feat : BaseToolParser.feed 增加可选 token_ids 参数

- format_chunk ABC 改为 (token, **kwargs)，body/token_ids 通过 kw 传入
- ProtocolHandler._handle_stream 逐 token encode 并透传
- Anthropic builder 用 **kwargs 吸收不使用的参数，零变更
- 新增 3 个 token_ids 参数测试

astrai/inference/api/openai.py

@@ -113,9 +113,10 @@ class OpenAIResponseBuilder(ResponseBuilder):
             )
         ]
 
-    def format_chunk(self, token: str, body: str) -> List[str]:
+    def format_chunk(self, token: str, **kwargs) -> List[str]:
+        body = kwargs.get("body", "")
         if self._parser is not None:
-            return self._format_tool_chunk(body)
+            return self._format_tool_chunk(body, **kwargs)
 
         return [
             sse_event(
@@ -135,8 +136,12 @@ class OpenAIResponseBuilder(ResponseBuilder):
             )
         ]
 
-    def _format_tool_chunk(self, body: str) -> List[str]:
-        deltas = self._parser.feed(body)
+    def _format_tool_chunk(self, body: str, **kwargs) -> List[str]:
+        deltas = self._parser.feed(
+            body,
+            current_token_ids=kwargs.get("current_token_ids"),
+            delta_token_ids=kwargs.get("delta_token_ids"),
+        )
         events: List[str] = []
         for d in deltas:
             if "content" in d: