perf: minor fixes

pkg/platform/sources/webchat.yaml

@@ -10,17 +10,7 @@ metadata:
     zh_Hans: "用于流水线调试的网页聊天适配器"
   icon: ""
 spec:
-  config:
-    - name: enable-stream-reply
-      label:
-        en_US: Enable Stream Reply Mode
-        zh_Hans: 启用电报流式回复模式
-      description:
-        en_US: If enabled, the bot will use the stream of telegram reply mode
-        zh_Hans: 如果启用，将使用电报流式方式来回复内容
-      type: boolean
-      required: true
-      default: false
+  config: []
 execution:
   python:
     path: "webchat.py"

pkg/provider/entities.py

@@ -148,8 +148,6 @@ class MessageChunk(pydantic.BaseModel):
 
     tool_call_id: typing.Optional[str] = None
 
-    # tool_calls: typing.Optional[list[ToolCallChunk]] = None
-
     is_final: bool = False
 
     def readable_str(self) -> str:

pkg/provider/modelmgr/requester.py

@@ -98,7 +98,6 @@ class ProviderAPIRequester(metaclass=abc.ABCMeta):
         """
         pass
 
-    @abc.abstractmethod
     async def invoke_llm_stream(
         self,
         query: core_entities.Query,

pkg/provider/runners/localagent.py

@@ -116,7 +116,6 @@ class LocalAgentRunner(runner.RequestRunner):
                 query.use_llm_model,
                 req_messages,
                 query.use_funcs,
-                stream=is_stream,
                 extra_args=query.use_llm_model.model_entity.extra_args,
             ):  
                 assert isinstance(msg, llm_entities.MessageChunk)
@@ -178,10 +177,8 @@ class LocalAgentRunner(runner.RequestRunner):
                     query.use_llm_model,
                     req_messages,
                     query.use_funcs,
-                    stream=is_stream,
                     extra_args=query.use_llm_model.model_entity.extra_args, 
                 ):  
-                    assert isinstance(msg, llm_entities.MessageChunk)
                     yield msg
                 if msg.tool_calls:
                     for tool_call in msg.tool_calls: