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>

common/chat-auto-parser-helpers.h

@@ -1,6 +1,7 @@
 #pragma once
 
 #include "chat-auto-parser.h"
+#include "peg-parser.h"
 #include <functional>
 #include <optional>
 #include <string>
@@ -57,6 +58,11 @@ std::vector<segment> segmentize_markers(const std::string & text);
 //                                   (MARKER, "</function>"), (MARKER, "</tool_call>") ]
 std::vector<segment> prune_whitespace_segments(const std::vector<segment> & segments);
 
+// Wrap parser with generation prompt parser
+common_peg_parser wrap_for_generation_prompt(common_chat_peg_builder &             p,
+                                             const common_peg_parser &             prs,
+                                             const autoparser::generation_params & inputs,
+                                             const std::string &                   reasoning_start = {});
 namespace autoparser {
 
 // Apply a template with the given parameters, returning the rendered string (empty on failure)