Merge pull request microsoft#370 from microsoft/dev

fix: Update azure-ai-agents dependency to >=1.2.0b1 to resolve compatibility issues with latest SDK features

Author: Prajwal-Microsoft

docs/DeploymentGuide.md

@@ -206,43 +206,9 @@ Once you've opened the project in [Codespaces](#github-codespaces), [Dev Contain
 
 5. Once the deployment has completed successfully, open the [Azure Portal](https://portal.azure.com/), go to the deployed resource group, find the App Service, and get the app URL from `Default domain`.
 
-6. If you are done trying out the application, you can delete the resources by running `azd down`.
+6. When Deployment is complete, follow steps in [Set Up Authentication in Azure App Service](../docs/azure_app_service_auth_setup.md) to add app authentication to your web app running on Azure App Service
 
-### Publishing Local Build Container to Azure Container Registry
-
-If you need to rebuild the source code and push the updated container to the deployed Azure Container Registry, follow these steps:
-
-1. Set the environment variable `USE_LOCAL_BUILD` to `True`:
-
-   - **Linux/macOS**:
-
-     ```bash
-     export USE_LOCAL_BUILD=True
-     ```
-
-   - **Windows (PowerShell)**:
-     ```powershell
-     $env:USE_LOCAL_BUILD = $true
-     ```
-
-2. Run the `az login` command
-
-   ```bash
-   az login
-   ```
-
-3. Run the `azd up` command again to rebuild and push the updated container:
-   ```bash
-   azd up
-   ```
-
-This will rebuild the source code, package it into a container, and push it to the Azure Container Registry associated with your deployment.
-
-This guide provides step-by-step instructions for deploying your application using Azure Container Registry (ACR) and Azure Container Apps.
-
-There are several ways to deploy the solution. You can deploy to run in Azure in one click, or manually, or you can deploy locally.
-
-When Deployment is complete, follow steps in [Set Up Authentication in Azure App Service](../docs/azure_app_service_auth_setup.md) to add app authentication to your web app running on Azure App Service
+7. If you are done trying out the application, you can delete the resources by running `azd down`.
 
 # Local setup
 

src/backend/app_kernel.py

@@ -74,7 +74,7 @@
 # Add this near the top of your app.py, after initializing the app
 app.add_middleware(
     CORSMiddleware,
-    allow_origins=[frontend_url],
+    allow_origins=[frontend_url],  # Allow all origins for development; restrict in production
     allow_credentials=True,
     allow_methods=["*"],
     allow_headers=["*"],
@@ -269,7 +269,7 @@ async def input_task_endpoint(input_task: InputTask, request: Request):
         if "Rate limit is exceeded" in error_msg:
             match = re.search(r"Rate limit is exceeded\. Try again in (\d+) seconds?\.", error_msg)
             if match:
-                error_msg = f"Rate limit is exceeded. Try again in {match.group(1)} seconds."
+                error_msg = "Application temporarily unavailable due to quota limits. Please try again later."
 
         track_event_if_configured(
             "InputTaskError",
@@ -279,7 +279,7 @@ async def input_task_endpoint(input_task: InputTask, request: Request):
                 "error": str(e),
             },
         )
-        raise HTTPException(status_code=400, detail=f"Error creating plan: {error_msg}") from e
+        raise HTTPException(status_code=400, detail=f"{error_msg}") from e
 
 
 @app.post("/api/human_feedback")

src/backend/pyproject.toml

@@ -8,6 +8,7 @@ dependencies = [
     "azure-ai-evaluation>=1.5.0",
     "azure-ai-inference>=1.0.0b9",
     "azure-ai-projects>=1.0.0b9",
+    "azure-ai-agents>=1.2.0b1",
     "azure-cosmos>=4.9.0",
     "azure-identity>=1.21.0",
     "azure-monitor-events-extension>=0.1.0",