feat: COW always-on architecture + cloud storage clear() fix (v5.11.0)
Major architectural improvements and critical bug fixes: ## COW Always-On Architecture - Removed cowEnabled flag from BaseStorage (COW cannot be disabled) - Eliminated marker file system (checkClearMarker, createClearMarker) - Simplified all code paths to assume COW is always enabled - COW automatically re-initializes after clear() operations ## Critical Bug Fix: Cloud Storage clear() - Fixed GCS clear() using correct paths (branches/ instead of entities/nouns/) - Fixed S3Compatible clear() path structure - Fixed R2 clear() implementation - Fixed Azure, FileSystem, OPFS, Memory clear() COW flag handling - clear() now deletes: branches/, _cow/, _system/ - Result: Cloud buckets can now be fully cleared (previously impossible) ## Container Memory Detection - Auto-detect Docker/K8s/Cloud Run memory limits (cgroup v1/v2) - Smart memory allocation (75% graph data, 25% query operations) - Environment variable support (CLOUD_RUN_MEMORY, MEMORY_LIMIT) - Production-grade containerized deployment support ## CommitLog streamHistory Feature - Added streamable commit history with pagination - Efficient memory usage for large commit histories - Support for branch filtering and time ranges ## Comprehensive Storage Documentation - Complete v5.11.0 file structure reference - Detailed path construction algorithms - 8 common storage scenarios with examples - Type-first storage, sharding, COW architecture explained - Public docs: docs/architecture/data-storage-architecture.md (1063 lines) ## Files Modified (14 files) - All 8 storage adapters (GCS, S3, R2, Azure, FS, OPFS, Memory, Historical) - BaseStorage core architecture - CommitLog with streaming - Brainy memory configuration - Parameter validation with container detection - Storage architecture documentation ## Breaking Changes NONE - COW was already enabled by default. This removes the ability to disable it. ## Migration No action required. Upgrade and clear() will work correctly on cloud storage. ## Impact - Users can now clear cloud storage buckets completely - No more corrupted buckets after clear() operations - Container deployments automatically optimize memory allocation - COW is mandatory and always enabled (safer, simpler) v5.11.0 - Production ready
This commit is contained in:
parent
28160a3052
commit
3e8b9aacc8
17 changed files with 2925 additions and 1207 deletions
383
tests/integration/memory-enhancements-v5.11.0.test.ts
Normal file
383
tests/integration/memory-enhancements-v5.11.0.test.ts
Normal file
|
|
@ -0,0 +1,383 @@
|
|||
/**
|
||||
* Integration tests for Memory Enhancements (v5.11.0)
|
||||
*
|
||||
* End-to-end tests verifying:
|
||||
* - streamHistory() works in production scenarios
|
||||
* - Container detection works correctly
|
||||
* - Memory limits are applied correctly
|
||||
* - getMemoryStats() provides accurate information
|
||||
* - All features work together seamlessly
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest'
|
||||
import { Brainy } from '../../src/brainy.js'
|
||||
import { mkdtempSync, rmSync } from 'fs'
|
||||
import { tmpdir } from 'os'
|
||||
import { join } from 'path'
|
||||
|
||||
describe('Memory Enhancements Integration (v5.11.0)', () => {
|
||||
let testDir: string
|
||||
let originalEnv: Record<string, string | undefined>
|
||||
|
||||
beforeEach(() => {
|
||||
testDir = mkdtempSync(join(tmpdir(), 'brainy-memory-integration-'))
|
||||
|
||||
originalEnv = {
|
||||
CLOUD_RUN_MEMORY: process.env.CLOUD_RUN_MEMORY,
|
||||
MEMORY_LIMIT: process.env.MEMORY_LIMIT
|
||||
}
|
||||
})
|
||||
|
||||
afterEach(() => {
|
||||
rmSync(testDir, { recursive: true, force: true })
|
||||
|
||||
Object.keys(originalEnv).forEach(key => {
|
||||
if (originalEnv[key] === undefined) {
|
||||
delete process.env[key]
|
||||
} else {
|
||||
process.env[key] = originalEnv[key]
|
||||
}
|
||||
})
|
||||
})
|
||||
|
||||
describe('Production Workflow: Workshop Snapshot Timeline', () => {
|
||||
it('should stream 1000 snapshots efficiently', async () => {
|
||||
const brain = new Brainy({
|
||||
storage: {
|
||||
type: 'filesystem',
|
||||
options: { path: testDir }
|
||||
},
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
// Create a realistic workflow: user creates entities and saves snapshots
|
||||
for (let i = 0; i < 100; i++) {
|
||||
// Add 10 entities
|
||||
for (let j = 0; j < 10; j++) {
|
||||
await brain.add({
|
||||
type: 'document',
|
||||
data: `Chapter ${i}, Section ${j}`
|
||||
})
|
||||
}
|
||||
|
||||
// Save snapshot
|
||||
await brain.commit({ message: `Version ${i}`, captureState: true })
|
||||
}
|
||||
|
||||
// Stream history efficiently
|
||||
const snapshots: string[] = []
|
||||
const startTime = Date.now()
|
||||
|
||||
for await (const commit of brain.streamHistory({ limit: 100 })) {
|
||||
snapshots.push(commit.message)
|
||||
}
|
||||
|
||||
const duration = Date.now() - startTime
|
||||
|
||||
expect(snapshots.length).toBe(100)
|
||||
expect(duration).toBeLessThan(5000) // Should complete in < 5s
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
|
||||
it('should handle large snapshot with filtering', async () => {
|
||||
const brain = new Brainy({
|
||||
storage: {
|
||||
type: 'filesystem',
|
||||
