Azure · howieleung · Jan 30, 2026 · Jan 31, 2026 · Jan 31, 2026 · Jan 31, 2026
@@ -9,10 +9,15 @@
 # 3. Run the tests (`pytest`) or run samples in the `samples` folder
 #
 
+# Set to true for console logging
+AZURE_AI_PROJECTS_CONSOLE_LOGGING=
+
 #######################################################################
 #
 # Used in samples
 #
+#######################################################################
+
 # Project endpoint has the format: 
 #  `https://<your-ai-services-account-name>.services.ai.azure.com/api/projects/<your-project-name>`
 AZURE_AI_PROJECT_ENDPOINT=
@@ -23,12 +28,8 @@ CONNECTION_NAME=
 AZURE_AI_PROJECTS_AZURE_SUBSCRIPTION_ID=
 AZURE_AI_PROJECTS_AZURE_RESOURCE_GROUP=
 AZURE_AI_PROJECTS_AZURE_AOAI_ACCOUNT=
-
-# Used in Memory Store samples
 MEMORY_STORE_CHAT_MODEL_DEPLOYMENT_NAME=
 MEMORY_STORE_EMBEDDING_MODEL_DEPLOYMENT_NAME=
-
-# Used in Agent tools samples
 IMAGE_GENERATION_MODEL_DEPLOYMENT_NAME=
 BING_PROJECT_CONNECTION_ID=
 MCP_PROJECT_CONNECTION_ID=
@@ -50,6 +51,7 @@ A2A_USER_INPUT=
 #######################################################################
 #
 # Used in tests
+#
 #######################################################################
 
 # Used for recording or playback

@@ -21,7 +21,10 @@
   * Rename class `MemorySearchTool` to `MemorySearchPreviewTool`.
   * Rename class `MicrosoftFabricAgentTool` to `MicrosoftFabricPreviewTool`.
   * Rename class `SharepointAgentTool` to `SharepointPreviewTool`.
-* Rename class `ItemParam` to `InputItem`.
+* Other class renames:
+  * Rename class `ItemParam` to `InputItem`.
+  * Rename class `PromptAgentDefinitionText` to `PromptAgentDefinitionTextOptions`
+  * Rename class `EvaluationComparisonRequest` to `InsightRequest`
 * Tracing: workflow actions in conversation item listings are now emitted as "gen_ai.conversation.item" events (with role="workflow") instead of "gen_ai.workflow.action" events in the list_conversation_items span.
 * Tracing: response generation span names changed from "responses {model_name}" to "chat {model_name}" for model calls and from "responses {agent_name}" to "invoke_agent {agent_name}" for agent calls.
 * Tracing: response generation operation names changed from "responses" to "chat" for model calls and from "responses" to "invoke_agent" for agent calls.
@@ -30,6 +33,11 @@
 * Tracing: "gen_ai.provider.name" attribute value changed to "microsoft.foundry".
 * Tracing: the format of the function tool call related traces in input and output messages changed to {"type": "tool_call", "id": "...", "name": "...", "arguments": {...}} and {"type": "tool_call_response", "id": "...", "result": "..."}
 
+### Sample updates
+
+* Add and update samples for `AzureFunctionTool`, `WebSearchTool`, and `WebSearchPreviewTool`
+* All samples for agent tools call `responses.create` API with `agent_reference` instead of `agent`
+
 ## 2.0.0b3 (2026-01-06)
 
 ### Features Added

@@ -8,6 +8,7 @@ resources in your Microsoft Foundry Project. Use it to:
   * Agent Memory Search
   * Agent-to-Agent (A2A)
   * Azure AI Search
+  * Azure Functions
   * Bing Custom Search
   * Bing Grounding
   * Browser Automation
@@ -20,7 +21,7 @@ resources in your Microsoft Foundry Project. Use it to:
   * Model Context Protocol (MCP)
   * OpenAPI
   * SharePoint
-  * Web Search
+  * Web Search/Web Search Preview
 * **Get an OpenAI client** using `.get_openai_client()` method to run Responses, Conversations, Evals and FineTuning operations with your Agent.
 * **Manage memory stores** for Agent conversations, using the `.memory_stores` operations.
 * **Explore additional evaluation tools** to assess the performance of your generative AI application, using the `.evaluation_rules`,
@@ -32,7 +33,7 @@ resources in your Microsoft Foundry Project. Use it to:
 * **Upload documents and create Datasets** to reference them using the `.datasets` operations.
 * **Create and enumerate Search Indexes** using methods the `.indexes` operations.
 
