[halfwhey]

Might be a dumb question but do you have to read the files in the same order in new sessions to ensure the correct prefix for the cache?

[weiliddat]

Also curious. With tool calls reading/searching different files, possible compacting reading a large codebase / long threads, I can't imagine how you hit 99% cache rate.

[WatchDog]

Yes, you have to use the same session, I guess you could load up a bunch of context, then fork the session into a few different tasks, although I haven't tried it.

[naaqq]

Sorry, I was wrong here. I meant a single long session. And there’s no compression, the 1M context is only half used.

[gbgarbeb]

Then where did 200M come from? 200,000 tokens?

[naaqq]

Not all read tokens are included in the context, many of the tokens are from read cache hits. I hit it many times so it grew to 200M. The number came from the API platform.