DEVX-149: fix: retry ansible-galaxy collection install on transient timeouts

README.md

@@ -87,7 +87,7 @@ extra index and list devx in your dependencies:
 ```toml
 [project]
 dependencies = [
-    "devx>=0.49.2",
+    "devx>=0.49.3",
 ]
 
 [tool.pip]
@@ -101,8 +101,8 @@ pip install -e .
 ```
 
 > **Note:** If your project requires a specific devx version, pin it in
-> `dependencies` (for example, `"devx==0.49.2"`) or use a version constraint
-> (for example, `"devx>=0.49.2,<0.50"`).
+> `dependencies` (for example, `"devx==0.49.3"`) or use a version constraint
+> (for example, `"devx>=0.49.3,<0.50"`).
 
 ### Optional extras
 

docs/index.md

@@ -74,14 +74,14 @@ Add devx to your `pyproject.toml` dependencies and configure the registry:
 ```toml
 [project]
 dependencies = [
-    "devx>=0.49.2",
+    "devx>=0.49.3",
 ]
 
 [tool.pip]
 extra-index-url = "https://git.oblachno.oblachno.fyi/api/packages/oblachno-oss/pypi/simple"
 ```
 
-Pin a specific version if needed: `"devx==0.49.2"` or `"devx>=0.49.2,<0.50"`.
+Pin a specific version if needed: `"devx==0.49.3"` or `"devx>=0.49.3,<0.50"`.
 
 ### Optional extras
 

docs/user/getting-started.md

@@ -48,12 +48,12 @@ Add devx to your `pyproject.toml`:
 ```toml
 [project]
 dependencies = [
-    "devx>=0.49.2",
+    "devx>=0.49.3",
 ]
 
 [project.optional-dependencies]
 dev = [
-    "devx>=0.49.2",
+    "devx>=0.49.3",
 ]
 ```
 

src/devx/__init__.py

@@ -1,3 +1,3 @@
 """devx — reusable development and CI/CD tools for oblachno-oss projects."""
 
-__version__ = "0.49.2"
+__version__ = "0.49.3"

src/devx/tools/setup.py

@@ -15,6 +15,7 @@ from pathlib import Path
 
 import click
 from dotenv import load_dotenv  # pyright: ignore[reportMissingImports,reportUnknownVariableType]
+from tenacity import retry, stop_after_attempt, wait_exponential
 
 from devx.tokens import get_developer_token
 
@@ -56,13 +57,22 @@ def _install_pre_commit_hooks(bin_dir: str) -> None:
 
 
 def _install_ansible_collections(bin_dir: str) -> None:
-    """Install required Ansible Galaxy collections if requirements exist."""
+    """Install required Ansible Galaxy collections if requirements exist.
+
+    Retries up to 3 times with exponential backoff to handle transient
+    network timeouts when contacting galaxy.ansible.com.
+    """
     galaxy = shutil.which("ansible-galaxy") or str(Path(bin_dir) / "ansible-galaxy")
     requirements = Path("ansible/requirements.yml")
     if not requirements.exists():
         click.echo("  ansible/requirements.yml not found — skipping collections.")
         return
-    _run([galaxy, "collection", "install", "-r", str(requirements)])
+
+    @retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=2, min=2, max=10), reraise=True)
+    def _do_install() -> None:
+        _run([galaxy, "collection", "install", "-r", str(requirements)])
+
+    _do_install()
 
 
 def _configure_tea_login() -> None:

tests/unit/test_setup.py

@@ -114,6 +114,49 @@ class TestInstallAnsibleCollections:
         _install_ansible_collections(".venv/bin")
         mock_run.assert_not_called()
 
+    @patch("tenacity.nap.time.sleep")
+    @patch("devx.tools.setup.shutil.which", return_value="/usr/local/bin/ansible-galaxy")
+    @patch("devx.tools.setup._run")
+    def test_retries_on_transient_failure(
+        self, mock_run: MagicMock, mock_which: MagicMock, mock_sleep: MagicMock, tmp_path: Path
+    ) -> None:
+        """ansible-galaxy install should retry on transient network errors."""
+        import subprocess as _subprocess
+
+        req = tmp_path / "ansible" / "requirements.yml"
+        req.parent.mkdir(parents=True)
+        req.write_text("collections: []")
+        # First call fails (timeout), second succeeds
+        mock_run.side_effect = [
+            _subprocess.CalledProcessError(1, ["ansible-galaxy", "collection", "install"]),
+            None,
+        ]
+        with patch("devx.tools.setup.Path") as mock_path:
+            mock_path.return_value.exists.return_value = True
+            mock_path.return_value.__str__ = lambda _: str(req)
+            _install_ansible_collections(".venv/bin")
+        assert mock_run.call_count == 2
+
+    @patch("tenacity.nap.time.sleep")
+    @patch("devx.tools.setup.shutil.which", return_value="/usr/local/bin/ansible-galaxy")
+    @patch("devx.tools.setup._run")
+    def test_exhausts_retries_then_raises(
+        self, mock_run: MagicMock, mock_which: MagicMock, mock_sleep: MagicMock, tmp_path: Path
+    ) -> None:
+        """After 3 attempts, the error should propagate."""
+        import subprocess as _subprocess
+
+        req = tmp_path / "ansible" / "requirements.yml"
+        req.parent.mkdir(parents=True)
+        req.write_text("collections: []")
+        mock_run.side_effect = _subprocess.CalledProcessError(1, ["ansible-galaxy"])
+        with patch("devx.tools.setup.Path") as mock_path:
+            mock_path.return_value.exists.return_value = True
+            mock_path.return_value.__str__ = lambda _: str(req)
+            with pytest.raises(_subprocess.CalledProcessError):
+                _install_ansible_collections(".venv/bin")
+        assert mock_run.call_count == 3
+
 
 class TestConfigureTeaLogin:
     @patch("devx.tools.setup.shutil.which", return_value=None)