-The client library uses version `2025-11-15-preview` of the AI Foundry [data plane REST APIs](https://aka.ms/azsdk/azure-ai-projects-v2/api-reference-2025-11-15-preview).
+The client library uses version `v1` of the AI Foundry [data plane REST APIs](https://aka.ms/azsdk/azure-ai-projects-v2/api-reference-v1).
 
 [Product documentation](https://aka.ms/azsdk/azure-ai-projects-v2/product-doc)
 | [Samples][samples]
@@ -64,12 +65,6 @@ To report an issue with the client library, or request additional features, plea
 pip install --pre azure-ai-projects
 ```
 
-Note that the packages [openai](https://pypi.org/project/openai) and [azure-identity](https://pypi.org/project/azure-identity) also need to be installed if you intend to call `get_openai_client()`:
-
-```bash
-pip install openai azure-identity
-```
-
 ## Key concepts
 
 ### Create and authenticate the client with Entra ID
@@ -167,8 +162,7 @@ with project_client.get_openai_client() as openai_client:
 
     response = openai_client.responses.create(
         conversation=conversation.id,
-        extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
-        input="",
+        extra_body={"agent_reference": {"name": agent.name, "type": "agent_reference"}},
     )
     print(f"Response output: {response.output_text}")
 
@@ -180,8 +174,7 @@ with project_client.get_openai_client() as openai_client:
 
     response = openai_client.responses.create(
         conversation=conversation.id,
-        extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
-        input="",
+        extra_body={"agent_reference": {"name": agent.name, "type": "agent_reference"}},
     )
     print(f"Response output: {response.output_text}")
 
@@ -288,20 +281,50 @@ if image_data and image_data[0]:
 
 See the full sample in file `\agents\tools\sample_agent_image_generation.py` in the [Samples][samples] folder.
 
-**Web Search**
+**Web Search/Web Search Preview**
 
-Perform general web searches to retrieve current information from the internet. [OpenAI Documentation](https://platform.openai.com/docs/guides/tools-web-search)
+Discover up-to-date web content with the GA Web Search tool or try the Web Search Preview tool for the latest enhancements. Guidance on when to use each option is in the documentation: https://learn.microsoft.com/azure/ai-foundry/agents/how-to/tools/web-overview?view=foundry#determine-the-best-tool-for-your-use-cases.
 
 <!-- SNIPPET:sample_agent_web_search.tool_declaration -->
 
 ```python
-tool = WebSearchPreviewTool(user_location=ApproximateLocation(country="GB", city="London", region="London"))
+tool = WebSearchTool(
+    user_location=WebSearchApproximateLocation(type="approximate", country="GB", city="London", region="London")
+)
 ```
 
 <!-- END SNIPPET -->
 
 See the full sample in file `\agents\tools\sample_agent_web_search.py` in the [Samples][samples] folder.
 
+<!-- SNIPPET:sample_agent_web_search_preview.tool_declaration -->
+
+```python
+tool = WebSearchPreviewTool(user_location=ApproximateLocation(country="GB", city="London", region="London"))
+```
+
+<!-- END SNIPPET -->
+
+See the full sample in file `\agents\tools\sample_agent_web_search_preview.py` in the [Samples][samples] folder.
+
+Use the GA Web Search tool with a Bing Custom Search connection to scope results to your custom search instance:
+
+<!-- SNIPPET:sample_agent_web_search_with_custom_search.tool_declaration -->
+
+```python
+tool = WebSearchTool(
+    custom_search_configuration=WebSearchConfiguration(
+        project_connection_id=os.environ["BING_CUSTOM_SEARCH_PROJECT_CONNECTION_ID"],
+        instance_name=os.environ["BING_CUSTOM_SEARCH_INSTANCE_NAME"],
+    )
+)
+```
+
+<!-- END SNIPPET -->
+
+See the full sample in file `\agents\tools\sample_agent_web_search_with_custom_search.py` in the [Samples][samples] folder.
+
+
 **Computer Use**
 
 Enable agents to interact directly with computer systems for task automation and system operations:
@@ -346,7 +369,7 @@ Call external APIs defined by OpenAPI specifications without additional client-s
 
