fix: implement type-aware storage prefixes for commits and trees

Fixed critical bug where BlobStorage hardcoded 'blob:' prefix in 10 locations,
ignoring the 'type' parameter passed to write operations. This caused:
- Commits stored as blob:${hash} instead of commit:${hash}
- Trees stored as blob:${hash} instead of tree:${hash}
- brain.getHistory() returning empty arrays

Changes:
- src/storage/cow/BlobStorage.ts: Implement type-aware prefixes in 10 methods
  - write(), read(), has(), delete(), getMetadata(), listBlobs()
  - writeMultipart(), incrementRefCount(), decrementRefCount()
- tests/integration/cow-commit-storage.test.ts: Add regression tests (6 tests)

Backward compatibility: read() auto-detects type by trying commit:, tree:, blob:
prefixes, allowing old blob:* files to be read.

Works for ALL storage adapters (filesystem, S3, Azure, GCS, R2, memory, OPFS).

Fixes: Workshop team bug report (getHistory returns empty despite commits)
Tests: 6/6 new tests pass, 6/6 existing COW tests pass (no regressions)
This commit is contained in:
David Snelling 2025-11-04 15:03:05 -08:00
parent 6d82cc45ed
commit bdca84c942
2 changed files with 264 additions and 26 deletions

View file

@ -222,11 +222,13 @@ export class BlobStorage {
await this.writeMultipart(hash, finalData, metadata)
} else {
// Small blob: single write
await this.adapter.put(`blob:${hash}`, finalData)
const prefix = options.type || 'blob'
await this.adapter.put(`${prefix}:${hash}`, finalData)
}
// Write metadata
await this.adapter.put(`blob-meta:${hash}`, Buffer.from(JSON.stringify(metadata)))
const prefix = options.type || 'blob'
await this.adapter.put(`${prefix}-meta:${hash}`, Buffer.from(JSON.stringify(metadata)))
// Update cache (write-through)
this.addToCache(hash, data, metadata)
@ -265,21 +267,32 @@ export class BlobStorage {
this.stats.cacheMisses++
}
// Read from storage
const data = await this.adapter.get(`blob:${hash}`)
// Try to read metadata to determine type (for backward compatibility)
// Try commit, tree, then blob prefixes
let prefix: string | null = null
let metadataBuffer: Buffer | undefined
let metadata: BlobMetadata | undefined
for (const tryPrefix of ['commit', 'tree', 'blob']) {
metadataBuffer = await this.adapter.get(`${tryPrefix}-meta:${hash}`)
if (metadataBuffer) {
prefix = tryPrefix
metadata = JSON.parse(metadataBuffer.toString())
break
}
}
if (!prefix || !metadata) {
throw new Error(`Blob metadata not found: ${hash}`)
}
// Read from storage using determined prefix
const data = await this.adapter.get(`${prefix}:${hash}`)
if (!data) {
throw new Error(`Blob not found: ${hash}`)
}
// Read metadata
const metadataBuffer = await this.adapter.get(`blob-meta:${hash}`)
if (!metadataBuffer) {
throw new Error(`Blob metadata not found: ${hash}`)
}
const metadata: BlobMetadata = JSON.parse(metadataBuffer.toString())
// Decompress if needed
