llm runtime_error ai_generated true

警告：由于系统消息在请求之间发生变化，提示缓存已禁用

Warning: Prompt caching disabled because system message changed between requests

ID: llm/prompt-caching-ignored-with-system-message-change

其他格式: JSON · Markdown 中文 · English
90%修复率
86%置信度
1证据数
2024-06-01首次发现

版本兼容性

版本状态引入弃用备注
anthropic-python>=0.25.0 active — — —
claude-3-opus-20240229 active — — —
claude-3-sonnet-20240229 active — — —

根因分析

LLM API 提示缓存（如 Anthropic 的提示缓存）要求跨请求的系统消息相同才能重用缓存前缀；任何更改都会使缓存失效。

English

LLM API prompt caching (e.g., Anthropic's prompt caching) requires identical system messages across requests to reuse cached prefixes; any change invalidates the cache.

generic

官方文档

https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching

解决方案

  1. Ensure system messages are identical across requests that should benefit from caching. Use a template system: `system_message = {"role": "system", "content": [{"type": "text", "text": "You are a helpful assistant.", "cache_control": {"type": "ephemeral"}}]}` and reuse this object.
  2. If system message must change, structure the prompt so that the variable part is in the user message, keeping system message static. Example: system = "You are a math tutor.", user = "Solve: {problem}".
  3. Monitor cache metrics via API response headers (e.g., `x-should-cache`) to verify caching is working.

无效尝试

常见但无效的做法:

  1. 90% 失败

    This defeats the purpose of caching and actually guarantees cache misses.

  2. 70% 失败

    Caching is most effective on system messages; user messages vary too much to benefit from caching.

  3. 80% 失败

    The warning indicates caching is disabled; ignoring it means paying for full compute on every request.