fix: vfs.rename() issues a metadata-only update + rollback of fresh adds removes them

Two fixes reported/found by downstream consumers:

(1) vfs.rename() spread the entire fetched entity into brain.update(),
forwarding a vector field that failed the 384-dimension validation when the
entity was fetched without vectors — every rename threw. A rename is a
path/metadata change, never a content change: the update is now metadata-only
(no vector touched, no re-embedding). Regression test covers the verbatim
consumer repro plus cross-directory moves and EEXIST.

(2) AddToHNSWOperation.itemExists() probed an optional getItem capability
with `await (index as any).getItem?.(id)` — `await undefined` resolves
without throwing, so every item was reported as pre-existing and rollback of
fresh adds never removed them, leaving phantom index entries after a failed
transaction. The probe now feature-detects the method and defaults to false
when absent; update flows pair this op with RemoveFromHNSWOperation whose own
rollback restores the prior vector, so reverse-order rollback reconstructs
the original state either way.

1479/1479 unit suite passing.
This commit is contained in:
David Snelling 2026-06-11 14:59:40 -07:00
parent 9b52629a0a
commit ac29b0e650
3 changed files with 97 additions and 18 deletions

View file

@ -51,13 +51,26 @@ export class AddToHNSWOperation implements Operation {
} }
/** /**
* Check if item exists in index * Check if item exists in index.
*
* `getItem` is an optional provider capability that the built-in HNSW index
* does not implement. When the capability is missing the answer must be
* `false`, not `true`: `await undefined` resolves without throwing, so the
* old probe reported every item as pre-existing and rollback of fresh adds
* never removed them leaving phantom index entries after a failed
* transaction. The safe default is to remove what this operation added;
* update flows pair this op with a RemoveFromHNSWOperation whose own
* rollback restores the prior vector, so reverse-order rollback
* reconstructs the original state either way.
*/ */
private async itemExists(id: string): Promise<boolean> { private async itemExists(id: string): Promise<boolean> {
const index = this.index as HNSWIndex & {
getItem?: (id: string) => Promise<unknown>
}
if (typeof index.getItem !== 'function') return false
try { try {
// Try to get item - if exists, no error const item = await index.getItem(id)
await (this.index as any).getItem?.(id) return item !== undefined && item !== null
return true
} catch { } catch {
return false return false
} }

View file

@ -1664,17 +1664,6 @@ export class VirtualFileSystem implements IVirtualFileSystem {
if (err.code !== VFSErrorCode.ENOENT) throw err if (err.code !== VFSErrorCode.ENOENT) throw err
} }
// Update entity metadata
const updatedEntity = {
...entity,
metadata: {
...entity.metadata,
path: newPath,
name: this.getBasename(newPath),
modified: Date.now()
}
}
// Update parent relationships if needed // Update parent relationships if needed
const oldParentPath = this.getParentPath(oldPath) const oldParentPath = this.getParentPath(oldPath)
const newParentPath = this.getParentPath(newPath) const newParentPath = this.getParentPath(newPath)
@ -1700,10 +1689,19 @@ export class VirtualFileSystem implements IVirtualFileSystem {
} }
} }
// Update the entity // A rename is a path/metadata change, never a content change — issue a
// metadata-only update. Spreading the whole entity here used to forward
// its vector field into update(), which failed dimension validation when
// the entity was fetched without vectors (and would needlessly touch the
// vector index when it wasn't).
await this.brain.update({ await this.brain.update({
...updatedEntity, id: entityId,
id: entityId metadata: {
...entity.metadata,
path: newPath,
name: this.getBasename(newPath),
modified: Date.now()
}
}) })
// Update path cache // Update path cache

View file

@ -0,0 +1,68 @@
/**
* @module vfs/vfs-rename-metadata-only.test
* @description Regression test for the vfs.rename() vector-dimension crash
* (7.31.7). rename() used to spread the entire fetched entity into
* brain.update(), forwarding a vector field that failed the 384-dimension
* validation when the entity was fetched without vectors. A rename is a
* path/metadata change the update must be metadata-only.
*
* Production repro (verbatim from the consumer report):
* await brain.vfs.writeFile('/a.txt', 'x')
* await brain.vfs.rename('/a.txt', '/b.txt') // threw pre-7.31.7
*/
import { describe, it, expect, beforeEach, afterEach } from 'vitest'
import { Brainy } from '../../../src/index.js'
describe('vfs.rename() issues a metadata-only update (7.31.7)', () => {
let brain: Brainy
beforeEach(async () => {
brain = new Brainy({ storage: { type: 'memory' } })
await brain.init()
})
afterEach(async () => {
await brain.close()
})
it('renames a file without touching vectors (the production repro)', async () => {
await brain.vfs.writeFile('/a.txt', 'x')
await brain.vfs.rename('/a.txt', '/b.txt')
expect(await brain.vfs.exists('/b.txt')).toBe(true)
expect(await brain.vfs.exists('/a.txt')).toBe(false)
const content = await brain.vfs.readFile('/b.txt')
expect(content.toString()).toBe('x')
})
it('preserves file content and custom metadata across rename', async () => {
await brain.vfs.writeFile('/notes/draft.md', 'hello world')
await brain.vfs.rename('/notes/draft.md', '/notes/final.md')
const content = await brain.vfs.readFile('/notes/final.md')
expect(content.toString()).toBe('hello world')
// The renamed entity's metadata carries the new basename
const stat = await brain.vfs.stat('/notes/final.md')
expect(stat.size).toBeGreaterThan(0)
expect(await brain.vfs.exists('/notes/draft.md')).toBe(false)
})
it('moves a file across directories', async () => {
await brain.vfs.mkdir('/src')
await brain.vfs.mkdir('/dest')
await brain.vfs.writeFile('/src/file.txt', 'moving')
await brain.vfs.rename('/src/file.txt', '/dest/file.txt')
expect(await brain.vfs.exists('/dest/file.txt')).toBe(true)
expect(await brain.vfs.exists('/src/file.txt')).toBe(false)
const content = await brain.vfs.readFile('/dest/file.txt')
expect(content.toString()).toBe('moving')
})
it('throws EEXIST when the target already exists', async () => {
await brain.vfs.writeFile('/one.txt', '1')
await brain.vfs.writeFile('/two.txt', '2')
await expect(brain.vfs.rename('/one.txt', '/two.txt')).rejects.toThrow(/exists/i)
})
})