brainy/src/transaction/operations/IndexOperations.ts

340 lines
11 KiB
TypeScript
Raw Normal View History

/**
* Index Operations with Rollback Support
*
* Provides transactional operations for all indexes:
* - JsHnswVectorIndex (unified vector index)
* - MetadataIndexManager (roaring bitmap filtering)
* - GraphAdjacencyIndex (LSM-tree graph storage)
*
* Each operation can be executed and rolled back atomically.
*/
import type { JsHnswVectorIndex } from '../../hnsw/hnswIndex.js'
import type { MetadataIndexManager } from '../../utils/metadataIndex.js'
feat(8.0): u64 BigInt graph provider contract — punch list a-d,g,h GraphIndexProvider now speaks BigInt at the boundary (D.2 mirror): - getNeighbors/getVerbIdsBySource/getVerbIdsByTarget take entity ints and return entity/verb ints as bigint[] - new REQUIRED verbIntsToIds(bigint[]) batch reverse resolver (L.7 identity-fingerprint design — verb ids are UUIDs by contract, so the provider-side interning is losslessly reversible) - addVerb(verb, sourceInt, targetInt) returns the interned verb int; removeVerb(verbId) joins the contract Coordinator (brainy.ts) owns ALL UUID <-> int conversion: getOrAssign on writes, getInt on reads (unmapped UUID -> empty result without calling the provider), getUuid / verbIntsToIds on returns, plus a bounded ~100k-entry insertion-order warm cache for verb-int -> verb-id pairs fed by addVerb returns and resolver results. GraphVerb gains derived sourceInt/targetInt (populated at add time, never persisted). findConnectedSubtype gains a native fast path that routes single-type single-subtype outgoing BFS through the provider when available. JS GraphAdjacencyIndex satisfies the contract while staying string/u32-keyed internally: entity ints resolve through the shared entity-id mapper (threaded in by the coordinator on init/fork/checkout), verb ints come from an in-process append-only interning map re-derived from storage on rebuild/cold-start. ColumnStoreProvider widens the same way: addEntity/ removeEntity take bigint, sortTopK/filteredSortTopK return bigint[]. relate() now rejects a caller-supplied id with a teaching error — verb ids are brainy-generated UUIDs by contract in 8.0 (previously a passed id was silently ignored). No Roaring64 provider-boundary decode site exists yet; the JS-internal column store stays Roaring32 and the Treemap decoder lands with the first consumer of provider-returned filter buffers. Public brain API unchanged. 1413 tests green (+10 new BigInt contract tests).
2026-06-10 10:45:45 -07:00
import type { GraphIndexProvider } from '../../plugin.js'
import type { GraphVerb } from '../../coreTypes.js'
import type { Operation, RollbackAction } from '../types.js'
/**
* Add to HNSW index with rollback support
*
* Rollback strategy:
* - Remove item from index
feat(8.0)!: delete fork/branch/commit/history/versions — superseded by the Db API The COW version-control surface (fork, branches, checkout, commit, getHistory/streamHistory, asOfCommit, brain.versions) is gone, along with its subsystems: src/versioning/, the COW object store (CommitLog, CommitObject, RefManager, TreeObject), HistoricalStorageAdapter, and the TypeAwareHNSWIndex path it kept alive. The Db API (now/transact/asOf/ with/persist/restore) is the one versioning model in 8.0. Survivors and replacements: - BlobStorage survives (the VFS stores file content through it), relocated to src/storage/blobStorage.ts with binaryDataCodec.ts; its adapter interface is now BlobStoreAdapter, slimmed to the consumed surface (write/read/has/delete/getMetadata + MIME-aware compression policy). - brain.migrate() backup branches are replaced by persist-before-migrate: MigrateOptions.backupTo persists a hard-link snapshot of the current generation before any transform runs; MigrationResult.backupPath reports it, and brain.restore(path) brings it back wholesale. - CLI: cow.ts (fork/branch/checkout/history/migrate) is replaced by snapshot.ts — snapshot <path>, restore <path>, history (tx-log), generation. - New public read API: brain.transactionLog({limit}) exposes the reified tx-log (generation/timestamp/meta, newest first) that backs the CLI history command; TxLogEntry is exported. Tests: superseded suites deleted; fork/commit blocks excised from shared suites; BlobStorage tests relocated + reworked against the slimmed store; migration tests now prove the backupTo snapshot/restore round trip; new transactionLog coverage in db-mvcc.
2026-06-10 15:22:47 -07:00
*/
export class AddToHNSWOperation implements Operation {
readonly name = 'AddToHNSW'
constructor(
private readonly index: JsHnswVectorIndex,
private readonly id: string,
private readonly vector: number[]
) {}
async execute(): Promise<RollbackAction> {
// Check if item already exists (for rollback decision)
const existed = await this.itemExists(this.id)
// Add to index
await this.index.addItem({ id: this.id, vector: this.vector })
// Return rollback action
return async () => {
if (!existed) {
// Remove newly added item
await this.index.removeItem(this.id)
}
// If item existed before, we don't rollback (update is OK)
// This prevents index corruption from removing pre-existing items
}
}
/**
* Check if item exists in index.
*
* `getItem` is an optional, feature-detected provider capability see the
* VectorIndexProvider docs; it is intentionally absent from the required
* contract (Brainy's JS HNSW index omits it). When the capability is
* missing the answer must be `false`, not `true`: treating unknowable
* pre-existence as "existed" made every rollback skip removeItem, leaving
* phantom entries in the index after a failed transaction. The safe default
* is to remove what this operation added update flows pair this op with a
* RemoveFromHNSWOperation whose own rollback restores the prior vector, so
* reverse-order rollback reconstructs the original state either way.
*/
private async itemExists(id: string): Promise<boolean> {
const index = this.index as JsHnswVectorIndex & {
getItem?: (id: string) => Promise<unknown>
}
if (typeof index.getItem !== 'function') return false
try {
const item = await index.getItem(id)
return item !== undefined && item !== null
} catch {
return false
}
}
}
/**
* Remove from HNSW index with rollback support
*
* Rollback strategy:
* - Re-add item to index with original vector
*
* Note: Requires storing the vector for rollback
*/
export class RemoveFromHNSWOperation implements Operation {
readonly name = 'RemoveFromHNSW'
constructor(
private readonly index: JsHnswVectorIndex,
private readonly id: string,
private readonly vector: number[] // Required for rollback
) {}
async execute(): Promise<RollbackAction> {
// Remove from index
await this.index.removeItem(this.id)
// Return rollback action
return async () => {
// Re-add item with original vector
await this.index.addItem({ id: this.id, vector: this.vector })
}
}
}
/**
* Add to metadata index with rollback support
*
* Rollback strategy:
* - Remove item from index
*/
export class AddToMetadataIndexOperation implements Operation {
readonly name = 'AddToMetadataIndex'
constructor(
private readonly index: MetadataIndexManager,
private readonly id: string,
private readonly entity: any // Entity or metadata structure
) {}
async execute(): Promise<RollbackAction> {
// Add to metadata index (skipFlush=true for transaction atomicity)
await this.index.addToIndex(this.id, this.entity, true)
// Return rollback action
return async () => {
// Remove from metadata index
await this.index.removeFromIndex(this.id, this.entity)
}
}
}
/**
* Remove from metadata index with rollback support
*
* Rollback strategy:
* - Re-add item to index with original metadata
*/
export class RemoveFromMetadataIndexOperation implements Operation {
readonly name = 'RemoveFromMetadataIndex'
constructor(
private readonly index: MetadataIndexManager,
private readonly id: string,
private readonly entity: any // Required for rollback
) {}
async execute(): Promise<RollbackAction> {
// Remove from metadata index
await this.index.removeFromIndex(this.id, this.entity)
// Return rollback action
return async () => {
// Re-add with original metadata (skipFlush=true)
await this.index.addToIndex(this.id, this.entity, true)
}
}
}
/**
* Add verb to graph index with rollback support
*
* Rollback strategy:
* - Remove verb from graph index
