Merge pull request #825 from MicrosoftDocs/main

Merge main to live

Author: moonbox3

agent-framework/integrations/ag-ui/backend-tool-rendering.md

@@ -147,7 +147,7 @@ ChatClient chatClient = new AzureOpenAIClient(
         new DefaultAzureCredential())
     .GetChatClient(deploymentName);
 
-ChatClientAgent agent = chatClient.AsIChatClient().CreateAIAgent(
+ChatClientAgent agent = chatClient.AsIChatClient().AsAIAgent(
     name: "AGUIAssistant",
     instructions: "You are a helpful assistant with access to restaurant information.",
     tools: tools);

agent-framework/integrations/ag-ui/frontend-tools.md

@@ -57,7 +57,7 @@ static string GetUserLocation()
 AITool[] frontendTools = [AIFunctionFactory.Create(GetUserLocation)];
 
 // Pass tools when creating the agent
-AIAgent agent = chatClient.CreateAIAgent(
+AIAgent agent = chatClient.AsAIAgent(
     name: "agui-client",
     description: "AG-UI Client Agent",
     tools: frontendTools);
@@ -67,7 +67,7 @@ The rest of your client code remains the same as shown in the Getting Started tu
 
 ### How Tools Are Sent to the Server
 
-When you register tools with `CreateAIAgent()`, the `AGUIChatClient` automatically:
+When you register tools with `AsAIAgent()`, the `AGUIChatClient` automatically:
 
 1. Captures the tool definitions (names, descriptions, parameter schemas)
 3. Sends the tools with each request to the server agent which maps them to `ChatAgentRunOptions.ChatOptions.Tools`
@@ -123,7 +123,7 @@ This middleware pattern allows you to:
 
 The following are new concepts for frontend tools:
 
-- **Client-side registration**: Tools are registered on the client using `AIFunctionFactory.Create()` and passed to `CreateAIAgent()`
+- **Client-side registration**: Tools are registered on the client using `AIFunctionFactory.Create()` and passed to `AsAIAgent()`
 - **Automatic capture**: Tools are automatically captured and sent via `ChatAgentRunOptions.ChatOptions.Tools`
 
 ## How Frontend Tools Work

agent-framework/integrations/ag-ui/getting-started.md

@@ -92,7 +92,7 @@ ChatClient chatClient = new AzureOpenAIClient(
         new DefaultAzureCredential())
     .GetChatClient(deploymentName);
 
-AIAgent agent = chatClient.AsIChatClient().CreateAIAgent(
+AIAgent agent = chatClient.AsIChatClient().AsAIAgent(
     name: "AGUIAssistant",
     instructions: "You are a helpful assistant.");
 
