Retry: sleep_for_retry uses max(wait, delay_max) — inflates small Retry-After to delay_max (60s floor) (#860)

.github/workflows/engineer-bot-followup.yml

@@ -94,6 +94,15 @@ jobs:
         with:
           python-version: '3.11'
 
+      # setup-poetry runs `poetry lock` (to reconcile the lock with the internal
+      # JFrog source it injects), which REWRITES tracked poetry.lock / pyproject.toml
+      # in the working tree. The venv is already built, so the tree no longer needs
+      # that churn — revert it, else the followup's fixup commit (or its leftover
+      # check) would sweep up these bot-untouched dirty files. Keep ONLY the
+      # agent's edits in the tree.
+      - name: Revert poetry lock/pyproject churn (keep only the agent's edits)
+        run: git checkout -- poetry.lock pyproject.toml || true
+
       # Shared prelude: mint the engineer-bot token (pushes fixup commits, posts
       # replies) + the engine-scoped token, set up Node, install the engine.
       - name: Bot prelude (tokens + Node + engine install)

.github/workflows/engineer-bot.yml

@@ -81,6 +81,15 @@ jobs:
         with:
           python-version: '3.11'
 
+      # setup-poetry runs `poetry lock` (to reconcile the lock with the internal
+      # JFrog source it injects), which REWRITES tracked poetry.lock / pyproject.toml
+      # in the working tree. The venv is already built, so the tree no longer needs
+      # that churn — revert it, else publish's leftover safety-net sees these
+      # bot-untouched dirty files and refuses to open the PR (they aren't in the
+      # agent's touched_files). Keep ONLY the agent's edits in the tree.
+      - name: Revert poetry lock/pyproject churn (keep only the agent's edits)
+        run: git checkout -- poetry.lock pyproject.toml || true
+
       # Shared prelude: mint the engineer-bot token (pushes the fix branch,
       # comments) + the engine-scoped token, set up Node, install the pinned
       # engine (PAT-free). `token` output is used by the steps below.

src/databricks/sql/auth/retry.py

@@ -297,7 +297,7 @@ def sleep_for_retry(self, response: BaseHTTPResponse) -> bool:
         else:
             proposed_wait = self.get_backoff_time()
 
-        proposed_wait = max(proposed_wait, self.delay_max)
+        proposed_wait = min(proposed_wait, self.delay_max)
         self.check_proposed_wait(proposed_wait)
         logger.debug(f"Retrying after {proposed_wait} seconds")
         time.sleep(proposed_wait)

tests/unit/test_retry.py

@@ -39,14 +39,23 @@ def test_sleep__no_retry_after(self, t_mock, retry_policy, error_history):
         retry_policy.history = [error_history, error_history]
         retry_policy.sleep(HTTPResponse(status=503))
 
-        expected_backoff_time = max(
-            self.calculate_backoff_time(
-                0, retry_policy.delay_min, retry_policy.delay_max
-            ),
-            retry_policy.delay_max,
+        expected_backoff_time = self.calculate_backoff_time(
+            0, retry_policy.delay_min, retry_policy.delay_max
         )
         t_mock.assert_called_with(expected_backoff_time)
 
+    @patch("time.sleep")
+    def test_sleep__retry_after_header_honored_not_inflated(
+        self, t_mock, retry_policy, error_history
+    ):
+        # A small server Retry-After must be honored as-is (capped at delay_max),
+        # not inflated up to delay_max.
+        retry_policy._retry_start_time = time.time()
+        retry_policy.history = [error_history, error_history]
+        retry_policy.sleep(HTTPResponse(status=503, headers={"Retry-After": "2"}))
+
+        t_mock.assert_called_with(2)
+
     @patch("time.sleep")
     def test_sleep__no_retry_after_header__multiple_retries(self, t_mock, retry_policy):
         num_attempts = retry_policy.stop_after_attempts_count
@@ -62,11 +71,8 @@ def test_sleep__no_retry_after_header__multiple_retries(self, t_mock, retry_poli
         expected_backoff_times = []
         for attempt in range(num_attempts):
             expected_backoff_times.append(
-                max(
-                    self.calculate_backoff_time(
-                        attempt, retry_policy.delay_min, retry_policy.delay_max
-                    ),
-                    retry_policy.delay_max,
+                self.calculate_backoff_time(
+                    attempt, retry_policy.delay_min, retry_policy.delay_max
                 )
             )