feat(8.0): u64 BigInt graph provider contract — punch list a-d,g,h GraphIndexProvider now speaks BigInt at the boundary (D.2 mirror): - getNeighbors/getVerbIdsBySource/getVerbIdsByTarget take entity ints and return entity/verb ints as bigint[] - new REQUIRED verbIntsToIds(bigint[]) batch reverse resolver (L.7 identity-fingerprint design — verb ids are UUIDs by contract, so the provider-side interning is losslessly reversible) - addVerb(verb, sourceInt, targetInt) returns the interned verb int; removeVerb(verbId) joins the contract Coordinator (brainy.ts) owns ALL UUID <-> int conversion: getOrAssign on writes, getInt on reads (unmapped UUID -> empty result without calling the provider), getUuid / verbIntsToIds on returns, plus a bounded ~100k-entry insertion-order warm cache for verb-int -> verb-id pairs fed by addVerb returns and resolver results. GraphVerb gains derived sourceInt/targetInt (populated at add time, never persisted). findConnectedSubtype gains a native fast path that routes single-type single-subtype outgoing BFS through the provider when available. JS GraphAdjacencyIndex satisfies the contract while staying string/u32-keyed internally: entity ints resolve through the shared entity-id mapper (threaded in by the coordinator on init/fork/checkout), verb ints come from an in-process append-only interning map re-derived from storage on rebuild/cold-start. ColumnStoreProvider widens the same way: addEntity/ removeEntity take bigint, sortTopK/filteredSortTopK return bigint[]. relate() now rejects a caller-supplied id with a teaching error — verb ids are brainy-generated UUIDs by contract in 8.0 (previously a passed id was silently ignored). No Roaring64 provider-boundary decode site exists yet; the JS-internal column store stays Roaring32 and the Treemap decoder lands with the first consumer of provider-returned filter buffers. Public brain API unchanged. 1413 tests green (+10 new BigInt contract tests).
2026-06-10 10:45:45 -07:00
*
* 8.0 u64 contract: the coordinator resolves both endpoint ints via the
* shared idMapper (`getOrAssign`) and passes them alongside the verb; the
* provider returns the interned verb int, which is surfaced through the
* optional `onVerbInt` callback so the coordinator can feed its warm cache.
*
* Generation: `generationFn` is resolved at execute time (not construction) so
* the edge is stamped at the transaction's in-flight commit generation which
* the generation store only assigns once the batch begins executing. The same
* generation is reused for the rollback removal, so an add and its undo
* reference one watermark in a provider's per-generation edge chain.
*/
export class AddToGraphIndexOperation implements Operation {
readonly name = 'AddToGraphIndex'
feat(8.0): u64 BigInt graph provider contract — punch list a-d,g,h GraphIndexProvider now speaks BigInt at the boundary (D.2 mirror): - getNeighbors/getVerbIdsBySource/getVerbIdsByTarget take entity ints and return entity/verb ints as bigint[] - new REQUIRED verbIntsToIds(bigint[]) batch reverse resolver (L.7 identity-fingerprint design — verb ids are UUIDs by contract, so the provider-side interning is losslessly reversible) - addVerb(verb, sourceInt, targetInt) returns the interned verb int; removeVerb(verbId) joins the contract Coordinator (brainy.ts) owns ALL UUID <-> int conversion: getOrAssign on writes, getInt on reads (unmapped UUID -> empty result without calling the provider), getUuid / verbIntsToIds on returns, plus a bounded ~100k-entry insertion-order warm cache for verb-int -> verb-id pairs fed by addVerb returns and resolver results. GraphVerb gains derived sourceInt/targetInt (populated at add time, never persisted). findConnectedSubtype gains a native fast path that routes single-type single-subtype outgoing BFS through the provider when available. JS GraphAdjacencyIndex satisfies the contract while staying string/u32-keyed internally: entity ints resolve through the shared entity-id mapper (threaded in by the coordinator on init/fork/checkout), verb ints come from an in-process append-only interning map re-derived from storage on rebuild/cold-start. ColumnStoreProvider widens the same way: addEntity/ removeEntity take bigint, sortTopK/filteredSortTopK return bigint[]. relate() now rejects a caller-supplied id with a teaching error — verb ids are brainy-generated UUIDs by contract in 8.0 (previously a passed id was silently ignored). No Roaring64 provider-boundary decode site exists yet; the JS-internal column store stays Roaring32 and the Treemap decoder lands with the first consumer of provider-returned filter buffers. Public brain API unchanged. 1413 tests green (+10 new BigInt contract tests).
2026-06-10 10:45:45 -07:00
/**
* @param index - The graph-index provider (JS baseline or native).
* @param verb - The verb to index (`sourceInt`/`targetInt` mirrored on it).
* @param sourceInt - The source entity's interned int.
* @param targetInt - The target entity's interned int.
* @param generationFn - Resolves the commit generation to stamp this edge at,
* evaluated when the operation executes (see class note).
feat(8.0): u64 BigInt graph provider contract — punch list a-d,g,h GraphIndexProvider now speaks BigInt at the boundary (D.2 mirror): - getNeighbors/getVerbIdsBySource/getVerbIdsByTarget take entity ints and return entity/verb ints as bigint[] - new REQUIRED verbIntsToIds(bigint[]) batch reverse resolver (L.7 identity-fingerprint design — verb ids are UUIDs by contract, so the provider-side interning is losslessly reversible) - addVerb(verb, sourceInt, targetInt) returns the interned verb int; removeVerb(verbId) joins the contract Coordinator (brainy.ts) owns ALL UUID <-> int conversion: getOrAssign on writes, getInt on reads (unmapped UUID -> empty result without calling the provider), getUuid / verbIntsToIds on returns, plus a bounded ~100k-entry insertion-order warm cache for verb-int -> verb-id pairs fed by addVerb returns and resolver results. GraphVerb gains derived sourceInt/targetInt (populated at add time, never persisted). findConnectedSubtype gains a native fast path that routes single-type single-subtype outgoing BFS through the provider when available. JS GraphAdjacencyIndex satisfies the contract while staying string/u32-keyed internally: entity ints resolve through the shared entity-id mapper (threaded in by the coordinator on init/fork/checkout), verb ints come from an in-process append-only interning map re-derived from storage on rebuild/cold-start. ColumnStoreProvider widens the same way: addEntity/ removeEntity take bigint, sortTopK/filteredSortTopK return bigint[]. relate() now rejects a caller-supplied id with a teaching error — verb ids are brainy-generated UUIDs by contract in 8.0 (previously a passed id was silently ignored). No Roaring64 provider-boundary decode site exists yet; the JS-internal column store stays Roaring32 and the Treemap decoder lands with the first consumer of provider-returned filter buffers. Public brain API unchanged. 1413 tests green (+10 new BigInt contract tests).
2026-06-10 10:45:45 -07:00
* @param onVerbInt - Optional hook invoked with the interned verb int
* returned by the provider (feeds the coordinator's verb-int warm cache).
*/
constructor(
feat(8.0): u64 BigInt graph provider contract — punch list a-d,g,h GraphIndexProvider now speaks BigInt at the boundary (D.2 mirror): - getNeighbors/getVerbIdsBySource/getVerbIdsByTarget take entity ints and return entity/verb ints as bigint[] - new REQUIRED verbIntsToIds(bigint[]) batch reverse resolver (L.7 identity-fingerprint design — verb ids are UUIDs by contract, so the provider-side interning is losslessly reversible) - addVerb(verb, sourceInt, targetInt) returns the interned verb int; removeVerb(verbId) joins the contract Coordinator (brainy.ts) owns ALL UUID <-> int conversion: getOrAssign on writes, getInt on reads (unmapped UUID -> empty result without calling the provider), getUuid / verbIntsToIds on returns, plus a bounded ~100k-entry insertion-order warm cache for verb-int -> verb-id pairs fed by addVerb returns and resolver results. GraphVerb gains derived sourceInt/targetInt (populated at add time, never persisted). findConnectedSubtype gains a native fast path that routes single-type single-subtype outgoing BFS through the provider when available. JS GraphAdjacencyIndex satisfies the contract while staying string/u32-keyed internally: entity ints resolve through the shared entity-id mapper (threaded in by the coordinator on init/fork/checkout), verb ints come from an in-process append-only interning map re-derived from storage on rebuild/cold-start. ColumnStoreProvider widens the same way: addEntity/ removeEntity take bigint, sortTopK/filteredSortTopK return bigint[]. relate() now rejects a caller-supplied id with a teaching error — verb ids are brainy-generated UUIDs by contract in 8.0 (previously a passed id was silently ignored). No Roaring64 provider-boundary decode site exists yet; the JS-internal column store stays Roaring32 and the Treemap decoder lands with the first consumer of provider-returned filter buffers. Public brain API unchanged. 1413 tests green (+10 new BigInt contract tests).
