Compare commits

..

No commits in common. "main" and "next/open-lazy-open-and-counts" have entirely different histories.

18 changed files with 60 additions and 950 deletions

View file

@ -5,10 +5,6 @@ name: CI
# sequential, so tag-triggered matrix jobs (~22 min) would queue AHEAD of the
# tag's publish-source run and starve every release (observed on 8.10.3 and
# 9.0.0: the publish sat behind the tag's own redundant CI).
concurrency:
group: ci-${{ github.ref }}
cancel-in-progress: true
on:
push:
branches: ['**']

View file

@ -2,35 +2,6 @@
All notable changes to this project will be documented in this file. See [standard-version](https://github.com/conventional-changelog/standard-version) for commit guidelines.
### [10.4.4](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.4.3...v10.4.4) (2026-08-28)
- fix(vfs): the old-root sweep narrates only when it has something to say (d49148e1)
- fix(tests): the health-gate pin follows the verdict, and the VFS suite uses its own store (42e2da25)
- Merge branch 'next/open-lazy-open-and-counts' (5ebd3b40)
- docs: the contract manifest stands alone; public docs describe this engine only (a8c724a2)
- docs(releases): 10.4.4 consumer notes — correctness and observability, with the performance line stated exactly (61a46927)
- docs: measurements in public history carry numbers, not provenance (02c61636)
- feat(open): name the two steps that hold the vfs-bootstrap phase (2cf38010)
- fix(storage): a dead flush watch falls back to the 500ms poll, not the 30s sweep (5c22f950)
- fix(storage): the flush watcher cannot arm twice in its async window (16d2e1a9)
- perf(idle): the flush-request watch is event-driven; the heartbeat is observability (fb1da1c5)
- perf(open): answer "are there any entities?" with one directory read (417ddb51)
- perf(generations): discover generations by directory name, not by walking the log (9dd39921)
- fix(flush): clear() and repairIndex() set the dirty witness themselves (e4c27fbc)
- feat(open): the open names the STEP that cost the time, not just the phase (5a091cca)
- perf(vfs): the old-root sweep runs once per store, not once per open (4a67aa0f)
- chore: keep the generated neural stamps at main's values (c1f09723)
- feat(contract): declare contract 1, serve three operators, refuse four by name (48802ba3)
- fix(open): a provider rebuilding itself is a third state, not a CRITICAL (50676c02)
- feat(open): open never waits for a provider that is rebuilding itself (131daa08)
- perf(flush): an idle brain does no work — no periodic flush without a write (f5a6cb3f)
- feat(repair): repairIndex narrates every phase and its receipt carries the walls (3fffd9c6)
- fix(storage): a suspect count ledger heals itself, and counts.json is written atomically (f4e2d34b)
- feat(open): the open narrates itself, on a channel production cannot clamp (afe08a1f)
- fix(storage): a clean close is recorded, and the writer lock is always given up (e652162c)
- docs: repository links point at soulcraftlabs/open-brainy — the soulcraft/brainy path becomes the native engine's repo tonight (38c3397b)
### [10.4.3](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.4.2...v10.4.3) (2026-08-27)
- Merge branch 'next/open-brainy-rename' (a58372f0)

4
package-lock.json generated
View file

@ -1,12 +1,12 @@
{
"name": "@soulcraftlabs/brainy",
"version": "10.4.4",
"version": "10.4.3",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@soulcraftlabs/brainy",
"version": "10.4.4",
"version": "10.4.3",
"license": "MIT",
"dependencies": {
"@msgpack/msgpack": "^3.1.2",

View file

@ -1,6 +1,6 @@
{
"name": "@soulcraftlabs/brainy",
"version": "10.4.4",
"version": "10.4.3",
"brainyContract": 1,
"description": "Universal Knowledge Protocol™ - World's first Triple Intelligence database unifying vector, graph, and document search in one API. Stage 3 CANONICAL: 42 nouns × 127 verbs covering 96-97% of all human knowledge.",
"main": "dist/index.js",

View file

@ -1,76 +0,0 @@
{
"product": "brainy",
"entries": [
{
"version": "11.0.5",
"date": "2026-09-02",
"headline": "Graph-first finds in production, and opens that stop rescanning history",
"items": [
"find({ connected, where }) now walks the neighbours first and filters only those rows through a native door — correct at every page and O(neighbours), never the whole store.",
"related() with a list of verb types returns every requested kind (a fast path had silently kept only the first).",
"Deferred-embedding recovery resumes from a low-water mark instead of rescanning the whole generation log at every open — measured at two minutes on a large brain, now milliseconds."
],
"url": null,
"thumb": null
},
{
"version": "11.0.4",
"date": "2026-09-01",
"headline": "Closes in milliseconds, index rebuilds without the disk-sync storm",
"items": [
"close() no longer pays deferred compaction or waits out an in-flight rebuild — measured 8 ms against the 4-minute closes it replaces; deferred work resumes at the next open, in the background.",
"The metadata index's rebuild syncs to disk per shard instead of per row, and the durability point moved to the publish step — the same guarantee, a fraction of the disk traffic.",
"A new native filter door evaluates queries over exactly the candidate rows a graph walk found, never the whole store."
],
"url": null,
"thumb": null
},
{
"version": "11.0.3",
"date": "2026-09-01",
"headline": "The embedding upgrade ceremony runs on every brain",
"items": [
"A brain opened through the standard plugin now carries its embedding-model identity, so the full-precision upgrade ceremony can run on it.",
"A one-fix release; nothing else changed."
],
"url": null,
"thumb": null
},
{
"version": "11.0.2",
"date": "2026-08-31",
"headline": "One embedding quality everywhere, 34× faster imports",
"items": [
"Every runtime embeds with the same full-precision model — search quality no longer depends on where you run.",
"Bulk embedding measured 3.14.2× faster, and an online re-embed ceremony upgrades existing stores without downtime.",
"The engine's change feed is documented, with the SSE/WebSocket fan-out pattern for realtime surfaces."
],
"url": null,
"thumb": null
},
{
"version": "11.0.1",
"date": "2026-08-31",
"headline": "Deletes inside transactions are safe",
"items": [
"Deleting relations inside a transact() no longer corrupts index bookkeeping.",
"A store that deletes its last relation keeps serving instead of refusing."
],
"url": null,
"thumb": null
},
{
"version": "11.0.0",
"date": "2026-08-28",
"headline": "One install, one engine — Brainy",
"items": [
"The former two-package pair is one package: the native engine under the familiar API. One import is the whole install.",
"A missing native build refuses loudly with its cures named; nothing falls back silently.",
"Stores open in place — no migration."
],
"url": null,
"thumb": null
}
],
"history": "The version line continues from the 4.3.x native-engine releases; their record lives in the product repository's CHANGELOG.md."
}

