chore: bump version to 4.8.1

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langbot"
-version = "4.8.0"
+version = "4.8.1"
 description = "Production-grade platform for building agentic IM bots"
 readme = "README.md"
 license-files = ["LICENSE"]

src/langbot/__init__.py

@@ -1,3 +1,3 @@
 """LangBot - Production-grade platform for building agentic IM bots"""
 
-__version__ = '4.8.0'
+__version__ = '4.8.1'

src/langbot/pkg/provider/modelmgr/requesters/deepseekchatcmpl.py

@@ -25,7 +25,7 @@ class DeepseekChatCompletions(chatcmpl.OpenAIChatCompletions):
         use_funcs: list[resource_tool.LLMTool] = None,
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
-    ) -> provider_message.Message:
+    ) -> tuple[provider_message.Message, dict]:
         self.client.api_key = use_model.provider.token_mgr.get_token()
 
         args = {}
@@ -57,4 +57,11 @@ class DeepseekChatCompletions(chatcmpl.OpenAIChatCompletions):
         # 处理请求结果
         message = await self._make_msg(resp, remove_think)
 
-        return message
+        # Extract token usage from response
+        usage_info = {}
+        if hasattr(resp, 'usage') and resp.usage:
+            usage_info['input_tokens'] = resp.usage.prompt_tokens or 0
+            usage_info['output_tokens'] = resp.usage.completion_tokens or 0
+            usage_info['total_tokens'] = resp.usage.total_tokens or 0
+
+        return message, usage_info

src/langbot/pkg/provider/modelmgr/requesters/modelscopechatcmpl.py

@@ -130,7 +130,7 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
         use_funcs: list[resource_tool.LLMTool] = None,
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
-    ) -> provider_message.Message:
+    ) -> tuple[provider_message.Message, dict]:
         self.client.api_key = use_model.provider.token_mgr.get_token()
 
         args = {}
@@ -162,7 +162,10 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
         # 处理请求结果
         message = await self._make_msg(resp)
 
-        return message
+        # ModelScope uses streaming, usage info not available
+        usage_info = {}
+
+        return message, usage_info
 
     async def _req_stream(
         self,

src/langbot/pkg/provider/modelmgr/requesters/moonshotchatcmpl.py

@@ -26,7 +26,7 @@ class MoonshotChatCompletions(chatcmpl.OpenAIChatCompletions):
         use_funcs: list[resource_tool.LLMTool] = None,
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
-    ) -> provider_message.Message:
+    ) -> tuple[provider_message.Message, dict]:
         self.client.api_key = use_model.provider.token_mgr.get_token()
 
         args = {}
@@ -57,4 +57,11 @@ class MoonshotChatCompletions(chatcmpl.OpenAIChatCompletions):
         # 处理请求结果
         message = await self._make_msg(resp, remove_think)
 
-        return message
+        # Extract token usage from response
+        usage_info = {}
+        if hasattr(resp, 'usage') and resp.usage:
+            usage_info['input_tokens'] = resp.usage.prompt_tokens or 0
+            usage_info['output_tokens'] = resp.usage.completion_tokens or 0
+            usage_info['total_tokens'] = resp.usage.total_tokens or 0
+
+        return message, usage_info

web/src/app/home/pipelines/PipelineDetailDialog.tsx

@@ -211,7 +211,7 @@ export default function PipelineDialog({
                         : t('pipelines.debugDialog.disconnected')}
                     </span>
                   </div>
-                  <div className="ml-auto">
+                  <div className="ml-auto mr-4">
                     <Button
                       variant="outline"
                       size="sm"