mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-03-31 21:25:59 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix(llama-cpp): Set enable_thinking in the correct place (#8973)

Browse Source 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
This commit is contained in:
Richard Palethorpe
2026-03-12 12:32:29 +00:00
committed by GitHub
parent 45d18813bd
commit b24ca51287
1 changed files with 10 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
backend/cpp/llama-cpp/grpc-server.cpp
View File

@@ -1348,11 +1348,14 @@ public:
body_json["min_p"] = data["min_p"];
}
// Pass metadata fields to body_json
// Pass enable_thinking via chat_template_kwargs (where oaicompat_chat_params_parse reads it)
const auto& metadata = request->metadata();
auto et_it = metadata.find("enable_thinking");
if (et_it != metadata.end()) {
body_json["enable_thinking"] = (et_it->second == "true");
if (!body_json.contains("chat_template_kwargs")) {
body_json["chat_template_kwargs"] = json::object();
}
body_json["chat_template_kwargs"]["enable_thinking"] = (et_it->second == "true");
}
// Debug: Print full body_json before template processing (includes messages, tools, tool_choice, etc.)
@@ -2071,11 +2074,14 @@ public:
body_json["min_p"] = data["min_p"];
}
// Pass metadata fields to body_json
// Pass enable_thinking via chat_template_kwargs (where oaicompat_chat_params_parse reads it)
const auto& predict_metadata = request->metadata();
auto predict_et_it = predict_metadata.find("enable_thinking");
if (predict_et_it != predict_metadata.end()) {
body_json["enable_thinking"] = (predict_et_it->second == "true");
if (!body_json.contains("chat_template_kwargs")) {
body_json["chat_template_kwargs"] = json::object();
}
body_json["chat_template_kwargs"]["enable_thinking"] = (predict_et_it->second == "true");
}
// Debug: Print full body_json before template processing (includes messages, tools, tool_choice, etc.)