2026-06-10 10:45:45 -07:00
private readonly index: GraphIndexProvider,
private readonly verb: GraphVerb,
private readonly sourceInt: bigint,
private readonly targetInt: bigint,
private readonly generationFn: () => bigint,
feat(8.0): u64 BigInt graph provider contract — punch list a-d,g,h GraphIndexProvider now speaks BigInt at the boundary (D.2 mirror): - getNeighbors/getVerbIdsBySource/getVerbIdsByTarget take entity ints and return entity/verb ints as bigint[] - new REQUIRED verbIntsToIds(bigint[]) batch reverse resolver (L.7 identity-fingerprint design — verb ids are UUIDs by contract, so the provider-side interning is losslessly reversible) - addVerb(verb, sourceInt, targetInt) returns the interned verb int; removeVerb(verbId) joins the contract Coordinator (brainy.ts) owns ALL UUID <-> int conversion: getOrAssign on writes, getInt on reads (unmapped UUID -> empty result without calling the provider), getUuid / verbIntsToIds on returns, plus a bounded ~100k-entry insertion-order warm cache for verb-int -> verb-id pairs fed by addVerb returns and resolver results. GraphVerb gains derived sourceInt/targetInt (populated at add time, never persisted). findConnectedSubtype gains a native fast path that routes single-type single-subtype outgoing BFS through the provider when available. JS GraphAdjacencyIndex satisfies the contract while staying string/u32-keyed internally: entity ints resolve through the shared entity-id mapper (threaded in by the coordinator on init/fork/checkout), verb ints come from an in-process append-only interning map re-derived from storage on rebuild/cold-start. ColumnStoreProvider widens the same way: addEntity/ removeEntity take bigint, sortTopK/filteredSortTopK return bigint[]. relate() now rejects a caller-supplied id with a teaching error — verb ids are brainy-generated UUIDs by contract in 8.0 (previously a passed id was silently ignored). No Roaring64 provider-boundary decode site exists yet; the JS-internal column store stays Roaring32 and the Treemap decoder lands with the first consumer of provider-returned filter buffers. Public brain API unchanged. 1413 tests green (+10 new BigInt contract tests).
2026-06-10 10:45:45 -07:00
private readonly onVerbInt?: (verbInt: bigint) => void
) {}
async execute(): Promise<RollbackAction> {
// Stamp this edge at the in-flight commit generation; reuse it for the
// rollback so add + undo reference the same watermark.
const generation = this.generationFn()
const verbInt = await this.index.addVerb(this.verb, this.sourceInt, this.targetInt, generation)
feat(8.0): u64 BigInt graph provider contract — punch list a-d,g,h GraphIndexProvider now speaks BigInt at the boundary (D.2 mirror): - getNeighbors/getVerbIdsBySource/getVerbIdsByTarget take entity ints and return entity/verb ints as bigint[] - new REQUIRED verbIntsToIds(bigint[]) batch reverse resolver (L.7 identity-fingerprint design — verb ids are UUIDs by contract, so the provider-side interning is losslessly reversible) - addVerb(verb, sourceInt, targetInt) returns the interned verb int; removeVerb(verbId) joins the contract Coordinator (brainy.ts) owns ALL UUID <-> int conversion: getOrAssign on writes, getInt on reads (unmapped UUID -> empty result without calling the provider), getUuid / verbIntsToIds on returns, plus a bounded ~100k-entry insertion-order warm cache for verb-int -> verb-id pairs fed by addVerb returns and resolver results. GraphVerb gains derived sourceInt/targetInt (populated at add time, never persisted). findConnectedSubtype gains a native fast path that routes single-type single-subtype outgoing BFS through the provider when available. JS GraphAdjacencyIndex satisfies the contract while staying string/u32-keyed internally: entity ints resolve through the shared entity-id mapper (threaded in by the coordinator on init/fork/checkout), verb ints come from an in-process append-only interning map re-derived from storage on rebuild/cold-start. ColumnStoreProvider widens the same way: addEntity/ removeEntity take bigint, sortTopK/filteredSortTopK return bigint[]. relate() now rejects a caller-supplied id with a teaching error — verb ids are brainy-generated UUIDs by contract in 8.0 (previously a passed id was silently ignored). No Roaring64 provider-boundary decode site exists yet; the JS-internal column store stays Roaring32 and the Treemap decoder lands with the first consumer of provider-returned filter buffers. Public brain API unchanged. 1413 tests green (+10 new BigInt contract tests).
