Skip to content

fix: handle network errors gracefully in token count estimation #437

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Jul 30, 2025
1 change: 1 addition & 0 deletions .pre-commit-config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ repos:

- id: trailing-whitespace
description: 'Trim trailing whitespace.'
exclude: CHANGELOG.md

- id: check-docstring-first
description: 'Check a common error of defining a docstring after code.'
Expand Down
9 changes: 8 additions & 1 deletion src/gitingest/output_formatter.py
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,11 @@

from __future__ import annotations

import ssl
import warnings
from typing import TYPE_CHECKING

import requests.exceptions
import tiktoken

from gitingest.schemas import FileSystemNode, FileSystemNodeType
Expand Down Expand Up @@ -190,7 +193,11 @@ def _format_token_count(text: str) -> str | None:
encoding = tiktoken.get_encoding("o200k_base") # gpt-4o, gpt-4o-mini
total_tokens = len(encoding.encode(text, disallowed_special=()))
except (ValueError, UnicodeEncodeError) as exc:
print(exc)
warnings.warn(f"Failed to estimate token size: {exc}", RuntimeWarning, stacklevel=3)
return None
except (requests.exceptions.RequestException, ssl.SSLError) as exc:
# If network errors, skip token count estimation instead of erroring out
warnings.warn(f"Failed to download tiktoken model: {exc}", RuntimeWarning, stacklevel=3)
return None

for threshold, suffix in _TOKEN_THRESHOLDS:
Expand Down
Loading