From 5c3c1b68a6992c125b48852d7ce3dd3850a02fbd Mon Sep 17 00:00:00 2001
From: luukunn <83932082+luukunn@users.noreply.github.com>
Date: Mon, 18 Aug 2025 14:49:40 +0800
Subject: [PATCH] Feature/online/vs think 20250813 (#3451)

* add stream

* fix ernie_vl_reasoning_parsers

* fix bug

* fix finish reason
---
 fastdeploy/entrypoints/openai/serving_chat.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fastdeploy/entrypoints/openai/serving_chat.py b/fastdeploy/entrypoints/openai/serving_chat.py
index 26d7597ad..5ca8898ab 100644
--- a/fastdeploy/entrypoints/openai/serving_chat.py
+++ b/fastdeploy/entrypoints/openai/serving_chat.py
@@ -443,7 +443,7 @@ class OpenAIServingChat:
         max_tokens = request.max_completion_tokens or request.max_tokens
         if has_no_token_limit or previous_num_tokens != max_tokens:
             choice.finish_reason = "stop"
-            if self.engine_client.reasoning_parser == "ernie_x1" and output.get("finish_reason", "") == "tool_calls":
+            if output.get("tool_call"):
                 choice.finish_reason = "tool_calls"
         else:
             choice.finish_reason = "length"