2026-06-10 10:45:45 -07:00
this.onVerbInt?.(verbInt)
// Return rollback action
return async () => {
// Remove verb from graph index
await this.index.removeVerb(this.verb.id, generation)
}
}
}
/**
* Remove verb from graph index with rollback support
*
* Rollback strategy:
* - Re-add verb to graph index
feat(8.0): u64 BigInt graph provider contract — punch list a-d,g,h GraphIndexProvider now speaks BigInt at the boundary (D.2 mirror): - getNeighbors/getVerbIdsBySource/getVerbIdsByTarget take entity ints and return entity/verb ints as bigint[] - new REQUIRED verbIntsToIds(bigint[]) batch reverse resolver (L.7 identity-fingerprint design — verb ids are UUIDs by contract, so the provider-side interning is losslessly reversible) - addVerb(verb, sourceInt, targetInt) returns the interned verb int; removeVerb(verbId) joins the contract Coordinator (brainy.ts) owns ALL UUID <-> int conversion: getOrAssign on writes, getInt on reads (unmapped UUID -> empty result without calling the provider), getUuid / verbIntsToIds on returns, plus a bounded ~100k-entry insertion-order warm cache for verb-int -> verb-id pairs fed by addVerb returns and resolver results. GraphVerb gains derived sourceInt/targetInt (populated at add time, never persisted). findConnectedSubtype gains a native fast path that routes single-type single-subtype outgoing BFS through the provider when available. JS GraphAdjacencyIndex satisfies the contract while staying string/u32-keyed internally: entity ints resolve through the shared entity-id mapper (threaded in by the coordinator on init/fork/checkout), verb ints come from an in-process append-only interning map re-derived from storage on rebuild/cold-start. ColumnStoreProvider widens the same way: addEntity/ removeEntity take bigint, sortTopK/filteredSortTopK return bigint[]. relate() now rejects a caller-supplied id with a teaching error — verb ids are brainy-generated UUIDs by contract in 8.0 (previously a passed id was silently ignored). No Roaring64 provider-boundary decode site exists yet; the JS-internal column store stays Roaring32 and the Treemap decoder lands with the first consumer of provider-returned filter buffers. Public brain API unchanged. 1413 tests green (+10 new BigInt contract tests).
2026-06-10 10:45:45 -07:00
*
* 8.0 u64 contract: rollback re-adds through `addVerb(verb, sourceInt,
* targetInt, generation)`, so the coordinator resolves the endpoint ints up
* front (while the entity int mappings are guaranteed to still exist). The
* removal generation is resolved at execute time and reused for the rollback
* re-add, so the round trip references one watermark.