options: { path: testDir }
|
||||
},
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
// Create snapshots by different authors
|
||||
for (let i = 0; i < 50; i++) {
|
||||
await brain.add({ type: 'document', data: `Content ${i}` })
|
||||
|
||||
await brain.commit({
|
||||
message: `Snapshot ${i}`,
|
||||
author: i % 3 === 0 ? 'alice' : i % 3 === 1 ? 'bob' : 'charlie',
|
||||
captureState: true
|
||||
})
|
||||
}
|
||||
|
||||
// Stream only alice's snapshots
|
||||
const aliceSnapshots: any[] = []
|
||||
|
||||
for await (const commit of brain.streamHistory({ author: 'alice', limit: 100 })) {
|
||||
aliceSnapshots.push(commit)
|
||||
}
|
||||
|
||||
expect(aliceSnapshots.length).toBeGreaterThan(0)
|
||||
aliceSnapshots.forEach(commit => {
|
||||
expect(commit.author).toBe('alice')
|
||||
})
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
})
|
||||
|
||||
describe('Production Workflow: Cloud Run Deployment', () => {
|
||||
it('should detect 4GB Cloud Run container and set optimal limits', async () => {
|
||||
process.env.CLOUD_RUN_MEMORY = '4Gi'
|
||||
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
// Verify container detected
|
||||
expect(stats.memory.containerLimit).toBe(4 * 1024 * 1024 * 1024)
|
||||
|
||||
// Verify optimal limits
|
||||
expect(stats.limits.basis).toBe('containerMemory')
|
||||
expect(stats.limits.maxQueryLimit).toBe(10000) // 25% of 4GB
|
||||
|
||||
// Verify can query with these limits
|
||||
for (let i = 0; i < 100; i++) {
|
||||
await brain.add({ type: 'document', data: `Entity ${i}` })
|
||||
}
|
||||
|
||||
const results = await brain.find({ limit: 10000 }) // Should not throw
|
||||
expect(results.length).toBe(100)
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
|
||||
it('should allow manual override for power users in containers', async () => {
|
||||
process.env.CLOUD_RUN_MEMORY = '4Gi'
|
||||
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
maxQueryLimit: 50000, // Override auto-detection
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
// Container detected but override used
|
||||
expect(stats.memory.containerLimit).toBe(4 * 1024 * 1024 * 1024)
|
||||
expect(stats.limits.basis).toBe('override')
|
||||
expect(stats.limits.maxQueryLimit).toBe(50000)
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
|
||||
it('should use reservedQueryMemory for fine-grained control', async () => {
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
reservedQueryMemory: 2 * 1024 * 1024 * 1024, // Reserve 2GB
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
expect(stats.limits.basis).toBe('reservedMemory')
|
||||
expect(stats.limits.maxQueryLimit).toBe(20000) // 2GB / 100MB * 1000
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
})
|
||||
|
||||
describe('Combined Features: Stream + Memory Management', () => {
|
||||
it('should stream large histories within memory limits', async () => {
|
||||
process.env.CLOUD_RUN_MEMORY = '2Gi'
|
||||
|
||||
const brain = new Brainy({
|
||||
storage: {
|
||||
type: 'filesystem',
|
||||
options: { path: testDir }
|
||||
},
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
// Create many snapshots
|
||||
for (let i = 0; i < 200; i++) {
|
||||
await brain.add({ type: 'document', data: `Data ${i}` })
|
||||
|
||||
if (i % 5 === 0) {
|
||||
await brain.commit({ message: `Checkpoint ${i / 5}`, captureState: true })
|
||||
}
|
||||
}
|
||||
|
||||
// Verify memory limits
|
||||
const stats = brain.getMemoryStats()
|
||||
expect(stats.limits.maxQueryLimit).toBe(5000) // 2GB * 0.25
|
||||
|
||||
// Stream all snapshots (should be ~40)
|
||||
const heapBefore = process.memoryUsage().heapUsed
|
||||
|
||||
let count = 0
|
||||
for await (const commit of brain.streamHistory({ limit: 100 })) {
|
||||
count++
|
||||
}
|
||||
|
||||
const heapAfter = process.memoryUsage().heapUsed
|
||||
const heapGrowth = heapAfter - heapBefore
|
||||
|
||||
expect(count).toBeGreaterThan(0)
|
||||
expect(heapGrowth).toBeLessThan(20 * 1024 * 1024) // < 20MB growth
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
})
|
||||
|
||||
describe('Memory Stats API', () => {
|
||||
it('should provide actionable recommendations', async () => {
|
||||
process.env.CLOUD_RUN_MEMORY = '4Gi'
|
||||
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
// Should have recommendations array
|
||||
expect(stats.recommendations).toBeDefined()
|
||||
expect(Array.isArray(stats.recommendations)).toBe(true)
|
||||
|
||||
// Should not have error recommendations for well-configured system
|
||||
const errorRecommendations = stats.recommendations?.filter(r =>
|
||||
r.toLowerCase().includes('error') || r.toLowerCase().includes('warning')
|
||||
)
|
||||
|
||||
expect(errorRecommendations?.length || 0).toBe(0)
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
|
||||
it('should help debug low limits in production', async () => {
|
||||
// Simulate production issue: container detected but low free memory
|
||||
process.env.CLOUD_RUN_MEMORY = '4Gi'
|
||||
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
// User can see why limits are what they are
|
||||
expect(stats.limits.basis).toBeDefined()
|
||||
expect(stats.memory.containerLimit).toBeDefined()
|
||||
expect(stats.config).toBeDefined()
|
||||
|
||||
// Can debug: "Why is my limit only 10k?"
