feat(ci): add support for running vision inference tests (#2972)

This PR significantly refactors the Integration Tests workflow. The main
goal behind the PR was to enable recording of vision tests which were
never run as part of our CI ever before. During debugging, I ended up
making several other changes refactoring and hopefully increasing the
robustness of the workflow.

After doing the experiments, I have updated the trigger event to be
`pull_request_target` so this workflow can get write permissions by
default but it will run with source code from the base (main) branch in
the source repository only. If you do change the workflow, you'd need to
experiment using the `workflow_dispatch` triggers. This should not be
news to anyone using Github Actions (except me!)

It is likely to be a little rocky though while I learn more about GitHub
Actions, etc. Please be patient :)

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

.github/workflows/README.md

@@ -10,6 +10,7 @@ Llama Stack uses GitHub Actions for Continuous Integration (CI). Below is a tabl
 | SqlStore Integration Tests | [integration-sql-store-tests.yml](integration-sql-store-tests.yml) | Run the integration test suite with SqlStore |
 | Integration Tests | [integration-tests.yml](integration-tests.yml) | Run the integration test suite from tests/integration |
 | Vector IO Integration Tests | [integration-vector-io-tests.yml](integration-vector-io-tests.yml) | Run the integration test suite with various VectorIO providers |
+| Vision Inference Integration Tests | [integration-vision-tests.yml](integration-vision-tests.yml) | Run vision inference integration test suite from tests/integration/inference |
 | 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 |
 | Python Package Build Test | [python-build-test.yml](python-build-test.yml) | Test building the llama-stack PyPI project |

.github/workflows/integration-tests.yml

@@ -5,7 +5,7 @@ run-name: Run the integration test suite from tests/integration
 on:
   push:
     branches: [ main ]
-  pull_request:
+  pull_request_target:
     branches: [ main ]
     types: [opened, synchronize, labeled]
     paths:
@@ -13,10 +13,10 @@ on:
       - 'tests/**'
       - 'uv.lock'
       - 'pyproject.toml'
-      - 'requirements.txt'
       - '.github/workflows/integration-tests.yml' # This workflow
       - '.github/actions/setup-ollama/action.yml'
-      - '.github/actions/run-integration-tests/action.yml'
+      - '.github/actions/setup-test-environment/action.yml'
+      - '.github/actions/run-and-record-tests/action.yml'
   schedule:
     # If changing the cron schedule, update the provider in the test-matrix job
     - cron: '0 0 * * *'  # (test latest client) Daily at 12 AM UTC
@@ -31,6 +31,10 @@ on:
         description: 'Test against a specific provider'
         type: string
         default: 'ollama'
+      force-inference-mode:
+        description: 'Force inference mode (record or replay)'
+        type: string
+        default: ''
 
 concurrency:
   # This creates three concurrency groups:
@@ -73,10 +77,16 @@ jobs:
       - name: Check if re-record-tests label exists
         id: check-rerecord-tests
         run: |
-          if [[ "${{ contains(github.event.pull_request.labels.*.name, 're-record-tests') }}" == "true" ]]; then
+          if [[ "${{ inputs.force-inference-mode }}" == "record" ]]; then
             echo "rerecord-tests=true" >> $GITHUB_OUTPUT
-          else
+          elif [[ "${{ inputs.force-inference-mode }}" == "replay" ]]; then
             echo "rerecord-tests=false" >> $GITHUB_OUTPUT
+          else
+            if [[ "${{ contains(github.event.pull_request.labels.*.name, 're-record-tests') }}" == "true" ]]; then
+              echo "rerecord-tests=true" >> $GITHUB_OUTPUT
+            else
+              echo "rerecord-tests=false" >> $GITHUB_OUTPUT
+            fi
           fi
 
   record-tests:
@@ -92,65 +102,26 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          ref: ${{ github.event.pull_request.head.ref }}
+          fetch-depth: 0
 
-      - name: Install dependencies
-        uses: ./.github/actions/setup-runner
+      - name: Setup test environment
+        uses: ./.github/actions/setup-test-environment
         with:
           python-version: "3.12"  # Use single Python version for recording
           client-version: "latest"
+          provider: ${{ inputs.test-provider || 'ollama' }}
 
-      - name: Setup ollama
-        if: ${{ inputs.test-provider == 'ollama' }}
-        uses: ./.github/actions/setup-ollama
-
-      - name: Setup vllm
-        if: ${{ inputs.test-provider == 'vllm' }}
-        uses: ./.github/actions/setup-vllm
-
-      - name: Build Llama Stack
-        run: |
-          uv run llama stack build --template ci-tests --image-type venv
-
-      - name: Configure git for commits
-        run: |
-          git config --local user.email "github-actions[bot]@users.noreply.github.com"
-          git config --local user.name "github-actions[bot]"
-
-      - name: Run Integration Tests for All Types (Recording Mode)
-        uses: ./.github/actions/run-integration-tests
+      - name: Run and record tests
+        uses: ./.github/actions/run-and-record-tests
         with:
           test-types: ${{ needs.discover-tests.outputs.test-types }}
           stack-config: 'server:ci-tests'  # recording must be done with server since more tests are run
-          provider: ${{ inputs.test-provider }}
+          provider: ${{ inputs.test-provider || 'ollama' }}
           inference-mode: 'record'
 
-      - name: Commit and push recordings
-        run: |
-          if ! git diff --quiet tests/integration/recordings/; then
-            echo "Committing recordings"
-            git add tests/integration/recordings/
-            git commit -m "Update recordings"
-            echo "Pushing all recording commits to PR"
-            git push origin HEAD:${{ github.head_ref }}
-          else
-            echo "No recording changes"
-          fi
-
-      - name: Write inference logs to file
-        if: ${{ always() }}
-        run: |
-          sudo docker logs ollama > ollama-recording.log || true
-
-      - name: Upload recording logs
-        if: ${{ always() }}
-        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
-        with:
-          name: recording-logs-${{ github.run_id }}
-          path: |
-            *.log
-          retention-days: 1
-
-  run-tests:
+  run-replay-mode-tests:
     # Skip this job if we're in recording mode (handled by record-tests job)
     if: ${{ needs.discover-tests.outputs.rerecord-tests != 'true' }}
     needs: discover-tests
@@ -169,41 +140,17 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
-      - name: Install dependencies
-        uses: ./.github/actions/setup-runner
+      - name: Setup test environment
+        uses: ./.github/actions/setup-test-environment
         with:
           python-version: ${{ matrix.python-version }}
           client-version: ${{ matrix.client-version }}
+          provider: ${{ matrix.provider }}
 
-      - name: Build Llama Stack
-        run: |
-          uv run llama stack build --template ci-tests --image-type venv
-
-      - name: Check Storage and Memory Available Before Tests
-        if: ${{ always() }}
-        run: |
-          free -h
-          df -h
-
-      - name: Run Integration Tests (Replay Mode)
-        uses: ./.github/actions/run-integration-tests
+      - name: Run and record tests
+        uses: ./.github/actions/run-and-record-tests
         with:
           test-types: ${{ needs.discover-tests.outputs.test-types }}
           stack-config: ${{ matrix.client-type == 'library' && 'ci-tests' || 'server:ci-tests' }}
           provider: ${{ matrix.provider }}
           inference-mode: 'replay'
-
-      - name: Check Storage and Memory Available After Tests
-        if: ${{ always() }}
-        run: |
-          free -h
-          df -h
-
-      - name: Upload test logs on failure
-        if: ${{ failure() }}
-        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
-        with:
-          name: test-logs-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.provider }}-${{ matrix.client-type }}-${{ matrix.python-version }}-${{ matrix.client-version }}
-          path: |
-            *.log
-          retention-days: 1

