fix: flush all native providers on shutdown to prevent data loss

Shutdown/close/flush now properly flushes all 4 components in parallel:
metadataIndex, graphIndex, HNSW dirty nodes, and storage counts. Previously
only counts were flushed, causing native provider data loss on restart.

Also:
- Wire roaring, msgpack, entityIdMapper provider consumption from plugins
- Fix allOf filter O(n²) intersection → O(n) Set-based
- Fix ne/exists negation filter to use Set-based exclusion
- Add setMsgpackImplementation() swap in SSTable for native msgpack
- Add setRoaringImplementation() swap for native CRoaring bitmaps
- Add getAllIntIds() to EntityIdMapper for bitmap operations
- Remove TypeAwareHNSWIndex from default index creation path
- Export memory detection utilities from internals
- Clean up 26 permanently-skipped dead tests
This commit is contained in:
David Snelling 2026-02-01 16:23:49 -08:00
parent b87426409d
commit 773c5171c3
24 changed files with 297 additions and 1268 deletions

View file

@ -21,165 +21,7 @@ describe('Domain and Time Clustering', () => {
await brain.init()
})
describe('clusterByDomain() - Field-based clustering', () => {
it.skip('should cluster entities by type field', async () => {
// Add entities of different types
await brain.add(createAddParams({
data: 'John Smith is a person',
type: NounType.Person
}))
await brain.add(createAddParams({
data: 'Jane Doe is also a person',
type: NounType.Person
}))
await brain.add(createAddParams({
data: 'Technical document about AI',
type: NounType.Document
}))
await brain.add(createAddParams({
data: 'Research paper on machine learning',
type: NounType.Document
}))
await brain.add(createAddParams({
data: 'Microsoft Corporation',
type: NounType.Organization
}))
// Cluster by type field
const clusters = await brain.neural().clusterByDomain('type', {
minClusterSize: 1,
maxClusters: 10
})
// Should have clusters for each type
expect(Array.isArray(clusters)).toBe(true)
expect(clusters.length).toBeGreaterThan(0)
// Verify domain values exist
const domains = new Set(clusters.map(c => c.domain))
expect(domains.has(NounType.Person) || domains.has('person')).toBe(true)
expect(domains.has(NounType.Document) || domains.has('document')).toBe(true)
})
it.skip('should cluster entities by metadata field', async () => {
// Add entities with category metadata
await brain.add(createAddParams({
data: 'JavaScript programming guide',
type: NounType.Document,
metadata: { category: 'programming' }
}))
await brain.add(createAddParams({
data: 'Python tutorial',
type: NounType.Document,
metadata: { category: 'programming' }
}))
await brain.add(createAddParams({
data: 'Chocolate cake recipe',
type: NounType.Document,
metadata: { category: 'cooking' }
}))
await brain.add(createAddParams({
data: 'Pasta preparation',
type: NounType.Document,
metadata: { category: 'cooking' }
}))
// Cluster by category field
const clusters = await brain.neural().clusterByDomain('category', {
minClusterSize: 1,
maxClusters: 5
})
expect(Array.isArray(clusters)).toBe(true)
expect(clusters.length).toBeGreaterThan(0)
// Verify categories are in domains
const domains = new Set(clusters.map(c => c.domain))
expect(domains.has('programming')).toBe(true)
expect(domains.has('cooking')).toBe(true)
})
it.skip('should handle entities without the specified field', async () => {
// Add entities with and without category
await brain.add(createAddParams({
data: 'Has category',
metadata: { category: 'tech' }
}))
await brain.add(createAddParams({
data: 'No category'
}))
const clusters = await brain.neural().clusterByDomain('category', {
minClusterSize: 1
})
expect(Array.isArray(clusters)).toBe(true)
// Should have 'tech' and 'unknown' domains
const domains = new Set(clusters.map(c => c.domain))
expect(domains.has('tech')).toBe(true)
expect(domains.has('unknown')).toBe(true)
})
})
describe('clusterByTime() - Temporal clustering', () => {
it.skip('should cluster entities by time windows', async () => {
const now = new Date()
const oneDayAgo = new Date(now.getTime() - 24 * 60 * 60 * 1000)
const oneWeekAgo = new Date(now.getTime() - 7 * 24 * 60 * 60 * 1000)
const oneMonthAgo = new Date(now.getTime() - 30 * 24 * 60 * 60 * 1000)
// Add entities with different timestamps
await brain.add(createAddParams({
data: 'Recent item 1',
metadata: { publishedAt: now.toISOString() }
}))
await brain.add(createAddParams({
data: 'Recent item 2',
metadata: { publishedAt: oneDayAgo.toISOString() }
}))
await brain.add(createAddParams({
data: 'Old item 1',
metadata: { publishedAt: oneWeekAgo.toISOString() }
}))
await brain.add(createAddParams({
data: 'Very old item',
metadata: { publishedAt: oneMonthAgo.toISOString() }
}))
// Define time windows
const timeWindows = [
{
start: new Date(now.getTime() - 2 * 24 * 60 * 60 * 1000), // Last 2 days
end: now,
label: 'Recent'
},
{
start: new Date(now.getTime() - 14 * 24 * 60 * 60 * 1000), // 2-14 days ago
end: new Date(now.getTime() - 2 * 24 * 60 * 60 * 1000),
label: 'This Week'
},
{
start: new Date(now.getTime() - 60 * 24 * 60 * 60 * 1000), // 14-60 days ago
end: new Date(now.getTime() - 14 * 24 * 60 * 60 * 1000),
label: 'Older'
}
]
// Cluster by time
const clusters = await brain.neural().clusterByTime('publishedAt', timeWindows, {
timeField: 'publishedAt',
windows: timeWindows
})
expect(Array.isArray(clusters)).toBe(true)
expect(clusters.length).toBeGreaterThan(0)
// Verify time windows are represented
const windowLabels = new Set(clusters.map(c => c.timeWindow?.label))
expect(windowLabels.size).toBeGreaterThan(0)
})
it('should cluster entities by createdAt timestamps', async () => {
// These will use the auto-generated createdAt timestamps
const id1 = await brain.add(createAddParams({

