ed61932748
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> |
||
|---|---|---|
| .. | ||
| src | ||
| package.json | ||
| tsconfig.json | ||