brainy/src/transaction/Transaction.ts
David Snelling 711d2f046a fix: honest response when a transaction rollback cannot complete
When a transaction failed and its rollback ALSO failed to undo a canonical
write (retries exhausted), the old path logged, continued, threw
TransactionRollbackError, and set state='rolled_back' — while the record it
could not undo stayed durable on disk. The caller got an error implying the
write was undone; a read-back showed the record. A failed rollback had no
truthful response (the post-commit response lie).

Give a failed rollback a two-branch honest contract, decided by observation:
both commit paths already hold byte-identical before-images, so after a failed
rollback the store compares current canonical state to them and classifies each
touched record as reconciled, an additive orphan (present when it should be
gone), or a restorative loss (gone/wrong when it should have been restored).

- Adopt-forward: a single-op write whose only damage is a durably-present
  orphan — the record the caller asked for — is committed forward (its
  generation buffered) and returns success with a loud warning that the derived
  index may be incomplete for that id until the next rebuild/repairIndex(). No
  error, no double-write; the record is durable and get-able immediately.
- Fail loud + quarantine: a multi-op batch, or ANY restorative loss, throws the
  new StoreInconsistentError naming every unreconciled record and its
  disposition, and puts the brain into write-quarantine (reads keep working,
  writes refused via assertWritable) until repairIndex() reconciles the derived
  indexes against canonical and lifts it. The counter is not advanced, and
  Transaction.rollback now reports state 'inconsistent' instead of the
  'rolled_back' lie when any undo failed.

New: StoreInconsistentError + UnreconciledRecord exported from the root;
repairIndex() forces a rebuild and clears the quarantine. Regression
tests/integration/rollback-trapdoor.test.ts injects index-add-throws +
canonical-delete-undo-fails and pins adopt-forward (durable, get-able, not
quarantined), fail-loud (StoreInconsistentError + quarantine + reads work +
repairIndex lifts it), and the error's record naming.
2026-07-12 12:19:09 -07:00