|
||||
// Answer: basis='containerMemory', container=4GB, 4GB * 0.25 = 1GB -> 10k
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
})
|
||||
|
||||
describe('Zero-Config Behavior', () => {
|
||||
it('should work optimally with no configuration', async () => {
|
||||
process.env.CLOUD_RUN_MEMORY = '4Gi'
|
||||
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
// Zero config, optimal behavior
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
expect(stats.limits.maxQueryLimit).toBe(10000)
|
||||
expect(stats.limits.basis).toBe('containerMemory')
|
||||
|
||||
// Should work without issues
|
||||
for (let i = 0; i < 100; i++) {
|
||||
await brain.add({ type: 'note', data: `Test ${i}` })
|
||||
}
|
||||
|
||||
const results = await brain.find({ limit: 100 })
|
||||
expect(results.length).toBe(100)
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
|
||||
it('should work on bare metal without containers', async () => {
|
||||
// No container env vars
|
||||
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
expect(stats.memory.containerLimit).toBeNull()
|
||||
expect(stats.limits.basis).toBe('freeMemory')
|
||||
expect(stats.limits.maxQueryLimit).toBeGreaterThan(0)
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
})
|
||||
|
||||
describe('Backward Compatibility', () => {
|
||||
it('should not break existing code', async () => {
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
// Existing APIs work
|
||||
await brain.add({ type: 'document', data: 'Test' })
|
||||
const results = await brain.find({ limit: 10 })
|
||||
|
||||
expect(results.length).toBe(1)
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
|
||||
it('should keep getHistory() working as before', async () => {
|
||||
const brain = new Brainy({
|
||||
storage: {
|
||||
type: 'filesystem',
|
||||
options: { path: testDir }
|
||||
},
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
// Create some snapshots
|
||||
for (let i = 0; i < 10; i++) {
|
||||
await brain.add({ type: 'note', data: `Test ${i}` })
|
||||
await brain.commit({ message: `Snapshot ${i}`, captureState: true })
|
||||
}
|
||||
|
||||
// Old API still works
|
||||
const history = await brain.getHistory({ limit: 10 })
|
||||
|
||||
expect(history.length).toBe(10)
|
||||
expect(history[0]).toHaveProperty('hash')
|
||||
expect(history[0]).toHaveProperty('message')
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
})
|
||||
})
|
||||
383
tests/unit/storage/cow/streamHistory.test.ts
Normal file
383
tests/unit/storage/cow/streamHistory.test.ts
Normal file
|
|
@ -0,0 +1,383 @@
|
|||
/**
|
||||
* Unit tests for streamHistory() - Memory-efficient commit history streaming (v5.11.0)
|
||||
*
|
||||
* Tests verify:
|
||||
* - Streaming yields commits one at a time (no accumulation)
|
||||
* - Filtering works correctly (since, until, author)
|
||||
* - Limits work correctly (maxCount)
|
||||
* - Memory efficiency vs getHistory()
|
||||
* - Integration with Brain.streamHistory()
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest'
|
||||
import { Brainy } from '../../../../src/brainy.js'
|
||||
import { mkdtempSync, rmSync } from 'fs'
|
||||
import { tmpdir } from 'os'
|
||||
import { join } from 'path'
|
||||
|
||||
describe('streamHistory() - Memory-Efficient Streaming', () => {
|
||||
let brain: Brainy
|
||||
let testDir: string
|
||||
|
||||
beforeEach(async () => {
|
||||
// Create temporary directory for test
|
||||
testDir = mkdtempSync(join(tmpdir(), 'brainy-stream-history-test-'))
|
||||
|
||||
// Initialize Brain with COW enabled
|
||||
brain = new Brainy({
|
||||
storage: {
|
||||
type: 'filesystem',
|
||||
options: { path: testDir }
|
||||
},
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
})
|
||||
|
||||
afterEach(async () => {
|
||||
await brain.close()
|
||||
rmSync(testDir, { recursive: true, force: true })
|
||||
})
|
||||
|
||||
describe('Basic Streaming', () => {
|
||||
it('should stream commits one at a time', async () => {
|
||||
// Create multiple commits
|
||||
const commitCount = 10
|
||||
|
||||
for (let i = 0; i < commitCount; i++) {
|
||||
await brain.add({
|
||||
type: 'document',
|
||||
data: `Entity ${i}`
|
||||
})
|
||||
|
||||
await brain.commit({ message: `Commit ${i}`, captureState: true })
|
||||
}
|
||||
|
||||
// Stream commits
|
||||
const streamedCommits: any[] = []
|
||||
|
||||
for await (const commit of brain.streamHistory({ limit: commitCount })) {
|
||||
streamedCommits.push(commit)
|
||||
// Verify commit structure
|
