Skip to content

LLM inference in C/C++

C++ ggml

cli : persist reasoning_content in chat history (#26362)

Nicoc629da565c80
diff --git a/tools/cli/cli-context.cpp b/tools/cli/cli-context.cpp
index 0de8f69025..3d801b73d4 100644
--- a/tools/cli/cli-context.cpp
+++ b/tools/cli/cli-context.cpp
@@ -624,10 +624,14 @@ int cli_context::run() {
generated_content content;
generate_completion(content, timings);
- impl->messages.push_back({
+ json assistant_msg = {
{"role", "assistant"},
{"content", content.content}
- });
+ };
+ if (!content.reasoning.empty()) {
+ assistant_msg["reasoning_content"] = content.reasoning;
+ }
+ impl->messages.push_back(std::move(assistant_msg));
if (output_file) {
std::string out_content = "Assistant:\n";