fixed streaming responses token count

Author: antonpirker

sentry_sdk/integrations/openai.py

@@ -286,6 +286,7 @@ async def new_iterator_async():
             # type: () -> AsyncIterator[ChatCompletionChunk]
             with capture_internal_exceptions():
                 async for x in old_iterator:
+                    # OpenAI chat completion API
                     if hasattr(x, "choices"):
                         choice_index = 0
                         for choice in x.choices:
@@ -297,6 +298,11 @@ async def new_iterator_async():
                                     data_buf.append([])
                                 data_buf[choice_index].append(content or "")
                             choice_index += 1
+                    # OpenAI responses API
+                    elif hasattr(x, "delta"):
+                        if len(data_buf) == 0:
+                            data_buf.append([])
+                        data_buf[0].append(x.delta or "")
                     yield x
                 if len(data_buf) > 0:
                     all_responses = list(map(lambda chunk: "".join(chunk), data_buf))