Merge pull request microsoft#1084 from microsoft/feat/model-changes

feat: Upgrade to GPT-5.4 model and enhance ACR build process

Author: Roopan-Microsoft

.github/agents/speckit.contentpack.agent.md

@@ -71,7 +71,7 @@ perform, not around a template. Ask yourself:
   "team_id": "00000000-0000-0000-0000-000000000008",
   "name": "Your Team Name",
   "status": "visible",           // REQUIRED — team won't appear in UI without this
-  "deployment_name": "gpt-4.1-mini",
+  "deployment_name": "gpt-5.4-mini",
   ...
 }
 ```
@@ -164,8 +164,8 @@ dict. Place it before the `# ── Example Pack ──` comment block:
             "kind": "azureOpenAI",
             "azureOpenAIParameters": {
                 "resourceUri": AI_SERVICES_ENDPOINT,
-                "deploymentId": "gpt-4.1-mini",
-                "modelName": "gpt-4.1-mini",
+                "deploymentId": "gpt-5.4-mini",
+                "modelName": "gpt-5.4-mini",
             },
         },
         "sources": [

.github/workflows/azd-template-validation.yml

@@ -34,7 +34,7 @@ jobs:
           AZURE_LOCATION: ${{ vars.AZURE_LOCATION }}
           AZURE_ENV_AI_SERVICE_LOCATION: ${{ vars.AZURE_AI_DEPLOYMENT_LOCATION }}
           AZURE_ENV_GPT_MODEL_CAPACITY: 1
-          AZURE_ENV_MODEL_4_1_CAPACITY: 1 # keep low to avoid potential quota issues
+          AZURE_ENV_MODEL_5_4_CAPACITY: 1 # keep low to avoid potential quota issues
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: print result

.github/workflows/azure-dev.yml

@@ -18,7 +18,7 @@ jobs:
       AZURE_LOCATION: ${{ vars.AZURE_LOCATION }}
       AZURE_ENV_AI_SERVICE_LOCATION: ${{ vars.AZURE_AI_DEPLOYMENT_LOCATION }}
       AZURE_ENV_GPT_MODEL_CAPACITY: 1
-      AZURE_ENV_MODEL_4_1_CAPACITY: 1
+      AZURE_ENV_MODEL_5_4_CAPACITY: 1
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       AZURE_DEV_COLLECT_TELEMETRY: ${{ vars.AZURE_DEV_COLLECT_TELEMETRY }}
     steps:

.github/workflows/deploy-waf.yml

@@ -22,9 +22,8 @@ jobs:
     runs-on: ubuntu-latest
     environment: production
     env:
-      GPT_MIN_CAPACITY: 1
-      O4_MINI_MIN_CAPACITY: 1
-      GPT41_MINI_MIN_CAPACITY: 1
+      GPT_5_4_MINI_MIN_CAPACITY: 1
+      GPT_5_4_MIN_CAPACITY: 1
     steps:
       - name: Checkout Code
         uses: actions/checkout@v6
@@ -40,9 +39,8 @@ jobs:
         id: quota-check
         env:
           AZURE_SUBSCRIPTION_ID: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
-          GPT_MIN_CAPACITY: ${{ env.GPT_MIN_CAPACITY }}
-          O4_MINI_MIN_CAPACITY: ${{ env.O4_MINI_MIN_CAPACITY }}
-          GPT41_MINI_MIN_CAPACITY: ${{ env.GPT41_MINI_MIN_CAPACITY }}
+          GPT_5_4_MINI_MIN_CAPACITY: ${{ env.GPT_5_4_MINI_MIN_CAPACITY }}
+          GPT_5_4_MIN_CAPACITY: ${{ env.GPT_5_4_MIN_CAPACITY }}
           AZURE_REGIONS: ${{ vars.AZURE_REGIONS }}
         run: |
           chmod +x infra/scripts/pre-provision/checkquota.sh
@@ -133,9 +131,8 @@ jobs:
               solutionName=${{ env.SOLUTION_PREFIX }} \
               location="${{ env.AZURE_LOCATION }}" \
               azureAiServiceLocation='${{ env.AZURE_LOCATION }}' \
-              gptDeploymentCapacity=${{ env.GPT_MIN_CAPACITY }} \
-              gpt4_1ModelCapacity=${{ env.GPT41_MINI_MIN_CAPACITY }} \
-              gptReasoningModelCapacity=${{ env.O4_MINI_MIN_CAPACITY }} \
+              gptDeploymentCapacity=${{ env.GPT_5_4_MINI_MIN_CAPACITY }} \
+              gpt5_4ModelCapacity=${{ env.GPT_5_4_MIN_CAPACITY }} \
               enableTelemetry=true \
               enableMonitoring=true \
               enablePrivateNetworking=true \

