Merge branch 'main' into content-extension

.github/actions/setup-runner/action.yml

@@ -28,7 +28,7 @@ runs:
         # Install llama-stack-client-python based on the client-version input
         if [ "${{ inputs.client-version }}" = "latest" ]; then
           echo "Installing latest llama-stack-client-python from main branch"
-          uv pip install git+https://github.com/meta-llama/llama-stack-client-python.git@main
+          uv pip install git+https://github.com/llamastack/llama-stack-client-python.git@main
         elif [ "${{ inputs.client-version }}" = "published" ]; then
           echo "Installing published llama-stack-client-python from PyPI"
           uv pip install llama-stack-client

.github/workflows/integration-tests.yml

@@ -5,7 +5,7 @@ run-name: Run the integration test suite from tests/integration in replay mode
 on:
   push:
     branches: [ main ]
-  pull_request:
+  pull_request_target:
     branches: [ main ]
     types: [opened, synchronize, reopened]
     paths:
@@ -34,7 +34,7 @@ on:
 
 concurrency:
   # Skip concurrency for pushes to main - each commit should be tested independently
-  group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
+  group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.event.pull_request.number }}
   cancel-in-progress: true
 
 jobs:
@@ -52,7 +52,8 @@ jobs:
         run: |
           # Get test directories dynamically, excluding non-test directories
           # NOTE: we are excluding post_training since the tests take too long
-          TEST_TYPES=$(find tests/integration -maxdepth 1 -mindepth 1 -type d -printf "%f\n" |
+          TEST_TYPES=$(find tests/integration -maxdepth 1 -mindepth 1 -type d |
+            sed 's|tests/integration/||' |
             grep -Ev "^(__pycache__|fixtures|test_cases|recordings|non_ci|post_training)$" |
             sort | jq -R -s -c 'split("\n")[:-1]')
           echo "test-types=$TEST_TYPES" >> $GITHUB_OUTPUT

.github/workflows/integration-vector-io-tests.yml

@@ -164,9 +164,9 @@ jobs:
           ENABLE_WEAVIATE: ${{ matrix.vector-io-provider == 'remote::weaviate' && 'true' || '' }}
           WEAVIATE_CLUSTER_URL: ${{ matrix.vector-io-provider == 'remote::weaviate' && 'localhost:8080' || '' }}
         run: |
-          uv run pytest -sv --stack-config="inference=inline::sentence-transformers,vector_io=${{ matrix.vector-io-provider }}" \
+          uv run pytest -sv --stack-config="files=inline::localfs,inference=inline::sentence-transformers,vector_io=${{ matrix.vector-io-provider }}" \
             tests/integration/vector_io \
-            --embedding-model sentence-transformers/all-MiniLM-L6-v2
+            --embedding-model inline::sentence-transformers/all-MiniLM-L6-v2
 
       - name: Check Storage and Memory Available After Tests
         if: ${{ always() }}

.github/workflows/semantic-pr.yml

@@ -11,7 +11,7 @@ on:
       - synchronize
 
 concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number }}
   cancel-in-progress: true
 
 permissions: