That is normal for this model. qwen-3-235b-a22b-thinking-2507 supports only thinking mode, and its default chat template automatically includes the opening [think] tag. So the model output legitimately contains only the closing [/think] without an explicit opening tag. It is a template difference between the two models, not something wrong with your streaming code. Source: https://github.com/Cerebras/cerebras-cloud-sdk-python/issues/10
Source: https://github.com/Cerebras/cerebras-cloud-sdk-python/issues/10