Merge branch 'main' into customize-solution-update

Author: Fr4nc3

.github/workflows/docker-build-and-push.yml

@@ -32,21 +32,13 @@ jobs:
         uses: docker/setup-buildx-action@v1
 
       - name: Log in to Azure Container Registry
-        if: ${{ github.ref_name == 'main' }}
+        if: ${{ github.event_name == 'push' && (github.ref_name == 'main' || github.ref_name == 'dev' || github.ref_name == 'demo' || github.ref_name == 'hotfix') }}
         uses: azure/docker-login@v2
         with:
           login-server: ${{ secrets.ACR_LOGIN_SERVER }}
           username: ${{ secrets.ACR_USERNAME }}
           password: ${{ secrets.ACR_PASSWORD }}
 
-      - name: Log in to Azure Container Registry (Dev/Demo)
-        if: ${{ github.ref_name == 'dev' || github.ref_name == 'demo' || github.ref_name == 'hotfix' }}
-        uses: azure/docker-login@v2
-        with:
-          login-server: ${{ secrets.ACR_DEV_LOGIN_SERVER }}
-          username: ${{ secrets.ACR_DEV_USERNAME }}
-          password: ${{ secrets.ACR_DEV_PASSWORD }}
-
       - name: Set Docker image tag
         run: |
           if [[ "${{ github.ref }}" == "refs/heads/main" ]]; then
@@ -57,27 +49,27 @@ jobs:
             echo "TAG=demo" >> $GITHUB_ENV
           elif [[ "${{ github.ref }}" == "refs/heads/hotfix" ]]; then
             echo "TAG=hotfix" >> $GITHUB_ENV
+          else
+            echo "TAG=pullrequest-ignore" >> $GITHUB_ENV
           fi
-      - name: Build and push Docker images
-        if: ${{ github.ref_name == 'main' }}
-        run: |
-          cd src/backend
-          docker build -t ${{ secrets.ACR_LOGIN_SERVER }}/macae-backend:${{ env.TAG }} -f Dockerfile . && \
-          docker push ${{ secrets.ACR_LOGIN_SERVER }}/macae-backend:${{ env.TAG }} && \
-          echo "Backend image built and pushed successfully."
-          cd ../frontend
-          docker build -t ${{ secrets.ACR_LOGIN_SERVER }}/mac-webapp:${{ env.TAG }} -f Dockerfile . && \
-          docker push ${{ secrets.ACR_LOGIN_SERVER }}/mac-webapp:${{ env.TAG }} && \
-          echo "Frontend image built and pushed successfully."
-      - name: Build and push Docker images (Dev/Demo/hotfix)
-        if: ${{ github.ref_name == 'dev' || github.ref_name == 'demo' || github.ref_name == 'hotfix' }}
+          
+      - name: Build and push Docker images optionally
         run: |
           cd src/backend
-          docker build -t ${{ secrets.ACR_DEV_LOGIN_SERVER }}/macae-backend:${{ env.TAG }} -f Dockerfile . && \
-          docker push ${{ secrets.ACR_DEV_LOGIN_SERVER }}/macae-backend:${{ env.TAG }} && \
-          echo "Dev/Demo/Hotfix Backend image built and pushed successfully."
+          docker build -t ${{ secrets.ACR_LOGIN_SERVER }}/macaebackend:${{ env.TAG }} -f Dockerfile . && \
+          if [[ "${{ env.TAG }}" == "latest" || "${{ env.TAG }}" == "dev" || "${{ env.TAG }}" == "demo" || "${{ env.TAG }}" == "hotfix"  ]]; then
+            docker push ${{ secrets.ACR_LOGIN_SERVER }}/macaebackend:${{ env.TAG }} && \
+            echo "Backend image built and pushed successfully."
+          else
+            echo "Skipping Docker push for backend with tag: ${{ env.TAG }}"
+          fi
           cd ../frontend
-          docker build -t ${{ secrets.ACR_DEV_LOGIN_SERVER }}/mac-webapp:${{ env.TAG }} -f Dockerfile . && \
-          docker push ${{ secrets.ACR_DEV_LOGIN_SERVER }}/mac-webapp:${{ env.TAG }} && \
-          echo "Dev/Demo/Hotfix Frontend image built and pushed successfully."
+          docker build -t ${{ secrets.ACR_LOGIN_SERVER }}/macaefrontend:${{ env.TAG }} -f Dockerfile . && \
+          if [[ "${{ env.TAG }}" == "latest" || "${{ env.TAG }}" == "dev" || "${{ env.TAG }}" == "demo" || "${{ env.TAG }}" == "hotfix"  ]]; then
+            docker push ${{ secrets.ACR_LOGIN_SERVER }}/macaefrontend:${{ env.TAG }} && \
+            echo "Frontend image built and pushed successfully."
+          else
+            echo "Skipping Docker push for frontend with tag: ${{ env.TAG }}"
+          fi
+
           

.github/workflows/test.yml

@@ -38,6 +38,7 @@ jobs:
           python -m pip install --upgrade pip
           pip install -r src/backend/requirements.txt
           pip install pytest-cov
+          pip install pytest-asyncio
 
       - name: Check if test files exist
         id: check_tests

README.md

@@ -1,4 +1,4 @@
-# Multi-Agent: Custom Automation Engine – Solution Accelerator
+# Multi-Agent-Custom-Automation-Engine – Solution Accelerator
 
 MENU: [**USER STORY**](#user-story) \| [**QUICK DEPLOY**](#quick-deploy)  \| [**SUPPORTING DOCUMENTATION**](#supporting-documentation) \|
 
@@ -13,23 +13,23 @@ Problem:
 Agentic AI systems are set to transform the way businesses operate, however it can be fairly complex to build an initial MVP to demonstrate this value. 
 
 Solution:
-The Multi-Agent -Custom Automation Engine Solution Accelerator provides a ready to go application to use as the base of the MVP, or as a reference, allowing you to hit the ground running.
+The Multi-Agent-Custom Automation Engine Solution Accelerator provides a ready to go application to use as the base of the MVP, or as a reference, allowing you to hit the ground running.
 
 ### Technology Note
 This accelerator uses the AutoGen framework from Microsoft Research.  This is an open source project that is maintained by [Microsoft Research’s AI Frontiers Lab](https://www.microsoft.com/research/lab/ai-frontiers/). Please see this [blog post](https://devblogs.microsoft.com/autogen/microsofts-agentic-frameworks-autogen-and-semantic-kernel/) for the latest information on using the AutoGen framework in production solutions.
 
 ### Use cases / scenarios
 The multi-agent approach allows users to utilize multiple AI agents simultaneously for repeatable tasks, ensuring consistency and efficiency. 
-The agents collaborate with a manager on various assignments for onboarding a new employee , such as HR and tech support AI working together to set up software accounts, configure hardware, schedule onboarding meetings, register employees for benefits, and send welcome emails. Additionally, these agents can handle tasks like procurement and drafting press releases.
+The agents collaborate with a manager on various assignments for onboarding a new employee, such as HR and tech support AI working together to set up software accounts, configure hardware, schedule onboarding meetings, register employees for benefits, and send welcome emails. Additionally, these agents can handle tasks like procurement and drafting press releases.
 
 ### Business value
-Multi-agent systems represent the next wave of Generative AI use cases, offering entirely new opportunities to drive efficiencies in your business. The Multi-Agent -Custom Automation Engine Solution Accelerator demonstrates several key benefits:
+Multi-agent systems represent the next wave of Generative AI use cases, offering entirely new opportunities to drive efficiencies in your business. The Multi-Agent-Custom-Automation-Engine Solution Accelerator demonstrates several key benefits:
 
 - **Allows people to focus on what matters:** by doing the heavy lifting involved with coordinating activities across an organization, peoples’ time is freed up to focus on their specializations.
 - **Enabling GenAI to scale:** by not needing to build one application after another, organizations are able to reduce the friction of adopting GenAI across their entire organization. One capability can unlock almost unlimited use cases.
 - **Applicable to most industries:** these are common challenges that most organizations face, across most industries.
 
