ci: aggregate checks with guardian (#20635)

(cherry picked from commit 02e2668)

Author: Borda

.github/checkgroup.yml

@@ -19,30 +19,7 @@ subprojects:
       - "!*.md"
       - "!**/*.md"
     checks:
-      - "pl-cpu (macOS-14, lightning, 3.9, 2.1, oldest)"
-      - "pl-cpu (macOS-14, lightning, 3.10, 2.1)"
-      - "pl-cpu (macOS-14, lightning, 3.11, 2.2.2)"
-      - "pl-cpu (macOS-14, lightning, 3.11, 2.3)"
-      - "pl-cpu (macOS-14, lightning, 3.12.7, 2.4.1)"
-      - "pl-cpu (macOS-14, lightning, 3.12.7, 2.5.1)"
-      - "pl-cpu (ubuntu-20.04, lightning, 3.9, 2.1, oldest)"
-      - "pl-cpu (ubuntu-20.04, lightning, 3.10, 2.1)"
-      - "pl-cpu (ubuntu-20.04, lightning, 3.11, 2.2.2)"
-      - "pl-cpu (ubuntu-20.04, lightning, 3.11, 2.3)"
-      - "pl-cpu (ubuntu-22.04, lightning, 3.12.7, 2.4.1)"
-      - "pl-cpu (ubuntu-22.04, lightning, 3.12.7, 2.5.1)"
-      - "pl-cpu (windows-2022, lightning, 3.9, 2.1, oldest)"
-      - "pl-cpu (windows-2022, lightning, 3.10, 2.1)"
-      - "pl-cpu (windows-2022, lightning, 3.11, 2.2.2)"
-      - "pl-cpu (windows-2022, lightning, 3.11, 2.3)"
-      - "pl-cpu (windows-2022, lightning, 3.12.7, 2.4.1)"
-      - "pl-cpu (windows-2022, lightning, 3.12.7, 2.5.1)"
-      - "pl-cpu (macOS-14, pytorch, 3.9, 2.1)"
-      - "pl-cpu (ubuntu-20.04, pytorch, 3.9, 2.1)"
-      - "pl-cpu (windows-2022, pytorch, 3.9, 2.1)"
-      - "pl-cpu (macOS-14, pytorch, 3.12.7, 2.5.1)"
-      - "pl-cpu (ubuntu-22.04, pytorch, 3.12.7, 2.5.1)"
-      - "pl-cpu (windows-2022, pytorch, 3.12.7, 2.5.1)"
+      - "pl-cpu-guardian" # aggregated check for all cases
 
   - id: "pytorch_lightning: Azure GPU"
     paths:
@@ -172,30 +149,7 @@ subprojects:
       - "!*.md"
       - "!**/*.md"
     checks:
-      - "fabric-cpu (macOS-14, lightning, 3.9, 2.1, oldest)"
-      - "fabric-cpu (macOS-14, lightning, 3.10, 2.1)"
-      - "fabric-cpu (macOS-14, lightning, 3.11, 2.2.2)"
-      - "fabric-cpu (macOS-14, lightning, 3.11, 2.3)"
-      - "fabric-cpu (macOS-14, lightning, 3.12.7, 2.4.1)"
-      - "fabric-cpu (macOS-14, lightning, 3.12.7, 2.5.1)"
-      - "fabric-cpu (ubuntu-20.04, lightning, 3.9, 2.1, oldest)"
-      - "fabric-cpu (ubuntu-20.04, lightning, 3.10, 2.1)"
-      - "fabric-cpu (ubuntu-20.04, lightning, 3.11, 2.2.2)"
-      - "fabric-cpu (ubuntu-20.04, lightning, 3.11, 2.3)"
-      - "fabric-cpu (ubuntu-22.04, lightning, 3.12.7, 2.4.1)"
-      - "fabric-cpu (ubuntu-22.04, lightning, 3.12.7, 2.5.1)"
-      - "fabric-cpu (windows-2022, lightning, 3.9, 2.1, oldest)"
-      - "fabric-cpu (windows-2022, lightning, 3.10, 2.1)"
-      - "fabric-cpu (windows-2022, lightning, 3.11, 2.2.2)"
-      - "fabric-cpu (windows-2022, lightning, 3.11, 2.3)"
-      - "fabric-cpu (windows-2022, lightning, 3.12.7, 2.4.1)"
-      - "fabric-cpu (windows-2022, lightning, 3.12.7, 2.5.1)"
-      - "fabric-cpu (macOS-14, fabric, 3.9, 2.1)"
-      - "fabric-cpu (ubuntu-20.04, fabric, 3.9, 2.1)"
-      - "fabric-cpu (windows-2022, fabric, 3.9, 2.1)"
-      - "fabric-cpu (macOS-14, fabric, 3.12.7, 2.5.1)"
-      - "fabric-cpu (ubuntu-22.04, fabric, 3.12.7, 2.5.1)"
-      - "fabric-cpu (windows-2022, fabric, 3.12.7, 2.5.1)"
+      - "fabric-cpu-guardian" # aggregated check for all cases
 
