tokenizer: support multiple end-of-generation tokens

Track an ordered eos_token_ids list (not just one id) and add is_eos().
gpt-oss/harmony ends the assistant turn on <|return|> and also treats
<|call|> and <|endoftext|> as terminators (generation_config.json
eos_token_id = [200002, 199999, 200012]); single-eos families are
unchanged.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

crates/xserv-tokenizer/src/bpe.rs

@@ -12,6 +12,7 @@ pub struct Tokenizer {
     special_token_ids: HashMap<u32, String>,
     pre_tokenize_re: Regex,
     eos_token_id: Option<u32>,
+    eos_token_ids: Vec<u32>,
     byte_fallback: bool,
 }
 
@@ -102,11 +103,27 @@ impl Tokenizer {
             decoder.resize(decoder.len().max(at.id as usize + 1), vec![]);
             decoder[at.id as usize] = at.content.as_bytes().to_vec();
         }
-        let eos_token_id = special_tokens
-            .get("<|im_end|>")
-            .or_else(|| special_tokens.get("<|end_of_text|>"))
-            .or_else(|| special_tokens.get("<|endoftext|>"))
-            .copied();
+        // End-of-generation tokens, in priority order. Families differ:
+        // Qwen uses <|im_end|>, Llama <|end_of_text|>, GPT-2 <|endoftext|>.
+        // gpt-oss (harmony) ends the assistant turn with <|return|> and also
+        // treats <|call|> (tool call) and <|endoftext|> as terminators
+        // (see generation_config.json eos_token_id = [200002, 199999, 200012]).
+        let eos_names = [
+            "<|im_end|>",
+            "<|end_of_text|>",
+            "<|return|>",
+            "<|call|>",
+            "<|endoftext|>",
+        ];
+        let mut eos_token_ids: Vec<u32> = Vec::new();
+        for name in eos_names {
+            if let Some(&id) = special_tokens.get(name) {
+                if !eos_token_ids.contains(&id) {
+                    eos_token_ids.push(id);
+                }
+            }
+        }
+        let eos_token_id = eos_token_ids.first().copied();
 
         // Pre-tokenization regex
         let pre_tokenize_re = if byte_fallback {
@@ -125,6 +142,7 @@ impl Tokenizer {
             special_token_ids,
             pre_tokenize_re,
             eos_token_id,
+            eos_token_ids,
             byte_fallback,
         }
     }
@@ -249,6 +267,12 @@ impl Tokenizer {
         self.eos_token_id
     }
 
+    /// True if `id` is any end-of-generation token (a model may have several;
+    /// gpt-oss/harmony ends on <|return|>, <|call|>, or <|endoftext|>).
+    pub fn is_eos(&self, id: u32) -> bool {
+        self.eos_token_ids.contains(&id)
+    }
+
     pub fn vocab_size(&self) -> usize {
         self.decoder.len()
     }