*/
export class RemoveFromGraphIndexOperation implements Operation {
readonly name = 'RemoveFromGraphIndex'
feat(8.0): u64 BigInt graph provider contract — punch list a-d,g,h GraphIndexProvider now speaks BigInt at the boundary (D.2 mirror): - getNeighbors/getVerbIdsBySource/getVerbIdsByTarget take entity ints and return entity/verb ints as bigint[] - new REQUIRED verbIntsToIds(bigint[]) batch reverse resolver (L.7 identity-fingerprint design — verb ids are UUIDs by contract, so the provider-side interning is losslessly reversible) - addVerb(verb, sourceInt, targetInt) returns the interned verb int; removeVerb(verbId) joins the contract Coordinator (brainy.ts) owns ALL UUID <-> int conversion: getOrAssign on writes, getInt on reads (unmapped UUID -> empty result without calling the provider), getUuid / verbIntsToIds on returns, plus a bounded ~100k-entry insertion-order warm cache for verb-int -> verb-id pairs fed by addVerb returns and resolver results. GraphVerb gains derived sourceInt/targetInt (populated at add time, never persisted). findConnectedSubtype gains a native fast path that routes single-type single-subtype outgoing BFS through the provider when available. JS GraphAdjacencyIndex satisfies the contract while staying string/u32-keyed internally: entity ints resolve through the shared entity-id mapper (threaded in by the coordinator on init/fork/checkout), verb ints come from an in-process append-only interning map re-derived from storage on rebuild/cold-start. ColumnStoreProvider widens the same way: addEntity/ removeEntity take bigint, sortTopK/filteredSortTopK return bigint[]. relate() now rejects a caller-supplied id with a teaching error — verb ids are brainy-generated UUIDs by contract in 8.0 (previously a passed id was silently ignored). No Roaring64 provider-boundary decode site exists yet; the JS-internal column store stays Roaring32 and the Treemap decoder lands with the first consumer of provider-returned filter buffers. Public brain API unchanged. 1413 tests green (+10 new BigInt contract tests).
2026-06-10 10:45:45 -07:00
/**
* @param index - The graph-index provider (JS baseline or native).
* @param verb - The verb being removed (required for rollback re-add).
* @param sourceInt - The source entity's interned int (rollback re-add).
* @param targetInt - The target entity's interned int (rollback re-add).
* @param generationFn - Resolves the commit generation for this removal,
* evaluated when the operation executes.
feat(8.0): u64 BigInt graph provider contract — punch list a-d,g,h GraphIndexProvider now speaks BigInt at the boundary (D.2 mirror): - getNeighbors/getVerbIdsBySource/getVerbIdsByTarget take entity ints and return entity/verb ints as bigint[] - new REQUIRED verbIntsToIds(bigint[]) batch reverse resolver (L.7 identity-fingerprint design — verb ids are UUIDs by contract, so the provider-side interning is losslessly reversible) - addVerb(verb, sourceInt, targetInt) returns the interned verb int; removeVerb(verbId) joins the contract Coordinator (brainy.ts) owns ALL UUID <-> int conversion: getOrAssign on writes, getInt on reads (unmapped UUID -> empty result without calling the provider), getUuid / verbIntsToIds on returns, plus a bounded ~100k-entry insertion-order warm cache for verb-int -> verb-id pairs fed by addVerb returns and resolver results. GraphVerb gains derived sourceInt/targetInt (populated at add time, never persisted). findConnectedSubtype gains a native fast path that routes single-type single-subtype outgoing BFS through the provider when available. JS GraphAdjacencyIndex satisfies the contract while staying string/u32-keyed internally: entity ints resolve through the shared entity-id mapper (threaded in by the coordinator on init/fork/checkout), verb ints come from an in-process append-only interning map re-derived from storage on rebuild/cold-start. ColumnStoreProvider widens the same way: addEntity/ removeEntity take bigint, sortTopK/filteredSortTopK return bigint[]. relate() now rejects a caller-supplied id with a teaching error — verb ids are brainy-generated UUIDs by contract in 8.0 (previously a passed id was silently ignored). No Roaring64 provider-boundary decode site exists yet; the JS-internal column store stays Roaring32 and the Treemap decoder lands with the first consumer of provider-returned filter buffers. Public brain API unchanged. 1413 tests green (+10 new BigInt contract tests).
2026-06-10 10:45:45 -07:00
*/
constructor(
feat(8.0): u64 BigInt graph provider contract — punch list a-d,g,h GraphIndexProvider now speaks BigInt at the boundary (D.2 mirror): - getNeighbors/getVerbIdsBySource/getVerbIdsByTarget take entity ints and return entity/verb ints as bigint[] - new REQUIRED verbIntsToIds(bigint[]) batch reverse resolver (L.7 identity-fingerprint design — verb ids are UUIDs by contract, so the provider-side interning is losslessly reversible) - addVerb(verb, sourceInt, targetInt) returns the interned verb int; removeVerb(verbId) joins the contract Coordinator (brainy.ts) owns ALL UUID <-> int conversion: getOrAssign on writes, getInt on reads (unmapped UUID -> empty result without calling the provider), getUuid / verbIntsToIds on returns, plus a bounded ~100k-entry insertion-order warm cache for verb-int -> verb-id pairs fed by addVerb returns and resolver results. GraphVerb gains derived sourceInt/targetInt (populated at add time, never persisted). findConnectedSubtype gains a native fast path that routes single-type single-subtype outgoing BFS through the provider when available. JS GraphAdjacencyIndex satisfies the contract while staying string/u32-keyed internally: entity ints resolve through the shared entity-id mapper (threaded in by the coordinator on init/fork/checkout), verb ints come from an in-process append-only interning map re-derived from storage on rebuild/cold-start. ColumnStoreProvider widens the same way: addEntity/ removeEntity take bigint, sortTopK/filteredSortTopK return bigint[]. relate() now rejects a caller-supplied id with a teaching error — verb ids are brainy-generated UUIDs by contract in 8.0 (previously a passed id was silently ignored). No Roaring64 provider-boundary decode site exists yet; the JS-internal column store stays Roaring32 and the Treemap decoder lands with the first consumer of provider-returned filter buffers. Public brain API unchanged. 1413 tests green (+10 new BigInt contract tests).
2026-06-10 10:45:45 -07:00
private readonly index: GraphIndexProvider,
private readonly verb: GraphVerb, // Required for rollback
private readonly sourceInt: bigint,
private readonly targetInt: bigint,
private readonly generationFn: () => bigint
) {}
async execute(): Promise<RollbackAction> {
// Resolve the removal generation once; reuse it for the rollback re-add.
const generation = this.generationFn()
await this.index.removeVerb(this.verb.id, generation)
// Return rollback action
return async () => {
// Re-add verb with original data
await this.index.addVerb(this.verb, this.sourceInt, this.targetInt, generation)
}
}
}
/**
* Batch operation: Add multiple items to HNSW index
*
* Useful for bulk imports with transaction support.
* Rolls back all items if any fail.
*/
export class BatchAddToHNSWOperation implements Operation {
readonly name = 'BatchAddToHNSW'
private operations: AddToHNSWOperation[]
constructor(
index: JsHnswVectorIndex,
items: Array<{ id: string; vector: number[] }>
) {
this.operations = items.map(
item => new AddToHNSWOperation(index, item.id, item.vector)
)
}
async execute(): Promise<RollbackAction> {
const rollbackActions: RollbackAction[] = []
// Execute all operations
for (const op of this.operations) {
const rollback = await op.execute()
if (rollback) {
rollbackActions.push(rollback)
}
}
// Return combined rollback action
return async () => {
// Execute all rollbacks in reverse order
for (let i = rollbackActions.length - 1; i >= 0; i--) {
await rollbackActions[i]()
}
}
}
}
/**
* Batch operation: Add multiple entities to metadata index
*
* Useful for bulk imports with transaction support.
*/
export class BatchAddToMetadataIndexOperation implements Operation {
readonly name = 'BatchAddToMetadataIndex'
private operations: AddToMetadataIndexOperation[]
constructor(
index: MetadataIndexManager,
items: Array<{ id: string; entity: any }>
) {
this.operations = items.map(
item => new AddToMetadataIndexOperation(index, item.id, item.entity)
)
}
async execute(): Promise<RollbackAction> {
const rollbackActions: RollbackAction[] = []
// Execute all operations
for (const op of this.operations) {
const rollback = await op.execute()
if (rollback) {
rollbackActions.push(rollback)
}
}
// Return combined rollback action
return async () => {
// Execute all rollbacks in reverse order
for (let i = rollbackActions.length - 1; i >= 0; i--) {
await rollbackActions[i]()
}
}
}
}