.github/workflows/deploy.yml

@@ -17,9 +17,8 @@ on:
     - cron: "0 11,23 * * *" # Runs at 11:00 AM and 11:00 PM GMT
   workflow_dispatch: #Allow manual triggering
 env:
-  GPT_MIN_CAPACITY: 50
-  O4_MINI_MIN_CAPACITY: 50
-  GPT41_MINI_MIN_CAPACITY: 50
+  GPT_5_4_MINI_MIN_CAPACITY: 100
+  GPT_5_4_MIN_CAPACITY: 150
   BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
 
 jobs:
@@ -47,9 +46,8 @@ jobs:
         id: quota-check
         env:
           AZURE_SUBSCRIPTION_ID: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
-          GPT_MIN_CAPACITY: ${{ env.GPT_MIN_CAPACITY }}
-          O4_MINI_MIN_CAPACITY: ${{ env.O4_MINI_MIN_CAPACITY }}
-          GPT41_MINI_MIN_CAPACITY: ${{ env.GPT41_MINI_MIN_CAPACITY }}
+          GPT_5_4_MINI_MIN_CAPACITY: ${{ env.GPT_5_4_MINI_MIN_CAPACITY }}
+          GPT_5_4_MIN_CAPACITY: ${{ env.GPT_5_4_MIN_CAPACITY }}
           AZURE_REGIONS: ${{ vars.AZURE_REGIONS }}
         run: |
           chmod +x infra/scripts/pre-provision/checkquota.sh
@@ -148,12 +146,12 @@ jobs:
               solutionName=${{ env.SOLUTION_PREFIX }} \
               location="${{ env.AZURE_LOCATION }}" \
               deploymentType="GlobalStandard" \
-              gptModelName="gpt-4.1-mini" \
-              gptModelVersion="2025-04-14" \
+              gptModelName="gpt-5.4-mini" \
+              gptModelVersion="2026-03-17" \
               backendContainerImageTag="${IMAGE_TAG}" \
               frontendContainerImageTag="${IMAGE_TAG}" \
               azureAiServiceLocation='${{ env.AZURE_LOCATION }}' \
-              gptDeploymentCapacity=50 \
+              gptDeploymentCapacity=100 \
               createdBy="Pipeline" \
               tags="{'Purpose':'Deploying and Cleaning Up Resources for Validation','CreatedDate':'$current_date'}" \
             --output json

.github/workflows/job-deploy.yml

@@ -98,9 +98,8 @@ on:
         value: ${{ jobs.azure-setup.outputs.QUOTA_FAILED }}
 
 env:
-  GPT_MIN_CAPACITY: 50
-  O4_MINI_MIN_CAPACITY: 50
-  GPT41_MINI_MIN_CAPACITY: 50
+  GPT_5_4_MINI_MIN_CAPACITY: 100
+  GPT_5_4_MIN_CAPACITY: 150
   BRANCH_NAME: ${{ github.event.workflow_run.head_branch || github.head_ref || github.ref_name }}
   WAF_ENABLED: ${{ inputs.trigger_type == 'workflow_dispatch' && (inputs.waf_enabled || false) || false }}
   EXP: ${{ inputs.trigger_type == 'workflow_dispatch' && (inputs.EXP || false) || false }}
@@ -306,9 +305,8 @@ jobs:
         id: quota-check
         env:
           AZURE_SUBSCRIPTION_ID: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
-          GPT_MIN_CAPACITY: ${{ env.GPT_MIN_CAPACITY }}
-          O4_MINI_MIN_CAPACITY: ${{ env.O4_MINI_MIN_CAPACITY }}
-          GPT41_MINI_MIN_CAPACITY: ${{ env.GPT41_MINI_MIN_CAPACITY }}
+          GPT_5_4_MINI_MIN_CAPACITY: ${{ env.GPT_5_4_MINI_MIN_CAPACITY }}
+          GPT_5_4_MIN_CAPACITY: ${{ env.GPT_5_4_MIN_CAPACITY }}
           AZURE_REGIONS: ${{ vars.AZURE_REGIONS }}
         run: |
           chmod +x infra/scripts/pre-provision/checkquota.sh

.github/workflows/job-send-notification.yml

@@ -68,7 +68,7 @@ on:
         type: string
 
 env:
-  GPT_MIN_CAPACITY: 100
+  GPT_5_4_MINI_MIN_CAPACITY: 100
   BRANCH_NAME: ${{ github.event.workflow_run.head_branch || github.head_ref || github.ref_name }}
   WAF_ENABLED: ${{ inputs.trigger_type == 'workflow_dispatch' && (inputs.waf_enabled || false) || false }}
   EXP: ${{ inputs.trigger_type == 'workflow_dispatch' && (inputs.EXP || false) || false }}

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-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.
+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-5.4 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-5.4. To ensure effective and responsible use of the accelerator, users should carefully consider their choices and use the system within its intended scope.

azure.yaml

@@ -17,6 +17,11 @@ hooks:
           Write-Host "===============================================================" -ForegroundColor Yellow
           Write-Host ""
 
+          Write-Host " Build and push the backend/frontend/mcp_server container images to ACR, then point the container app and webapp at them:" -ForegroundColor White
+          Write-Host "  👉 Run the following command in Bash:" -ForegroundColor White
+          Write-Host "   bash infra/scripts/post-provision/build_and_push_images.sh" -ForegroundColor Cyan
+          Write-Host ""
+
           Write-Host " Upload Team Configurations, index sample data and create the Knowledge base from content Packs" -ForegroundColor White
           Write-Host "  👉 Run the following command in Bash:" -ForegroundColor White
           Write-Host "   bash infra/scripts/post-provision/post_deploy.sh" -ForegroundColor Cyan
@@ -33,9 +38,14 @@ hooks:
           Write-Host "===============================================================" -ForegroundColor Yellow
           Write-Host ""
 
+          Write-Host " Build and push the backend/frontend/mcp_server container images to ACR, then point the container app and webapp at them:" -ForegroundColor White
+          Write-Host "  👉 Run the following command in PowerShell:" -ForegroundColor White
+          Write-Host "   .\infra\scripts\post-provision\Build-And-Push-Images.ps1" -ForegroundColor Cyan
+          Write-Host ""
+
           Write-Host " Upload Team Configurations, index sample data and create the Knowledge base from content Packs" -ForegroundColor White
           Write-Host "  👉 Run the following command in PowerShell:" -ForegroundColor White
-          Write-Host "   infra\scripts\post-provision\post_deploy.ps1" -ForegroundColor Cyan
+          Write-Host "   .\infra\scripts\post-provision\post_deploy.ps1" -ForegroundColor Cyan
           Write-Host ""
 
           Write-Host "🌐 Access your deployed Frontend application at:" -ForegroundColor Green
@@ -58,6 +68,10 @@ hooks:
         printf "${Green} POST-DEPLOYMENT STEPS (Bash)\n"
         printf "${Yellow}===============================================================${NC}\n\n"
 
+        printf  "Build and push the backend/frontend/mcp_server container images to ACR, then point the container app and webapp at them:\n"
+        printf  "  👉 Run the following command in Bash:\n"
+        printf  "   ${Blue}bash infra/scripts/post-provision/build_and_push_images.sh${NC}\n\n"
+
         printf  "Upload Team Configurations, index sample data and create the Knowledge base from content Packs:\n"
         printf  "  👉 Run the following command in Bash:\n"
         printf  "   ${Blue}bash infra/scripts/post-provision/post_deploy.sh${NC}\n\n"

content_packs/README.md

@@ -67,7 +67,7 @@ perform, not around a template. Ask yourself:
   "team_id": "00000000-0000-0000-0000-000000000008",
   "name": "Your Team Name",
   "status": "visible",           // REQUIRED — team won't appear in UI without this
-  "deployment_name": "gpt-4.1-mini",
+  "deployment_name": "gpt-5.4-mini",
   ...
 }
 ```
@@ -160,8 +160,8 @@ dict. Place it before the `# ── Example Pack ──` comment block:
             "kind": "azureOpenAI",
             "azureOpenAIParameters": {
                 "resourceUri": AI_SERVICES_ENDPOINT,
-                "deploymentId": "gpt-4.1-mini",
-                "modelName": "gpt-4.1-mini",
+                "deploymentId": "gpt-5.4-mini",
+                "modelName": "gpt-5.4-mini",
             },
         },
         "sources": [