Spring AI's retrieval of reasoning content from deep-thinking model responses is overly cumbersome. Can you provide a unified solution for obtaining reasoning content?
Currently, processing thinking content is very cumbersome, as follows:
`
AtomicBoolean atomicBoolean = new AtomicBoolean(false);
clientRequestSpec
.stream()
.chatResponse()
.doOnNext(response -> {
AssistantMessage output = response.getResult().getOutput();
String text = output.getText();
if(StringUtils.hasText(text)){
atomicBoolean.set(true);
}
boolean noThink = atomicBoolean.get();
if(!noThink){
String reasoningContent ;
if(output instanceof DeepSeekAssistantMessage deepSeekAssistantMessage){
reasoningContent = deepSeekAssistantMessage.getReasoningContent();
}else{
Map
}
})
.doOnError(error->{
String errorMsg = error.getMessage();
})
.doOnComplete(() -> {})
.subscribe();`
In LangChain4j, a dedicated interface for acquiring thinking content is provided, which is very convenient, as follows: `public interface TokenStream {
TokenStream onPartialResponse(Consumer<String> partialResponseHandler);
/**
* The provided consumer will be invoked every time a new partial thinking/reasoning text (usually a single token)
* from a language model is available.
*/
default TokenStream onPartialThinking(Consumer<PartialThinking> partialThinkingHandler) {
throw new UnsupportedOperationException("not implemented");
}
TokenStream onCompleteResponse(Consumer<ChatResponse> completeResponseHandler);
TokenStream onError(Consumer<Throwable> errorHandler);
} `
I hope to get your help. thanks!
Comment From: sunyuhan1998
This is a great suggestion. However, currently we only support retrieving the reasoning content in a few models, such as DeepSeek. To implement the capability mentioned in this issue—regardless of the specific form—it is essential to first enable reasoning retrieval across all models. As far as I know, the team is already working on this enhancement.