soulcraft/brainy
2
0
Fork 0
Code Issues 1 Pull requests Projects Releases 335 Packages Wiki Activity Actions

fix: extraction, multi-hop traversal, and aggregate result shape (BR-ADV-FEATURES-BUN)

Browse source 
Three advanced-API correctness fixes, all reproducible on Node (not Bun-specific):

- Entity/concept extraction returned []. SmartExtractor combined agreeing signals
  with a weighted sum compared against an absolute 0.60 gate, so a confident
  low-weight signal lost selection to a mediocre high-weight one that then failed
  the gate, dropping the whole result. Select and gate on a normalized weighted
  average instead. The public `confidence` option now controls the threshold (was
  a dead hardcoded 0.60), and the embedding-signal timeout is raised 100ms -> 2000ms
  so the neural signal is not silently dropped on slower runtimes.

- Multi-hop find({ connected }) returned only the 1-hop neighbour. executeGraphSearch
  ignored depth/via; it now delegates to the depth-aware neighbors() BFS.

- find({ aggregate }) hid groupKey/metrics/count under .metadata, so callers
  expecting AggregateResult saw empty rows. Expose those fields at the top level.

Adds real-embedding regression tests in tests/integration/advanced-apis-regression.test.ts.
This commit is contained in:
David Snelling 2026-05-26 11:32:46 -07:00
parent 07754d135a
commit 0a9d1d9a17
8 changed files with 297 additions and 74 deletions
Download patch file Download diff file Expand all files Collapse all files

71
src/brainy.ts
View file

@ -4559,7 +4559,7 @@ export class Brainy<T = any> implements BrainyInterface<T> {
}
): Promise<string[]> {
const entities = await this.extract(text, {
types: [NounType.Concept, NounType.Concept],
types: [NounType.Concept],
confidence: options?.confidence || 0.7,
neuralMatching: true
})
@ -6787,36 +6787,58 @@ export class Brainy<T = any> implements BrainyInterface<T> {
}
/**
* Execute graph search component with O(1) traversal
* Execute graph search component.
*
* Honors the full `GraphConstraints` contract: multi-hop `depth` (breadth-first via
* `neighbors()`), `via`/`type` verb-type filtering, and `direction`. Previously this read
* only `from`/`to`/`direction` and did a single 1-hop `getNeighbors()`, so `depth` and `via`
* were silently ignored — `find({ connected: { from, depth: 3 } })` returned only the
* immediate neighbour at every depth.
*/
private async executeGraphSearch(params: FindParams<T>, existingResults: Result<T>[]): Promise<Result<T>[]> {
if (!params.connected) return existingResults
const { from, to, direction = 'both' } = params.connected
const connectedIds: string[] = []
const { from, to, depth, direction = 'both' } = params.connected
const via = params.connected.via ?? params.connected.type
// GraphConstraints speaks 'in' | 'out' | 'both'; neighbors() speaks 'incoming' | 'outgoing' | 'both'.
const toNeighborDir = (d: 'in' | 'out' | 'both'): 'incoming' | 'outgoing' | 'both' =>
d === 'in' ? 'incoming' : d === 'out' ? 'outgoing' : 'both'
// Collect reachable ids honoring depth + verb-type filter. `via` may be a single VerbType
// or an array; reuse the depth-aware BFS in neighbors() (one pass per requested verb type).
const collect = async (id: string, dir: 'incoming' | 'outgoing' | 'both'): Promise<string[]> => {
const verbTypes: Array<VerbType | undefined> =
via === undefined ? [undefined] : Array.isArray(via) ? via : [via]
const ids = new Set<string>()
for (const verbType of verbTypes) {
const hops = await this.neighbors(id, { direction: dir, depth: depth ?? 1, verbType })
for (const n of hops) ids.add(n)
}
return [...ids]
}
const connectedIds = new Set<string>()
if (from) {
const neighbors = await this.graphIndex.getNeighbors(from, direction)
connectedIds.push(...neighbors)
for (const id of await collect(from, toNeighborDir(direction))) connectedIds.add(id)
}
if (to) {
const reverseDirection = direction === 'in' ? 'out' : direction === 'out' ? 'in' : 'both'
const neighbors = await this.graphIndex.getNeighbors(to, reverseDirection)
connectedIds.push(...neighbors)
const reverse: 'in' | 'out' | 'both' = direction === 'in' ? 'out' : direction === 'out' ? 'in' : 'both'
for (const id of await collect(to, toNeighborDir(reverse))) connectedIds.add(id)
}
// Filter existing results to only connected entities
if (existingResults.length > 0) {
const connectedIdSet = new Set(connectedIds)
return existingResults.filter(r => connectedIdSet.has(r.id))
return existingResults.filter(r => connectedIds.has(r.id))
}
// Batch-load connected entities for 10x faster cloud storage performance
// GCS: 20 entities = 1×50ms vs 20×50ms = 1000ms (20x faster)
// Batch-load connected entities for fast cloud-storage performance
const results: Result<T>[] = []
const entitiesMap = await this.batchGet(connectedIds)
for (const id of connectedIds) {
const ids = [...connectedIds]
const entitiesMap = await this.batchGet(ids)
for (const id of ids) {
const entity = entitiesMap.get(id)
if (entity) {
results.push(this.createResult(id, 1.0, entity))
@ -7912,7 +7934,14 @@ export class Brainy<T = any> implements BrainyInterface<T> {
type: NounType.Measurement,
metadata: entity.metadata,
data: entity.data,
entity
entity,
// Surface the documented AggregateResult fields at the top level so consumers can read
// groupKey/metrics/count directly. Previously these were only reachable under .metadata,
// so callers expecting an AggregateResult saw rows with no groupKey/metrics/count and
// interpreted the output as degenerate/empty.
groupKey: agg.groupKey,
metrics: agg.metrics,
count: agg.count
}
})
}

