Merge branch 'MicrosoftDocs:main' into heidist-rag

Author: HeidiSteen

.github/policies/disallow-edits.yml

@@ -19,18 +19,14 @@ configuration:
                 @${issueAuthor} - You tried to add an index file to this repository; this is not permitted so your pull request will be closed automatically.
           - closePullRequest
 
-      - description: Close PRs to the "personalizer" and "responsible-ai" folders where the author isn't a member of the MicrosoftDocs org (i.e. PRs in public repo).
+      - description: Close PRs to the "responsible-ai" folders where the author isn't a member of the MicrosoftDocs org (i.e. PRs in public repo).
         if:
           - payloadType: Pull_Request
           - isAction:
               action: Opened
-          - or:
-            - filesMatchPattern:
-                matchAny: true
-                pattern: articles/ai-foundry/responsible-ai/*
-            - filesMatchPattern:
-                matchAny: true
-                pattern: articles/ai-services/personalizer/*
+          - filesMatchPattern:
+              matchAny: true
+              pattern: articles/ai-foundry/responsible-ai/*
           - not:
               activitySenderHasAssociation:
                 association: Member
@@ -40,50 +36,15 @@ configuration:
                 @${issueAuthor} - Pull requests that modify files in this folder aren't accepted from public contributors.
           - closePullRequest
 
-      - description: \@mention specific people when a PR is opened in the "personalizer" or "responsible-ai" folder.
-        if:
-          - payloadType: Pull_Request
-          - isAction:
-              action: Opened
-          - or:
-            - filesMatchPattern:
-                matchAny: true
-                pattern: articles/ai-foundry/responsible-ai/*
-            - filesMatchPattern:
-                matchAny: true
-                pattern: articles/ai-services/personalizer/*
-          - activitySenderHasAssociation:
-              association: Member
-          - not:
-              or:
-                - isActivitySender:
-                    user: eric-urban
-                - isActivitySender:
-                    user: nitinme
-                - isActivitySender:
-                    user: mrbullwinkle
-        then:
-          - addReply:
-              reply: >-
-                @${issueAuthor} - Please don't sign off on this PR. The area owners will sign off once they've reviewed your contribution.
-          - mentionUsers:
-              mentionees:
-                - eric-urban
-                - nitinme
-                - mrbullwinkle
-              replyTemplate: ${mentionees} - Please review this PR and sign off when you're ready to merge it.
-              assignMentionees: True # This part probably won't work since the bot doesn't have write perms.
-          - addLabel:
-              label: needs-human-review
 
-      - description: \@mention specific people when a PR is opened in the "ai-services/responsible-ai" folder.
+      - description: \@mention specific people when a PR is opened in the "ai-foundry/responsible-ai" folder.
         if:
           - payloadType: Pull_Request
           - isAction:
               action: Opened
           - filesMatchPattern:
               matchAny: true
-              pattern: articles/ai-services/responsible-ai/*
+              pattern: articles/ai-foundry/responsible-ai/*
           - activitySenderHasAssociation:
               association: Member
           - not:
@@ -100,8 +61,6 @@ configuration:
                     user: laujan
                 - isActivitySender:
                     user: patrickfarley
-                - isActivitySender:
-                    user: jboback
                 - isActivitySender:
                     user: heidisteen
                 - isActivitySender:
@@ -118,7 +77,6 @@ configuration:
                 - aahill
                 - laujan
                 - patrickfarley
-                - jboback
                 - heidisteen
                 - haileytap
               replyTemplate: ${mentionees} - Please review this PR and sign off when you're ready to merge it.

.openpublishing.publish.config.json

@@ -188,6 +188,12 @@
       "branch": "main",
       "branch_mapping": {}
     },
+    {
+      "path_to_root": "azure-search-dotnet-samples",
+      "url": "https://github.com/Azure-Samples/azure-search-dotnet-samples",
+      "branch": "main",
+      "branch_mapping": {}
+    },
     {
       "path_to_root": "azureai-model-inference-bicep",
       "url": "https://github.com/Azure-Samples/azureai-model-inference-bicep",
@@ -199,6 +205,12 @@
       "url": "https://github.com/MicrosoftDocs/azure-docs-pr",
       "branch": "main",
       "branch_mapping": {}
+    },
+    {
+        "path_to_root": "azure-policy-autogen-docs",
+        "url": "https://github.com/MicrosoftDocs/azure-policy-autogen-docs",
+        "branch": "main",
+        "branch_mapping": {}
     }
   ],
   "branch_target_mapping": {},

