Matt Rossman e4a9b6882c fix(assistant): use extractTextOnly in conciseness scorer (#43612) ...

`concisenessScorer` was passing full serialized text + tool calls JSON
to the LLM judge (SQL queries, GraphQL payloads, etc.). Switches to
`extractTextOnly` so the judge only evaluates text the user actually
sees.

Prerequisite for https://github.com/supabase/supabase/pull/43613 to set
a fair conciseness baseline score.

Ref AI-402

2026-03-11 13:55:02 -04:00

..

.gitignore

feat: assistant evals (#41311)

2025-12-22 23:45:48 -05:00

assistant.eval.ts

feat(assistant): online evals support and CI workflows (#43194)

2026-03-09 13:05:26 -04:00

dataset.ts

feat(assistant): score URL validity and fix support ticket URL guidance (#42227)

2026-01-30 09:53:21 -05:00

output.ts

feat(assistant): online evals support and CI workflows (#43194)

2026-03-09 13:05:26 -04:00

scorer-online-manifest.json

feat(assistant): online evals support and CI workflows (#43194)

2026-03-09 13:05:26 -04:00

scorer-online.ts

feat(assistant): online evals support and CI workflows (#43194)

2026-03-09 13:05:26 -04:00

scorer-wasm.ts

feat(assistant): online evals support and CI workflows (#43194)

2026-03-09 13:05:26 -04:00

scorer.ts

fix(assistant): use extractTextOnly in conciseness scorer (#43612)

2026-03-11 13:55:02 -04:00