mtmd: fix silent prompt truncation on embedded NUL (#25548)

* mtmd: fix silent prompt truncation on embedded NUL

mtmd_input_text carried the prompt as a bare const char* with no
length, so a NUL byte in message content cut the prompt at the
tokenizer boundary and dropped every later message plus the assistant
marker, with no log. Add an explicit text_len and thread it through,
matching llama_tokenize and the text only path.

* cleanup

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>

tools/mtmd/mtmd-cli.cpp

@@ -250,7 +250,8 @@ static int eval_message(mtmd_cli_context & ctx, common_chat_msg & msg) {
     LOG_DBG("formatted_chat.prompt: %s\n", formatted_chat.c_str());
 
     mtmd_input_text text;
-    text.text          = formatted_chat.c_str();
+    text.text          = formatted_chat.data();
+    text.text_len      = formatted_chat.size();
     text.add_special   = add_bos;
     text.parse_special = true;
 

tools/mtmd/mtmd.cpp

@@ -809,7 +809,7 @@ void mtmd_free(mtmd_context * ctx) {
 struct mtmd_tokenizer {
     mtmd_context * ctx;
 
-    std::string input_text;
+    std::string input_text; // note: can contain null bytes; do not use c_str()
     bool add_special;
     bool parse_special;
     const llama_vocab * vocab;
@@ -839,9 +839,10 @@ struct mtmd_tokenizer {
             size_t n_bitmaps) : ctx(ctx) {
         add_special   = text->add_special;
         parse_special = text->parse_special;
-        input_text    = text->text;
         vocab         = ctx->vocab;
 
+        input_text.assign(text->text, text->text_len);
+
         std::vector<const mtmd_bitmap *> bitmaps(bmps, bmps + n_bitmaps);
         auto parts_str = split_text(input_text, ctx->media_marker);
         size_t i_bm = 0;

tools/mtmd/mtmd.h

@@ -67,6 +67,7 @@ struct mtmd_batch;
 
 struct mtmd_input_text {
     const char * text;
+    size_t text_len;
     bool add_special;
     bool parse_special;
 };

tools/server/server-common.cpp

@@ -705,7 +705,8 @@ server_tokens process_mtmd_prompt(mtmd_context * mctx, const std::string & promp
     std::vector<server_tokens> inputs;
     // multimodal
     mtmd_input_text inp_txt = {
-        prompt.c_str(),
+        prompt.data(),
+        prompt.size(),
         /* add_special */   true,
         /* parse_special */ true,
     };