Merge branch 'main' into content-extension

.github/actions/run-and-record-tests/action.yml

@@ -2,13 +2,6 @@ name: 'Run and Record Tests'
 description: 'Run integration tests and handle recording/artifact upload'
 
 inputs:
-  test-subdirs:
-    description: 'Comma-separated list of test subdirectories to run'
-    required: true
-  test-pattern:
-    description: 'Regex pattern to pass to pytest -k'
-    required: false
-    default: ''
   stack-config:
     description: 'Stack configuration to use'
     required: true
@@ -18,10 +11,18 @@ inputs:
   inference-mode:
     description: 'Inference mode (record or replay)'
     required: true
-  run-vision-tests:
-    description: 'Whether to run vision tests'
+  test-suite:
+    description: 'Test suite to use: base, responses, vision, etc.'
     required: false
-    default: 'false'
+    default: ''
+  test-subdirs:
+    description: 'Comma-separated list of test subdirectories to run; overrides test-suite'
+    required: false
+    default: ''
+  test-pattern:
+    description: 'Regex pattern to pass to pytest -k'
+    required: false
+    default: ''
 
 runs:
   using: 'composite'
@@ -42,7 +43,7 @@ runs:
           --test-subdirs '${{ inputs.test-subdirs }}' \
           --test-pattern '${{ inputs.test-pattern }}' \
           --inference-mode '${{ inputs.inference-mode }}' \
-          ${{ inputs.run-vision-tests == 'true' && '--run-vision-tests' || '' }} \
+          --test-suite '${{ inputs.test-suite }}' \
           | tee pytest-${{ inputs.inference-mode }}.log
 
 
@@ -57,12 +58,7 @@ runs:
           echo "New recordings detected, committing and pushing"
           git add tests/integration/recordings/
 
-          if [ "${{ inputs.run-vision-tests }}" == "true" ]; then
-            git commit -m "Recordings update from CI (vision)"
-          else
-            git commit -m "Recordings update from CI"
-          fi
-
+          git commit -m "Recordings update from CI (test-suite: ${{ inputs.test-suite }})"
           git fetch origin ${{ github.ref_name }}
           git rebase origin/${{ github.ref_name }}
           echo "Rebased successfully"

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

@@ -1,17 +1,17 @@
 name: Setup Ollama
 description: Start Ollama
 inputs:
-  run-vision-tests:
-    description: 'Run vision tests: "true" or "false"'
+  test-suite:
+    description: 'Test suite to use: base, responses, vision, etc.'
     required: false
-    default: 'false'
+    default: ''
 runs:
   using: "composite"
   steps:
     - name: Start Ollama
       shell: bash
       run: |
-        if [ "${{ inputs.run-vision-tests }}" == "true" ]; then
+        if [ "${{ inputs.test-suite }}" == "vision" ]; then
           image="ollama-with-vision-model"
         else
           image="ollama-with-models"

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

@@ -12,10 +12,10 @@ inputs:
     description: 'Provider to setup (ollama or vllm)'
     required: true
     default: 'ollama'
-  run-vision-tests:
-    description: 'Whether to setup provider for vision tests'
+  test-suite:
+    description: 'Test suite to use: base, responses, vision, etc.'
     required: false
-    default: 'false'
+    default: ''
   inference-mode:
     description: 'Inference mode (record or replay)'
     required: true
@@ -33,7 +33,7 @@ runs:
       if: ${{ inputs.provider == 'ollama' && inputs.inference-mode == 'record' }}
       uses: ./.github/actions/setup-ollama
       with:
-        run-vision-tests: ${{ inputs.run-vision-tests }}
+        test-suite: ${{ inputs.test-suite }}
 
     - name: Setup vllm
       if: ${{ inputs.provider == 'vllm' && inputs.inference-mode == 'record' }}

.github/workflows/README.md

@@ -5,10 +5,11 @@ Llama Stack uses GitHub Actions for Continuous Integration (CI). Below is a tabl
 | Name | File | Purpose |
 | ---- | ---- | ------- |
 | Update Changelog | [changelog.yml](changelog.yml) | Creates PR for updating the CHANGELOG.md |
+| API Conformance Tests | [conformance.yml](conformance.yml) | Run the API Conformance test suite on the changes. |
 | Installer CI | [install-script-ci.yml](install-script-ci.yml) | Test the installation script |
 | Integration Auth Tests | [integration-auth-tests.yml](integration-auth-tests.yml) | Run the integration test suite with Kubernetes authentication |
 | SqlStore Integration Tests | [integration-sql-store-tests.yml](integration-sql-store-tests.yml) | Run the integration test suite with SqlStore |
-| Integration Tests (Replay) | [integration-tests.yml](integration-tests.yml) | Run the integration test suite from tests/integration in replay mode |
+| Integration Tests (Replay) | [integration-tests.yml](integration-tests.yml) | Run the integration test suites from tests/integration in replay mode |
 | Vector IO Integration Tests | [integration-vector-io-tests.yml](integration-vector-io-tests.yml) | Run the integration test suite with various VectorIO providers |
 | Pre-commit | [pre-commit.yml](pre-commit.yml) | Run pre-commit checks |
 | Test Llama Stack Build | [providers-build.yml](providers-build.yml) | Test llama stack build |

.github/workflows/conformance.yml

@@ -0,0 +1,57 @@
+# API Conformance Tests
+# This workflow ensures that API changes maintain backward compatibility and don't break existing integrations
+# It runs schema validation and OpenAPI diff checks to catch breaking changes early
+
+name: API Conformance Tests
+
+run-name: Run the API Conformance test suite on the changes.
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+    types: [opened, synchronize, reopened]
+    paths:
+      - 'llama_stack/**'
+      - '!llama_stack/ui/**'
+      - 'tests/**'
+      - 'uv.lock'
+      - 'pyproject.toml'
+      - '.github/workflows/conformance.yml' # This workflow itself
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
+  # Cancel in-progress runs when new commits are pushed to avoid wasting CI resources
+  cancel-in-progress: true
+
+jobs:
+  # Job to check if API schema changes maintain backward compatibility
+  check-schema-compatibility:
+    runs-on: ubuntu-latest
+    steps:
+      # Using specific version 4.1.7 because 5.0.0 fails when trying to run this locally using `act`
+      # This ensures consistent behavior between local testing and CI
+      - name: Checkout PR Code
+        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
+
+      # Checkout the base branch to compare against (usually main)
+      # This allows us to diff the current changes against the previous state
+      - name: Checkout Base Branch
+        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
+        with:
+          ref: ${{ github.event.pull_request.base.ref }}
+          path: 'base'
+
+      # Install oasdiff: https://github.com/oasdiff/oasdiff, a tool for detecting breaking changes in OpenAPI specs.
+      - name: Install oasdiff
+        run: |
+          curl -fsSL https://raw.githubusercontent.com/oasdiff/oasdiff/main/install.sh | sh
+
+      # Run oasdiff to detect breaking changes in the API specification
+      # This step will fail if incompatible changes are detected, preventing breaking changes from being merged
+      - name: Run OpenAPI Breaking Change Diff
+        run: |
+          oasdiff breaking --fail-on ERR base/docs/_static/llama-stack-spec.yaml docs/_static/llama-stack-spec.yaml --match-path '^/v1/openai/v1' \
+          --match-path '^/v1/vector-io' \
+          --match-path '^/v1/vector-dbs'

.github/workflows/integration-tests.yml

@@ -1,6 +1,6 @@
 name: Integration Tests (Replay)
 
-run-name: Run the integration test suite from tests/integration in replay mode
+run-name: Run the integration test suites from tests/integration in replay mode
 
 on:
   push:
@@ -32,14 +32,6 @@ on:
         description: 'Test against a specific provider'
         type: string
         default: 'ollama'
-      test-subdirs:
-        description: 'Comma-separated list of test subdirectories to run'
-        type: string
-        default: ''
-      test-pattern:
-        description: 'Regex pattern to pass to pytest -k'
-        type: string
-        default: ''
 
 concurrency:
   # Skip concurrency for pushes to main - each commit should be tested independently
@@ -50,7 +42,7 @@ jobs:
 
   run-replay-mode-tests:
     runs-on: ubuntu-latest
-    name: ${{ format('Integration Tests ({0}, {1}, {2}, client={3}, vision={4})', matrix.client-type, matrix.provider, matrix.python-version, matrix.client-version, matrix.run-vision-tests) }}
+    name: ${{ format('Integration Tests ({0}, {1}, {2}, client={3}, {4})', matrix.client-type, matrix.provider, matrix.python-version, matrix.client-version, matrix.test-suite) }}
 