||||
expect(commit).toHaveProperty('hash')
|
||||
expect(commit).toHaveProperty('message')
|
||||
expect(commit).toHaveProperty('author')
|
||||
expect(commit).toHaveProperty('timestamp')
|
||||
}
|
||||
|
||||
// Verify all commits were streamed
|
||||
expect(streamedCommits.length).toBe(commitCount)
|
||||
|
||||
// Verify order (newest first)
|
||||
for (let i = 0; i < streamedCommits.length - 1; i++) {
|
||||
expect(streamedCommits[i].timestamp).toBeGreaterThanOrEqual(
|
||||
streamedCommits[i + 1].timestamp
|
||||
)
|
||||
}
|
||||
})
|
||||
|
||||
it('should work with empty history', async () => {
|
||||
// No commits created
|
||||
|
||||
const commits: any[] = []
|
||||
|
||||
for await (const commit of brain.streamHistory({ limit: 100 })) {
|
||||
commits.push(commit)
|
||||
}
|
||||
|
||||
expect(commits.length).toBe(0)
|
||||
})
|
||||
|
||||
it('should handle single commit', async () => {
|
||||
await brain.add({ type: 'document', data: 'Test' })
|
||||
await brain.commit({ message: 'Single commit', captureState: true })
|
||||
|
||||
const commits: any[] = []
|
||||
|
||||
for await (const commit of brain.streamHistory()) {
|
||||
commits.push(commit)
|
||||
}
|
||||
|
||||
expect(commits.length).toBe(1)
|
||||
expect(commits[0].message).toBe('Single commit')
|
||||
})
|
||||
})
|
||||
|
||||
describe('Filtering', () => {
|
||||
beforeEach(async () => {
|
||||
// Create commits with different authors
|
||||
const baseTime = Date.now()
|
||||
|
||||
for (let i = 0; i < 5; i++) {
|
||||
await brain.add({ type: 'document', data: `Entity ${i}` })
|
||||
await brain.commit({
|
||||
message: `Commit ${i}`,
|
||||
author: i % 2 === 0 ? 'alice' : 'bob',
|
||||
captureState: true
|
||||
})
|
||||
}
|
||||
})
|
||||
|
||||
it('should filter by author', async () => {
|
||||
const aliceCommits: any[] = []
|
||||
|
||||
for await (const commit of brain.streamHistory({ author: 'alice' })) {
|
||||
aliceCommits.push(commit)
|
||||
}
|
||||
|
||||
expect(aliceCommits.length).toBe(3) // Commits 0, 2, 4
|
||||
aliceCommits.forEach(commit => {
|
||||
expect(commit.author).toBe('alice')
|
||||
})
|
||||
})
|
||||
|
||||
it('should filter by limit', async () => {
|
||||
const commits: any[] = []
|
||||
|
||||
for await (const commit of brain.streamHistory({ limit: 3 })) {
|
||||
commits.push(commit)
|
||||
}
|
||||
|
||||
expect(commits.length).toBe(3)
|
||||
})
|
||||
|
||||
it('should filter by timestamp (since)', async () => {
|
||||
// Get middle commit timestamp
|
||||
const allCommits = await brain.getHistory({ limit: 100 })
|
||||
const middleTimestamp = allCommits[2].timestamp
|
||||
|
||||
const recentCommits: any[] = []
|
||||
|
||||
for await (const commit of brain.streamHistory({ since: middleTimestamp })) {
|
||||
recentCommits.push(commit)
|
||||
}
|
||||
|
||||
// Should get commits 0, 1, 2 (3 commits at or after middle)
|
||||
expect(recentCommits.length).toBeGreaterThanOrEqual(2)
|
||||
recentCommits.forEach(commit => {
|
||||
expect(commit.timestamp).toBeGreaterThanOrEqual(middleTimestamp)
|
||||
})
|
||||
})
|
||||
|
||||
it('should combine filters', async () => {
|
||||
const commits: any[] = []
|
||||
|
||||
for await (const commit of brain.streamHistory({
|
||||
author: 'alice',
|
||||
limit: 2
|
||||
})) {
|
||||
commits.push(commit)
|
||||
}
|
||||
|
||||
expect(commits.length).toBe(2)
|
||||
commits.forEach(commit => {
|
||||
expect(commit.author).toBe('alice')
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
describe('Memory Efficiency', () => {
|
||||
it('should not accumulate commits in memory', async () => {
|
||||
// Create many commits
|
||||
const commitCount = 100
|
||||
|
||||
for (let i = 0; i < commitCount; i++) {
|
||||
await brain.add({ type: 'document', data: `Entity ${i}` })
|
||||
await brain.commit({ message: `Commit ${i}`, captureState: true })
|
||||
}
|
||||
|
||||
// Track memory usage during streaming
|
||||
const heapBefore = process.memoryUsage().heapUsed
|
||||
let peakHeap = heapBefore
|
||||
|
||||
let count = 0
|
||||
for await (const commit of brain.streamHistory({ limit: commitCount })) {
|
||||
count++
|
||||
|
||||
// Check heap periodically
|
||||
if (count % 10 === 0) {
|
||||
const currentHeap = process.memoryUsage().heapUsed
|
||||
peakHeap = Math.max(peakHeap, currentHeap)
|
||||
}
|
||||
}
|
||||
|
||||
expect(count).toBe(commitCount)
|
||||
|
||||
// Peak heap should not grow significantly (< 10MB increase)
|
||||
const heapGrowth = peakHeap - heapBefore
|
||||
expect(heapGrowth).toBeLessThan(10 * 1024 * 1024) // 10MB threshold
|
||||
})
|
||||
|
||||
it('should stream large histories without error', async () => {
|
||||
// Create a larger history
|
||||
const commitCount = 500
|
||||
|
||||
for (let i = 0; i < commitCount; i++) {
|
||||
await brain.add({ type: 'document', data: `Entity ${i}` })
|
||||
|
||||
// Commit every 10 entities
|
||||
if (i % 10 === 0) {
|
||||
await brain.commit({ message: `Batch ${i / 10}`, captureState: true })
|
||||
}
|
||||
}
|
||||
|
||||
// Stream all commits
|
||||
let count = 0
|
||||
for await (const commit of brain.streamHistory({ limit: 1000 })) {
|
||||
count++
|
||||
}
|
||||
|
||||
expect(count).toBeGreaterThan(0)
|
||||
expect(count).toBeLessThanOrEqual(50) // Should have ~50 commits
|
||||
})
|
||||
})
|
||||
|
||||
describe('Comparison with getHistory()', () => {
|
||||
beforeEach(async () => {
|
||||
// Create test commits
|
||||
for (let i = 0; i < 10; i++) {
|
||||
await brain.add({ type: 'document', data: `Entity ${i}` })
|
||||
await brain.commit({ message: `Commit ${i}`, captureState: true })
|
||||
}
|
||||
})
|
||||
|
||||
it('should return same commits as getHistory()', async () => {
|
||||
// Get commits using both methods
|
||||
const arrayCommits = await brain.getHistory({ limit: 10 })
|
||||
|
||||
const streamedCommits: any[] = []
|
||||
for await (const commit of brain.streamHistory({ limit: 10 })) {
|
||||
streamedCommits.push(commit)
|
||||
}
|
||||
|
||||
expect(streamedCommits.length).toBe(arrayCommits.length)
|
||||
|
||||
// Verify same commits (by hash)
|
||||
for (let i = 0; i < streamedCommits.length; i++) {
|
||||
expect(streamedCommits[i].hash).toBe(arrayCommits[i].hash)
|
||||
expect(streamedCommits[i].message).toBe(arrayCommits[i].message)
|
||||
expect(streamedCommits[i].timestamp).toBe(arrayCommits[i].timestamp)
|
||||
}
|
||||
})
|
||||
|
||||
it('should use less memory than getHistory() for large histories', async () => {
|
||||
// Add more commits
|
||||
for (let i = 10; i < 100; i++) {
|
||||
await brain.add({ type: 'document', data: `Entity ${i}` })
|
||||
await brain.commit({ message: `Commit ${i}`, captureState: true })
|
||||
}
|
||||
|
||||
// Measure getHistory() memory
|
||||
global.gc && global.gc() // Force GC if available
|
||||
const heapBefore = process.memoryUsage().heapUsed
|
||||
|
||||
const arrayCommits = await brain.getHistory({ limit: 100 })
|
||||
|
||||
const heapAfterArray = process.memoryUsage().heapUsed
|
||||
const arrayMemoryUsage = heapAfterArray - heapBefore
|
||||
|
||||
// Clear and measure streamHistory() memory
|
||||
global.gc && global.gc() // Force GC if available
|
||||
const streamHeapBefore = process.memoryUsage().heapUsed
|
||||
|
||||
let count = 0
|
||||
for await (const commit of brain.streamHistory({ limit: 100 })) {
|
||||
count++
|
||||
}
|
||||
|
||||
const streamHeapAfter = process.memoryUsage().heapUsed
|
||||
const streamMemoryUsage = streamHeapAfter - streamHeapBefore
|
||||
|
||||
// Stream should use less memory (or similar, but not more)
|
||||
// Allow some tolerance for measurement variance
|
||||
expect(streamMemoryUsage).toBeLessThanOrEqual(arrayMemoryUsage * 1.5)
|
||||
})
|
||||
})
|
||||
|
||||
describe('Error Handling', () => {
|
||||
it('should throw error if COW not enabled', async () => {
|
||||
// Create brain without COW
|
||||
const memBrain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
silent: true
|
||||
})
|
||||
|
||||
await memBrain.init()
|
||||
|
||||
await expect(async () => {
|
||||
for await (const commit of memBrain.streamHistory()) {
|
||||
// Should not reach here
|
||||
}
|
||||
}).rejects.toThrow(/COW-enabled storage/i)
|
||||
|
||||
await memBrain.close()
|
||||
})
|
||||
|
||||
it('should handle iteration break', async () => {
|
||||
// Create commits
|
||||
for (let i = 0; i < 10; i++) {
|
||||
await brain.add({ type: 'document', data: `Entity ${i}` })
|
||||
await brain.commit({ message: `Commit ${i}`, captureState: true })
|
||||
}
|
||||
|
||||
// Break early
|
||||
let count = 0
|
||||
for await (const commit of brain.streamHistory({ limit: 100 })) {
|
||||
count++
|
||||
if (count === 3) {
|
||||
break // Break early
|
||||
}
|
||||
}
|
||||
|
||||
expect(count).toBe(3)
|
||||
})
|
||||
})
|
||||
|
||||
describe('Production Scenarios', () => {
|
||||
it('should handle pagination via manual iteration', async () => {
|
||||
// Create commits
|
||||
for (let i = 0; i < 30; i++) {
|
||||
await brain.add({ type: 'document', data: `Entity ${i}` })
|
||||
await brain.commit({ message: `Commit ${i}`, captureState: true })
|
||||
}
|
||||
|
||||
// Paginate: 10 per page
|
||||
const page1: any[] = []
|
||||
let count = 0
|
||||
|
||||
for await (const commit of brain.streamHistory()) {
|
||||
page1.push(commit)
|
||||
count++
|
||||
if (count === 10) break
|
||||
}
|
||||
|
||||
expect(page1.length).toBe(10)
|
||||
|
||||
// Can process page without holding full history in memory
|
||||
const timestamps = page1.map(c => c.timestamp)
|
||||
expect(timestamps[0]).toBeGreaterThanOrEqual(timestamps[timestamps.length - 1])
|
||||
})
|
||||
|
||||
it('should support real-time processing (e.g., streaming to UI)', async () => {
|
||||
// Simulate streaming commits to a UI
|
||||
for (let i = 0; i < 20; i++) {
|
||||
await brain.add({ type: 'document', data: `Entity ${i}` })
|
||||
await brain.commit({ message: `Commit ${i}`, captureState: true })
|
||||
}
|
||||
|
||||
// Process commits as they arrive
|
||||
const processedCommits: string[] = []
|
||||
|
||||
for await (const commit of brain.streamHistory({ limit: 20 })) {
|
||||
// Simulate UI update
|
||||
processedCommits.push(commit.message)
|
||||
|
||||
// Simulate async processing (e.g., rendering)
|
||||
await new Promise(resolve => setTimeout(resolve, 1))
|
||||
}
|
||||
|
||||
expect(processedCommits.length).toBe(20)
|
||||
})
|
||||
})
|
||||
})
|
||||
394
tests/unit/utils/memoryLimits.test.ts
Normal file
394
tests/unit/utils/memoryLimits.test.ts
Normal file
|
|
@ -0,0 +1,394 @@
|
|||
/**
|
||||
* Unit tests for memory limit calculation and container detection (v5.11.0)
|
||||
*
|
||||
* Tests verify:
|
||||
* - Container memory detection (cgroup v1/v2, env vars)
|
||||
* - Smart memory limit calculation
|
||||
* - Configuration overrides
|
||||
* - Memory stats API
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest'
|
||||
import { Brainy } from '../../../src/brainy.js'
|
||||
import { ValidationConfig } from '../../../src/utils/paramValidation.js'
|
||||
import { mkdtempSync, rmSync, writeFileSync, mkdirSync } from 'fs'
|
||||
import { tmpdir } from 'os'
|
||||
import { join } from 'path'
|
||||
|
||||
describe('Memory Limits - Container Detection & Smart Calculation', () => {
|
||||
let testDir: string
|
||||
let originalEnv: Record<string, string | undefined>
|
||||
|
||||
beforeEach(() => {
|
||||
testDir = mkdtempSync(join(tmpdir(), 'brainy-memory-test-'))
|
||||
|
||||
// Save original environment variables
|
||||
originalEnv = {
|
||||
CLOUD_RUN_MEMORY: process.env.CLOUD_RUN_MEMORY,
|
||||
MEMORY_LIMIT: process.env.MEMORY_LIMIT
|
||||
}
|
||||
|
||||
// Reset ValidationConfig singleton before each test
|
||||
ValidationConfig.reset()
|
||||
})
|
||||
|
||||
afterEach(() => {
|
||||
rmSync(testDir, { recursive: true, force: true })
|
||||
|
||||
// Restore original environment
|
||||
Object.keys(originalEnv).forEach(key => {
|
||||
if (originalEnv[key] === undefined) {
|
||||
delete process.env[key]
|
||||
} else {
|
||||
process.env[key] = originalEnv[key]
|
||||
}
|
||||
})
|
||||
|
||||
// Reset ValidationConfig after each test
|
||||
ValidationConfig.reset()
|
||||
})
|
||||
|
||||
describe('Container Memory Detection', () => {
|
||||
it('should detect Cloud Run memory limit from env var', () => {
|
||||
process.env.CLOUD_RUN_MEMORY = '4Gi'
|
||||
|
||||
const config = ValidationConfig.getInstance()
|
||||
|
||||
expect(config.detectedContainerLimit).toBe(4 * 1024 * 1024 * 1024)
|
||||
expect(config.limitBasis).toBe('containerMemory')
|
||||
|
||||
// 4GB * 0.25 = 1GB query memory = 10k limit
|
||||
expect(config.maxLimit).toBeGreaterThan(5000)
|
||||
})
|
||||
|
||||
it('should detect Cloud Run memory limit in Mi units', () => {
|
||||
process.env.CLOUD_RUN_MEMORY = '512Mi'
|
||||
|
||||
const config = ValidationConfig.getInstance()
|
||||
|
||||
expect(config.detectedContainerLimit).toBe(512 * 1024 * 1024)
|
||||
expect(config.limitBasis).toBe('containerMemory')
|
||||
|
||||
// 512MB * 0.25 = 128MB query memory
|
||||
expect(config.maxLimit).toBeGreaterThan(0)
|
||||
})
|
||||
|
||||
it('should detect generic MEMORY_LIMIT env var', () => {
|
||||
process.env.MEMORY_LIMIT = String(2 * 1024 * 1024 * 1024) // 2GB
|
||||
|
||||
const config = ValidationConfig.getInstance()
|
||||
|
||||
expect(config.detectedContainerLimit).toBe(2 * 1024 * 1024 * 1024)
|
||||
expect(config.limitBasis).toBe('containerMemory')
|
||||
})
|
||||
|
||||