@@ -107,7 +107,7 @@ await app.RunAsync();
 - **`AddAGUI`**: Registers AG-UI services with the dependency injection container
 - **`MapAGUI`**: Extension method that registers the AG-UI endpoint with automatic request/response handling and SSE streaming
 - **`ChatClient` and `AsIChatClient()`**: `AzureOpenAIClient.GetChatClient()` returns OpenAI's `ChatClient` type. The `AsIChatClient()` extension method (from `Microsoft.Extensions.AI.OpenAI`) converts it to the `IChatClient` interface required by Agent Framework
-- **`CreateAIAgent`**: Creates an Agent Framework agent from an `IChatClient`
+- **`AsAIAgent`**: Creates an Agent Framework agent from an `IChatClient`
 - **ASP.NET Core Integration**: Uses ASP.NET Core's native async support for streaming responses
 - **Instructions**: The agent is created with default instructions, which can be overridden by client messages
 - **Configuration**: `AzureOpenAIClient` with `DefaultAzureCredential` provides secure authentication
@@ -149,7 +149,7 @@ dotnet add package Microsoft.Agents.AI --prerelease
 ```
 
 > [!NOTE]
-> The `Microsoft.Agents.AI` package provides the `CreateAIAgent()` extension method.
+> The `Microsoft.Agents.AI` package provides the `AsAIAgent()` extension method.
 
 ### Client Code
 
@@ -174,11 +174,11 @@ using HttpClient httpClient = new()
 
 AGUIChatClient chatClient = new(httpClient, serverUrl);
 
-AIAgent agent = chatClient.CreateAIAgent(
+AIAgent agent = chatClient.AsAIAgent(
     name: "agui-client",
     description: "AG-UI Client Agent");
 
-AgentThread thread = agent.GetNewThread();
+AgentThread thread = await agent.GetNewThreadAsync();
 List<ChatMessage> messages =
 [
     new(ChatRole.System, "You are a helpful assistant.")
@@ -256,7 +256,7 @@ catch (Exception ex)
 
 - **Server-Sent Events (SSE)**: The protocol uses SSE for streaming responses
 - **AGUIChatClient**: Client class that connects to AG-UI servers and implements `IChatClient`
-- **CreateAIAgent**: Extension method on `AGUIChatClient` to create an agent from the client
+- **AsAIAgent**: Extension method on `AGUIChatClient` to create an agent from the client
 - **RunStreamingAsync**: Streams responses as `AgentResponseUpdate` objects
 - **AsChatResponseUpdate**: Extension method to access chat-specific properties like `ConversationId` and `ResponseId`
 - **Thread Management**: The `AgentThread` maintains conversation context across requests

agent-framework/integrations/ag-ui/index.md

@@ -251,7 +251,7 @@ To get started with AG-UI integration:
 
 - [Agent Framework Documentation](../../overview/agent-framework-overview.md)
 - [AG-UI Protocol Documentation](https://docs.ag-ui.com/introduction)
-- [AG-UI Dojo App](https://github.com/ag-oss/ag-ui/tree/main/apps/dojo) - Example application demonstrating Agent Framework integration
+- [AG-UI Dojo App](https://dojo.ag-ui.com/) - Example application demonstrating Agent Framework integration
 - [Agent Framework GitHub Repository](https://github.com/microsoft/agent-framework)
 
 ::: zone-end

agent-framework/integrations/ag-ui/state-management.md

@@ -255,7 +255,7 @@ AIAgent CreateRecipeAgent(JsonSerializerOptions jsonSerializerOptions)
     var chatClient = azureClient.GetChatClient(deploymentName);
 
     // Create base agent
-    AIAgent baseAgent = chatClient.AsIChatClient().CreateAIAgent(
+    AIAgent baseAgent = chatClient.AsIChatClient().AsAIAgent(
         name: "RecipeAgent",
         instructions: """
             You are a helpful recipe assistant. When users ask you to create or suggest a recipe,

agent-framework/integrations/ag-ui/testing-with-dojo.md

@@ -11,7 +11,7 @@ ms.service: agent-framework
 
 # Testing with AG-UI Dojo
 
-The [AG-UI Dojo application](https://github.com/ag-oss/ag-ui/tree/main/apps/dojo) provides an interactive environment to test and explore Microsoft Agent Framework agents that implement the AG-UI protocol. Dojo offers a visual interface to connect to your agents and interact with all 7 AG-UI features.
+The [AG-UI Dojo application](https://dojo.ag-ui.com/) provides an interactive environment to test and explore Microsoft Agent Framework agents that implement the AG-UI protocol. Dojo offers a visual interface to connect to your agents and interact with all 7 AG-UI features.
 
 :::zone pivot="programming-language-python"
 
