Bernd Rodler
dda7adf565
Three pieces built together tonight since they're naturally linked (the
server-class proxy is the real entitlement enforcement chokepoint):
1. Multi-key BYOK (public class): several named provider profiles
(name/baseUrl/model), each with its own key in lib/ai/key-store.ts
(keyed by profile id, not a single fixed 'public' slot). The "Try it"
pane lets you pick which saved profile answers each question - not one
fixed default.
2. `server` class, real: app/api/ai/server/{models,chat} proxy through
this app's own backend to AI_SERVER_BASE_URL - same-origin from the
browser, no CORS/OLLAMA_ORIGINS story at all, standing in tonight for
VNC's EU/CH-hosted infra with the real Ollama on this Mac (swapping to
the real instance tomorrow is a config change).
3. Real entitlement enforcement (lib/ai/entitlement.ts), scoped to `server`
only (not local/public, per the 2026-08-05 decisions): checkAndAssignSeat()
re-validates on every /api/ai/server/chat call - first use auto-assigns a
seat if any remain, further calls from an unlicensed user get a 402 with
a specific reason. recordUsage() appends to an append-only metering
ledger (timestamp/user/model/tokens/latency) that IS the billing record.
Admin data endpoints at /api/admin/ai/entitlement (seat total, revoke) -
the visual admin console is a separate, not-yet-built task.
Two real bugs found and fixed during verification, not just claimed fixed:
- /api/ai/policy never actually added 'server' to entitlement.classes even
when AI_SERVER_BASE_URL was set (only the type comment was updated) - the
Server radio option silently never appeared until this was caught live.
- The new routes used readStalwartAuthContext(0) (hardcoded slot, SSO/reauth-
specific) instead of getStalwartCredentials() (the general multi-slot
session resolver every other authenticated route uses) - reachable but
wrong, and would have hidden a real auth gap behind "works on my slot".
Verified end-to-end for real: built + ran the actual server, logged in via
the real (non-demo) auth flow, selected Server, listed the real Ollama
models through the proxy, asked "Reply with exactly the words: SERVER CLASS
WORKS" and got back exactly that - plus confirmed on disk (not just in the
UI) that data/admin-state/ai-entitlement.json recorded the seat assignment
and ai-metering.jsonl recorded real prompt/completion token counts and
latency from the actual model call. Rejection-path logic (seat limit
reached, zero seats configured, revocation) covered by 5 new unit tests
rather than a second live round trip. Full suite: typecheck clean, lint
clean, translations 48/48, production build succeeds.
57 lines
2.4 KiB
TypeScript
57 lines
2.4 KiB
TypeScript
import { NextRequest, NextResponse } from 'next/server';
|
|
import { requireAdminAuth, getClientIP } from '@/lib/admin/session';
|
|
import { auditLog } from '@/lib/admin/audit';
|
|
import { logger } from '@/lib/logger';
|
|
import { getEntitlementState, setSeatTotal, revokeSeat, readMeteringLedger } from '@/lib/ai/entitlement';
|
|
|
|
export const runtime = 'nodejs';
|
|
|
|
/**
|
|
* Admin-only data endpoints for the `server` AI class's real entitlement
|
|
* enforcement (lib/ai/entitlement.ts). This is the data plumbing only — the
|
|
* visual admin console (docs/AI-ASSISTANT-CONCEPT.md §6) is a separate,
|
|
* not-yet-built UI on top of these same endpoints.
|
|
*/
|
|
export async function GET(request: NextRequest) {
|
|
const result = await requireAdminAuth(request);
|
|
if ('error' in result) return result.error;
|
|
|
|
try {
|
|
const [state, ledger] = await Promise.all([getEntitlementState(), readMeteringLedger()]);
|
|
return NextResponse.json({ ...state, recentUsage: ledger }, { headers: { 'Cache-Control': 'no-store' } });
|
|
} catch (error) {
|
|
logger.error('ai entitlement read error', { error: error instanceof Error ? error.message : String(error) });
|
|
return NextResponse.json({ error: 'Internal server error' }, { status: 500 });
|
|
}
|
|
}
|
|
|
|
export async function PUT(request: NextRequest) {
|
|
const result = await requireAdminAuth(request);
|
|
if ('error' in result) return result.error;
|
|
const ip = getClientIP(request);
|
|
|
|
let body: { seatsTotal?: unknown; revokeUsername?: unknown };
|
|
try {
|
|
body = await request.json();
|
|
} catch {
|
|
return NextResponse.json({ error: 'invalid JSON body' }, { status: 400 });
|
|
}
|
|
|
|
try {
|
|
if (typeof body.seatsTotal === 'number') {
|
|
const state = await setSeatTotal(body.seatsTotal);
|
|
await auditLog('ai.entitlement.seats_total', { seatsTotal: state.seatsTotal }, ip);
|
|
return NextResponse.json(state);
|
|
}
|
|
if (typeof body.revokeUsername === 'string' && body.revokeUsername) {
|
|
const state = await revokeSeat(body.revokeUsername);
|
|
await auditLog('ai.entitlement.revoke_seat', { username: body.revokeUsername }, ip);
|
|
return NextResponse.json(state);
|
|
}
|
|
return NextResponse.json({ error: 'seatsTotal or revokeUsername is required' }, { status: 400 });
|
|
} catch (error) {
|
|
logger.error('ai entitlement update error', { error: error instanceof Error ? error.message : String(error) });
|
|
return NextResponse.json({ error: 'Internal server error' }, { status: 500 });
|
|
}
|
|
}
|