256 lines
7.8 KiB
TypeScript

/**
* Transaction - Atomic Unit of Work
*
* Executes operations atomically: all succeed or all rollback.
* Prevents partial failures that leave system in inconsistent state.
*
* Usage:
* ```typescript
* const tx = new Transaction()
* tx.addOperation(operation1)
* tx.addOperation(operation2)
* await tx.execute() // Both succeed or both rollback
* ```
*/
import {
Operation,
RollbackAction,
TransactionState,
TransactionContext,
TransactionOptions
} from './types.js'
import {
InvalidTransactionStateError,
TransactionExecutionError,
TransactionRollbackError,
TransactionTimeoutError
} from './errors.js'
import { prodLog } from '../utils/logger.js'
/**
* Default transaction options
*/
const DEFAULT_OPTIONS: Required<TransactionOptions> = {
timeout: 30000, // 30 seconds
logging: false,
maxRollbackRetries: 3
}
/**
* Transaction class
*/
export class Transaction implements TransactionContext {
private operations: Operation[] = []
private rollbackActions: RollbackAction[] = []
private state: TransactionState = 'pending'
private readonly options: Required<TransactionOptions>
private startTime?: number
private endTime?: number
constructor(options: TransactionOptions = {}) {
this.options = { ...DEFAULT_OPTIONS, ...options }
}
/**
* Add an operation to the transaction
*/
addOperation(operation: Operation): void {
if (this.state !== 'pending') {
throw new InvalidTransactionStateError(
this.state,
'add operation'
)
}
this.operations.push(operation)
}
/**
* Get current transaction state
*/
getState(): TransactionState {
return this.state
}
/**
* Get number of operations in transaction
*/
getOperationCount(): number {
return this.operations.length
}
/**
* Execute all operations atomically
*/
async execute(): Promise<void> {
if (this.state !== 'pending') {
throw new InvalidTransactionStateError(
this.state,
'execute'
)
}
this.state = 'executing'
this.startTime = Date.now()
if (this.options.logging) {
prodLog.info(`[Transaction] Executing ${this.operations.length} operations`)
}
try {
// Execute each operation in order. This loop is the sole rollback-guarded
// region: ANY error that escapes it — an operation failure OR a
// mid-flight timeout — is caught below and rolls back every operation
// applied so far, in reverse order. That single guarantee is the
// transaction's atomicity contract, and the generation-store commit path
// depends on it: its abort cleanup assumes a throw from here already
// restored the applied operations byte-identically (it only discards the
// uncommitted staging directory). A rollback per exit path — the previous
// design — let the timeout throw slip past rollback and strand the
// already-applied writes as torn, generation-less state in canonical
// storage.
for (let i = 0; i < this.operations.length; i++) {
// Budget check BEFORE starting the next operation. A trip here throws
// 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)
}
const operation = this.operations[i]
if (this.options.logging) {
prodLog.info(`[Transaction] Executing operation ${i}: ${operation.name || 'unnamed'}`)
}
let rollbackAction: RollbackAction | undefined
try {
rollbackAction = await operation.execute()
} catch (error) {
// Normalize an operation failure to a TransactionExecutionError; the
// outer catch performs the (single) rollback and surfaces it.
throw new TransactionExecutionError(
`Operation ${i} failed: ${(error as Error).message}`,
i,
operation.name,
error as Error
)
}
// Record rollback action (if the operation provided one)
if (rollbackAction) {
this.rollbackActions.push(rollbackAction)
}
}
} catch (error) {
// Single rollback point: undo everything applied so far, in reverse
// order, then surface the original error. A rollback failure supersedes
// it (rollback() throws TransactionRollbackError wrapping this error).
await this.rollback(error as Error)
throw error
}
// All operations succeeded — commit.
this.commit()
}
/**
* Commit the transaction
*/
private commit(): void {
this.state = 'committed'
this.endTime = Date.now()
if (this.options.logging) {
const duration = this.endTime - (this.startTime || this.endTime)
prodLog.info(`[Transaction] Committed successfully in ${duration}ms`)
}
// Clear rollback actions - no longer needed
this.rollbackActions = []
}
/**
* Rollback all executed operations in reverse order
*/
private async rollback(originalError: Error): Promise<void> {
this.state = 'rolling_back'
if (this.options.logging) {
prodLog.info(`[Transaction] Rolling back ${this.rollbackActions.length} operations`)
}
const rollbackErrors: Error[] = []
// Execute rollback actions in REVERSE order
for (let i = this.rollbackActions.length - 1; i >= 0; i--) {
const action = this.rollbackActions[i]
// Retry rollback with exponential backoff
let attempts = 0
let success = false
while (attempts < this.options.maxRollbackRetries && !success) {
try {
await action()
success = true
if (this.options.logging) {
prodLog.info(`[Transaction] Rolled back operation ${i}`)
}
} catch (error) {
attempts++
if (attempts >= this.options.maxRollbackRetries) {
// Max retries exceeded - log error and continue
const rollbackError = error as Error
rollbackErrors.push(rollbackError)
prodLog.error(
`[Transaction] Rollback failed for operation ${i} after ${attempts} attempts: ${rollbackError.message}`
)
} else {
// Retry with exponential backoff
const delayMs = Math.pow(2, attempts) * 100
await new Promise(resolve => setTimeout(resolve, delayMs))
}
}
}
}
// Honest terminal state: only claim 'rolled_back' when EVERY undo applied.
// If any undo failed, the store is not cleanly rolled back — mark
// 'inconsistent' so the commit orchestration reconciles rather than trusts
// a false 'rolled_back'. (Fixes the state half of the post-commit response
// lie: the record whose undo failed is still durable.)
this.state = rollbackErrors.length > 0 ? 'inconsistent' : 'rolled_back'
this.endTime = Date.now()
if (this.options.logging) {
const duration = this.endTime - (this.startTime || this.endTime)
prodLog.info(`[Transaction] ${this.state === 'inconsistent' ? 'Rollback INCOMPLETE' : 'Rolled back'} in ${duration}ms`)
}
// If rollback encountered errors, wrap them with original error. The
// orchestration keys on `instanceof TransactionRollbackError` to know the
// undo did not fully apply and reconciliation is required.
if (rollbackErrors.length > 0) {
throw new TransactionRollbackError(
`Transaction rollback encountered ${rollbackErrors.length} errors during cleanup`,
originalError,
rollbackErrors
)
}
}
/**
* Get transaction execution time in milliseconds
*/
getExecutionTimeMs(): number | undefined {
if (this.startTime && this.endTime) {
return this.endTime - this.startTime
}
return undefined
}
}