From f2250ef96d63a0a3d79900b92d790d1fee7d72ca Mon Sep 17 00:00:00 2001
From: shamoon <4887959+shamoon@users.noreply.github.com>
Date: Wed, 26 Aug 2026 09:30:24 -0700
Subject: [PATCH] The LLM-generated test for that last thing

---
 src/documents/tests/test_caching.py | 63 +++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

diff --git a/src/documents/tests/test_caching.py b/src/documents/tests/test_caching.py
index 32460a47c..d5ee9cc35 100644
--- a/src/documents/tests/test_caching.py
+++ b/src/documents/tests/test_caching.py
@@ -3,8 +3,11 @@ from concurrent.futures import ThreadPoolExecutor
 from threading import Event
 from threading import Lock
 
+import pytest
+
 from documents.caching import StoredLRUCache
 from documents.caching import retrieve_llm_suggestions
+from paperless_ai.exceptions import LLMTimeoutError
 
 
 def test_lru_cache_entries() -> None:
@@ -103,3 +106,63 @@ def test_llm_suggestions_are_generated_once_for_concurrent_requests(mocker) -> N
 
     assert calls == 1
     mock_get_classification.assert_called_once_with(document, user, None)
+
+
+def test_llm_suggestions_waiter_does_not_rerun_a_failed_generation(mocker) -> None:
+    """
+    A request queued behind a generation that fails should give up, not take
+    its turn at re-running a query that just failed.
+    """
+    generation_started = Event()
+    fail_generation = Event()
+    waiter_started = Event()
+    call_lock = Lock()
+    calls = 0
+    document = mocker.Mock(pk=43)
+    user = mocker.Mock()
+
+    def generate(*args) -> dict:
+        nonlocal calls
+        with call_lock:
+            calls += 1
+        generation_started.set()
+        assert fail_generation.wait(timeout=2)
+        raise ValueError("Unknown model")
+
+    def wait_for_generation(_interval: float) -> None:
+        waiter_started.set()
+        assert fail_generation.wait(timeout=2)
+
+    mocker.patch(
+        "paperless_ai.ai_classifier.get_ai_document_classification",
+        side_effect=generate,
+    )
+    mocker.patch("documents.caching.time.sleep", side_effect=wait_for_generation)
+
+    with ThreadPoolExecutor(max_workers=2) as executor:
+        first = executor.submit(
+            retrieve_llm_suggestions,
+            document,
+            user,
+            None,
+            backend="ollama:model",
+            lock_timeout=10,
+        )
+        assert generation_started.wait(timeout=2)
+        second = executor.submit(
+            retrieve_llm_suggestions,
+            document,
+            user,
+            None,
+            backend="ollama:model",
+            lock_timeout=10,
+        )
+        assert waiter_started.wait(timeout=2)
+        fail_generation.set()
+
+        with pytest.raises(ValueError, match="Unknown model"):
+            first.result(timeout=2)
+        with pytest.raises(LLMTimeoutError):
+            second.result(timeout=2)
+
+    assert calls == 1