View file

@ -1,122 +0,0 @@
{
"product": "open-brainy",
"entries": [
{
"version": "10.4.10",
"date": "2026-09-02",
"headline": "A planner door for indexes, batched containment repair, and a fixed near()",
"items": [
"An optional planFindPage door lets an index plan a find() and answer it in one call, instead of the engine assembling the plan itself.",
"repairContainment's reconcile pass now walks paged edges once instead of issuing one graph call per file.",
"find({ near }) now searches around the anchor's own vector and refuses by name when none is available, instead of silently querying with no vector at all."
],
"url": "https://source.soulcraft.com/soulcraftlabs/open-brainy/releases/tag/v10.4.10",
"thumb": null
},
{
"version": "10.4.9",
"date": "2026-09-02",
"headline": "Graph-first finds, honest verb arrays, and opens that stop rescanning history",
"items": [
"find({ connected, where }) now walks the neighbours first and filters only those rows — correct at every page, and O(neighbours) instead of O(store).",
"related() with a list of verb types (or sources, or targets) returns every requested kind — four fast paths silently kept only the first.",
"Deferred-embedding recovery resumes from a low-water mark instead of rescanning the whole generation log at every open — measured at two minutes on a large brain, now milliseconds."
],
"url": "https://source.soulcraft.com/soulcraftlabs/open-brainy/releases/tag/v10.4.9",
"thumb": null
},
{
"version": "10.4.7",
"date": "2026-09-01",
"headline": "Count ledgers can no longer race themselves",
"items": [
"Concurrent count flushes coalesce into one writer with a trailing pass — parallel flushes can no longer corrupt a store's count ledger.",
"Atomic writes carry a per-process sequence, so two processes' temp files can never collide."
],
"url": "https://source.soulcraft.com/soulcraftlabs/open-brainy/releases/tag/v10.4.7",
"thumb": null
},
{
"version": "10.4.6",
"date": "2026-08-31",
"headline": "Transactions cross the index seam safely",
"items": [
"Deleting relations inside a transact() no longer fails against the metadata index — operations take a JSON-safe view at the moment they execute.",
"Fixes a class of transaction failures on stores with integer-mapped relation endpoints."
],
"url": "https://source.soulcraft.com/soulcraftlabs/open-brainy/releases/tag/v10.4.6",
"thumb": null
},
{
"version": "10.4.5",
"date": "2026-08-31",
"headline": "Recovery tells the truth, docs live at home",
"items": [
"A torn generation-log tail is a terminal verdict with a named cure — never an endless wait at open.",
"A sealed segment declares only the generations it actually holds.",
"The engine's documentation now publishes from its own repository."
],
"url": "https://source.soulcraft.com/soulcraftlabs/open-brainy/releases/tag/v10.4.5",
"thumb": null
},
{
"version": "10.4.4",
"date": "2026-08-28",
"headline": "Faster opens, quieter idle",
"items": [
"Opening a store discovers generations from directory names instead of walking the log, and answers \"any entities?\" with one directory read.",
"The flush-request watch is event-driven; idle stores stop paying a polling heartbeat.",
"A slow open now names the exact step it is in, so operators see what is being paid and why."
],
"url": "https://source.soulcraft.com/soulcraftlabs/open-brainy/releases/tag/v10.4.4",
"thumb": null
},
{
"version": "10.4.3",
"date": "2026-08-27",
"headline": "Open Brainy, under its own name",
"items": [
"The same engine as 10.4.2, now published as @soulcraftlabs/brainy — the MIT reference engine, on The Source.",
"No code changes; your imports change once and everything else stays put."
],
"url": "https://source.soulcraft.com/soulcraftlabs/open-brainy/releases/tag/v10.4.3",
"thumb": null
},
{
"version": "10.4.2",
"date": "2026-08-27",
"headline": "Vectors that lie are refused, counts that drift are caught",
"items": [
"A zero-norm vector is not a vector: the index refuses them, rebuilds skip them, and a sanctioned unvector door removes them cleanly.",
"The canonical count ledger derives from identity records and marks legacy-derived ledgers suspect at load.",
"Plugin activation failures keep their original error as cause, so the real frame reaches your logs."
],
"url": "https://source.soulcraft.com/soulcraftlabs/open-brainy/releases/tag/v10.4.2",
"thumb": null
},
{
"version": "10.4.1",
"date": "2026-08-26",
"headline": "Writes that change nothing cost nothing",
"items": [
"The read gate is per index family, and a write carrying unchanged data never re-embeds.",
"The vectored-row count joins the ledger, so vector coverage is a number you can read, not a guess."
],
"url": "https://source.soulcraft.com/soulcraftlabs/open-brainy/releases/tag/v10.4.1",
"thumb": null
},
{
"version": "10.4.0",
"date": "2026-08-26",
"headline": "Repair routing, the vector ledger, and honest empties",
"items": [
"Repairs route to the index that owns the damage, and the open gate closes the vector leg until coverage is proven.",
"An empty string is real data, not a missing field.",
"The metadata crossing never carries raw integer relation endpoints — a whole class of serialization faults closed."
],
"url": "https://source.soulcraft.com/soulcraftlabs/open-brainy/releases/tag/v10.4.0",
"thumb": null
}
],
"history": "Earlier releases are recorded in CHANGELOG.md in this repository."
}

View file

@ -237,7 +237,7 @@ fi
# and RELEASES.md are the record; this just gives The Source's UI a release page).
echo -e "${BLUE}🔟 Creating release page on The Source...${NC}"
if [ -n "${FORGEJO_RELEASE_TOKEN:-}" ]; then
if curl -sf -X POST "https://source.soulcraft.com/api/v1/repos/soulcraftlabs/open-brainy/releases" \
if curl -sf -X POST "https://source.soulcraft.com/api/v1/repos/soulcraft/brainy/releases" \
-H "Authorization: token ${FORGEJO_RELEASE_TOKEN}" -H "Content-Type: application/json" \
-d "{\"tag_name\":\"v${NEW_VERSION}\",\"name\":\"v${NEW_VERSION}\",\"prerelease\":${PRERELEASE}}" >/dev/null; then
echo -e "${GREEN}✅ Release page created on The Source${NC}\n"
@ -248,12 +248,17 @@ else
echo -e "${RED}⚠️ FORGEJO_RELEASE_TOKEN unset — no release page created; tag + CHANGELOG remain the record${NC}\n"
fi
# Step 12 RETIRED (2026-08-31, CORTEX-SITE-BRAINY-RENAME round 12, David-ruled):
# soulcraft.com/docs carries the paid product's documentation only. This
# engine's documentation home is THIS repository — README and docs/ — and the
# site serves 301s for the slugs this rail used to push. The push script stays
# in the tree for history; the rail no longer calls it.
echo -e "${BLUE}Docs step: this engine documents itself in its own repo (site push retired 2026-08-31)${NC}"
# Step 12: Push public docs to the soulcraft.com docs ingest door
# (VENUE-DOCS-RELEASE-PUSH). Skips with a loud warning when
# DOCS_INGEST_SECRET is unset; fails loudly (without undoing the publish —
# that already happened) when a push errors, so the docs site never
# silently trails npm.
echo -e "${BLUE}1⃣2⃣ Pushing public docs to soulcraft.com/docs...${NC}"
if node scripts/push-docs.js; then
echo -e "${GREEN}✅ Docs push step done${NC}\n"
else
echo -e "${RED}❌ Docs push FAILED — soulcraft.com/docs trails npm until re-run or interim sync${NC}\n"
fi
echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
echo -e "${GREEN}🎉 Release ${NEW_VERSION} complete!${NC}"

