litellm/tests/test_litellm/completion_extras
mateo-berri 429ad06972 fix(guardrails): write structured_messages rewrites back into /v1/responses input
Message-rewriting guardrails such as Headroom return their rewrite in
structured_messages and leave texts untouched. The responses guardrail
translation only mapped texts back, so compression never reached the
upstream request on /v1/responses while the retrieve tool still got
injected. Convert the returned messages back to Responses input (plus
instructions) the way the chat and Anthropic handlers already do, and
keep developer messages as input_text in the chat-to-responses bridge.

Resolves LIT-6494
2026-08-29 14:23:57 -07:00
..
litellm_responses_transformation fix(guardrails): write structured_messages rewrites back into /v1/responses input 2026-08-29 14:23:57 -07:00
__init__.py Litellm oss staging 030626 (#29578) 2026-06-03 11:01:51 -07:00
test_litellm_responses_transformation_transformation.py fix(litellm): support OpenAI chat completions custom tool calls end to end 2026-08-01 11:26:09 -07:00
test_responses_bridge_provider_propagation.py fix: bedrock mantle fixes (#30083) 2026-06-12 07:25:16 -07:00