
expect(persistUser).not.toHaveBeenCalled()
expect(persistAssistant).not.toHaveBeenCalled()
})
describe('persist: true (chat console)', () => {
it('creates/resumes the thread, writes both turns, returns the conversation id', async () => {
const res = await POST(
createMockRequest('/x', {
method: 'POST',
body: body({ persist: true, context_ref: 'report:vat:2026-07' }),
}),
)
const { status, body: b } = await parseJsonResponse<{
data: { answer: string; model: string; conversation_id: string }
}>(res)
expect(status).toBe(200)
expect(b.data.conversation_id).toBe('conv-9')
expect(b.data.answer).toBe('Svar')
// Order matters: resolve → user turn → answer → assistant turn.
expect(resolveConv).toHaveBeenCalledWith(
supabase,
'user-1',
'company-1',
undefined,
'Hur gick juli?',
'report:vat:2026-07',
)
expect(persistUser).toHaveBeenCalledWith(supabase, 'conv-9', 'Hur gick juli?')
expect(answer).toHaveBeenCalled()
expect(persistAssistant).toHaveBeenCalledWith(supabase, 'conv-9', 'Svar')
})
it('resumes with a supplied conversation_id', async () => {
resolveConv.mockResolvedValue({ ok: true, conversationId: 'conv-7', created: false })
const res = await POST(
createMockRequest('/x', {
method: 'POST',
body: body({ persist: true, conversation_id: '11111111-1111-4111-8111-111111111111' }),
}),
)
const { status, body: b } = await parseJsonResponse<{ data: { conversation_id: string } }>(res)
expect(status).toBe(200)
expect(b.data.conversation_id).toBe('conv-7')
expect(resolveConv).toHaveBeenCalledWith(
supabase,
'user-1',
'company-1',
'11111111-1111-4111-8111-111111111111',
'Hur gick juli?',
undefined,
)
})
it("404s on a conversation that isn't the user's, without answering or persisting", async () => {
resolveConv.mockResolvedValue({ ok: false, reason: 'not_found' })
const res = await POST(
createMockRequest('/x', {
method: 'POST',
body: body({ persist: true, conversation_id: '22222222-2222-4222-8222-222222222222' }),
}),
)
expect(res.status).toBe(404)
expect(persistUser).not.toHaveBeenCalled()
expect(answer).not.toHaveBeenCalled()
expect(persistAssistant).not.toHaveBeenCalled()
})
it('still 503s (no write) when no backend is configured', async () => {
aiStatus.mockReturnValue({ configured: false })
const res = await POST(createMockRequest('/x', { method: 'POST', body: body({ persist: true }) }))
expect(res.status).toBe(503)
expect(resolveConv).not.toHaveBeenCalled()
expect(persistUser).not.toHaveBeenCalled()
})
})
})