View file

@ -12497,18 +12497,6 @@ export class Brainy<T = any> implements BrainyInterface<T> {
* healed by `repairIndex()`, whose unconditional recount rebuilds the
* rollups from a canonical walk and re-stamps. Best-effort: a stamp-write
* fault warns loudly but never fails the flush that carried real data.
*
* THE SOURCE IS `committedGeneration()`, NEVER `generation()`. The latter is
* the ALLOCATED counter a number a write in flight has claimed and may
* never commit. Stamping it made the stamp's generation label a claim about
* counts it was not taken at, and every crash inside a write window then
* produced a spurious verdict at the next open: either `sourceGeneration N
* is ahead of the log head N-1` (the allocated generation died with the
* process) or `rollup invariant 'nounCount': stamped X, observed Y` (the
* recovery fold folded facts the stamp's counts predate). MEASURED on the
* crash-consistency lane before this line changed: 4 of 11 SIGKILL cycles on
* a coherent store raised one of those two verdicts, each of them naming
* `repairIndex()` a whole-store recount as the cure for nothing.
*/
private async stampEntityTree(): Promise<void> {
if (this.isReadOnly) return
@ -12519,7 +12507,7 @@ export class Brainy<T = any> implements BrainyInterface<T> {
])
await writeFamilyStamp(this.storage, ENTITY_TREE_STAMP_PATH, {
family: 'entity-tree',
sourceGeneration: this.generationStore.committedGeneration(),
sourceGeneration: this.generationStore.generation(),
members: { mode: 'rollup', invariants: { nounCount, verbCount } }
})
} catch (error) {
@ -12532,24 +12520,16 @@ export class Brainy<T = any> implements BrainyInterface<T> {
/**
* @description Open-time coherence check for the entity tree's family stamp:
* compare `sourceGeneration` against the store's COMMITTED generation and
* the stamped rollup invariants against the live counters. Verdicts:
* compare `sourceGeneration` against the log head and the stamped rollup
* invariants against the live counters. Verdicts:
* - `coherent` / `absent` (legacy store; first flush stamps) silent.
* - `behind` benign for the tree (it is written BY the commit; only the
* stamp is stale a crash landed between commit and flush). Refreshed at
* the next flush.
* - `torn` a TORN GENERATION-LOG TAIL, handled by
* {@link demoteTornEntityTreeStamp}: terminal, never a wait.
* - `incoherent` LOUD: the tree or its counters diverged from what was
* stamped `repairIndex()` recounts from canonical and re-stamps.
* Never blocks open; a fault reading the stamp is surfaced as unverifiable,
* never conflated with absence.
*
* THE COMPARISON IS AGAINST `committedGeneration()`, matching what
* {@link stampEntityTree} writes and what every other open-time watermark in
* this class already reasons about (the fact-scan capability, the metadata /
* graph / HNSW watermark verdicts). Comparing against the allocated counter
* was the one place that disagreed, and disagreeing was the whole defect.
*/
private async verifyEntityTreeStamp(): Promise<void> {
let stamp: FamilyStamp | null
@ -12566,16 +12546,11 @@ export class Brainy<T = any> implements BrainyInterface<T> {
this.storage.getNounCount(),
this.storage.getVerbCount()
])
const verdict = verifyFamilyStamp(stamp, this.generationStore.committedGeneration(), {
const verdict = verifyFamilyStamp(stamp, this.generationStore.generation(), {
nounCount,
verbCount
})
if (verdict.state === 'torn') {
await this.demoteTornEntityTreeStamp(stamp as FamilyStamp, verdict.stampSource, verdict.head, {
nounCount,
verbCount
})
} else if (verdict.state === 'incoherent') {
if (verdict.state === 'incoherent') {
prodLog.warn(
`[Brainy] entity-tree stamp INCOHERENT at open: ${verdict.failures.join('; ')}. ` +
`The canonical tree or its counters diverged from the stamped state — run ` +
@ -12589,92 +12564,6 @@ export class Brainy<T = any> implements BrainyInterface<T> {
}
}
/**
* @description THE TERMINAL VERDICT for a torn generation-log tail.
*
* A stamp whose `sourceGeneration` sits ABOVE the store's committed
* watermark witnesses a generation that is not in the log: the stamp's fsync
* outlived the tail's. By the time this runs, log-authority recovery has
* already folded every intact fact above the manifest and advanced the
* watermark to cover them so if the stamp is STILL ahead, the generation
* it names is not merely late, it is GONE. There is nothing to wait for.
*
* That is the whole point of this method. A field report of this class
* (single-process store, abrupt termination mid-fold) described a reopen
* that narrated the tear and then held 100% CPU with zero log growth for
* eight minutes before an operator wiped the directory. A recovery that
* cannot say what it is waiting for has no business spinning; the honest
* answer here is a verdict, taken now, at O(1) cost.
*
* WHAT THE VERDICT DOES the stamped surface is UNUSABLE, so it is
* discarded rather than believed: the stamped counts describe a generation
* that never became durable, and comparing them against live counters can
* only produce noise. The tree itself is not in question (it IS canonical
* every commit writes it, and the fold re-applied every after-image the log
* still holds), so the demotion is a re-derivation of this family's verified
* surface at the generation the store can actually show:
*
* - WRITER open re-stamp at `committedGeneration()` from the live
* counters exactly what the next flush would write, taken now so the
* tear cannot re-narrate on every subsequent open. Both count sets are
* logged so an operator can see whether anything really moved.
* - READER open a reader cannot re-stamp. Narrate the same terminal
* verdict with the named cure and carry on serving; a read-only inspector
* is never locked out of a store, and never left waiting either.
*
* BOUNDEDNESS: straight-line code. No loop, no retry, no await on any
* external progress signal the two counter reads and one stamp write are
* the entire cost, and none of them scales with the store.
*/
private async demoteTornEntityTreeStamp(
stamp: FamilyStamp,
stampSource: number,
head: number,
observed: { nounCount: number; verbCount: number }
): Promise<void> {
const stamped = stamp.members.mode === 'rollup' ? stamp.members.invariants : {}
const detail =
`[Brainy] TORN GENERATION-LOG TAIL at open: ${ENTITY_TREE_STAMP_PATH} witnesses source ` +
`generation ${stampSource} (stamped ${stamp.committedAt}), but the store's committed ` +
`generation is ${head} after crash recovery — the stamp's fsync outlived the log tail's, ` +
`and generation ${stampSource} is not in the log to arrive. Stamped rollups ` +
`${JSON.stringify(stamped)}; observed ${JSON.stringify(observed)}.`
if (this.isReadOnly) {
prodLog.warn(
`${detail} This open is READ-ONLY, so the stamp cannot be re-derived: the entity-tree ` +
`family stays UNVERIFIED for this session (reads are unaffected — the canonical tree ` +
`is the truth this stamp only describes). Cure: open the store with a writer, or run ` +
`brain.repairIndex() there, to recount from canonical and re-stamp.`
)
return
}
const startedAt = Date.now()
try {
await writeFamilyStamp(this.storage, ENTITY_TREE_STAMP_PATH, {
family: 'entity-tree',
sourceGeneration: head,
members: {
mode: 'rollup',
invariants: { nounCount: observed.nounCount, verbCount: observed.verbCount }
}
})
prodLog.warn(
`${detail} DEMOTED: the unusable stamp was re-derived at committed generation ${head} ` +
`from the live counters in ${Date.now() - startedAt}ms — terminal, not a wait. If the ` +
`observed counts above look wrong for your data, run brain.repairIndex() to recount ` +
`from canonical.`
)
} catch (error) {
prodLog.warn(
`${detail} The demotion's re-stamp FAILED (${(error as Error).message}) — the tear will ` +
`narrate again at the next open, which is the honest outcome; the store still serves ` +
`from canonical. Cure: run brain.repairIndex() to recount from canonical and re-stamp.`
)
}
}
/**
* Ask the writer process serving this data directory to flush its in-memory
* indexes to disk, so a read-only inspector can observe fresh state.

