Add request rate limiting for users on OpenAI Usage tier 1

[jamiehaywood]

My current usage limits are pretty low (I'm not a prolific user of OpenAI API). I've not looked into the source code yet, but I suspect that micro-agent is sending more requests / using more tokens than the Usage tier 1 allows:

MODEL	TOKEN LIMITS	REQUEST AND OTHER LIMITS	BATCH QUEUE LIMITS
gpt-4o	30,000 TPM	500 RPM	90,000 TPD
gpt-3.5-turbo	60,000 TPM	500 RPM 10,000 RPD	200,000 TPD
gpt-4	10,000 TPM	500 RPM 10,000 RPD	100,000 TPD
gpt-4-turbo	30,000 TPM	500 RPM	90,000 TPD
text-embedding-3-small	1,000,000 TPM	3,000 RPM	3,000,000 TPD
dall-e-3		5 images per minute
tts-1		50 RPM
whisper-1		50 RPM