Break up unit tests into separate runners for python and scala

.github/workflows/on-pr-comment.yml

@@ -39,19 +39,19 @@ jobs:
         pr_number: ${{ github.event.issue.number }}
         message: ${{ steps.parse_commands.outputs.help_message }}
 
-  unit-test:
-    if: ${{ github.event.issue.pull_request && contains(github.event.comment.body, '/unit_test') }}
+  unit-test-python:
+    if: ${{ github.event.issue.pull_request && (contains(github.event.comment.body, '/unit_test_py') || endsWith(github.event.comment.body, '/unit_test')) }}
     runs-on: ubuntu-latest
     # TODO(kmonte): Reduce this :(
     timeout-minutes: 120
     steps:
-    - name: Run Unit Tests
+    - name: Run Python Unit Tests
       uses: snapchat/gigl/.github/actions/run-command-on-pr@main
       with:
         github-token: ${{ secrets.GITHUB_TOKEN }}
         pr_number: ${{ github.event.issue.number }}
         should_leave_progress_comments: "true"
-        descriptive_workflow_name: "Unit Test"
+        descriptive_workflow_name: "Python Unit Test"
         setup_gcloud: "true"
         # We use cloud run here instead of using github hosted runners because of limitation of tests
         # using GFile library (a.k.a anything that does IO w/ Tensorflow). GFile does not understand
@@ -62,7 +62,28 @@ jobs:
         workload_identity_provider: ${{ secrets.WORKLOAD_IDENTITY_PROVIDER }}
         gcp_service_account_email: ${{ secrets.GCP_SERVICE_ACCOUNT_EMAIL }}
         command: |
-          make unit_test
+          make unit_test_py
+
+  unit-test-scala:
+    if: ${{ github.event.issue.pull_request && (contains(github.event.comment.body, '/unit_test_scala') || endsWith(github.event.comment.body, '/unit_test')) }}
+    runs-on: ubuntu-latest
+    timeout-minutes: 20
+    steps:
+    - name: Run Scala Unit Tests
+      uses: snapchat/gigl/.github/actions/run-command-on-pr@main
+      with:
+        github-token: ${{ secrets.GITHUB_TOKEN }}
+        pr_number: ${{ github.event.issue.number }}
+        should_leave_progress_comments: "true"
+        descriptive_workflow_name: "Scala Unit Test"
+        setup_gcloud: "true"
+        use_cloud_run: "true"
+        gcp_project_id: ${{ vars.GCP_PROJECT_ID }}
+        workload_identity_provider: ${{ secrets.WORKLOAD_IDENTITY_PROVIDER }}
+        gcp_service_account_email: ${{ secrets.GCP_SERVICE_ACCOUNT_EMAIL }}
+        command: |
+          make unit_test_scala
+
   integration-test:
     if: ${{ github.event.issue.pull_request && contains(github.event.comment.body, '/integration_test') }}
     runs-on: ubuntu-latest
@@ -83,6 +104,7 @@ jobs:
         gcp_service_account_email: ${{ secrets.GCP_SERVICE_ACCOUNT_EMAIL }}
         command: |
             make integration_test
+
   integration-e2e-test:
     if: ${{ github.event.issue.pull_request && contains(github.event.comment.body, '/e2e_test') }}
     runs-on: ubuntu-latest

.github/workflows/on-pr-merge.yml

@@ -16,7 +16,7 @@ permissions:
   issues: 'write'
 
 jobs:
-  ci-unit-test:
+  ci-unit-test-python:
     # Because of limitation discussed https://github.com/orgs/community/discussions/46757#discussioncomment-4912738
     # We skip when the workflow is triggered by a pull_request event; otherwise we will run the check twice.
     # Once before it gets into the merge queue and once when it is in the merge queue.
@@ -32,14 +32,37 @@ jobs:
           gcp_project_id: ${{ vars.GCP_PROJECT_ID }}
           workload_identity_provider: ${{ secrets.workload_identity_provider }}
           gcp_service_account_email: ${{ secrets.gcp_service_account_email }}
-    - name: Run Unit Tests
+    - name: Run Python Unit Tests
       # We use cloud run here instead of using github hosted runners because of limitation of tests
       # using GFile library (a.k.a anything that does IO w/ Tensorflow). GFile does not understand
       # how to leverage Workload Identity Federation to read assets from GCS, et al. See:
       # https://github.com/tensorflow/tensorflow/issues/57104
       uses: snapchat/gigl/.github/actions/run-cloud-run-command-on-active-checkout@main
       with:
-        cmd: "make unit_test"
+        cmd: "make unit_test_py"
+        service_account:  ${{ secrets.gcp_service_account_email }}
+        project:  ${{ vars.GCP_PROJECT_ID }}
+
+  ci-unit-test-scala:
+    # Because of limitation discussed https://github.com/orgs/community/discussions/46757#discussioncomment-4912738
+    # We skip when the workflow is triggered by a pull_request event; otherwise we will run the check twice.
+    # Once before it gets into the merge queue and once when it is in the merge queue.
+    # Our tests take a long time to run, so this is not ideal.
+    if: github.event_name == 'merge_group'
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Setup development environment
+      uses: snapchat/gigl/.github/actions/setup-python-tools@main
+      with:
+          setup_gcloud: "true"
+          gcp_project_id: ${{ vars.GCP_PROJECT_ID }}
+          workload_identity_provider: ${{ secrets.workload_identity_provider }}
+          gcp_service_account_email: ${{ secrets.gcp_service_account_email }}
+    - name: Run Scala Unit Tests
+      uses: snapchat/gigl/.github/actions/run-cloud-run-command-on-active-checkout@main
+      with:
+        cmd: "make unit_test_scala"
         service_account:  ${{ secrets.gcp_service_account_email }}
         project:  ${{ vars.GCP_PROJECT_ID }}