upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-02 16:10:48 -05:00
Code Issues Packages Projects Releases Wiki Activity

cli : persist reasoning_content in chat history (#26362)

Browse Source 
* cli : persist reasoning_content in chat history

llama-cli collected reasoning from the stream for display but only
stored assistant content in messages, so --reasoning-preserve could
not re-inject prior thoughts on later turns.
This commit is contained in:
Nico
2026-08-01 12:03:32 -04:00
committed by GitHub
parent de699957b9
commit c629da565c
1 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tools/cli/cli-context.cpp
View File

@@ -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";