feat: update new models glm-5.2 and support reasoning_effort

README.md

@@ -11,7 +11,7 @@
 ## ✨ Core Features
 
 ### 🤖 **Chat Completions**
-- **Standard Chat**: Create chat completions with various models including `glm-5.1`
+- **Standard Chat**: Create chat completions with various models including `glm-5.2`
 - **Streaming Support**: Real-time streaming responses for interactive applications
 - **Tool Calling**: Function calling capabilities for enhanced AI interactions
 - **Multimodal Chat**: Image understanding capabilities with vision models
@@ -104,7 +104,7 @@ client = ZhipuAiClient(api_key="your-api-key")
 
 # Create chat completion
 response = client.chat.completions.create(
-    model="glm-5.1",
+    model="glm-5.2",
     messages=[
         {"role": "user", "content": "Hello, Z.ai!"}
     ]
@@ -278,7 +278,7 @@ client = ZaiClient(api_key="your-api-key")
 
 try:
     response = client.chat.completions.create(
-        model="glm-5.1",
+        model="glm-5.2",
         messages=[
             {"role": "user", "content": "Hello, Z.ai!"}
         ]

README_CN.md

@@ -11,7 +11,7 @@
 ## ✨ 核心功能
 
 ### 🤖 **对话补全**
-- **标准对话**: 支持 `glm-5.1` 等多种模型的对话补全
+- **标准对话**: 支持 `glm-5.2` 等多种模型的对话补全
 - **流式支持**: 实时流式响应，适用于交互式应用
 - **工具调用**: 函数调用能力，增强 AI 交互体验
 - **多模态对话**: 支持图像理解的视觉模型
@@ -106,7 +106,7 @@ client = ZhipuAiClient(api_key="your-api-key")
 
 # Create chat completion
 response = client.chat.completions.create(
-    model="glm-5.1",
+    model="glm-5.2",
     messages=[
         {"role": "user", "content": "Hello, Z.ai!"}
     ]
@@ -285,7 +285,7 @@ client = ZaiClient(api_key="your-api-key")  # 请填写您自己的APIKey
 
 try:
     response = client.chat.completions.create(
-        model="glm-5.1",
+        model="glm-5.2",
         messages=[
             {"role": "user", "content": "你好， Z.ai ！"}
         ]

examples/basic_usage.py

@@ -6,7 +6,7 @@ def completion():
 
 	# Create chat completion
 	response = client.chat.completions.create(
-		model='glm-5.1',
+		model='glm-5.2',
 		messages=[{'role': 'user', 'content': 'Hello, Z.ai!'}],
 		temperature=1.0,
 	)
@@ -19,7 +19,7 @@ def completion_with_stream():
 
 	# Create chat completion
 	response = client.chat.completions.create(
-		model='glm-5.1',
+		model='glm-5.2',
 		messages=[
 			{'role': 'system', 'content': 'You are a helpful assistant.'},
 			{'role': 'user', 'content': 'Tell me a story about AI.'},
@@ -38,7 +38,7 @@ def completion_with_websearch():
 
 	# Create chat completion
 	response = client.chat.completions.create(
-		model='glm-5.1',
+		model='glm-5.2',
 		messages=[
 			{'role': 'system', 'content': 'You are a helpful assistant.'},
 			{'role': 'user', 'content': 'What is artificial intelligence?'},
@@ -66,7 +66,7 @@ def completion_with_mcp_server_url():
 
 	# Create chat completion with MCP server URL
 	response = client.chat.completions.create(
-		model='glm-5.1',
+		model='glm-5.2',
 		stream=False,
 		messages=[{'role': 'user', 'content': 'Hello, please introduce GPT?'}],
 		tools=[
@@ -95,7 +95,7 @@ def completion_with_mcp_server_label():
 
