supabase / supabase / 21023091353

66%

push

github

feat(assistant): hallucination scorers + corrective measures for storage versioning answers (#41655)

* feat: "Docs Faithfulness" scorer

* feat: test case for storage object restoration

* feat: "Factuality" scorer

* feat: "Factuality" -> "Correctness"

* feat: update Storage recovery test case

* feat: finishReason in task output

* feat: encourage parallel tool calls + docs search, discourage superfluous context gathering

* prompt tuning (tool selection strategy)

* add data recovery section in chat prompt

* test: S3 versioning support correctness

* refactor: derive stepsSerialized/textOnly from shared steps data

* fix: input in correctness scorer

674 of 778 branches covered (86.63%)

Branch coverage included in aggregate %.

2551 of 3962 relevant lines covered (64.39%)

122.25 hits per line