remove temporary onTask debug field

Root cause confirmed as a stale endpoint deployment (redeployed old
revision after the label fix), not a code bug. mathWord now works
as expected; no longer need the raw prediction exposed in the API
response.

handler.py

@@ -101,7 +101,6 @@ class Utterance:
             'wordCount': self.word_count,
             'numMathTerms': self.num_math_terms,
             'mathTerms': self.math_terms,
-            'onTask': self.on_task,  # temporary: raw {label, score} for debugging mathWord source
             'vocabularyTerms': self.vocabulary_terms,
             'vocabularyMatches': self.vocabulary_matches
         }