it('should fall back to free memory if no container detected', () => {
|
||||
// No environment variables set
|
||||
|
||||
const config = ValidationConfig.getInstance()
|
||||
|
||||
expect(config.limitBasis).toBe('freeMemory')
|
||||
expect(config.maxLimit).toBeGreaterThan(0)
|
||||
})
|
||||
})
|
||||
|
||||
describe('Smart Memory Limit Calculation', () => {
|
||||
it('should allocate 25% of container memory for queries', () => {
|
||||
process.env.CLOUD_RUN_MEMORY = '4Gi'
|
||||
|
||||
const config = ValidationConfig.getInstance()
|
||||
|
||||
// 4GB * 0.25 = 1GB for queries
|
||||
// 1GB / 100MB = 10 units * 1000 = 10,000 limit
|
||||
expect(config.maxLimit).toBe(10000)
|
||||
})
|
||||
|
||||
it('should respect absolute maximum of 100k', () => {
|
||||
// Simulate huge container
|
||||
process.env.MEMORY_LIMIT = String(100 * 1024 * 1024 * 1024) // 100GB
|
||||
|
||||
const config = ValidationConfig.getInstance()
|
||||
|
||||
// Should cap at 100,000 even with huge memory
|
||||
expect(config.maxLimit).toBe(100000)
|
||||
})
|
||||
|
||||
it('should handle small containers gracefully', () => {
|
||||
process.env.CLOUD_RUN_MEMORY = '512Mi' // Use 512MB instead of 128MB for realistic test
|
||||
|
||||
const config = ValidationConfig.getInstance()
|
||||
|
||||
// 512MB * 0.25 = 128MB for queries
|
||||
// 128MB / 100MB = 1.28 floor to 1 * 1000 = 1000 limit
|
||||
expect(config.maxLimit).toBeGreaterThan(0)
|
||||
expect(config.limitBasis).toBe('containerMemory')
|
||||
})
|
||||
})
|
||||
|
||||
describe('Configuration Overrides', () => {
|
||||
it('should respect maxQueryLimit override', () => {
|
||||
const config = ValidationConfig.getInstance({ maxQueryLimit: 50000 })
|
||||
|
||||
expect(config.maxLimit).toBe(50000)
|
||||
expect(config.limitBasis).toBe('override')
|
||||
})
|
||||
|
||||
it('should respect reservedQueryMemory override', () => {
|
||||
// Reserve 1GB for queries
|
||||
const config = ValidationConfig.getInstance({
|
||||
reservedQueryMemory: 1 * 1024 * 1024 * 1024
|
||||
})
|
||||
|
||||
expect(config.maxLimit).toBe(10000) // 1GB / 100MB * 1000
|
||||
expect(config.limitBasis).toBe('reservedMemory')
|
||||
})
|
||||
|
||||
it('should prioritize maxQueryLimit over reservedQueryMemory', () => {
|
||||
const config = ValidationConfig.getInstance({
|
||||
maxQueryLimit: 25000,
|
||||
reservedQueryMemory: 1 * 1024 * 1024 * 1024
|
||||
})
|
||||
|
||||
expect(config.maxLimit).toBe(25000)
|
||||
expect(config.limitBasis).toBe('override')
|
||||
})
|
||||
|
||||
it('should cap explicit overrides at 100k for safety', () => {
|
||||
const config = ValidationConfig.getInstance({
|
||||
maxQueryLimit: 200000 // Try to set above max
|
||||
})
|
||||
|
||||
expect(config.maxLimit).toBe(100000) // Capped
|
||||
expect(config.limitBasis).toBe('override')
|
||||
})
|
||||
})
|
||||
|
||||
describe('ValidationConfig Reconfiguration', () => {
|
||||
it('should reconfigure singleton with new options', () => {
|
||||
const config1 = ValidationConfig.getInstance()
|
||||
const originalLimit = config1.maxLimit
|
||||
|
||||
// Reconfigure
|
||||
const config2 = ValidationConfig.reconfigure({ maxQueryLimit: 30000 })
|
||||
|
||||
expect(config2.maxLimit).toBe(30000)
|
||||
expect(config2.limitBasis).toBe('override')
|
||||
|
||||
// Verify singleton updated
|
||||
const config3 = ValidationConfig.getInstance()
|
||||
expect(config3.maxLimit).toBe(30000)
|
||||
})
|
||||
|
||||
it('should reset singleton', () => {
|
||||
const config1 = ValidationConfig.getInstance({ maxQueryLimit: 10000 })
|
||||
expect(config1.maxLimit).toBe(10000)
|
||||
|
||||
ValidationConfig.reset()
|
||||
|
||||
const config2 = ValidationConfig.getInstance()
|
||||
// Should recalculate based on system memory
|
||||
expect(config2.maxLimit).not.toBe(10000)
|
||||
})
|
||||
})
|
||||
|
||||
describe('Brain Integration', () => {
|
||||
it('should configure memory limits via Brain constructor', async () => {
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
maxQueryLimit: 15000,
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
expect(stats.limits.maxQueryLimit).toBe(15000)
|
||||
expect(stats.limits.basis).toBe('override')
|
||||
expect(stats.config.maxQueryLimit).toBe(15000)
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
|
||||
it('should configure reserved memory via Brain constructor', async () => {
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
reservedQueryMemory: 500 * 1024 * 1024, // 500MB
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
