Merge pull request #6714 from MicrosoftDocs/main

Auto Publish – main to live - 2025-08-22 05:07 UTC

Author: learn-build-service-prod[bot]

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

@@ -1228,6 +1228,11 @@
           "redirect_url": "/azure/ai-foundry/",
           "redirect_document_id": false
         },
+        {
+          "source_path_from_root": "/articles/ai-foundry/agents/concepts/tracing.md",
+          "redirect_url": "/azure/ai-foundry/how-to/develop/trace-agents-sdk",
+          "redirect_document_id": true
+        },
         {
           "source_path_from_root": "/articles/ai-foundry/how-to/online-evaluation.md",
           "redirect_url": "/azure/ai-foundry/how-to/monitor-applications",

articles/ai-foundry/agents/concepts/tracing.md

@@ -44,7 +44,7 @@ Tools are optional capabilities you can add to your AI agent for AI models to de
 
 You can add tools at the agent, thread, or run level. By providing tools at a narrower level, the tool resources will **override** tool resources at a broader level. For example, tool resources at the run level override tool resources at thread level. Currently, you can add multiple tools but you can add **one instance of each** of the following tools: File Search, Azure AI Search, Grounding with Bing Search, Grounding with Bing Custom Search, Microsoft Fabric, and other tools under `knowledge` section. 
 
-When a user sends a query to the agent, it will create a [thread, run, and message](../../concepts\threads-runs-messages.md). For each run, the AI model decides what tools to invoke based on the user intent and available tool resources. Based on the tool outputs, the AI model might decide to invoke another tool or call the same tool again to get more context. For example, when you use Grounding with Bing Search tool, you might see multiple Bing Search queries when [tracing a thread](../../concepts\tracing.md). This means the AI model actually calls the Grounding with Bing Search tool multiple times with different queries to get more information. If you want to learn more about what tools are called and how the AI model invokes them, check the run step details.
+When a user sends a query to the agent, it will create a [thread, run, and message](../../concepts\threads-runs-messages.md). For each run, the AI model decides what tools to invoke based on the user intent and available tool resources. Based on the tool outputs, the AI model might decide to invoke another tool or call the same tool again to get more context. For example, when you use Grounding with Bing Search tool, you might see multiple Bing Search queries when [tracing a thread](../../../how-to/develop/trace-agents-sdk.md). This means the AI model actually calls the Grounding with Bing Search tool multiple times with different queries to get more information. If you want to learn more about what tools are called and how the AI model invokes them, check the run step details.
 
 There are various ways to influence how your AI agent invokes tools:
 

articles/ai-foundry/agents/how-to/tools/overview.md

@@ -104,7 +104,7 @@ Azure AI Foundry Agent Service provides a production-ready foundation for deploy
 | **3. Tool orchestration** | Server-side execution and retry of [tool calls](how-to\tools\overview.md) with structured logging. No manual orchestration required. |
 | **4. Trust and safety** | Integrated [content filters](../openai/how-to/content-filters.md) help prevent misuse and mitigate prompt injection risks (XPIA). all outputs are policy-governed. |
 | **5. Enterprise integration** | Bring your own [storage](./how-to/use-your-own-resources.md#use-an-existing-azure-cosmos-db-for-nosql-account-for-thread-storage), [Azure AI Search index](./how-to/use-your-own-resources.md#use-an-existing-azure-ai-search-resource), and [virtual network](how-to\virtual-networks.md) to meet compliance needs. |
-| **6. Observability and debugging** | Threads, tool invocations, and message traces are [fully traceable](concepts\tracing.md); [Application Insights integration](./how-to/metrics.md) for telemetry |
+| **6. Observability and debugging** | Threads, tool invocations, and message traces are [fully traceable](../how-to/develop/trace-agents-sdk.md); [Application Insights integration](./how-to/metrics.md) for telemetry |
 | **7. Identity and policy control** | Built on Microsoft Entra with full support for RBAC, audit logs, and enterprise conditional access. |
 
 ## Get started with Foundry Agent Service

articles/ai-foundry/agents/overview.md

@@ -146,7 +146,7 @@ items:
     - name: Service monitoring
       href: how-to/metrics.md
     - name: Trace and observe agents
-      href: concepts/tracing.md
+      href: ../how-to/develop/trace-agents-sdk.md
 - name: Responsible AI
   items:
     - name: Transparency note

articles/ai-foundry/agents/toc.yml

@@ -66,7 +66,7 @@ The [AI Foundry Visual Studio Code extension](../../ai-foundry/how-to/develop/vs
 
 #### Trace agents
 
-Debug and monitor your agents by [tracing agent threads](concepts\tracing.md) to clearly see the inputs and outputs of each primitive involved in a particular agent run, in the order in which they were invoked. 
+Debug and monitor your agents by [tracing agent threads](../how-to/develop/trace-agents-sdk.md) to clearly see the inputs and outputs of each primitive involved in a particular agent run, in the order in which they were invoked. 
 
 #### Trigger agents using Azure Logic Apps 
 
@@ -122,7 +122,7 @@ Azure AI Service is now available in preview. The service builds off of the Assi
     * [.NET](quickstart.md?pivots=programming-language-csharp) 
     * [The Azure Python SDK](quickstart.md?pivots=programming-language-python-azure)  
     * [The OpenAI Python SDK](quickstart.md?pivots=programming-language-python-openai)   
-* Debugging support using [tracing with Application Insights](concepts\tracing.md)
+* Debugging support using [tracing with Application Insights](../how-to/develop/trace-agents-sdk.md)
 
 ## Next steps
 

articles/ai-foundry/agents/whats-new.md

@@ -64,7 +64,7 @@ To perform inferencing with Cohere rerank models, you're required to use Cohere'
 
 *Queries*, not to be confused with a user's query, is a pricing meter that refers to the cost associated with the tokens used as input for inference of a Cohere Rerank model. Cohere counts a single search unit as a query with up to 100 documents to be ranked. Documents longer than 500 tokens (for Cohere-rerank-v3.5) or longer than 4096 tokens (for Cohere-rerank-v3-English and Cohere-rerank-v3-multilingual) when including the length of the search query are split up into multiple chunks, where each chunk counts as a single document.
 
-See the [Cohere model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=cohere).
+See the [Cohere model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=Cohere).
 
 ## Core42
 
@@ -119,7 +119,7 @@ The following table provides links to examples of how to use Meta Llama models.
 
 ## Microsoft
 
-Microsoft models include various model groups such as MAI models, Phi models, healthcare AI models, and more. To see all the available Microsoft models, view [the Microsoft model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=phi).
+Microsoft models include various model groups such as MAI models, Phi models, healthcare AI models, and more. To see all the available Microsoft models, view [the Microsoft model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=Microsoft).
 
 The following table provides links to examples of how to use Microsoft models.
 
@@ -133,7 +133,7 @@ The following table provides links to examples of how to use Microsoft models.
 | Llama-Index                               | Python            | [Link](https://aka.ms/azureai/llamaindex)             |  
 
 
-See [the Microsoft model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=phi).
+See [the Microsoft model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=Microsoft).
 
 
 ## Mistral AI
@@ -199,7 +199,7 @@ There are four pricing meters that determine the price you pay. These meters are
 | paygo-finetuned-model-inference-input-tokens | Costs associated with the tokens used as input for inference when *finetune_steps* > 0 |
 | paygo-finetuned-model-inference-output-tokens | Costs associated with the tokens used as output for inference when *finetune_steps* > 0 |
 
-See the [Nixtla model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=nixtla).
+See the [Nixtla model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=Nixtla).
 
 ## Stability AI