scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-15 09:12:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 311
litellm/ui
History
Exact
mateo-berri 61479093dd fix(decisions): forward OpenAI-format bodies to OpenAI and Azure deployments as sent 
An OpenAI or Azure OpenAI deployment on /v1/decisions now gets the caller's body unchanged, with model set to the deployment's model and LiteLLM settings removed, instead of a body rebuilt from the internal request shape. Fields LiteLLM does not model yet (developer messages, input_json parts, prompt cache breakpoints, array instructions, more than 128 questions) reach OpenAI, and OpenAI's answers come back as sent. Deployments of other providers keep translating and still answer 400 before calling the provider.
2026-11-03 04:00:24 -08:00
..
docker-entrypoint.d feat(helm): support a separate hostname per component in the componentized deploy (#46360) 2026-10-14 14:56:36 -07:00
litellm-dashboard fix(decisions): forward OpenAI-format bodies to OpenAI and Azure deployments as sent 2026-11-03 04:00:24 -08:00
Dockerfile build(docker): refresh base images and ship only runtime files in component images (#48279) 2026-10-24 22:33:45 -07:00
nginx.conf feat(helm): support a separate hostname per component in the componentized deploy (#46360) 2026-10-14 14:56:36 -07:00