class RubyLLM::Thinking

A Thinking holds the reasoning output a provider returned alongside a response. Instances appear on Message#thinking, and on Chunk#thinking while streaming, when the model exposes its thinking.

chat = RubyLLM.chat(model: 'claude-opus-4.5').with_thinking(effort: :high)
response = chat.ask "What is 15 * 23?"
response.thinking&.text
response.thinking&.signature