Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 14 additions & 7 deletions application/prompt_client/litellm_router.py
Original file line number Diff line number Diff line change
Expand Up @@ -8,15 +8,17 @@

from __future__ import annotations

from cre_logging import get_logger

logger = get_logger(__name__)

import logging
import os
import time
from typing import Any, Callable, List, Optional, Sequence

from application.prompt_client.llm_error_utils import is_rate_limit_error
from application.prompt_client.llm_error_utils import (
is_rate_limit_error,
is_transient_llm_error,
)

logger = logging.getLogger(__name__)

LlmFn = Callable[[str, str], str]

Expand Down Expand Up @@ -47,21 +49,26 @@ def with_rate_limit_retry(
max_retries: Optional[int] = None,
retry_sleep_seconds: Optional[int] = None,
) -> Any:
"""Retry rate limits and transient connection/timeout blips."""
default_retries, default_sleep = retry_policy()
retries = default_retries if max_retries is None else max_retries
sleep_s = default_sleep if retry_sleep_seconds is None else retry_sleep_seconds
for attempt in range(retries + 1):
try:
return fn()
except Exception as err:
if not is_rate_limit_error(err) or attempt >= retries:
retriable = is_transient_llm_error(err) or is_rate_limit_error(err)
if not retriable or attempt >= retries:
raise
kind = "rate/quota" if is_rate_limit_error(err) else "transient"
logger.info(
"rate/quota limited during %s; sleeping %ss (attempt %s/%s)",
"%s error during %s; sleeping %ss (attempt %s/%s): %s",
kind,
context,
sleep_s,
attempt + 1,
retries + 1,
type(err).__name__,
)
time.sleep(sleep_s)
raise RuntimeError("unreachable: retry loop exited unexpectedly")
Expand Down
35 changes: 35 additions & 0 deletions application/prompt_client/llm_error_utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -31,3 +31,38 @@ def is_rate_limit_error(err: BaseException) -> bool:
if code == 429:
return True
return False


def is_transient_llm_error(err: BaseException) -> bool:
"""Connection / timeout blips that are safe to retry (not model refusal)."""
if is_rate_limit_error(err):
return True
name = type(err).__name__.lower()
if any(
tok in name
for tok in (
"connect",
"timeout",
"apiconnection",
"remoteprotocol",
"network",
)
):
return True
msg = str(err).lower()
return any(
tok in msg
for tok in (
"connection reset",
"connection aborted",
"connection refused",
"temporarily unavailable",
"broken pipe",
"timed out",
"timeout",
"errno 54",
"errno 104",
"server disconnected",
"remote end closed",
)
)
Loading
Loading