server: improve user message detection and create checkpoints at every user message (#24176)

* server : improve message span logic

* cont : cast size_t to int32_t in comparisons

* server : create checkpoints before every user msg

* chat : remove \n in gemma4 delimiters

* chat : merge msg delimiter structs into one

* cont : reword comment

* cont : initialize tokens in delimiter

* cont : add server_tokens::get_raw_tokens() for mtmd

* cont : move message finding to server_tokens and skip mtmd tokens

* cont : update cohere2moe parser

* cont : increase min-step to 8192 and always produce a chkpt for last user message

tools/server/server-common.h

@@ -218,6 +218,9 @@ public:
 
     size_t get_common_prefix(const server_tokens & b) const;
 
+    // split the tokens into message spans, skipping over media chunks
+    common_chat_msg_spans find_message_spans(const common_chat_msg_delimiters & delims) const;
+
     // make sure all text tokens are within the vocab range
     bool validate(const struct llama_context * ctx) const;