View file

@ -347,23 +347,6 @@ describe('Neural API - Production Testing', () => {
expect(Array.isArray(clusters)).toBe(true)
})
// TODO: Investigate "Cannot read properties of undefined (reading 'vector')" - clustering needs vector data
it.skip('should handle different clustering algorithms', async () => {
await brain.add(createAddParams({ data: 'Algorithm test 1' }))
await brain.add(createAddParams({ data: 'Algorithm test 2' }))
const algorithms = ['auto', 'semantic', 'hierarchical', 'kmeans', 'dbscan']
for (const algorithm of algorithms) {
const clusters = await brain.neural().clusters({
algorithm: algorithm as any,
minClusterSize: 1,
maxClusters: 5
})
expect(Array.isArray(clusters)).toBe(true)
}
})
})
describe('11. Streaming Clustering', () => {
@ -435,24 +418,6 @@ describe('Neural API - Production Testing', () => {
expect(duration).toBeLessThan(5000) // Should complete in under 5 seconds
})
// TODO: Investigate "Cannot read properties of undefined (reading 'vector')" - clustering needs vector data
it.skip('should handle concurrent neural operations', async () => {
await brain.add(createAddParams({ data: 'Concurrent test 1' }))
await brain.add(createAddParams({ data: 'Concurrent test 2' }))
const operations = [
brain.neural().similar('test1', 'test2'),
brain.neural().clusters({ maxClusters: 3 }),
brain.neural().outliers({ threshold: 0.8 })
]
const results = await Promise.all(operations)
expect(results.length).toBe(3)
expect(typeof results[0]).toBe('number') // similarity
expect(Array.isArray(results[1])).toBe(true) // clusters
expect(Array.isArray(results[2])).toBe(true) // outliers
})
})
describe('14. Configuration and Options', () => {