amos c3c9d6e872 Count a model refusing an oversized request as context_limit, not an infrastructure failure
Long Qwen sessions on build-*/archive-* tasks grew past 460 KB and the service answered
400 straight away; batch resampled them as model_http and paused after three in a row,
so those tasks could never finish their trials. context_limit pays the line like
output_limit and does not count toward the environment pause.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 05:07:48 +08:00
..