SRCmail/app/api/ai/server/chat/route.ts

import { NextRequest, NextResponse } from 'next/server';
import { getStalwartCredentials } from '@/lib/stalwart/credentials';
import { checkAndAssignSeat, recordUsage } from '@/lib/ai/entitlement';
import { logger } from '@/lib/logger';

export const runtime = 'nodejs';

const MAX_BODY_BYTES = 200 * 1024;

interface ChatMessage {
  role: 'system' | 'user' | 'assistant';
  content: string;
}

interface OllamaChatResponse {
  message?: { content?: string };
  prompt_eval_count?: number;
  eval_count?: number;
}

/**
 * POST /api/ai/server/chat — the one real enforcement chokepoint for the
 * `server` AI class (docs/AI-ASSISTANT-CONCEPT.md §10 point 2: "re-validates
 * ... entitlement against live state; rejects on mismatch ... never trusts
 * the client"). Every call re-checks the seat; nothing here is cosmetic.
 *
 * Retrieval already happened client-side (the same /api/offline/search leg
 * `local`/`public` use) — this route receives the already-built prompt
 * messages and only proxies the model call + records the metering entry
 * that IS the billing record (lib/ai/entitlement.ts).
 */
export async function POST(request: NextRequest) {
  const auth = await getStalwartCredentials(request);
  if (!auth) {
    return NextResponse.json({ error: 'not authenticated' }, { status: 401 });
  }

  const seat = await checkAndAssignSeat(auth.username);
  if (!seat.allowed) {
    return NextResponse.json({ error: seat.reason ?? 'not entitled' }, { status: 402 });
  }

  const rawBody = await request.text();
  if (rawBody.length > MAX_BODY_BYTES) {
    return NextResponse.json({ error: 'request too large' }, { status: 413 });
  }

  let body: { model?: unknown; messages?: unknown };
  try {
    body = JSON.parse(rawBody);
  } catch {
    return NextResponse.json({ error: 'invalid JSON body' }, { status: 400 });
  }

  const model = typeof body.model === 'string' ? body.model : '';
  const messages = Array.isArray(body.messages) ? (body.messages as ChatMessage[]) : null;
  if (!model || !messages || messages.length === 0) {
    return NextResponse.json({ error: 'model and messages are required' }, { status: 400 });
  }

  const baseUrl = process.env.AI_SERVER_BASE_URL;
  if (!baseUrl) {
    return NextResponse.json({ error: 'AI server class is not configured' }, { status: 503 });
  }

  const startedAt = Date.now();
  try {
    const res = await fetch(`${baseUrl.replace(/\/+$/, '')}/api/chat`, {
      method: 'POST',
      headers: { 'Content-Type': 'application/json' },
      body: JSON.stringify({ model, messages, stream: false }),
    });
    if (!res.ok) {
      return NextResponse.json({ error: `AI server returned ${res.status}` }, { status: 502 });
    }
    const data = (await res.json()) as OllamaChatResponse;
    const content = data.message?.content;
    if (!content) {
      return NextResponse.json({ error: 'AI server returned no message content' }, { status: 502 });
    }

    await recordUsage({
      timestamp: new Date().toISOString(),
      username: auth.username,
      model,
      promptTokens: data.prompt_eval_count ?? 0,
      completionTokens: data.eval_count ?? 0,
      latencyMs: Date.now() - startedAt,
    });

    return NextResponse.json({ answer: content, seatJustAssigned: seat.seatJustAssigned === true });
  } catch (cause) {
    logger.error('ai server chat failed', { error: cause instanceof Error ? cause.message : String(cause) });
    return NextResponse.json({ error: 'AI server unreachable' }, { status: 502 });
  }
}