It's specific to the harness. Using dynamic context pruning, the budget cuts it off after a select amount of tokens and the budget message tells the model to use subgents to finish whatever it's thinking about
It's specific to the harness. Using dynamic context pruning, the budget cuts it off after a select amount of tokens and the budget message tells the model to use subgents to finish whatever it's thinking about
Nice. Does it use a summarization, or a hard cutoff?
llama.cpp uses a hard cutoff. The agent then does "something" that is specific to the agent's implementation and configuration. It might summarize and then "finish the thought" with a different model, and then resubmit the prompt to the llama.cpp API endpoint with <think>..</think> prefilled. The primary model then infers the remainder of the reply.