Ethanfel 22fd24b29e Re-enable reasoning for accurate verdicts (no-think rubber-stamped 'match') ...

Disabling thinking made reasoning models mark everything 'match' even when ref/gen
clearly differ. Added an enable_thinking toggle (default ON) threaded through the
generation path; the prompt now allows reasoning then asks for the result, and
verdict_rule explicitly warns against lazy 'match'. _parse_json now scans for the
JSON object AFTER the reasoning prose (last balanced object with 'axes'), and the
markdown fallback already reads reasoned per-axis output. Default max_new_tokens
2048->3072 so verdicts don't get cut off.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-27 10:56:47 +02:00

..

workflow_api.json

Re-enable reasoning for accurate verdicts (no-think rubber-stamped 'match')

2026-06-27 10:56:47 +02:00

workflow_describe_api.json

Re-enable reasoning for accurate verdicts (no-think rubber-stamped 'match')

2026-06-27 10:56:47 +02:00