let finalData = data
@ -315,9 +328,15 @@ export class BlobStorage {
return true
}
// Check storage
const exists = await this.adapter.get(`blob:${hash}`)
return exists !== undefined
// Check storage - try all prefixes for backward compatibility
for (const prefix of ['commit', 'tree', 'blob']) {
const exists = await this.adapter.get(`${prefix}:${hash}`)
if (exists !== undefined) {
return true
}
}
return false
}
/**
@ -339,11 +358,21 @@ export class BlobStorage {
return
}
// Determine prefix by checking which one exists
let prefix = 'blob'
for (const tryPrefix of ['commit', 'tree', 'blob']) {
const exists = await this.adapter.get(`${tryPrefix}:${hash}`)
if (exists !== undefined) {
prefix = tryPrefix
break
}
}
// Delete blob data
await this.adapter.delete(`blob:${hash}`)
await this.adapter.delete(`${prefix}:${hash}`)
// Delete metadata
await this.adapter.delete(`blob-meta:${hash}`)
await this.adapter.delete(`${prefix}-meta:${hash}`)
// Remove from cache
this.removeFromCache(hash)
@ -359,11 +388,16 @@ export class BlobStorage {
* @returns Blob metadata
*/
async getMetadata(hash: string): Promise<BlobMetadata | undefined> {
const data = await this.adapter.get(`blob-meta:${hash}`)
if (!data) {
return undefined
// Try to read metadata with type-aware prefix (backward compatible)
// Try commit, tree, then blob prefixes
for (const prefix of ['commit', 'tree', 'blob']) {
const data = await this.adapter.get(`${prefix}-meta:${hash}`)
if (data) {
return JSON.parse(data.toString())
}
}
return JSON.parse(data.toString())
return undefined
}
/**
@ -397,8 +431,18 @@ export class BlobStorage {
* @returns Array of blob hashes
*/
async listBlobs(): Promise<string[]> {
const keys = await this.adapter.list('blob:')
return keys.map((key: string) => key.replace(/^blob:/, ''))
// List all types of blobs
const hashes = new Set<string>()
for (const prefix of ['commit', 'tree', 'blob']) {
const keys = await this.adapter.list(`${prefix}:`)
keys.forEach((key: string) => {
const hash = key.replace(new RegExp(`^${prefix}:`), '')
hashes.add(hash)
})
}
return Array.from(hashes)
}
/**
@ -489,7 +533,8 @@ export class BlobStorage {
): Promise<void> {
// For now, just write as single blob
// TODO: Implement actual multipart upload for S3/R2/GCS
await this.adapter.put(`blob:${hash}`, data)
const prefix = metadata.type || 'blob'
await this.adapter.put(`${prefix}:${hash}`, data)
}
/**
@ -503,8 +548,9 @@ export class BlobStorage {
metadata.refCount++
const prefix = metadata.type || 'blob'
await this.adapter.put(
`blob-meta:${hash}`,
`${prefix}-meta:${hash}`,
Buffer.from(JSON.stringify(metadata))
)
@ -522,8 +568,9 @@ export class BlobStorage {
metadata.refCount = Math.max(0, metadata.refCount - 1)
const prefix = metadata.type || 'blob'
await this.adapter.put(
`blob-meta:${hash}`,
`${prefix}-meta:${hash}`,
Buffer.from(JSON.stringify(metadata))
)

