Files
deepseek-harness/docs/user/guide
Yichen Jiang a0a04158f8 fix(models): keep reasoning edits with their model and mirror pi-ai refusals
The reasoning-level editor kept the levels it switched off, its row order,
and typed text in component state, while the model list keys rows by
position, so deleting a row handed that state to the next model: turning
the survivor's switch on wrote the deleted model's levels into it. The
editor now renders only from the model; rows follow the stored order,
switching on always starts from the defaults, and only the focused field
keeps its typed text until the field is left.

The reasoning check moves out of the shared model validator into the two
cards whose rows edit it, so DeepSeek and catalog routes are untouched,
and it now mirrors every pi-ai refusal: a valueless field, a missing value
on a level besides off, and an empty value. A refused value marks its
field, and leaving that field repairs it with the level name.

The Providers guide now points custom model API users to the page before
the YAML, and both package READMEs describe the new behavior.
2026-10-15 14:53:56 +08:00
..