2025-12-11 13:26:07 -08:00
/ * *
* VFS bulkWrite Race Condition Fix Tests ( v6 . 5.0 )
*
* Tests for the race condition where parallel mkdir and write operations
* could create duplicate directory entities , causing files to become invisible .
*
* Bug : When mkdir and write for related paths are in the same parallel batch ,
* the mkdir mutex race window can create duplicate entities . Files created
* with the "wrong" parent entity become invisible in tree traversal .
*
* Fix : Sort operations so mkdirs run first ( sequentially , by depth ) , then
* other operations in parallel batches .
* /
import { describe , it , expect , beforeEach } from 'vitest'
import { Brainy } from '../../src/brainy.js'
import { VirtualFileSystem } from '../../src/vfs/VirtualFileSystem.js'
describe ( 'VFS bulkWrite Race Condition Fix' , ( ) = > {
let brain : Brainy
let vfs : VirtualFileSystem
beforeEach ( async ( ) = > {
feat(8.0)!: flip requireSubtype default to true (BRAINY-8.0-SUBTYPE-CONTRACT § C-1)
Brainy 8.0 makes subtype required by default on every public write path
(`add`, `addMany`, `update`, `relate`, `relateMany`, `updateRelation`,
import). Per the locked C-1 contract, every entity and relation gets a
non-empty subtype string by the time the storage layer sees it.
OPT-OUT REMAINS FULLY SUPPORTED
The runtime flag is still consumer-controlled. Three opt-out paths
cover migration / legacy fixtures / typed escape:
- `new Brainy({ requireSubtype: false })` — last-resort: turn off the
contract entirely. Recommended only for migration windows or test
fixtures that legitimately can't supply a subtype.
- `new Brainy({ requireSubtype: { except: [NounType.Thing, ...] } })` —
per-type allowlist: strict everywhere except the listed types.
- `brain.requireSubtype(type, options)` — per-type registration with
optional vocabulary. Composes with the brain-wide flag.
Default is now `true`. Opt-out is explicit and documented; nothing
silently degrades.
TEST SWEEP
Bulk-applied `requireSubtype: false` to every `new Brainy({...})` call
site across 120 test files. Three sed patterns covered the shapes:
- `new Brainy({` → `new Brainy({ requireSubtype: false,`
- `new Brainy<T>({` → `new Brainy<T>({ requireSubtype: false,`
- `new Brainy()` → `new Brainy({ requireSubtype: false })`
tests/helpers/test-factory.ts → createTestConfig() defaults
`requireSubtype: false` so test files using the helper inherit the
opt-out without per-site edits.
The test sites that DO exercise subtype semantics (the
subtype-and-facets suite, the strict-mode-self-test suite, the verb-
subtype-and-enforcement suite, etc.) already pass real subtypes — they
were the 7.30.x acceptance tests for this contract. Those tests
continue to pass unchanged.
CHANGES
src/brainy.ts
- normalizeConfig() — `requireSubtype` default `false` → `true`.
Comment refreshed to document the three opt-out paths.
tests/* (120 files)
- Bulk-edited brain construction sites. No functional test changes; the
opt-out preserves the test author's original intent.
tests/helpers/test-factory.ts
- createTestConfig() base config gains `requireSubtype: false`.
NO-OP for consumers who were already passing subtype on every write.
For consumers who weren't, the upgrade path is one of the three opt-out
forms above. Migration recipe documented in 8.0 release notes (next
commit).
