can not trace LLM-calls in Langfuse using 'qwen3-vl-plus' model, but in Langsmith it worked

[eanson023]

{
"devDependencies": {
"@midscene/web": "^1.0.3",
"@playwright/test": "^1.57.0",
"playwright": "^1.57.0",
"tsx": "^4.21.0"
},
"dependencies": {
"crypto": "^1.0.1",
"dotenv": "^17.2.3",
"langfuse": "^3.38.6",
"langsmith": "^0.4.2"
}
}

can not trace LLM-calls in Langfuse using 'qwen3-vl-plus' model, but in Langsmith it worked

[yuyutaotao]

Did you see the log says 'DEBUGGING MODE: langfuse wrapper enabled' in your command line ?

[eanson023]

"DEBUGGING MODE: langfuse wrapper enabled" is in the log, but not in langfuse. I tried other models too, not just qwen.

my code is following:

import { chromium } from 'playwright';
import { PlaywrightAgent } from '@midscene/web/playwright';
import 'dotenv/config'; // read environment variables from .env file

const sleep = (ms) => new Promise((r) => setTimeout(r, ms));

Promise.resolve(
  (async () => {
    const browser = await chromium.launch({
      headless: false, // 'true' means we can't see the browser window
      args: ['--no-sandbox', '--disable-setuid-sandbox'],
    });

    const page = await browser.newPage();
    await page.setViewportSize({
      width: 1280,
      height: 768,
    });
    await page.goto('https://www.ebay.com');
    await sleep(5000); // 👀 init Midscene agent
    const agent = new PlaywrightAgent(page,{
        modelConfig: {
                MIDSCENE_MODEL_BASE_URL: "xxxx",
                MIDSCENE_MODEL_API_KEY: "xxxx",
                MIDSCENE_MODEL_NAME: "qwen3-vl-plus",
                MIDSCENE_MODEL_FAMILY: "qwen3-vl"
            },
    });

    // 👀 type keywords, perform a search
    await agent.aiAct('type "Headphones" in search box, hit Enter, get the first item in the list, then Tap, then wait for the loading, and scroll down');

    await browser.close();
  })(),
);

[Z-feiyao]

What progress has been made on this issue?