feat(embedding): deferred-embed markers become log records — the sidecar recovery path is deleted
The private recovery discipline, applied to its own machinery: pending- embed markers stop being sidecar files and become first-class log records riding the write's OWN commit fact — embed.pending lands in the same atomic append as its after-image (a marker can never be orphaned from its write, or vice versa; in durable-at-ack mode it shares the write's covering fsync — zero extra syncs), and the worker's landing commit rides embed.landed with the inline vector. Crash recovery is now a FOLD of the log (pending without a matching landed = recovered), skipped wholesale on brains with no v2 history; the one-time legacy bridge folds existing sidecar files in, migrates them as one fact, and deletes them — idempotent under a crash mid-bridge. No code path writes the sidecar again. Plus the ENTITY-TRUTH digest law, found by this train's own pins: canonical vector wrappers denormalize HNSW residue (connections + the randomly-assigned node level) that the log deliberately does not carry — the verification oracle digested it and would have reported false state-differs on ~any nonzero-level node (a ~15% flake in the cutover pin was the symptom). Both sides of every oracle comparison now normalize to entity truth (nounEntityTruth); index residue has its own rebuild path and is not entity state. Pins: embed-markers-in-log 5/5 (same-generation marker, landed+fold-to- zero, crash recovery via the log with the sidecar prefix EMPTY on disk, legacy bridge, VFS hung-embedder ack) · deferred-embedding 5/5 unchanged (the contract outlived its mechanism) · kill-matrix 11/11 · cutover 5/5 ×10 runs (flake dead) · unit 2031/2031.
This commit is contained in:
parent
c95bea8887
commit
b47787bbf7
7 changed files with 637 additions and 76 deletions
|
|
@ -51,7 +51,8 @@ import {
|
|||
storageSupportsFactLog,
|
||||
type CommitFact,
|
||||
type FactOp,
|
||||
type FactIntMinter
|
||||
type FactIntMinter,
|
||||
type FactMarkerRecord
|
||||
} from './factLog.js'
|
||||
import { GenerationSegmentStore, type FoldGeneration } from './generationSegments.js'
|
||||
import { crc32c } from '../utils/crc32c.js'
|
||||
|
|
@ -903,6 +904,8 @@ export class GenerationStore {
|
|||
nouns: string[]
|
||||
verbs: string[]
|
||||
meta?: Record<string, unknown>
|
||||
/** V2 marker records riding this fact (same generation, same append). */
|
||||
records?: FactMarkerRecord[]
|
||||
}): Promise<CommitFact> {
|
||||
const ops: FactOp[] = []
|
||||
const afterRecords: GenerationRecord[] = []
|
||||
|
|
@ -926,7 +929,8 @@ export class GenerationStore {
|
|||
timestamp: args.timestamp,
|
||||
ops,
|
||||
...(args.meta ? { meta: args.meta } : {}),
|
||||
...(blobHashes.length > 0 ? { blobHashes } : {})
|
||||
...(blobHashes.length > 0 ? { blobHashes } : {}),
|
||||
...(args.records && args.records.length > 0 ? { records: args.records } : {})
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -939,6 +943,12 @@ export class GenerationStore {
|
|||
* per-record analogue of `ifAtGeneration`. A throw aborts the whole batch:
|
||||
* the generation reservation is returned and no staging I/O has happened. */
|
||||
precommit?: (before: CommitBeforeImages) => void
|
||||
/** Optional v2 marker records riding this batch's ONE commit fact (e.g.
|
||||
* the deferred-embedding lifecycle markers) — same generation, same
|
||||
* atomic append, same durability barrier as the batch itself, so a
|
||||
* marker can never be orphaned from its write nor the write from its
|
||||
* marker. Additive: omitted on every markerless path. */
|
||||
records?: FactMarkerRecord[]
|
||||
execute: () => Promise<void>
|
||||
}): Promise<{ generation: number; timestamp: number }> {
|
||||
return this.withMutex(async () => {
|
||||
|
|
@ -1075,7 +1085,8 @@ export class GenerationStore {
|
|||
timestamp,
|
||||
nouns,
|
||||
verbs,
|
||||
...(args.meta ? { meta: args.meta } : {})
|
||||
...(args.meta ? { meta: args.meta } : {}),
|
||||
...(args.records && args.records.length > 0 ? { records: args.records } : {})
|
||||
})
|
||||
await this.factLog.append(fact)
|
||||
await this.factLog.sync()
|
||||
|
|
@ -1288,6 +1299,18 @@ export class GenerationStore {
|
|||
touched: { nouns?: string[]; verbs?: string[] }
|
||||
execute: () => Promise<void>
|
||||
precommit?: (before: CommitBeforeImages) => void
|
||||
/**
|
||||
* Optional v2 marker records riding this write's commit fact (e.g. the
|
||||
* deferred-embedding lifecycle markers) — same generation, same atomic
|
||||
* append, and in 'at-ack' log durability the SAME covering fsync as the
|
||||
* write itself (zero extra sync). A marker can never be orphaned from
|
||||
* its write nor the write from its marker. Additive: omitted on every
|
||||
* markerless path. When the storage hosts no fact log the markers have
|
||||
* no durable home — matching that storage's overall durability posture
|
||||
* (it cannot host the log's crash guarantees either); callers own
|
||||
* surfacing that honestly.
|
||||
*/
|
||||
records?: FactMarkerRecord[]
|
||||
}): Promise<{ generation: number; timestamp: number; degraded?: string[] }> {
|
||||
return this.withMutex(async () => {
|
||||
// Refuse to accept a write whose history we cannot make durable: if the
|
||||
|
|
@ -1357,7 +1380,13 @@ export class GenerationStore {
|
|||
// buffered history).
|
||||
if (this.factLog) {
|
||||
await this.factLog.append(
|
||||
await this.buildCommitFact({ generation: gen, timestamp, nouns, verbs })
|
||||
await this.buildCommitFact({
|
||||
generation: gen,
|
||||
timestamp,
|
||||
nouns,
|
||||
verbs,
|
||||
...(args.records && args.records.length > 0 ? { records: args.records } : {})
|
||||
})
|
||||
)
|
||||
}
|
||||
prodLog.warn(
|
||||
|
|
@ -1411,7 +1440,13 @@ export class GenerationStore {
|
|||
if (this.factLog) {
|
||||
try {
|
||||
await this.factLog.append(
|
||||
await this.buildCommitFact({ generation: gen, timestamp, nouns, verbs })
|
||||
await this.buildCommitFact({
|
||||
generation: gen,
|
||||
timestamp,
|
||||
nouns,
|
||||
verbs,
|
||||
...(args.records && args.records.length > 0 ? { records: args.records } : {})
|
||||
})
|
||||
)
|
||||
if (this.logDurability === 'at-ack') {
|
||||
await this.factLog.ensureSynced()
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue