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

Author: s-polly

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

@@ -7,7 +7,7 @@ manager: nitinme
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-agent-service
 ms.topic: how-to
-ms.date: 08/15/2025
+ms.date: 09/26/2025
 author: aahill
 ms.author: aahi
 ms.custom: azure-ai-agents
@@ -40,7 +40,7 @@ The authorization will happen between Grounding with Bing Custom Search service
 
 Developers and end users don't have access to raw content returned from Grounding with Bing Custom Search. The model response, however, includes citations with links to the websites used to generate the response and is allowed to be stored using the mechanisms provided by the Agents Service. You can retrieve the model response by accessing the data in the thread that was created. These references must be retained and displayed in the exact form provided by Microsoft, as per Grounding with Bing Custom Search's Use and Display Requirements. 
 
- 
+Transactions with your Grounding with Bing resource are counted by the number of tool calls per run. You can see how many tool calls are made from the run step.
 
 ## Setup 
 

articles/ai-foundry/agents/how-to/tools/bing-grounding.md

@@ -7,7 +7,7 @@ manager: nitinme
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-agent-service
 ms.topic: how-to
-ms.date: 08/07/2025
+ms.date: 09/26/2025
 author: aahill
 ms.author: aahi
 ms.custom: azure-ai-agents
@@ -38,6 +38,8 @@ Grounding with Bing returns relevant search results to the customer's model depl
 
 The authorization will happen between Grounding with Bing Search service and Azure AI Foundry Agent Service. Any Bing search query that is generated and sent to Bing for the purposes of grounding is transferred, along with the resource key, outside of the Azure compliance boundary to the Grounding with Bing Search service. Grounding with Bing Search is subject to Bing's terms and do not have the same compliance standards and certifications as the Azure AI Foundry Agent Service, as described in the [Grounding with Bing Search Terms of Use](https://www.microsoft.com/bing/apis/grounding-legal). It is your responsibility to assess whether the use of Grounding with Bing Search in your agent meets your needs and requirements.
 
+Transactions with your Grounding with Bing resource are counted by the number of tool calls per run. You can see how many tool calls are made from the run step.
+
 ## Supported capabilities and known issues
 - Grounding with Bing Search tool is designed to retrieve real-time information from web, NOT specific web domains.
 - NOT Recommended to **summarize** an entire web page.

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

@@ -32,7 +32,7 @@ Use this article to find code samples for connecting Azure AI Foundry Agent Serv
 Create a client object that contains the endpoint for connecting to your AI project and other resources.
 
 > [!NOTE]
-> You can find an asynchronous example on [GitHub](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/ai/Azure.AI.Agents.Persistent/samples/Sample26_PersistentAgents_MCP.md)
+> You can find an asynchronous example on [GitHub](https://github.com/Azure/azure-sdk-for-net/tree/main/sdk/ai/Azure.AI.Agents.Persistent/samples)
 
 ```csharp
 var projectEndpoint = System.Environment.GetEnvironmentVariable("PROJECT_ENDPOINT");

articles/ai-foundry/agents/overview.md

@@ -8,7 +8,7 @@ ms.author: aahi
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-agent-service
 ms.topic: overview
-ms.date: 06/25/2025
+ms.date: 09/26/2025
 ms.custom: azure-ai-agents
 ---
 
@@ -117,6 +117,20 @@ Start with the [environment setup](environment-setup.md) and [quickstart](quicks
 1. After you create a project, you can deploy a compatible model such as GPT-4o.
 1. When you have a deployed model, you can also start making API calls to the service using the SDKs.
 
+## Business Continuity and Disaster Recovery (BCDR) for Agents
+
+To support service resilience, the Azure AI Foundry Agent service relies on customer-provisioned Cosmos DB accounts. This ensures that your agent state can be preserved and recovered in the event of a regional outage.
+
+### Use your own Cosmos DB account
+
+* As an Azure Standard customer, you provision and manage your own single-tenant Cosmos DB account. All agent state is stored in your Cosmos DB.
+* Backup and recovery rely on Cosmos DB’s native capabilities, which you control.
+* If the primary region becomes unavailable, the agent will automatically become available in the secondary region by connecting to the same Cosmos DB account.
+* Since all history is preserved in Cosmos DB, the agent can continue operation with minimal disruption.
+
+### Current guidance
+
+We recommend customers provision and maintain their Cosmos DB account and ensure appropriate backup and recovery policies are configured. This ensures seamless continuity if the primary region becomes unavailable.
 
 ## Next steps
 

articles/ai-foundry/foundry-models/how-to/configure-entra-id.md

@@ -1,18 +1,21 @@
 ---
 title: Configure key-less authentication with Microsoft Entra ID
 titleSuffix: Azure AI Foundry
-description: Learn how to configure key-less authorization to use Azure AI Foundry Models with Microsoft Entra ID.
+description: Learn how to configure key-less authorization to use Azure AI Foundry Models with Microsoft Entra ID and enhance security.
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-model-inference
 ms.topic: how-to
-ms.date: 08/29/2025
+ms.date: 09/26/2025
 ms.custom: ignite-2024, github-universe-2024
 author: msakande
 ms.author: mopeakande
 recommendations: false
 zone_pivot_groups: azure-ai-models-deployment
 ms.reviewer: fasantia
 reviewer: santiagxf
+ai-usage: ai-assisted
+
+#CustomerIntent: As a developer, I want to configure keyless authentication with Microsoft Entra ID for Azure AI Foundry Models so that I can secure my AI model deployments without relying on API keys and leverage role-based access control for better security and compliance.
 ---
 
 # Configure key-less authentication with Microsoft Entra ID
@@ -29,6 +32,6 @@ reviewer: santiagxf
 [!INCLUDE [bicep](../../foundry-models/includes/configure-entra-id/bicep.md)]
 ::: zone-end
 
-## Next steps
+## Next step
 
 * [Develop applications using Azure AI Foundry Models](../../model-inference/supported-languages.md)

articles/ai-foundry/foundry-models/includes/code-create-chat-client-entra.md

@@ -3,20 +3,20 @@ manager: nitinme
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-model-inference
 ms.topic: include
-ms.date: 1/21/2025
+ms.date: 09/26/2025
 ms.author: fasantia
 author: santiagxf
 ---
 
 # [Python](#tab/python)
 
-Install the package `azure-ai-inference` using your package manager, like pip:
+Install the `azure-ai-inference` package, using a package manager like pip:
 
 ```bash
 pip install azure-ai-inference
 ```
 
-Then, you can use the package to consume the model. The following example shows how to create a client to consume chat completions with Entra ID:
+Then, use the package to consume the model. The following example shows how to create a client to consume chat completions with Microsoft Entra ID:
 
 ```python
 import os
@@ -32,13 +32,13 @@ client = ChatCompletionsClient(
 
 # [JavaScript](#tab/javascript)
 
-Install the package `@azure-rest/ai-inference` using npm:
+Install the `@azure-rest/ai-inference` package with npm:
 
 ```bash
 npm install @azure-rest/ai-inference
 ```
 
-Then, you can use the package to consume the model. The following example shows how to create a client to consume chat completions with Entra ID:
+Then, use the package to consume the model. The following example shows how to create a client to consume chat completions with Microsoft Entra ID:
 
 ```javascript
 import ModelClient from "@azure-rest/ai-inference";
@@ -76,7 +76,7 @@ using Azure.Identity;
 using Azure.AI.Inference;
 ```
 
-Then, you can use the package to consume the model. The following example shows how to create a client to consume chat completions with Entra ID:
+Then, use the package to consume the model. The following example shows how to create a client to consume chat completions with Microsoft Entra ID:
 
 ```csharp
 TokenCredential credential = new DefaultAzureCredential();
@@ -108,7 +108,7 @@ Add the package to your project:
 </dependency>
 ```
 
-Then, you can use the package to consume the model. The following example shows how to create a client to consume chat completions:
+Then, use the package to consume the model. The following example shows how to create a client to consume chat completions:
 
 ```java
 TokenCredential defaultCredential = new DefaultAzureCredentialBuilder().build();
@@ -118,11 +118,11 @@ ChatCompletionsClient client = new ChatCompletionsClientBuilder()
     .buildClient();
 ```
 
-Explore our [samples](https://github.com/Azure/azure-sdk-for-java/tree/main/sdk/ai/azure-ai-inference/src/samples) and read the [API reference documentation](https://aka.ms/azsdk/azure-ai-inference/java/reference) to get yourself started.
+Explore our [samples](https://github.com/Azure/azure-sdk-for-java/tree/main/sdk/ai/azure-ai-inference/src/samples) and read the [API reference documentation](https://aka.ms/azsdk/azure-ai-inference/java/reference) to get started.
 
 # [REST](#tab/rest)
 
-Use the reference section to explore the API design and which parameters are available and indicate authentication token in the header `Authorization`. For example, the reference section for [Chat completions](../../model-inference/reference/reference-model-inference-chat-completions.md) details how to use the route `/chat/completions` to generate predictions based on chat-formatted instructions. Notice that the path `/models` is included to the root of the URL:
+Use the reference section to explore the API design and see which parameters are available. Indicate the authentication token in the header `Authorization`. For example, the reference section for [Chat completions](../../model-inference/reference/reference-model-inference-chat-completions.md) details how to use the route `/chat/completions` to generate predictions based on chat-formatted instructions. The path `/models` is included in the root of the URL:
 
 __Request__
 
@@ -132,7 +132,7 @@ Authorization: Bearer <bearer-token>
 Content-Type: application/json
 ```
 
-Tokens have to be issued with scope `https://cognitiveservices.azure.com/.default`.
+Tokens must be issued with scope `https://cognitiveservices.azure.com/.default`.
 
 For testing purposes, the easiest way to get a valid token for your user account is to use the Azure CLI. In a console, run the following Azure CLI command:
 

articles/ai-foundry/foundry-models/includes/configure-entra-id/about-credentials.md

@@ -4,15 +4,15 @@ author: santiagxf
 ms.author: fasantia 
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-model-inference
-ms.date: 01/23/2025
+ms.date: 09/26/2025
 ms.topic: include
 ---
 
 ### Options for credential when using Microsoft Entra ID
 
-`DefaultAzureCredential` is an opinionated, ordered sequence of mechanisms for authenticating to Microsoft Entra ID. Each authentication mechanism is a class derived from the `TokenCredential` class and is known as a credential. At runtime, `DefaultAzureCredential` attempts to authenticate using the first credential. If that credential fails to acquire an access token, the next credential in the sequence is attempted, and so on, until an access token is successfully obtained. In this way, your app can use different credentials in different environments without writing environment-specific code.
+`DefaultAzureCredential` is an opinionated, ordered sequence of mechanisms for authenticating to Microsoft Entra ID. Each authentication mechanism is a class derived from the `TokenCredential` class and is known as a credential. At runtime, `DefaultAzureCredential` attempts to authenticate by using the first credential. If that credential fails to acquire an access token, the next credential in the sequence is attempted, and so on, until an access token is successfully obtained. In this way, your app can use different credentials in different environments without writing environment-specific code.
 
-When the preceding code runs on your local development workstation, it looks in the environment variables for an application service principal or at locally installed developer tools, such as Visual Studio, for a set of developer credentials. Either approach can be used to authenticate the app to Azure resources during local development.
+When the preceding code runs on your local development workstation, it looks in the environment variables for an application service principal or at locally installed developer tools, such as Visual Studio, for a set of developer credentials. You can use either approach to authenticate the app to Azure resources during local development.
 
 When deployed to Azure, this same code can also authenticate your app to other Azure resources. `DefaultAzureCredential` can retrieve environment settings and managed identity configurations to authenticate to other services automatically.
 

articles/ai-foundry/foundry-models/includes/configure-entra-id/bicep.md

@@ -4,7 +4,7 @@ author: santiagxf
 ms.author: fasantia 
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-model-inference
-ms.date: 12/15/2024
+ms.date: 09/26/2025
 ms.topic: include
 zone_pivot_groups: azure-ai-models-deployment
 ---
@@ -19,7 +19,7 @@ zone_pivot_groups: azure-ai-models-deployment
 
 ## About this tutorial
 
-The example in this article is based on code samples contained in the [Azure-Samples/azureai-model-inference-bicep](https://github.com/Azure-Samples/azureai-model-inference-bicep) repository. To run the commands locally without having to copy or paste file content, use the following commands to clone the repository and go to the folder for your coding language:
+The example in this article is based on code samples in the [Azure-Samples/azureai-model-inference-bicep](https://github.com/Azure-Samples/azureai-model-inference-bicep) repository. To run the commands locally without copying or pasting file content, use the following commands to clone the repository and go to the folder for your coding language:
 
