Faultiness

感谢您的回复和解释。 请问有无计划提供批量导出录播地址以便使用其它工具进行下载的功能？

Same error ``` FAIL: test_lm_score_may_fail_numerically_for_external_meliad (__main__.LmInferenceTest) ---------------------------------------------------------------------- Traceback (most recent call last): File "/export/data/username/imo/alphageometry/lm_inference_test.py", line 82, in test_lm_score_may_fail_numerically_for_external_meliad self.assertEqual( AssertionError: Lists differ: [-1.1633697, -1.122621] != [-1.1860729455947876, -1.1022869348526] First differing element...

又一个时代的落幕... 祝好😢

Update: The error happened on line 44, which is the login part belonging to `TelnetShell` class, not `TelnetShellG2HPro`. Failed to login due to different login methods. I copied the `login()`...

This is just so f*** stupid. Such a simple function surprisingly has no official implementation.

遇到相同问题 运行约20分钟后浏览器崩溃 日志中无报错信息 使用配置： mac 15.3.1 + chrome 144.0.7390.77 commit 01dc676版本

> 请发后台详细报错日志，方便排查 遇到相同问题，稳定触发方式如下： ``` curl http://localhost:8002/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer " \ -d '{ "model": "gemini-2.5-flash-preview-04-17", "messages": [ {"role": "system", "content": "You are a professional translator."},...

It would be great if deep research were supported, as I have many automated processes that need to use this. Looking forward to the update :-)