@@ -226,18 +226,18 @@ If you see authentication errors:
 
 ## Next Steps
 
-- Explore the [example agents](https://github.com/ag-oss/ag-ui/tree/main/integrations/microsoft-agent-framework/python/examples/agents) to see implementation patterns
+- Explore the [example agents](https://github.com/ag-ui-protocol/ag-ui/tree/main/integrations/microsoft-agent-framework/python/examples/agents) to see implementation patterns
 - Learn about [Backend Tool Rendering](backend-tool-rendering.md) to customize tool UIs
 <!-- - Implement [Human-in-the-Loop](human-in-the-loop.md) workflows for approval flows -->
 <!-- - Add [State Management](state-management.md) for complex interactive experiences -->
 
 ## Additional Resources
 
 - [AG-UI Documentation](https://docs.ag-ui.com/introduction)
-- [AG-UI GitHub Repository](https://github.com/ag-oss/ag-ui)
-- [Dojo Application](https://github.com/ag-oss/ag-ui/tree/main/apps/dojo)
+- [AG-UI GitHub Repository](https://github.com/ag-ui-protocol/ag-ui)
+- [Dojo Application](https://dojo.ag-ui.com/)
 
-- [Microsoft Agent Framework Integration Examples](https://github.com/ag-oss/ag-ui/tree/main/integrations/microsoft-agent-framework)
+- [Microsoft Agent Framework Integration Examples](https://github.com/ag-ui-protocol/ag-ui/tree/main/integrations/microsoft-agent-framework)
 
 :::zone-end
 

agent-framework/migration-guide/from-autogen/index.md

@@ -234,7 +234,7 @@ async def example():
     )
 
     # Factory method (more convenient)
-    agent = client.create_agent(
+    agent = client.as_agent(
         name="assistant",
         instructions="You are a helpful assistant.",
         tools=[get_weather],
@@ -489,7 +489,7 @@ agent = ChatAgent(
 For detailed examples, see:
 
 - [Azure AI with Code Interpreter](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/agents/azure_ai/azure_ai_with_code_interpreter.py) - Code execution tool
-- [Azure AI with Multiple Tools](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/agents/azure_ai/azure_ai_with_multiple_tools.py) - Multiple hosted tools
+- [Azure AI with Multiple Tools](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_multiple_tools.py) - Multiple hosted tools
 - [OpenAI with Web Search](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/agents/openai/openai_chat_client_with_web_search.py) - Web search integration
 
 Requirements and caveats:
@@ -1183,7 +1183,7 @@ async def concurrent_example():
 For concurrent execution examples, see:
 
 - [Concurrent Agents](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/workflows/orchestration/concurrent_agents.py) - Parallel agent execution
-- [Concurrent Custom Executors](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/workflows/orchestration/concurrent_custom_executors.py) - Custom parallel patterns
+- [Concurrent Custom Executors](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/workflows/orchestration/concurrent_custom_agent_executors.py) - Custom parallel patterns
 - [Concurrent with Custom Aggregator](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/workflows/orchestration/concurrent_custom_aggregator.py) - Result aggregation patterns
 
 #### MagenticOneGroupChat Pattern
@@ -1703,7 +1703,7 @@ async def observability_example():
 For detailed observability examples, see:
 
 - [Zero-code Setup](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/observability/advanced_zero_code.py) - Environment variable configuration
-- [Manual Setup](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/observability/setup_observability_with_parameters.py) - Programmatic configuration
+- [Manual Setup](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/observability/configure_otel_providers_with_parameters.py) - Programmatic configuration
 - [Agent Observability](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/observability/agent_observability.py) - Single agent telemetry
 - [Workflow Observability](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/observability/workflow_observability.py) - Multi-agent workflow tracing
 

agent-framework/migration-guide/from-semantic-kernel/index.md

@@ -73,7 +73,7 @@ AzureAIAgent agent = new(definition, azureAgentClient);
 Agent creation in Agent Framework is made simpler with extensions provided by all main providers.
 
