Merge pull request #923 from MicrosoftDocs/main

Merge main to live

Author: moonbox3

.openpublishing.redirection.json

@@ -1022,17 +1022,22 @@
     },
     {
       "source_path": "agent-framework/user-guide/agents/agent-types/azure-ai-foundry-agent.md",
-      "redirect_url": "/agent-framework/agents/providers/azure-ai-foundry",
+      "redirect_url": "/agent-framework/agents/providers/microsoft-foundry",
       "redirect_document_id": true
     },
     {
       "source_path": "agent-framework/user-guide/agents/agent-types/azure-ai-foundry-models-chat-completion-agent.md",
-      "redirect_url": "/agent-framework/agents/providers/azure-ai-foundry",
+      "redirect_url": "/agent-framework/agents/providers/microsoft-foundry",
       "redirect_document_id": false
     },
     {
       "source_path": "agent-framework/user-guide/agents/agent-types/azure-ai-foundry-models-responses-agent.md",
-      "redirect_url": "/agent-framework/agents/providers/azure-ai-foundry",
+      "redirect_url": "/agent-framework/agents/providers/microsoft-foundry",
+      "redirect_document_id": false
+    },
+    {
+      "source_path": "agent-framework/agents/providers/azure-ai-foundry.md",
+      "redirect_url": "/agent-framework/agents/providers/microsoft-foundry",
       "redirect_document_id": false
     },
     {

agent-framework/TOC.yml

@@ -99,7 +99,7 @@ items:
     - name: OpenAI
       href: agents/providers/openai.md
     - name: Microsoft Foundry
-      href: agents/providers/azure-ai-foundry.md
+      href: agents/providers/microsoft-foundry.md
     - name: Anthropic
       href: agents/providers/anthropic.md
     - name: Ollama

agent-framework/agents/background-responses.md

@@ -5,7 +5,7 @@ zone_pivot_groups: programming-languages
 author: sergeymenshykh
 ms.topic: reference
 ms.author: semenshi
-ms.date: 10/16/2025
+ms.date: 03/13/2026
 ms.service: agent-framework
 ---
 
@@ -58,7 +58,7 @@ For non-streaming scenarios, when you initially run an agent, it may or may not
 AIAgent agent = new AzureOpenAIClient(
     new Uri("https://<myresource>.openai.azure.com"),
     new DefaultAzureCredential())
-    .GetOpenAIResponseClient("<deployment-name>")
+    .GetResponsesClient("<deployment-name>")
     .AsAIAgent();
 
 AgentRunOptions options = new()
@@ -103,7 +103,7 @@ In streaming scenarios, background responses work much like regular streaming re
 AIAgent agent = new AzureOpenAIClient(
     new Uri("https://<myresource>.openai.azure.com"),
     new DefaultAzureCredential())
-    .GetOpenAIResponseClient("<deployment-name>")
+    .GetResponsesClient("<deployment-name>")
     .AsAIAgent();
 
 AgentRunOptions options = new()
@@ -180,7 +180,7 @@ agent = Agent(
     client=OpenAIResponsesClient(model_id="o3"),
 )
 
-session = await agent.create_session()
+session = agent.create_session()
 
