Check default answer in accuracy rating
What does this MR do and why?
Check default answer in accuracy rating
Sometimes proper tools are picked, but in the end default final answer is used (typically because Anthropic fails to prefix final answer with "Final answer:"). In such cases it makes sense to add 0 accuracy for it because user gets only default not-helpful message anyway.
Screenshots or screen recordings
Screenshots are required for UI changes, and strongly recommended for all other merge requests.
Before | After |
---|---|
How to set up and validate locally
Numbered steps to set up and validate the change are strongly suggested.
MR acceptance checklist
This checklist encourages us to confirm any changes have been analyzed to reduce risks in quality, performance, reliability, security, and maintainability.
-
I have evaluated the MR acceptance checklist for this MR.