Preserve semantic note layouts and checkpoint on provider quota failures

tests/test_regressions.py

@@ -119,11 +119,13 @@ def test_automatic_glossary_does_not_force_generic_senses_or_implicit_surnames()
 def test_auto_aliases_require_evidence_but_explicit_nicknames_remain():
     from src.translation.glossary import sanitize_automatic_terms
     terms, _ = sanitize_automatic_terms([
+        {'source': 'The Wall Street Journal', 'target': '《华尔街日报》', 'aliases': ['the Journal']},
         {'source': 'Theresa May', 'target': '特蕾莎·梅', 'aliases': ['May']},
         {'source': 'University of California, Berkeley', 'target': '加州大学伯克利分校', 'aliases': ['Berkeley', 'UC Berkeley']},
         {'source': 'Masayoshi Son', 'target': '孙正义', 'aliases': ['Masa'], 'notes': 'Masa is his nickname.'}], set())
     glossary = BookGlossary(terms)
     assert not glossary.validate('In May he stayed at the Berkeley hotel.', '五月他住在伯克利酒店。')
+    assert not glossary.validate('A domestic journal reported. The journal said.', '一家国内期刊报道。该期刊说。')
     assert glossary.validate('Masa studied at UC Berkeley.', '他去上学。')
     assert glossary.validate('Theresa May visited.', '五月来访。')
 
@@ -333,3 +335,49 @@ def test_output_budget_and_truncation_handling(finish_reason):
     else:
         with pytest.raises(ValueError,match='Incomplete'):
             asyncio.run(call)
+
+
+@pytest.mark.parametrize('status', [401, 402, 403])
+def test_access_errors_stop_retries_and_queued_requests(status):
+    import httpx
+    from openai import APIStatusError
+    from types import SimpleNamespace
+    from src.common.exceptions import ProviderAccessError
+    from src.translation.llm_client import RateLimiter
+    client = object.__new__(LLMClient)
+    client.model = 'test'; client.max_output_tokens = 100; client.temperature = None
+    client.rate_limiter = RateLimiter(0, 1)
+    calls = []
+    async def create(**kwargs):
+        calls.append(kwargs)
+        response = httpx.Response(status, request=httpx.Request('POST', 'https://example.test'))
+        raise APIStatusError('provider response', response=response, body={})
+    client.client = SimpleNamespace(chat=SimpleNamespace(completions=SimpleNamespace(create=create)))
+    async def run():
+        for _ in range(2):
+            with pytest.raises(ProviderAccessError, match=f'HTTP {status}'):
+                await client._make_request('system', 'source')
+    asyncio.run(run())
+    assert len(calls) == 1
+
+
+def test_quota_failure_preserves_completed_translation_and_checkpoint():
+    from src.common.exceptions import ProviderAccessError
+    class Client:
+        model = 'test'
+        calls = 0
+        async def translate_chunk(self, items, **kwargs):
+            self.calls += 1
+            if self.calls > 1:
+                raise ProviderAccessError('API HTTP 402: quota exhausted')
+            return {items[0].entry_id: '已完成。'}
+    entries = [entry(f'<p id="p{i}">Plain source {i}.</p>') for i in range(3)]
+    for i, item in enumerate(entries): item.entry_id = str(i)
+    snapshots = []
+    translator = Translator(Client(), chunk_size=1, max_concurrent=1,
+                            on_chunk_complete=lambda: snapshots.append([e.translated_text for e in entries]))
+    with pytest.raises(ProviderAccessError):
+        asyncio.run(translator.translate(entries, BookProfile(title='Test', author='Test')))
+    assert entries[0].translated_text == '已完成。'
+    assert not any(e.translated_text for e in entries[1:])
+    assert snapshots and snapshots[-1][0] == '已完成。'