Skip to content

[FEATURE]: Model switch doesn't take effect after API error (429) until conversation is stopped #41587

Description

@wsu2059q

Feature hasn't been suggested before.

  • I have verified this feature I'm about to request hasn't been suggested before.

Describe the enhancement you want to request

When I'm using a model and hit a 429 (plan limit exceeded), I switch to another model in the dropdown and hit Enter to retry.

The UI shows the new model, but the request still goes to the old one — I get the 429 again. The only way to actually use the new model is to click Stop first, then hit Enter again.

This is confusing. If I change the model in the dropdown, that should be the model used for the next send, regardless of previous errors.

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions