Merge branch 'main' of https://github.com/MicrosoftDocs/azure-ai-docs-pr

Author: s-polly

articles/ai-foundry/agents/concepts/threads-runs-messages.md

@@ -1,17 +1,17 @@
 ---
-title: Threads, Runs, and Messages in Azure AI Foundry Agent Service
+title: Threads, Runs, and Messages in the Azure AI Foundry Agent Service
 titleSuffix: Azure AI Foundry
 description: Learn about the components used in the Azure AI Foundry Agent Service.
 manager: nitinme
 author: aahill
 ms.author: aahi
 ms.service: azure-ai-agent-service
 ms.topic: conceptual
-ms.date: 04/15/2025
+ms.date: 09/24/2025
 ms.custom: azure-ai-agents
 ---
 
-# Threads, Runs, and Messages in Azure AI Foundry Agent Service
+# Threads, runs, and messages in Azure AI Foundry Agent Service
 
 Azure AI Foundry Agent Service supports persistent threads, runs, and messages, which are essential components for managing conversation states and interactions with users.
 
@@ -30,7 +30,7 @@ When you use an Agent, there are a series of steps that are involved.
 
 ## Agent
 
-A custom AI that uses AI models in conjunction with tools.
+An agent is a configurable orchestration component that uses AI models with instructions, tools, parameters, and optional safety/governance controls. At run time an agent uses these components and a given thread's message history to respond to user inputs. 
 
 ## Threads
 

articles/ai-foundry/agents/how-to/metrics.md

@@ -1,7 +1,7 @@
 ---
 title: Monitor Azure AI Foundry Agent Service
 description: Start here to learn how to use Azure Monitor to capture and analyze metrics for your Azure AI Foundry Agent Service.
-ms.date: 06/02/2025
+ms.date: 09/24/2025
 ms.custom: horz-monitor, subject-monitoring
 ms.topic: conceptual
 author: aahill

articles/ai-foundry/agents/how-to/tools/file-search.md

@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 08/01/2025
+ms.date: 09/24/2025
 author: aahill
 ms.author: aahi
 ms.custom: azure-ai-agents, references_regions

articles/ai-foundry/agents/how-to/tools/model-context-protocol.md

@@ -17,6 +17,9 @@ ms.custom: references_regions
 > [!NOTE]
 > Supported regions are `westus`, `westus2`, `uaenorth`, `southindia`, and `switzerlandnorth`.
 
+> [!NOTE]
+> When using a [Network Secured Azure AI Foundry](../../how-to/virtual-networks.md), private MCP servers deployed in the same virtual network is not supported, only publicly accessible MCP servers are supported.
+
 You can extend the capabilities of your Azure AI Foundry agent by connecting it to tools hosted on remote [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) servers (bring your own MCP server endpoint). Developers and organizations maintain these servers. The servers expose tools that MCP-compatible clients, such as Azure AI Foundry Agent Service, can access.
 
 MCP is an open standard that defines how applications provide tools and contextual data to large language models (LLMs). It enables consistent, scalable integration of external tools into model workflows.

articles/ai-foundry/agents/how-to/virtual-networks.md

@@ -42,6 +42,7 @@ For customers without an existing virtual network, the Standard Setup with Priva
 - **Region availability**:
   - For supported regions for model deployments, see: [Azure OpenAI model region support](../concepts/model-region-support.md#available-models).
 - **Azure Blob Storage**: using Azure Blob Storage files with the File Search tool isn't supported.
+- **Private MCP Server**: using private MCP servers deployed in the same virtual network is not supported, only publicly accessible MCP servers are supported.
 
 ## Prerequisites
 * An Azure subscription - [Create one for free](https://azure.microsoft.com/free/cognitive-services).

articles/ai-foundry/foundry-models/includes/models-azure-direct-others.md

@@ -87,8 +87,12 @@ xAI's Grok models in Azure AI Foundry Models include a diverse set of models des
     > [!NOTE]
     > [Registration is required for access to the grok-code-fast-1 model](https://aka.ms/xai/grok-code-fast-1).
 
