.NET: Python: feat(google): Add production-ready Google AI chat client with compreh…

.devcontainer/dotnet/devcontainer.json

@@ -1,10 +1,11 @@
 {
   "name": "C# (.NET)",
-  "image": "mcr.microsoft.com/devcontainers/dotnet:9.0",
+  "image": "mcr.microsoft.com/devcontainers/dotnet:10.0",
   "features": {
     "ghcr.io/devcontainers/features/dotnet:2.4.0": {},
     "ghcr.io/devcontainers/features/powershell:1.5.1": {},
-    "ghcr.io/devcontainers/features/azure-cli:1.2.8": {}
+    "ghcr.io/devcontainers/features/azure-cli:1.2.8": {},
+    "ghcr.io/devcontainers/features/docker-in-docker:2.12.4": {}
   },
   "workspaceFolder": "/workspaces/agent-framework/dotnet/",
   "customizations": {

.github/CODEOWNERS

@@ -0,0 +1,4 @@
+# Code ownership assignments
+# https://docs.github.com/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-code-owners
+
+python/packages/azurefunctions/ @microsoft/agentframework-durabletask-developers

.github/actions/azure-functions-integration-setup/action.yml

@@ -0,0 +1,36 @@
+name: Azure Functions Integration Test Setup
+description: Prepare local emulators and tools for Azure Functions integration tests
+
+runs:
+    using: "composite"
+    steps:
+      - name: Start Durable Task Scheduler Emulator
+        shell: bash
+        run: |
+          if [ "$(docker ps -aq -f name=dts-emulator)" ]; then
+            echo "Stopping and removing existing Durable Task Scheduler Emulator"
+            docker rm -f dts-emulator
+          fi
+          echo "Starting Durable Task Scheduler Emulator"
+          docker run -d --name dts-emulator -p 8080:8080 -p 8082:8082 mcr.microsoft.com/dts/dts-emulator:latest
+          echo "Waiting for Durable Task Scheduler Emulator to be ready"
+          timeout 30 bash -c 'until curl --silent http://localhost:8080/healthz; do sleep 1; done'
+          echo "Durable Task Scheduler Emulator is ready"
+      - name: Start Azurite (Azure Storage emulator)
+        shell: bash
+        run: |
+          if [ "$(docker ps -aq -f name=azurite)" ]; then
+            echo "Stopping and removing existing Azurite (Azure Storage emulator)"
+            docker rm -f azurite
+          fi
+          echo "Starting Azurite (Azure Storage emulator)"
+          docker run -d --name azurite -p 10000:10000 -p 10001:10001 -p 10002:10002 mcr.microsoft.com/azure-storage/azurite
+          echo "Waiting for Azurite (Azure Storage emulator) to be ready"
+          timeout 30 bash -c 'until curl --silent http://localhost:10000/devstoreaccount1; do sleep 1; done'
+          echo "Azurite (Azure Storage emulator) is ready"
+      - name: Install Azure Functions Core Tools
+        shell: bash
+        run: |
+          echo "Installing Azure Functions Core Tools"
+          npm install -g azure-functions-core-tools@4 --unsafe-perm true
+          func --version

.github/dependabot.yml

@@ -11,9 +11,6 @@ updates:
     schedule:
       interval: "cron"
       cronjob: "0 8 * * 4,0" # Every Thursday(4) and Sunday(0) at 8:00 UTC
-    experimental:
-      nuget-native-updater: false
-      enable-cooldown-metrics-collection: false
     ignore:
       # For all System.* and Microsoft.Extensions/Bcl.* packages, ignore all major version updates
       - dependency-name: "System.*"
@@ -28,6 +25,14 @@ updates:
       - "dependencies"
 
   # Maintain dependencies for python
+  - package-ecosystem: "pip"
+    directory: "python/"
+    schedule:
+      interval: "weekly"
+      day: "monday"
+    labels:
+      - "python"
+      - "dependencies"
   - package-ecosystem: "uv"
     directory: "python/"
     schedule:

.github/instructions/durabletask-dotnet.instructions.md

@@ -0,0 +1,17 @@
+---
+applyTo: "dotnet/src/Microsoft.Agents.AI.DurableTask/**,dotnet/src/Microsoft.Agents.AI.Hosting.AzureFunctions/**"
+---
+
+# Durable Task area code instructions
+
+The following guidelines apply to pull requests that modify files under
+`dotnet/src/Microsoft.Agents.AI.DurableTask/**` or
+`dotnet/src/Microsoft.Agents.AI.Hosting.AzureFunctions/**`:
+
+## CHANGELOG.md
+
+- Each pull request that modifies code should add just one bulleted entry to the `CHANGELOG.md` file containing a change title (usually the PR title) and a link to the PR itself.
+- New PRs should be added to the top of the `CHANGELOG.md` file under a "## [Unreleased]" heading.
+- If the PR is the first since the last release, the existing "## [Unreleased]" heading should be replaced with a "## v[X.Y.Z]" heading and the PRs since the last release should be added to the new "## [Unreleased]" heading.
+- The style of new `CHANGELOG.md` entries should match the style of the other entries in the file.
+- If the PR introduces a breaking change, the changelog entry should be prefixed with "[BREAKING]".

.github/upgrades/prompts/SemanticKernelToAgentFramework.md

@@ -142,9 +142,9 @@ Replace these Semantic Kernel agent classes with their Agent Framework equivalen
 |----------------------|----------------------------|-------------------|
 | `IChatCompletionService` | `IChatClient` | Convert to `IChatClient` using `chatService.AsChatClient()` extensions |
 | `ChatCompletionAgent` | `ChatClientAgent` | Remove `Kernel` parameter, add `IChatClient` parameter |
-| `OpenAIAssistantAgent` | `AIAgent` (via extension) | **New**: `OpenAIClient.GetAssistantClient().CreateAIAgent()` <br> **Existing**: `OpenAIClient.GetAssistantClient().GetAIAgent(assistantId)` |
+| `OpenAIAssistantAgent` | `AIAgent` (via extension) | ⚠️ **Deprecated** - Use Responses API instead. <br> **New**: `OpenAIClient.GetAssistantClient().CreateAIAgent()` <br> **Existing**: `OpenAIClient.GetAssistantClient().GetAIAgent(assistantId)` |
 | `AzureAIAgent` | `AIAgent` (via extension) | **New**: `PersistentAgentsClient.CreateAIAgent()` <br> **Existing**: `PersistentAgentsClient.GetAIAgent(agentId)` |
-| `OpenAIResponseAgent` | `AIAgent` (via extension) | Replace with `OpenAIClient.GetOpenAIResponseClient().CreateAIAgent()` |
+| `OpenAIResponseAgent` | `AIAgent` (via extension) | Replace with `OpenAIClient.GetOpenAIResponseClient(modelId).CreateAIAgent()` |
 | `A2AAgent` | `AIAgent` (via extension) | Replace with `A2ACardResolver.GetAIAgentAsync()` |
 | `BedrockAgent` | Not supported | Custom implementation required |
 
@@ -529,14 +529,14 @@ AIAgent agent = new OpenAIClient(apiKey)
     .CreateAIAgent(instructions: instructions);
 ```
 
-**OpenAI Assistants (New):**
+**OpenAI Assistants (New):** ⚠️ *Deprecated - Use Responses API instead*
 ```csharp
 AIAgent agent = new OpenAIClient(apiKey)
     .GetAssistantClient()
     .CreateAIAgent(modelId, instructions: instructions);
 ```
 
-**OpenAI Assistants (Existing):**
+**OpenAI Assistants (Existing):** ⚠️ *Deprecated - Use Responses API instead*
 ```csharp
 AIAgent agent = new OpenAIClient(apiKey)
     .GetAssistantClient()
@@ -562,6 +562,20 @@ AIAgent agent = await new PersistentAgentsClient(endpoint, credential)
     .GetAIAgentAsync(agentId);
 ```
 
+**OpenAI Responses:** *(Recommended for OpenAI)*
+```csharp
+AIAgent agent = new OpenAIClient(apiKey)
+    .GetOpenAIResponseClient(modelId)
+    .CreateAIAgent(instructions: instructions);
+```
+
+**Azure OpenAI Responses:** *(Recommended for Azure OpenAI)*
+```csharp
+AIAgent agent = new AzureOpenAIClient(endpoint, credential)
+    .GetOpenAIResponseClient(deploymentName)
+    .CreateAIAgent(instructions: instructions);
+```
+
 **A2A:**
 ```csharp
 A2ACardResolver resolver = new(new Uri(agentHost));
@@ -762,35 +776,57 @@ await foreach (var content in agent.InvokeAsync(userInput, thread))
 
