Separate settings per generation step; explain Practice and Exam on shares
All checks were successful
Verify and publish V2 container / build-and-push (push) Successful in 29s

- Settings -> AI: Planning, Writing, Python check and Second review each get
  their own model, reasoning effort, temperature and output limit, shown under
  Content generation. Unset choices follow Content generation, then the
  default model.
- Shared quizzes say what Practice and Exam mean under the mode toggle.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Elijah 2026-11-16 11:08:21 -07:00
parent 2454ab6e95
commit 10be5c39da
9 changed files with 128 additions and 36 deletions

View file

@ -447,7 +447,8 @@ export interface AiModel {
/** USD per million cached input tokens; null = the provider's usual cache discount. */
priceCachedIn: number | null;
}
export type TaskName = 'chat' | 'generate' | 'vision' | 'quick';
/** Tasks, and the steps of content generation (plan, write, check, review). */
export type TaskName = 'chat' | 'generate' | 'plan' | 'write' | 'check' | 'review' | 'vision' | 'quick';
/** Reasoning effort levels, lowest to highest. Each provider maps them onto what it accepts. */
export const REASONING_EFFORTS = [
{ value: 'none', label: 'Off' },