会话修剪

Session pruning trims ''old tool results'' from the in-memory context right before each LLM call. It does ''not'' rewrite the on-disk session history (''*.jsonl'').

- ''mode: "cache-ttl"''但启用在、会话的最后一个人間消息但''ttl''比旧場合。

- Only affects the messages sent to the model for that request.

- Only active for Anthropic API calls (and OpenRouter Anthropic models).

- For best results, match ''ttl'' to your model ''cacheControlTtl''.

- After a prune, the TTL window resets so subsequent requests keep cache until ''ttl'' expires again.

修剪是工具结果在仅適用被：

- ''tool_result''消息

- ''tool_use'' messages are ''not pruned'' (needed for the LLM to know which tool it called)

Currently supported strategies:

- Context size reduction: old tool results are removed, making context smaller

- Cost reduction: API calls are made with smaller context, reducing costs

ReferenceConceptsSessionPruningPage step 03: P4

有效使用会话修剪的最佳实践：

- Match TTL to models' ''cacheControlTtl''

{

"sessionPruning": {

"mode": "cache-ttl",

如果修剪未按预期工作，请进行故障排除：

- Claude 3.5 Sonnet：''cacheControlTtl''

- Confirm you're using Anthropic API (doesn't work with other providers)

- Confirm the session's last human message is older than TTL

修剪在是下一个限制有：

- Anthropic API（以及OpenRouter Anthropic模型）在仅機能执行

修剪的动作监控执行在是、日志确认执行：

- Only works with Anthropic API (and OpenRouter Anthropic models)

- Only tool results are pruned (other message types are not affected)

- 修剪後的上下文大小但日志在显示被

要监控修剪行为，请检查日志：

```json

{

"sessionPruning": {

有效使用会话修剪的最佳实践：

- Match TTL to models' ''cacheControlTtl''

如果修剪未按预期工作，请进行故障排除：

- Confirm TTL value matches models' ''cacheControlTtl''

- Confirm you're using Anthropic API (doesn't work with other providers)

- Confirm the session's last human message is older than TTL

- Check logs to confirm pruning is running

ReferenceConceptsSessionPruningPage step 11: P6

ReferenceConceptsSessionPruningPage step 11: P7

会话修剪是防止长会话中上下文膨胀的强大工具。使用基于TTL的修剪策略，您可以删除旧的工具结果，减少上下文大小，并改善成本和性能。

{
  agent: {
    contextPruning: { mode: "off" },
  },
}

It works with Anthropic API and coordinates with model cache control settings to provide optimal results.

{
  agent: {
    contextPruning: { mode: "cache-ttl", ttl: "5m" },
  },
}

ReferenceConceptsSessionPruningPage step 12: P3

{
  agent: {
    contextPruning: {
      mode: "cache-ttl",
      tools: { allow: ["exec", "read"], deny: ["*image*"] },
    },
  },
}

ReferenceConceptsSessionPruningPage step 12: P4