feat(log): log authority is the fleet default — adopt-at-open, oracle-gated; plus the power-cut throw-site cures and the loud torn-record contract
THE DEFAULT FLIP (ruled on proven evidence — at-ack survived 301/301 acked-writes-through-power-cut in block-layer fault injection; deferred tree authority demonstrably loses flush-covered acks): a brain with NO stored authority artifact now ADOPTS LOG AUTHORITY AT OPEN. The oracle gates the flip exactly as the guarded adoption path always did — curable divergences baseline-backfilled, the flip lands ONLY on a green verdict — and a brain that cannot verify STAYS tree-authoritative loudly, with the refusal recorded on the switch artifact so subsequent opens are cheap. config logAuthority: 'defer' is the explicit documented opt-out (no automatic adoption; declared flush-window loss; adoptLogAuthority() flips later). A stored artifact always wins. RELEASES.md carries the posture. Two standing .fails debt pins FLIP TO HOLDING under the default: the at-ack crash-survival gap and the ack-at-log durability target — both now permanent asserted truths, not aspirations. POWER-CUT THROW SITES (fault-injection findings, brainy-alone config): - A manifest-listed-but-unloadable column segment QUARANTINES at discovery (loud once, counted always, quarantinedSegments() exposed for the heal) and the field serves its remaining segments DEGRADED — never a raw throw killing every query on the field. Real storage faults still propagate untouched. - Torn generation artifacts (NaN/garbage in manifest or counter) DISCARD with narration at the store's open and recovery re-derives — plus a defensive finite-integer guard at the init consumer. Never a RangeError killing an open. THE LOUD TORN-RECORD CONTRACT: an existing-but-unparseable stored record now surfaces as a typed, counted TornRecordError on every entity-read surface (including fifteen previously-blind per-item batch catches); ENOENT stays clean-absent; artifact readers with designed absent-recovery keep null-tolerance behind the loud floor. Disk corruption can no longer read as silent data invisibility. Suite migration: the default's pins inverted deliberately, generation baselines made relative, quarantine-contract pins rewritten to the ruled behavior. Gates: tsc 0 · unit 2065/2065 (159 files) · integration 826 (93 files) · conformance 31/31 · kill-matrix 15/15 · torn-open guards 2/2.
This commit is contained in:
parent
67c606be69
commit
214c98b4d5
23 changed files with 833 additions and 154 deletions
|
|
@ -32,6 +32,7 @@ import { BlobStorage, type BlobStoreAdapter } from './blobStorage.js'
|
|||
import { unwrapBinaryData } from './binaryDataCodec.js'
|
||||
import { prodLog } from '../utils/logger.js'
|
||||
import { isAbsentError } from '../utils/errorClassification.js'
|
||||
import { isTornRecordError } from './tornRecordError.js'
|
||||
import { BrainyError, ProtectedArtifactError, DerivedArtifactMissingError } from '../errors/brainyError.js'
|
||||
import { MetadataWriteBuffer } from '../utils/metadataWriteBuffer.js'
|
||||
import {
|
||||
|
|
@ -674,6 +675,10 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
// — hash verification must run on the original content bytes.
|
||||
return unwrapBinaryData(data)
|
||||
} catch (error) {
|
||||
// A TORN blob object (exists but undecodable) must not read as
|
||||
// "blob absent" — that would misdiagnose disk corruption as a
|
||||
// missing blob. Propagate the typed error to the blob layer.
|
||||
if (isTornRecordError(error)) throw error
|
||||
return undefined
|
||||
}
|
||||
},
|
||||
|
|
@ -768,6 +773,20 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
if (m) hashes.add(m[1])
|
||||
}
|
||||
|
||||
// Recovery-path read: a TORN object here maps to "not usable" (null) BY
|
||||
// DESIGN — the adapter has already logged + counted the encounter, and
|
||||
// treating a torn `_cas/` copy as absent lets the re-copy from `_cow/`
|
||||
// OVERWRITE the corrupt file with the good original (the heal), while a
|
||||
// torn `_cow/` original is reported via `incomplete`. Real faults propagate.
