Jules ed17e21523 fix(ai-review): restore Claude reviews on Opus 5 ...

* style(ai-review): use double hyphens instead of em dashes

* fix(ai-review): size token budget for thinking models

Opus 5 and later think by default and `max_tokens` covers thinking plus
response text, so the 4000-token budget left the reviewer's JSON empty or
truncated. Raise it to 16k and cap thinking depth with `output_config.effort`,
gated to the models that accept it.

* fix(ai-review): report unusable reviewer output

A reviewer that answered with unparseable JSON resolved successfully, so the
run posted a two-model review that one model contributed nothing to. Flag it
on the PR comment, log the stop reason and raw response, and fall back to the
unmerged reviewer issues when synthesis itself is unusable.

* chore(ai-review): lower job timeout to 10 minutes

2026-08-03 20:54:23 +09:00

..

ai-review.yml

fix(ai-review): restore Claude reviews on Opus 5

2026-08-03 20:54:23 +09:00

test.yml

fix(cms): use preview host for Vercel admin

2026-07-02 22:52:46 +09:00