 # Start a background run — returns immediately
 response = await agent.run(
@@ -212,7 +212,7 @@ print(response.text)
 In streaming scenarios, background responses work like regular streaming — the agent streams updates back in real time. The key difference is that each update includes a `continuation_token`, enabling stream resumption if the connection is interrupted:
 
 ```python
-session = await agent.create_session()
+session = agent.create_session()
 
 # Start a streaming background run
 last_token = None

agent-framework/agents/index.md

@@ -19,7 +19,7 @@ The Microsoft Agent Framework provides support for several types of agents to ac
 All agents are derived from a common base class, `AIAgent`, which provides a consistent interface for all agent types. This allows for building common, agent agnostic, higher level functionality such as multi-agent orchestrations.
 ::: zone-end
 ::: zone pivot="programming-language-python"
-All agents are derived from a common base class, [`Agent`](/python/api/agent-framework-core/agent_framework.agent?view=agent-framework-python-latest), which provides a consistent interface for all agent types. This allows for building common, agent agnostic, higher level functionality such as multi-agent orchestrations.
+All agents are derived from a common base class, `Agent`, which provides a consistent interface for all agent types. This allows for building common, agent agnostic, higher level functionality such as multi-agent orchestrations.
 ::: zone-end
 
 ## Default Agent Runtime Execution Model
@@ -57,9 +57,9 @@ To make creating these agents even easier, Agent Framework provides helpers for
 
 | Underlying inference service | Description | Service chat history storage supported | InMemory/Custom chat history storage supported |
 |------------------------------|-------------|----------------------------------------|------------------------------------------------|
-|[Microsoft Foundry Agent](./providers/azure-ai-foundry.md)|An agent that uses the Foundry Agent Service as its backend.|Yes|No|
-|[Foundry Models ChatCompletion](./providers/azure-ai-foundry.md)|An agent that uses any of the models deployed in the Foundry Service as its backend via ChatCompletion.|No|Yes|
-|[Foundry Models Responses](./providers/azure-ai-foundry.md)|An agent that uses any of the models deployed in the Foundry Service as its backend via Responses.|Yes|Yes|
+|[Microsoft Foundry Agent](./providers/microsoft-foundry.md)|An agent that uses the Foundry Agent Service as its backend.|Yes|No|
+|[Foundry Models ChatCompletion](./providers/microsoft-foundry.md)|An agent that uses any of the models deployed in the Foundry Service as its backend via ChatCompletion.|No|Yes|
+|[Foundry Models Responses](./providers/microsoft-foundry.md)|An agent that uses any of the models deployed in the Foundry Service as its backend via Responses.|Yes|Yes|
 |[Foundry Anthropic](./providers/anthropic.md)|An agent that uses a Claude model via the Foundry Anthropic Service as its backend.|No|Yes|
 |[Azure OpenAI ChatCompletion](./providers/azure-openai.md)|An agent that uses the Azure OpenAI ChatCompletion service.|No|Yes|
 |[Azure OpenAI Responses](./providers/azure-openai.md)|An agent that uses the Azure OpenAI Responses service.|Yes|Yes|
@@ -101,7 +101,7 @@ When using Foundry, Azure OpenAI, OpenAI services, or Anthropic services, you ha
 | [Azure OpenAI](/azure/ai-foundry/openai/overview) <sup>1</sup> | Azure OpenAI SDK <sup>2</sup> | [Azure.AI.OpenAI](https://www.nuget.org/packages/Azure.AI.OpenAI) | https://&lt;resource&gt;.openai.azure.com/ |
 | [Azure OpenAI](/azure/ai-foundry/openai/overview) <sup>1</sup> | OpenAI SDK | [OpenAI](https://www.nuget.org/packages/OpenAI) | https://&lt;resource&gt;.openai.azure.com/openai/v1/ |
 | OpenAI | OpenAI SDK | [OpenAI](https://www.nuget.org/packages/OpenAI) | No url required |
-| [Azure AI Foundry Anthropic](/azure/ai-foundry/foundry-models/how-to/use-foundry-models-claude?view=foundry-classic) | Anthropic Foundry SDK | [Anthropic.Foundry](https://www.nuget.org/packages/Anthropic.Foundry) | Resource name required |
+| [Azure AI Foundry Anthropic](/azure/ai-foundry/foundry-models/how-to/use-foundry-models-claude) | Anthropic Foundry SDK | [Anthropic.Foundry](https://www.nuget.org/packages/Anthropic.Foundry) | Resource name required |
 | Anthropic | Anthropic SDK | [Anthropic](https://www.nuget.org/packages/Anthropic) | No url or resource name required |
 
 1. [Upgrading from Azure OpenAI to Foundry](/azure/ai-foundry/how-to/upgrade-azure-openai)
@@ -201,7 +201,7 @@ AIAgent agent = client.AsAIAgent(
 
 Agent Framework makes it easy to create simple agents based on many different inference services.
 Any inference service that provides a chat client implementation can be used to build these agents.
