[no-ci] coverage: fix Linux git ownership and add Windows stack wrapper

.github/workflows/coverage.yml

@@ -68,6 +68,10 @@ jobs:
         with:
           fetch-depth: 0
 
+      - name: Fix workspace ownership
+        run: |
+          chown -R $(id -u):$(id -g) "$GITHUB_WORKSPACE"
+
       - name: Install dependencies
         uses: ./.github/actions/install_unix_deps
         continue-on-error: false
@@ -342,46 +346,25 @@ jobs:
           cd "${{ steps.install-root.outputs.INSTALL_ROOT }}"
           "$GITHUB_WORKSPACE/.venv/Scripts/pytest" -v --cov=./cuda --cov-append --cov-context=test --cov-config="$GITHUB_WORKSPACE/.coveragerc" "$GITHUB_WORKSPACE/cuda_pathfinder/tests"
 
+      # Cython linetrace under coverage on Windows needs more stack than the
+      # default 1 MB thread size.  The helper runs pytest on an 8 MB thread.
       - name: Run cuda.bindings tests (with 8MB stack)
         continue-on-error: true
         run: |
-          cd "${{ steps.install-root.outputs.INSTALL_ROOT }}"
-          # Run pytest in 8MB stack thread (Cython linetrace requirement)
-          "$GITHUB_WORKSPACE/.venv/Scripts/python" << PYTEST_EOF
-          import os
-          import sys
-          import threading
-          import pytest
-
-          os.chdir(r'${{ steps.install-root.outputs.INSTALL_ROOT }}')
-          threading.stack_size(8 * 1024 * 1024)
-          result = {'code': 1}
-
-          def _run():
-              workspace = os.environ['GITHUB_WORKSPACE']
-              result['code'] = pytest.main([
-                  '-v',
-                  '--cov=./cuda',
-                  '--cov-append',
-                  '--cov-context=test',
-                  f'--cov-config={workspace}/.coveragerc',
-                  f'{workspace}/cuda_bindings/tests'
-              ])
-
-          t = threading.Thread(target=_run)
-          t.start()
-          t.join()
-
-          print(f'Bindings tests exit code: {result["code"]}')
-          # Exit with actual code (continue-on-error handles it)
-          sys.exit(result['code'])
-          PYTEST_EOF
+          "$GITHUB_WORKSPACE/.venv/Scripts/python" "$GITHUB_WORKSPACE/ci/tools/run_pytest_with_stack.py" \
+            --cwd "${{ steps.install-root.outputs.INSTALL_ROOT }}" \
+            -v --cov=./cuda --cov-append --cov-context=test \
+            --cov-config="$GITHUB_WORKSPACE/.coveragerc" \
+            "$GITHUB_WORKSPACE/cuda_bindings/tests"
 
-      - name: Run cuda.core tests
+      - name: Run cuda.core tests (with 8MB stack)
         continue-on-error: true
         run: |
-          cd "${{ steps.install-root.outputs.INSTALL_ROOT }}"
-          "$GITHUB_WORKSPACE/.venv/Scripts/pytest" -v --cov=./cuda --cov-append --cov-context=test --cov-config="$GITHUB_WORKSPACE/.coveragerc" "$GITHUB_WORKSPACE/cuda_core/tests"
+          "$GITHUB_WORKSPACE/.venv/Scripts/python" "$GITHUB_WORKSPACE/ci/tools/run_pytest_with_stack.py" \
+            --cwd "${{ steps.install-root.outputs.INSTALL_ROOT }}" \
+            -v --cov=./cuda --cov-append --cov-context=test \
+            --cov-config="$GITHUB_WORKSPACE/.coveragerc" \
+            "$GITHUB_WORKSPACE/cuda_core/tests"
 
       - name: Copy Windows coverage file to workspace
         run: |

ci/tools/run_pytest_with_stack.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python3
+
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+#
+# SPDX-License-Identifier: Apache-2.0
+
+"""Run pytest on a thread with a larger stack size.
+
+Cython linetrace instrumentation under coverage on Windows can exceed the
+default 1 MB thread stack.  This helper spawns a single worker thread with
+a configurable stack (default 8 MB) so the rest of the CI workflow stays
+readable.
+
+Usage:
+    python run_pytest_with_stack.py [--stack-mb N] [--cwd DIR] [pytest args ...]
+"""
+
+import argparse
+import concurrent.futures
+import os
+import sys
+import threading
+
+import pytest
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument(
+        "--stack-mb",
+        type=int,
+        default=8,
+        help="Thread stack size in megabytes (default: 8)",
+    )
+    parser.add_argument(
+        "--cwd",
+        default=None,
+        help="Working directory for the test run",
+    )
+    args, pytest_args = parser.parse_known_args()
+
+    if args.cwd:
+        os.chdir(args.cwd)
+
+    threading.stack_size(args.stack_mb * 1024 * 1024)
+
+    with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
+        code = pool.submit(pytest.main, pytest_args).result()
+
+    sys.exit(code)
+
+
+if __name__ == "__main__":
+    main()