master

Roman-Andrfeat(llm-client): thread cached input tokens through Usage into trace spans

02471552创建于 13 天前历史提交

文件	最后提交记录	最后更新时间
src	feat(llm-client): thread cached input tokens through Usage into trace spans Account for cache-read tokens end to end: - Usage carries cached_tokens (OpenAI prompt_tokens_details.cached_tokens; Anthropic cache_read_input_tokens), threaded into LLM_CALL / TURN trace spans. - Anthropic marks cache_control ephemeral on the stable system-prefix block ONLY, never the volatile Context block, so the breakpoint is read back across turns instead of being rewritten every turn. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>	13 天前
Cargo.toml	rename hook crate name	2 个月前