DEVX-143: fix: add retry logic to TeaCLI for transient HTTP errors (502/503/504/429)

src/devx/gitea_cli.py

@@ -40,21 +40,35 @@ Usage::
 from __future__ import annotations
 
 import json
+import logging
 import shutil
 import subprocess  # nosec B404
 from typing import Any
 
 import click
+from tenacity import (
+    before_sleep_log,
+    retry,
+    retry_if_exception_type,
+    stop_after_attempt,
+    wait_exponential,
+)
 
-from devx.config import GITEA_API_URL
+from devx.config import GITEA_API_URL, MAX_RETRIES, RETRY_BACKOFF_BASE, RETRY_STATUS_CODES
 from devx.i18n import _
 from devx.tokens import get_ci_token
 
+logger = logging.getLogger("gitea_cli")
+
 
 class TeaCLIError(Exception):
     """Raised when a tea CLI command fails."""
 
 
+class _TransientTeaError(TeaCLIError):
+    """Tea CLI error caused by a transient HTTP status (502/503/504/429)."""
+
+
 def configure_tea_login(login_name: str = "devx") -> None:
     """Configure tea CLI login from CI_GITEA_API_TOKEN and DEVX_GITEA_API_URL.
 
@@ -140,6 +154,10 @@ class TeaCLI:
     def _run(self, args: list[str], json_output: bool = True) -> str:
         """Run a tea command and return stdout.
 
+        Retries up to ``MAX_RETRIES`` times on transient HTTP errors
+        (502/503/504/429) detected in stderr/stdout, with exponential
+        backoff. Non-transient errors fail immediately.
+
         Args:
             args: Command arguments (without the leading ``tea``).
             json_output: If True, append ``--output json`` to the command.
@@ -148,30 +166,50 @@ class TeaCLI:
             stdout as a string.
 
         Raises:
-            TeaCLIError: If the command fails.
+            TeaCLIError: If the command fails after retries are exhausted.
         """
         cmd = [self._tea, *args]
         if json_output:
             cmd.extend(["--output", "json"])
+
+        def _execute() -> str:
+            try:
+                result = subprocess.run(  # nosec B603
+                    cmd,
+                    capture_output=True,
+                    text=True,
+                    check=False,
+                )
+            except FileNotFoundError as e:
+                raise TeaCLIError(f"tea binary not found ('{self._tea}'). Install tea or add it to PATH.") from e
+            if result.returncode != 0:
+                parts = [
+                    f"tea command failed (rc={result.returncode}): {' '.join(args)}",
+                    f"stdout: {result.stdout.strip()}" if result.stdout.strip() else "",
+                    f"stderr: {result.stderr.strip()}" if result.stderr.strip() else "",
+                ]
+                msg = "\n".join(p for p in parts if p)
+                combined = f"{result.stdout} {result.stderr}".lower()
+                if any(str(code) in combined for code in RETRY_STATUS_CODES):
+                    raise _TransientTeaError(msg)
+                raise TeaCLIError(msg)
+            return result.stdout.strip()
+
+        retry_decorator = retry(
+            stop=stop_after_attempt(MAX_RETRIES),
+            wait=wait_exponential(
+                multiplier=RETRY_BACKOFF_BASE,
+                min=RETRY_BACKOFF_BASE,
+                max=RETRY_BACKOFF_BASE**MAX_RETRIES,
+            ),
+            retry=retry_if_exception_type(_TransientTeaError),
+            before_sleep=before_sleep_log(logger, logging.WARNING),
+            reraise=True,
+        )
         try:
-            result = subprocess.run(  # nosec B603
-                cmd,
-                capture_output=True,
-                text=True,
-                check=False,
-            )
-        except FileNotFoundError as e:
-            raise TeaCLIError(f"tea binary not found ('{self._tea}'). Install tea or add it to PATH.") from e
-        if result.returncode != 0:
-            # tea writes some errors to stdout (for example, "no available
-            # login"), so include both stdout and stderr for debugging.
-            parts = [
-                f"tea command failed (rc={result.returncode}): {' '.join(args)}",
-                f"stdout: {result.stdout.strip()}" if result.stdout.strip() else "",
-                f"stderr: {result.stderr.strip()}" if result.stderr.strip() else "",
-            ]
-            raise TeaCLIError("\n".join(p for p in parts if p))
-        return result.stdout.strip()
+            return retry_decorator(_execute)()
+        except _TransientTeaError as e:
+            raise TeaCLIError(str(e)) from e
 
     def _run_raw(self, args: list[str]) -> str:
         """Run a tea command without JSON output and return stdout."""

tests/unit/test_gitea_cli.py

@@ -7,7 +7,13 @@ from unittest.mock import MagicMock, patch
 
 import pytest
 
-from devx.gitea_cli import TeaCLI, TeaCLIError, _extract_issue_number, _extract_pr_number, configure_tea_login
+from devx.gitea_cli import (
+    TeaCLI,
+    TeaCLIError,
+    _extract_issue_number,
+    _extract_pr_number,
+    configure_tea_login,
+)
 
 
 class TestExtractIssueNumber:
@@ -119,6 +125,46 @@ class TestTeaCLIRun:
         cmd = mock_run.call_args[0][0]
         assert "--output" not in cmd
 
+    def test_run_retries_on_502(self) -> None:
+        """Transient 502 errors should be retried, then succeed."""
+        cli = TeaCLI(tea_bin="/fake/tea")
+        fail_result = MagicMock(returncode=1, stdout="", stderr="502 Bad Gateway")
+        success_result = MagicMock(returncode=0, stdout='[{"id": 1}]', stderr="")
+        with patch("subprocess.run", side_effect=[fail_result, success_result]) as mock_run:
+            with patch("tenacity.nap.time.sleep"):
+                output = cli._run(["labels", "list"])
+        assert output == '[{"id": 1}]'
+        assert mock_run.call_count == 2
+
+    def test_run_retries_on_503_then_fails(self) -> None:
+        """If all retries are exhausted on 503, raise TeaCLIError."""
+        cli = TeaCLI(tea_bin="/fake/tea")
+        fail_result = MagicMock(returncode=1, stdout="", stderr="503 Service Unavailable")
+        with patch("subprocess.run", return_value=fail_result):
+            with patch("tenacity.nap.time.sleep"):
+                with pytest.raises(TeaCLIError, match="503"):
+                    cli._run(["issues", "create"])
+        # MAX_RETRIES=3, so 3 attempts total
+
+    def test_run_no_retry_on_non_transient_error(self) -> None:
+        """Non-transient errors (e.g. auth) should fail immediately without retry."""
+        cli = TeaCLI(tea_bin="/fake/tea")
+        fail_result = MagicMock(returncode=1, stdout="", stderr="auth error")
+        with patch("subprocess.run", return_value=fail_result) as mock_run:
+            with pytest.raises(TeaCLIError, match="auth error"):
+                cli._run(["labels", "list"])
+        assert mock_run.call_count == 1
+
+    def test_run_retries_on_429_in_stdout(self) -> None:
+        """429 rate limit in stdout should trigger retry."""
+        cli = TeaCLI(tea_bin="/fake/tea")
+        fail_result = MagicMock(returncode=1, stdout="429 Too Many Requests", stderr="")
+        success_result = MagicMock(returncode=0, stdout="ok", stderr="")
+        with patch("subprocess.run", side_effect=[fail_result, success_result]):
+            with patch("tenacity.nap.time.sleep"):
+                output = cli._run(["releases", "create"])
+        assert output == "ok"
+
 
 class TestRepoArg:
     def test_with_repo_arg(self) -> None: