feat: scaled transact budgets + labeled timeout diagnostics + envelope docs

- The transact apply budget scales with the batch — max(30s, opCount x 2s) —
  or is exactly the caller's new TransactOptions.timeoutMs. A flat 30s cap
  silently limited honest bulk work to ~15 operations on network-attached
  storage (~2s/op measured in a production import) while looking generous for
  small batches. Internal batch paths (removeMany chunks) get the same
  scaling via the shared transactTimeoutBudget helper.
- TransactionTimeoutError now reports the operation it stopped at as i/N with
  the operation's name, elapsed vs budgeted time, and states the batch rolled
  back atomically and is retryable; context carries the fields
  programmatically.
- The transact operational envelope is documented (optimistic-concurrency
  guide): budget math, chunking with ifAbsent idempotency, when to reach for
  addMany vs transact, and the precompute pattern (embedBatch + per-op
  vector) that keeps inference out of the commit path.
- Embedding claims made honest per an end-to-end probe of the built dist:
  batch and single embedding paths produce bit-identical vectors and a
  vector-supplied add is fully searchable, but batch throughput on the
  default WASM engine measures comparable to sequential (~160ms/text) — the
  5-10x speedup claim in the addMany JSDoc is replaced with the measured
  reality and the actual win (inference outside the budgeted write path).
This commit is contained in:
David Snelling 2026-07-17 16:49:38 -07:00
parent e0f6e7722f
commit 6ef9fcb7a2
7 changed files with 175 additions and 15 deletions

View file

@ -71,6 +71,7 @@ import type {
} from './plugin.js'
import { ConnectionsCodec } from './hnsw/connectionsCodec.js'
import { TransactionManager } from './transaction/TransactionManager.js'
import { transactTimeoutBudget } from './transaction/Transaction.js'
import { RevisionConflictError } from './transaction/RevisionConflictError.js'
import { EntityNotFoundError, RelationNotFoundError } from './errors/notFound.js'
import {
@ -1752,7 +1753,11 @@ export class Brainy<T = any> implements BrainyInterface<T> {
captureAndCheck({ nouns, verbs } as CommitBeforeImages)
}
await this.generationStore.runWithoutGeneration(() =>
this.transactionManager.executeTransaction(run)
this.transactionManager.executeTransaction(run, {
timeout: transactTimeoutBudget(
(touched.nouns?.length ?? 0) + (touched.verbs?.length ?? 0)
)
})
)
const timestamp = Date.now()
// Bootstrap writes are not generation-stamped; emit without one.
@ -1764,7 +1769,12 @@ export class Brainy<T = any> implements BrainyInterface<T> {
receipt = await this.generationStore.commitSingleOp({
touched,
precommit: captureAndCheck,
execute: () => this.transactionManager.executeTransaction(run)
execute: () =>
this.transactionManager.executeTransaction(run, {
timeout: transactTimeoutBudget(
(touched.nouns?.length ?? 0) + (touched.verbs?.length ?? 0)
)
})
})
} catch (err) {
// A failed rollback that left the store inconsistent (a remove/update
@ -6655,10 +6665,13 @@ export class Brainy<T = any> implements BrainyInterface<T> {
/**
* Add multiple entities in a single batch operation
*
* Uses batch embedding (embedBatch) to pre-compute all vectors in a single
* WASM forward pass instead of N individual embed() calls, providing 5-10x
* speedup on bulk inserts. Automatically adapts batch size and parallelism
* to the storage adapter (e.g., smaller batches for cloud storage).
* Uses batch embedding (embedBatch) to pre-compute all vectors before any
* storage write, keeping model inference out of the per-item write path.
* (On the default WASM engine, batch throughput is comparable to sequential
* embed() calls measured ~160 ms/text either way; a native embedding
* provider may batch faster.) Automatically adapts batch size and
* parallelism to the storage adapter (e.g., smaller batches for cloud
* storage).
*
* @param params - Batch add parameters
* @param params.items - Array of AddParams (same shape as brain.add())
@ -7797,11 +7810,17 @@ export class Brainy<T = any> implements BrainyInterface<T> {
ifAtGeneration: options?.ifAtGeneration,
precommit: casPrecommit,
execute: async () => {
await this.transactionManager.executeTransaction(async (tx) => {
for (const operation of plan.operations) {
tx.addOperation(operation)
}
})
await this.transactionManager.executeTransaction(
async (tx) => {
for (const operation of plan.operations) {
tx.addOperation(operation)
}
},
// Budget scales with the batch (or the caller's explicit
// timeoutMs): a flat 30s cap silently limited honest bulk work
// to ~15 ops on network disks (~2s/op measured in the field).
{ timeout: transactTimeoutBudget(plan.operations.length, options?.timeoutMs) }
)
}
}))
} catch (err) {