     strategy:
       fail-fast: false
@@ -61,7 +53,7 @@ jobs:
         # Use Python 3.13 only on nightly schedule (daily latest client test), otherwise use 3.12
         python-version: ${{ github.event.schedule == '0 0 * * *' && fromJSON('["3.12", "3.13"]') || fromJSON('["3.12"]') }}
         client-version: ${{ (github.event.schedule == '0 0 * * *' || github.event.inputs.test-all-client-versions == 'true') && fromJSON('["published", "latest"]') || fromJSON('["latest"]') }}
-        run-vision-tests: [true, false]
+        test-suite: [base, vision]
 
     steps:
       - name: Checkout repository
@@ -73,15 +65,13 @@ jobs:
           python-version: ${{ matrix.python-version }}
           client-version: ${{ matrix.client-version }}
           provider: ${{ matrix.provider }}
-          run-vision-tests: ${{ matrix.run-vision-tests }}
+          test-suite: ${{ matrix.test-suite }}
           inference-mode: 'replay'
 
       - name: Run tests
         uses: ./.github/actions/run-and-record-tests
         with:
-          test-subdirs: ${{ inputs.test-subdirs }}
-          test-pattern: ${{ inputs.test-pattern }}
           stack-config: ${{ matrix.client-type == 'library' && 'ci-tests' || 'server:ci-tests' }}
           provider: ${{ matrix.provider }}
           inference-mode: 'replay'
-          run-vision-tests: ${{ matrix.run-vision-tests }}
+          test-suite: ${{ matrix.test-suite }}

.github/workflows/record-integration-tests.yml

@@ -10,18 +10,18 @@ run-name: Run the integration test suite from tests/integration
 on:
   workflow_dispatch:
     inputs:
-      test-subdirs:
-        description: 'Comma-separated list of test subdirectories to run'
-        type: string
-        default: ''
       test-provider:
         description: 'Test against a specific provider'
         type: string
         default: 'ollama'
-      run-vision-tests:
-        description: 'Whether to run vision tests'
-        type: boolean
-        default: false
+      test-suite:
+        description: 'Test suite to use: base, responses, vision, etc.'
+        type: string
+        default: ''
+      test-subdirs:
+        description: 'Comma-separated list of test subdirectories to run; overrides test-suite'
+        type: string
+        default: ''
       test-pattern:
         description: 'Regex pattern to pass to pytest -k'
         type: string
@@ -38,11 +38,11 @@ jobs:
       - name: Echo workflow inputs
         run: |
           echo "::group::Workflow Inputs"
-          echo "test-subdirs: ${{ inputs.test-subdirs }}"
-          echo "test-provider: ${{ inputs.test-provider }}"
-          echo "run-vision-tests: ${{ inputs.run-vision-tests }}"
-          echo "test-pattern: ${{ inputs.test-pattern }}"
           echo "branch: ${{ github.ref_name }}"
+          echo "test-provider: ${{ inputs.test-provider }}"
+          echo "test-suite: ${{ inputs.test-suite }}"
+          echo "test-subdirs: ${{ inputs.test-subdirs }}"
+          echo "test-pattern: ${{ inputs.test-pattern }}"
           echo "::endgroup::"
 
       - name: Checkout repository
@@ -56,15 +56,15 @@ jobs:
           python-version: "3.12"  # Use single Python version for recording
           client-version: "latest"
           provider: ${{ inputs.test-provider || 'ollama' }}
-          run-vision-tests: ${{ inputs.run-vision-tests }}
+          test-suite: ${{ inputs.test-suite }}
           inference-mode: 'record'
 
       - name: Run and record tests
         uses: ./.github/actions/run-and-record-tests
         with:
-          test-pattern: ${{ inputs.test-pattern }}
-          test-subdirs: ${{ inputs.test-subdirs }}
           stack-config: 'server:ci-tests'  # recording must be done with server since more tests are run
           provider: ${{ inputs.test-provider || 'ollama' }}
           inference-mode: 'record'
-          run-vision-tests: ${{ inputs.run-vision-tests }}
+          test-suite: ${{ inputs.test-suite }}
+          test-subdirs: ${{ inputs.test-subdirs }}
+          test-pattern: ${{ inputs.test-pattern }}