# 警告：由于系统消息在请求之间发生变化，提示缓存已禁用

- **ID:** `llm/prompt-caching-ignored-with-system-message-change`
- **领域:** llm
- **类别:** runtime_error
- **验证级别:** ai_generated
- **修复率:** 90%

## 根因

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。

## 版本兼容性

| 版本 | 状态 | 引入 | 弃用 |
|------|------|------|------|
| anthropic-python>=0.25.0 | active | — | — |
| claude-3-opus-20240229 | active | — | — |
| claude-3-sonnet-20240229 | active | — | — |

## 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

- **** — This defeats the purpose of caching and actually guarantees cache misses. (90% 失败率)
- **** — Caching is most effective on system messages; user messages vary too much to benefit from caching. (70% 失败率)
- **** — The warning indicates caching is disabled; ignoring it means paying for full compute on every request. (80% 失败率)