Add Azure OpenAI Custom Model Integration (#1001)

Fixes #710 

This PR implements comprehensive Azure OpenAI integration for Dyad,
enabling users to leverage Azure
OpenAI models through proper environment variable configuration. The
implementation adds Azure as a
supported provider with full integration into the existing language
model architecture, including support
  for GPT-5 models. Key features include environment-based
configuration using `AZURE_API_KEY` and `AZURE_RESOURCE_NAME`,
specialized UI components that provide clear
setup instructions and status indicators, and seamless integration with
Dyad's existing provider system.
The Azure provider leverages the @ai-sdk/azure package (v1.3.25) for
compatibility with the current
  TypeScript language model interfaces.

The implementation includes robust error handling for missing
configuration, comprehensive test coverage
with 9 new unit tests covering critical functionality like model client
creation and error scenarios, and
  an E2E test for the Azure-specific settings UI. 

<img width="1510" height="908" alt="Screenshot 2025-08-18 at 9 14 32 PM"
src="https://github.com/user-attachments/assets/04aa99e1-1590-4bb0-86c9-a67b97bc7500"
/>

---------

Co-authored-by: graphite-app[bot] <96075541+graphite-app[bot]@users.noreply.github.com>
Co-authored-by: Will Chen <willchen90@gmail.com>

src/ipc/shared/language_model_helpers.ts

@@ -211,6 +211,40 @@ export const MODEL_OPTIONS: Record<string, ModelOption[]> = {
       temperature: 0,
     },
   ],
+  azure: [
+    {
+      name: "gpt-5",
+      displayName: "GPT-5",
+      description: "Azure OpenAI GPT-5 model with reasoning capabilities",
+      maxOutputTokens: 128_000,
+      contextWindow: 400_000,
+      temperature: 0,
+    },
+    {
+      name: "gpt-5-mini",
+      displayName: "GPT-5 Mini",
+      description: "Azure OpenAI GPT-5 Mini model",
+      maxOutputTokens: 128_000,
+      contextWindow: 400_000,
+      temperature: 0,
+    },
+    {
+      name: "gpt-5-nano",
+      displayName: "GPT-5 Nano",
+      description: "Azure OpenAI GPT-5 Nano model",
+      maxOutputTokens: 128_000,
+      contextWindow: 400_000,
+      temperature: 0,
+    },
+    {
+      name: "gpt-5-chat",
+      displayName: "GPT-5 Chat",
+      description: "Azure OpenAI GPT-5 Chat model",
+      maxOutputTokens: 16_384,
+      contextWindow: 128_000,
+      temperature: 0,
+    },
+  ],
 };
 
 export const PROVIDER_TO_ENV_VAR: Record<string, string> = {
@@ -218,6 +252,7 @@ export const PROVIDER_TO_ENV_VAR: Record<string, string> = {
   anthropic: "ANTHROPIC_API_KEY",
   google: "GEMINI_API_KEY",
   openrouter: "OPENROUTER_API_KEY",
+  azure: "AZURE_API_KEY",
 };
 
 export const CLOUD_PROVIDERS: Record<
@@ -258,6 +293,12 @@ export const CLOUD_PROVIDERS: Record<
     websiteUrl: "https://academy.dyad.sh/settings",
     gatewayPrefix: "dyad/",
   },
+  azure: {
+    displayName: "Azure OpenAI",
+    hasFreeTier: false,
+    websiteUrl: "https://portal.azure.com/",
+    gatewayPrefix: "",
+  },
 };
 
 const LOCAL_PROVIDERS: Record<

src/ipc/utils/get_model_client.ts

@@ -1,6 +1,7 @@
 import { createOpenAI } from "@ai-sdk/openai";
 import { createGoogleGenerativeAI as createGoogle } from "@ai-sdk/google";
 import { createAnthropic } from "@ai-sdk/anthropic";
+import { azure } from "@ai-sdk/azure";
 import { createOpenRouter } from "@openrouter/ai-sdk-provider";
 import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
 import type { LargeLanguageModel, UserSettings } from "../../lib/schemas";
@@ -224,6 +225,54 @@ function getRegularModelClient(
         backupModelClients: [],
       };
     }
+    case "azure": {
+      // Check if we're in e2e testing mode
+      const testAzureBaseUrl = getEnvVar("TEST_AZURE_BASE_URL");
+
+      if (testAzureBaseUrl) {
+        // Use fake server for e2e testing
+        logger.info(`Using test Azure base URL: ${testAzureBaseUrl}`);
+        const provider = createOpenAICompatible({
+          name: "azure-test",
+          baseURL: testAzureBaseUrl,
+          apiKey: "fake-api-key-for-testing",
+        });
+        return {
+          modelClient: {
+            model: provider(model.name),
+            builtinProviderId: providerId,
+          },
+          backupModelClients: [],
+        };
+      }
+
+      // Azure OpenAI requires both API key and resource name as env vars
+      // We use environment variables for Azure configuration
+      const resourceName = getEnvVar("AZURE_RESOURCE_NAME");
+      const azureApiKey = getEnvVar("AZURE_API_KEY");
+
+      if (!resourceName) {
+        throw new Error(
+          "Azure OpenAI resource name is required. Please set the AZURE_RESOURCE_NAME environment variable.",
+        );
+      }
+
+      if (!azureApiKey) {
+        throw new Error(
+          "Azure OpenAI API key is required. Please set the AZURE_API_KEY environment variable.",
+        );
+      }
+
+      // Use the default Azure provider with environment variables
+      // The azure provider automatically picks up AZURE_RESOURCE_NAME and AZURE_API_KEY
+      return {
+        modelClient: {
+          model: azure(model.name),
+          builtinProviderId: providerId,
+        },
+        backupModelClients: [],
+      };
+    }
     case "ollama": {
       const provider = createOllamaProvider({ baseURL: getOllamaApiUrl() });
       return {