-Whilst still an emerging area, investing in agentic use cases, digitatization and developing tools will be key to ensuring you are able to leverage these new technologies and seize the GenAI moment.
+Whilst still an emerging area, investing in agentic use cases, digitization and developing tools will be key to ensuring you are able to leverage these new technologies and seize the GenAI moment.
 
 ### Technical key features
 
@@ -177,15 +177,18 @@ To add your newly created backend image:
         name: 'FRONTEND_SITE_NAME'
         value: 'https://<website Name>.azurewebsites.net'
 
+        name: 'APPLICATIONINSIGHTS_INSTRUMENTATION_KEY'
+        value: <Application Insights Instrumentation Key>
+
 - Click 'Save' and deploy your new revision
 
 To add the new container to your website run the following:
 
 ```
-az webapp config container set --resource-group macae_full_deploy2_rg \
---name macae-frontend-2t62qyozi76bs \
---container-image-name macaeacr2t62qyozi76bs.azurecr.io/frontendmacae:latest  \
---container-registry-url https://macaeacr2t62qyozi76bs.azurecr.io
+az webapp config container set --resource-group <resource_group_name> \
+--name <container_name> \
+--container-image-name <e.g. macaeacr2t62qyozi76bs.azurecr.io/frontendmacae:latest>  \
+--container-registry-url <e.g. https://macaeacr2t62qyozi76bs.azurecr.io>
 ```
 
 
@@ -196,7 +199,7 @@ To add the identity provider, please follow the steps outlined in [Set Up Authen
 
 To debug the solution, you can use the Cosmos and OpenAI services you have manually deployed.  To do this, you need to ensure that your Azure identity has the required permissions on the Cosmos and OpenAI services. 
 
-- For OpeAI service, you can add yourself to the ‘Cognitive Services OpenAI User’ permission in the Access Control (IAM) pane of the Azure portal.  
+- For OpenAI service, you can add yourself to the ‘Cognitive Services OpenAI User’ permission in the Access Control (IAM) pane of the Azure portal.  
 - Cosmos is a little more difficult as it requires permissions be added through script.  See these examples for more information: 
   - [Use data plane role-based access control - Azure Cosmos DB for NoSQL | Microsoft Learn](https://learn.microsoft.com/en-us/azure/cosmos-db/nosql/security/how-to-grant-data-plane-role-based-access?tabs=built-in-definition%2Cpython&pivots=azure-interface-cli) 
   - [az cosmosdb sql role assignment | Microsoft Learn](https://learn.microsoft.com/en-us/cli/azure/cosmosdb/sql/role/assignment?view=azure-cli-latest#az-cosmosdb-sql-role-assignment-create) 

deploy/macae-continer-oc.json

@@ -6,7 +6,7 @@
     "_generator": {
       "name": "bicep",
       "version": "0.32.4.45862",
-      "templateHash": "17567587246932458853"
+      "templateHash": "13282901028774763433"
     }
   },
   "parameters": {
@@ -366,13 +366,18 @@
                 {
                   "name": "FRONTEND_SITE_NAME",
                   "value": "[format('https://{0}.azurewebsites.net', format(variables('uniqueNameFormat'), 'frontend'))]"
+                },
+                {
+                  "name": "APPLICATIONINSIGHTS_INSTRUMENTATION_KEY",
+                  "value": "[reference('appInsights').ConnectionString]"
                 }
               ]
             }
           ]
         }
       },
       "dependsOn": [
+        "appInsights",
         "cosmos::autogenDb",
         "containerAppEnv",
         "cosmos",

deploy/macae-continer.bicep

@@ -279,6 +279,10 @@ resource containerApp 'Microsoft.App/containerApps@2024-03-01' = {
               name: 'FRONTEND_SITE_NAME'
               value: 'https://${format(uniqueNameFormat, 'frontend')}.azurewebsites.net'
             }
+            {
+              name: 'APPLICATIONINSIGHTS_INSTRUMENTATION_KEY'
+              value: appInsights.properties.ConnectionString
+            }
           ]
         }
       ]

documentation/LocalDeployment.md

@@ -22,7 +22,7 @@
      ```
    - To specify a tenant, use:
      ```bash
-     az login --tenant 16b3c013-0000-0000-0000-000000000
+     az login --tenant <tenant_id>
      ```
 
 3. **Create a Resource Group:**
@@ -42,29 +42,47 @@
      ```bash
      az ad signed-in-user show --query id -o tsv
      ```
-     You will also be prompted for locations for Cosmos and Open AI services.  This is to allow separate regions where there may be service quota restrictions
+     You will also be prompted for locations for Cosmos and Open AI services.  This is to allow separate regions where there may be service quota restrictions.
 
