mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-25 05:54:53 +00:00
cd95dd318a
Some checks failed
LiteLLM Rust / rust-lint (push) Waiting to run
LiteLLM Rust / rust-test (push) Waiting to run
LiteLLM Rust / rust-wheel (push) Waiting to run
Terraform Modules / fmt, validate, test (aws) (push) Has been cancelled
Terraform Modules / fmt, validate, test (gcp) (push) Has been cancelled
The OpenAI Responses transformation now raises max_output_tokens to the minimum of 16, strips Anthropic cache_control marks, decodes tool parameters sent as JSON strings and drops null fields from replayed reasoning items. Against OpenAI it also drops reasoning LiteLLM minted while bridging another provider and tool-call item ids OpenAI did not issue. Rewrites that read the model cost map or Python's regex engine (GPT-5 sampling rules, tool schema repair, prompt cache breakpoints) decline to the Python route |
||
|---|---|---|
| .. | ||
| cli | ||
| shared | ||
| strategies | ||
| __init__.py | ||
| __main__.py | ||
| AGENTS.md | ||
| conftest.py | ||