Python: Tuning auto sample validation workflow

.github/workflows/python-sample-validation.yml

@@ -8,6 +8,8 @@ on:
 env:
   # Configure a constant location for the uv cache
   UV_CACHE_DIR: /tmp/.uv-cache
+  # GitHub Copilot configuration
+  GITHUB_COPILOT_MODEL: claude-opus-4.6
 
 jobs:
   validate-01-get-started:
@@ -16,24 +18,35 @@ jobs:
     permissions:
       contents: read
     env:
-      # Azure AI configuration for get-started samples
-      AZURE_AI_PROJECT_ENDPOINT: ${{ secrets.AZURE_AI_PROJECT_ENDPOINT }}
-      AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ secrets.AZURE_AI_MODEL_DEPLOYMENT_NAME }}
-      # GitHub Copilot configuration
-      GITHUB_COPILOT_MODEL: ${{ vars.GITHUB_COPILOT_MODEL }}
+      # Required configuration for get-started samples
+      AZURE_AI_PROJECT_ENDPOINT: ${{ vars.AZURE_AI_PROJECT_ENDPOINT }}
+      AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
+      AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
+      AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
     defaults:
       run:
         working-directory: python
     steps:
       - uses: actions/checkout@v6
 
+      - name: Set up Node.js environment
+        uses: actions/setup-node@v4
+
+      - name: Install Copilot CLI
+        run: npm install -g @github/copilot
+
+      - name: Authenticate Copilot CLI
+        run: echo ${{ secrets.GITHUB_TOKEN }} | gh auth login --with-token
+
+      - name: Test Copilot CLI
+        run: |
+          copilot -p "What can you do?"
+
       - name: Set up python and install the project
         uses: ./.github/actions/python-setup
         with:
           python-version: "3.12"
           os: ${{ runner.os }}
-        env:
-          UV_CACHE_DIR: /tmp/.uv-cache
 
       - name: Run sample validation
         run: |

python/samples/_sample_validation/create_dynamic_workflow_executor.py

@@ -55,7 +55,7 @@ class BatchCompletion:
     "You are validating exactly one Python sample.\n"
     "Analyze the sample code and execute it. Determine if it runs successfully, fails, or times out.\n"
     "The sample can be interactive. If it is interactive, respond to the sample when prompted "
-    "based on your analysis of the code. You do not need to consult human on what to respond\n"
+    "based on your analysis of the code. You do not need to consult human on what to respond.\n"
     "Return ONLY valid JSON with this schema:\n"
     "{\n"
     '  "status": "success|failure|timeout|error",\n'