before this change, we estimate the token count of the contents to cache and use it to compare with the threshold user set. but that's not precise , so we use the actual prompt token count of previous llm request.
We won't create cache for the very initial request
PiperOrigin-RevId: 814484840
1. add a context cache config in app level which will apply to all agents in the app
2. pass on cache config through invocation context to llm_reqeust
3. store cache metadata in llm_response
4. lookup old cache metadata from latest event for reusing old cache
5. create new cache if old cache cannot be reused
PiperOrigin-RevId: 809158578
Xiang (Sean) ZhouandCopybara-Service