v1.81.14-stable.gpt-5.4-patch6
📦 litellmView on GitHub →
🐛 2 fixes🔧 1 symbols
Summary
This patch release focuses on fixing critical bugs related to tool call handling for the Gemini 1.5 Flash model on the completion endpoint.
🐛 Bug Fixes
- Fixed an issue where the `completion` endpoint was incorrectly returning an empty list for `tool_calls` when using `gemini/gemini-1.5-flash`.
- Resolved a bug where `gemini/gemini-1.5-flash` was failing to return the correct `tool_calls` structure.