fixes

.github/actions/run-integration-tests/action.yml

@@ -27,6 +27,26 @@ outputs:
 runs:
   using: 'composite'
   steps:
+    - name: Run Llama Stack Server
+      if: ${{ contains(inputs.stack-config, 'server:') }}
+      run: |
+        # Run this so pytest in a loop doesn't start-stop servers in a loop
+        echo "Starting Llama Stack Server"
+        nohup uv run llama stack run ci-tests --image-type venv > server.log 2>&1 &
+
+        echo "Waiting for Llama Stack Server to start"
+        for i in {1..30}; do
+          if curl -s http://localhost:8321/v1/health | grep -q "OK"; then
+            echo "Llama Stack Server started"
+            exit 0
+          fi
+          sleep 1
+        done
+
+        echo "Llama Stack Server failed to start"
+        cat server.log
+        exit 1
+
     - name: Run Integration Tests
       env:
         LLAMA_STACK_CLIENT_TIMEOUT: "300"

.github/actions/setup-test-environment/action.yml

@@ -16,19 +16,10 @@ inputs:
     description: 'Whether to setup provider for vision tests'
     required: false
     default: 'false'
-  inference-mode:
-    description: 'Inference mode (record or replay)'
-    required: true
 
 runs:
   using: 'composite'
   steps:
-    - name: Checkout repository
-      uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-      with:
-        ref: ${{ inputs.inference-mode == 'record' && github.event.pull_request.head.ref || '' }}
-        fetch-depth: ${{ inputs.inference-mode == 'record' && '0' || '1' }}
-
     - name: Install dependencies
       uses: ./.github/actions/setup-runner
       with: