feat(index): watermark stamps on every TS projection — adopt/catchup/rescan verdicts at load, stamp-after-data

Every persisted projection artifact (metadata field indexes + column
segments, HNSW node records, graph adjacency LSM trees) now carries a
stamp asserting 'this state reflects every committed generation ≤ W,
atomically' — written LAST in each owner's flush (stamp-after-data: a
crash between data and stamp = unstamped = rescan, never trust). At load,
each owner computes the three-way verdict: stamped==committed → adopt
(zero work) · behind → catchup (gap reported) · above/unstamped → RESCAN,
loudly. Legacy artifacts re-derive once, then are stamped forever. Shared
law in projectionWatermark.ts (the aggregation verdict machinery,
generalized); vector artifacts carry model dimensions. Verdicts are
computed and exposed (watermark()/watermarkVerdict()/watermarkGap());
rebuild triggers unchanged — acting on 'catchup' is the fold train.

Pins: 22 unit (7 metadata · 8 hnsw · 7 graph, incl. spy-order
stamp-after-data) + the end-to-end reopen-adopts pin.
This commit is contained in:
David Snelling 2026-08-10 10:55:11 -07:00
parent 26c6025158
commit b35d87a7ab
8 changed files with 1259 additions and 1 deletions

View file

@ -13,6 +13,13 @@ import { MetadataIndexCache, MetadataIndexCacheConfig } from './metadataIndexCac
import { compareCodePoints } from './collation.js'
import { prodLog } from './logger.js'
import { getGlobalCache, UnifiedCache } from './unifiedCache.js'
import {
computeWatermarkVerdict,
makeProjectionStamp,
readStampedWatermark,
type WatermarkVerdict,
type WatermarkVerdictResult
} from './projectionWatermark.js'
import {
NounType,
VerbType,
@ -109,6 +116,15 @@ interface FieldStats {
normalizationStrategy?: 'none' | 'precision' | 'bucket'
}
/**
* Storage key for the metadata projection's watermark stamp a sidecar
* record beside the artifact (field registry + field indexes + chunked
* sparse indexes + column-store segments + id-mapper records). Written LAST
* in {@link MetadataIndexManager.flush} so stamp-after-data ordering holds
* for every byte the stamp certifies.
*/
export const METADATA_INDEX_STAMP_KEY = '__index_metadata_watermark__'
/**
* Implements {@link MetadataIndexProvider}: the metadata-index surface Brainy
* calls on whatever the `'metadataIndex'` provider resolves to (its own
@ -124,6 +140,14 @@ export class MetadataIndexManager implements MetadataIndexProvider {
private lastFlushTime = Date.now()
private autoFlushThreshold = 10 // Start with 10 for more frequent non-blocking flushes
// --- Watermark stamp state (see utils/projectionWatermark for the law) ---
/** Generation handed in via {@link stampWatermark}, awaiting the next flush. */
private pendingWatermark: number | null = null
/** Last watermark durably stamped by this instance or loaded at init. */
private stampedWatermark: number | null = null
/** The three-way verdict computed at init; null until init runs. */
private loadVerdict: WatermarkVerdictResult | null = null
// Cardinality and field statistics tracking
private fieldStats = new Map<string, FieldStats>()
private cardinalityUpdateInterval = 100 // Update cardinality every N operations
@ -250,6 +274,13 @@ export class MetadataIndexManager implements MetadataIndexProvider {
// Must run first to populate fieldIndexes directory before warming cache
await this.loadFieldRegistry()
// Compute the watermark verdict for the persisted artifact BEFORE any
// early return below — the verdict is recorded for every open, whether
// the workspace is empty, rebuilding, or warm. Computed and exposed
// only: today's rebuild triggers are unchanged (acting on 'catchup' —
// the incremental fold — lands with the coordinator's wiring).
await this.loadWatermarkVerdict()
// Initialize EntityIdMapper (loads UUID ↔ integer mappings from storage)
await this.idMapper.init()
@ -2599,6 +2630,10 @@ export class MetadataIndexManager implements MetadataIndexProvider {
// Check if we have anything else to flush
if (this.dirtyFields.size === 0) {
// Nothing dirty — but a pending watermark still stamps (the registry
// + id-mapper writes above are the only bytes this pass touched, and
// they are durable at this point). Stamp-after-data holds.
await this.writePendingStamp()
return // No dirty field indexes to flush
}
@ -2638,8 +2673,131 @@ export class MetadataIndexManager implements MetadataIndexProvider {
if (this.columnStore) {
await this.columnStore.flush()
}
// STAMP-AFTER-DATA: the watermark stamp is the LAST write of the flush —
