153 work summarizer token counter fix

[shreyashkgupta]

Pull Request Description: 153 work summarizer token counter fix

Summary

This pull request addresses a bug fix in the token counter functionality within the kaizen/llms/provider.py file. The main purpose of these changes is to correct the way tokens are counted by the litellm.token_counter function, ensuring that the correct parameters are passed to it.

Significant Modifications

1. Bug Fix in Token Counter: The available_tokens method in kaizen/llms/provider.py has been updated to pass the parameters to litellm.token_counter using keyword arguments (model=self.model, text=message) instead of positional arguments. This change ensures that the function receives the correct inputs, potentially fixing any issues related to incorrect token counting.

2. Version Bump: The project version in pyproject.toml has been incremented from 0.1.13 to 0.1.14. This version bump indicates a minor update, likely reflecting the bug fix.

Impact

• Error Handling: The change improves the reliability of the token counting mechanism, which is crucial for functionalities that depend on accurate token limits.
• Maintainability: Using keyword arguments enhances code readability and reduces the risk of errors related to parameter ordering.
• Versioning: The version increment helps in tracking the update and ensuring that users can identify the bug fix release.

Please review the changes and provide feedback or approval as necessary.

✨ Generated with love by Kaizen ❤️

Original Description

None

[cloudcodeai-nightly]

Code Review

✅ This is a good review! 👍

Here are some feedback:

Potential Issues

[important] -> The `available_tokens` method does not handle potential exceptions that might be raised by `litellm.get_max_tokens` or `litellm.token_counter`. This could lead to unhandled exceptions and potential crashes.

**Fix:** Add error handling to manage potential exceptions from `litellm.get_max_tokens` and `litellm.token_counter`. For example, use try-except blocks to catch and handle specific exceptions. kaizen/llms/provider.py | 72 - 75

✨ Generated with love by Kaizen ❤️

[cloudcodeai-nightly]

Code Review

✅ This is a good review! 👍

Here are some feedback:

Potential Issues

[important] -> The `available_tokens` method does not handle potential exceptions that might be raised by `litellm.get_max_tokens` or `litellm.token_counter`. This could lead to unhandled exceptions and potential crashes.

**Fix:** Add error handling to manage potential exceptions from `litellm.get_max_tokens` and `litellm.token_counter`. For example, use try-except blocks to catch and handle specific exceptions. kaizen/llms/provider.py | 72 - 75

✨ Generated with love by Kaizen ❤️