VERIFICATION
- npx tsc --noEmit: clean
- npm test: 1408 / 1409 (same pre-existing race-condition outstanding;
no other regressions from the flip)
2026-06-09 14:58:25 -07:00
brain = new Brainy ( { requireSubtype : false ,
2025-12-11 13:26:07 -08:00
storage : { type : 'memory' } ,
embeddingModel : 'Q8'
} )
await brain . init ( )
vfs = brain . vfs
await vfs . init ( )
} )
describe ( 'operation ordering' , ( ) = > {
it ( 'should create directories before files when mixed in same batch' , async ( ) = > {
// This is the exact scenario that triggered the race condition:
// mkdir and write for related paths in the same batch
const result = await vfs . bulkWrite ( [
{ type : 'write' , path : '/data/config.json' , data : '{}' } ,
{ type : 'mkdir' , path : '/data' } ,
{ type : 'write' , path : '/data/users.json' , data : '[]' } ,
{ type : 'mkdir' , path : '/logs' } ,
{ type : 'write' , path : '/logs/app.log' , data : 'log entry' }
] )
expect ( result . successful ) . toBe ( 5 )
expect ( result . failed . length ) . toBe ( 0 )
// Verify all files are visible
const dataFiles = await vfs . readdir ( '/data' )
expect ( dataFiles ) . toContain ( 'config.json' )
expect ( dataFiles ) . toContain ( 'users.json' )
const logFiles = await vfs . readdir ( '/logs' )
expect ( logFiles ) . toContain ( 'app.log' )
} )
it ( 'should handle nested directory creation in correct order' , async ( ) = > {
const result = await vfs . bulkWrite ( [
{ type : 'write' , path : '/a/b/c/file.txt' , data : 'content' } ,
{ type : 'mkdir' , path : '/a/b/c' } , // deepest
{ type : 'mkdir' , path : '/a' } , // shallowest
{ type : 'mkdir' , path : '/a/b' } , // middle
] )
expect ( result . successful ) . toBe ( 4 )
// Verify tree structure is correct
const rootDirs = await vfs . readdir ( '/' )
expect ( rootDirs ) . toContain ( 'a' )
const aContent = await vfs . readdir ( '/a' )
expect ( aContent ) . toContain ( 'b' )
const bContent = await vfs . readdir ( '/a/b' )
expect ( bContent ) . toContain ( 'c' )
const cContent = await vfs . readdir ( '/a/b/c' )
expect ( cContent ) . toContain ( 'file.txt' )
} )
it ( 'should not create duplicate directory entities under concurrent load' , async ( ) = > {
// Simulate the exact race condition scenario with many operations
const operations : Array < {
type : 'write' | 'mkdir'
path : string
data? : string
options ? : { recursive? : boolean }
} > = [ ]
// Mix mkdir and write operations that would trigger race condition
// Using recursive: true makes mkdir idempotent (no error if exists)
for ( let i = 0 ; i < 20 ; i ++ ) {
operations . push ( { type : 'mkdir' , path : ` /concurrent-test- ${ i % 5 } ` , options : { recursive : true } } )
operations . push ( {
type : 'write' ,
path : ` /concurrent-test- ${ i % 5 } /file ${ i } .txt ` ,
data : ` content ${ i } `
} )
}
const result = await vfs . bulkWrite ( operations )
// All operations should succeed (mkdirs are idempotent with recursive: true)
expect ( result . failed . length ) . toBe ( 0 )
// Verify no duplicate directories
const rootChildren = await vfs . getDirectChildren ( '/' )
const dirNames = rootChildren
. filter ( c = > c . metadata . vfsType === 'directory' )
. map ( c = > c . metadata . name )
// Each directory name should appear exactly once
for ( let i = 0 ; i < 5 ; i ++ ) {
const count = dirNames . filter ( n = > n === ` concurrent-test- ${ i } ` ) . length
expect ( count ) . toBe ( 1 )
}
// Verify all files are visible in their directories
for ( let i = 0 ; i < 5 ; i ++ ) {
const files = await vfs . readdir ( ` /concurrent-test- ${ i } ` )
expect ( files . length ) . toBe ( 4 ) // 4 files per directory (indices 0,5,10,15 for dir 0, etc.)
}
} )
fix: recalibrate find({ limit }) cap + two-tier enforcement + caller location
Brainy 7.30.0 introduced a memory-derived synchronous cap on `find({ limit })`
to prevent OOM. The cap was sound in intent but ~4x too conservative in
calibration: assumed 100 KB per result while typical entity footprint is 7-10 KB
(384-dim float32 vector ≈ 1.5 KB + standard fields + metadata). On a 900 MB
free-memory box the cap derived to 9000 — breaking common safety-cap patterns
like `find({ type, where, limit: 10_000 })` that typically return 10-500
entities. Surfaced as a runtime regression with cascading 500s degrading
production dashboards.