// every byte it certifies (field indexes, registry, id-mapper records,
// column-store segments) is durable before the stamp lands. A crash
// anywhere above leaves the artifact behind-stamped or unstamped, which
// verdicts as catchup/rescan on the next open — never a wrong adopt.
await this.writePendingStamp()
}
/**
* @description Record the committed generation this projection reflects.
* The stamp is NOT written here it is written as the final storage write
* of the next {@link flush} (stamp-after-data ordering is a module
* guarantee, not a caller obligation). The coordinator calls this with the
* store's committed generation right before flushing.
* @param generation - The committed generation every flushed byte reflects.
*/
stampWatermark(generation: number): void {
this.pendingWatermark = generation
}
/**
* @description The projection's current watermark: the stamp loaded at
* init (or the last stamp durably written by this instance). Null =
* unstamped (legacy artifact, first boot, or stamping never wired).
*/
watermark(): number | null {
return this.stampedWatermark
}
/**
* @description The three-way adoption verdict computed at init
* `'adopt'` (stamped == committed, zero work), `'catchup'` (stamped <
* committed; the gap from {@link watermarkGap} awaits an incremental
* fold), `'rescan'` (unstamped or stamped above committed never
* trusted). Null until init() has run. Computed and exposed only; no
* load behavior changes ride on it yet.
*/
watermarkVerdict(): WatermarkVerdict | null {
return this.loadVerdict?.verdict ?? null
}
/**
* @description The catch-up window `(from, to]` when the init verdict was
* `'catchup'`; null otherwise.
*/
watermarkGap(): { from: number; to: number } | null {
return this.loadVerdict?.gap ?? null
}
/**
* @description Write the pending watermark stamp as a sidecar record
* always called AFTER the data it certifies is durable. A stamp-write
* failure is fail-safe (the artifact stays unstamped/behind rescan or
* catchup on next open, never a wrong adopt) but is said out loud and the
* pending stamp is retained for the next flush.
*/
private async writePendingStamp(): Promise<void> {
if (this.pendingWatermark === null) return
const watermark = this.pendingWatermark
try {
await this.storage.saveMetadata(METADATA_INDEX_STAMP_KEY, {
noun: 'IndexWatermark',
...makeProjectionStamp(watermark)
})
this.stampedWatermark = watermark
this.pendingWatermark = null
} catch (error) {
prodLog.error(
`[MetadataIndex] failed to write watermark stamp (generation ${watermark}) — ` +
`artifact stays behind-stamped (safe: verdicts catchup/rescan, never wrong-adopt); ` +
`retrying on next flush:`,
error
)
}
}
/**
* @description Read the artifact's stamp and compute the three-way verdict
* against the store's committed generation. Unstamped state on a stamped
* store verdicts `'rescan'` LOUDLY never a silent adopt.
*
* MIGRATION COST: existing pre-stamp brains verdict `'rescan'` exactly
* once (this open re-derives from source as it already does today); the
* next flush stamps them, and every later open adopts.
*/
private async loadWatermarkVerdict(): Promise<void> {
const committed = this.storage.committedGeneration?.() ?? null
let stamped: number | null = null
try {
const record = await this.storage.getMetadata(METADATA_INDEX_STAMP_KEY)
stamped = readStampedWatermark(record)
} catch {
// An unreadable stamp is unstamped — the fail-safe direction.
stamped = null
}
const result = computeWatermarkVerdict(stamped, committed)
this.loadVerdict = result
this.stampedWatermark = stamped
if (result.verdict === 'rescan') {
const artifactPresent = this.fieldIndexes.size > 0 || stamped !== null
if (artifactPresent) {
prodLog.warn(
`[MetadataIndex] watermark verdict: RESCAN — persisted index is ` +
(stamped === null
? 'unstamped (legacy pre-stamp artifact, or a crash between data and stamp)'
: `stamped at generation ${stamped}, ABOVE the store's committed generation ${committed}`) +
` — never adopting unverifiable state`
)
} else {
prodLog.debug(
'[MetadataIndex] watermark verdict: rescan (no persisted artifact — first boot)'
)
}
} else if (result.verdict === 'catchup') {
prodLog.info(
`[MetadataIndex] watermark verdict: catchup — index stamped at generation ` +
`${stamped}, store committed at ${committed}; the (${stamped}, ${committed}] ` +
`window awaits an incremental fold (verdict exposed; the fold lands with the ` +
`coordinator's wiring)`
)
}
}
/**
* Yield control back to the Node.js event loop
* Prevents blocking during long-running operations