 ```csharp
-AIAgent openAIAgent = chatClient.CreateAIAgent(instructions: ParrotInstructions);
+AIAgent openAIAgent = chatClient.AsAIAgent(instructions: ParrotInstructions);
 AIAgent azureFoundryAgent = await persistentAgentsClient.CreateAIAgentAsync(instructions: ParrotInstructions);
 AIAgent openAIAssistantAgent = await assistantClient.CreateAIAgentAsync(instructions: ParrotInstructions);
 ```
@@ -103,7 +103,7 @@ The agent is responsible for creating the thread.
 
 ```csharp
 // New.
-AgentThread thread = agent.GetNewThread();
+AgentThread thread = await agent.GetNewThreadAsync();
 ```
 
 ## 4. Hosted Agent Thread Cleanup
@@ -160,7 +160,7 @@ ChatCompletionAgent agent = new() { Kernel = kernel, ... };
 In Agent Framework, in a single call you can register tools directly in the agent creation process.
 
 ```csharp
-AIAgent agent = chatClient.CreateAIAgent(tools: [AIFunctionFactory.Create(GetWeather)]);
+AIAgent agent = chatClient.AsAIAgent(tools: [AIFunctionFactory.Create(GetWeather)]);
 ```
 
 ## 6. Agent Non-Streaming Invocation
@@ -281,7 +281,7 @@ serviceContainer.AddKeyedSingleton<SemanticKernel.Agents.Agent>(
 Agent Framework provides the `AIAgent` type as the base abstraction class.
 
 ```csharp
-services.AddKeyedSingleton<AIAgent>(() => client.CreateAIAgent(...));
+services.AddKeyedSingleton<AIAgent>(() => client.AsAIAgent(...));
 ```
 
 ## 11. Agent Type Consolidation
@@ -381,7 +381,7 @@ Or, with the convenience methods provided by chat clients:
 ```python
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
-agent = AzureOpenAIChatClient(credential=AzureCliCredential()).create_agent(instructions="You are a helpful assistant")
+agent = AzureOpenAIChatClient(credential=AzureCliCredential()).as_agent(instructions="You are a helpful assistant")
 ```
 
 The direct method exposes all possible parameters you can set for your agent. While the convenience method has a subset, you can still pass in the same set of parameters, because it calls the direct method internally.
@@ -467,7 +467,7 @@ def get_weather(location: str) -> str:
     """Get the weather for a given location."""
     return f"The weather in {location} is sunny."
 
-agent = chat_client.create_agent(tools=get_weather)
+agent = chat_client.as_agent(tools=get_weather)
 ```
 
 > [!NOTE]
@@ -516,7 +516,7 @@ class Plugin:
         return f"The weather in {location} is sunny with a high of 25°C and a low of 15°C."
 
 plugin = Plugin("Initial state")
-agent = chat_client.create_agent(tools=[plugin.get_weather, plugin.get_weather_details])
+agent = chat_client.as_agent(tools=[plugin.get_weather, plugin.get_weather_details])
 
 ... # use the agent
 
@@ -575,7 +575,7 @@ kernel_function = KernelFunctionFromPrompt(
 agent_tool = kernel_function.as_agent_framework_tool(kernel=kernel)
 
 # Use the tool with an Agent Framework agent
-agent = OpenAIResponsesClient(model_id="gpt-4o").create_agent(tools=agent_tool)
+agent = OpenAIResponsesClient(model_id="gpt-4o").as_agent(tools=agent_tool)
 response = await agent.run("What kind of day is it?")
 print(response.text)
 ```
@@ -595,7 +595,7 @@ def get_weather(self, location: str) -> str:
 agent_tool = get_weather.as_agent_framework_tool()
 
 # Use the tool with an Agent Framework agent
-agent = OpenAIResponsesClient(model_id="gpt-4o").create_agent(tools=agent_tool)
+agent = OpenAIResponsesClient(model_id="gpt-4o").as_agent(tools=agent_tool)
 response = await agent.run("What's the weather in Seattle?")
 print(response.text)
 ```
@@ -663,7 +663,7 @@ async with collection:
     search_tool = search_function.as_agent_framework_tool()
 
