Reasoning Model Deepseek Reasoner

A UI renders deepseek-reasoner output by concatenating reasoning_content and content into one block shown to the end user.

Render content as the user-facing answer and treat reasoning_content (the chain-of-thought) as separate — surface it only behind an optional 'show reasoning' affordance. Do not merge the two fields into the displayed answer.

For multi-turn deepseek-reasoner chat, the client appends the full prior assistant message — including reasoning_content — into messages[] for the next request.

When constructing the next request, include only the prior assistant content (the final answer) and strip reasoning_content from the message before resending. Per docs, reasoning_content must not be passed back into the messages history.

deepseek-reasoner is streamed. Chunks first carry delta.reasoning_content, then later carry delta.content. The client appends every delta into one buffer.

Accumulate delta.reasoning_content into a reasoning buffer and delta.content into the answer buffer separately, switching as the stream transitions. Keep the two streams distinct so the user-visible answer excludes the CoT.