full chat implemented

src/engine/tokenizer.rs

@@ -209,6 +209,24 @@ impl Tokenizer {
         output
     }
 
+    pub(super) fn encode_continuation(&self, prompt: &str, reasoning: ReasoningMode) -> Vec<i32> {
+        let mut output = Vec::new();
+        if self.family == ModelFamily::DeepSeek {
+            output.push(self.eos);
+        }
+        output.push(self.user);
+        output.extend(self.tokenize(prompt));
+        output.push(self.assistant);
+        if reasoning != ReasoningMode::Direct {
+            output.push(self.think_start);
+        } else if self.family == ModelFamily::Glm {
+            output.extend([self.think_start, self.think_end]);
+        } else {
+            output.push(self.think_end);
+        }
+        output
+    }
+
     pub(super) fn eos(&self) -> i32 {
         self.eos
     }