brainy/tests/unit/migration-lock.test.ts
David Snelling 67bbf69a5c feat(8.0): #18 coordinated migration LOCK — block-and-queue the 7.x→8.0 auto-upgrade
Replaces rc.8's no-freeze deference with an automatic, observable, coordinated
migration LOCK (David's reversal: "unknown/halfway states are more dangerous
than blocking"). While a native provider runs its one-time 7.x→8.0
rebuild-from-canonical (`isMigrating()===true`), brainy blocks/queues data-plane
reads AND writes so no operation ever touches a half-built index — closing the
three seam-map gaps (lost mid-rebuild writes, degraded reads, read-time rebuild).

Mechanism (one choke point):
- awaitMigrationLock() at ensureInitialized() covers all ~40 data-plane methods;
  a non-migrating brain pays one boolean check. Polls isMigrating() at 250ms;
  after migrationWaitTimeoutMs (default 30s) throws a retryable, exported
  MigrationInProgressError. The timeout bounds the CALLER'S WAIT, not the
  migration — the rebuild is unbounded and never interrupted.
- init() awaits the lock before VFS bootstrap + before serving ("not ready until
  upgraded"); a rebuild past the budget surfaces MigrationInProgressError at init
  (raise the budget, or run the offline migrator).

Observability (readiness-probe correct — never gated):
- getIndexStatus() gains `migrating` + `migration` (MigrationProgress); a probe
  maps migrating→HTTP 503+Retry-After, not 500. health()/checkHealth() lock-exempt
  (health() reports a `warn` migration check). stampBrainFormat()/close() are
  ungated so cor can clear the lock — no deadlock.
- Optional provider migrationStatus() is relayed verbatim for a live %.

verifyGraphAdjacencyLive() honors the lock (no self-rebuild mid-migration); the
stamp is still withheld while any provider migrates (cor stamps after verify).

Adversarially verified: fixed a critical init/VFS-bootstrap deadlock, a mixed-
provider busy-spin (dropped the event-driven signal → pure poll), a not-yet-
initialized getIndexStatus crash, and once-per-window log/clock resets. 10 lock
tests (incl. the init-during-migration regression). Gates: typecheck 0, build 0,
test:unit 1753/1753.
2026-07-01 10:26:27 -07:00

