Preserve semantic note layouts and checkpoint on provider quota failures

src/translation/llm_client.py

@@ -5,12 +5,13 @@ import time
 from datetime import datetime
 from pathlib import Path
 from typing import List, Dict, Optional
-from openai import AsyncOpenAI
-from tenacity import retry, stop_after_attempt, wait_exponential
+from openai import AsyncOpenAI, APIStatusError
+from tenacity import retry, stop_after_attempt, wait_exponential, retry_if_not_exception_type
 from loguru import logger
 
 from src.common.data_model import ManifestEntry
 from src.common.utils import setup_logger, ensure_directory
+from src.common.exceptions import ProviderAccessError
 
 logger = setup_logger("llm_client")
 
@@ -238,10 +239,15 @@ Output Format:
         """Generic chat completion."""
         return await self._make_request(system_prompt, user_prompt)
 
-    @retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=2, max=10))
+    @retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=2, max=10),
+           retry=retry_if_not_exception_type(ProviderAccessError))
     async def _make_request(self, system_prompt: str, user_prompt: str) -> str:
+        if getattr(self, '_access_error', None):
+            raise self._access_error
         await self.rate_limiter.acquire()
         try:
+            if getattr(self, '_access_error', None):
+                raise self._access_error
             options = {"max_completion_tokens": self.max_output_tokens}
             if self.temperature is not None:
                 options["temperature"] = self.temperature
@@ -257,6 +263,13 @@ Output Format:
             if choice.finish_reason != "stop" or not choice.message.content:
                 raise ValueError(f"Incomplete model response: {choice.finish_reason}")
             return choice.message.content.strip()
+        except APIStatusError as exc:
+            if exc.status_code in {401, 402, 403}:
+                reason = 'quota exhausted' if exc.status_code == 402 else 'access denied'
+                self._access_error = ProviderAccessError(
+                    f'API HTTP {exc.status_code}: {reason}; restore access and resume with the saved manifest.')
+                raise self._access_error from None
+            raise
         finally:
             self.rate_limiter.release()