View file

@ -12,11 +12,9 @@
* the verified surface is a small set of rollup invariants (entity/
* relationship counts) plus `sourceGeneration`.
*
* `sourceGeneration` is the COMMITTED generation of the source-of-truth log
* this projection reflects never the allocated counter, which names a
* generation that may never commit (see {@link StampVerdict.torn}) so
* open-time coherence becomes a COMPARISON (stamp vs committed head), not a
* walk:
* `sourceGeneration` is the generation of the source-of-truth log this
* projection reflects open-time coherence becomes a COMPARISON (stamp vs
* log head), not a walk:
*
* - equal + invariants hold coherent, serve.
* - behind the projection missed the tail (crash between commit and stamp);
@ -26,9 +24,6 @@
* - invariants FAIL at equal generation genuine incoherence: loud, and the
* repair ritual (`repairIndex()`, whose recount rebuilds the rollups from a
* canonical walk) heals it.
* - AHEAD a torn generation-log tail: the stamp's fsync outlived the log
* tail's. TERMINAL, never a wait the generation the stamp names does not
* exist to arrive.
*
* Stamps are JSON on purpose every incident gets debugged by reading a
* stamp in a terminal.
@ -75,12 +70,6 @@ export type StampVerdict =
| { state: 'coherent' }
| { state: 'absent' } // legacy store — first stamp writes at the next flush
| { state: 'behind'; stampSource: number; head: number }
/**
* TORN GENERATION-LOG TAIL: the stamp witnesses a source generation the
* store's committed watermark can no longer show. TERMINAL there is no
* generation to wait for, so the open demotes (or refuses) and never spins.
*/
| { state: 'torn'; stampSource: number; head: number }
| { state: 'incoherent'; failures: string[] }
| { state: 'unverifiable'; reason: string } // a FAULT reading the stamp — never conflated with absence
@ -129,15 +118,12 @@ export function verifyFamilyStamp(
): StampVerdict {
if (stamp === null) return { state: 'absent' }
if (stamp.sourceGeneration > head) {
// A stamp AHEAD of committed truth witnesses a generation the store can no
// longer show: the stamp's fsync survived a crash that the log tail did
// not. This is the TORN GENERATION-LOG TAIL — its own class, never folded
// in with `incoherent` (a count that drifted at a generation both sides
// agree on), because the two have opposite cures: incoherence is recounted,
// a tear is DEMOTED. It is also terminal by construction — there is no
// generation the open can wait for, because the one the stamp names is
// gone.
return { state: 'torn', stampSource: stamp.sourceGeneration, head }
// A stamp AHEAD of the log claims state that never committed — the
// projection was stamped against truth that a crash rolled back.
return {
state: 'incoherent',
failures: [`sourceGeneration ${stamp.sourceGeneration} is ahead of the log head ${head}`]
}
}
if (stamp.sourceGeneration < head) {
return { state: 'behind', stampSource: stamp.sourceGeneration, head }

View file

@ -147,60 +147,6 @@ export class GenerationSegmentStore {
return this.coveringSegment(gen) !== null
}
/**
* @description True when `meta` declares more generations than it holds
* frames a segment sealed by a writer that folded across a hole. The
* manifest records `frames` at fold time, so this is an O(1) comparison
* against the declared span and needs no I/O.
*/
private isSparse(meta: SegmentMeta): boolean {
return meta.lastGeneration - meta.firstGeneration + 1 !== meta.frames
}
/**
* @description The generations this tier ACTUALLY holds, as coalesced
* ascending intervals not what the segments declare.
*
* Dense segments (every one a current writer produces) contribute their
* declared range with no I/O. A SPARSE segment one sealed before the
* density law was enforced, whose declared range spans generations it has
* no frame for has its real generation list read from its sidecar and
* contributed instead, with the discrepancy narrated once.
*
* This is what keeps a store that already carries the damage from wedging.
* `open()` seeds `committedRanges` from these intervals, so a hole is never
* re-admitted as a committed generation, and the auto-compaction pass that
* used to fail on every run with "packed history is damaged" simply never
* asks for the missing frame.
*
* @returns Ascending, non-overlapping `[first, last]` intervals.
*/
async actualRanges(): Promise<Array<[number, number]>> {
const out: Array<[number, number]> = []
for (const meta of this.manifest.segments) {
if (!this.isSparse(meta)) {
out.push([meta.firstGeneration, meta.lastGeneration])
continue
}
const missing = meta.lastGeneration - meta.firstGeneration + 1 - meta.frames
prodLog.warn(
`[GenerationSegments] sealed segment ${meta.file} declares generations ` +
`${meta.firstGeneration}..${meta.lastGeneration} but holds only ${meta.frames} ` +
`frame(s) — ${missing} generation(s) in that span were never folded into it. ` +
`Serving the frames it actually holds; the declared span is not treated as ` +
`committed history. (Written by a pre-density-law writer that folded across a ` +
`gap; the segment itself is intact and no record is lost.)`
)
const idx = await this.sidecarFor(meta)
for (const [gen] of idx.generations) {
const last = out[out.length - 1]
if (last !== undefined && gen === last[1] + 1) last[1] = gen
else out.push([gen, gen])
}
}
return out
}
/**
* Fold consecutive generations into ONE new sealed segment + sidecar and
* append it to the manifest atomically. Caller guarantees: `gens` is
@ -218,38 +164,6 @@ export class GenerationSegmentStore {
throw new Error('[GenerationSegments] fold() input must be strictly ascending')
}
}
// THE DENSITY LAW, MADE MECHANICAL.
//
// A sealed segment declares a CONTIGUOUS range [firstGeneration,
// lastGeneration] and every reader treats that range as containment:
// `coveringSegment` is an interval test, `hasGeneration` returns true for
// anything inside it, and `open()` seeds committedRanges from it. So a
// segment folded from a SPARSE input silently claims generations it does
// not hold, and the first read of one of those holes throws
// "inside sealed segment ... but has no frame — packed history is damaged".
//
// That is exactly how the damage was produced. `repackHistory` skipped
// generations mid-batch — ones absent from committedRanges, ones still in
// the pending buffer, ones whose tx.json would not read — and handed the
// survivors here, where the range was computed from the first and last of
// them. Worse, the mis-declared range was then merged back into
// committedRanges at the next open, which is what turned a quiet hole into
// a repeating auto-compaction failure on every subsequent run.
//
// Callers now split at discontinuities; this refusal is what keeps any
// future caller from reintroducing the class. A refusal here loses
// nothing — the generations stay in the live tier, readable, and the next
// pass folds them correctly.
for (let i = 1; i < gens.length; i++) {
if (gens[i].generation !== gens[i - 1].generation + 1) {
throw new Error(
`[GenerationSegments] fold() input is not contiguous: ${gens[i - 1].generation}` +
`${gens[i].generation} skips ${gens[i].generation - gens[i - 1].generation - 1} ` +
`generation(s). A sealed segment declares a dense range, so folding a sparse ` +
`batch would claim generations it does not hold. Split the batch at the gap.`
)
}
}
const last = this.manifest.segments[this.manifest.segments.length - 1]
if (last && gens[0].generation <= last.lastGeneration) {
throw new Error(
@ -450,37 +364,12 @@ export class GenerationSegmentStore {
return this.decodeFrame(payload)
}
}
// Inside the covering range but with no frame. Two very different causes,
// and conflating them is what made this class wedge every maintenance pass
// on the affected stores.
//
// (1) A SPARSE SEGMENT — the manifest's own `frames` count is smaller than
// the span it declares. That segment was sealed by a writer that
// folded across a hole (the class this file's density law now bars).
// The segment is INTACT and nothing is lost; it simply never held this
// generation. Answering "not packed" is the honest answer, and it lets
// the caller's two-tier read decide what a genuinely absent generation
// means, instead of every compaction pass dying on a repeating throw.
// `actualRanges()` keeps such holes out of committedRanges at open, so
// in a healed store nobody asks this question in the first place.
//
// (2) A DENSE SEGMENT missing a frame it says it has — the manifest and
// the sidecar disagree about a segment that claims to be complete.
// That IS damage, and it stays loud.
if (this.isSparse(meta)) {
prodLog.warn(
`[GenerationSegments] generation ${gen} falls inside sealed segment ${meta.file}'s ` +
`declared range ${meta.firstGeneration}..${meta.lastGeneration}, but that segment ` +
`holds ${meta.frames} frame(s) for a ${meta.lastGeneration - meta.firstGeneration + 1}` +
`-generation span — it was sealed across a gap and never held this generation. ` +
`Reporting it as unpacked rather than as damage; no record is lost.`
)
return null
}
// In the covering range but not present: the packed tier is dense by
// construction (fold packs every generation it is handed, including
// record-less ones) — absence inside a sealed range is damage.
throw new Error(
`[GenerationSegments] generation ${gen} is inside sealed segment ${meta.file}'s declared ` +
`range but has no frame, and that segment declares a complete ${meta.frames}-frame ` +
`span — the manifest and the sidecar disagree; packed history is damaged`
`range but has no frame — packed history is damaged`
)
}

View file

@ -96,35 +96,6 @@ export const FOLD_CHECKPOINT_PATH = '_system/fold-checkpoint.json'
/** Storage-root-relative prefix of the per-generation record directories. */
export const GENERATIONS_PREFIX = '_generations'
/**
* @description Split an ascending list of fold candidates into maximal
* CONTIGUOUS runs `[7,8,9,12,13]` becomes `[[7,8,9],[12,13]]`.
*
* A sealed segment declares one dense range `[firstGeneration,
* lastGeneration]`, and every reader treats that range as containment. So a
* batch with a hole in it must never become one segment: it would claim a
* generation it does not hold, and the first read of that hole reports the
* packed history as damaged. One run, one segment the ranges then describe
* exactly what the segments contain.
*
* @param gens - Fold candidates, strictly ascending by generation.
* @returns One array per contiguous run, in ascending order. Empty in, empty out.
*/
export function contiguousRuns(gens: FoldGeneration[]): FoldGeneration[][] {
const runs: FoldGeneration[][] = []
let run: FoldGeneration[] = []
for (const g of gens) {
const prev = run[run.length - 1]
if (prev !== undefined && g.generation !== prev.generation + 1) {
runs.push(run)
run = []
}
run.push(g)
}
if (run.length > 0) runs.push(run)
return runs
}
/**
* @description Phases of the {@link GenerationStore.commitTransaction} commit
* protocol at which a test-only fault injector can simulate a process crash.
@ -813,15 +784,9 @@ export class GenerationStore {
if (storageSupportsFactLog(this.storage)) {
this.segments = new GenerationSegmentStore(this.storage)
await this.segments.open()
// ACTUAL ranges, not declared ones. A segment sealed by a pre-density-law
// writer can declare a span wider than the frames it holds; seeding
// committedRanges from the declared span re-admits those holes as
// committed generations, and every later maintenance pass then asks for a
// frame that was never written. `actualRanges()` reads the real
// generation list from the sidecar for exactly those segments (and does
// no I/O for the dense ones, which is all of them on a healthy store).
const packedRanges = (await this.segments.actualRanges())
.map((r): [number, number] => [r[0], Math.min(r[1], this.committed)])
const packedRanges = this.segments
.segments()
.map((s): [number, number] => [s.firstGeneration, Math.min(s.lastGeneration, this.committed)])
.filter(([lo, hi]) => lo <= hi)
if (packedRanges.length > 0) {
// Merge packed (older) + live (newer) interval sets — both ascending;
@ -3156,26 +3121,13 @@ export class GenerationStore {
foldInput.push({ generation: gen, timestamp: delta.timestamp, delta, records })
}
if (foldInput.length === 0) continue
// SPLIT AT DISCONTINUITIES. `eligible` is NOT contiguous — three
// filters above punch holes in it: a generation missing from
// committedRanges never appears, one still in the pending buffer is
// skipped, and one whose tx.json will not read is skipped. A sealed
// segment declares a DENSE range, so folding across such a hole makes
// the segment claim a generation it does not hold; the next open
// merges that mis-declared range into committedRanges, and every
// subsequent auto-compaction pass then asks for the missing frame and
// fails with "packed history is damaged". Fold each contiguous RUN as
// its own segment instead — same bytes, honest ranges.
for (const run of contiguousRuns(foldInput)) {
if (deadline !== undefined && Date.now() >= deadline) break
await segments.fold(run)
segmentsCreated++
// Segment + manifest durable → the live copies retire.
for (const g of run) {
await this.storage.removeRawPrefix(`${GENERATIONS_PREFIX}/${g.generation}`)
}
folded += run.length
await segments.fold(foldInput)
segmentsCreated++
// Segment + manifest durable → the live copies retire.
for (const g of foldInput) {
await this.storage.removeRawPrefix(`${GENERATIONS_PREFIX}/${g.generation}`)
}
folded += foldInput.length
}
if (folded > 0) {
prodLog.info(

