mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-24 00:52:24 +00:00
The flag step never read it: parseVerdict destructures duplicate_of, confidence and evidence only, so considered cost tokens on every issue and went straight on the floor. The parse test now covers extra keys being dropped instead of asserting a field that no longer exists. |
||
|---|---|---|
| .. | ||
| duplicate-issue-check.md | ||
| duplicate-issue-check.schema.json | ||