-5. **Create a `.env` file:**
+   - **Additional Notes**:
+
+     **Role Assignments in Bicep Deployment:**
+     
+      The **macae-dev.bicep** deployment includes the assignment of the appropriate roles to AOAI and Cosmos services. If you want to modify an existing implementation—for example, to use resources deployed as part of the simple deployment for local debugging—you will need to add your own credentials to access the Cosmos and AOAI services. You can add these permissions using the following commands:
+     ```bash
+     az cosmosdb sql role assignment create --resource-group <solution-accelerator-rg> --account-name <cosmos-db-account-name> --role-definition-name "Cosmos DB Built-in Data Contributor" --principal-id <aad-user-object-id> --scope /subscriptions/<subscription-id>/resourceGroups/<solution-accelerator-rg>/providers/Microsoft.DocumentDB/databaseAccounts/<cosmos-db-account-name>
+     ```
+
+     ```bash
+     az role assignment create --assignee <aad-user-upn> --role "Cognitive Services OpenAI User" --scope /subscriptions/<subscription-id>/resourceGroups/<solution-accelerator-rg>/providers/Microsoft.CognitiveServices/accounts/<azure-openai-account-name>
+     ```
+      **Using a Different Database in Cosmos:**
+
+      You can set the solution up to use a different database in Cosmos. For example, you can name it something like autogen-dev. To do this:
+		1. Change the environment variable **COSMOSDB_DATABASE** to the new database name.
+ 		2. You will need to create the database in the Cosmos DB account. You can do this from the Data Explorer pane in the portal, click on the drop down labeled “_+ New Container_” and provide all the necessary details.
+
+6. **Create a `.env` file:**
 
    - Navigate to the `src` folder and create a `.env` file based on the provided `.env.sample` file.
 
-6. **Fill in the `.env` file:**
+7. **Fill in the `.env` file:**
 
    - Use the output from the deployment or check the Azure Portal under "Deployments" in the resource group.
 
-7. **(Optional) Set up a virtual environment:**
+8. **(Optional) Set up a virtual environment:**
 
    - If you are using `venv`, create and activate your virtual environment for both the frontend and backend folders.
 
-8. **Install requirements - frontend:**
+9. **Install requirements - frontend:**
 
    - In each of the frontend and backend folders -
      Open a terminal in the `src` folder and run:
      ```bash
      pip install -r requirements.txt
      ```
 
-9. **Run the application:**
+10. **Run the application:**
    - From the src/backend directory:
    ```bash
    python app.py

documentation/azure_app_service_auth_setup.md

@@ -18,7 +18,7 @@
 
 ![Add Provider](./images/azure-app-service-auth-setup/AppAuthIdentityProviderAdd.png)
 
-5. Accept the default values and click on `Add` button to go back to the previous page with the identify provider added.
+5. Accept the default values and click on `Add` button to go back to the previous page with the idenity provider added.
 
 ![Add Provider](./images/azure-app-service-auth-setup/AppAuthIdentityProviderAdded.png)
 

src/backend/.env.sample

@@ -5,6 +5,7 @@ COSMOSDB_CONTAINER=memory
 AZURE_OPENAI_ENDPOINT=
 AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
 AZURE_OPENAI_API_VERSION=2024-08-01-preview
+APPLICATIONINSIGHTS_INSTRUMENTATION_KEY=
 
