Add GLM 5.3 Flash support

src/engine/tokenizer.rs

@@ -1,5 +1,8 @@
 use super::gguf::Gguf;
-use super::{ChatTurn, ModelFamily};
+use super::{
+    ChatTurn, ModelFamily, VISION_END_TOKEN, VISION_IMAGE_TOKEN, VISION_START_TOKEN,
+    VISION_TOKEN_END, VISION_TOKEN_START,
+};
 use crate::settings::ReasoningMode;
 use std::collections::HashMap;
 
@@ -160,6 +163,22 @@ impl Tokenizer {
         let mut span = 0;
         let mut position = 0;
         while position < bytes.len() {
+            if bytes[position..].starts_with(VISION_TOKEN_START.as_bytes())
+                && let Some(relative_end) =
+                    text[position + VISION_TOKEN_START.len()..].find(VISION_TOKEN_END)
+            {
+                let count_start = position + VISION_TOKEN_START.len();
+                let count_end = count_start + relative_end;
+                if let Ok(count) = text[count_start..count_end].parse::<usize>() {
+                    self.tokenize_plain(&text[span..position], &mut output);
+                    output.push(VISION_START_TOKEN);
+                    output.extend(std::iter::repeat_n(VISION_IMAGE_TOKEN, count));
+                    output.push(VISION_END_TOKEN);
+                    position = count_end + VISION_TOKEN_END.len();
+                    span = position;
+                    continue;
+                }
+            }
             let special = self
                 .rendered_specials
                 .iter()