Three concurrent fixes:
A. RECALIBRATE THE FORMULA
- src/utils/paramValidation.ts:175,196,212 — the three memory-derived priorities
(reservedQueryMemory / containerMemory / freeMemory) all divided by
100 * 1024 * 1024 (100 KB per result, ~10-15x over conservative). Replaced
with a new MAX_LIMIT_KB_PER_RESULT = 25 constant that matches observed
entity size.
- Result: 4 GB container cap goes 10_000 → 40_000; 2 GB cap goes 5_000 →
20_000; 900 MB free-memory cap goes 9_000 → ~36_000. 100k hard ceiling
unchanged. `maxQueryLimit` / `reservedQueryMemory` constructor overrides
unchanged in behavior.
B. TWO-TIER ENFORCEMENT (warn-then-throw)
- Below cap (limit <= maxLimit): silent pass, unchanged.
- Soft tier (maxLimit < limit <= 2 * maxLimit): NEW — one-time warning per
call site (dedup keyed on caller stack frame + limit value), query
proceeds. Pre-7.30.2 code that relied on the cap silently allowing typical
safety-cap limits keeps working; the warning teaches the recipe so consumers
can fix it intentionally.
- Hard tier (limit > 2 * maxLimit): throw with the same teaching message
format. Real OOM territory; the cap stops being a recommendation and becomes
a guardrail.
- The 2x soft margin absorbs typical safety-cap patterns (limit: 10_000
against a 9 K-cap box) without disabling OOM protection. Real OOM territory
on a JS in-memory brain is hundreds of thousands of results, not 10x the
safety cap.
C. IMPROVED ERROR / WARNING MESSAGE
- Same shape as the 7.30.1 enforcement-error messages: state the problem,
name the three escape valves (maxQueryLimit / reservedQueryMemory /
pagination), include caller location, link to docs.
- Extracted findCallerLocation() helper from brainy.ts to a new
src/utils/callerLocation.ts so both the subtype enforcement (7.30.1) and
the limit enforcement (7.30.2) share one implementation without circular
imports.
DOCS
- New docs/guides/find-limits.md (public: true) — full reference: why the cap
exists, the four memory sources the auto-config considers, the three escape
valves with when-to-use-which guidance, and an explicit "pagination is the
future-proof pattern" callout (8.0 may tighten the cap further; pagination
keeps working unchanged).
- docs/api/README.md find() entry gets a one-paragraph `limit` tip + pointer
to the new guide.
- RELEASES.md v7.30.2 entry.
TESTS
- New tests/integration/find-limits.test.ts (9 tests): below-cap silent pass;
soft-tier warns once per call site (dedup verified by exercising same vs.
different source lines via wrapper closures); soft-tier message format
(names all three escape valves + docs link); soft-tier message includes
caller location; hard-tier throws; hard-tier message format same as
soft-tier; consumer maxQueryLimit override raises the cap and shifts both
tiers accordingly; pre-7.30.2 regression scenario explicitly covered.
- tests/unit/utils/memoryLimits.test.ts — 4 tests updated for the recalibrated
cap values (hardcoded expected numbers bumped 4x to match new 25 KB/result
assumption).
- tests/unit/utils/paramValidation.test.ts — auto-limit test extended to cover
the three-tier semantics (below-cap pass / soft-tier silent / hard-tier
throw).
- Existing suites unchanged: subtype-and-facets 26/26, verb-subtype-and-
enforcement 30/30, strict-mode-self-test 13/13. Unit 1468/1468.
CORTEX COMPATIBILITY
- Zero Cortex changes required. Every change is JS-side: formula recalibration
runs in ValidationConfig.constructor(), two-tier enforcement runs in
validateFindParams(), both fire before any storage / index / Cortex call.
