diff --git a/apps/application/tests/test_langchain_compatibility.py b/apps/application/tests/test_langchain_compatibility.py
index ffd29b409a1..b0f107e0110 100644
--- a/apps/application/tests/test_langchain_compatibility.py
+++ b/apps/application/tests/test_langchain_compatibility.py
@@ -16,6 +16,8 @@
 from botocore.exceptions import ClientError
 from django.test import SimpleTestCase
 from langchain_core.messages import AIMessage, AIMessageChunk, HumanMessage, SystemMessage, ToolMessage
+from langchain_core.outputs import ChatGeneration, ChatResult
+from langchain_openai import ChatOpenAI
 from openai import RateLimitError
 
 from application.workflow.backend import sandbox_shell
@@ -61,6 +63,52 @@ def llm_node():
 
 
 class LangChainMessageCompatibilityTests(SimpleTestCase):
+    def test_empty_stream_falls_back_to_invoke(self):
+        model = openai_model(streaming=True)
+        expected = AIMessage(content="fallback")
+
+        def empty_stream(*args, **kwargs):
+            return
+            yield
+
+        with (
+            patch.object(ChatOpenAI, "_stream", new=empty_stream),
+            patch.object(
+                ChatOpenAI,
+                "_generate",
+                return_value=ChatResult(generations=[ChatGeneration(message=expected)]),
+            ) as generate,
+        ):
+            chunks = list(model.stream([HumanMessage(content="hello")]))
+
+        self.assertEqual("".join(chunk.content for chunk in chunks), "fallback")
+        generate.assert_called_once()
+
+    def test_empty_async_stream_falls_back_to_ainvoke(self):
+        model = openai_model(streaming=True)
+        expected = AIMessage(content="fallback")
+
+        async def empty_stream(*args, **kwargs):
+            return
+            yield
+
+        with (
+            patch.object(ChatOpenAI, "_astream", new=empty_stream),
+            patch.object(
+                ChatOpenAI,
+                "_agenerate",
+                new=AsyncMock(return_value=ChatResult(generations=[ChatGeneration(message=expected)])),
+            ) as agenerate,
+        ):
+            chunks = asyncio.run(self._collect_async_stream(model))
+
+        self.assertEqual("".join(chunk.content for chunk in chunks), "fallback")
+        agenerate.assert_awaited_once()
+
+    @staticmethod
+    async def _collect_async_stream(model):
+        return [chunk async for chunk in model.astream([HumanMessage(content="hello")])]
+
     async def test_complete_messages_preserve_text_tools_metadata_and_input(self):
         contents = [
             "你好",
diff --git a/apps/models_provider/impl/base_chat_open_ai.py b/apps/models_provider/impl/base_chat_open_ai.py
index f35641257f8..3ecc911a509 100644
--- a/apps/models_provider/impl/base_chat_open_ai.py
+++ b/apps/models_provider/impl/base_chat_open_ai.py
@@ -5,6 +5,7 @@
 
 from langchain_core.language_models import LanguageModelInput
 from langchain_core.messages import (
+    AIMessage,
     BaseMessage,
     get_buffer_string,
     BaseMessageChunk,
@@ -130,16 +131,24 @@ def get_num_tokens(self, text: str) -> int:
         )
 
     def _stream(self, *args: Any, **kwargs: Any) -> Iterator[ChatGenerationChunk]:
+        chunk = None
         for chunk in super()._stream(*args, **kwargs):
             if chunk.message.usage_metadata is not None:
                 self.usage_metadata = chunk.message.usage_metadata
             yield chunk
+        if chunk is None:
+            message = cast(AIMessage, self.invoke(*args, **{**kwargs, "stream": False}))
+            yield ChatGenerationChunk(message=AIMessageChunk(**message.model_dump(exclude={"type"})))
 
     async def _astream(self, *args: Any, **kwargs: Any) -> AsyncIterator[ChatGenerationChunk]:
+        chunk = None
         async for chunk in super()._astream(*args, **kwargs):
             if chunk.message.usage_metadata is not None:
                 self.usage_metadata = chunk.message.usage_metadata
             yield chunk
+        if chunk is None:
+            message = cast(AIMessage, await self.ainvoke(*args, **{**kwargs, "stream": False}))
+            yield ChatGenerationChunk(message=AIMessageChunk(**message.model_dump(exclude={"type"})))
 
     def _convert_chunk_to_generation_chunk(
         self,