fix: handle network errors gracefully in token count estimation #437
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
LGTM but we needs to add log when it fails. |
|
@ix-56h done! I used print because I think that's how logs are managed on the CLI, but lmk if I need to import some other logger. |
…log.md markdownlint errors
ix-56h
approved these changes
Jul 26, 2025
NicolasIRAGNE
requested changes
Jul 26, 2025
I've edited the changelog because it markdownlint report an error. |
|
@NicolasIRAGNE done. |
|
danke, needs a quick rebase and I think we good to go |
ix-56h
approved these changes
Jul 28, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
When downloading tiktoken models fails due to network issues (SSL errors, connection problems), skip token count estimation silently instead of crashing.
This solves a very specific problem I have with an enterprise environment.