 	# Create chat completion with MCP server label
 	response = client.chat.completions.create(
-		model='glm-5.1',
+		model='glm-5.2',
 		stream=False,
 		messages=[{'role': 'user', 'content': 'Hello, please introduce GPT?'}],
 		tools=[
@@ -217,7 +217,7 @@ def ofZai():
     client = ZaiClient()
     print(client.base_url)
     response = client.chat.completions.create(
-        model='glm-5.1',
+        model='glm-5.2',
         messages=[{'role': 'user', 'content': 'Hello, Z.ai!'}],
         temperature=0.7,
     )
@@ -227,7 +227,7 @@ def ofZhipu():
 	client = ZhipuAiClient()
 	print(client.base_url)
 	response = client.chat.completions.create(
-		model='glm-5.1',
+		model='glm-5.2',
 		messages=[{'role': 'user', 'content': 'Hello, Z.ai!'}],
 		temperature=0.7,
 	)

examples/glm_example.py

@@ -23,7 +23,7 @@ def stream_web_search_example():
     }]
     client = ZaiClient()
     response = client.chat.completions.create(
-        model="glm-5.1",
+        model="glm-5.2",
         messages=messages,
         tools=tools,
         stream=True
@@ -35,7 +35,7 @@ def sync_example():
     print("=== GLM-4 Synchronous Example ===")
     client = ZaiClient()
     response = client.chat.completions.create(
-        model="glm-5.1",
+        model="glm-5.2",
         messages=[
             {"role": "system", "content": "You are a helpful assistant who provides professional, accurate, and insightful advice."},
             {"role": "user", "content": "I'm very interested in the planets of the solar system, especially Saturn. Please provide basic information about Saturn, including its size, composition, ring system, and any unique astronomical phenomena."},
@@ -47,7 +47,7 @@ def async_example():
     print("=== GLM-4 Async Example ===")
     client = ZaiClient()
     response = client.chat.asyncCompletions.create(
-        model="glm-5.1",
+        model="glm-5.2",
         messages=[
             {
                 "role": "user",

examples/glm_thinking.py

@@ -15,7 +15,7 @@ class ZaiSampler(SamplerBase):
 
     def __init__(
         self,
-        model: str = "glm-5",
+        model: str = "glm-5.2",
         api_key: str = '',
         system_message: Optional[str] = None,
         temperature: float = 0.0,

examples/stream_tools.py

@@ -4,7 +4,7 @@ def main():
     client = ZhipuAiClient()
     # create chat completion with tool calls and streaming
     response = client.chat.completions.create(
-        model="glm-5.1",
+        model="glm-5.2",
         messages=[
             {"role": "user", "content": "How is the weather in Beijing and Shanghai? Please provide the answer in Celsius."},
         ],

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "zai-sdk"
-version = "0.2.2"
+version = "0.2.3"
 description = "A SDK library for accessing big model apis from Z.ai"
 authors = ["Z.ai"]
 readme = "README.md"

src/zai/_version.py

@@ -1,2 +1,2 @@
 __title__ = 'Z.ai'
-__version__ = '0.2.2'
+__version__ = '0.2.3'

src/zai/api_resource/chat/completions.py

@@ -66,7 +66,8 @@ def create(
 		response_format: object | None = None,
 		thinking: object | None = None,
 		watermark_enabled: Optional[bool] | NotGiven = NOT_GIVEN,
-        tool_stream: bool | NotGiven = NOT_GIVEN,
+		tool_stream: bool | NotGiven = NOT_GIVEN,
+		reasoning_effort: Optional[str] | NotGiven = NOT_GIVEN,
 	) -> Completion | StreamResponse[ChatCompletionChunk]:
 		"""
 		Create a chat completion
@@ -95,6 +96,7 @@ def create(
 			thinking (Optional[object]): Configuration parameters for model reasoning
 			watermark_enabled (Optional[bool]): Whether to enable watermark on generated audio
 			tool_stream (Optional[bool]): Whether to enable tool streaming
+			reasoning_effort (Optional[str]): Reasoning effort level, supports none, minimal, low, medium, high, xhigh, max. Effective for glm-5.2 and above models.
 		"""
 		logger.debug(f'temperature:{temperature}, top_p:{top_p}')
 		if temperature is not None and temperature != NOT_GIVEN:
@@ -143,7 +145,8 @@ def create(
 				'response_format': response_format,
 				'thinking': thinking,
 				'watermark_enabled': watermark_enabled,
-                'tool_stream': tool_stream,
+				'tool_stream': tool_stream,
+				'reasoning_effort': reasoning_effort,
 			}
 		)
 		return self._post(