common/parser: add proper reasoning tag prefill reading (#20424)

* Implement proper prefill extraction

* Refactor cli parameters, update docs, move reasoning budget sampler part to common/reasoning-budget.cpp

* Update tools/server/server-task.cpp

* refactor: move grammars to variant, remove grammar_external, handle exception internally

* Make code less C++y

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Piotr Wilkin (ilintar) 2026-03-19 16:58:21 +01:00 committed by GitHub
parent c1258830b2
commit 5e54d51b19
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
33 changed files with 651 additions and 454 deletions

View file

@ -282,7 +282,7 @@ static void render_scenario(const common_chat_template & tmpl,
LOG_ERR("Messages:\n%s\n", final_messages.dump(2).c_str());
try {
autoparser::templates_params inputs;
autoparser::generation_params inputs;
inputs.messages = final_messages;
inputs.add_generation_prompt = add_generation_prompt;
inputs.extra_context["enable_thinking"] = enable_thinking;
@ -395,7 +395,7 @@ int main(int argc, char ** argv) {
analysis.analyze_template(chat_template);
// Generate Parser
autoparser::templates_params params;
autoparser::generation_params params;
params.messages = json::array({ build_user_message() });
params.reasoning_format =
opts.enable_reasoning ? COMMON_REASONING_FORMAT_DEEPSEEK : COMMON_REASONING_FORMAT_NONE;