2025-11-11 15:24:43 -08:00
import { describe , it , expect , beforeEach } from 'vitest'
import { Brainy } from '../../src/brainy.js'
import { VerbType } from '../../src/types/graphTypes.js'
/ * *
* Regression test for v5 . 7.0 deadlock bug
*
* BUG DESCRIPTION :
* v5 . 7.0 introduced a circular dependency deadlock during GraphAdjacencyIndex initialization :
* - GraphAdjacencyIndex . rebuild ( ) calls storage . getVerbs ( )
* - storage . getVerbsBySource_internal ( ) calls getGraphIndex ( )
* - getGraphIndex ( ) is waiting for rebuild ( ) to complete
* - DEADLOCK : Each waits for the other
*
* SYMPTOMS :
* - ALL imports hang at "Reading Data Structure" stage
* - brain . add ( ) operations take 12 + seconds per entity ( 50 x slower )
* - No errors thrown - infinite wait
* - Process continues ( heartbeats ) but makes no progress
*
* FIX ( v5 . 7.1 ) :
* Reverted storage internals ( getVerbsBySource_internal , getVerbsByTarget_internal )
* to v5 . 6.3 implementation - no getGraphIndex ( ) calls from storage layer .
*
* TEST STRATEGY :
* 1 . Create entities with relationships ( triggers GraphAdjacencyIndex lazy init )
* 2 . Force rebuild by accessing graph operations
* 3 . Verify completes in < 1 second ( not 760 + seconds )
* /
describe ( 'v5.7.0 Deadlock Regression' , ( ) = > {
let brain : Brainy
beforeEach ( async ( ) = > {
brain = new Brainy ( { storage : { type : 'memory' } } )
await brain . init ( )
} )
it ( 'should not deadlock during GraphAdjacencyIndex rebuild with existing verbs' , async ( ) = > {
// Create 10 entities
const entities = [ ]
for ( let i = 0 ; i < 10 ; i ++ ) {
const id = await brain . add ( {
data : ` Entity ${ i } ` ,
type : 'thing' ,
metadata : { index : i }
} )
entities . push ( id )
}
// Create relationships between them (triggers GraphAdjacencyIndex)
for ( let i = 0 ; i < 9 ; i ++ ) {
await brain . relate ( {
from : entities [ i ] ,
to : entities [ i + 1 ] ,
type : VerbType . RelatedTo
} )
}
// This should complete in <1 second (not hang forever)
const start = Date . now ( )
// Force GraphAdjacencyIndex usage by querying relationships
const relations = await brain . getRelations ( { from : entities [ 0 ] } )
const elapsed = Date . now ( ) - start
// Verify no deadlock
expect ( elapsed ) . toBeLessThan ( 1000 )
expect ( relations . length ) . toBeGreaterThan ( 0 )
} )
it ( 'should handle imports without 12+ second delays per entity' , async ( ) = > {
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
// Simulate import workflow (like A consumer's Excel import)
2025-11-11 15:24:43 -08:00
const start = Date . now ( )
// Import 5 entities with relationships
const importedEntities = [ ]
for ( let i = 0 ; i < 5 ; i ++ ) {
const id = await brain . add ( {
data : ` Imported Entity ${ i } ` ,
type : 'person' ,
metadata : {
importId : 'test-import-001' ,
sourceRow : i
}
} )
importedEntities . push ( id )
}
// Add relationships
for ( let i = 0 ; i < 4 ; i ++ ) {
await brain . relate ( {
from : importedEntities [ i ] ,
to : importedEntities [ i + 1 ] ,
type : VerbType . Knows
} )
}
const elapsed = Date . now ( ) - start
// In v5.7.0, this took 12+ seconds per entity (60+ seconds total)
// In v5.7.1, should complete in <5 seconds for 5 entities
expect ( elapsed ) . toBeLessThan ( 5000 )
// Verify all entities were created
for ( const id of importedEntities ) {
const entity = await brain . get ( id )
expect ( entity ) . toBeDefined ( )
}
} )
it ( 'should allow GraphAdjacencyIndex rebuild without circular dependency' , async ( ) = > {
// Create initial data
const entity1 = await brain . add ( { data : 'Node A' , type : 'thing' } )
const entity2 = await brain . add ( { data : 'Node B' , type : 'thing' } )
const entity3 = await brain . add ( { data : 'Node C' , type : 'thing' } )
await brain . relate ( { from : entity1 , to : entity2 , type : VerbType . RelatedTo } )
await brain . relate ( { from : entity2 , to : entity3 , type : VerbType . RelatedTo } )
// Accessing storage internals should not cause deadlock
// GraphAdjacencyIndex initialization should complete successfully
const start = Date . now ( )
// This would trigger initialization if not already done
const relations = await brain . getRelations ( { from : entity1 } )
const elapsed = Date . now ( ) - start
// Should be fast (no deadlock, no 12s delays)
expect ( elapsed ) . toBeLessThan ( 500 )
expect ( relations ) . toHaveLength ( 1 )
expect ( relations [ 0 ] . to ) . toBe ( entity2 )
} )
it ( 'should handle multiple concurrent adds without deadlock' , async ( ) = > {
// Simulate concurrent entity creation (like batch import)
const start = Date . now ( )
const promises = [ ]
for ( let i = 0 ; i < 10 ; i ++ ) {
promises . push (
brain . add ( {
data : ` Concurrent Entity ${ i } ` ,
type : 'thing' ,
metadata : { batch : true , index : i }
} )
)
}
const ids = await Promise . all ( promises )
const elapsed = Date . now ( ) - start
// Should complete quickly (no 12s per entity delays)
// 10 entities should take <2 seconds, not 120+ seconds
expect ( elapsed ) . toBeLessThan ( 2000 )
expect ( ids ) . toHaveLength ( 10 )
} )
} )