feat(ci): introduce workflow for re-recording inference outputs (#3002)

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

@@ -0,0 +1,109 @@
+name: Integration Tests (Record)
+
+run-name: Run the integration test suite from tests/integration
+
+on:
+  pull_request:
+    branches: [ main ]
+    types: [opened, synchronize, labeled]
+    paths:
+      - 'llama_stack/**'
+      - 'tests/**'
+      - 'uv.lock'
+      - 'pyproject.toml'
+      - '.github/workflows/record-integration-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-provider:
+        description: 'Test against a specific provider'
+        type: string
+        default: 'ollama'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  discover-tests:
+    if: contains(github.event.pull_request.labels.*.name, 're-record-tests') ||
+      contains(github.event.pull_request.labels.*.name, 're-record-vision-tests')
+    runs-on: ubuntu-latest
+    outputs:
+      test-types: ${{ steps.generate-test-types.outputs.test-types }}
+      matrix-modes: ${{ steps.generate-test-types.outputs.matrix-modes }}
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Generate test types
+        id: generate-test-types
+        run: |
+          # Get test directories dynamically, excluding non-test directories
+          TEST_TYPES=$(find tests/integration -maxdepth 1 -mindepth 1 -type d -printf "%f\n" |
+            grep -Ev "^(__pycache__|fixtures|test_cases|recordings|post_training)$" |
+            sort | jq -R -s -c 'split("\n")[:-1]')
+          echo "test-types=$TEST_TYPES" >> $GITHUB_OUTPUT
+
+          labels=$(gh pr view ${{ github.event.pull_request.number }} --json labels --jq '.labels[].name')
+          echo "labels=$labels"
+
+          modes_array=()
+          if [[ $labels == *"re-record-vision-tests"* ]]; then
+            modes_array+=("vision")
+          fi
+          if [[ $labels == *"re-record-tests"* ]]; then
+            modes_array+=("non-vision")
+          fi
+
+          # Convert to JSON array
+          if [ ${#modes_array[@]} -eq 0 ]; then
+            matrix_modes="[]"
+          else
+            matrix_modes=$(printf '%s\n' "${modes_array[@]}" | jq -R -s -c 'split("\n")[:-1]')
+          fi
+          echo "matrix_modes=$matrix_modes"
+          echo "matrix-modes=$matrix_modes" >> $GITHUB_OUTPUT
+
+        env:
+          GH_TOKEN: ${{ github.token }}
+
+  record-tests:
+    needs: discover-tests
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        mode: ${{ fromJSON(needs.discover-tests.outputs.matrix-modes) }}
+
+    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: ${{ inputs.test-provider || 'ollama' }}
+          run-vision-tests: ${{ matrix.mode == 'vision' && 'true' || 'false' }}
+          inference-mode: 'record'
+
+      - 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 || 'ollama' }}
+          inference-mode: 'record'
+          run-vision-tests: ${{ matrix.mode == 'vision' && 'true' || 'false' }}