 ```azurecli
 git clone https://github.com/Azure-Samples/azureai-model-inference-bicep
@@ -33,24 +33,24 @@ cd azureai-model-inference-bicep/infra
 
 ## Understand the resources
 
-The tutorial helps you create:
+In this tutorial, you create the following resources:
 
-> [!div class="checklist"]
-> * An Azure AI Foundry (formerly known Azure AI Services) resource with key access disabled. For simplicity, this template doesn't deploy models.
-> * A role-assignment for a given security principal with the role **Cognitive Services User**.
 
-You are using the following assets to create those resources:
+* An Azure AI Foundry resource (formerly known as Azure AI Services resource) with key access disabled. For simplicity, this template doesn't deploy models.
+* A role-assignment for a given security principal with the role **Cognitive Services User**.
 
-1. Use the template `modules/ai-services-template.bicep` to describe your Azure AI Foundry (formerly known Azure AI Services) resource:
+To create these resources, use the following assets:
+
+1. Use the template `modules/ai-services-template.bicep` to describe your Azure AI Foundry resource:
 
     __modules/ai-services-template.bicep__
 
     :::code language="bicep" source="~/azureai-model-inference-bicep/infra/modules/ai-services-template.bicep":::
 
     > [!TIP]
-    > Notice that this template can take the parameter `allowKeys` which, when `false` will disable the use of keys in the resource. This configuration is optional.
+    > This template accepts the `allowKeys` parameter. Set it to `false` to disable key access in the resource. This configuration is optional.
 
-2. Use the template `modules/role-assignment-template.bicep` to describe a role assignment in Azure:
+1. Use the template `modules/role-assignment-template.bicep` to describe a role assignment in Azure:
 
     __modules/role-assignment-template.bicep__
 
@@ -66,36 +66,36 @@ In your console, follow these steps:
 
     :::code language="bicep" source="~/azureai-model-inference-bicep/infra/deploy-entra-id.bicep":::
 
-2. Log into Azure:
+1. Sign in to Azure:
 
     ```azurecli
     az login
     ```
 
-3. Ensure you are in the right subscription:
+1. Make sure you're in the right subscription:
 
     ```azurecli
     az account set --subscription "<subscription-id>"
     ```
 
-4. Run the deployment:
+1. Run the deployment:
 
     ```azurecli
     RESOURCE_GROUP="<resource-group-name>"
     SECURITY_PRINCIPAL_ID="<your-security-principal-id>"
     
     az deployment group create \
       --resource-group $RESOURCE_GROUP \
-      --securityPrincipalId $SECURITY_PRINCIPAL_ID
+      --parameters securityPrincipalId=$SECURITY_PRINCIPAL_ID \
       --template-file deploy-entra-id.bicep
     ```
 
-7. The template outputs the Azure AI Foundry Models endpoint that you can use to consume any of the model deployments you have created.
+1. The template outputs the Azure AI Foundry Models endpoint that you can use to consume any of the model deployments you created.
 
 
 ## Use Microsoft Entra ID in your code
 
-Once you configured Microsoft Entra ID in your resource, you need to update your code to use it when consuming the inference endpoint. The following example shows how to use a chat completions model:
+After you configure Microsoft Entra ID in your resource, update your code to use it when consuming the inference endpoint. The following example shows how to use a chat completions model:
 
 [!INCLUDE [code](../code-create-chat-client-entra.md)]
 
@@ -107,7 +107,7 @@ Once you configured Microsoft Entra ID in your resource, you need to update your
 
 ## Disable key-based authentication in the resource
 
-Disabling key-based authentication is advisable when you implemented Microsoft Entra ID and fully addressed compatibility or fallback concerns in all the applications that consume the service. You can achieve it by changing the property `disableLocalAuth`:
+Disable key-based authentication when you implement Microsoft Entra ID and fully address compatibility or fallback concerns in all the applications that consume the service. Change the `disableLocalAuth` property to disable key-based authentication:
 
 __modules/ai-services-template.bicep__