Rate limit tokens per minute #1086
Description
Hi!
First of all thanks for what seems like a great framework! Seems like so much thought was put into this, well done!
Secondly, I'm hitting a rate limit quota when using google Gemini and the playwright MCP. The moment the rate limit is hit, the execution stops. Is there a way of limiting the speed of the agent execution in order to not hit the ceiling of tokens per minute?
Agent setup:
Agent(
instructions="You are an autonomous agent...",
api_key = api_key,
llm="gemini/gemini-2.5-flash",
tools=MCP(
command="npx",
args=["@playwright/mcp@latest"],
timeout=120,
),
self_reflect=True,
verbose=True
)The error I'm getting:
{
"error": {
"code": 429,
"message": "You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits.",
"status": "RESOURCE_EXHAUSTED",
"details": [
{
"@type": "type.googleapis.com/google.rpc.QuotaFailure",
"violations": [
{
"quotaMetric": "generativelanguage.googleapis.com/generate_content_paid_tier_input_token_count",
"quotaId": "GenerateContentPaidTierInputTokensPerModelPerMinute",
"quotaDimensions": {
"location": "global",
"model": "gemini-2.5-flash"
},
"quotaValue": "1000000"
}
]
},
{
"@type": "type.googleapis.com/google.rpc.Help",
"links": [
{
"description": "Learn more about Gemini API quotas",
"url": "https://ai.google.dev/gemini-api/docs/rate-limits"
}
]
},
{
"@type": "type.googleapis.com/google.rpc.RetryInfo",
"retryDelay": "58s"
}
]
}
}