ai-agents-streaming-error-hand-azurechatopenai-with-streaming-enabled-fails-with--ef589fff

THEN Detect whether the model supports streaming before calling stream(). If not, fall back to a non-streaming generation method like invoke(). Alternatively, provide a parameter to force streaming off when instantiating AzureChatOpenAI, e.g., streaming=False. Also handle content filter errors (openai.BadRequestError with code content_filter) gracefully instead of raising an assertion.

class AzureChatOpenAI:
    def stream(self, prompt):
        if not self.supports_streaming:
            # fallback to non-streaming generation
            return self.generate(prompt)
        # ... existing streaming code ...