wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #4067 from omChauhanDev/fix-gemini3-flash-thinking-default

Browse Source 
fix: default thinking config for Gemini 3+ Flash models
This commit is contained in:
kompfner
2026-04-10 10:41:44 -04:00
committed by GitHub
parent d07eebff20 fa982a05c0
commit 8e5fe8afda
2 changed files with 10 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/4067.fixed.md Normal file
View File

@@ -0,0 +1 @@
- GoogleLLMService now applies a low-latency thinking default (`thinking_level="minimal"`) for Gemini 3+ Flash models.