 BACKEND_API_URL='http://localhost:8000'
 FRONTEND_SITE_NAME='http://127.0.0.1:3000'

src/backend/agents/agentutils.py

@@ -1,11 +1,13 @@
 import json
 
-from autogen_core.components.models import (AssistantMessage,
-                                            AzureOpenAIChatCompletionClient)
+from autogen_core.components.models import (
+    AssistantMessage,
+    AzureOpenAIChatCompletionClient,
+)
 from pydantic import BaseModel
 
 from context.cosmos_memory import CosmosBufferedChatCompletionContext
-from models.messages import InputTask, PlanStatus, Step, StepStatus
+from models.messages import Step
 
 common_agent_system_message = "If you do not have the information for the arguments of the function you need to call, do not call the function. Instead, respond back to the user requesting further information. You must not hallucinate or invent any of the information used as arguments in the function. For example, if you need to call a function that requires a delivery address, you must not generate 123 Example St. You must skip calling functions and return a clarification message along the lines of: Sorry, I'm missing some information I need to help you with that. Could you please provide the delivery address so I can do that for you?"
 
@@ -27,7 +29,7 @@ class FSMStateAndTransition(BaseModel):
             identifiedTargetState: str
             identifiedTargetTransition: str
 
-        cosmos = CosmosBufferedChatCompletionContext(session_id or "",user_id)
+        cosmos = CosmosBufferedChatCompletionContext(session_id or "", user_id)
         combined_LLM_messages = [
             AssistantMessage(content=step.action, source="GroupChatManager")
         ]

src/backend/agents/base_agent.py

@@ -3,16 +3,26 @@
 
 from autogen_core.base import AgentId, MessageContext
 from autogen_core.components import RoutedAgent, message_handler
-from autogen_core.components.models import (AssistantMessage,
-                                            AzureOpenAIChatCompletionClient,
-                                            LLMMessage, SystemMessage,
-                                            UserMessage)
+from autogen_core.components.models import (
+    AssistantMessage,
+    AzureOpenAIChatCompletionClient,
+    LLMMessage,
+    SystemMessage,
+    UserMessage,
+)
 from autogen_core.components.tool_agent import tool_agent_caller_loop
 from autogen_core.components.tools import Tool
 
 from context.cosmos_memory import CosmosBufferedChatCompletionContext
-from models.messages import (ActionRequest, ActionResponse,
-                             AgentMessage, Step, StepStatus)
+from models.messages import (
+    ActionRequest,
+    ActionResponse,
+    AgentMessage,
+    Step,
+    StepStatus,
+)
+from event_utils import track_event_if_configured
+
 
 class BaseAgent(RoutedAgent):
     def __init__(
@@ -94,15 +104,54 @@ async def handle_action_request(
                     step_id=message.step_id,
                 )
             )
+
+            track_event_if_configured(
+                "Base agent - Added into the cosmos",
+                {
+                    "session_id": message.session_id,
+                    "user_id": self._user_id,
+                    "plan_id": message.plan_id,
+                    "content": f"{result}",
+                    "source": self._agent_name,
+                    "step_id": message.step_id,
+                },
+            )
+
         except Exception as e:
-            print(f"Error during LLM call: {e}")
+            logging.exception(f"Error during LLM call: {e}")
+            track_event_if_configured(
+                "Base agent - Error during llm call, captured into the cosmos",
+                {
+                    "session_id": message.session_id,
+                    "user_id": self._user_id,
+                    "plan_id": message.plan_id,
+                    "content": f"{e}",
+                    "source": self._agent_name,
+                    "step_id": message.step_id,
+                },
+            )
+
             return
         print(f"Task completed: {result}")
 
         step.status = StepStatus.completed
         step.agent_reply = result
         await self._model_context.update_step(step)
 
+        track_event_if_configured(
+            "Base agent - Updated step and updated into the cosmos",
+            {
+                "status": StepStatus.completed,
+                "session_id": message.session_id,
+                "agent_reply": f"{result}",
+                "user_id": self._user_id,
+                "plan_id": message.plan_id,
+                "content": f"{result}",
+                "source": self._agent_name,
+                "step_id": message.step_id,
+            },
+        )
+
         action_response = ActionResponse(
             step_id=step.id,
             plan_id=step.plan_id,