ci: optimize runner usage with conditional OS matrix and parallel limit

- Only run full OS matrix (ubuntu-24.04, macos-14, windows-latest) on main branch pushes
- PR branches use ubuntu-24.04 only to reduce runner wait time
- Add max-parallel: 2 to limit concurrent job execution

Author: kaisongli

.github/workflows/api_test.yml

@@ -44,8 +44,9 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: false
+      max-parallel: 2
       matrix:
-        os: [ubuntu-24.04, ubuntu-24.04-arm, macos-14, macos-15-intel, windows-latest]
+        os: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/main') && fromJSON('["ubuntu-24.04", "macos-14", "windows-latest"]') || fromJSON('["ubuntu-24.04"]') }}
 
     steps:
       - uses: actions/checkout@v6