|
||||
const readOrNullIfTorn = async (p: string): Promise<any | null> => {
|
||||
try {
|
||||
return await this.readObjectFromPath(p)
|
||||
} catch (error) {
|
||||
if (isTornRecordError(error)) return null
|
||||
throw error
|
||||
}
|
||||
}
|
||||
|
||||
let adopted = 0
|
||||
let alreadyPresent = 0
|
||||
let incomplete = 0
|
||||
|
|
@ -775,15 +794,15 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
// A blob counts as present only when BOTH its bytes and its metadata
|
||||
// already live in `_cas/`. A half-adopted blob (bytes without meta — the
|
||||
// exact "Blob metadata not found" state) is re-adopted.
|
||||
const casBlob = await this.readObjectFromPath(`_cas/blob:${hash}`)
|
||||
const casMeta = await this.readObjectFromPath(`_cas/blob-meta:${hash}`)
|
||||
const casBlob = await readOrNullIfTorn(`_cas/blob:${hash}`)
|
||||
const casMeta = await readOrNullIfTorn(`_cas/blob-meta:${hash}`)
|
||||
if (casBlob !== null && casMeta !== null) {
|
||||
alreadyPresent++
|
||||
continue
|
||||
}
|
||||
|
||||
const cowBlob = await this.readObjectFromPath(`_cow/blob:${hash}`)
|
||||
const cowMeta = await this.readObjectFromPath(`_cow/blob-meta:${hash}`)
|
||||
const cowBlob = await readOrNullIfTorn(`_cow/blob:${hash}`)
|
||||
const cowMeta = await readOrNullIfTorn(`_cow/blob-meta:${hash}`)
|
||||
if (cowBlob === null || cowMeta === null) {
|
||||
// Can't register a blob the store can't fully describe — report it so an
|
||||
// operator investigates rather than silently half-adopting.
|
||||
|
|
@ -1134,12 +1153,28 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
* cache (record-layer files are written through
|
||||
* {@link BaseStorage.writeRawObject} only).
|
||||
*
|
||||
* TORN-record contract (deliberate, loud-by-design): this surface serves
|
||||
* SYSTEM ARTIFACTS — manifests with recovery paths, markers whose verdict
|
||||
* machinery treats "unreadable" as rescan, generation/transaction records
|
||||
* whose recovery is built for absent artifacts. For these readers a torn
|
||||
* file maps to their existing absent-artifact degrade, so a typed
|
||||
* torn-record error from the adapter is caught here and returned as `null`
|
||||
* — AFTER the adapter has already logged a production ERROR and counted
|
||||
* the per-process torn-record gauge (never silent). Entity reads do NOT go
|
||||
* through this surface; they use the canonical read paths, which propagate
|
||||
* the typed error. Real storage faults (EIO/EACCES/…) still propagate.
|
||||
*
|
||||
* @param path - Storage-root-relative object path (e.g. `_system/manifest.json`).
|
||||
* @returns The parsed object, or `null` if absent.
|
||||
* @returns The parsed object, or `null` if absent (or torn — logged + counted).
|
||||
*/
|
||||
public async readRawObject(path: string): Promise<any | null> {
|
||||
await this.ensureInitialized()
|
||||
return this.readObjectFromPath(path)
|
||||
try {
|
||||
return await this.readObjectFromPath(path)
|
||||
} catch (error) {
|
||||
if (isTornRecordError(error)) return null
|
||||
throw error
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
@ -2146,6 +2181,9 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
if (!metadata) return null
|
||||
return { deserialized, metadata }
|
||||
} catch (error) {
|
||||
// A TORN record must surface typed — a paginated read that
|
||||
// silently skips a corrupt row hides data loss from the caller.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip nouns that fail to load
|
||||
return null
|
||||
}
|
||||
|
|
@ -2175,6 +2213,8 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
}
|
||||
}
|
||||
} catch (error) {
|
||||
// A TORN record propagates (typed) — only shard-listing absence is skippable.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip shards that have no data
|
||||
}
|
||||
}
|
||||
|
|
@ -2283,7 +2323,9 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
batch.map(async (id) => {
|
||||
try {
|
||||
return { id, metadata: await this.getNounMetadata(id) }
|
||||
} catch {
|
||||
} catch (error) {
|
||||
// A TORN record must surface typed, never as a skipped id.
|
||||
if (isTornRecordError(error)) throw error
|
||||
return null
|
||||
}
|
||||
})
|
||||
|
|
@ -2305,6 +2347,8 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
}
|
||||
}
|
||||
} catch (error) {
|
||||
// A TORN record propagates (typed) — only shard-listing absence is skippable.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip shards with no data
|
||||
}
|
||||
}
|
||||
|
|
@ -2515,10 +2559,15 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
// reserved fields top-level, ONLY custom fields in `metadata`.
|
||||
collected.push({ verb: this.hydrateVerbWithMetadata(verb, metadata), shard })
|
||||
} catch (error) {
|
||||
// A TORN record must surface typed — a paginated read that
|
||||
// silently skips a corrupt row hides data loss from the caller.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip verbs that fail to load
|
||||
}
|
||||
}
|
||||
} catch (error) {
|
||||
// A TORN record propagates (typed) — only shard-listing absence is skippable.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip shards that have no data
|
||||
}
|
||||
}
|
||||
|
|
@ -3669,8 +3718,17 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
)
|
||||
|
||||
for (const result of chunkResults) {
|
||||
if (result.status === 'fulfilled' && result.value.data !== null) {
|
||||
results.set(result.value.path, result.value.data)
|
||||
if (result.status === 'fulfilled') {
|
||||
if (result.value.data !== null) {
|
||||
results.set(result.value.path, result.value.data)
|
||||
}
|
||||
} else {
|
||||
// A rejected read is a torn record or a real storage fault — NOT an
|
||||
// absent object. Batch hydration backs entity reads (getNounBatch /
|
||||
// getVerbsBatch / find hydration); swallowing the rejection would
|
||||
// silently drop a row the caller cannot distinguish from "never
|
||||
// existed". Propagate the typed/real error loudly instead.
|
||||
throw result.reason
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -4636,10 +4694,15 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
}
|
||||
}
|
||||
} catch (error) {
|
||||
// A TORN record must surface typed — an enumeration that silently
|
||||
// skips a corrupt row hides data loss from the caller.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip nouns that fail to load
|
||||
}
|
||||
}
|
||||
} catch (error) {
|
||||
// A TORN record propagates (typed) — only shard-listing absence is skippable.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip shards that have no data
|
||||
}
|
||||
}
|
||||
|
|
@ -4825,11 +4888,16 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
results.push(this.hydrateVerbWithMetadata(verb, metadata))
|
||||
}
|
||||
} catch (error) {
|
||||
// A TORN record must surface typed — an enumeration that silently
|
||||
// skips a corrupt row hides data loss from the caller.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip verbs that fail to load
|
||||
prodLog.debug(`[BaseStorage] Failed to load verb from ${verbPath}:`, error)
|
||||
}
|
||||
}
|
||||
} catch (error) {
|
||||
// A TORN record propagates (typed) — only shard-listing absence is skippable.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip shards that have no data
|
||||
}
|
||||
}
|
||||
|
|
@ -4945,6 +5013,9 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
sourceVerbs.push(hydratedVerb)
|
||||
}
|
||||
} catch (error) {
|
||||
// A TORN record propagates (typed) — batch hydration must not
|
||||
// silently drop a corrupt row. Only shard-listing absence is skippable.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip shards that have no data
|
||||
}
|
||||
}
|
||||
|
|
@ -5030,10 +5101,15 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
results.push(this.hydrateVerbWithMetadata(verb, metadata))
|
||||
}
|
||||
} catch (error) {
|
||||
// A TORN record must surface typed — an enumeration that silently
|
||||
// skips a corrupt row hides data loss from the caller.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip verbs that fail to load
|
||||
}
|
||||
}
|
||||
} catch (error) {
|
||||
// A TORN record propagates (typed) — only shard-listing absence is skippable.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip shards that have no data
|
||||
}
|
||||
}
|
||||
|
|
@ -5078,10 +5154,15 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
)
|
||||
)
|
||||
} catch (error) {
|
||||
// A TORN record must surface typed — an enumeration that silently
|
||||
// skips a corrupt row hides data loss from the caller.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip verbs that fail to load
|
||||
}
|
||||
}
|
||||
} catch (error) {
|
||||
// A TORN record propagates (typed) — only shard-listing absence is skippable.
|
||||
if (isTornRecordError(error)) throw error
|
||||
// Skip shards that have no data
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue