Sameer Kankute 21a21e01f7 fix(responses): use OpenAI SSEDecoder for Responses API streaming (#28566) ... * fix(responses): use OpenAI SSEDecoder for Responses API streaming httpx aiter_lines() uses str.splitlines(), which splits on U+2028 inside JSON payloads and silently drops response.completed (no spend log). Use openai._streaming.SSEDecoder (bytes.splitlines before decode) instead. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(responses): drop redundant SSE prefix strip after SSEDecoder switch SSEDecoder already strips the 'data:' field prefix from each event, so the extra call to _strip_sse_data_from_chunk on sse.data was redundant and could incorrectly mangle payloads whose actual content starts with 'data:'. Co-authored-by: Yassin Kortam <yassin@berri.ai> --------- Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: Yassin Kortam <yassin@berri.ai>		2026-05-22 10:03:36 -07:00
..
file_search	fix(ci): resolve mypy and ruff lint failures	2026-04-15 21:12:51 -07:00
litellm_completion_transformation	Litellm oss staging 1 (#28337)	2026-05-20 17:27:03 -07:00
mcp	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
main.py	Litellm oss staging 1 (#28337)	2026-05-20 17:27:03 -07:00
sse_output_recovery.py	Litellm oss staging 04 21 2026 2 (#26569)	2026-05-20 21:25:19 -07:00
streaming_iterator.py	fix(responses): use OpenAI SSEDecoder for Responses API streaming (#28566)	2026-05-22 10:03:36 -07:00
utils.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00