LightAgent 0.2.8__tar.gz → 0.2.85__tar.gz

{lightagent-0.2.8 → lightagent-0.2.85}/LightAgent/la_core.py

@@ -11,6 +11,7 @@ import logging
 import os
 import httpx
 import importlib
+from openai.types.chat import ChatCompletionChunk
 
 # 全局工具注册表
 _FUNCTION_MAPPINGS = {}  # 工具名称 -> 工具函数
@@ -18,7 +19,7 @@ _FUNCTION_INFO = {}   # 工具名称 -> 工具info信息
 _OPENAI_FUNCTION_SCHEMAS = []  # OpenAI 格式的工具描述
 _PROMPT_FUNCTION_SCHEMAS = []  # prompt 格式的工具描述
 
-__version__ = "0.2.8"  # 你可以根据需要设置版本号
+__version__ = "0.2.85"  # 你可以根据需要设置版本号
 
 
 def register_tool_manually(tools: List[Union[str, Callable]]) -> bool:
@@ -154,7 +155,7 @@ def get_tools_str() -> str:
 
 
 class LightAgent:
-    __version__ = "0.2.1"  # 将版本号放在类中
+    __version__ = "0.2.85"  # 将版本号放在类中
 
     def __init__(
             self,
@@ -478,15 +479,19 @@ class LightAgent:
                 output = ""
                 function_call_name = ""
                 tool_calls = response.choices[0].message.tool_calls
-                self.log("DEBUG", "tool_calls", {"tool_calls": tool_calls})
+                self.log("DEBUG", "non_stream tool_calls", {"tool_calls": tool_calls})
 
                 # 遍历所有工具调用
                 for tool_call in tool_calls:
                     function_call = tool_call.function
-                    self.log("DEBUG", "function_call", {"function_call": function_call.model_dump()})
 
+                    # 尝试自动修复常见转义问题
+                    fixed_args = function_call.arguments.replace('\\"', '"').replace('\\\\', '\\')
+                    self.log("DEBUG", "non_stream function_call", {"function_call": fixed_args})
+
+                    function_args = json.loads(fixed_args)
                     # 解析函数参数
-                    function_args = json.loads(function_call.arguments)
+                    # function_args = json.loads(function_call.arguments)
 
                     # 调用工具并获取响应
                     tool_response = dispatch_tool(function_call.name, function_args)
@@ -495,7 +500,7 @@ class LightAgent:
 
                     # 如果工具返回的是生成器（流式输出），则将所有 chunk 叠加
                     if isinstance(tool_response, Generator):
-                        # print(f"Streaming response from tool: {function_call.name}")
+                        print(f"Streaming response from tool: {function_call.name}")
                         for chunk in tool_response:
                             # print("Received chunk:", chunk)  # 打印每个 chunk
                             if function_call_name == 'finish':
@@ -520,16 +525,18 @@ class LightAgent:
                     else:
                         # print(f"Non-streaming response from tool: {function_call.name}")
                         combined_response = tool_response
+                        # print("tool_response type:",type(combined_response))
                         # 如果是 JSON 字符串，解析并转换为中文
                         if isinstance(combined_response, str):
                             try:
                                 combined_response = json.loads(combined_response)  # 解析 JSON
                                 combined_response = json.dumps(combined_response, ensure_ascii=False)  # 转换为中文
                             except json.JSONDecodeError:
+                                combined_response = tool_response
                                 pass  # 如果不是 JSON 字符串，保持原样
                         tool_responses.append(combined_response)  # 直接添加普通响应
 
-                    self.log("INFO", "tool_response", {"tool_response": combined_response})
+                    self.log("INFO", "non_stream tool_response", {"tool_response": combined_response})
 
                     # 将工具调用的结果添加到列表中
                     tool_responses.append(combined_response)
@@ -560,8 +567,13 @@ class LightAgent:
             # 更新响应
             if function_call_name == 'finish':
                 return  # 如果最后调用了finish工具，则结束生成器
-            # print(params)
-            response = self.client.chat.completions.create(**params)
+            # print("params:",params)
+            self.log("DEBUG", "chat-completions params", {"params": params})
+
+            try:
+                response = self.client.chat.completions.create(**params)
+            except Exception as e:
+                print(f"An error occurred: {e}")
 
         # 重试次数用尽
         self.log("ERROR", "max_retry_reached", {"message": "Failed to generate a valid response."})
@@ -653,14 +665,17 @@ class LightAgent:
                                         combined_response = ""
                                         for chunk in tool_response:
                                             # 将工具返回的数据继续流出
-                                            tool_output = {
-                                                "name": tool_call["name"],
-                                                "title": _FUNCTION_INFO.get(tool_call["name"], {}).get(
-                                                    'tool_title') or '',
-                                                "output": chunk,
-                                            }
-                                            self.log("INFO", "tool_call", {"tool_output": tool_output})
-                                            yield tool_output
+                                            if isinstance(chunk, ChatCompletionChunk):
+                                                yield chunk
+                                            else:
+                                                tool_output = {
+                                                    "name": tool_call["name"],
+                                                    "title": _FUNCTION_INFO.get(tool_call["name"], {}).get(
+                                                        'tool_title') or '',
+                                                    "output": chunk,
+                                                }
+                                                self.log("INFO", "tool_call", {"tool_output": tool_output})
+                                                yield tool_output
                                             # 将工具的调用信息推送给开发者
                                             if function_call_name == 'finish':
                                                 content = chunk.choices[0].delta.content or ""
@@ -669,8 +684,11 @@ class LightAgent:
                                                 combined_response += chunk  # 将每个 chunk 叠加
                                         tool_responses.append(combined_response)  # 将叠加后的完整响应添加到列表
                                     else:
-                                        # print(f"Non-streaming response from tool: {function_call['name']}")
-                                        tool_responses.append(tool_response)  # 直接添加普通响应
+                                        # print(f"Non-streaming response from tool: {tool_response}")
+                                        combined_response = tool_response
+                                        tool_responses.append(combined_response)  # 直接添加普通响应
+                                    self.log("INFO", "stream tool_response", {"tool_response": combined_response})
+
 
