diff --git a/src/errors/brainyError.ts b/src/errors/brainyError.ts index a58236e3..4301d3f7 100644 --- a/src/errors/brainyError.ts +++ b/src/errors/brainyError.ts @@ -405,3 +405,68 @@ export class MigrationInProgressError extends BrainyError { } } } + +/** + * THE INDEXABLE-ARRAY BOUND. An array-valued metadata field indexes one posting + * per element, so an unbounded array is an unbounded write — a 384-float + * embedding parked in the metadata bag would mint 384 postings for one row. + * The bound exists to keep that out of the index. + * + * 64 is hardcoded on purpose (the zero-config law: no knob). It sits far above + * every legitimate multi-value field the engine has seen — tags, authors, + * categories, labels, participant lists — and far below any real embedding + * width, so the two populations do not overlap and no caller has to tune it. + * + * It replaces a limit of 10 that was applied SILENTLY: a row whose `tags` array + * held eleven entries had that field skipped entirely and dropped out of every + * filtered search on it, with no error, no warning and no way to tell the + * difference from "no row matches". A rule this consequential is a law with a + * name and a refusal, not a `continue`. + */ +export const MAX_INDEXED_ARRAY_LENGTH = 64 + +/** + * A metadata field carries an array longer than {@link MAX_INDEXED_ARRAY_LENGTH}. + * + * Thrown at the WRITE door (`add` / `update` / `relate` / `updateRelation`), so + * the caller learns at the moment of writing that the field will not be + * searchable — rather than discovering it later as rows that quietly fail to + * match. Carries the field, its length and the bound so a handler can report + * or repair without parsing the message. + * + * The cure is one of: store the long array outside the indexed bag (`data` + * carries arbitrary content and is not indexed element-wise); pass an embedding + * as the first-class `vector` parameter, which is where a vector belongs; or + * shorten the field to the values that are actually queried. + */ +export class MetadataArrayTooLargeError extends BrainyError { + /** The metadata field whose array is too long (its full dotted address). */ + public readonly field: string + /** How many elements that array holds. */ + public readonly length: number + /** The bound it exceeded — {@link MAX_INDEXED_ARRAY_LENGTH}. */ + public readonly limit: number + + constructor(site: string, field: string, length: number, limit: number) { + super( + `${site}: metadata field '${field}' holds ${length} array elements, ` + + `over the ${limit}-element indexing bound. An array field indexes one ` + + `posting per element, so an unbounded array is an unbounded write. ` + + `This write is refused rather than indexed partially or skipped silently ` + + `— a skipped field drops the row out of every filtered search on '${field}' ` + + `with no way to tell that from "nothing matched". ` + + `Cures: put the long array in 'data' (stored, not indexed element-wise); ` + + `pass an embedding as the first-class 'vector' parameter; or keep only ` + + `the values you actually query in '${field}'.`, + 'VALIDATION', + false + ) + this.name = 'MetadataArrayTooLargeError' + this.field = field + this.length = length + this.limit = limit + if (Error.captureStackTrace) { + Error.captureStackTrace(this, MetadataArrayTooLargeError) + } + } +} diff --git a/src/index.ts b/src/index.ts index e946f15c..673e1e6f 100644 --- a/src/index.ts +++ b/src/index.ts @@ -203,7 +203,7 @@ export { EntityNotFoundError, RelationNotFoundError } from './errors/notFound.js // Base error + typed migration-lock error — thrown by any data-plane call while a // brain runs its one-time 7.x→8.0 upgrade; catch to answer HTTP 503 + Retry-After. -export { BrainyError, MigrationInProgressError, GraphIndexNotReadyError, MetadataIndexNotReadyError, VectorIndexNotReadyError, ProtectedArtifactError, DerivedArtifactMissingError } from './errors/brainyError.js' +export { BrainyError, MigrationInProgressError, GraphIndexNotReadyError, MetadataIndexNotReadyError, VectorIndexNotReadyError, ProtectedArtifactError, DerivedArtifactMissingError, MetadataArrayTooLargeError, MAX_INDEXED_ARRAY_LENGTH } from './errors/brainyError.js' export type { BrainyErrorType } from './errors/brainyError.js' // ============= 8.0 Db API — generational MVCC ============= diff --git a/src/utils/metadataIndex.ts b/src/utils/metadataIndex.ts index 83d37379..1a882945 100644 --- a/src/utils/metadataIndex.ts +++ b/src/utils/metadataIndex.ts @@ -40,7 +40,7 @@ import { import { EntityIdMapper } from './entityIdMapper.js' import { RoaringBitmap32, roaringLibraryInitialize } from './roaring/index.js' import { FieldTypeInference, FieldType } from './fieldTypeInference.js' -import { BrainyError } from '../errors/brainyError.js' +import { BrainyError, MAX_INDEXED_ARRAY_LENGTH } from '../errors/brainyError.js' /** * Fields whose values are stored in the sparse index as BUCKETED values @@ -289,8 +289,10 @@ export class MetadataIndexManager implements MetadataIndexProvider { // No name-based exclude/allow lists — the field-addressing law: every // user field indexes, whatever its name ('content', 'data', 'id', // 'vector', … included). Bulk payloads are kept out by uniform value- - // SHAPE rules in extractIndexableFields (arrays >10 never become - // posting scalars; >100-char values index hashed), never by name. + // SHAPE rules in extractIndexableFields (arrays longer than + // MAX_INDEXED_ARRAY_LENGTH never become posting scalars, and the write + // door refuses them by name; >100-char values index hashed), never by + // field name. } // Initialize metadata cache with similar config to search cache @@ -1387,9 +1389,10 @@ export class MetadataIndexManager implements MetadataIndexProvider { * 'content', 'vector' in a bag are ordinary user fields) * - Record-frame plumbing (vector, connections, level, data, _rev, id) * never indexes — that is namespace routing, not a name carve-out - * - Value-SHAPE rules apply uniformly to all names: arrays >10 never - * become posting scalars; purely numeric key names (array indices) - * skip; >100-char values index hashed (normalizeValue) + * - Value-SHAPE rules apply uniformly to all names: arrays longer than + * MAX_INDEXED_ARRAY_LENGTH never become posting scalars (and say so — + * the write door refuses them outright); purely numeric key names + * (array indices) skip; >100-char values index hashed (normalizeValue) */ private extractIndexableFields(data: any): Array<{ field: string, value: any }> { const fields: Array<{ field: string, value: any }> = [] @@ -1451,13 +1454,37 @@ export class MetadataIndexManager implements MetadataIndexProvider { // This catches vectors stored as objects: {0: 0.1, 1: 0.2, ...} if (/^\d+$/.test(key)) continue - // Skip large arrays (> 10 elements) - likely vectors or bulk data - if (Array.isArray(value) && value.length > 10) continue + // THE INDEXABLE-ARRAY BOUND ({@link MAX_INDEXED_ARRAY_LENGTH}). An + // array field mints one posting per element, so the index has always + // carried a ceiling — it was 10, and it was applied by this bare + // `continue`: an eleven-element `tags` array had its whole field + // skipped and the row dropped out of every filtered search on it, with + // no error, no warning, and nothing to distinguish that from "no row + // matches". The ceiling is not the defect; the silence was. + // + // The write door refuses this shape by name now + // (`MetadataArrayTooLargeError`, thrown from paramValidation's + // `rejectOversizeIndexArrays`), so a live add/update never reaches + // here over the bound. Reaching it means the row is ALREADY on disk — + // written by an older engine under the old rule — and this is a + // rebuild, a catch-up fold or a remove reading it back. Refusing there + // would make an existing store un-rebuildable, so the row is admitted + // and the skipped field is NARRATED instead. Never silent, either way. + if (Array.isArray(value) && value.length > MAX_INDEXED_ARRAY_LENGTH) { + prodLog.warn( + `[brainy] metadata field '${fullKey}' holds ${value.length} array elements, ` + + `over the ${MAX_INDEXED_ARRAY_LENGTH}-element indexing bound — the field is ` + + `NOT indexed for this row, so it will not match a where-clause on '${fullKey}'. ` + + `This row predates the bound (the write door refuses this shape now). ` + + `Move the long array into 'data', or pass an embedding as the 'vector' parameter.` + ) + continue + } if (value && typeof value === 'object' && !Array.isArray(value)) { // Recurse into nested objects (but not arrays), keeping the frame extract(value, fullKey, frame) - } else if (Array.isArray(value) && value.length <= 10) { + } else if (Array.isArray(value)) { // Small arrays: index as multi-value field (all with same field name) // Example: tags: ["javascript", "node"] → field="tags", value="javascript" + field="tags", value="node" for (const item of value) { diff --git a/src/utils/paramValidation.ts b/src/utils/paramValidation.ts index 00790a4a..f1addb5b 100644 --- a/src/utils/paramValidation.ts +++ b/src/utils/paramValidation.ts @@ -18,6 +18,7 @@ import { findCallerLocation } from './callerLocation.js' import * as os from 'node:os' import * as fs from 'node:fs' import { parseFieldAddress, UnsupportedFindOptionError } from '../db/fieldAddressing.js' +import { MAX_INDEXED_ARRAY_LENGTH, MetadataArrayTooLargeError } from '../errors/brainyError.js' const getSystemMemory = (): number => { if (os) { @@ -538,8 +539,53 @@ function rejectForgedSystemKeys(metadata: Record | undefined, s } } +/** + * THE INDEXABLE-ARRAY BOUND, enforced at the write door. + * + * An array-valued metadata field indexes one posting per element, so the index + * has always carried a ceiling. It used to be 10, and it was applied by a bare + * `continue` deep inside field extraction: a row whose `tags` array held eleven + * entries had that field skipped entirely and dropped out of every filtered + * search on it — no error, no warning, and no way for the caller to tell the + * difference from "no row matches". Silence is the defect; the ceiling is not. + * + * The bound is now {@link MAX_INDEXED_ARRAY_LENGTH}, high enough that every + * legitimate multi-value field clears it, and it REFUSES here instead of + * dropping data downstream. Refusing at the write door is what makes it + * actionable: the caller learns at the moment of writing, with the field, the + * length and the bound in hand. + * + * Scope is the caller's own metadata bag — the values that become postings. + * Nested bags are walked, because a nested field indexes under its dotted + * address exactly like a top-level one. Arrays of OBJECTS are not walked: the + * index only ever makes postings from an array's scalar elements. + * + * @param metadata - The caller's metadata bag (undefined is fine). + * @param site - The write door's name, for the message ('add()', 'update()', …). + * @throws {MetadataArrayTooLargeError} Naming the field, its length and the bound. + */ +function rejectOversizeIndexArrays(metadata: Record | undefined, site: string): void { + if (!metadata) return + + const walk = (bag: Record, prefix: string): void => { + for (const [key, value] of Object.entries(bag)) { + const address = prefix ? `${prefix}.${key}` : key + if (Array.isArray(value)) { + if (value.length > MAX_INDEXED_ARRAY_LENGTH) { + throw new MetadataArrayTooLargeError(site, address, value.length, MAX_INDEXED_ARRAY_LENGTH) + } + } else if (value && typeof value === 'object') { + walk(value as Record, address) + } + } + } + + walk(metadata, '') +} + export function validateAddParams(params: AddParams): void { rejectForgedSystemKeys(params.metadata as Record | undefined, 'add()') + rejectOversizeIndexArrays(params.metadata as Record | undefined, 'add()') // 'data' is ABSENT only when null/undefined — an empty string ('') is real // content (a legitimate empty file's first write) and must not be treated // as missing. Falsy-but-present values (0, false, '') all count as present; @@ -608,6 +654,7 @@ export function validateAddParams(params: AddParams): void { */ export function validateUpdateParams(params: UpdateParams): void { rejectForgedSystemKeys(params.metadata as Record | undefined, 'update()') + rejectOversizeIndexArrays(params.metadata as Record | undefined, 'update()') // Same absent-vs-empty distinction as validateAddParams: '' is a real new // value (e.g. truncating a file to empty content via overwrite), only // null/undefined means "no new data was given". @@ -682,6 +729,7 @@ export function validateUpdateParams(params: UpdateParams): void { */ export function validateRelateParams(params: RelateParams): void { rejectForgedSystemKeys(params.metadata as Record | undefined, 'relate()') + rejectOversizeIndexArrays(params.metadata as Record | undefined, 'relate()') // 8.0 verb-id contract (L.7): verb ids are UUIDs, generated by brainy. // RelateParams has no `id` field — an untyped caller passing one would // previously have it silently ignored (a generated UUID was used instead). @@ -731,6 +779,7 @@ export function validateRelateParams(params: RelateParams): void { */ export function validateUpdateRelationParams(params: UpdateRelationParams): void { rejectForgedSystemKeys(params.metadata as Record | undefined, 'updateRelation()') + rejectOversizeIndexArrays(params.metadata as Record | undefined, 'updateRelation()') if (!params.id) { throw new Error('id is required for updateRelation') } diff --git a/tests/integration/metadata-vector-exclusion.test.ts b/tests/integration/metadata-vector-exclusion.test.ts index 9e11f9dc..0ca25388 100644 --- a/tests/integration/metadata-vector-exclusion.test.ts +++ b/tests/integration/metadata-vector-exclusion.test.ts @@ -26,6 +26,7 @@ import { describe, it, expect, beforeEach, afterEach } from 'vitest' import { Brainy } from '../../src/brainy.js' import { NounType } from '../../src/types/graphTypes.js' import { existsSync, rmSync } from 'fs' +import { MetadataArrayTooLargeError, MAX_INDEXED_ARRAY_LENGTH } from '../../src/errors/brainyError.js' describe('Metadata Vector Exclusion Fix', () => { let brainy: Brainy @@ -155,29 +156,56 @@ describe('Metadata Vector Exclusion Fix', () => { expect(results[0].entity.metadata?.name).toBe('Bob') }) - it('should skip indexing large arrays (>10 elements)', async () => { - // Add entity with a large array (not a vector, just bulk data). + it('should REFUSE an array over the indexing bound, by name', async () => { + // A large array (not a vector, just bulk data). This used to be SKIPPED in + // silence at a bound of 10 — the field simply vanished from the index and + // the row dropped out of every `where` on it, indistinguishably from "no + // row matches". The bound is now MAX_INDEXED_ARRAY_LENGTH and it REFUSES. const largeArray = Array.from({ length: 100 }, (_, i) => `item${i}`) - await brainy.add({ - type: NounType.Document, - data: 'Doc with large array', - metadata: { - name: 'Doc with large array', - items: largeArray - } - }) + const err = await brainy + .add({ + type: NounType.Document, + data: 'Doc with large array', + metadata: { + name: 'Doc with large array', + items: largeArray + } + }) + .catch((e: any) => e) - // Large arrays (> 10 elements) are deliberately skipped to avoid indexing - // bulk/vector-like payloads: 'items' must NOT appear, and the 100 elements - // must NOT have produced 100 indexed fields. + expect(err).toBeInstanceOf(MetadataArrayTooLargeError) + expect(err.field).toBe('items') + expect(err.length).toBe(100) + expect(err.limit).toBe(MAX_INDEXED_ARRAY_LENGTH) + + // Nothing was indexed from the refused write — no 'items' field, and above + // all no per-element numeric fields (the original explosion class). const fields = await brainy.getAvailableFields() expect(fields).not.toContain('items') const numericFields = fields.filter(f => /(^|\.)\d+$/.test(f)) expect(numericFields).toEqual([]) + }) - // The scalar 'name' field IS indexed. - expect(fields).toContain('name') + it('should index an array UP TO the bound — the old limit of 10 was the bug', async () => { + await brainy.add({ + type: NounType.Document, + data: 'Doc with a long-but-legitimate tag list', + metadata: { + name: 'Doc with many tags', + items: Array.from({ length: MAX_INDEXED_ARRAY_LENGTH }, (_, i) => `item${i}`) + } + }) + + const fields = await brainy.getAvailableFields() + // The field IS indexed now, and still without per-element numeric fields. + expect(fields).toContain('items') + expect(fields.filter(f => /(^|\.)\d+$/.test(f))).toEqual([]) + + // And the eleventh element — the one the old bound silently dropped the + // whole field for — really is searchable. + const hits = await brainy.find({ where: { items: 'item10' } }) + expect(hits.length).toBeGreaterThan(0) }) it('should preserve HNSW vector search functionality', async () => { diff --git a/tests/unit/utils/metadataIndex-array-bound.test.ts b/tests/unit/utils/metadataIndex-array-bound.test.ts new file mode 100644 index 00000000..cbbf6b63 --- /dev/null +++ b/tests/unit/utils/metadataIndex-array-bound.test.ts @@ -0,0 +1,242 @@ +/** + * @module tests/unit/utils/metadataIndex-array-bound + * @description THE INDEXABLE-ARRAY BOUND — a law with a name and a refusal, + * not a `continue`. + * + * THE DEFECT. An array-valued metadata field indexes one posting per element, + * so the index has always carried a ceiling. It was 