-This can be done using the [`SupportsChatGetResponse`](/python/api/agent-framework-core/agent_framework.supportschatgetresponse?view=agent-framework-python-latest), which defines a standard for the methods that a client needs to support to be used with the standard [`Agent`](/python/api/agent-framework-core/agent_framework.agent?view=agent-framework-python-latest) class.
+This can be done using the `SupportsChatGetResponse` protocol, which defines a standard for the methods that a client needs to support to be used with the standard `Agent` class.
 
 These agents support a wide range of functionality out of the box:
 
@@ -211,7 +211,7 @@ These agents support a wide range of functionality out of the box:
 1. Structured output
 1. Streaming responses
 
-To create one of these agents, simply construct an [`Agent`](/python/api/agent-framework-core/agent_framework.agent?view=agent-framework-python-latest) using the chat client implementation of your choice.
+To create one of these agents, simply construct an `Agent` using the chat client implementation of your choice.
 
 
 ```python
@@ -239,15 +239,15 @@ agent = AzureOpenAIResponsesClient(credential=DefaultAzureCredential(), project_
 ```
 
 > [!NOTE]
-> This example shows using the AzureOpenAIResponsesClient, but the same pattern applies to any chat client that implements [`SupportsChatGetResponse`](/python/api/agent-framework-core/agent_framework.supportschatgetresponse?view=agent-framework-python-latest), see [providers overview](./providers/index.md) for more details on other clients.
+> This example shows using the AzureOpenAIResponsesClient, but the same pattern applies to any chat client that implements `SupportsChatGetResponse`, see [providers overview](./providers/index.md) for more details on other clients.
 
 For detailed examples, see the agent-specific documentation sections below.
 
 ### Supported Chat Providers
 
 |Underlying Inference Service|Description|Service Chat History storage supported|
 |---|---|---|
-|[Foundry Agent](./providers/azure-ai-foundry.md)|An agent that uses the Agent Service as its backend.|Yes|
+|[Foundry Agent](./providers/microsoft-foundry.md)|An agent that uses the Agent Service as its backend.|Yes|
 |[Azure OpenAI Chat Completion](./providers/azure-openai.md)|An agent that uses the Azure OpenAI Chat Completion service.|No|
 |[Azure OpenAI Responses](./providers/azure-openai.md)|An agent that uses the Azure OpenAI Responses service.|Yes|
 |[Azure OpenAI Assistants](./providers/azure-openai.md)|An agent that uses the Azure OpenAI Assistants service.|Yes|
@@ -258,7 +258,7 @@ For detailed examples, see the agent-specific documentation sections below.
 |[Amazon Bedrock](https://github.com/microsoft/agent-framework/tree/main/python/packages/bedrock)|An agent that uses Amazon Bedrock models through the Agent Framework Bedrock chat client.|No|
 |[GitHub Copilot](./providers/github-copilot.md)|An agent that uses the GitHub Copilot SDK backend.|No|
 |[Ollama (OpenAI-compatible)](./providers/ollama.md)|An agent that uses locally hosted Ollama models via OpenAI-compatible APIs.|No|
-|[Any other ChatClient](./providers/custom.md)|You can also use any other implementation of [`SupportsChatGetResponse`](/python/api/agent-framework-core/agent_framework.supportschatgetresponse?view=agent-framework-python-latest) to create an agent.|Varies|
+|[Any other ChatClient](./providers/custom.md)|You can also use any other implementation of `SupportsChatGetResponse` to create an agent.|Varies|
 
 Custom chat history storage is supported whenever session-based conversation state is supported.
 
@@ -315,7 +315,7 @@ For tools and tool patterns, see [Tools overview](./tools/index.md).
 
 ## Custom agents
 
-For fully custom implementations (for example deterministic agents or API-backed agents), see [Custom Agents](./providers/custom.md). That page covers implementing [`SupportsAgentRun`](/python/api/agent-framework-core/agent_framework.supportsagentrun?view=agent-framework-python-latest) or extending [`BaseAgent`](/python/api/agent-framework-core/agent_framework.baseagent?view=agent-framework-python-latest), including streaming updates with [`AgentResponseUpdate`](/python/api/agent-framework-core/agent_framework.agentresponseupdate?view=agent-framework-python-latest).
+For fully custom implementations (for example deterministic agents or API-backed agents), see [Custom Agents](./providers/custom.md). That page covers implementing `SupportsAgentRun` or extending `BaseAgent`, including streaming updates with `AgentResponseUpdate`.
 
 ## Other agent types
 

agent-framework/agents/providers/anthropic.md

@@ -515,4 +515,4 @@ See the [Agent getting started tutorials](../../get-started/your-first-agent.md)
 ## Next steps
 
 > [!div class="nextstepaction"]
-> [Azure AI Agents](./azure-ai-foundry.md)
+> [Azure AI Agents](./microsoft-foundry.md)

agent-framework/agents/providers/azure-openai.md

@@ -150,27 +150,29 @@ pip install agent-framework --pre
 
 Each client type uses different environment variables:
 
-### Chat Completion
+# [Chat Completion](#tab/aoai-chat-completion)
 
