Show the Brain beside the AI chat and make schedules from chosen material

The Brain and AI page lists Brain material (failed documents hidden) with
search, open, delete and per-material or select-all ticks. New schedules use
only the ticked material, kept through topic edits and resumes; nothing ticked
means the whole Brain. With material ticked, the agent skips the content topic
question and names the material in the chat and plan.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Iqbal
2026-10-27 22:53:38 +07:00
parent ef4fb7d971
commit 3b56c27210
10 changed files with 298 additions and 102 deletions

View File

@@ -23,6 +23,16 @@ describe('instruction agent', () => {
expect(nextQuestion(say('make 3 quizzes per week', t('agent.optWholeBrain')))?.type).toBe('language')
})
it('asks no topic for content when material is chosen, and names that material in the plan', () => {
const s = { ...say('make 1 scorm per week'), sources: '“LLM”' }
expect(nextQuestion(s)?.type).toBe('language')
expect(respond({ ...EMPTY, sources: '“LLM”' }, 'make 1 scorm per week').reply).toMatch(/from “LLM”/)
})
it('still asks what to research on the internet when material is chosen', () => {
expect(nextQuestion({ ...say('research every day'), sources: '“LLM”' })?.type).toBe('topic')
})
it('asks about a video count that has no cadence', () => {
const s = say('3 videos per week about onboarding')
expect(nextQuestion(s)?.type).toBe('video')