fix: Bugfixes and Content Corrections

README.md

@@ -180,7 +180,7 @@ This template uses Azure Key Vault to store all connections to communicate betwe
 
 This template also uses [Managed Identity](https://learn.microsoft.com/entra/identity/managed-identities-azure-resources/overview) for local development and deployment.
 
-To ensure continued best practices in your own repository, we recommend that anyone creating solutions based on our templates ensure that the [Github secret scanning](https://docs.github.com/code-security/secret-scanning/about-secret-scanning) setting is enabled.
+To ensure continued best practices in your own repository, we recommend that anyone creating solutions based on our templates ensure that the [GitHub secret scanning](https://docs.github.com/code-security/secret-scanning/about-secret-scanning) setting is enabled.
 
 You may want to consider additional security measures, such as:
 

TRANSPARENCY_FAQS.md

@@ -26,4 +26,4 @@ The system allows users to review, reorder and approve steps generated in a plan
 
 ## What operational factors and settings allow for effective and responsible use of Multi Agent: Custom Automation Engine – Solution Accelerator? 
 Effective and responsible use of the Multi Agent: Custom Automation Engine – Solution Accelerator depends on several operational factors and settings. The system is designed to perform reliably and safely across a range of business tasks that it was evaluated for. Users can customize certain settings, such as the planning language model used by the system, the types of tasks that agents are assigned, and the specific actions that agents can take (e.g., sending emails or scheduling orientation sessions for new employees). However, it's important to note that these choices may impact the system's behavior in real-world scenarios.
-For example, selecting a planning language model that is not well-suited to the complexity of the tasks may result in lower accuracy and performance. Similarly, assigning tasks that are outside the system's intended scope may lead to errors or incomplete results. Users can choose the LLM that is optimized for responsible use. The default LLM is GPT-4o which inherits the existing RAI mechanisms and filters from the LLM provider. Caching is enabled by default to increase reliability and control cost. We encourage developers to review [OpenAI’s Usage policies](https://openai.com/policies/usage-policies/) and [Azure OpenAI’s Code of Conduct](https://learn.microsoft.com/en-us/legal/cognitive-services/openai/code-of-conduct) when using GPT-40. To ensure effective and responsible use of the accelerator, users should carefully consider their choices and use the system within its intended scope.
+For example, selecting a planning language model that is not well-suited to the complexity of the tasks may result in lower accuracy and performance. Similarly, assigning tasks that are outside the system's intended scope may lead to errors or incomplete results. Users can choose the LLM that is optimized for responsible use. The default LLM is GPT-4.1 which inherits the existing RAI mechanisms and filters from the LLM provider. Caching is enabled by default to increase reliability and control cost. We encourage developers to review [OpenAI’s Usage policies](https://openai.com/policies/usage-policies/) and [Azure OpenAI’s Code of Conduct](https://learn.microsoft.com/en-us/legal/cognitive-services/openai/code-of-conduct) when using GPT-4.1. To ensure effective and responsible use of the accelerator, users should carefully consider their choices and use the system within its intended scope.

docs/AVMPostDeploymentGuide.md

@@ -26,7 +26,7 @@ Before starting the post-deployment process, ensure you have the following:
 
 2. **[Azure CLI](https://learn.microsoft.com/en-us/cli/azure/install-azure-cli)** <small>(v2.50+)</small> - Command-line tool for managing Azure resources
 
-3. **[Python](https://www.python.org/downloads/)** <small>(v4.9+ recommended)</small> - Required for data processing scripts
+3. **[Python](https://www.python.org/downloads/)** <small>(v3.9+ recommended)</small> - Required for data processing scripts
 
 4. **[Git](https://git-scm.com/downloads/)** - Version control system for cloning the repository
 5. **[Bicep CLI](https://learn.microsoft.com/azure/azure-resource-manager/bicep/install)** <small>(v0.33.0+)</small> - Required for compiling infrastructure templates

docs/AzureGPTQuotaSettings.md

@@ -5,6 +5,6 @@
 3. **Go to** the `Management Center` from the bottom-left navigation menu.  
 4. Select `Quota`  
    - Click on the `GlobalStandard` dropdown.  
-   - Select the required **GPT model** (`GPT-4o`)
+   - Select the required **GPT model** (`GPT-4.1`)
    - Choose the **region** where the deployment is hosted.  
 5. Request More Quota or delete any unused model deployments as needed.  

docs/SampleQuestions.md

@@ -6,12 +6,13 @@ To help you get started, here are some **Sample Prompts** you can ask in the app
 ## **Teams** 
 Select the Team option from the top-left section, then click Continue after choosing the desired team.
 
-> _Note: Five teams are available only if all teams are selected during post-deployment; otherwise, only selected teams are visible._
+> _Note: Six teams are available only if all teams are selected during post-deployment; otherwise, only selected teams are visible._
 - Retail
 - HR
 - Marketing
 - RFP
 - Contract Compliance
+- Retail Marketing Content Generation
 
 ![Application](images/samplequestion_1.png)
 
@@ -68,7 +69,6 @@ _Sample operation:_
   department: hr, role: manager, start date: 11/23/2025, orientation date: 11/25/2025, location: onsite, email: js@contoso.com, mentor: Jim Shorts, benefits package:   standard, ID Card: yes, salary: 70000, Laptop : Dell 14 Plus
   ```
   > _Observe: It will trigger "Generating Plan Action" and "Proposed Plan" with 4 or more Steps_
-</br>
 
 - Task: Click on **"Approve Task Plan"** Button.
   > _Note: Average response time is around 01 minute 15 seconds._ <br>
@@ -89,7 +89,6 @@ _Sample operation:_
 
   > _Note: Average response time is 10–15 minutes._ <br>
   > _Observe: It will trigger the "Generating Plan Action" and give the Proposed Plan with 5 or more Steps_
-</br>
 
 - Task: Click on **"Approve Task Plan"** Button.
   > _Note: Average response time is around 01 minute._ <br>
@@ -110,12 +109,31 @@ _Sample operation:_
 
   > _Note: Average response time is 10–15 minutes._ <br>
   > _Observe: It will trigger the "Generating Plan Action" and give the Proposed Plan with 4 or more Steps_
-</br>
 
 - Task: Click on **"Approve Task Plan"** Button.
   > _Note: Average response time is around 01 minute._ <br>
   > _Observe: It goes into "Thinking Process", "Processing your plan" and "coordinating with AI Agents"._ <br>
   > _Review the output._
 
+### **Retail Marketing Content Generation Scenario**
+If you select the Retail Marketing Content Generation team, follow the prompts below.
+
+>**Agents Used:** Triage, Planning, Research, Text Content, Image Content, Compliance
+
+The Retail Marketing Content Generation Scenario allows users to generate end-to-end marketing assets (copy + image) for retail campaigns, grounded in the Contoso Paint product catalog. Key tasks include:
+
+_Sample operation:_
+
+- Task: Switch to the **"Retail Marketing Content Generation Team"** from the top left section and click **"Continue"** button.
+- Task: From the Quick Tasks, select **"Generate a social media post"** and submit it.
+
+  > _Note: Average response time is 30–60 seconds for plan generation._ <br>
+  > _Observe: It will trigger the "Generating Plan Action" and give the Proposed Plan with 5 or more Steps (Planning → Research → Text Content → Image Content → Compliance)._
+
+- Task: Click on **"Approve Task Plan"** Button.
+  > _Note: Average response time is around 02–03 minutes (image generation included)._ <br>
+  > _Observe: It goes into "Thinking Process", "Processing your plan" and "coordinating with AI Agents". The final output includes marketing copy (headline, body, CTA, hashtags), a rendered campaign image, and a compliance review._ <br>
+  > _Review the output._
+
 
 This structured approach ensures that users receive automated, AI-coordinated task execution and intelligent responses from specialized agents.

docs/TroubleShootingSteps.md

@@ -166,4 +166,4 @@ Use these as quick reference guides to unblock your deployments.
 ---------------------------------
 
 💡 Note: If you encounter any other issues, you can refer to the [Common Deployment Errors](https://learn.microsoft.com/en-us/azure/azure-resource-manager/troubleshooting/common-deployment-errors) documentation.
-If the problem persists, you can also raise an bug in our [MACAE Github Issues](https://github.com/microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator/issues) for further support.
+If the problem persists, you can also raise a bug in our [MACAE GitHub Issues](https://github.com/microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator/issues) for further support.

docs/mcp_server.md

@@ -1,20 +1,20 @@
 Capturing the notes from auth install before deleting for docs...
 
 ### Auth section:
-Requires and app registration as in azure_app_service_auth_setup.md so not deployed by default.
+Requires an app registration as in azure_app_service_auth_setup.md so not deployed by default.
 
 To setup basic auth with FastMCP - bearer token - you can integrate with Azure by using it as your token provider.
 
 ``` from fastmcp.server.auth import JWTVerifier```
 
 ```
 auth = JWTVerifier(
-    jwks_uri="https://login.microsoftonline.com/52b39610-0746-4c25-a83d-d4f89fadedfe/discovery/v2.0/keys",
-    #issuer="https://login.microsoftonline.com/52b39610-0746-4c25-a83d-d4f89fadedfe/v2.0",
+    jwks_uri="https://login.microsoftonline.com/<your-tenant-id>/discovery/v2.0/keys",
+    #issuer="https://login.microsoftonline.com/<your-tenant-id>/v2.0",
     # This issuer is not correct in the docs. Found by decoding the token.
-    issuer="https://sts.windows.net/52b39610-0746-4c25-a83d-d4f89fadedfe/",
+    issuer="https://sts.windows.net/<your-tenant-id>/",
     algorithm="RS256",
-    audience="api://7a95e70b-062e-4cd3-a88c-603fc70e1c73"
+    audience="api://<your-app-client-id>"
 )
 ```
 

docs/quota_check.md

@@ -1,7 +1,7 @@
 ## Check Quota Availability Before Deployment
 
 Before deploying the accelerator, **ensure sufficient quota availability** for the required model.
-> **For Global Standard | GPT-4o - the capacity to at least 150k tokens for optimal performance.**
+> **For Global Standard | GPT-4.1 — ensure a capacity of at least 150k tokens for optimal performance.**
 