101
src/neural/SmartExtractor.ts
View file

@ -211,12 +211,18 @@ export class SmartExtractor {
formatContext?: FormatContext
allTerms?: string[]
metadata?: any
}
},
minConfidence?: number
): Promise<ExtractionResult | null> {
this.stats.calls++
// Per-call confidence threshold (falls back to the instance default). This lets callers
// such as brain.extractEntities({ confidence }) actually loosen or tighten the gate; it is
// part of the cache key below so results computed at one threshold are not reused at another.
const threshold = minConfidence ?? this.options.minConfidence
// Check cache first
const cacheKey = this.getCacheKey(candidate, context)
const cacheKey = this.getCacheKey(candidate, context, threshold)
const cached = this.getFromCache(cacheKey)
if (cached !== undefined) {
this.stats.cacheHits++
@ -282,8 +288,8 @@ export class SmartExtractor {
// Combine using ensemble or best signal
const result = this.options.enableEnsemble
? this.combineEnsemble(signalResults, formatHints, context?.formatContext)
: this.selectBestSignal(signalResults, formatHints, context?.formatContext)
? this.combineEnsemble(signalResults, formatHints, context?.formatContext, threshold)
: this.selectBestSignal(signalResults, formatHints, context?.formatContext, threshold)
// Cache result (including nulls to avoid recomputation)
this.addToCache(cacheKey, result)
@ -509,7 +515,8 @@ export class SmartExtractor {
private combineEnsemble(
signalResults: SignalResult[],
formatHints: string[],
formatContext?: FormatContext
formatContext?: FormatContext,
minConfidence: number = this.options.minConfidence
): ExtractionResult | null {
// Filter out null results
const validResults = signalResults.filter(r => r.type !== null)
@ -518,58 +525,63 @@ export class SmartExtractor {
return null
}
// Count votes by type with weighted confidence
const typeScores = new Map<NounType, { score: number; signals: SignalResult[] }>()
// Group the signals by the type they voted for
const typeScores = new Map<NounType, SignalResult[]>()
for (const result of validResults) {
if (!result.type) continue
const weighted = result.confidence * result.weight
const existing = typeScores.get(result.type)
if (existing) {
existing.score += weighted
existing.signals.push(result)
existing.push(result)
} else {
typeScores.set(result.type, { score: weighted, signals: [result] })
typeScores.set(result.type, [result])
}
}
// Find best type
// Score each candidate type by a NORMALIZED, weighted-average confidence
// — Σ(confidence·weight) / Σ(weight of its signals) — plus a small boost when
// multiple signals concur, then select the type with the highest such confidence.
//
// Why an average and not a sum (this was the bug): a weighted *sum* lives on the
// signal-weight scale, so two signals agreeing on a fresh brain summed to ≈0.37 —
// below the 0.60 gate — meaning agreement was effectively *penalized*. Worse, selecting
// the best type by that sum let a high-weight signal with mediocre confidence
// (embedding @0.51 · 0.35 = 0.179) outrank a low-weight signal with high confidence
// (pattern @0.82 · 0.20 = 0.164); the wrong type won selection, then failed the threshold
// on its own 0.51 confidence, and the whole extraction returned null. Averaging keeps the
// score on the same 0–1 scale as the threshold, so selection and the gate agree and the
// most-confident type wins (pattern @0.82 here).
let bestType: NounType | null = null
let bestScore = 0
let finalConfidence = 0
let bestSignals: SignalResult[] = []
