diff --git a/assets/wechat.jpg b/assets/wechat.jpg
index cfc353527..3dde06d24 100644
Binary files a/assets/wechat.jpg and b/assets/wechat.jpg differ
diff --git a/dbgpt/app/openapi/api_v1/api_v1.py b/dbgpt/app/openapi/api_v1/api_v1.py
index 6c3dd0d86..87b69634e 100644
--- a/dbgpt/app/openapi/api_v1/api_v1.py
+++ b/dbgpt/app/openapi/api_v1/api_v1.py
@@ -439,9 +439,7 @@ async def stream_generator(chat, incremental: bool, model_name: str):
         _type_: streaming responses
     """
     span = root_tracer.start_span("stream_generator")
-    msg = "[LLM_ERROR]: llm server has no output, maybe your prompt template is wrong."
 
-    stream_id = f"chatcmpl-{str(uuid.uuid1())}"
     previous_response = ""
     async for chunk in chat.stream_call():
         if chunk:
@@ -453,7 +451,7 @@ async def stream_generator(chat, incremental: bool, model_name: str):
                     delta=DeltaMessage(role="assistant", content=incremental_output),
                 )
                 chunk = ChatCompletionStreamResponse(
-                    id=stream_id, choices=[choice_data], model=model_name
+                    id=chat.chat_session_id, choices=[choice_data], model=model_name
                 )
                 yield f"data: {chunk.json(exclude_unset=True, ensure_ascii=False)}\n\n"
             else:
diff --git a/dbgpt/client/client.py b/dbgpt/client/client.py
index bb064f227..eccbd26ae 100644
--- a/dbgpt/client/client.py
+++ b/dbgpt/client/client.py
@@ -247,7 +247,7 @@ class Client:
             if response.status_code == 200:
                 async for line in response.aiter_lines():
                     try:
-                        if line == "data: [DONE]\n":
+                        if line.strip() == "data: [DONE]":
                             break
                         if line.startswith("data:"):
                             json_data = json.loads(line[len("data: ") :])