Files
synth 17abdfc78c fix(system-agent): leave reasoning room in local model setup probes (#124405)
* fix(system-agent): increase setup inference probe max tokens from 32 to 128

The 32-token cap starves reasoning models that spend tokens on thinking
before emitting visible text. The probe gets a reasoning-only turn and
reports healthy local models as broken inference.

Increase to 128 tokens to accommodate reasoning model thinking overhead.

Fixes #124345

* fix(system-agent): leave reasoning room in setup probes

Co-authored-by: synthclaw <synthalorian@gmail.com>

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-08-23 23:46:27 -07:00
..