 ```python
 with open(weather_asset_file_path, "r") as f:
-    openapi_weather = jsonref.loads(f.read())
+    openapi_weather = cast(dict[str, Any], jsonref.loads(f.read()))
 
 tool = OpenApiTool(
     openapi=OpenApiFunctionDefinition(
@@ -393,6 +416,45 @@ tool = FunctionTool(
 
 See the full sample in file `\agents\tools\sample_agent_function_tool.py` in the [Samples][samples] folder.
 
+**Azure Functions**
+
+Integrate Azure Functions with agents to extend capabilities via serverless compute. Functions are invoked through Azure Storage Queue triggers, allowing asynchronous execution of custom logic.
+
+<!-- SNIPPET:sample_agent_azure_function.tool_declaration -->
+
+```python
+tool = AzureFunctionTool(
+    azure_function=AzureFunctionDefinition(
+        input_binding=AzureFunctionBinding(
+            storage_queue=AzureFunctionStorageQueue(
+                queue_name=os.environ["STORAGE_INPUT_QUEUE_NAME"],
+                queue_service_endpoint=os.environ["STORAGE_QUEUE_SERVICE_ENDPOINT"],
+            )
+        ),
+        output_binding=AzureFunctionBinding(
+            storage_queue=AzureFunctionStorageQueue(
+                queue_name=os.environ["STORAGE_OUTPUT_QUEUE_NAME"],
+                queue_service_endpoint=os.environ["STORAGE_QUEUE_SERVICE_ENDPOINT"],
+            )
+        ),
+        function=AzureFunctionDefinitionFunction(
+            name="queue_trigger",
+            description="Get weather for a given location",
+            parameters={
+                "type": "object",
+                "properties": {"location": {"type": "string", "description": "location to determine weather for"}},
+            },
+        ),
+    )
+)
+```
+
+<!-- END SNIPPET -->
+
+*After calling `responses.create()`, the agent enqueues function arguments to the input queue. Your Azure Function processes the request and returns results via the output queue.*
+
+See the full sample in file `\agents\tools\sample_agent_azure_function.py` and the Azure Function implementation in `\agents\tools\get_weather_func_app.py` in the [Samples][samples] folder.
+
 * **Memory Search Tool**
 
   The Memory Store Tool adds Memory to an Agent, allowing the Agent's AI model to search for past information related to the current user prompt.
@@ -594,7 +656,7 @@ Call external APIs defined by OpenAPI specifications using project connection au
 
 ```python
 with open(tripadvisor_asset_file_path, "r") as f:
-    openapi_tripadvisor = jsonref.loads(f.read())
+    openapi_tripadvisor = cast(dict[str, Any], jsonref.loads(f.read()))
 
 tool = OpenApiTool(
     openapi=OpenApiFunctionDefinition(
@@ -954,7 +1016,7 @@ You can add an Application Insights Azure resource to your Microsoft Foundry pro
 Make sure to install OpenTelemetry and the Azure SDK tracing plugin via
 
 ```bash
-pip install "azure-ai-projects>=2.0.0b1" azure-identity opentelemetry-sdk azure-core-tracing-opentelemetry azure-monitor-opentelemetry
+pip install "azure-ai-projects>=2.0.0b4" opentelemetry-sdk azure-core-tracing-opentelemetry azure-monitor-opentelemetry
 ```
 
 You will also need an exporter to send telemetry to your observability backend. You can print traces to the console or use a local viewer such as [Aspire Dashboard](https://learn.microsoft.com/dotnet/aspire/fundamentals/dashboard/standalone?tabs=bash).

@@ -1,3 +1,3 @@
 {
-  "apiVersion": "2025-11-15-preview"
+  "apiVersion": "v1"
 }