// 500MB / 100MB * 1000 = 5000
|
||||
expect(stats.limits.maxQueryLimit).toBe(5000)
|
||||
expect(stats.limits.basis).toBe('reservedMemory')
|
||||
expect(stats.config.reservedQueryMemory).toBe(500 * 1024 * 1024)
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
|
||||
it('should auto-detect container limits when no config provided', async () => {
|
||||
process.env.CLOUD_RUN_MEMORY = '2Gi'
|
||||
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
expect(stats.memory.containerLimit).toBe(2 * 1024 * 1024 * 1024)
|
||||
expect(stats.limits.basis).toBe('containerMemory')
|
||||
// 2GB * 0.25 = 500MB -> 5000 limit
|
||||
expect(stats.limits.maxQueryLimit).toBe(5000)
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
})
|
||||
|
||||
describe('getMemoryStats() API', () => {
|
||||
it('should return complete memory statistics', async () => {
|
||||
process.env.CLOUD_RUN_MEMORY = '4Gi'
|
||||
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
maxQueryLimit: 20000,
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
// Memory stats
|
||||
expect(stats.memory).toHaveProperty('heapUsed')
|
||||
expect(stats.memory).toHaveProperty('heapTotal')
|
||||
expect(stats.memory).toHaveProperty('external')
|
||||
expect(stats.memory).toHaveProperty('rss')
|
||||
expect(stats.memory).toHaveProperty('free')
|
||||
expect(stats.memory).toHaveProperty('total')
|
||||
expect(stats.memory).toHaveProperty('containerLimit')
|
||||
|
||||
expect(stats.memory.containerLimit).toBe(4 * 1024 * 1024 * 1024)
|
||||
|
||||
// Limits
|
||||
expect(stats.limits.maxQueryLimit).toBe(20000)
|
||||
expect(stats.limits.basis).toBe('override')
|
||||
expect(stats.limits.maxQueryLength).toBeGreaterThan(0)
|
||||
expect(stats.limits.maxVectorDimensions).toBe(384)
|
||||
|
||||
// Config
|
||||
expect(stats.config.maxQueryLimit).toBe(20000)
|
||||
|
||||
// Recommendations
|
||||
expect(Array.isArray(stats.recommendations)).toBe(true)
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
|
||||
it('should provide recommendations when appropriate', async () => {
|
||||
// Large container but using free memory basis
|
||||
process.env.CLOUD_RUN_MEMORY = '4Gi'
|
||||
|
||||
// Don't set overrides, let it use containerMemory
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
expect(stats.recommendations).toBeDefined()
|
||||
expect(stats.recommendations!.length).toBeGreaterThanOrEqual(0)
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
|
||||
it('should handle browser environment gracefully', async () => {
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
// Should not crash in any environment
|
||||
expect(stats).toBeDefined()
|
||||
expect(stats.limits).toBeDefined()
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
})
|
||||
|
||||
describe('Production Scenarios', () => {
|
||||
it('should handle 4GB Cloud Run container optimally', async () => {
|
||||
process.env.CLOUD_RUN_MEMORY = '4Gi'
|
||||
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
// Should allocate 1GB (25% of 4GB) for queries
|
||||
expect(stats.memory.containerLimit).toBe(4 * 1024 * 1024 * 1024)
|
||||
expect(stats.limits.maxQueryLimit).toBe(10000)
|
||||
expect(stats.limits.basis).toBe('containerMemory')
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
|
||||
it('should allow manual override for power users', async () => {
|
||||
process.env.CLOUD_RUN_MEMORY = '4Gi'
|
||||
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
maxQueryLimit: 50000, // Power user wants higher limit
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
expect(stats.limits.maxQueryLimit).toBe(50000)
|
||||
expect(stats.limits.basis).toBe('override')
|
||||
|
||||
// Should note override in recommendations
|
||||
const overrideNote = stats.recommendations?.find(r => r.includes('override'))
|
||||
expect(overrideNote).toBeDefined()
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
|
||||
it('should handle bare metal deployment (no container)', async () => {
|
||||
// No container env vars
|
||||
|
||||
const brain = new Brainy({
|
||||
storage: { type: 'memory' },
|
||||
silent: true
|
||||
})
|
||||
|
||||
await brain.init()
|
||||
|
||||
const stats = brain.getMemoryStats()
|
||||
|
||||
expect(stats.memory.containerLimit).toBeNull()
|
||||
expect(stats.limits.basis).toBe('freeMemory')
|
||||
expect(stats.limits.maxQueryLimit).toBeGreaterThan(0)
|
||||
|
||||
await brain.close()
|
||||
})
|
||||
})
|
||||
})
|
||||
Loading…
Add table
Add a link
Reference in a new issue