Files
esh-pfi-infrastructure/stacks
Vuong Hoang 6692701571 docs(voices-seat): every voice prefixes an empty think block unless the caller disables it
Found while smoke-testing the lv-mccarthy ship. Measured live:

  default                 -> '<think>\n\n</think>\n\nThere were no horses in the road...'
  enable_thinking=false   -> 'The sun was hot on the dry riverbed and the stones were red...'

This is the Qwen3-4B-Instruct CHAT TEMPLATE, not an adapter property, so it applies
to lv-yarros, lv-bronte and lv-hemingway equally and has done since this seat went
up on 2026-09-16.

No gate number is affected: gen_beats_chat_yarros.py sets enable_thinking when the
template supports it, so every arm in every r49 gate was generated without the tags.
But a caller that does not pass chat_template_kwargs gets 17 junk characters at the
head of every passage -- and any word-count or in-band check run over that string is
counting the tags as prose. Skaldsong should be checked.
2026-09-21 18:02:56 -07:00
..