View file

@ -116,6 +116,16 @@ export interface TransactOptions {
* record is staged.
*/
ifAtGeneration?: number
/**
* Budget (ms) for the atomic apply phase. When omitted, the budget SCALES
* with the batch: `max(30 000, opCount × 2 000)` production imports on
* network-attached disks measure ~2 s per operation, so a flat 30 s budget
* silently capped honest bulk work at ~15 operations. A tripped budget
* rolls the whole batch back and throws a retryable
* `TransactionTimeoutError` naming the operation it stopped at, the batch
* size, and the elapsed/budget times.
*/
timeoutMs?: number
}
/**

View file

@ -37,6 +37,24 @@ const DEFAULT_OPTIONS: Required<TransactionOptions> = {
maxRollbackRetries: 3
}
/**
* The apply-phase budget for a batch of `opCount` operations.
*
* An explicit override wins untouched. Otherwise the budget SCALES with the
* batch: `max(30 000 ms, opCount × 2 000 ms)`. The per-op term is calibrated
* from field data bulk imports on network-attached disks measure ~2 s per
* operation (each op pays canonical writes + fsync + index maintenance) so
* a flat 30 s budget silently capped honest work at ~15 operations while
* looking generous for small batches. Scaling keeps small transacts
* fast-failing and gives bulk ones a budget proportional to the work they
* actually asked for; a trip still rolls back atomically and throws a
* retryable, fully-labeled TransactionTimeoutError.
*/
export function transactTimeoutBudget(opCount: number, override?: number): number {
if (override !== undefined) return override
return Math.max(30_000, opCount * 2_000)
}
/**
* Transaction class
*/
@ -114,7 +132,11 @@ export class Transaction implements TransactionContext {
// into the catch below and rolls back like any other failure — it must
// never bypass rollback.
if (Date.now() - this.startTime > this.options.timeout) {
throw new TransactionTimeoutError(this.options.timeout, i)
throw new TransactionTimeoutError(this.options.timeout, i, {
elapsedMs: Date.now() - this.startTime,
totalOperations: this.operations.length,
operationName: this.operations[i]?.name
})
}
const operation = this.operations[i]

View file

@ -77,11 +77,24 @@ export class InvalidTransactionStateError extends TransactionError {
export class TransactionTimeoutError extends TransactionError {
constructor(
timeoutMs: number,
operationIndex: number
operationIndex: number,
telemetry?: {
elapsedMs?: number
totalOperations?: number
operationName?: string
}
) {
const progress =
telemetry?.totalOperations !== undefined
? `${operationIndex}/${telemetry.totalOperations}`
: String(operationIndex)
const name = telemetry?.operationName ? ` ('${telemetry.operationName}')` : ''
const elapsed =
telemetry?.elapsedMs !== undefined ? `${telemetry.elapsedMs}ms elapsed, ` : ''
super(
`Transaction timed out after ${timeoutMs}ms at operation ${operationIndex}`,
{ timeoutMs, operationIndex }
`Transaction timed out at operation ${progress}${name}${elapsed}budget ${timeoutMs}ms. ` +
`The batch rolled back atomically; retry with a higher timeoutMs or a smaller batch.`,
{ timeoutMs, operationIndex, ...telemetry }
)
this.name = 'TransactionTimeoutError'
}