     # Use the tool with an Agent Framework agent
-    agent = OpenAIResponsesClient(model_id="gpt-4o").create_agent(
+    agent = OpenAIResponsesClient(model_id="gpt-4o").as_agent(
         instructions="You are a travel agent that helps people find hotels.",
         tools=search_tool
     )
@@ -779,7 +779,7 @@ from agent_framework.openai import OpenAIChatClient
 client = OpenAIChatClient()
 
 # Set default options at agent creation
-agent = client.create_agent(
+agent = client.as_agent(
     instructions="You are a helpful assistant.",
     default_options={
         "max_tokens": 1000,

agent-framework/support/upgrade/typed-options-guide-python.md

@@ -54,7 +54,7 @@ response = await client.get_response(
 )
 ```
 
-> **Note:** For **Agents**, the `instructions` and `tools` parameters remain available as direct keyword arguments on `ChatAgent.__init__()` and `client.create_agent()`. For `agent.run()`, only `tools` is available as a keyword argument:
+> **Note:** For **Agents**, the `instructions` and `tools` parameters remain available as direct keyword arguments on `ChatAgent.__init__()` and `client.as_agent()`. For `agent.run()`, only `tools` is available as a keyword argument:
 >
 > ```python
 > # Agent creation accepts both tools and instructions as keyword arguments

agent-framework/tutorials/agents/agent-as-function-tool.md

@@ -48,7 +48,7 @@ AIAgent weatherAgent = new AzureOpenAIClient(
     new Uri("https://<myresource>.openai.azure.com"),
     new AzureCliCredential())
      .GetChatClient("gpt-4o-mini")
-     .CreateAIAgent(
+     .AsAIAgent(
         instructions: "You answer questions about the weather.",
         name: "WeatherAgent",
         description: "An agent that answers questions about the weather.",
@@ -62,7 +62,7 @@ AIAgent agent = new AzureOpenAIClient(
     new Uri("https://<myresource>.openai.azure.com"),
     new AzureCliCredential())
      .GetChatClient("gpt-4o-mini")
-     .CreateAIAgent(instructions: "You are a helpful assistant who responds in French.", tools: [weatherAgent.AsAIFunction()]);
+     .AsAIAgent(instructions: "You are a helpful assistant who responds in French.", tools: [weatherAgent.AsAIFunction()]);
 ```
 
 Invoke the main agent as normal. It can now call the weather agent as a tool, and should respond in French.
@@ -103,7 +103,7 @@ Create a `ChatAgent` that uses the function tool.
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
 
-weather_agent = AzureOpenAIChatClient(credential=AzureCliCredential()).create_agent(
+weather_agent = AzureOpenAIChatClient(credential=AzureCliCredential()).as_agent(
     name="WeatherAgent",
     description="An agent that answers questions about the weather.",
     instructions="You answer questions about the weather.",
@@ -114,7 +114,7 @@ weather_agent = AzureOpenAIChatClient(credential=AzureCliCredential()).create_ag
 Now, create a main agent and provide the `weather_agent` as a function tool by calling `.as_tool()` to convert `weather_agent` to a function tool.
 
 ```python
-main_agent = AzureOpenAIChatClient(credential=AzureCliCredential()).create_agent(
+main_agent = AzureOpenAIChatClient(credential=AzureCliCredential()).as_agent(
     instructions="You are a helpful assistant who responds in French.",
     tools=weather_agent.as_tool()
 )
@@ -138,7 +138,7 @@ weather_tool = weather_agent.as_tool(
     arg_description="The weather query or location"
 )
 
-main_agent = AzureOpenAIChatClient(credential=AzureCliCredential()).create_agent(
+main_agent = AzureOpenAIChatClient(credential=AzureCliCredential()).as_agent(
     instructions="You are a helpful assistant who responds in French.",
     tools=weather_tool
 )