litellm/litellm/responses
2026-08-29 18:11:58 -07:00
..
file_search refactor(repositories): type prisma table access with one generic protocol 2026-08-25 12:14:17 +00:00
litellm_completion_transformation fix(realtime): carry audio output tokens into response.done usage so Gemini Live native audio bills at the audio rate 2026-08-26 21:10:12 -07:00
mcp refactor(repositories): type prisma table access with one generic protocol 2026-08-25 12:14:17 +00:00
main.py feat(spend): report prompt caching savings as total and gateway-attributed (#38134) 2026-08-28 00:19:06 -07:00
sse_output_recovery.py refactor(repositories): type prisma table access with one generic protocol 2026-08-25 12:14:17 +00:00
streaming_iterator.py fix(proxy): emit timing headers and overhead for /v1/messages and /v1/responses (#38840) 2026-08-29 18:11:58 -07:00
utils.py fix(prompts): apply prompt templates before routing on /v1/responses and honor ignore_prompt_manager_model 2026-08-26 14:12:28 -07:00