mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-07-01 05:08:12 +00:00
d09e3f4544
LiteLLM returns provider usage as-is, nesting cache-read / cache-creation / reasoning counts under provider-specific shapes (e.g. prompt_tokens_details.cached_tokens, Anthropic-style cache_read_input_tokens). Surface them as flat cached_prompt_tokens / reasoning_tokens / cache_creation_tokens keys so the span pipeline can read them; prompt / completion / total token counts are left untouched.