mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-11 08:38:24 +00:00
73aaf9e3da
* fix(mistral): forward prompt_cache_key to the Mistral API * fix(mistral): send prompt_cache_key only to Mistral's API and accept reasoning_effort on devstral and code-agent models * fix(mistral): keep the upstream api_base out of the prompt_cache_key rejection message * fix(mistral): honor allowed_openai_params for prompt_cache_key and gate codestral async and env hosts * test(mistral): annotate the new adapter prompt_cache_key tests * fix(mistral): drop or reject a prompt_cache_key the Mistral API cannot take A non-ASCII prompt_cache_key gets a 500 from api.mistral.ai, and a non-string one a 422, so both now drop under drop_params and answer 400 without it, like any value the provider cannot take. The /v1/messages adapter derives no key from a non-ASCII Claude Code session for Mistral, and the 400 names the caller's provider, so a codestral deployment's error says codestral. * fix(mistral): send a reasoning_effort object as its level and keep UnsupportedParamsError on sync calls * fix(mistral): keep async codestral file uploads working by not rewriting the caller's file blocks |
||
|---|---|---|
| .. | ||
| adapters | ||
| context_management | ||
| native | ||
| responses_adapters | ||
| __init__.py | ||
| conftest.py | ||
| test_advisor_orchestration.py | ||
| test_anthropic_native_passthrough_spend_logging.py | ||
| test_caller_model_checks.py | ||
| test_convertible_blocks.py | ||
| test_reasoning_effort_fields.py | ||
| test_safeguards.py | ||
| test_stream_assembly.py | ||