更新

backend/tests/test_batch_start_queue.py

@@ -87,6 +87,42 @@ class BatchStartQueueTests(unittest.IsolatedAsyncioTestCase):
         self.assertEqual(maximum_active, 2)
         self.assertEqual(active, 0)
 
+    async def test_default_concurrency_admits_more_than_two_accounts(self):
+        with patch.dict(os.environ, {}, clear=False):
+            os.environ.pop("KEFU_BATCH_START_CONCURRENCY", None)
+            queue = BatchStartQueue(lambda _account_id: None)
+        self.assertEqual(queue.concurrency, batch_start_module.DEFAULT_CONCURRENCY)
+        self.assertGreaterEqual(queue.concurrency, 4)
+
+    async def test_dead_worker_is_replaced_so_width_never_shrinks(self):
+        """One crashed worker must not permanently narrow the queue.
+
+        Width used to be restored only when every worker had exited, so a
+        single unexpected worker death left later batches crawling through the
+        survivors until the process restarted.
+        """
+
+        async def handler(account_id: int) -> dict:
+            return {"message": f"started-{account_id}"}
+
+        queue = self._make_queue(handler, concurrency=3)
+        first = await queue.submit([91])
+        await self._wait_for_complete(queue, first["batch_id"])
+        self.assertEqual(len(queue._workers), 3)
+
+        casualty = queue._workers[0]
+        casualty.cancel()
+        await asyncio.gather(casualty, return_exceptions=True)
+
+        second = await queue.submit([92])
+        await self._wait_for_complete(queue, second["batch_id"])
+
+        self.assertEqual(len(queue._workers), 3)
+        self.assertNotIn(casualty, queue._workers)
+        self.assertTrue(all(not task.done() for task in queue._workers))
+        names = [task.get_name() for task in queue._workers]
+        self.assertEqual(len(set(names)), 3)
+
     async def test_submit_returns_while_handler_is_blocked(self):
         handler_started = asyncio.Event()
         release_handler = asyncio.Event()