xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-07 14:20:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: exclude RateLimitError from retry logic

Browse Source
This commit is contained in:
Kangmoon Seo
2025-05-22 15:04:16 +09:00
parent 4e80f3999c
commit 466ec4ce90
3 changed files with 34 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
pr_agent/algo/ai_handlers/litellm_ai_handler.py
View File

@ -3,7 +3,7 @@ import litellm
import openai
import requests
from litellm import acompletion
from tenacity import retry, retry_if_exception_type, stop_after_attempt
from tenacity import retry, retry_if_exception_type, retry_if_not_exception_type, stop_after_attempt
from pr_agent.algo import CLAUDE_EXTENDED_THINKING_MODELS, NO_SUPPORT_TEMPERATURE_MODELS, SUPPORT_REASONING_EFFORT_MODELS, USER_MESSAGE_ONLY_MODELS
from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
@ -274,8 +274,8 @@ class LiteLLMAIHandler(BaseAiHandler):
return get_settings().get("OPENAI.DEPLOYMENT_ID", None)
@retry(
retry=retry_if_exception_type((openai.APIError, openai.APIConnectionError, openai.APITimeoutError)), # No retry on RateLimitError
stop=stop_after_attempt(OPENAI_RETRIES)
retry=retry_if_exception_type(openai.APIError) & retry_if_not_exception_type(openai.RateLimitError),
stop=stop_after_attempt(OPENAI_RETRIES),
)
async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2, img_path: str = None):
try:
@ -371,13 +371,13 @@ class LiteLLMAIHandler(BaseAiHandler):
get_logger().info(f"\nUser prompt:\n{user}")
response = await acompletion(**kwargs)
except (openai.RateLimitError) as e:
except openai.RateLimitError as e:
get_logger().error(f"Rate limit error during LLM inference: {e}")
raise
except (openai.APIError, openai.APITimeoutError) as e:
except openai.APIError as e:
get_logger().warning(f"Error during LLM inference: {e}")
raise
except (Exception) as e:
except Exception as e:
get_logger().warning(f"Unknown error during LLM inference: {e}")
raise openai.APIError from e
if response is None or len(response["choices"]) == 0: