Update Azure AI Foundry and GitHub Models documentation to use strongly-typed model constants (#5302)

* Initial plan

* Update documentation to use AIFoundryModel and GitHubModel constants

Co-authored-by: IEvangelist <[email protected]>

* Update compatibility matrix to use GitHubModel constant

Co-authored-by: IEvangelist <[email protected]>

* Apply suggestions from code review

---------

Co-authored-by: copilot-swe-agent[bot] <[email protected]>
Co-authored-by: IEvangelist <[email protected]>
Co-authored-by: David Pine <[email protected]>

Author: Copilot

docs/azureai/ai-integrations-compatibility-matrix.md

@@ -117,7 +117,8 @@ The [Aspire.Hosting.GitHub.Models](https://www.nuget.org/packages/Aspire.Hosting
 ```csharp
 var builder = DistributedApplication.CreateBuilder(args);
 
-var chat = builder.AddGitHubModel("chat", "openai/gpt-4o-mini");
+var model = GitHubModel.OpenAI.OpenAIGpt4oMini;
+var chat = builder.AddGitHubModel("chat", model);
 
 builder.AddProject<Projects.ExampleProject>()
        .WithReference(chat);

docs/azureai/azureai-foundry-integration.md

@@ -62,7 +62,8 @@ var builder = DistributedApplication.CreateBuilder(args);
 
 var foundry = builder.AddAzureAIFoundry("foundry");
 
-var chat = foundry.AddDeployment("chat", "Phi-4", "1", "Microsoft");
+var model = AIFoundryModel.Microsoft.Phi4;
+var chat = foundry.AddDeployment("chat", model);
 
 builder.AddProject<Projects.ExampleProject>()
        .WithReference(chat)
@@ -74,17 +75,18 @@ builder.AddProject<Projects.ExampleProject>()
 The preceding code:
 
 - Adds an Azure AI Foundry resource named `foundry`.
-- Adds an Azure AI Foundry deployment resource named `chat` with a model name of `Phi-4`. The model name must correspond to an [available model](/azure/ai-foundry/foundry-models/concepts/models) in the Azure AI Foundry service.
+- Adds an Azure AI Foundry deployment resource named `chat` using the <xref:Aspire.Hosting.Azure.AIFoundryModel> constant for Phi-4. The model must correspond to an [available model](/azure/ai-foundry/foundry-models/concepts/models) in the Azure AI Foundry service.
 
-> [!NOTE]
-> The `format` parameter of the `AddDeployment(...)` method can be found in the Azure AI Foundry portal in the details page of the model, right after the `Quick facts` text.
+> [!TIP]
+> Use the strongly-typed <xref:Aspire.Hosting.Azure.AIFoundryModel> constants to avoid typos and ensure you're using valid model identifiers. These constants are grouped by publisher (for example, `AIFoundryModel.Microsoft.Phi4`, `AIFoundryModel.OpenAI.Gpt4o`).
 
 ### Configure deployment properties
 
 You can customize deployment properties using the <xref:Aspire.Hosting.AzureAIFoundryExtensions.WithProperties*> method:
 
 ```csharp
-var chat = foundry.AddDeployment("chat", "Phi-4", "1", "Microsoft")
+var model = AIFoundryModel.Microsoft.Phi4;
+var chat = foundry.AddDeployment("chat", model)
                   .WithProperties(deployment =>
                   {
                       deployment.SkuName = "Standard";
@@ -130,7 +132,8 @@ var builder = DistributedApplication.CreateBuilder(args);
 var foundry = builder.AddAzureAIFoundry("foundry")
                      .RunAsFoundryLocal();
 
-var chat = foundry.AddDeployment("chat", "phi-3.5-mini", "1", "Microsoft");
+var model = AIFoundryModel.Local.Phi35Mini;
+var chat = foundry.AddDeployment("chat", model);
 
 builder.AddProject<Projects.ExampleProject>()
        .WithReference(chat)
@@ -143,6 +146,9 @@ When the AppHost starts up, the local foundry service is also started. This requ
 
 The <xref:Aspire.Hosting.AzureAIFoundryExtensions.RunAsFoundryLocal*> method configures the resource to run as an emulator. It downloads and loads the specified models locally. The method provides health checks for the local service and automatically manages the Foundry Local lifecycle.
 
+> [!TIP]
+> Use the strongly-typed `AIFoundryModel.Local` constants for local development models. These constants are specifically optimized for Foundry Local (for example, `AIFoundryModel.Local.Phi4Mini`, `AIFoundryModel.Local.DeepseekR17b`).
+
 ### Assign roles to resources
 
 You can assign specific roles to resources that need to access the Azure AI Foundry service. Use the <xref:Aspire.Hosting.AzureAIFoundryExtensions.WithRoleAssignments*> method:

docs/github/github-models-integration.md

@@ -39,15 +39,19 @@ To add a `GitHubModelResource` to your AppHost project, call the `AddGitHubModel
 ```csharp
 var builder = DistributedApplication.CreateBuilder(args);
 
-var chat = builder.AddGitHubModel("chat", "openai/gpt-4o-mini");
+var model = GitHubModel.OpenAI.OpenAIGpt4oMini;
+var chat = builder.AddGitHubModel("chat", model);
 
 builder.AddProject<Projects.ExampleProject>()
        .WithReference(chat);
 
 // After adding all resources, run the app...
 ```
 
-The preceding code adds a GitHub Model resource named `chat` using the `openai/gpt-4o-mini` model. The <xref:Aspire.Hosting.ResourceBuilderExtensions.WithReference*> method passes the connection information to the `ExampleProject` project.
+The preceding code adds a GitHub Model resource named `chat` using the <xref:Aspire.Hosting.GitHub.GitHubModel> constant for OpenAI's GPT-4o-mini model. The <xref:Aspire.Hosting.ResourceBuilderExtensions.WithReference*> method passes the connection information to the `ExampleProject` project.
+
+> [!TIP]
+> Use the strongly-typed <xref:Aspire.Hosting.GitHub.GitHubModel> constants to avoid typos and ensure you're using valid model identifiers. These constants are grouped by publisher (for example, `GitHubModel.OpenAI.OpenAIGpt4oMini`, `GitHubModel.Microsoft.Phi4MiniInstruct`, `GitHubModel.DeepSeek.DeepSeekV30324`).
 
