Missing cached token information for OpenAI

[golbin]

The OpenAI usage includes the following information, but only Anthropic services store cached token details:

"usage": {
  "prompt_tokens": 2006,
  "completion_tokens": 300,
  "total_tokens": 2306,
  "prompt_tokens_details": {
    "cached_tokens": 1920
  },
  "completion_tokens_details": {
    "reasoning_tokens": 0
  }
}

I noticed that it's being prepared as shown below. It might be better to transition this to the OpenAI service:

pipecat/src/pipecat/services/openai_realtime_beta/events.py

Line 367 in ca15d97

class TokenDetails(BaseModel):

[vipyne]

Thanks @golbin, Would you be up to making a PR with the changes you envision?