View file

@ -76,11 +76,6 @@ export class VirtualFileSystem implements IVirtualFileSystem {
* `_system/`, like every other marker there never enumerated as data.
*/
private static readonly ROOT_SWEEP_MARKER_PATH = '_system/vfs-root-sweep.json'
/**
* Below this wall, a sweep that removed nothing says nothing see
* {@link sweepOldRootsIfNeeded}.
*/
private static readonly ROOT_SWEEP_NARRATE_MS = 1_000
private currentUser: string = 'system' // Track current user for collaboration
// Knowledge Layer features available via augmentation (brain.use('knowledge'))
@ -439,31 +434,21 @@ export class VirtualFileSystem implements IVirtualFileSystem {
} catch {
// Unreadable marker: sweep, and rewrite it below.
}
// NARRATION HAS A THRESHOLD, like every other line this engine emits on the
// always-visible channel. On a fresh or small store this sweep finds
// nothing and costs a millisecond, and announcing it — twice — on a
// channel a production log level deliberately CANNOT silence would train
// operators to ignore the one channel that exists to be impossible to
// ignore. It speaks when it has something to say: duplicates removed, or a
// wall long enough that somebody watching a slow first open deserves to
// know what is running. Otherwise it does its work and stays quiet.
prodLog.narrate(
'[VFS] one-time sweep for pre-fixed-id root directories running in the background — ' +
'the open does not wait for it, and once it has run this store never sweeps again.'
)
const startedAt = Date.now()
const duplicatesRemoved = await this.cleanupOldRoots()
const elapsedMs = Date.now() - startedAt
await this.cleanupOldRoots()
try {
await store.writeRawObject(VirtualFileSystem.ROOT_SWEEP_MARKER_PATH, {
sweptAt: new Date().toISOString(),
durationMs: elapsedMs
durationMs: Date.now() - startedAt
})
if (duplicatesRemoved > 0 || elapsedMs >= VirtualFileSystem.ROOT_SWEEP_NARRATE_MS) {
prodLog.narrate(
`[VFS] one-time old-root sweep complete in ${elapsedMs}ms` +
(duplicatesRemoved > 0
? `, ${duplicatesRemoved} pre-fixed-id root(s) removed`
: '') +
' and recorded — no future open pays for it.'
)
}
prodLog.narrate(
`[VFS] old-root sweep complete in ${Date.now() - startedAt}ms and recorded — ` +
'no future open pays for it.'
)
} catch (error) {
// Unrecorded sweep = the next open sweeps again. Conservative, and said
// out loud rather than quietly repeated forever.
@ -510,8 +495,7 @@ export class VirtualFileSystem implements IVirtualFileSystem {
return null
}
private async cleanupOldRoots(): Promise<number> {
let removed = 0
private async cleanupOldRoots(): Promise<void> {
try {
// Find any old VFS roots with UUID-based IDs (not our fixed ID)
const oldRoots = await this.brain.find({
@ -533,7 +517,6 @@ export class VirtualFileSystem implements IVirtualFileSystem {
for (const duplicate of duplicates) {
try {
await this.brain.remove(duplicate.id)
removed++
console.log(`VFS: Deleted old root ${duplicate.id.substring(0, 8)}`)
} catch (error) {
console.warn(`VFS: Failed to delete old root ${duplicate.id}:`, error)
@ -546,7 +529,6 @@ export class VirtualFileSystem implements IVirtualFileSystem {
// Non-critical error - log and continue
console.warn('VFS: Cleanup of old roots failed (non-critical):', error)
}
return removed
}
/**

View file

@ -57,11 +57,7 @@ describe('entity-tree family stamp', () => {
const invariants = (stamp.members as any).invariants
expect(invariants.nounCount).toBe(await brain.storage.getNounCount())
expect(invariants.verbCount).toBe(await brain.storage.getVerbCount())
// THE SOURCE IS COMMITTED TRUTH, never the allocated counter. Stamping the
// counter labelled the stamp with a generation a write in flight had merely
// claimed, so every crash inside a write window produced a spurious verdict
// at the next open (see the torn-tail pins below).
expect(stamp.sourceGeneration).toBe(brain.generationStore.committedGeneration())
expect(stamp.sourceGeneration).toBe(brain.generation())
expect(stamp.generation).toBeGreaterThanOrEqual(1)
})
@ -116,96 +112,6 @@ describe('entity-tree family stamp', () => {
expect(stillIncoherent).toEqual([])
})
/**
* Rewrite the on-disk stamp so its `sourceGeneration` sits ABOVE the store's
* committed watermark the durable shape a torn generation-log tail leaves
* behind (the stamp's fsync outlived the tail's). Fabricated rather than
* crash-produced so the pin is deterministic; the seeded-SIGKILL lane
* (`scripts/crash-consistency.mjs` in the engine repo) produces the same
* shape from a real abrupt termination.
*/
const fabricateTear = (ahead: number): FamilyStamp => {
const file = path.join(dir, `${ENTITY_TREE_STAMP_PATH}.gz`)
const zlib = require('node:zlib')
const raw = JSON.parse(zlib.gunzipSync(fs.readFileSync(file)).toString('utf-8')) as FamilyStamp
const torn: FamilyStamp = { ...raw, sourceGeneration: raw.sourceGeneration + ahead }
fs.writeFileSync(file, zlib.gzipSync(JSON.stringify(torn)))
return torn
}
it('a torn generation-log tail is a TERMINAL VERDICT at open: narrated, demoted, never a wait', async () => {
for (let i = 0; i < 3; i++)
await brain.add({ data: `torn${i}`, type: 'document', metadata: { i } })
await brain.close()
const torn = fabricateTear(5)
const warn = vi.spyOn(prodLog, 'warn')
const startedAt = Date.now()
brain = await open()
const openMs = Date.now() - startedAt
const tearLines = warn.mock.calls.filter((c) => String(c[0]).includes('TORN GENERATION-LOG TAIL'))
expect(tearLines.length).toBe(1)
const said = String(tearLines[0][0])
// Narrated PRECISELY: both generations, the file, and the named cure.
expect(said).toContain(`source generation ${torn.sourceGeneration}`)
expect(said).toContain(`committed generation ${brain.generationStore.committedGeneration()}`)
expect(said).toContain(ENTITY_TREE_STAMP_PATH)
expect(said).toContain('DEMOTED')
expect(said).toMatch(/repairIndex\(\)/)
// Terminal, not a wait: the demotion is O(1) straight-line work, so a tear
// cannot turn an open into the 8-minute spin this class was reported as.
expect(openMs).toBeLessThan(30_000)
// The store SERVES — a tear in a stamp never locks an owner out of the
// canonical tree the stamp merely describes.
expect((await brain.find({ type: 'document', limit: 100 })).length).toBe(3)
// The demotion CONVERGED: the stamp now names committed truth, and the
// next open is quiet. A verdict that re-narrates every open is a wait
// wearing a different hat.
const restamped = (await readFamilyStamp(brain.storage, ENTITY_TREE_STAMP_PATH)) as FamilyStamp
expect(restamped.sourceGeneration).toBe(brain.generationStore.committedGeneration())
await brain.close()
const warn2 = vi.spyOn(prodLog, 'warn')
brain = await open()
expect(warn2.mock.calls.filter((c) => String(c[0]).includes('TORN'))).toEqual([])
})
it('a READ-ONLY open on a torn tail refuses to guess: terminal verdict + named cure, no re-stamp', async () => {
await brain.add({ data: 'ro', type: 'document', metadata: {} })
await brain.close()
const torn = fabricateTear(3)
const warn = vi.spyOn(prodLog, 'warn')
const reader: any = await Brainy.openReadOnly({
requireSubtype: false,
storage: { type: 'filesystem', path: dir },
silent: true,
dimensions: 384
})
const tearLines = warn.mock.calls.filter((c) => String(c[0]).includes('TORN GENERATION-LOG TAIL'))
expect(tearLines.length).toBe(1)
const said = String(tearLines[0][0])
expect(said).toContain('READ-ONLY')
expect(said).toContain('UNVERIFIED')
expect(said).toMatch(/repairIndex\(\)/)
await reader.close()
// A reader never rewrites the store: read the bytes back off disk (not
// through a writer open, which would demote them) — the torn stamp is
// exactly as it was found.
const onDisk = JSON.parse(
require('node:zlib')
.gunzipSync(fs.readFileSync(path.join(dir, `${ENTITY_TREE_STAMP_PATH}.gz`)))
.toString('utf-8')
) as FamilyStamp
expect(onDisk.sourceGeneration).toBe(torn.sourceGeneration)
expect(onDisk.generation).toBe(torn.generation)
brain = await open()
})
it('the one verifier handles both member modes', () => {
const rollup: FamilyStamp = {
family: 'x',
@ -221,13 +127,7 @@ describe('entity-tree family stamp', () => {
stampSource: 5,
head: 9
})
// AHEAD is its own class — a torn generation-log tail, never folded in
// with `incoherent`: the two have opposite cures (recount vs demote).
expect(verifyFamilyStamp(rollup, 3, { nounCount: 10 })).toEqual({
state: 'torn',
stampSource: 5,
head: 3
})
expect(verifyFamilyStamp(rollup, 3, { nounCount: 10 }).state).toBe('incoherent') // ahead of head
expect(verifyFamilyStamp(null, 5, {})).toEqual({ state: 'absent' })
const enumerated: FamilyStamp = {

View file

@ -188,7 +188,7 @@ describe('health gate (b) — unledgered is unknown: never blocks a serving prov
describe('health gate (c) — degraded-but-serving narrates once per generation', () => {
// PER-FAMILY LAW (10.4.1): a metadata find() consults the METADATA leg only — the
// degraded report lives on the family the read actually consults.
it('a heal:"repair" failure serves; narrates once per DISTINCT VERDICT, not once per generation bump', async () => {
it('a heal:"repair" failure serves; narrates once per generation, twice across a generation bump', async () => {
const brain = new Brainy(createTestConfig({ silent: true }))
await brain.init()
brains.push(brain)
@ -197,13 +197,12 @@ describe('health gate (c) — degraded-but-serving narrates once per generation'
const internals = internalsOf(brain)
let generation = 1
let detail = 'counter drift'
internals.metadataIndex.healthReport = () =>
healthReport({
provider: 'vector',
serving: true,
healthy: false,
invariants: [invariant({ name: 'stale-vector-counter', holds: false, heal: 'repair', detail })],
invariants: [invariant({ name: 'stale-vector-counter', holds: false, heal: 'repair', detail: 'counter drift' })],
generation
})
@ -213,22 +212,11 @@ describe('health gate (c) — degraded-but-serving narrates once per generation'
await expect(brain.find({ where: { team: 'atlas' } })).resolves.toHaveLength(1)
await expect(brain.find({ where: { team: 'atlas' } })).resolves.toHaveLength(1)
expect(countNarrations()).toBe(1) // same verdict both times — one narration
expect(countNarrations()).toBe(1) // same generation both times — one narration
// THE DEDUPE KEY IS THE VERDICT, NOT THE COUNTER. A provider's `generation`
// bumps on every ledger mutation and every rebuild boundary, so keying the
// narration on it re-printed an UNCHANGED health line on every read that
// consulted a busy provider — and, in the other direction, let a provider
// that never bumped suppress a line whose reasons had genuinely changed.
// An unchanged verdict is silent however the counter moves:
generation = 2
await expect(brain.find({ where: { team: 'atlas' } })).resolves.toHaveLength(1)
expect(countNarrations()).toBe(1) // generation bumped, verdict identical — still silent
// ...and a CHANGED verdict is always heard, bump or no bump:
detail = 'counter drift widened to 12 rows'
await expect(brain.find({ where: { team: 'atlas' } })).resolves.toHaveLength(1)
expect(countNarrations()).toBe(2) // the reasons changed — a new narration
expect(countNarrations()).toBe(2) // generation bumped — a second narration
delete internals.metadataIndex.healthReport
})

View file

@ -16,7 +16,6 @@ import { describe, it, expect, afterEach } from 'vitest'
import * as fs from 'node:fs'
import * as path from 'node:path'
import * as os from 'node:os'
import * as zlib from 'node:zlib'
import { Brainy } from '../../src/brainy.js'
import { NounType } from '../../src/types/graphTypes.js'
import { GenerationStore } from '../../src/db/generationStore.js'
@ -58,107 +57,6 @@ describe('history repacking — the two-tier lifecycle', () => {
}
})
/**
* THE HOLE, END TO END the shape a real store carries.
*
* A forensic fixture was measured with generation directories 1..2503
* present except for exactly one: 1416. Its fact-log segment already showed
* the tell `seg-...1410.bfl` declaring firstGeneration 1410, lastGeneration
* 1940 (531 generations) while recording only 530 facts.
*
* Before the fix, repacking such a store folded ACROSS that hole: the batch
* skipped 1416 (no readable delta) and the sealed segment declared a range
* spanning it anyway. The next open merged that declared range back into
* committedRanges, re-admitting 1416 as committed history, and every
* subsequent auto-compaction pass then asked the packed tier for a frame
* that was never written producing, on EVERY run, the non-fatal narration
*
* Auto-compaction of generational history failed (non-fatal): generation
* N is inside sealed segment seg-....bgs's declared range but has no frame
* packed history is damaged
*
* This pin removes a generation directory to make the same hole, then
* requires repack + reopen + compaction to complete cleanly.
*/
it('a missing generation directory does not poison the packed tier', async () => {
const dir = tempDir()
// `retention: 'all'` throughout: close() otherwise auto-compacts the
// history away, and this pin needs the cold generations still on disk so
// there is something to punch a hole in. The live window stays at its
// production default for the build phase, so nothing folds yet.
const archival = async (): Promise<Brainy> => {
const b = new Brainy({
requireSubtype: false,
storage: { type: 'filesystem', path: dir },
embeddingFunction: stub,
retention: 'all'
})
await b.init()
return b
}
const brain = await archival()
const id = await brain.add({
data: 'holed-entity',
type: NounType.Document,
metadata: { v: 0 }
})
// One flush per update: single-op writes coalesce inside a flush window,
// so a history deep enough to have a middle needs the windows separated.
for (let v = 1; v <= 12; v++) {
await brain.update({ id, metadata: { v } })
await brain.flush()
}
await brain.close()
// Punch the hole: delete ONE generation directory in the middle of the
// cold range, exactly as the real store presents it.
const genRoot = path.join(dir, '_generations')
const numeric = fs
.readdirSync(genRoot, { withFileTypes: true })
.filter((e) => e.isDirectory() && /^\d+$/.test(e.name))
.map((e) => Number(e.name))
.sort((a, b) => a - b)
expect(numeric.length).toBeGreaterThan(6)
const victim = numeric[Math.floor(numeric.length / 2)]
fs.rmSync(path.join(genRoot, String(victim)), { recursive: true, force: true })
// Now shrink the live window and reopen. close() repacks automatically
// (brainy.ts phase 0b), so this is the production sequence exactly: a
// store with a hole in its history gets folded by ordinary housekeeping,
// with nobody asking for it.
;(GenerationStore as any).REPACK_LIVE_WINDOW = 3
const reopened = await archival()
const result = await reopened.repackHistory()
expect(result.foldedGenerations).toBeGreaterThan(0)
const segDir = path.join(dir, SEGMENTS_PREFIX)
const manifestPath = ['manifest.json', 'manifest.json.gz']
.map((f) => path.join(segDir, f))
.find((p) => fs.existsSync(p))!
const raw = manifestPath.endsWith('.gz')
? zlib.gunzipSync(fs.readFileSync(manifestPath)).toString('utf8')
: fs.readFileSync(manifestPath, 'utf8')
const manifest = JSON.parse(raw) as {
segments: Array<{ firstGeneration: number; lastGeneration: number; frames: number }>
}
// THE LAW: every sealed segment declares exactly as many generations as it
// holds frames, and none of them spans the victim.
for (const s of manifest.segments) {
expect(s.lastGeneration - s.firstGeneration + 1).toBe(s.frames)
expect(victim >= s.firstGeneration && victim <= s.lastGeneration).toBe(false)
}
await reopened.close()
// And the pass that used to fail on every run now completes: reopen (which
// re-seeds committedRanges from the packed tier) then compact history.
const third = await openBrain(dir)
await expect(third.compactHistory({ maxGenerations: 2 })).resolves.toBeDefined()
await third.close()
})
it('repack preserves every historical read across cold reopen; folded dirs are gone', async () => {
;(GenerationStore as any).REPACK_LIVE_WINDOW = 3
const dir = tempDir()

