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.
alt Hacker News
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.