- The new guide notes that Brainy 8.0's Datomic-style Db.find() may tighten
per-call limits to keep snapshot semantics cheap; pagination remains the
pattern that's guaranteed to keep working.
REPO-WIDE CLEANUP
Brainy is the only Soulcraft project that is open source. This commit also
scrubs closed-source product names and product-specific class/field references
from every tracked file in the repo (src/, docs/, tests/, RELEASES.md,
CHANGELOG.md). Consumer-reported bugs, regression scenarios, and release
notes now refer to "a consumer", "a downstream application", "a production
deployment", or "an internal report" — never to the named product. Two
product-named test files renamed to neutral diagnostic names. CLAUDE.md gains
a project-level guard rule documenting the policy and an example list of the
identifiers that may not appear in tracked code.
Verification
- npx tsc --noEmit: clean
- npm test: 1468 / 1468 unit
- All four integration subtype + verb + strict + find-limits suites: 78/78
- npm run build: clean
- Closed-source product reference audit: clean
2026-06-08 12:34:05 -07:00
it ( 'should handle the Consumer template creation scenario' , async ( ) = > {
2025-12-11 13:26:07 -08:00
// Exact scenario from bug report: template creation with mixed ops
const operations = [
{ type : 'mkdir' as const , path : '/project/src' } ,
{ type : 'mkdir' as const , path : '/project/src/components' } ,
{ type : 'write' as const , path : '/project/src/index.ts' , data : '// index' } ,
{ type : 'write' as const , path : '/project/src/components/App.tsx' , data : '// app' } ,
{ type : 'mkdir' as const , path : '/project/public' } ,
{ type : 'write' as const , path : '/project/public/index.html' , data : '<html>' } ,
{ type : 'write' as const , path : '/project/package.json' , data : '{}' } ,
{ type : 'write' as const , path : '/project/README.md' , data : '# Project' } ,
{ type : 'mkdir' as const , path : '/project' } , // Parent after children - should work
{ type : 'write' as const , path : '/project/tsconfig.json' , data : '{}' } ,
]
const result = await vfs . bulkWrite ( operations )
expect ( result . successful ) . toBe ( 10 )
expect ( result . failed . length ) . toBe ( 0 )
// Verify tree structure via getTreeStructure (this was failing before fix)
const tree = await vfs . getTreeStructure ( '/' , { maxDepth : 4 } )
// Find project directory
const projectDir = tree . children ? . find ( c = > c . name === 'project' )
expect ( projectDir ) . toBeDefined ( )
expect ( projectDir ? . type ) . toBe ( 'directory' )
// Verify all files are visible
const projectFiles = await vfs . readdir ( '/project' )
expect ( projectFiles ) . toContain ( 'src' )
expect ( projectFiles ) . toContain ( 'public' )
expect ( projectFiles ) . toContain ( 'package.json' )
expect ( projectFiles ) . toContain ( 'README.md' )
expect ( projectFiles ) . toContain ( 'tsconfig.json' )
const srcFiles = await vfs . readdir ( '/project/src' )
expect ( srcFiles ) . toContain ( 'index.ts' )
expect ( srcFiles ) . toContain ( 'components' )
const componentFiles = await vfs . readdir ( '/project/src/components' )
expect ( componentFiles ) . toContain ( 'App.tsx' )
} )
} )
describe ( 'edge cases' , ( ) = > {
it ( 'should handle empty operations array' , async ( ) = > {
const result = await vfs . bulkWrite ( [ ] )
expect ( result . successful ) . toBe ( 0 )
expect ( result . failed . length ) . toBe ( 0 )
} )
it ( 'should handle only mkdir operations' , async ( ) = > {
const result = await vfs . bulkWrite ( [
