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:
@@ -63,6 +63,17 @@ describe('content language', () => {
|
||||
})
|
||||
})
|
||||
|
||||
describe('chosen material', () => {
|
||||
it('marks a schedule made from chosen material in its brief, and reads it back as chosen', () => {
|
||||
const r = rule('summary', 2, 'week', 'sales', 'Bahasa Indonesia')
|
||||
const config = configFor(r, 0, true)
|
||||
expect(config.instructions).toMatch(/Use only the Brain material chosen for this schedule\./)
|
||||
expect(configFor(r).instructions).not.toMatch(/chosen/)
|
||||
expect(ruleOf(agentFrom(config))).toEqual({ ...r, chosen: true })
|
||||
expect(ruleOf(agentFrom(configFor(r)))).toEqual(r)
|
||||
})
|
||||
})
|
||||
|
||||
describe('ruleOf', () => {
|
||||
it.each([
|
||||
rule('summary', 3),
|
||||
|
||||
Reference in New Issue
Block a user