matrixify

.github/workflows/integration-tests.yml

@@ -26,6 +26,7 @@ jobs:
         # Listing tests manually since some of them currently fail
         # TODO: generate matrix list from tests/integration when fixed
         test-type: [agents, inference, datasets, inspect, scoring, post_training, providers]
+        stack-config: [ollama, http://localhost:8321]
       fail-fast: false # we want to run all tests regardless of failure
 
     steps:
@@ -76,6 +77,7 @@ jobs:
           exit 1
 
       - name: Start Llama Stack server in background
+        if: matrix.stack-config == "http://localhost:8321"
         env:
           INFERENCE_MODEL: "meta-llama/Llama-3.2-3B-Instruct"
         run: |
@@ -83,6 +85,7 @@ jobs:
           nohup uv run llama stack run ./llama_stack/templates/ollama/run.yaml --image-type venv > server.log 2>&1 &
 
       - name: Wait for Llama Stack server to be ready
+        if: matrix.stack-config == "http://localhost:8321"
         run: |
           echo "Waiting for Llama Stack server..."
           for i in {1..30}; do
@@ -96,18 +99,11 @@ jobs:
           cat server.log
           exit 1
 
-      - name: Run Integration Tests via library client
+      - name: Run Integration Tests
         env:
           INFERENCE_MODEL: "meta-llama/Llama-3.2-3B-Instruct"
         run: |
-          uv run pytest -v tests/integration/${{ matrix.test-type }} --stack-config=ollama \
-            -k "not(builtin_tool_code or safety_with_image or code_interpreter_for)" \
-            --text-model="meta-llama/Llama-3.2-3B-Instruct" \
-            --embedding-model=all-MiniLM-L6-v2
-
-      - name: Run Integration Tests via http client
-        run: |
-          uv run pytest -v tests/integration/${{ matrix.test-type }} --stack-config=http://localhost:8321 \
-            -k "not(builtin_tool_code or safety_with_image or code_interpreter_for)" \
+          uv run pytest -v tests/integration/${{ matrix.test-type }} --stack-config=${{ matrix.stack-config }} \
+            -k "not(builtin_tool or safety_with_image or code_interpreter or test_rag)" \
             --text-model="meta-llama/Llama-3.2-3B-Instruct" \
             --embedding-model=all-MiniLM-L6-v2