brainy/tests/unit/utils/paramValidation.test.ts

296 lines
9.4 KiB
TypeScript
Raw Normal View History

import { describe, it, expect, beforeEach } from 'vitest'
import {
validateFindParams,
validateAddParams,
validateUpdateParams,
validateRelateParams,
getValidationConfig,
recordQueryPerformance
} from '../../../src/utils/paramValidation.js'
import { NounType, VerbType } from '../../../src/types/graphTypes.js'
import { FindParams, AddParams, UpdateParams, RelateParams } from '../../../src/types/brainy.types.js'
describe('Zero-Config Parameter Validation', () => {
describe('validateFindParams', () => {
it('should accept valid parameters', () => {
expect(() => validateFindParams({
query: 'test query',
limit: 10,
offset: 0
})).not.toThrow()
expect(() => validateFindParams({
type: NounType.Document,
where: { status: 'active' }
})).not.toThrow()
})
it('should reject negative limit', () => {
expect(() => validateFindParams({
limit: -1
})).toThrow('limit must be non-negative')
})
it('should reject negative offset', () => {
expect(() => validateFindParams({
offset: -1
})).toThrow('offset must be non-negative')
})
it('should reject threshold outside 0-1 range', () => {
expect(() => validateFindParams({
near: { id: 'test', threshold: -0.1 }
})).toThrow('threshold must be between 0 and 1')
expect(() => validateFindParams({
near: { id: 'test', threshold: 1.1 }
})).toThrow('threshold must be between 0 and 1')
})
it('should reject both query and vector', () => {
expect(() => validateFindParams({
query: 'test',
vector: new Array(384).fill(0)
})).toThrow('cannot specify both query and vector')
})
it('should reject both cursor and offset', () => {
expect(() => validateFindParams({
cursor: 'abc123',
offset: 10
})).toThrow('cannot use both cursor and offset pagination')
})
it('should validate vector dimensions', () => {
expect(() => validateFindParams({
vector: new Array(100).fill(0) // Wrong dimensions
})).toThrow('vector must have exactly 384 dimensions')
expect(() => validateFindParams({
vector: new Array(384).fill(0) // Correct dimensions
})).not.toThrow()
})
it('should validate NounType enum', () => {
expect(() => validateFindParams({
type: 'InvalidType' as any
})).toThrow('invalid NounType: InvalidType')
expect(() => validateFindParams({
type: NounType.Document
})).not.toThrow()
})
it('should validate array of NounTypes', () => {
expect(() => validateFindParams({
type: [NounType.Document, NounType.Person]
})).not.toThrow()
expect(() => validateFindParams({
type: [NounType.Document, 'InvalidType' as any]
})).toThrow('invalid NounType: InvalidType')
})
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 auto-limit based on system memory (two-tier enforcement)', () => {
const config = getValidationConfig()
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
// 7.30.2+ design: the cap fires in two tiers.
// - Below cap (`limit <= maxLimit`): silent pass, no signal.
// - Soft tier (`maxLimit < limit <= 2 * maxLimit`): one-time warning
// per call site, query proceeds. No throw.
// - Hard tier (`limit > 2 * maxLimit`): real OOM danger zone, throw.
// Below cap → pass
expect(() => validateFindParams({ limit: config.maxLimit })).not.toThrow()
// Soft tier → no throw (just a warn we don't assert here — proper coverage
// lives in the find-limits integration suite which can intercept the log).