   - id: "lightning_fabric: Azure GPU"
     paths:
@@ -259,27 +213,4 @@ subprojects:
       - "!*.md"
       - "!**/*.md"
     checks:
-      - "install-pkg (ubuntu-22.04, fabric, 3.9)"
-      - "install-pkg (ubuntu-22.04, fabric, 3.11)"
-      - "install-pkg (ubuntu-22.04, pytorch, 3.9)"
-      - "install-pkg (ubuntu-22.04, pytorch, 3.11)"
-      - "install-pkg (ubuntu-22.04, lightning, 3.9)"
-      - "install-pkg (ubuntu-22.04, lightning, 3.11)"
-      - "install-pkg (ubuntu-22.04, notset, 3.9)"
-      - "install-pkg (ubuntu-22.04, notset, 3.11)"
-      - "install-pkg (macOS-14, fabric, 3.9)"
-      - "install-pkg (macOS-14, fabric, 3.11)"
-      - "install-pkg (macOS-14, pytorch, 3.9)"
-      - "install-pkg (macOS-14, pytorch, 3.11)"
-      - "install-pkg (macOS-14, lightning, 3.9)"
-      - "install-pkg (macOS-14, lightning, 3.11)"
-      - "install-pkg (macOS-14, notset, 3.9)"
-      - "install-pkg (macOS-14, notset, 3.11)"
-      - "install-pkg (windows-2022, fabric, 3.9)"
-      - "install-pkg (windows-2022, fabric, 3.11)"
-      - "install-pkg (windows-2022, pytorch, 3.9)"
-      - "install-pkg (windows-2022, pytorch, 3.11)"
-      - "install-pkg (windows-2022, lightning, 3.9)"
-      - "install-pkg (windows-2022, lightning, 3.11)"
-      - "install-pkg (windows-2022, notset, 3.9)"
-      - "install-pkg (windows-2022, notset, 3.11)"
+      - "install-pkg-guardian" # aggregated check for all cases

.github/workflows/ci-pkg-install.yml

@@ -103,3 +103,17 @@ jobs:
           LIGHTING_TESTING: 1 # path for require wrapper
           PY_IGNORE_IMPORTMISMATCH: 1
         run: python -m pytest src/lit/${PKG_NAME} --ignore-glob="**/cli/*-template/**" --doctest-plus
+
+  install-pkg-guardian:
+    runs-on: ubuntu-latest
+    needs: install-pkg
+    if: always()
+    steps:
+      - run: echo "${{ needs.install-pkg.result }}"
+      - name: failing...
+        if: needs.install-pkg.result == 'failure'
+        run: exit 1
+      - name: cancelled or skipped...
+        if: contains(fromJSON('["cancelled", "skipped"]'), needs.install-pkg.result)
+        timeout-minutes: 1
+        run: sleep 90

.github/workflows/ci-tests-fabric.yml

@@ -186,3 +186,17 @@ jobs:
           flags: ${{ env.COVERAGE_SCOPE }},cpu,pytest,python${{ matrix.python-version }}
           name: CPU-coverage
           fail_ci_if_error: false
+
+  fabric-cpu-guardian:
+    runs-on: ubuntu-latest
+    needs: fabric-cpu
+    if: always()
+    steps:
+      - run: echo "${{ needs.fabric-cpu.result }}"
+      - name: failing...
+        if: needs.fabric-cpu.result == 'failure'
+        run: exit 1
+      - name: cancelled or skipped...
+        if: contains(fromJSON('["cancelled", "skipped"]'), needs.fabric-cpu.result)
+        timeout-minutes: 1
+        run: sleep 90

.github/workflows/ci-tests-pytorch.yml

@@ -223,3 +223,17 @@ jobs:
           flags: ${{ env.COVERAGE_SCOPE }},cpu,pytest-full,python${{ matrix.python-version }},pytorch${{ matrix.pytorch-version }}
           name: CPU-coverage
           fail_ci_if_error: false
+
+  pl-cpu-guardian:
+    runs-on: ubuntu-latest
+    needs: pl-cpu
+    if: always()
+    steps:
+      - run: echo "${{ needs.pl-cpu.result }}"
+      - name: failing...
+        if: needs.pl-cpu.result == 'failure'
+        run: exit 1
+      - name: cancelled or skipped...
+        if: contains(fromJSON('["cancelled", "skipped"]'), needs.pl-cpu.result)
+        timeout-minutes: 1
+        run: sleep 90