No, server-side compaction is inherently tied to the model's current context. This uses a full side prompt to get the compaction result, then swap the context with new compaction result. I did a bunch of tests and the results from Luna were indistinguishable from Sol
Is this using the server side compaction of the responses API?
No, server-side compaction is inherently tied to the model's current context. This uses a full side prompt to get the compaction result, then swap the context with new compaction result. I did a bunch of tests and the results from Luna were indistinguishable from Sol