 ```bash
 AZURE_OPENAI_ENDPOINT="https://<myresource>.openai.azure.com"
 AZURE_OPENAI_CHAT_DEPLOYMENT_NAME="gpt-4o-mini"
 ```
 
-### Responses
+# [Responses](#tab/aoai-responses)
 
 ```bash
 AZURE_OPENAI_ENDPOINT="https://<myresource>.openai.azure.com"
 AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME="gpt-4o-mini"
 ```
 
-### Assistants
+# [Assistants](#tab/aoai-assistants)
 
 ```bash
 AZURE_OPENAI_ENDPOINT="https://<myresource>.openai.azure.com"
 AZURE_OPENAI_CHAT_DEPLOYMENT_NAME="gpt-4o-mini"
 ```
 
+---
+
 Optionally, you can also set:
 
 ```bash
@@ -180,7 +182,9 @@ AZURE_OPENAI_API_KEY="<your-api-key>"  # If not using Azure CLI authentication
 
 All clients use Azure credentials for authentication. The simplest approach is `AzureCliCredential` after running `az login`. All Azure clients accept a unified `credential` parameter that supports `TokenCredential`, `AsyncTokenCredential`, or a callable token provider — token caching and refresh are handled automatically.
 
-## Chat Completion Client
+## Create Azure OpenAI Agents
+
+# [Chat Completion](#tab/aoai-chat-completion)
 
 `AzureOpenAIChatClient` uses the Chat Completions API — the simplest option with broad model support.
 
@@ -202,7 +206,7 @@ asyncio.run(main())
 
 **Supported tools:** Function tools, web search, local MCP tools.
 
-## Responses Client
+# [Responses](#tab/aoai-responses)
 
 `AzureOpenAIResponsesClient` uses the Responses API — the most feature-rich option with hosted tools.
 
@@ -269,7 +273,7 @@ async def hosted_tools_example():
     print(result)
 ```
 
-## Assistants Client
+# [Assistants](#tab/aoai-assistants)
 
 `AzureOpenAIAssistantsClient` uses the Assistants API — server-managed agents with built-in code interpreter and file search. Note the `async with` context manager for automatic assistant lifecycle management.
 
@@ -291,6 +295,8 @@ asyncio.run(main())
 
 **Supported tools:** Function tools, code interpreter, file search, local MCP tools.
 
+---
+
 ## Common Features
 
 All three client types support these standard agent features:

agent-framework/agents/providers/index.md

@@ -19,7 +19,7 @@ Microsoft Agent Framework supports several types of agents to accommodate differ
 |----------|:---:|:---:|:---:|:---:|:---:|:---:|
 | [Azure OpenAI](./azure-openai.md) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
 | [OpenAI](./openai.md) | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ |
-| [Microsoft Foundry](./azure-ai-foundry.md) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
+| [Microsoft Foundry](./microsoft-foundry.md) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
 | [Anthropic](./anthropic.md) | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ |
 | [Ollama](./ollama.md) | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ |
 | [GitHub Copilot](./github-copilot.md) | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ |
@@ -39,7 +39,7 @@ The following providers are available for .NET:
 
 - **[Azure OpenAI](./azure-openai.md)** — Full-featured provider with chat completion, responses API, and tool support.
 - **[OpenAI](./openai.md)** — Direct OpenAI API access with chat completion and responses API.
-- **[Foundry](./azure-ai-foundry.md)** — Persistent server-side agents with managed chat history.
+- **[Foundry](./microsoft-foundry.md)** — Persistent server-side agents with managed chat history.
 - **[Anthropic](./anthropic.md)** — Claude models with function tools and streaming support.
 - **[Ollama](./ollama.md)** — Run open-source models locally.
 - **[GitHub Copilot](./github-copilot.md)** — GitHub Copilot SDK integration with shell and file access.
@@ -56,7 +56,7 @@ Agent Framework supports many different inference services through chat clients.
 
 - **[Azure OpenAI](./azure-openai.md)** — Full-featured provider with Azure identity support.
 - **[OpenAI](./openai.md)** — Direct OpenAI API access.
-- **[Foundry](./azure-ai-foundry.md)** — Persistent server-side agents with managed chat history.
+- **[Foundry](./microsoft-foundry.md)** — Persistent server-side agents with managed chat history.
 - **[Anthropic](./anthropic.md)** — Claude models with extended thinking and hosted tools support.
 - **[Ollama](./ollama.md)** — Run open-source models locally.
 - **[GitHub Copilot](./github-copilot.md)** — GitHub Copilot SDK integration.