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

@@ -0,0 +1,141 @@
+name: Vision Inference Integration Tests
+
+run-name: Run vision inference integration test suite from tests/integration/inference
+
+on:
+  push:
+    branches: [ main ]
+  pull_request_target:
+    branches: [ main ]
+    types: [opened, synchronize, labeled]
+    paths:
+      - 'llama_stack/**'
+      - 'tests/**'
+      - 'uv.lock'
+      - 'pyproject.toml'
+      - '.github/workflows/integration-vision-tests.yml' # This workflow
+      - '.github/actions/setup-ollama/action.yml'
+      - '.github/actions/setup-test-environment/action.yml'
+      - '.github/actions/run-and-record-tests/action.yml'
+  workflow_dispatch:
+    inputs:
+      test-all-client-versions:
+        description: 'Test against both the latest and published versions'
+        type: boolean
+        default: false
+      force-inference-mode:
+        description: 'Force inference mode (record or replay)'
+        type: string
+        default: ''
+
+concurrency:
+  # This creates three concurrency groups:
+  #   ${{ github.workflow }}-${{ github.ref }}-rerecord (for valid triggers with re-record-tests label)
+  #   ${{ github.workflow }}-${{ github.ref }}-replay (for valid triggers without re-record-tests label)
+  #   ${{ github.workflow }}-${{ github.ref }}-no-run (for invalid triggers that will be skipped)
+  # The "no-run" group ensures that irrelevant label events don't interfere with the real workflows.
+  group: >-
+    ${{ github.workflow }}-${{ github.ref }}-${{
+    ((github.event.action == 'opened' || github.event.action == 'synchronize') && 'replay') ||
+    ((github.event.action == 'labeled' && contains(github.event.pull_request.labels.*.name, 're-record-tests')) && 'rerecord' ||
+    'no-run')
+    }}
+  cancel-in-progress: true
+
+jobs:
+  discover-tests:
+    if: |
+      github.event.action == 'opened' ||
+      github.event.action == 'synchronize' ||
+      (github.event.action == 'labeled' && contains(github.event.pull_request.labels.*.name, 're-record-tests'))
+    runs-on: ubuntu-latest
+    outputs:
+      rerecord-tests: ${{ steps.check-rerecord-tests.outputs.rerecord-tests }}
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Check if re-record-tests label exists
+        id: check-rerecord-tests
+        run: |
+          if [[ "${{ inputs.force-inference-mode }}" == "record" ]]; then
+            echo "rerecord-tests=true" >> $GITHUB_OUTPUT
+          elif [[ "${{ inputs.force-inference-mode }}" == "replay" ]]; then
+            echo "rerecord-tests=false" >> $GITHUB_OUTPUT
+          else
+            if [[ "${{ contains(github.event.pull_request.labels.*.name, 're-record-tests') }}" == "true" ]]; then
+              echo "rerecord-tests=true" >> $GITHUB_OUTPUT
+            else
+              echo "rerecord-tests=false" >> $GITHUB_OUTPUT
+            fi
+          fi
+
+  record-tests:
+    # Sequential job for recording to avoid SQLite conflicts
+    if: ${{ needs.discover-tests.outputs.rerecord-tests == 'true' }}
+    needs: discover-tests
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: write
+      pull-requests: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          ref: ${{ github.event.pull_request.head.ref }}
+          fetch-depth: 0
+
+      - name: Setup test environment
+        uses: ./.github/actions/setup-test-environment
+        with:
+          python-version: "3.12"  # Use single Python version for recording
+          client-version: "latest"
+          provider: 'ollama'
+          run-vision-tests: 'true'
+
+      - name: Run and record tests
+        uses: ./.github/actions/run-and-record-tests
+        with:
+          test-types: '["vision"]'
+          stack-config: 'server:ci-tests'  # re-recording must be done in server mode
+          provider: 'ollama'
+          inference-mode: 'record'
+          run-vision-tests: 'true'
+
+  run-replay-mode-tests:
+    # Skip this job if we're in recording mode (handled by record-tests job)
+    if: ${{ needs.discover-tests.outputs.rerecord-tests != 'true' }}
+    needs: discover-tests
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+      matrix:
+        client-type: [library]
+        provider: [ollama]
+        python-version: ["3.12"]
+        client-version: ["latest"]
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Setup test environment
+        uses: ./.github/actions/setup-test-environment
+        with:
+          python-version: ${{ matrix.python-version }}
+          client-version: ${{ matrix.client-version }}
+          provider: ${{ matrix.provider }}
+          run-vision-tests: 'true'
+
+      - name: Run and record tests
+        uses: ./.github/actions/run-and-record-tests
+        with:
+          test-types: '["vision"]'
+          stack-config: ${{ matrix.client-type == 'library' && 'ci-tests' || 'server:ci-tests' }}
+          provider: ${{ matrix.provider }}
+          inference-mode: 'replay'
+          run-vision-tests: 'true'