最近一段时间有空的时候在研究如何降低openclaw的token消耗
因为基本上如果一天不干什么不和它对话的话，也要吞掉我十几二十刀的gpt5.4额度
于是看了一下平常的请求，发现heartbeat这个操作真耗token啊，动不动一个请求就90k token 
这费用还是我给openclaw打了缓存补丁之后，要是没打补丁更是上天
我的heartbeat相关配置之前是这样的，当时就是直接照抄了站内的教程（我记得是两篇巨长的文章）
"heartbeat": {
"every": "30m",
"target": "last",
"directPolicy": "allow"
},
然后我发现请求体里面一直在同一个session重复 “Read HEARTBEAT.md …”, 都重复一百多次了！
{
"model": "gpt-5.4",
"input": [
{
"role": "developer",
"content": "You are a personal assistant running inside OpenClaw.\n## Tooling\nTool availabili...[42548 chars]"
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": (省略。。。)
}
]
},
{
"type": "message",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "I'll check HEARTBEAT.md for any periodic tasks.",
"annotations": []
}
],
"status": "completed",
"id": "msg_1"
},
(省略一堆function call。。。)
{
"type": "message",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "Memory maintenance was already done today (2026-04-03). The backup notification ...[63 chars]",
"annotations": []
}
],
"status": "completed",
"id": "msg_5"
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[311 chars]"
}
]
},
"...[159 more items]"
],
"tools": [
(省略。。。)
],
"reasoning": {
"effort": "high",
"summary": "auto"
},
(省略。。。)
"instructions": (省略。。。)
}
然后我就把这个问题丢给codex了，让我添加这两个配置：
"heartbeat": {
"every": "30m",
"isolatedSession": true,
"lightContext": true,
"target": "none",
"directPolicy": "allow"
},
isolatedSession写成true的意思是，heartbeat 会在“没有 prior conversation history 的 isolated session”里运行，能明显减少token消耗- 如果再启用
lightContext，那么比如AGENTS.md、USER.md、TOOLS.md、MEMORY.md之类的bootstrap文件就不会在heartbeat的时候注入（只有HEARTBEAT.md会被注入上下文）。所以如果你的HEARTBEAT.md写的很明确，告诉openclaw要读哪个文件要干什么，那就完全可以开启，进一步节省token. 如果HEARTBEAT.md写的很模糊，需要openclaw综合你的AGENTS.md,MEMORY.md之类的进行综合判断，那可能还是别加了。 - "target"改为none，就防止heartbeat的消息和用户消息放的太近
修改后，我的heartbeat请求基本上只有10k左右token了
每次的请求体也明显干净多了
{
"model": "gpt-5.4",
"input": [
{
"role": "developer",
"content": "You are a personal assistant running inside OpenClaw.\n## Tooling\nTool availabili...[36009 chars]"
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not i...[313 chars]"
}
]
}
],
"tools": [
(省略。。。)
],
"reasoning": {
"effort": "high",
"summary": "auto"
},
"instructions": (省略。。。)
这样heartbeat就不会带一堆重复的heartbeat请求了 