 **With this Agent Framework CodeInterpreter pattern:**
 ```csharp
+using System.Text;
+using Microsoft.Agents.AI;
+using Microsoft.Extensions.AI;
+
 var result = await agent.RunAsync(userInput, thread);
 Console.WriteLine(result);
 
-// Extract chat response MEAI type via first level breaking glass
-var chatResponse = result.RawRepresentation as ChatResponse;
+// Get the CodeInterpreterToolCallContent (code input)
+CodeInterpreterToolCallContent? toolCallContent = result.Messages
+    .SelectMany(m => m.Contents)
+    .OfType<CodeInterpreterToolCallContent>()
+    .FirstOrDefault();
+
+if (toolCallContent?.Inputs is not null)
+{
+    DataContent? codeInput = toolCallContent.Inputs.OfType<DataContent>().FirstOrDefault();
+    if (codeInput?.HasTopLevelMediaType("text") ?? false)
+    {
+        Console.WriteLine($"Code Input: {Encoding.UTF8.GetString(codeInput.Data.ToArray())}");
+    }
+}
 
-// Extract underlying SDK updates via second level breaking glass
-var underlyingStreamingUpdates = chatResponse?.RawRepresentation as IEnumerable<object?> ?? [];
+// Get the CodeInterpreterToolResultContent (code output)
+CodeInterpreterToolResultContent? toolResultContent = result.Messages
+    .SelectMany(m => m.Contents)
+    .OfType<CodeInterpreterToolResultContent>()
+    .FirstOrDefault();
 
-StringBuilder generatedCode = new();
-foreach (object? underlyingUpdate in underlyingStreamingUpdates ?? [])
+if (toolResultContent?.Outputs is not null)
 {
-    if (underlyingUpdate is RunStepDetailsUpdate stepDetailsUpdate && stepDetailsUpdate.CodeInterpreterInput is not null)
+    TextContent? resultOutput = toolResultContent.Outputs.OfType<TextContent>().FirstOrDefault();
+    if (resultOutput is not null)
     {
-        generatedCode.Append(stepDetailsUpdate.CodeInterpreterInput);
+        Console.WriteLine($"Code Tool Result: {resultOutput.Text}");
     }
 }
 
-if (!string.IsNullOrEmpty(generatedCode.ToString()))
+// Getting any annotations generated by the tool
+foreach (AIAnnotation annotation in result.Messages
+    .SelectMany(m => m.Contents)
+    .SelectMany(c => c.Annotations ?? []))
 {
-    Console.WriteLine($"\n# {chatResponse?.Messages[0].Role}:Generated Code:\n{generatedCode}");
+    Console.WriteLine($"Annotation: {annotation}");
 }
 ```
 
 **Functional differences:**
-1. Code interpreter output is separate from text content, not a metadata property
-2. Access code via `RunStepDetailsUpdate.CodeInterpreterInput` instead of metadata
-3. Use breaking glass pattern to access underlying SDK objects
-4. Process text content and code interpreter output independently
+1. Code interpreter content is now available via MEAI abstractions - no breaking glass required
+2. Use `CodeInterpreterToolCallContent` to access code inputs (the generated code)
+3. Use `CodeInterpreterToolResultContent` to access code outputs (execution results)
+4. Annotations are accessible via `AIAnnotation` on content items
 </behavioral_changes>
 