for (const [type, data] of typeScores.entries()) {
// Apply agreement boost (multiple signals agree)
let finalScore = data.score
if (data.signals.length > 1) {
const agreementBoost = 0.05 * (data.signals.length - 1)
finalScore += agreementBoost
this.stats.agreementBoosts++
for (const [type, signals] of typeScores.entries()) {
const weightSum = signals.reduce((sum, s) => sum + s.weight, 0)
const weightedConfidence = signals.reduce((sum, s) => sum + s.confidence * s.weight, 0)
let confidence = weightSum > 0 ? weightedConfidence / weightSum : 0
// Reward agreement between independent signals
if (signals.length > 1) {
confidence = Math.min(confidence + 0.05 * (signals.length - 1), 1.0)
}
if (finalScore > bestScore) {
bestScore = finalScore
if (confidence > finalConfidence) {
finalConfidence = confidence
bestType = type
bestSignals = data.signals
bestSignals = signals
}
}
// Determine final confidence score
// FIX: When only one signal matches, use its original confidence instead of weighted score
// The weighted score is too low when only one signal matches (e.g., 0.8 * 0.2 = 0.16 < 0.60 threshold)
let finalConfidence = bestScore
if (bestSignals.length === 1) {
// Single signal: use its original confidence
finalConfidence = bestSignals[0].confidence
}
// Check minimum confidence threshold
if (!bestType || finalConfidence < this.options.minConfidence) {
if (!bestType || finalConfidence < minConfidence) {
return null
}
if (bestSignals.length > 1) {
this.stats.agreementBoosts++
}
// Track signal contributions
const usedSignals = bestSignals.length
this.stats.averageSignalsUsed =
@ -604,13 +616,17 @@ export class SmartExtractor {
private selectBestSignal(
signalResults: SignalResult[],
formatHints: string[],
formatContext?: FormatContext
formatContext?: FormatContext,
minConfidence: number = this.options.minConfidence
): ExtractionResult | null {
// Filter valid results and sort by weighted confidence
// Select by confidence — the same metric the threshold checks below. Sorting by
// weighted score (confidence·weight) instead would let a high-weight, mediocre-confidence
// signal outrank a low-weight, high-confidence one and then fail the gate, dropping the
// result entirely (the same defect fixed in combineEnsemble). Weight matters for ensemble
// voting, not for picking the single best signal.
const validResults = signalResults
.filter(r => r.type !== null)
.map(r => ({ ...r, weightedScore: r.confidence * r.weight }))
.sort((a, b) => b.weightedScore - a.weightedScore)
.sort((a, b) => b.confidence - a.confidence)
if (validResults.length === 0) {
return null
@ -618,9 +634,7 @@ export class SmartExtractor {
const best = validResults[0]
// FIX: Use original confidence, not weighted score for threshold check
// Weighted score is for ranking signals, not for absolute threshold
if (best.confidence < this.options.minConfidence) {
if (best.confidence < minConfidence) {
return null
}
@ -661,11 +675,12 @@ export class SmartExtractor {
/**
* Get cache key from candidate and context
*/
private getCacheKey(candidate: string, context?: any): string {
private getCacheKey(candidate: string, context?: any, minConfidence?: number): string {
const normalized = candidate.toLowerCase().trim()
const defSnippet = context?.definition?.substring(0, 50) || ''
const format = context?.formatContext?.format || ''
return `${normalized}:${defSnippet}:${format}`
const threshold = minConfidence ?? this.options.minConfidence
return `${normalized}:${defSnippet}:${format}:${threshold}`
}
/**

