run demo failed, Error: 400 Missing required parameter: 'response_format.json_schema'. (request id: 202412201428294827994785579509)

[hankunfang]

/Users/hankunfang/workspace/midscene-example/puppeteer-demo/node_modules/@midscene/web/dist/lib/puppeteer.js:1291
throw new Error(`${errorTask == null ? void 0 : errorTask.error}
^

Error: 400 Missing required parameter: 'response_format.json_schema'. (request id: 202412201428294827994785579509)
Error: 400 Missing required parameter: 'response_format.json_schema'. (request id: 202412201428294827994785579509)
at Function.generate (/Users/hankunfang/workspace/midscene-example/puppeteer-demo/node_modules/openai/src/error.ts:70:14)
at OpenAI.makeStatusError (/Users/hankunfang/workspace/midscene-example/puppeteer-demo/node_modules/openai/src/core.ts:397:21)
at OpenAI.makeRequest (/Users/hankunfang/workspace/midscene-example/puppeteer-demo/node_modules/openai/src/core.ts:460:24)
at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
at async call (/Users/hankunfang/workspace/midscene-example/puppeteer-demo/node_modules/@midscene/core/dist/lib/index.js:5530:22)
at async callToGetJSONObject (/Users/hankunfang/workspace/midscene-example/puppeteer-demo/node_modules/@midscene/core/dist/lib/index.js:5576:20)
at async callAiFn (/Users/hankunfang/workspace/midscene-example/puppeteer-demo/node_modules/@midscene/core/dist/lib/index.js:5608:32)
at async plan (/Users/hankunfang/workspace/midscene-example/puppeteer-demo/node_modules/@midscene/core/dist/lib/index.js:5895:30)
at async Object.executor (/Users/hankunfang/workspace/midscene-example/puppeteer-demo/node_modules/@midscene/web/dist/lib/puppeteer.js:839:24)
at async Executor.flush (/Users/hankunfang/workspace/midscene-example/puppeteer-demo/node_modules/@midscene/core/dist/lib/index.js:4607:25)
at PuppeteerAgent.aiAction (/Users/hankunfang/workspace/midscene-example/puppeteer-demo/node_modules/@midscene/web/dist/lib/puppeteer.js:1291:13)
at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
at async (/Users/hankunfang/workspace/midscene-example/puppeteer-demo/demo.ts:28:5)

[yuyutaotao]

配置了什么模型？

[hankunfang]

export MIDSCENE_MODEL_NAME=gpt-4o

[yuyutaotao]

再看下 @midscene/web 的版本号？

如果已经是最近的 latest 或者 beta，应该是没问题的才对。是否是 API 平台的问题？

[hankunfang]

"devDependencies": {
    "@midscene/web": "^0.8.7",
    "dotenv": "^16.4.5",
    "puppeteer": "^23.11.1",
    "ts-node": "^10.9.2",
    "tsx": "^4.19.1"
}

[hankunfang]

chrome 插件用相同的配置是ok的

[yuyutaotao]

试了一下，能跑通的，没排查思路了

能给我临时签发一个 token 来试跑么？ 发送到邮箱 yutao.tao # bytedance.com

[hankunfang]

刚问了公司，说没有临时的token。。。

[hankunfang]

这个是使用了哪个API？

[yuyutaotao]

我们刚在这个仓库里新增了可用性测试的目录：

https://github.com/web-infra-dev/midscene-example/tree/main/connectivity-test

你可以把它的用例运行起来，看看是 API 本身可用性的问题 or Midscene 的问题。