View file

@ -0,0 +1,191 @@
/**
* Regression test for v5.3.3 bug fix:
* Commits were being stored as blob:${hash} instead of commit:${hash}
*
* This caused getHistory() to return empty arrays because it couldn't find
* commit objects on disk.
*
* Related bugs:
* - Workshop team report: BRAINY_V5.3.0_SNAPSHOT_BUG_REPORT.md
* - Root cause: BlobStorage.ts hardcoded 'blob:' prefix in 9 locations
*/
import { describe, it, expect, beforeEach, afterEach } from 'vitest'
import { Brainy } from '../../src/brainy.js'
import * as fs from 'fs/promises'
import * as path from 'path'
describe('COW Commit Storage Type-Aware Prefixes', () => {
let brain: Brainy
let testDir: string
beforeEach(async () => {
testDir = path.join('/tmp', `brainy-cow-test-${Date.now()}`)
brain = new Brainy({
storage: {
type: 'filesystem',
path: testDir,
branch: 'main',
enableCompression: true
},
disableAutoRebuild: true,
silent: true
})
await brain.init()
})
afterEach(async () => {
// Clean up test directory
try {
await fs.rm(testDir, { recursive: true, force: true })
} catch (err) {
// Ignore cleanup errors
}
})
it('should store commits with commit: prefix (not blob: prefix)', async () => {
// Create a commit
await brain.commit('Test commit for type-aware storage')
// Check filesystem directly
const cowDir = path.join(testDir, '_cow')
const files = await fs.readdir(cowDir)
// Should have commit: files
const commitFiles = files.filter(f => f.startsWith('commit:'))
expect(commitFiles.length).toBeGreaterThan(0)
// Should NOT have blob: files that are actually commits
// (blob: files should only be for actual blob data)
const blobFiles = files.filter(f => f.startsWith('blob:') && !f.includes('-meta'))
// Read metadata of blob files to ensure none are commits
for (const blobFile of blobFiles) {
const metaFile = blobFile.replace('blob:', 'blob:-meta:')
if (files.includes(metaFile)) {
const metaPath = path.join(cowDir, metaFile)
const metaContent = await fs.readFile(metaPath, 'utf8')
const metadata = JSON.parse(metaContent)
expect(metadata.type).not.toBe('commit')
}
}
})
it('should allow getHistory() to retrieve commits', async () => {
// Create multiple commits
await brain.commit('First commit')
await brain.add({
data: 'Testing commit storage',
type: 'concept'
})
await brain.commit('Second commit with entity')
// Get history - should NOT be empty
const history = await brain.getHistory({ limit: 10 })
expect(history).toBeDefined()
expect(Array.isArray(history)).toBe(true)
expect(history.length).toBeGreaterThanOrEqual(2)
// Verify commit structure
expect(history[0]).toHaveProperty('hash')
expect(history[0]).toHaveProperty('message')
expect(history[0]).toHaveProperty('timestamp')
expect(history[0]).toHaveProperty('author')
})
it('should store trees with tree: prefix (if trees are created)', async () => {
// Add an entity and commit
await brain.add({
data: 'Testing tree storage',
type: 'concept'
})
await brain.commit('Commit with tree')
// Check filesystem - trees might or might not be created depending on implementation
// The important thing is that IF trees are created, they use tree: prefix
const cowDir = path.join(testDir, '_cow')
const files = await fs.readdir(cowDir)
// Verify commit files exist (this is the critical part)
const commitFiles = files.filter(f => f.startsWith('commit:'))
expect(commitFiles.length).toBeGreaterThan(0)
// If tree files exist, they should use tree: prefix (not blob:)
const treeFiles = files.filter(f => f.startsWith('tree:'))
const blobTrees = files.filter(f => f.startsWith('blob:') && !f.includes('-meta'))
// Trees should be in tree: files, not blob: files
// (Or no tree files at all if implementation doesn't create them)
expect(blobTrees.filter(f => f.includes('tree')).length).toBe(0)
})
it('should maintain backward compatibility with old blob: prefix', async () => {
// This test verifies that read() auto-detects type by trying multiple prefixes
// We'll verify this by checking that the auto-detection code works
// Create a commit normally (will use commit: prefix)
await brain.commit('Test commit for backward compat check')
// The commit should be readable even though read() tries multiple prefixes
const history = await brain.getHistory({ limit: 1 })
expect(history.length).toBe(1)
// Verify the commit hash is readable via BlobStorage
const blobStorage = (brain as any).storage.blobStorage
const commitHash = history[0].hash
// This should work via auto-detection
const readData = await blobStorage.read(commitHash)
expect(readData).toBeDefined()
expect(readData.length).toBeGreaterThan(0)
})
it('should handle fork() and snapshot creation with proper commit storage', async () => {
// Add some data
await brain.add({
data: 'Testing snapshots',
type: 'concept'
})
await brain.commit('Commit before fork')
// Create a fork (snapshot branch)
const snapshotBranch = `snapshot-${Date.now()}`
await brain.fork(snapshotBranch)
// Get history - should work (this is the critical test)
const history = await brain.getHistory({ limit: 10 })
expect(history.length).toBeGreaterThanOrEqual(1)
// History working proves commits are stored correctly
})
it('should properly delete commits with type-aware prefix', async () => {
// Create a commit
await brain.commit('Commit to delete')
const history = await brain.getHistory({ limit: 1 })
const commitHash = history[0].hash
// Delete via BlobStorage
const blobStorage = (brain as any).storage.blobStorage
await blobStorage.delete(commitHash)
// Verify deleted
const exists = await blobStorage.has(commitHash)
expect(exists).toBe(false)
// Verify files removed from disk
const cowDir = path.join(testDir, '_cow')
const files = await fs.readdir(cowDir)
const commitFile = files.find(f => f.includes(commitHash) && f.startsWith('commit:'))
expect(commitFile).toBeUndefined()
})
})