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>

common/common.cpp

@@ -445,6 +445,27 @@ std::string string_strip(const std::string & str) {
     return str.substr(start, end - start);
 }
 
+std::string string_lcs(std::string_view a, std::string_view b) {
+    if (a.empty() || b.empty()) return {};
+
+    std::vector<std::vector<size_t>> dp(a.size() + 1, std::vector<size_t>(b.size() + 1, 0));
+    size_t best_len = 0;
+    size_t best_end_a = 0;
+
+    for (size_t i = 1; i <= a.size(); ++i) {
+        for (size_t j = 1; j <= b.size(); ++j) {
+            if (a[i - 1] == b[j - 1]) {
+                dp[i][j] = dp[i - 1][j - 1] + 1;
+                if (dp[i][j] > best_len) {
+                    best_len = dp[i][j];
+                    best_end_a = i;
+                }
+            }
+        }
+    }
+    return std::string(a.substr(best_end_a - best_len, best_len));
+}
+
 std::string string_get_sortable_timestamp() {
     using clock = std::chrono::system_clock;