10, and it was applied by a + * bare `continue` deep inside field extraction: + * + * if (Array.isArray(value) && value.length > 10) continue + * + * A row whose `tags` array held ELEVEN entries therefore had that field skipped + * entirely — no posting, no error, no warning. The row then failed to match + * every filtered search on `tags`, including `{ tags: 'a-tag-it-really-has' }`, + * and the caller had no way to tell that from "no row matches". Eleven tags is + * not an exotic shape; the eleventh tag made the row invisible. + * + * THE LAW. Arrays of scalars index up to {@link MAX_INDEXED_ARRAY_LENGTH} = 64, + * hardcoded (the zero-config law: no knob), which clears every legitimate + * multi-value field and stays far below any embedding width. Above it the WRITE + * IS REFUSED by name — `MetadataArrayTooLargeError`, carrying the field, the + * length and the bound — at `add`, `update`, `relate` and `updateRelation` + * alike. Nothing is skipped in silence. + * + * THE ONE PLACE THE BOUND STILL SKIPS is a row already on disk, written by an + * older engine under the old rule and read back by a rebuild, a catch-up fold + * or a remove. Refusing there would make an existing store un-rebuildable — so + * the row is admitted and the skipped field is NARRATED. Both sides are pinned. + */ +import { describe, it, expect, beforeEach, vi, afterEach } from 'vitest' +import { Brainy } from '../../../src/brainy' +import { NounType, VerbType } from '../../../src/types/graphTypes' +import { MetadataArrayTooLargeError, MAX_INDEXED_ARRAY_LENGTH } from '../../../src/errors/brainyError' +import { resolveEntityId } from '../../../src/utils/idNormalization' +import { prodLog } from '../../../src/utils/logger' + +/** `n` distinct scalar tags. */ +function tags(n: number, prefix = 't'): string[] { + return Array.from({ length: n }, (_, i) => `${prefix}${i}`) +} + +describe('the indexable-array bound', () => { + let brain: Brainy + + beforeEach(async () => { + brain = new Brainy({ requireSubtype: false, storage: { type: 'memory' } }) + await brain.init() + }) + + describe('BELOW the bound: the array indexes, every element of it', () => { + it('the eleven-element array that used to vanish is searchable', async () => { + // ELEVEN — one over the old silent limit, the whole shape of the defect. + await brain.add({ + id: 'eleven', + data: 'a row with eleven tags', + type: NounType.Document, + metadata: { tags: tags(11) }, + vector: [] + }) + + // Every element is a posting, including the eleventh. + for (const tag of tags(11)) { + const hits = await brain.find({ where: { tags: tag }, limit: 10 } as any) + expect(hits.map((r: any) => r.id)).toContain(resolveEntityId('eleven')) + } + }) + + it('indexes right up to the bound — all 64 elements', async () => { + await brain.add({ + id: 'at-bound', + data: 'a row at the bound', + type: NounType.Document, + metadata: { tags: tags(MAX_INDEXED_ARRAY_LENGTH) }, + vector: [] + }) + + // The first, the last, and one in the middle. + for (const tag of ['t0', `t${MAX_INDEXED_ARRAY_LENGTH - 1}`, 't31']) { + const hits = await brain.find({ where: { tags: tag }, limit: 10 } as any) + expect(hits.map((r: any) => r.id)).toContain(resolveEntityId('at-bound')) + } + }) + + it('a nested bag\'s array indexes under its dotted address', async () => { + await brain.add({ + id: 'nested', + data: 'a row with a nested tag list', + type: NounType.Document, + metadata: { facets: { labels: tags(20, 'l') } }, + vector: [] + }) + const hits = await brain.find({ where: { 'facets.labels': 'l19' }, limit: 10 } as any) + expect(hits.map((r: any) => r.id)).toContain(resolveEntityId('nested')) + }) + }) + + describe('ABOVE the bound: the write is refused, by name', () => { + const OVER = MAX_INDEXED_ARRAY_LENGTH + 1 + + it('add() throws a typed error naming the field, the length and the bound', async () => { + const err = await brain + .add({ + id: 'too-many', + data: 'a row with too many tags', + type: NounType.Document, + metadata: { tags: tags(OVER) }, + vector: [] + } as any) + .catch((e: any) => e) + + expect(err).toBeInstanceOf(MetadataArrayTooLargeError) + expect(err.field).toBe('tags') + expect(err.length).toBe(OVER) + expect(err.limit).toBe(MAX_INDEXED_ARRAY_LENGTH) + expect(err.type).toBe('VALIDATION') + // The message carries all three, and names the