brainy/tests/integration/aggregate-reserved-fields.test.ts

/**
 * @module tests/integration/aggregate-reserved-fields
 * @description One field-resolution law across the whole aggregation + query
 * surface (SELF-AGGREGATE-DELETE-DRIFT). Laws:
 * (1) aggregates grouped by a RESERVED field (subtype) decrement on delete —
 *     the delete-side entity view carries every reserved field, so the
 *     decrement finds its group (counts must never drift from ground truth);
 * (2) same for update: moving an entity between reserved-field groups
 *     decrements the old group and increments the new one (no double-count);
 * (3) aggregation source.where on a reserved field (subtype) FILTERS instead
 *     of silently matching nothing;
 * (4) removeMany refuses empty/invalid selectors loudly (bare array, empty
 *     object, ids: []) instead of resolving as a silent no-op;
 * (5) find() accepts both where spellings: flattened (entry.title) and
 *     storage-shaped (metadata.entry.title) resolve to the same rows.
 */
import { describe, it, expect, beforeEach, afterEach } from 'vitest'
import { Brainy } from '../../src/brainy.js'
import { NounType } from '../../src/types/graphTypes.js'

const stubEmbedding = async (text: string): Promise<number[]> => {
  const hash = text.split('').reduce((acc, char) => acc + char.charCodeAt(0), 0)
  return new Array(384).fill(0).map((_, i) => Math.sin(hash + i))
}

describe('aggregation + query field-resolution law', () => {
  let brain: Brainy

  beforeEach(async () => {
    brain = new Brainy({
      requireSubtype: false,
      storage: { type: 'memory' as const },
      embeddingFunction: stubEmbedding
    })
    await brain.init()
  })

  afterEach(async () => {
    await brain.close()
  })

  it('reserved-field groupBy decrements on delete (the drift bug)', async () => {
    brain.defineAggregate({
      name: 'by_subtype',
      source: { type: NounType.Document },
      groupBy: ['subtype'],
      metrics: { count: { op: 'count' } }
    })

    const ids: string[] = []
    for (let i = 0; i < 5; i++) {
      ids.push(
        await brain.add({
          data: `doc-${i}`,
          type: NounType.Document,
          subtype: 'note',
          metadata: { team: 'alpha' }
        })
      )
    }
    let groups = await brain.queryAggregate('by_subtype')
    expect(groups).toHaveLength(1)
    expect(groups[0].groupKey).toEqual({ subtype: 'note' })
    expect(groups[0].metrics.count).toBe(5)

    await brain.remove(ids[0])
    await brain.flush()

    groups = await brain.queryAggregate('by_subtype')
    expect(groups[0].metrics.count).toBe(4)
    const live = await brain.find({ type: NounType.Document, limit: 100 })
    expect(groups[0].metrics.count).toBe(live.length)
  })

  it('reserved-field groupBy moves between groups on update (no double-count)', async () => {
    brain.defineAggregate({
      name: 'by_subtype',
      source: { type: NounType.Document },
      groupBy: ['subtype'],
      metrics: { count: { op: 'count' } }
    })
    const id = await brain.add({
      data: 'doc-move',
      type: NounType.Document,
      subtype: 'draft'
    })
    await brain.update({ id, subtype: 'published' })

    const groups = await brain.queryAggregate('by_subtype')
    const byKey = Object.fromEntries(
      groups.map((g) => [String(g.groupKey.subtype), g.metrics.count])
    )
    expect(byKey['published']).toBe(1)
    // The old group must be gone or zero — never still counting the entity.
    expect(byKey['draft'] ?? 0).toBe(0)
  })

  it('source.where on a reserved field filters instead of matching nothing', async () => {
    brain.defineAggregate({
      name: 'notes_only',
      source: { type: NounType.Document, where: { subtype: 'note' } },
      groupBy: ['team'],
      metrics: { count: { op: 'count' } }
    })
    await brain.add({
      data: 'n1',
      type: NounType.Document,
      subtype: 'note',
      metadata: { team: 'alpha' }
    })
    await brain.add({
      data: 'd1',
      type: NounType.Document,
      subtype: 'draft',
      metadata: { team: 'alpha' }
    })

    const groups = await brain.queryAggregate('notes_only')
    expect(groups).toHaveLength(1)
    expect(groups[0].metrics.count).toBe(1) // the note, never the draft
  })

  it('removeMany refuses empty/invalid selectors loudly', async () => {
    const id = await brain.add({ data: 'keep-me', type: NounType.Document })

    // Bare array passed positionally — the classic silent no-op.
    await expect(
      brain.removeMany([id] as unknown as Parameters<typeof brain.removeMany>[0])
    ).rejects.toThrow(/bare array/)
    // Empty selector object.
    await expect(
      brain.removeMany({} as Parameters<typeof brain.removeMany>[0])
    ).rejects.toThrow(/requires a selector/)
    // Explicit empty id list.
    await expect(brain.removeMany({ ids: [] })).rejects.toThrow(/ids: \[\]/)

    // Nothing was deleted by any of the refused calls.
    expect(await brain.get(id)).toBeTruthy()
  })

  it('find() accepts both flattened and metadata.-prefixed where spellings', async () => {
    await brain.add({
      data: 'nested-doc',
      type: NounType.Document,
      metadata: { entry: { title: 'T1' }, classifier: { contextHints: { vfsPath: '/n/a.md' } } }
    })
    await brain.flush()

    const flat = await brain.find({
      type: NounType.Document,
      where: { 'entry.title': 'T1' },
      limit: 10
    })
    const prefixed = await brain.find({
      type: NounType.Document,
      where: { 'metadata.entry.title': 'T1' },
      limit: 10
    })
    const deepPrefixed = await brain.find({
      type: NounType.Document,
      where: { 'metadata.classifier.contextHints.vfsPath': '/n/a.md' },
      limit: 10
    })
    expect(flat).toHaveLength(1)
    expect(prefixed).toHaveLength(1)
    expect(prefixed[0].id).toBe(flat[0].id)
    expect(deepPrefixed).toHaveLength(1)
  })
})