 ### Login if you have not done so already
 ```

src/App/src/commonComponents/modules/ChatExample.tsx

@@ -45,7 +45,7 @@ const ChatExample: React.FC = () => {
             <div className="bot-tag">BOT</div>
           </div>
           <div className="message-content">
-            You got it! I've initiated a background check and everything looks good to go— You're ready to move onto helping Jessica set up and Office 365 account. Want me to hand that over to your Manager Agent?
+            You got it! I've initiated a background check and everything looks good to go — you're ready to move on to helping Jessica set up an Office 365 account. Want me to hand that over to your Manager Agent?
           </div>
           <div className="message-actions">
             <button className="action-button">👍</button>

src/App/src/components/common/TeamSelector.tsx

@@ -721,7 +721,7 @@ const TeamSelector: React.FC<TeamSelectorProps> = ({
                 Are you sure you want to delete "{teamToDelete?.name}"?
               </DialogTitle>
               <Text className={styles.deleteConfirmText}>
-                This team configurations and its agents are shared across all users in the system. Deleting this team will permanently remove it for everyone, and this action cannot be undone.
+                This team configuration and its agents are shared across all users in the system. Deleting this team will permanently remove it for everyone, and this action cannot be undone.
               </Text>
             </DialogBody>
             <div className={styles.deleteDialogActions}>

src/App/vitest.config.ts

@@ -8,7 +8,7 @@ export default defineConfig({
     test: {
         globals: true,
         environment: 'jsdom',
-        setupFiles: ['./src/setupTests.ts'],
+        setupFiles: ['./src/setupTests.tsx'],
         css: true,
     },
     resolve: {

src/backend/auth/auth_utils.py

@@ -40,7 +40,7 @@ def get_tenantid(client_principal_b64):
             # Decode the base64 header to get the JSON string
             decoded_bytes = base64.b64decode(client_principal_b64)
             decoded_string = decoded_bytes.decode("utf-8")
-            # Convert the JSON string1into a Python dictionary
+            # Convert the JSON string into a Python dictionary
             user_info = json.loads(decoded_string)
             # Extract the tenant ID
             tenant_id = user_info.get("tid")  # 'tid' typically holds the tenant ID

src/backend/common/utils/otlp_tracing.py

@@ -7,7 +7,7 @@
 
 def configure_oltp_tracing(endpoint: str = None) -> trace.TracerProvider:
     # Configure Tracing
-    tracer_provider = TracerProvider(resource=Resource({"service.name": "macwe"}))
+    tracer_provider = TracerProvider(resource=Resource({"service.name": "macae"}))
     processor = BatchSpanProcessor(OTLPSpanExporter())
     tracer_provider.add_span_processor(processor)
     trace.set_tracer_provider(tracer_provider)

src/tests/backend/common/utils/test_otlp_tracing.py

@@ -79,7 +79,7 @@ def test_configure_oltp_tracing_default_parameters(
         result = configure_oltp_tracing()
 
         # Verify Resource creation
-        mock_resource.assert_called_once_with({"service.name": "macwe"})
+        mock_resource.assert_called_once_with({"service.name": "macae"})
 
         # Verify TracerProvider creation
         mock_tracer_provider_class.assert_called_once_with(resource=mock_resource_instance)
@@ -126,7 +126,7 @@ def test_configure_oltp_tracing_with_endpoint_parameter(
         result = configure_oltp_tracing(endpoint=endpoint)
 
         # Verify the same behavior as default case (endpoint parameter is currently unused)
-        mock_resource.assert_called_once_with({"service.name": "macwe"})
+        mock_resource.assert_called_once_with({"service.name": "macae"})
         mock_tracer_provider_class.assert_called_once_with(resource=mock_resource_instance)
         mock_exporter.assert_called_once_with()
         mock_processor.assert_called_once_with(mock_exporter_instance)
@@ -162,7 +162,7 @@ def test_configure_oltp_tracing_with_none_endpoint(
         result = configure_oltp_tracing(endpoint=None)
 
         # Verify the same behavior as default case
-        mock_resource.assert_called_once_with({"service.name": "macwe"})
+        mock_resource.assert_called_once_with({"service.name": "macae"})
         mock_tracer_provider_class.assert_called_once_with(resource=mock_resource_instance)
         mock_exporter.assert_called_once_with()
         mock_processor.assert_called_once_with(mock_exporter_instance)
@@ -269,7 +269,7 @@ def test_configure_oltp_tracing_tracer_provider_creation_error(
             configure_oltp_tracing()
 
         # Verify Resource was created but subsequent operations were not called
-        mock_resource.assert_called_once_with({"service.name": "macwe"})
+        mock_resource.assert_called_once_with({"service.name": "macae"})
         mock_exporter.assert_not_called()
         mock_processor.assert_not_called()
         mock_trace.set_tracer_provider.assert_not_called()
@@ -297,7 +297,7 @@ def test_configure_oltp_tracing_exporter_creation_error(
             configure_oltp_tracing()
 
         # Verify creation up to exporter was called
-        mock_resource.assert_called_once_with({"service.name": "macwe"})
+        mock_resource.assert_called_once_with({"service.name": "macae"})
         mock_tracer_provider_class.assert_called_once_with(resource=mock_resource_instance)
         mock_exporter.assert_called_once_with()
 
@@ -332,7 +332,7 @@ def test_configure_oltp_tracing_processor_creation_error(
             configure_oltp_tracing()
 
         # Verify creation up to processor was called
-        mock_resource.assert_called_once_with({"service.name": "macwe"})
+        mock_resource.assert_called_once_with({"service.name": "macae"})
         mock_tracer_provider_class.assert_called_once_with(resource=mock_resource_instance)
         mock_exporter.assert_called_once_with()
         mock_processor.assert_called_once_with(mock_exporter_instance)
@@ -369,7 +369,7 @@ def test_configure_oltp_tracing_add_span_processor_error(
             configure_oltp_tracing()
 
         # Verify all creation steps were called
-        mock_resource.assert_called_once_with({"service.name": "macwe"})
+        mock_resource.assert_called_once_with({"service.name": "macae"})
         mock_tracer_provider_class.assert_called_once_with(resource=mock_resource_instance)
         mock_exporter.assert_called_once_with()
         mock_processor.assert_called_once_with(mock_exporter_instance)
@@ -407,7 +407,7 @@ def test_configure_oltp_tracing_set_tracer_provider_error(
             configure_oltp_tracing()
 
         # Verify all steps up to set_tracer_provider were called
-        mock_resource.assert_called_once_with({"service.name": "macwe"})
+        mock_resource.assert_called_once_with({"service.name": "macae"})
         mock_tracer_provider_class.assert_called_once_with(resource=mock_resource_instance)
         mock_exporter.assert_called_once_with()
         mock_processor.assert_called_once_with(mock_exporter_instance)
@@ -452,7 +452,7 @@ def test_configure_oltp_tracing_service_name_configuration(
         result = configure_oltp_tracing()
 
         # Verify service name is set correctly
-        mock_resource.assert_called_once_with({"service.name": "macwe"})
+        mock_resource.assert_called_once_with({"service.name": "macae"})
 
         # Verify the resource is used in TracerProvider
         mock_tracer_provider_class.assert_called_once_with(resource=mock_resource_instance)
@@ -487,7 +487,7 @@ def test_configure_oltp_tracing_call_sequence(
 
         # Verify call sequence using call order
         expected_calls = [
-            call({"service.name": "macwe"}),  # Resource creation
+            call({"service.name": "macae"}),  # Resource creation
         ]
         mock_resource.assert_has_calls(expected_calls)
 
@@ -542,7 +542,7 @@ def test_configure_oltp_tracing_with_empty_string_endpoint(
         result = configure_oltp_tracing(endpoint="")
 
         # Verify same behavior as default (endpoint parameter is unused in current implementation)
-        mock_resource.assert_called_once_with({"service.name": "macwe"})
+        mock_resource.assert_called_once_with({"service.name": "macae"})
         mock_tracer_provider_class.assert_called_once_with(resource=mock_resource_instance)
         mock_exporter.assert_called_once_with()
         mock_processor.assert_called_once_with(mock_exporter_instance)