To many requests being sent out

[leofratu]

Plugin Type

VSCode Extension

App Version

4.111.9

Description

Kilo Code seems to be sending out way to many requests with Gemini 3.0 Pro Preview more then 100 per minute, hitting rate limits even on paid accounts. Also somehow fills out 1 million tokens per minute, Even it dose not contribute to cost , in UI it sends out about 4/5 Per minute but for some reason i get this.

Gemini generate context stream error: got status: 429 Too Many Requests. {"error":{"message":"{\n "error": {\n "code": 429,\n "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. To monitor your current usage, head to: https://ai.dev/usage?tab=rate-limit. \n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_paid_tier_input_token_count, limit: 1000000, model: gemini-3-pro\nPlease retry in 45.837906927s.",\n "status": "RESOURCE_EXHAUSTED",\n "details": [\n {\n "@type": "type.googleapis.com/google.rpc.Help",\n "links": [\n {\n "description": "Learn more about Gemini API quotas",\n "url": "https://ai.google.dev/gemini-api/docs/rate-limits"\n }\n ]\n },\n {\n "@type": "type.googleapis.com/google.rpc.QuotaFailure",\n "violations": [\n {\n "quotaMetric": "generativelanguage.googleapis.com/generate_content_paid_tier_input_token_count",\n "quotaId": "GenerateContentPaidTierInputTokensPerModelPerMinute",\n "quotaDimensions": {\n "location": "global",\n "model": "gemini-3-pro"\n },\n "quotaValue": "1000000"\n }\n ]\n },\n {\n "@type": "type.googleapis.com/google.rpc.RetryInfo",\n "retryDelay": "45s"\n }\n ]\n }\n}\n","code":429,"status":"Too Many Requests"}}

Retry attempt 3
Retrying now...

Reproduction steps

1. Use Gemini 3.0 on a existing codebsae somewhat large

Provider

Gemini AI Studio

Model

No response

System Information

No response

[leofratu]

Example - Gemini generate context stream error: got status: 429 Too Many Requests. {"error":{"message":"{\n "error": {\n "code": 429,\n "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. To monitor your current usage, head to: https://ai.dev/usage?tab=rate-limit. \n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_paid_tier_input_token_count, limit: 1000000, model: gemini-3-pro\nPlease retry in 35.959070268s.",\n "status": "RESOURCE_EXHAUSTED",\n "details": [\n {\n "@type": "type.googleapis.com/google.rpc.Help",\n "links": [\n {\n "description": "Learn more about Gemini API quotas",\n "url": "https://ai.google.dev/gemini-api/docs/rate-limits"\n }\n ]\n },\n {\n "@type": "type.googleapis.com/google.rpc.QuotaFailure",\n "violations": [\n {\n "quotaMetric": "generativelanguage.googleapis.com/generate_content_paid_tier_input_token_count",\n "quotaId": "GenerateContentPaidTierInputTokensPerModelPerMinute",\n "quotaDimensions": {\n "model": "gemini-3-pro",\n "location": "global"\n },\n "quotaValue": "1000000"\n }\n ]\n },\n {\n "@type": "type.googleapis.com/google.rpc.RetryInfo",\n "retryDelay": "35s"\n }\n ]\n }\n}\n","code":429,"status":"Too Many Requests"}}

Retry attempt 2
Retrying now...

KILO Code displaying a 10 tool calls total and 250K input tokens.

[chrarnoldus]

You have about 200k context, which means you will hit 1M input tokens after about 5 requests.

If you are unable to get higher rate limits, you can introduce a delay between requests with these settings under Providers > Advanced Settings:

Hope that helps.