 ### Specify an organization
 
@@ -57,7 +61,8 @@ For organization-specific requests, you can specify an organization parameter:
 var builder = DistributedApplication.CreateBuilder(args);
 
 var organization = builder.AddParameter("github-org");
-var chat = builder.AddGitHubModel("chat", "openai/gpt-4o-mini", organization);
+var model = GitHubModel.OpenAI.OpenAIGpt4oMini;
+var chat = builder.AddGitHubModel("chat", model, organization);
 
 builder.AddProject<Projects.ExampleProject>()
        .WithReference(chat);
@@ -76,7 +81,8 @@ The GitHub Models integration supports multiple ways to configure authentication
 By default, the integration creates a parameter named `{resource_name}-gh-apikey` that automatically falls back to the `GITHUB_TOKEN` environment variable:
 
 ```csharp
-var chat = builder.AddGitHubModel("chat", "openai/gpt-4o-mini");
+var model = GitHubModel.OpenAI.OpenAIGpt4oMini;
+var chat = builder.AddGitHubModel("chat", model);
 ```
 
 Then in user secrets:
@@ -95,7 +101,8 @@ You can also specify a custom parameter for the API key:
 
 ```csharp
 var apiKey = builder.AddParameter("my-api-key", secret: true);
-var chat = builder.AddGitHubModel("chat", "openai/gpt-4o-mini")
+var model = GitHubModel.OpenAI.OpenAIGpt4oMini;
+var chat = builder.AddGitHubModel("chat", model)
                   .WithApiKey(apiKey);
 ```
 
@@ -114,7 +121,8 @@ Then in user secrets:
 You can add health checks to verify the GitHub Models endpoint accessibility and API key validity:
 
 ```csharp
-var chat = builder.AddGitHubModel("chat", "openai/gpt-4o-mini")
+var model = GitHubModel.OpenAI.OpenAIGpt4oMini;
+var chat = builder.AddGitHubModel("chat", model)
                   .WithHealthCheck();
 ```
 
@@ -123,14 +131,14 @@ var chat = builder.AddGitHubModel("chat", "openai/gpt-4o-mini")
 
 ### Available models
 
-GitHub Models supports various AI models. Some popular options include:
+GitHub Models supports various AI models. Use the strongly-typed <xref:Aspire.Hosting.GitHub.GitHubModel> constants for the most up-to-date list of available models. Some popular options include:
 
-- `openai/gpt-4o-mini`
-- `openai/gpt-4o`
-- `deepseek/DeepSeek-V3-0324`
-- `microsoft/Phi-4-mini-instruct`
+- `GitHubModel.OpenAI.OpenAIGpt4oMini`
+- `GitHubModel.OpenAI.OpenAIGpt41Mini`
+- `GitHubModel.DeepSeek.DeepSeekV30324`
+- `GitHubModel.Microsoft.Phi4MiniInstruct`
 
-Check the [GitHub Models documentation](https://docs.github.com/github-models) for the most up-to-date list of available models.
+Check the [GitHub Models documentation](https://docs.github.com/github-models) for more information about these models and their capabilities.
 
 ## Client integration
 
@@ -171,7 +179,6 @@ public class ExampleService(ChatCompletionsClient client)
     public async Task<string> GetResponseAsync(string prompt)
     {
         var response = await client.GetChatCompletionsAsync(
-            "openai/gpt-4o-mini",
             new[]
             {
                 new ChatMessage(ChatRole.User, prompt)
@@ -237,7 +244,7 @@ public class ChatService(OpenAIClient client)
 {
     public async Task<string> GetChatResponseAsync(string prompt)
     {
-        var chatClient = client.GetChatClient("openai/gpt-4o-mini");
+        var chatClient = client.GetChatClient(GitHubModel.OpenAI.OpenAIGpt4oMini);
 
         var response = await chatClient.CompleteChatAsync(
             new[]
@@ -271,7 +278,8 @@ When running an app in GitHub Codespaces or GitHub Actions, the `GITHUB_TOKEN` e
 
 ```csharp
 // No additional configuration needed in Codespaces/GitHub Actions
-var chat = builder.AddGitHubModel("chat", "openai/gpt-4o-mini");
+var model = GitHubModel.OpenAI.OpenAIGpt4oMini;
+var chat = builder.AddGitHubModel("chat", model);
 ```
 
 ##### Personal access tokens for local development

docs/snippets/azure/AppHost/AppHost.cs

@@ -6,7 +6,7 @@
 var foundryDeployment = foundry.AddDeployment(
     name: "chat",
     modelName: "Phi-4",
-    modelVersion: "1",
+    modelVersion: "7",
     format: "Microsoft");
 
 builder.AddAzureAppConfiguration("config");