11
src/neural/entityExtractor.ts
View file

@ -140,14 +140,17 @@ export class NeuralEntityExtractor {
// Step 2: Classify each candidate using SmartExtractor
for (const candidate of candidates) {
// Use SmartExtractor for unified neural + rule-based classification
// Use SmartExtractor for unified neural + rule-based classification.
// Pass the caller's threshold through so `confidence` actually controls the gate
// (previously SmartExtractor applied a hardcoded 0.60 floor, so a low confidence
// option had no loosening effect).
const classification = await this.smartExtractor.extract(candidate.text, {
definition: candidate.context,
allTerms: [candidate.text, candidate.context]
})
}, minConfidence)
// Skip if SmartExtractor returns null (low confidence) or below threshold
if (!classification || classification.confidence < minConfidence) {
// SmartExtractor already gates at minConfidence; this guards against null only.
if (!classification) {
continue
}

7
src/neural/signals/EmbeddingSignal.ts
View file

@ -43,7 +43,10 @@ export interface EmbeddingSignalOptions {
minConfidence?: number // Minimum confidence threshold (default: 0.60)
checkGraph?: boolean // Check against graph entities (default: true)
checkHistory?: boolean // Check against historical data (default: true)
timeout?: number // Max time in ms (default: 100)
timeout?: number // Max time in ms (default: 2000). A real transformer embed of a single
// candidate is commonly 50–200ms (cold/under load higher); the previous
// 100ms default silently timed out, dropping the neural signal entirely —
// which alone left concept extraction (no regex fallback) returning nothing.
cacheSize?: number // LRU cache size (default: 1000)
}
@ -110,7 +113,7 @@ export class EmbeddingSignal {
minConfidence: options?.minConfidence ?? 0.60,
checkGraph: options?.checkGraph ?? true,
checkHistory: options?.checkHistory ?? true,
timeout: options?.timeout ?? 100,
timeout: options?.timeout ?? 2000,
cacheSize: options?.cacheSize ?? 1000
}
}

8
src/types/brainy.types.ts
View file

@ -122,6 +122,14 @@ export interface Result<T = any> {
semanticScore?: number // Semantic similarity score (0-1)
matchSource?: 'text' | 'semantic' | 'both' // Where this result came from
rrfScore?: number // Raw RRF fusion score (for advanced ranking analysis)
// Aggregation: present only on rows returned by find({ aggregate }). These mirror the
// documented AggregateResult shape so callers can read group/metric data at the top level
// instead of digging into `metadata`. (The same values are also flattened into `metadata`
// for backward compatibility.)
groupKey?: Record<string, string | number> // Group-by key values for this aggregate row
metrics?: Record<string, number> // Computed metric values (sum/avg/min/max/count)
count?: number // Total entity count in this group
}
/**