{ type : 'mkdir' , path : '/only-dirs/a' } ,
{ type : 'mkdir' , path : '/only-dirs/b' } ,
{ type : 'mkdir' , path : '/only-dirs' }
] )
expect ( result . successful ) . toBe ( 3 )
expect ( await vfs . exists ( '/only-dirs/a' ) ) . toBe ( true )
expect ( await vfs . exists ( '/only-dirs/b' ) ) . toBe ( true )
} )
it ( 'should handle only write operations' , async ( ) = > {
// Pre-create directory
await vfs . mkdir ( '/files-only' , { recursive : true } )
const result = await vfs . bulkWrite ( [
{ type : 'write' , path : '/files-only/a.txt' , data : 'a' } ,
{ type : 'write' , path : '/files-only/b.txt' , data : 'b' } ,
{ type : 'write' , path : '/files-only/c.txt' , data : 'c' }
] )
expect ( result . successful ) . toBe ( 3 )
} )
it ( 'should handle mkdir for already existing directories gracefully' , async ( ) = > {
// Pre-create directory
await vfs . mkdir ( '/existing' , { recursive : true } )
const result = await vfs . bulkWrite ( [
{ type : 'mkdir' , path : '/existing' , options : { recursive : true } } ,
{ type : 'write' , path : '/existing/new-file.txt' , data : 'content' }
] )
// mkdir should succeed (no-op for existing dir with recursive: true)
expect ( result . successful ) . toBe ( 2 )
expect ( await vfs . exists ( '/existing/new-file.txt' ) ) . toBe ( true )
} )
it ( 'should handle delete operations after writes' , async ( ) = > {
// First create some files
await vfs . mkdir ( '/temp' , { recursive : true } )
await vfs . writeFile ( '/temp/to-delete.txt' , 'delete me' )
await vfs . writeFile ( '/temp/to-keep.txt' , 'keep me' )
const result = await vfs . bulkWrite ( [
{ type : 'write' , path : '/temp/new-file.txt' , data : 'new' } ,
{ type : 'delete' , path : '/temp/to-delete.txt' }
] )
expect ( result . successful ) . toBe ( 2 )
expect ( await vfs . exists ( '/temp/new-file.txt' ) ) . toBe ( true )
expect ( await vfs . exists ( '/temp/to-delete.txt' ) ) . toBe ( false )
expect ( await vfs . exists ( '/temp/to-keep.txt' ) ) . toBe ( true )
} )
it ( 'should handle update operations' , async ( ) = > {
await vfs . writeFile ( '/doc.txt' , 'original content' )
const result = await vfs . bulkWrite ( [
{ type : 'update' , path : '/doc.txt' , options : { metadata : { custom : 'value' } } }
] )
expect ( result . successful ) . toBe ( 1 )
const entity = await vfs . getEntity ( '/doc.txt' )
expect ( entity . metadata . custom ) . toBe ( 'value' )
} )
} )
describe ( 'error handling' , ( ) = > {
it ( 'should continue processing after mkdir failure' , async ( ) = > {
// Create a file where we'll try to mkdir
await vfs . writeFile ( '/not-a-dir' , 'content' )
const result = await vfs . bulkWrite ( [
{ type : 'mkdir' , path : '/not-a-dir' } , // Will fail - file exists
{ type : 'mkdir' , path : '/good-dir' } ,
{ type : 'write' , path : '/good-dir/file.txt' , data : 'content' }
] )
expect ( result . successful ) . toBe ( 2 ) // good-dir and file.txt
expect ( result . failed . length ) . toBe ( 1 ) // not-a-dir
expect ( await vfs . exists ( '/good-dir/file.txt' ) ) . toBe ( true )
} )
it ( 'should continue processing after write failure' , async ( ) = > {
const result = await vfs . bulkWrite ( [
{ type : 'mkdir' , path : '/test-dir' } ,
{ type : 'write' , path : '/test-dir/good.txt' , data : 'content' } ,
{ type : 'delete' , path : '/nonexistent/file.txt' } // Will fail
] )
expect ( result . successful ) . toBe ( 2 ) // mkdir and write
expect ( result . failed . length ) . toBe ( 1 ) // delete
expect ( await vfs . exists ( '/test-dir/good.txt' ) ) . toBe ( true )
} )
} )
} )