fix parsing multi tool calls in stream_chunk_builder

[omerc7]

Title

Fix - parsing multi tool calls in stream_chunk_builder

Type

🐛 Bug Fix

Changes

Add index to last function call in stream_chunk_builder Fix function name in multi tool calls

[REQUIRED] Testing

Did not find any tests with actual data parsing retuned from llm (or mock) in litellm/tests/test_stream_chunk_builder.py

In the print screens below the llm want to call

1. function name: aws-s3-list with no args
2. function name: aws-list-secrets with args: {"max_items": "3"}

Before:

After:

[vercel[bot]]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
litellm	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Jul 29, 2024 1:24pm

[krrishdholakia]

hey @omerc7 thank you for this pr. can you add a test for this in test_stream_chunk_builder.py + share a screenshot of it passing?

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[github-actions[bot]]

This pull request has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.