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

apps/studio/evals/scorer.ts

@@ -117,7 +117,7 @@ export const concisenessScorer: EvalScorer<
 > = async ({ input, output }) => {
   return await concisenessEvaluator({
     input: input.prompt,
-    output: serializeSteps(output.steps),
+    output: extractTextOnly(output.steps),
   })
 }