.openpublishing.redirection.json

@@ -460,6 +460,11 @@
       "redirect_url": "../foundry-models/overview",
       "redirect_document_id": false
     },
+    {
+      "source_path": "articles/ai-foundry/concepts/concept-model-distillation.md",
+      "redirect_url": "../openai/how-to/stored-completions",
+      "redirect_document_id": false
+    },
     {
       "source_path": "articles/ai-foundry/model-inference/quotas-limits.md",
       "redirect_url": "../foundry-models/quotas-limits",
@@ -486,4 +491,4 @@
       "redirect_document_id": false
     }
   ]
-}
+}

articles/ai-foundry/.openpublishing.redirection.ai-studio.json

@@ -450,9 +450,19 @@
             "redirect_url": "/azure/ai-foundry/how-to/troubleshoot-secure-connection-project",
             "redirect_document_id": true
           },
+          {
+            "source_path_from_root": "/articles/ai-foundry/foundry-models/supported-languages-openai.md",
+            "redirect_url": "/azure/ai-services/openai/supported-languages",
+            "redirect_document_id": false
+          },
           {
             "source_path_from_root": "/articles/ai-studio/how-to/use-blocklists.md",
-            "redirect_url": "/azure/ai-foundry/how-to/use-blocklists",
+            "redirect_url": "/azure/ai-foundry/foundry-models/how-to/use-blocklists",
+            "redirect_document_id": false
+          },
+          {
+            "source_path_from_root": "/articles/ai-foundry/how-to/use-blocklists.md",
+            "redirect_url": "/azure/ai-foundry/foundry-models/how-to/use-blocklists",
             "redirect_document_id": true
           },
           {
@@ -772,6 +782,16 @@
           "redirect_url": "/azure/ai-foundry/context/context.json",
           "redirect_document_id": false
         },
+        {
+            "source_path_from_root": "/articles/ai-foundry/foundry-models/index.yml",
+            "redirect_url": "/azure/ai-foundry/",
+            "redirect_document_id": false
+        },
+        {
+          "source_path_from_root": "/articles/ai-foundry/foundry-models/context/context.yml",
+          "redirect_url": "/azure/ai-foundry/context/context",
+          "redirect_document_id": false
+        },
         {
             "source_path_from_root": "/articles/ai-studio/responsible-use-of-ai-overview.md",
             "redirect_url": "/azure/ai-foundry/responsible-use-of-ai-overview",

articles/ai-foundry/agents/how-to/tools/deep-research-samples.md

@@ -17,6 +17,9 @@ Use this article to learn how to use the Deep Research tool with the Azure AI Pr
 
 ## Prerequisites
 
+> [!NOTE]
+> * The  `o3-deep-research` model and the GPT model deployments should be part of your AI Foundry project resulting in all three resources in the same Azure subscription and same region. Supported regions are **West US** and **Norway East**.
+
 * The requirements in the [Deep Research overview](./deep-research.md).
 * The Deep Research tool requires the latest prerelease versions of the `azure-ai-projects` library. You can install it with the following command:
 

articles/ai-foundry/agents/how-to/tools/deep-research.md

@@ -35,24 +35,29 @@ The deep research tool is a **code-only release** and available for use using th
 ## Knowledge source support
 The deep research tool is tightly integrated with Grounding with Bing Search and only supports web-based research.
 
-## How Deep Research works
-
-At its core, the Deep Research tool orchestrates a multi-step research pipeline uses the Azure OpenAI's `o3-deep-research` model together with Grounding with Bing Search to autonomously search for and read information from multiple online sources appropriate to the user prompt. This enables the Deep Research tool to generate thorough, documented, and cited reports on complex topics. 
+## Region support
+The Deep Research tool is supported in the following regions where the deep research model is available for deployment.
 
-### Deep research model deployment
+|West US  | Norway East |
+|---------|---------|
+| ✔️ | ✔️ | 
 
-The Deep Research tool uses the Azure OpenAI `o3-deep-research` model for its research tasks. The model was fine-tuned on the Azure OpenAI `o3` reasoning model.
+## Deep research model
+The Deep Research tool uses the Azure OpenAI `o3-deep-research` model for its research tasks. The model was fine-tuned on the Azure OpenAI `o3` reasoning model. Key features:
 
-**Key features**:
 - Handles data as part of its research tasks.
 - 200-K context length, 100-K completion tokens, and May 31, 2024 knowledge cutoff.
 - Outputs its thinking as reasoning summary as it analyzes information.
 - Delivers a synthesized report at the end of the research task.
 