+- Grok 4 Fast, an efficiency-optimized language model that delivers near-Grok 4 reasoning capabilities with significantly lower latency and cost, and can bypass reasoning entirely for ultra-fast applications. It is trained for safe and effective tool use, with built-in refusal behaviors, a fixed safety-enforcing system prompt, and input filters to prevent misuse.
+
 | Model  | Type | Capabilities | Deployment type (region availability) | Project type |
 | ------ | ---- | ------------ | ------------------------------------- | ------------ |
+| [grok-4-fast-reasoning](https://ai.azure.com/explore/models/grok-4-fast-reasoning/version/1/registry/azureml-xai/?cid=learnDocs)  | chat-completion | - **Input:** text, image (2,000,000 tokens) <br /> - **Output:** text (2,000,000 tokens) <br /> - **Languages:** `en` <br />  - **Tool calling:** yes <br /> - **Response formats:** text |- Global standard (all regions)  | Foundry, Hub-based |
+| [grok-4-fast-non-reasoning](https://ai.azure.com/explore/models/grok-4-fast-non-reasoning/version/1/registry/azureml-xai/?cid=learnDocs)  | chat-completion | - **Input:** text, image (2,000,000 tokens) <br /> - **Output:** text (2,000,000 tokens) <br /> - **Languages:** `en` <br />  - **Tool calling:** yes <br /> - **Response formats:** text |- Global standard (all regions)  | Foundry, Hub-based |
 | [grok-code-fast-1](https://ai.azure.com/explore/models/grok-code-fast-1/version/1/registry/azureml-xa/?cid=learnDocs)  | chat-completion | - **Input:** text (256,000 tokens) <br /> - **Output:** text (8,192 tokens) <br /> - **Languages:** `en` <br />  - **Tool calling:** yes <br /> - **Response formats:** text |- Global standard (all regions)  | Foundry, Hub-based |
 | [grok-3](https://ai.azure.com/explore/models/grok-3/version/1/registry/azureml-xai/?cid=learnDocs) | chat-completion | - **Input:** text (131,072 tokens) <br /> - **Output:** text (131,072 tokens) <br /> - **Languages:** `en` <br />  - **Tool calling:** yes <br /> - **Response formats:** text |- Global standard (all regions) <br> - Data zone standard (US) | Foundry, Hub-based |
 | [grok-3-mini](https://ai.azure.com/explore/models/grok-3-mini/version/1/registry/azureml-xai/?cid=learnDocs) | chat-completion | - **Input:** text (131,072 tokens) <br /> - **Output:** text (131,072 tokens) <br /> - **Languages:** `en` <br />  - **Tool calling:** yes <br /> - **Response formats:** text | - Global standard (all regions) <br> - Data zone standard (US) | Foundry, Hub-based |

articles/ai-foundry/foundry-models/includes/use-chat-reasoning/csharp.md

@@ -97,6 +97,10 @@ Usage:
 
 ### Reasoning content
 
+> [!NOTE]
+> This information on reasoning content does not apply to Azure OpenAI models. Azure OpenAI reasoning models use the [reasoning summaries feature](../../../openai/how-to/reasoning.md#reasoning-summary).
+
+
 Some reasoning models, like DeepSeek-R1, generate completions and include the reasoning behind it. The reasoning associated with the completion is included in the response's content within the tags `<think>` and `</think>`. The model may select on which scenarios to generate reasoning content. You can extract the reasoning content from the response to understand the model's thought process as follows:
 
 ```csharp

articles/ai-foundry/foundry-models/includes/use-chat-reasoning/java.md

@@ -89,6 +89,10 @@ Usage:
 
 ### Reasoning content
 
+> [!NOTE]
+> This information on reasoning content does not apply to Azure OpenAI models. Azure OpenAI reasoning models use the [reasoning summaries feature](../../../openai/how-to/reasoning.md#reasoning-summary).
+
+
 Some reasoning models, like DeepSeek-R1, generate completions and include the reasoning behind it. The reasoning associated with the completion is included in the response's content within the tags `<think>` and `</think>`. The model may select on which scenarios to generate reasoning content. You can extract the reasoning content from the response to understand the model's thought process as follows:
 
 ```java

articles/ai-foundry/foundry-models/includes/use-chat-reasoning/javascript.md

@@ -96,6 +96,9 @@ Usage:
 
 ### Reasoning content
 
+> [!NOTE]
+> This information on reasoning content does not apply to Azure OpenAI models. Azure OpenAI reasoning models use the [reasoning summaries feature](../../../openai/how-to/reasoning.md#reasoning-summary).
+
 Some reasoning models, like DeepSeek-R1, generate completions and include the reasoning behind it. The reasoning associated with the completion is included in the response's content within the tags `<think>` and `</think>`. The model may select on which scenarios to generate reasoning content. You can extract the reasoning content from the response to understand the model's thought process as follows:
 
 ```javascript

articles/ai-foundry/foundry-models/includes/use-chat-reasoning/python.md

@@ -171,6 +171,9 @@ Usage:
 
 ### Reasoning content
 
+> [!NOTE]
+> This information on reasoning content does not apply to Azure OpenAI models. Azure OpenAI reasoning models use the [reasoning summaries feature](../../../openai/how-to/reasoning.md#reasoning-summary).
+
 Some reasoning models, like DeepSeek-R1, generate completions and include the reasoning behind it. 
 
 # [OpenAI API](#tab/openai)