brainy/tests/manual/vfs-multiple-init-diagnostic.test.ts

208 lines
5.9 KiB
TypeScript
Raw Normal View History

/**
* VFS Multiple Init() Diagnostic Test
*
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
* Tests a consumer's issue: Does calling vfs.init() multiple times
* create duplicate root entities?
*
* Scenario:
* - Create brain instance
* - Call vfs.init() multiple times (simulating multiple requests)
* - Check if multiple root entities are created
*/
import { describe, it, expect, beforeAll, afterAll } from 'vitest'
import { Brainy } from '../../src/brainy.js'
import * as fs from 'fs'
import * as path from 'path'
describe('VFS Multiple Init Diagnostic', () => {
const testDir = path.join(process.cwd(), 'test-vfs-multi-init')
let brain: Brainy
beforeAll(async () => {
// Clean up test directory
if (fs.existsSync(testDir)) {
fs.rmSync(testDir, { recursive: true, force: true })
}
fs.mkdirSync(testDir, { recursive: true })
// Create brain with filesystem storage
brain = new Brainy({
storage: {
type: 'filesystem',
path: testDir
}
})
await brain.init()
})
afterAll(() => {
// Clean up
if (fs.existsSync(testDir)) {
fs.rmSync(testDir, { recursive: true, force: true })
}
})
it('should not create duplicate roots when calling vfs.init() multiple times on SAME instance', async () => {
2025-11-02 11:38:12 -08:00
const vfs = brain.vfs
// Call init multiple times
await vfs.init()
await vfs.init()
await vfs.init()
// Query for root entities using workaround (where clause is broken)
const collections = await brain.find({
type: 'collection',
limit: 100
})
const roots = collections.filter(e =>
e.metadata?.path === '/' &&
e.metadata?.vfsType === 'directory'
)
console.log(`\n✅ Test 1: Same VFS instance`)
console.log(` Total collections: ${collections.length}`)
console.log(` Roots found: ${roots.length}`)
roots.forEach((root, i) => {
console.log(` Root ${i + 1}: ${root.id}`)
})
expect(roots.length).toBe(1)
})
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 not create duplicate roots when creating MULTIPLE VFS instances (the reported scenario)', async () => {
// Simulate the reported scenario: Getting VFS on multiple requests
2025-11-02 11:38:12 -08:00
// brain.vfs returns cached instance, so this should be safe
const vfs1 = brain.vfs
const vfs2 = brain.vfs
const vfs3 = brain.vfs
await vfs1.init()
await vfs2.init()
await vfs3.init()
// Query for root entities using workaround
const collections = await brain.find({
type: 'collection',
limit: 100
})
const roots = collections.filter(e =>
e.metadata?.path === '/' &&
e.metadata?.vfsType === 'directory'
)
console.log(`\n✅ Test 2: Multiple VFS references (cached)`)
console.log(` VFS instances are same? ${vfs1 === vfs2 && vfs2 === vfs3}`)
console.log(` Roots found: ${roots.length}`)
roots.forEach((root, i) => {
console.log(` Root ${i + 1}: ${root.id}`)
})
expect(vfs1).toBe(vfs2) // Should be same instance (cached)
expect(roots.length).toBe(1) // Should still be 1 root
})
it('should handle NEW brain instances gracefully (per-user scenario)', async () => {
// Simulate creating separate brain instances per user
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
// This is closer to a consumer's getUserBrainy() pattern
const brain2 = new Brainy({
storage: {
type: 'filesystem',
path: testDir // Same storage!
}
})
await brain2.init()
const vfs2 = brain2.vfs()
await vfs2.init()
// Query for roots using workaround
const collections = await brain.find({
type: 'collection',
limit: 100
})
const roots = collections.filter(e =>
e.metadata?.path === '/' &&
e.metadata?.vfsType === 'directory'
)
console.log(`\n✅ Test 3: New Brainy instance (same storage)`)
console.log(` Roots found: ${roots.length}`)
roots.forEach((root, i) => {
console.log(` Root ${i + 1}: ${root.id} (created: ${root.metadata?.createdAt})`)
})
// This is the CRITICAL test - should find existing root, not create new one
expect(roots.length).toBe(1)
})
it('should verify readdir works after multiple inits', async () => {
// Create a test directory
2025-11-02 11:38:12 -08:00
const vfs = brain.vfs
await vfs.mkdir('/test-dir', { recursive: true })
await vfs.writeFile('/test-dir/test.txt', 'Hello')
// Call init again (simulating new request)
const brain3 = new Brainy({
storage: {
type: 'filesystem',
path: testDir
}
})
await brain3.init()
const vfs3 = brain3.vfs()
await vfs3.init()
// Try to read root directory
const entries = await vfs3.readdir('/', { withFileTypes: true })
console.log(`\n✅ Test 4: readdir after new brain instance`)
console.log(` Entries found: ${entries.length}`)
entries.forEach((entry: any) => {
console.log(` - ${entry.name} (${entry.type})`)
})
expect(entries.length).toBeGreaterThan(0)
})
it('should show if Contains relationships are created', async () => {
2025-11-02 11:38:12 -08:00
const vfs = brain.vfs
// Get root entity ID using workaround
const collections = await brain.find({
type: 'collection',
limit: 100
})
const roots = collections.filter(e =>
e.metadata?.path === '/' &&
e.metadata?.vfsType === 'directory'
)
expect(roots.length).toBeGreaterThanOrEqual(1)
const rootId = roots[0].id
// Check for Contains relationships FROM root
const relations = await brain.getRelations({
from: rootId
})
console.log(`\n✅ Test 5: Contains relationships`)
console.log(` Root ID: ${rootId}`)
console.log(` Relationships from root: ${relations.length}`)
relations.forEach((rel) => {
console.log(` - ${rel.from} -> ${rel.to} (${rel.type})`)
})
// Root should have at least one Contains relationship (to /test-dir)
const containsRels = relations.filter(r => r.type === 'contains')
console.log(` Contains relationships: ${containsRels.length}`)
expect(containsRels.length).toBeGreaterThan(0)
})
})