-**Deployment information**:
-- Deployment type: Global Standard
-- Available regions: West US, Norway East
-- Quotas and limits: Enterprise: `30K RPS / 30M TPM`, Default: `3K RPS / 3M TPM`
+### Deployment information
+- **Deployment type**: Global Standard
+- **Available regions**: West US, Norway East
+- **Quotas and limits**: Enterprise: `30K RPS / 30M TPM`, Default: `3K RPS / 3M TPM`
+  
+## How Deep Research works
+
+At its core, the Deep Research tool orchestrates a multi-step research pipeline uses the Azure OpenAI's `o3-deep-research` model and any GPT model together with Grounding with Bing Search to autonomously search for and read information from multiple online sources appropriate to the user prompt. This enables the Deep Research tool to generate thorough, documented, and cited reports on complex topics. 
 
 ### GPT model deployment for clarifying intent
 
@@ -74,16 +79,19 @@ The output is a structured report that documents not only the comprehensive answ
 
 ## Prerequisites
 - If you already have access to the Azure OpenAI `o3` model, no request is required to access the `o3-deep-research`  model. Otherwise, fill out the [request form](https://aka.ms/OAI/deepresearchaccess). 
-- An Azure subscription with the ability to create resources [Set up your environment](../../environment-setup.md)
+- An Azure subscription with the ability to create AI Foundry project, Grounding with Bing Search, deep research model and GPT model resources [Set up your environment](../../environment-setup.md) in the **West US** and **Norway East** regions.
 - [Grounding with Bing Search tool](./bing-grounding.md) resource for connecting to your Azure AI Foundry project.
 - [Model deployments](../../../model-inference/how-to/create-model-deployments.md) for the following models
     - `o3-deep-research` version `2025-06-26`. This model is available in `West US` and `Norway East`.
-    - Any Azure OpenAI GPT model like `gpt-4o` for intent clarification.
+    - Any Azure OpenAI GPT model like `gpt-4o` for intent clarification. Deploy in the same regions.
 
 ## Setup 
 
 To use the Deep Research tool, you need to create the Azure AI Foundry type project, add your Grounding with Bing Search resource as a new connection, deploy the `o3-deep-research-model`, and deploy the selected Azure OpenAI GPT model. 
 
+> [!NOTE]
+> * The  `o3-deep-research` model and the GPT model deployments should be part of your AI Foundry project resulting in all three resources in the same Azure subscription and same region. Supported regions are **West US** and **Norway East**.
+
 :::image type="content" source="../../media/tools/deep-research/setup-deep-research-tool.png" alt-text="A diagram of the steps to set up the deep research tool." lightbox="../../media/tools/deep-research/setup-deep-research-tool.png":::
 
 1. Navigate to the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs) and create a new project.

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

@@ -17,7 +17,7 @@ ms.custom: azure-ai-agents-code
 
 Use this article to find step-by-step instructions and code samples for connecting Foundry Agent service with MCP.
 
-Follow the [REST API Quickstart](../../quickstart.md?pivots=rest-api#api-call-information) to set the right values for the environment variables `AGENT_TOKEN`, `AZURE_AI_FOUNDRY_PROJECT_ENDPOINT` and `API_VERSION`.
+Follow the [REST API Quickstart](../../quickstart.md?pivots=rest-api#api-call-information) to set the right values for the environment variables `AGENT_TOKEN`, `AZURE_AI_FOUNDRY_PROJECT_ENDPOINT`, and `API_VERSION`.
 
 
 ## Create an Agent with the MCP tool enabled
@@ -35,7 +35,7 @@ curl --request POST \
               "type": "mcp",
               "server_label": "<unique name for your MCP server>",
               "server_url": "<your MCP server url>",
-              "require_approval": "never",
+              "allowed_tools": ["<tool_name>"], # optional
           }
       ],
   "name": "my-assistant",
@@ -68,7 +68,13 @@ curl --request POST \
 
 ## Create a run and check the output
 
-Create a run to pass headers for the tool and observe that the model uses the Grounding with Bing Search tool to provide a response to the user's question.
+Create a run to pass headers for the tool and observe that the model uses the Grounding with Bing Search tool to provide a response to the user's question. 
+`require_approval` parameter is optional. If not provided, `always` is the default value, meaning each time developer needs to approve before calling. Supported values:
+
+- `always` by default
+- `never` meaning no approval is required
+- `{"never":[<tool_name_1>, <tool_name_2>]}` you can also provide a list of tools without required approval
+- `{"always":[<tool_name_1>, <tool_name_2>]}` you can provide a list of tools with required approval
 
 ```bash
 curl --request POST \
@@ -81,9 +87,11 @@ curl --request POST \
           "mcp": [
             {
                 "server_label": "<the same unique name you provided during agent creation>",
+		"require_approval": "always" #always by default
                 "headers": {
                     "Authorization": "Bearer <token>",
                 }
+
             }
           ]
       },
@@ -97,6 +105,62 @@ curl --request GET \
   -H "Authorization: Bearer $AGENT_TOKEN"
 ```
 