                             except json.JSONDecodeError as e:
                                 self.log("ERROR", "json_decode_error",
@@ -702,6 +720,7 @@ class LightAgent:
             # 更新响应
             if function_call_name == 'finish':
                 return  # 如果最后调用了finish工具，则结束生成器
+            self.log("DEBUG", "chat-completions params", {"params": params})
             response = self.client.chat.completions.create(**params)
 
         # 重试次数用尽
@@ -1087,4 +1106,4 @@ class LightSwarm:
 if __name__ == "__main__":
     # Example of registering and using a tool
     print("This is LightAgent")
-    # print(dispatch_tool("example_tool", {"param1": "test"}))
+    # print(dispatch_tool("example_tool", {"param1": "test"}))

{lightagent-0.2.8 → lightagent-0.2.85}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: LightAgent
-Version: 0.2.8
+Version: 0.2.85
 Summary: **LightAgent** is an extremely lightweight active Agentic Framework with memory (`mem0`), tools (`Tools`), and a Tree of Thought (`ToT`). It supports swarm-like multi-agent collaboration, automated tool generation, and agent assessment, with underlying model support for OpenAI, Zhipu ChatGLM, Baichuan Large Model, DeepSeek R1, Qwen series large models, and more. At the same time, LightAgent supports OpenAI streaming format API service output, seamlessly integrating with major mainstream chat frameworks. 🌟
 Home-page: https://github.com/wxai-space/LightAgent
 License: Apache 2.0
@@ -356,6 +356,7 @@ def get_weather(
 # Define tool information inside the function
 get_weather.tool_info = {
     "tool_name": "get_weather",
+    "tool_title": "get weather",
     "tool_description": "Get current weather information for the specified city.",
     "tool_params": [
         {"name": "city_name", "description": "The name of the city to query", "type": "string", "required": True},
@@ -378,6 +379,7 @@ def search_news(
 # Define tool information inside the function
 search_news.tool_info = {
     "tool_name": "search_news",
+    "tool_title": "search news",
     "tool_description": "Search news based on keywords.",
     "tool_params": [
         {"name": "keyword", "description": "Search keyword", "type": "string", "required": True},
@@ -1077,6 +1079,7 @@ def get_weather(
 # 在函数内部定义工具信息
 get_weather.tool_info = {
     "tool_name": "get_weather",
+    "tool_name": "获取天气",
     "tool_description": "获取指定城市的当前天气信息",
     "tool_params": [
         {"name": "city_name", "description": "要查询的城市名称", "type": "string", "required": True},
@@ -1099,6 +1102,7 @@ def search_news(
 # 在函数内部定义工具信息
 search_news.tool_info = {
     "tool_name": "search_news",
+    "tool_name": "联网搜索",
     "tool_description": "根据关键词搜索新闻",
     "tool_params": [
         {"name": "keyword", "description": "搜索关键词", "type": "string", "required": True},

{lightagent-0.2.8 → lightagent-0.2.85}/README.md

@@ -335,6 +335,7 @@ def get_weather(
 # Define tool information inside the function
 get_weather.tool_info = {
     "tool_name": "get_weather",
+    "tool_title": "get weather",
     "tool_description": "Get current weather information for the specified city.",
     "tool_params": [
         {"name": "city_name", "description": "The name of the city to query", "type": "string", "required": True},
@@ -357,6 +358,7 @@ def search_news(
 # Define tool information inside the function
 search_news.tool_info = {
     "tool_name": "search_news",
+    "tool_title": "search news",
     "tool_description": "Search news based on keywords.",
     "tool_params": [
         {"name": "keyword", "description": "Search keyword", "type": "string", "required": True},

{lightagent-0.2.8 → lightagent-0.2.85}/README.zh-CN.md

@@ -339,6 +339,7 @@ def get_weather(
 # 在函数内部定义工具信息
 get_weather.tool_info = {
     "tool_name": "get_weather",
+    "tool_name": "获取天气",
     "tool_description": "获取指定城市的当前天气信息",
     "tool_params": [
         {"name": "city_name", "description": "要查询的城市名称", "type": "string", "required": True},
@@ -361,6 +362,7 @@ def search_news(
 # 在函数内部定义工具信息
 search_news.tool_info = {
     "tool_name": "search_news",
+    "tool_name": "联网搜索",
     "tool_description": "根据关键词搜索新闻",
     "tool_params": [
         {"name": "keyword", "description": "搜索关键词", "type": "string", "required": True},

{lightagent-0.2.8 → lightagent-0.2.85}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "LightAgent"
-version = "0.2.8"
+version = "0.2.85"
 description = "**LightAgent** is an extremely lightweight active Agentic Framework with memory (`mem0`), tools (`Tools`), and a Tree of Thought (`ToT`). It supports swarm-like multi-agent collaboration, automated tool generation, and agent assessment, with underlying model support for OpenAI, Zhipu ChatGLM, Baichuan Large Model, DeepSeek R1, Qwen series large models, and more. At the same time, LightAgent supports OpenAI streaming format API service output, seamlessly integrating with major mainstream chat frameworks. 🌟"
 authors = ["caiweige <caiweige@qq.com>"]
 license = "Apache 2.0"