Auto-retry live-API tests on transient upstream errors

.github/workflows/python-package.yml

@@ -13,9 +13,9 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - name: Set up Python 3.14
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: "3.14"
           cache: "pip"
@@ -36,9 +36,9 @@ jobs:
         python-version: ["3.9", "3.13", "3.14"]
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: ${{ matrix.python-version }}
           cache: "pip"

.github/workflows/python-publish.yml

@@ -21,9 +21,9 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v6
     - name: Set up Python
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v6
       with:
         python-version: '3.x'
         cache: 'pip'

.github/workflows/sphinx-docs.yml

@@ -11,11 +11,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           persist-credentials: false
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: "3.13"
           cache: "pip"

pyproject.toml

@@ -35,6 +35,7 @@ dataretrieval = ["py.typed"]
 test = [
   "pytest > 5.0.0",
   "pytest-cov[all]",
+  "pytest-rerunfailures",
   "coverage",
   "requests-mock",
   "ruff",

tests/conftest.py

@@ -0,0 +1,41 @@
+"""Auto-retry live-API tests on transient upstream errors.
+
+After PR #273, paginated ``waterdata`` getters propagate mid-walk HTTP
+errors (429 / 5xx / connection drops) instead of silently truncating the
+result. That's the correct behavior for users but makes any CI test that
+hits the live USGS Water Data API susceptible to flaking on a transient
+upstream blip — e.g. the HTTP 502 Bad Gateway that broke CI on PR #273's
+merge to main.
+
+Heuristic: any test that does NOT request the ``requests_mock`` fixture
+is treated as live and gets retried on transient-error patterns only.
+Library bugs raising other exception types still fail on the first try.
+"""
+
+import pytest
+
+# Anchored loosely — the failure trace embeds the exception message
+# after a long preamble.
+_TRANSIENT_PATTERNS = [
+    r"RuntimeError:\s*(?:429|5\d\d):",  # _raise_for_non_200 output
+    r"ConnectionError",  # requests/urllib3
+    r"ReadTimeout|ConnectTimeout|Timeout",
+]
+
+# 5 seconds is generous enough for a USGS upstream replica to recover
+# from a brief 5xx but short enough that CI doesn't drag.
+_RETRY_DELAY_SEC = 5
+_MAX_RERUNS = 2
+
+
+def pytest_collection_modifyitems(config, items):
+    for item in items:
+        if "requests_mock" in item.fixturenames:
+            continue
+        item.add_marker(
+            pytest.mark.flaky(
+                reruns=_MAX_RERUNS,
+                reruns_delay=_RETRY_DELAY_SEC,
+                only_rerun=_TRANSIENT_PATTERNS,
+            )
+        )