+If the model is trying to invoke a tool in your MCP server with approval required, you get a run with `require_action` status.
+```bash
+{
+  "id": "run_123",
+  "object": "thread.run",
+  ...
+  "status": "requires_action",
+  ...
+  "required_action": {
+    "type": "submit_tool_approval",
+    "submit_tool_approval": {
+      "tool_calls": [
+        {
+          "id": "call_123",
+          "type": "mcp",
+          "arguments": "{...}",
+          "name": "<tool_name>",
+          "server_label": "<server_label_you_provided>"
+        }
+      ]
+    }
+  },
+  ...
+  "tools": [
+    {
+      "type": "mcp",
+      "server_label": "<server_label_you_provided>",
+      "server_url": "<server_url_you_provided>",
+      "allowed_tools": null
+    }
+  ],
+ ...
+}
+```
+Make sure you carefully reviewed the tool and argument(s) to be passed and make an informed decision for approval.
+
+## Submit your approval
+If you decide to approve, you need to set the `approve` parameter to be `true` with the `id` for the preceding tool calls.
+```bash
+curl --request POST \
+  --url $AZURE_AI_FOUNDRY_PROJECT_ENDPOINT/threads/thread_abc123/runs/run_abc123/submit_tool_outputs?api-version=$API_VERSION \
+  -H "Authorization: Bearer $AGENT_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+	"tool_approvals": [
+        {
+            "tool_call_id": "call_abc123",
+            "approve": true,
+            "headers": {
+            }
+        }
+    ]
+}
+```
+
+
 ## Retrieve the agent response
 
 ```bash

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

@@ -27,7 +27,7 @@ You can bring multiple remote MCP servers to Foundry Agent service by adding the
 
 > [!Note]
 > * You need to bring a remote MCP server (an existing MCP server endpoint)
-> * With current MCP tool in Foundry Agent, explicit approval is not supported (only `never` is accepted for `require_approval` parameter). Please review carefully what MCP server(s) you added to Foundry Agent service. We recommend reviewing all data being shared with remote MCP servers and optionally logging it for auditing purposes.
+> * With current MCP tool in Foundry Agent, approval is required by default. Please review carefully what MCP server(s) you added to Foundry Agent service. We recommend reviewing all data being shared with remote MCP servers and optionally logging it for auditing purposes.
 > * Supported regions: `westus`, `westus2`, `uaenorth`, `southindia` and `switzerlandnorth`
 > * The MCP tool supports custom headers for a specific run, allowing you to pass headers as needed by MCP server, such as authentication schema. Headers you pass in will only be available for the current run and will not be persisted.
 
@@ -43,11 +43,20 @@ You can bring multiple remote MCP servers to Foundry Agent service by adding the
 1. Find the remote MCP server you want to connect to, such as GitHub MCP Server. Create or update a Foundry Agent with a `mcp` tool with the following information:
    1. `server_url`: the url of the MCP server, for example, `https://api.githubcopilot.com/mcp/`
    2. `server_label`: a unique identifier of this MCP server to the agent, for example, `github`
-   3. `require_approval`: only `never` is supported right now
+   3. `allowed_tools`: optional, a list of tools you want to allow without approval
 
 1. Create a run and pass additional information about the `mcp` tool in `tool_resources` with headers
    1. `tool_label`: use the identifier you provided during create/update agent
    2. `headers`: pass a set of headers required by the MCP server
+   3. `require_approval`: optional, if not provided, `always` is the default value, meaning each time developer needs to approve before calling. Supported values:
+      1. `always` by default
+      2. `never` meaning no approval is required
+      3. `{"never":[<tool_name_1>, <tool_name_2>]}` you can also provide a list of tools without required approval
+      4. `{"always":[<tool_name_1>, <tool_name_2>]}` you can provide a list of tools with required approval
+
+1. If the model is trying to invoke a tool in your MCP server with approval required, you will get Run status as `require_action`. Within `require_action` field, you can get more details on which tool in MCP server to be called, argument(s) to be passed and `call_id`. Make sur eyou review the tool, argument(s) and make an informed decision for approval. 
+
+1. Submit your approval to the agent with `call_id` by setting `approve` to `true.
 
 ## Next steps