Migrate to GLM-4.6

resp = client.chat.completions.create(
    model="glm-4.6",
    messages=[{"role": "user", "content": "Briefly describe the advantages of GLM-4.6"}]
)

# Plan A: Use temperature (recommended)
resp = client.chat.completions.create(
    model="glm-4.6",
    messages=[{"role": "user", "content": "Write a more creative brand introduction"}],
    temperature=1.0
)

# Plan B: Use top_p
resp = client.chat.completions.create(
    model="glm-4.6",
    messages=[{"role": "user", "content": "Generate more stable technical documentation"}],
    top_p=0.8
)

resp = client.chat.completions.create(
    model="glm-4.6",
    messages=[{"role": "user", "content": "Design a three-tier microservice architecture for me"}],
    thinking={"type": "enabled"}
)

response = client.chat.completions.create(
    model="glm-4.6",
    messages=[{"role": "user", "content": "How's the weather in Beijing"}],
    tools=[
        {
            "type": "function",
            "function": {
                "name": "get_weather",
                "description": "Get current weather conditions for a specified location",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "location": {"type": "string", "description": "City, eg: Beijing, Shanghai"},
                        "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
                    },
                    "required": ["location"]
                }
            }
        }
    ],
    stream=True,
    tool_stream=True,
)

# Initialize streaming collection variables
reasoning_content = ""
content = ""
final_tool_calls = {}
reasoning_started = False
content_started = False

# Process streaming response
for chunk in response:
    if not chunk.choices:
        continue

    delta = chunk.choices[0].delta

    # Streaming reasoning process output
    if hasattr(delta, 'reasoning_content') and delta.reasoning_content:
        if not reasoning_started and delta.reasoning_content.strip():
            print("\n🧠 Thinking Process:")
            reasoning_started = True
        reasoning_content += delta.reasoning_content
        print(delta.reasoning_content, end="", flush=True)

    # Streaming answer content output
    if hasattr(delta, 'content') and delta.content:
        if not content_started and delta.content.strip():
            print("\n\n💬 Answer Content:")
            content_started = True
        content += delta.content
        print(delta.content, end="", flush=True)

    # Streaming tool call information (parameter concatenation)
    if delta.tool_calls:
        for tool_call in delta.tool_calls:
            idx = tool_call.index
            if idx not in final_tool_calls:
                final_tool_calls[idx] = tool_call
                final_tool_calls[idx].function.arguments = tool_call.function.arguments
            else:
                final_tool_calls[idx].function.arguments += tool_call.function.arguments

# Output final tool call information
if final_tool_calls:
    print("\n📋 Function Calls Triggered:")
    for idx, tool_call in final_tool_calls.items():
        print(f"  {idx}: Function Name: {tool_call.function.name}, Parameters: {tool_call.function.arguments}")