Yassin Kortam cb3a7accdd fix(streaming): surface in-body error payloads on OpenAI-compatible streams (#32237) ... * fix(streaming): surface in-body error payloads on OpenAI-compatible streams vLLM and sglang return HTTP 200 streams whose SSE body carries the error, e.g. data: {"error": {"message": "...", "code": 400}}. The OpenAI-compatible chunk parser had no detection for this shape: since #23931 the payload parsed into an empty chunk (choices=[]) and the stream ended silently with 200, losing the provider's error and never attempting configured fallbacks. Detect the payload in OpenAIChatCompletionStreamingHandler.chunk_parser and raise OpenAIError with the upstream message and status code. The existing mid-stream gate then applies: 4xx surface directly to the client, 5xx wrap into MidStreamFallbackError so the router can run configured fallbacks. Fixes #25492 * fix(streaming): serialize messageless error payloads as JSON Address review feedback: an error dict without a message field now serializes via json.dumps instead of Python dict repr		2026-07-06 08:13:25 -07:00
..
guardrail_translation	Litellm OSS Staging 010626 (#29422)	2026-06-01 21:42:51 -07:00
__init__.py	Guardrail API - support tool call checks on OpenAI /chat/completions, OpenAI /responses, Anthropic /v1/messages (#17459)	2025-12-03 21:20:39 -08:00
test_openai_gpt_transformation.py	fix(streaming): surface in-body error payloads on OpenAI-compatible streams (#32237)	2026-07-06 08:13:25 -07:00