// Responses API end-to-end test through the proxy (UTF-8 safe).
import { readFileSync } from "node:fs";
const B64 = readFileSync("C:/Users/12914/Desktop/vscode/.mimo2codex-audit/red64.png").toString("base64");

async function responsesTest(model, content) {
  const item = typeof content === "string"
    ? { type: "message", role: "user", content }
    : { type: "message", role: "user", content };
  const res = await fetch("http://127.0.0.1:8788/v1/responses", {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ model, stream: false, input: [item] }),
  });
  const j = await res.json().catch(() => null);
  const msg = j?.output?.find((o) => o.type === "message");
  const text = msg?.content?.find((c) => c.type === "output_text")?.text;
  return { status: res.status, text: text?.slice(0, 160), err: j?.error?.message?.slice(0, 200) };
}

// 1. multimodal to mimo-v2.5 (vision-capable, Responses wire)
const r1 = await responsesTest("mimo-v2.5", [
  { type: "input_text", text: "这张图片是什么颜色？只回答颜色词。" },
  { type: "input_image", image_url: `data:image/png;base64,${B64}` },
]);
console.log("mimo-v2.5 + image  :", JSON.stringify(r1));

// 2. plain text to mimo-v2.5
const r2 = await responsesTest("mimo-v2.5", "只回答一个数字：6+6=?");
console.log("mimo-v2.5 text     :", JSON.stringify(r2));

// 3. image to kimi-k3 (vision-capable upstream but translator strips for non-mimo) — expect OCR note
const r3 = await responsesTest("kimi-k3", [
  { type: "input_text", text: "这张图片是什么颜色？" },
  { type: "input_image", image_url: `data:image/png;base64,${B64}` },
]);
console.log("kimi-k3 + image    :", JSON.stringify(r3));

// 4. image to glm-5.3 (non-vision) — expect OCR strip note
const r4 = await responsesTest("glm-5.3", [
  { type: "input_text", text: "这张图片是什么颜色？" },
  { type: "input_image", image_url: `data:image/png;base64,${B64}` },
]);
console.log("glm-5.3 + image    :", JSON.stringify(r4));