Configuration options

是否应用提示词缓存。

缓存内容的生存时间。有效值： '5m' or '1h'。请注意，Amazon Nova 模型仅支持 '5m'.

开始缓存前的最小消息数。系统提示词算作一条消息。

使用不支持的模型时的行为。选项： 'ignore', 'warn', or 'raise'.

Full example

中间件将每个请求中的内容缓存至并包括最新消息。在 TTL 窗口内（5 分钟或 1 小时）的后续请求中，先前已处理的内容会从缓存中检索，而非重新处理，从而降低成本和延迟。

工作原理： 1. 第一个请求：系统提示词、函数和用户消息被发送到 API 并缓存 2. 第二个请求：从缓存中检索已缓存的内容。只需处理新消息 3. 每一轮都遵循此模式，每个请求都会重用缓存的对话历史

const getWeather = tool(
  async ({ city }) => `The weather in ${city} is sunny and 72F.`,
  {
    name: "get_weather",
    description: "Get the current weather for a city.",
    schema: z.object({ city: z.string() }),
  }
);

// System prompt must exceed 1,024 tokens for caching to take effect
const LONG_PROMPT =
  "You are a helpful weather assistant with deep expertise in meteorology, " +
  "climate science, and atmospheric phenomena. When answering questions about " +
  "weather, provide accurate and up-to-date information. " +
  "You should always strive to give the most helpful response possible. ".repeat(85);

const agent = createAgent({
  model: new ChatBedrockConverse({ model: "us.anthropic.claude-sonnet-4-5-20250929-v1:0" }),
  systemPrompt: LONG_PROMPT,
  tools: [getWeather],
  middleware: [bedrockPromptCachingMiddleware({ ttl: "5m" })], // [!code highlight]
});

// First invocation: writes the cache (system prompt, tool definitions, and message)
let response = await agent.invoke({
  messages: [new HumanMessage("What is the weather in Miami?")],
});
const last = response.messages.at(-1);
console.log(last?.content);

// Check cache token usage
if (AIMessage.isInstance(last)) {
  const details = last.usage_metadata?.input_token_details;
  if (details) {
    console.log(`Cache read: ${details.cache_read ?? 0}, Cache write: ${details.cache_creation ?? 0}`);
  }
}

// Second invocation within the TTL: reuses the cached system prompt and tool definitions
response = await agent.invoke({
  messages: [new HumanMessage("How about Seattle?")],
});
console.log(response.messages.at(-1)?.content);