server: fix checkpoints creation (#22929)

* common : add common_chat_split_by_role

* cont : fix spans to reach end of message

* server: fix checkpoints creation

- extract message_spans from chat templates
- find the prompt token position before the latest user message
- split prompt batching at that position
- create a context checkpoint before the latest user input
- avoid periodic mid-prompt checkpoints when that position is known
- handle multimodal prompts when mapping text/template positions to server prompt tokens
- add --checkpoint-min-step to control minimum spacing between checkpoints

* cont : clean-up

* Support autoparser detection for message barriers

* server: fix message span delimiter and update docs

---------

Co-authored-by: Alde Rojas <hello@alde.dev>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Piotr Wilkin <piotr.wilkin@syndatis.com>

tools/server/server-common.cpp

@@ -1110,6 +1110,16 @@ json oaicompat_chat_params_parse(
         llama_params["chat_parser"] = chat_params.parser;
     }
 
+    llama_params["message_spans"] = json::array();
+
+    for (const auto & span : chat_params.message_spans) {
+        llama_params["message_spans"].push_back({
+            { "role", span.role },
+            { "pos",  span.pos  },
+            { "len",  span.len  },
+        });
+    }
+
     // Reasoning budget: pass parameters through to sampling layer
     {
         int reasoning_budget = opt.reasoning_budget;