freezmo/app/api/chat/extract/route.ts

import { z } from "zod";

import { extractNotes, notesToText } from "@/lib/ai";
import { getServerConfig } from "@/lib/config";
import { INERT_OLLAMA_AUTH, resolveModelTarget } from "@/lib/providers-server";
import { friendlyErrorMessage, OllamaError } from "@/lib/ollama";
import { rejectCrossOrigin, rejectOversizedBody, requestLocale } from "@/lib/http-guard";
import { clientKey, rateLimit, rateLimitResponse } from "@/lib/rate-limit";
import { acquireModelGate } from "@/lib/model-guard";
import { dataUrlSchema } from "@/lib/schemas";
import { translate } from "@/lib/i18n-dict";

export const runtime = "nodejs";
export const dynamic = "force-dynamic";
export const maxDuration = 300;

/** Same ceiling as deck generation: up to 16 resized photos. */
const MAX_BODY_BYTES = 33554432;
const MAX_IMAGE_CHARS = 8_000_000;

const requestSchema = z.object({

  model: z.string().min(1).max(200).optional(),
  images: z.array(dataUrlSchema(MAX_IMAGE_CHARS)).max(16).optional(),
  text: z.string().max(120_000).optional(),
});

/**
 * Turns chat attachments (photos, scanned pages, pasted document text) into
 * plain text with the existing vision pipeline, so any chat model — including
 * text-only ones — can use them. Never stores anything.
 */
export async function POST(request: Request) {
  const locale = requestLocale(request);
  const crossOrigin = rejectCrossOrigin(request);
  if (crossOrigin) return crossOrigin;
  const oversized = rejectOversizedBody(request, MAX_BODY_BYTES);
  if (oversized) return oversized;

  const config = getServerConfig();

  const limit = rateLimit(`chat:${clientKey(request)}`, config.rateLimits.chat, config.rateLimits.windowMs);
  if (!limit.allowed) return rateLimitResponse(limit, locale);

  // Ollama (server-configured) or a cloud provider the browser sent a key for.
  const resolved = resolveModelTarget(config, request, locale);
  if ("error" in resolved) {
    return Response.json({ error: resolved.error.message, kind: resolved.error.kind }, { status: resolved.error.status });
  }
  const target = resolved.target;
  const provider = target.kind === "provider" ? target.target : undefined;
  const baseAuth = target.kind === "provider" ? INERT_OLLAMA_AUTH : target.auth;

  let payload: unknown;
  try {
    payload = await request.json();
  } catch {
    return Response.json({ error: translate(locale, "server.bodyNotJson") }, { status: 400 });
  }

  const parsed = requestSchema.safeParse(payload);
  if (!parsed.success) {
    return Response.json(
      { error: translate(locale, "server.invalidRequest", { detail: parsed.error.issues[0]?.message ?? "" }) },
      { status: 400 },
    );
  }

  const images = (parsed.data.images ?? []).map(stripDataUrlPrefix).filter(Boolean);
  const text = parsed.data.text?.trim() ?? "";
  if (images.length === 0 && !text) {
    return Response.json({ error: translate(locale, "server.needContent") }, { status: 400 });
  }

  // Provider runs carry the model the user picked in Settings → Providers.
  const providerModel = provider ? parsed.data.model : undefined;
  if (provider && !providerModel) {
    return Response.json(
      { error: translate(locale, "server.providerModelNeeded"), kind: "bad_provider" },
      { status: 400 },
    );
  }
  const textModel = provider ? providerModel! : config.textModel;
  const visionModel = provider ? providerModel! : config.visionModel;

  const gate = acquireModelGate(request, config, locale);
  if ("response" in gate) return gate.response;
  const abort = new AbortController();
  const timer = setTimeout(() => abort.abort(), config.timeoutMs);
  const onRequestAbort = () => abort.abort();
  if (request.signal.aborted) abort.abort();
  else request.signal.addEventListener("abort", onRequestAbort, { once: true });
  try {
    if (images.length === 0) {
      // Plain text needs no model call at all.
      return Response.json({ text: text.slice(0, 48_000) });
    }
    const extraction = await extractNotes({
      model: visionModel,
      repairModel: textModel,
      auth: baseAuth,
      provider,
      images,
      text: text || undefined,
      signal: abort.signal,
    });
    const extracted = notesToText(extraction.notes).slice(0, 48_000);
    if (!extracted.trim()) {
      return Response.json({ error: translate(locale, "chat.attachEmpty"), kind: "bad_response" }, { status: 422 });
    }
    return Response.json({ text: extracted });
  } catch (error) {
    console.error("[api/chat/extract]", error instanceof OllamaError ? `${error.kind}: ${error.message}` : error);
    return Response.json(
      {
        error: friendlyErrorMessage(error, baseAuth.baseUrl || provider?.baseUrl || '', locale),
        kind: error instanceof OllamaError ? error.kind : "unknown",
      },
      { status: 502 },
    );
  } finally {
    clearTimeout(timer);
    request.signal.removeEventListener("abort", onRequestAbort);
    gate.gate.release();
  }
}

function stripDataUrlPrefix(value: string): string {
  const commaIndex = value.indexOf(",");
  if (value.startsWith("data:") && commaIndex !== -1) return value.slice(commaIndex + 1);
  return value;
}