OpenAI's prompt_tokens includes cached tokens, but Anthropic's
input_tokens semantic excludes them. The adapter was mapping
prompt_tokens → input_tokens verbatim, causing downstream code
(cache hit rate, cost, autocompact) to double-count.
Real-world impact: DeepSeek returns prompt_tokens=34097 with
cached_tokens=34048, displayed as 50% hit rate instead of 99.86%.
Co-Authored-By: glm-5.1 <zai-org@claude-code-best.win>
ed61932748