 #### Provider-Specific Options Configuration
@@ -980,6 +1016,8 @@ AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), new AzureCliCredential(
 
 ### 3. OpenAI Assistants Migration
 
+> ⚠️ **DEPRECATION WARNING**: The OpenAI Assistants API has been deprecated. The Agent Framework extension methods for Assistants are marked as `[Obsolete]`. **Please use the Responses API instead** (see Section 6: OpenAI Responses Migration).
+
 <configuration_changes>
 **Remove Semantic Kernel Packages:**
 ```xml
@@ -1291,52 +1329,7 @@ var result = await agent.RunAsync(userInput, thread);
 ```
 </api_changes>
 
-### 8. A2A Migration
-
-<configuration_changes>
-**Remove Semantic Kernel Packages:**
-```xml
-<PackageReference Include="Microsoft.SemanticKernel.Agents.A2A" />
-```
-
-**Add Agent Framework Packages:**
-```xml
-<PackageReference Include="Microsoft.Agents.AI.A2A" />
-```
-</configuration_changes>
-
-<api_changes>
-**Replace this Semantic Kernel pattern:**
-```csharp
-using A2A;
-using Microsoft.SemanticKernel;
-using Microsoft.SemanticKernel.Agents;
-using Microsoft.SemanticKernel.Agents.A2A;
-
-using var httpClient = CreateHttpClient();
-var client = new A2AClient(agentUrl, httpClient);
-var cardResolver = new A2ACardResolver(url, httpClient);
-var agentCard = await cardResolver.GetAgentCardAsync();
-Console.WriteLine(JsonSerializer.Serialize(agentCard, s_jsonSerializerOptions));
-var agent = new A2AAgent(client, agentCard);
-```
-
-**With this Agent Framework pattern:**
-```csharp
-using System;
-using A2A;
-using Microsoft.Agents.AI;
-using Microsoft.Agents.AI.A2A;
-
-// Initialize an A2ACardResolver to get an A2A agent card.
-A2ACardResolver agentCardResolver = new(new Uri(a2aAgentHost));
-
-// Create an instance of the AIAgent for an existing A2A agent specified by the agent card.
-AIAgent agent = await agentCardResolver.GetAIAgentAsync();
-```
-</api_changes>
-
-### 9. Unsupported Providers (Require Custom Implementation)
+### 8. Unsupported Providers (Require Custom Implementation)
 
 <behavioral_changes>
 #### BedrockAgent Migration
@@ -1507,7 +1500,7 @@ Console.WriteLine(result);
 ```
 </behavioral_changes>
 
-### 10. Function Invocation Filtering
+### 9. Function Invocation Filtering
 
 **Invocation Context**
 
@@ -1615,25 +1608,4 @@ var filteredAgent = originalAgent
     .Build();
 ```
 
-### 11. Function Invocation Contexts
-
-**Invocation Context**
-
-Semantic Kernel's `IAutoFunctionInvocationFilter` provides a `AutoFunctionInvocationContext` where Agent Framework provides `FunctionInvocationContext` 
-
-The property mapping guide from a `AutoFunctionInvocationContext` to a `FunctionInvocationContext` is as follows:
 
-| Semantic Kernel | Agent Framework |
-| --- | --- |
-| RequestSequenceIndex | Iteration |
-| FunctionSequenceIndex | FunctionCallIndex |
-| ToolCallId | CallContent.CallId |
-| ChatMessageContent | Messages[0] |
-| ExecutionSettings | Options |
-| ChatHistory | Messages |
-| Function | Function |
-| Kernel | N/A |
-| Result | Use `return` from the delegate |
-| Terminate | Terminate |
-| CancellationToken | provided via argument to middleware delegate |
-| Arguments | Arguments |

.github/workflows/codeql-analysis.yml

@@ -32,7 +32,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
         with:
           persist-credentials: false