expect(() => validateFindParams({ limit: config.maxLimit + 1 })).not.toThrow()
expect(() => validateFindParams({ limit: config.maxLimit * 2 })).not.toThrow()
// Hard tier → throw with the new message format
expect(() => validateFindParams({
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
limit: config.maxLimit * 2 + 1
})).toThrow(/exceeds the auto-configured query limit/)
})
it('should auto-limit query length', () => {
const config = getValidationConfig()
const longQuery = 'a'.repeat(config.maxQueryLength + 1)
expect(() => validateFindParams({
query: longQuery
})).toThrow(`query exceeds auto-configured maximum length of ${config.maxQueryLength}`)
})
})
describe('validateAddParams', () => {
it('should accept valid add parameters', () => {
expect(() => validateAddParams({
data: 'test content',
type: NounType.Document
})).not.toThrow()
expect(() => validateAddParams({
vector: new Array(384).fill(0),
type: NounType.Person
})).not.toThrow()
})
it('should require either data or vector', () => {
expect(() => validateAddParams({
type: NounType.Document
} as AddParams)).toThrow('Invalid add() parameters: Missing required field \'data\'')
})
it('should validate NounType', () => {
expect(() => validateAddParams({
data: 'test',
type: 'InvalidType' as any
})).toThrow('Invalid NounType: \'InvalidType\'')
})
it('should validate vector dimensions', () => {
expect(() => validateAddParams({
vector: new Array(100).fill(0),
type: NounType.Document
})).toThrow('vector must have exactly 384 dimensions')
})
})
describe('validateUpdateParams', () => {
it('should accept valid update parameters', () => {
expect(() => validateUpdateParams({
id: 'test-id',
data: 'new content'
})).not.toThrow()
expect(() => validateUpdateParams({
id: 'test-id',
metadata: { status: 'updated' }
})).not.toThrow()
})
it('should require an ID', () => {
expect(() => validateUpdateParams({
data: 'new content'
} as UpdateParams)).toThrow('id is required for update')
})
it('should require at least one field to update', () => {
expect(() => validateUpdateParams({
id: 'test-id'
})).toThrow('must specify at least one field to update')
})
it('should validate NounType if changing', () => {
expect(() => validateUpdateParams({
id: 'test-id',
type: 'InvalidType' as any
})).toThrow('invalid NounType: InvalidType')
expect(() => validateUpdateParams({
id: 'test-id',
type: NounType.Event
})).not.toThrow()
})
})
describe('validateRelateParams', () => {
it('should accept valid relate parameters', () => {
expect(() => validateRelateParams({
from: 'entity1',
to: 'entity2',
type: VerbType.RelatedTo
})).not.toThrow()
expect(() => validateRelateParams({
from: 'entity1',
to: 'entity2',
type: VerbType.Creates,
weight: 0.8
})).not.toThrow()
})
it('should require from and to', () => {
expect(() => validateRelateParams({
to: 'entity2',
type: VerbType.RelatedTo
} as RelateParams)).toThrow('from entity ID is required')
expect(() => validateRelateParams({
from: 'entity1',
type: VerbType.RelatedTo
} as RelateParams)).toThrow('to entity ID is required')
})
// Self-referential relationships are now allowed (valid in graph systems)
// Previous test "should reject self-referential relationships" removed
it('should validate VerbType', () => {
expect(() => validateRelateParams({
from: 'entity1',
to: 'entity2',
type: 'InvalidVerb' as any
})).toThrow('invalid VerbType: InvalidVerb')
})
it('should validate weight range', () => {
expect(() => validateRelateParams({
from: 'entity1',
to: 'entity2',
type: VerbType.RelatedTo,
weight: -0.1
})).toThrow('weight must be between 0 and 1')
expect(() => validateRelateParams({
from: 'entity1',
to: 'entity2',
type: VerbType.RelatedTo,
weight: 1.1
})).toThrow('weight must be between 0 and 1')
})
})
describe('Auto-configuration', () => {
it('should provide configuration based on system resources', () => {
const config = getValidationConfig()
expect(config.maxLimit).toBeGreaterThan(0)
expect(config.maxLimit).toBeLessThanOrEqual(100000)
expect(config.maxQueryLength).toBeGreaterThan(0)
expect(config.maxVectorDimensions).toBe(384)
expect(config.systemMemory).toBeGreaterThan(0)
expect(config.availableMemory).toBeGreaterThan(0)
})
it('should adapt limits based on query performance', () => {
const initialConfig = getValidationConfig()
const initialLimit = initialConfig.maxLimit
// Simulate fast queries with large results
for (let i = 0; i < 10; i++) {
recordQueryPerformance(50, initialLimit * 0.9)
}
const updatedConfig = getValidationConfig()
// Limit might increase if performance is good
expect(updatedConfig.maxLimit).toBeGreaterThanOrEqual(initialLimit)
// Simulate slow queries
for (let i = 0; i < 10; i++) {
recordQueryPerformance(2000, 100)
}
const finalConfig = getValidationConfig()
// Limit should decrease if performance is poor
expect(finalConfig.maxLimit).toBeLessThanOrEqual(updatedConfig.maxLimit)
})
})
})