Fix token counting bug

[AtefEl-Hennnawy]

Description

Fixes a minor bug in embedding token-counting within TokenCountingHandler.
The current implementation replaces \n with spaces (" ") before sending the prompt to the model (e.g., OpenAI), but this replacement is not applied when counting tokens locally.
This causes a mismatch between actual usage reported by the provider and what LlamaIndex estimates.

Fix

Added .replace("\n", " ") before counting tokens to align local counting with what is actually sent.

Fixes: No associated issue number (happy to file one if needed).

New Package?

Did I fill in the tool.llamahub section in the pyproject.toml and provide a detailed README.md for my new integration or package?

• Yes
• No

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

• Yes
• No

Type of Change

• Bug fix (non-breaking change which fixes an issue)

How Has This Been Tested?

• Manually compared OpenAI API usage reports with TokenCountingHandler output after the fix

Suggested Checklist:

• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added Google Colab support for the newly added notebooks.
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes