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> |
||
|---|---|---|
| .. | ||
| claude-for-chrome-mcp | ||
| computer-use-input | ||
| computer-use-mcp | ||
| computer-use-swift | ||
| ink | ||
| model-provider | ||