feat(agent): provider-agnostic single-call assistant endpoint (runs on a local model) (#1759)

WS1 rip track, RIP-2 (audit Option A), stacked on the AI provider abstraction (#1740). The first replacement for the streaming Anthropic chat runtime: a page-scoped, single-call assistant answer. - lib/agent/ask/ask-service.ts: answerAssistantQuestion() uses getAiService().generateText, so it runs on whatever backend is configured: AWS Bedrock, the direct Anthropic API, OR any OpenAI-compatible endpoint, including a local model (Qwen behind llama.cpp/Ollama/vLLM). No tool loop, no Anthropic wire format, nothing to translate per provider. The caller (a page) supplies the context; the service reads only the company's own profile for grounding, and the system prompt forbids inventing figures. - POST /api/agent/ask: same auth/rate-limit/sandbox/paywall gates as /invoke, but gated on getAiStatus().configured (not assistantAvailable), because ANY provider works here. That is the difference that lets the assistant answer on a local model where the streaming /invoke returns 503. This is the non-UI foundation of the rip: the thin /chat console and the page-scoped actions (RIP-3, UI, gated on visual sign-off) will consume this endpoint; run-turn.ts's streaming path and the intents' getAnthropic() usage are removed once nothing calls them. Verified: 10 unit tests (service prompt shape + tier + context-as-data + truncation; route 401/429/400/403 paywall/200-on-openai-compatible/503 unconfigured) + a live smoke against a local OpenAI-compatible mock (resolved provider openai-compatible, POSTed model qwen3.8 with a placeholder key, returned an answer). 421 agent/ai tests green; tsc, guards, lint clean. Co-authored-by: Jakob Wennberg <311770904+jakobwennberg-oss@users.noreply.github.com> Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-08-20 19:48:43 +02:00
parent 4ecc888416
commit a071a0220b
4 changed files with 331 additions and 0 deletions
@@ -0,0 +1,74 @@
+import { describe, it, expect, vi, beforeEach } from 'vitest'
+import { NextResponse } from 'next/server'
+import { createMockRequest, parseJsonResponse } from '@/tests/helpers'
+
+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) }))
+
+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' })
+})
+
+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()
+  })
+})
@@ -0,0 +1,88 @@
+import { NextResponse } from 'next/server'
+import { z } from 'zod'
+import { requireAuth } from '@/lib/auth/require-auth'
+import { getActiveCompanyId } from '@/lib/company/context'
+import { checkAgentRateLimit, agentRateLimitResponseBody } from '@/lib/rate-limits/agent'
+import { guardSandbox } from '@/lib/sandbox/guard'
+import { requireCapability } from '@/lib/entitlements/has-capability'
+import { CAPABILITY } from '@/lib/entitlements/keys'
+import { getAiStatus } from '@/lib/ai'
+import { answerAssistantQuestion } from '@/lib/agent/ask/ask-service'
+import { getErrorMessage as getUserErrorMessage } from '@/lib/errors/get-error-message'
+
+/**
+ * POST /api/agent/ask: a single-call, provider-agnostic assistant answer.
+ *
+ * Unlike POST /api/agent/invoke (the streaming Anthropic chat runtime, which
+ * is gated on `assistantAvailable` and only runs on the Anthropic family),
+ * this endpoint uses getAiService().generateText, so it runs on ANY configured
+ * backend, including an OpenAI-compatible local model. It is therefore gated
+ * on `configured`, not `assistantAvailable`. This is the replacement chat
+ * surface's server side (audit Option A / rip): a page posts its context and
+ * a question, gets one answer back.
+ */
+
+const Schema = z.object({
+  question: z.string().min(1).max(4000),
+  context: z.string().max(24_000).optional(),
+  tier: z.enum(['assistant', 'heavy']).optional(),
+  company_id: z.string().uuid().optional(),
+})
+
+export async function POST(request: Request): Promise<Response> {
+  const { user, supabase, error } = await requireAuth()
+  if (error) return error
+
+  const rate = await checkAgentRateLimit(supabase, user.id)
+  if (!rate.ok) return NextResponse.json(agentRateLimitResponseBody(rate), { status: 429 })
+
+  let body: unknown
+  try {
+    body = await request.json()
+  } catch {
+    return NextResponse.json({ error: 'Invalid JSON' }, { status: 400 })
+  }
+  const parsed = Schema.safeParse(body)
+  if (!parsed.success) {
+    return NextResponse.json({ error: 'Ogiltig fråga.', type: 'validation_error' }, { status: 400 })
+  }
+
+  const companyId = parsed.data.company_id ?? (await getActiveCompanyId(supabase, user.id))
+  if (!companyId) return NextResponse.json({ error: 'No active company' }, { status: 400 })
+
+  const { data: membership } = await supabase
+    .from('company_members')
+    .select('user_id')
+    .eq('company_id', companyId)
+    .eq('user_id', user.id)
+    .maybeSingle()
+  if (!membership) return NextResponse.json({ error: 'Forbidden' }, { status: 403 })
+
+  const blocked = await guardSandbox(supabase, companyId)
+  if (blocked) return blocked
+
+  const capBlocked = await requireCapability(supabase, companyId, CAPABILITY.ai)
+  if (capBlocked) return capBlocked
+
+  // Distinct from the paywall: no AI backend configured at all. Unlike the
+  // chat loop, ANY provider works here, so we gate on `configured`.
+  if (!getAiStatus().configured) {
+    return NextResponse.json(
+      { error: 'Assistenten är inte konfigurerad på den här installationen.', code: 'ai_unconfigured' },
+      { status: 503 },
+    )
+  }
+
+  try {
+    const result = await answerAssistantQuestion({
+      supabase,
+      companyId,
+      question: parsed.data.question,
+      pageContext: parsed.data.context,
+      tier: parsed.data.tier,
+    })
+    return NextResponse.json({ data: result })
+  } catch (err) {
+    return NextResponse.json({ error: getUserErrorMessage(err) }, { status: 500 })
+  }
+}