litellm/tests/rust-python-harness/strategies
narmstrong-berry 258f50dfd9 feat(rust): shape native OpenAI responses requests like Python
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
2026-10-19 08:30:59 -07:00
..
e2e_parity feat(rust): shape native OpenAI responses requests like Python 2026-10-19 08:30:59 -07:00
trace_parity docs(agents): ban semicolons and colons in human-facing text (#45684) 2026-10-09 16:36:32 -07:00
unit_tests_parity refactor(rust): remove gateway, config, router, realtime, and trace-parity infrastructure 2026-09-16 16:00:07 +00:00
unit_tests_rust refactor(rust): remove gateway, config, router, realtime, and trace-parity infrastructure 2026-09-16 16:00:07 +00:00
__init__.py test: add OCR python-to-rust test parity ledger (WIP) (#39434) 2026-09-02 19:22:52 -07:00