170 lines
6.5 KiB
TypeScript

/**
* Migration LOCK (#18) — coordinated, automatic 7.x → 8.0 auto-upgrade.
*
* Exercises the real block-and-queue behavior of `awaitMigrationLock` at the
* `ensureInitialized` choke point: while ANY index provider reports
* `isMigrating() === true`, data-plane reads and writes WAIT (no operation
* touches a half-built index); observability (`getIndexStatus`, `health`) and
* the lock-clearing `stampBrainFormat` stay exempt; and a lock that outlives the
* configured window surfaces a retryable `MigrationInProgressError`.
*
* A native (cortex) provider owns the real migration; here we simulate the lock
* by feature-detect-injecting `isMigrating()` onto a live provider, exactly as
* the production feature-detection reads it.
*/
import { describe, it, expect, beforeEach } from 'vitest'
import { Brainy, NounType, MigrationInProgressError } from '../../src/index.js'
import { GraphAdjacencyIndex } from '../../src/graph/graphAdjacencyIndex.js'
/** Force the graph provider to hold (or release) the migration lock. */
function setMigrating(brain: any, migrating: boolean): void {
brain.graphIndex.isMigrating = () => migrating
}
describe('Migration LOCK (#18) — coordinated 7.x→8.0 auto-upgrade', () => {
let brain: any
beforeEach(async () => {
brain = new Brainy({
requireSubtype: false,
storage: { type: 'memory' },
migrationWaitTimeoutMs: 5000 // generous; timing tests clear well within it
})
await brain.init()
})
it('does not gate operations when no provider is migrating (fast path)', async () => {
const id = await brain.add({ data: 'hello', type: NounType.Concept })
expect(id).toBeTruthy()
const status = await brain.getIndexStatus()
expect(status.migrating).toBe(false)
expect(status.migration).toBeUndefined()
})
it('getIndexStatus() reports migrating WITHOUT blocking (lock-exempt observability)', async () => {
setMigrating(brain, true)
const status = await brain.getIndexStatus() // must resolve, never hang
expect(status.migrating).toBe(true)
expect(status.migration).toBeDefined()
expect(typeof status.migration.elapsedMs).toBe('number')
})
it('health() surfaces the migration as a warn check without blocking', async () => {
setMigrating(brain, true)
const h = await brain.health() // lock-exempt
expect(h.overall).toBe('warn')
expect(h.checks.some((c: any) => c.name === 'migration')).toBe(true)
})
it('checkHealth() answers during a migration (lock-exempt diagnostics)', async () => {
setMigrating(brain, true)
const r = await brain.checkHealth()
expect(r).toHaveProperty('healthy')
})
it('blocks a write while migrating (poll path), then completes when the lock clears', async () => {
setMigrating(brain, true)
let resolved = false
const p = brain
.add({ data: 'queued write', type: NounType.Concept })
.then((id: string) => {
resolved = true
return id
})
// Still blocked shortly after issue.
await new Promise((r) => setTimeout(r, 40))
expect(resolved).toBe(false)
// Clearing the lock releases the queued write against the good indexes.
setMigrating(brain, false)
const id = await p
expect(resolved).toBe(true)
expect(id).toBeTruthy()
})
it('blocks a read while migrating, then releases when the flag clears (poll path)', async () => {
let migrating = true
brain.graphIndex.isMigrating = () => migrating
const p = brain.find({ type: NounType.Concept }) // a read → gated
let resolved = false
p.then(() => {
resolved = true
})
await new Promise((r) => setTimeout(r, 40))
expect(resolved).toBe(false)
// Clearing the flag lets the next poll release the read against good indexes.
migrating = false
await expect(p).resolves.toEqual([])
})
it('throws a retryable MigrationInProgressError when the lock outlives the timeout', async () => {
const shortBrain: any = new Brainy({
requireSubtype: false,
storage: { type: 'memory' },
migrationWaitTimeoutMs: 120
})
await shortBrain.init()
setMigrating(shortBrain, true) // never clears
await expect(shortBrain.find({ type: NounType.Concept })).rejects.toBeInstanceOf(
MigrationInProgressError
)
try {
await shortBrain.add({ data: 'x', type: NounType.Concept })
throw new Error('expected MigrationInProgressError')
} catch (e: any) {
expect(e).toBeInstanceOf(MigrationInProgressError)
expect(e.retryable).toBe(true)
expect(typeof e.elapsedMs).toBe('number')
}
})
it('stampBrainFormat() is NOT gated — cor clears the lock through it (no deadlock)', async () => {
setMigrating(brain, true)
// Must resolve, not hang, even while a migration is "in progress".
await expect(brain.stampBrainFormat()).resolves.toBeUndefined()
})
it('close() is NOT gated — an instance can shut down mid-migration', async () => {
setMigrating(brain, true)
await expect(brain.close()).resolves.toBeUndefined()
})
it('C1: init() waits out a migration BEFORE VFS bootstrap (no deadlock, no failure)', async () => {
// The critical regression: init()'s own VFS bootstrap (get/add/find on the
// root) routes through the gated ensureInitialized. If a provider migrates
// during init, init must WAIT for the lock to clear BEFORE bootstrapping VFS —
// otherwise it deadlocks (< timeout) or throws MigrationInProgressError past
// the timeout. We make the graph provider report migrating for a short window
// spanning init, then clear it, and assert init completes and the brain works.
const orig = (GraphAdjacencyIndex.prototype as any).isMigrating
let migrating = true
;(GraphAdjacencyIndex.prototype as any).isMigrating = () => migrating
const clearMigration = setTimeout(() => {
migrating = false
}, 60)
try {
const b: any = new Brainy({
requireSubtype: false,
storage: { type: 'memory' },
migrationWaitTimeoutMs: 5000
})
await b.init() // must resolve once the migration clears — not hang, not throw
expect(b.isInitialized).toBe(true)
// VFS bootstrapped post-migration → normal write/read work end-to-end.
const id = await b.add({ data: 'after upgrade', type: NounType.Concept })
expect(id).toBeTruthy()
expect(await b.get(id)).not.toBeNull()
await b.close()
} finally {
clearTimeout(clearMigration)
if (orig) (GraphAdjacencyIndex.prototype as any).isMigrating = orig
else delete (GraphAdjacencyIndex.prototype as any).isMigrating
}
})
})