cures. + expect(err.message).toContain('tags') + expect(err.message).toContain(String(OVER)) + expect(err.message).toContain(String(MAX_INDEXED_ARRAY_LENGTH)) + expect(err.message).toContain('vector') + }) + + it('the refused row is not written at all — no half-indexed ghost', async () => { + await expect( + brain.add({ + id: 'refused', + data: 'refused', + type: NounType.Document, + metadata: { tags: tags(OVER) }, + vector: [] + } as any) + ).rejects.toBeInstanceOf(MetadataArrayTooLargeError) + + expect(await brain.get('refused')).toBeNull() + const hits = await brain.find({ where: { tags: 't0' }, limit: 10 } as any) + expect(hits.map((r: any) => r.id)).not.toContain(resolveEntityId('refused')) + }) + + it('a 384-float embedding parked in the metadata bag is refused, not swallowed', async () => { + const err = await brain + .add({ + id: 'bag-vector', + data: 'an embedding in the wrong place', + type: NounType.Document, + metadata: { embedding: Array.from({ length: 384 }, (_, i) => i / 384) }, + vector: [] + } as any) + .catch((e: any) => e) + + expect(err).toBeInstanceOf(MetadataArrayTooLargeError) + expect(err.field).toBe('embedding') + expect(err.length).toBe(384) + }) + + it('update() refuses it too', async () => { + await brain.add({ + id: 'grow', + data: 'starts small', + type: NounType.Document, + metadata: { tags: tags(3) }, + vector: [] + }) + await expect( + brain.update({ id: 'grow', metadata: { tags: tags(OVER) } } as any) + ).rejects.toBeInstanceOf(MetadataArrayTooLargeError) + + // And the row keeps the values it had. + const hits = await brain.find({ where: { tags: 't1' }, limit: 10 } as any) + expect(hits.map((r: any) => r.id)).toContain(resolveEntityId('grow')) + }) + + it('relate() refuses it on a verb\'s metadata', async () => { + await brain.add({ id: 'a', data: 'a', type: NounType.Thing, vector: [] }) + await brain.add({ id: 'b', data: 'b', type: NounType.Thing, vector: [] }) + await expect( + brain.relate({ + from: 'a', + to: 'b', + type: VerbType.RelatedTo, + metadata: { tags: tags(OVER) } + } as any) + ).rejects.toBeInstanceOf(MetadataArrayTooLargeError) + }) + + it('a nested oversize array is refused under its dotted address', async () => { + const err = await brain + .add({ + id: 'nested-over', + data: 'nested and too long', + type: NounType.Document, + metadata: { facets: { labels: tags(OVER, 'l') } }, + vector: [] + } as any) + .catch((e: any) => e) + expect(err).toBeInstanceOf(MetadataArrayTooLargeError) + expect(err.field).toBe('facets.labels') + }) + }) + + describe('a row already on disk is admitted, and the skip is NARRATED', () => { + afterEach(() => { + vi.restoreAllMocks() + }) + + it('extraction over an old oversize row warns by field, length and bound', async () => { + const warn = vi.spyOn(prodLog, 'warn').mockImplementation(() => {}) + const index = (brain as any).metadataIndex + + // The shape an older engine persisted: the write door never saw it, so + // this reaches extraction directly — exactly as a rebuild or a remove + // reading the row back would. + const fields = index.extractIndexableFields({ + metadata: { tags: tags(MAX_INDEXED_ARRAY_LENGTH + 5), keep: 'me' } + }) + + // The oversize field contributes nothing... + expect(fields.filter((f: any) => f.field === 'tags')).toHaveLength(0) + // ...the rest of the row indexes normally — the row is not rejected... + expect(fields.some((f: any) => f.field === 'keep' && f.value === 'me')).toBe(true) + // ...and the skip is said out loud, with everything needed to act on it. + expect(warn).toHaveBeenCalled() + const said = warn.mock.calls.map((c: any[]) => String(c[0])).join('\n') + expect(said).toContain('tags') + expect(said).toContain(String(MAX_INDEXED_ARRAY_LENGTH + 5)) + expect(said).toContain(String(MAX_INDEXED_ARRAY_LENGTH)) + expect(said).toContain('NOT indexed') + }) + + it('an at-bound row on disk is indexed in full and says nothing', async () => { + const warn = vi.spyOn(prodLog, 'warn').mockImplementation(() => {}) + const index = (brain as any).metadataIndex + + const fields = index.extractIndexableFields({ + metadata: { tags: tags(MAX_INDEXED_ARRAY_LENGTH) } + }) + expect(fields.filter((f: any) => f.field === 'tags')).toHaveLength(MAX_INDEXED_ARRAY_LENGTH) + + const said = warn.mock.calls.map((c: any[]) => String(c[0])).join('\n') + expect(said).not.toContain('indexing bound') + }) + }) +})