View file

@ -21,16 +21,10 @@ describe('Hybrid Search with VFS', () => {
testDir = path.join(os.tmpdir(), `brainy-hybrid-vfs-test-${Date.now()}`)
fs.mkdirSync(testDir, { recursive: true })
// `storage.path`, NOT the pre-8.0 `options.basePath` alias. That alias was
// removed at the 8.0 major and configures nothing, so this suite silently
// opened the DEFAULT store instead of its own temp directory — sharing one
// on-disk brain with every other run on the machine, accumulating tens of
// thousands of rows, and eventually failing on that shared store's graph
// adjacency rather than on anything it was written to test.
brain = new Brainy({ requireSubtype: false,
storage: {
type: 'filesystem',
path: testDir
options: { basePath: testDir }
}
})
await brain.init()

View file

@ -20,7 +20,6 @@ import { join } from 'node:path'
import { Brainy } from '../../src/brainy.js'
import { NounType } from '../../src/types/graphTypes.js'
import { VirtualFileSystem } from '../../src/vfs/VirtualFileSystem.js'
import { prodLog } from '../../src/utils/logger.js'
describe('the VFS old-root sweep', () => {
const dirs: string[] = []
@ -81,32 +80,6 @@ describe('the VFS old-root sweep', () => {
expect(sweepSpy).not.toHaveBeenCalled()
}, 180_000)
it('a sweep that removes nothing on a fresh store says nothing', async () => {
const dir = mkdtempSync(join(tmpdir(), 'brainy-root-sweep-quiet-'))
dirs.push(dir)
// The always-visible channel cannot be silenced by a log level, so a line
// on it has to earn its place. A fresh store's sweep finds no duplicate
// roots and costs a millisecond — it must do its work, record its marker,
// and stay quiet, or it trains operators to ignore the one channel that
// exists to be impossible to ignore.
const narrated: string[] = []
const spy = vi.spyOn(prodLog, 'narrate').mockImplementation(((...args: unknown[]) => {
narrated.push(args.map((a) => String(a)).join(' '))
}) as typeof prodLog.narrate)
const brain = await open(dir)
await (brain.vfs as unknown as { whenRootSweepSettled: () => Promise<void> }).whenRootSweepSettled()
spy.mockRestore()
expect(narrated.filter((l) => /old-root sweep/i.test(l))).toEqual([])
// ...and it still did the work: the marker is recorded, so no future open sweeps.
expect(
existsSync(join(dir, '_system', 'vfs-root-sweep.json')) ||
existsSync(join(dir, '_system', 'vfs-root-sweep.json.gz'))
).toBe(true)
}, 180_000)
it('the open does not wait for the sweep', async () => {
const dir = mkdtempSync(join(tmpdir(), 'brainy-root-sweep-async-'))
dirs.push(dir)

View file

@ -147,119 +147,4 @@ describe('db/GenerationSegmentStore — the D1+D3 packed tier', () => {
await expect(store.fold([gen(4), gen(4)])).rejects.toThrow(/strictly ascending/)
await expect(store.fold([])).rejects.toThrow(/at least one generation/)
})
// ==========================================================================
// THE DENSITY LAW
// ==========================================================================
//
// A sealed segment declares a CONTIGUOUS range and every reader treats that
// range as containment. Folding a sparse batch therefore makes the segment
// claim generations it does not hold — and because `open()` merges declared
// ranges back into committedRanges, the hole is re-admitted as committed
// history and every later maintenance pass fails asking for a frame that was
// never written. That is the "generation N is inside sealed segment
// seg-....bgs's declared range but has no frame — packed history is damaged"
// narration seen on every run of the affected stores.
it('fold REFUSES a batch with a hole — a dense range may not be declared over sparse input', async () => {
await expect(store.fold([gen(1), gen(2), gen(4)])).rejects.toThrow(
/not contiguous: 2 → 4 skips 1 generation/
)
// The refusal loses nothing: no segment was sealed, so the generations
// stay in the live tier and the next pass folds them correctly.
expect(store.segments()).toHaveLength(0)
expect(store.hasGeneration(1)).toBe(false)
})
it('a wider gap names how many generations it would have swallowed', async () => {
await expect(store.fold([gen(10), gen(20)])).rejects.toThrow(
/not contiguous: 10 → 20 skips 9 generation\(s\)/
)
})
it('two contiguous runs folded separately declare honest ranges', async () => {
// What the caller now does instead of folding across the gap.
const a = await store.fold([gen(1), gen(2), gen(3)])
const b = await store.fold([gen(7), gen(8)])
expect(a).toMatchObject({ firstGeneration: 1, lastGeneration: 3, frames: 3 })
expect(b).toMatchObject({ firstGeneration: 7, lastGeneration: 8, frames: 2 })
// The gap is honestly outside the packed tier.
for (const g of [4, 5, 6]) expect(store.hasGeneration(g)).toBe(false)
for (const g of [1, 2, 3, 7, 8]) expect(store.hasGeneration(g)).toBe(true)
expect(await store.actualRanges()).toEqual([
[1, 3],
[7, 8]
])
})
it('actualRanges() is exact and I/O-free for dense segments', async () => {
await store.fold([gen(1), gen(2)])
await store.fold([gen(3), gen(4)])
// Adjacent dense segments each contribute their declared range.
expect(await store.actualRanges()).toEqual([
[1, 2],
[3, 4]
])
})
// ---- pre-existing damage: a store sealed by the old writer ----------------
/**
* Seal a SPARSE segment the way the pre-fix writer did: write the bytes and
* sidecar for a contiguous run, then rewrite the manifest so the segment
* declares a wider range than the frames it holds. This reproduces on disk
* exactly what the affected stores carry, without needing the old code.
*/
const sealSparseSegment = async (): Promise<void> => {
await store.fold([gen(1), gen(2), gen(3)])
const manifest = (await storage.readRawObject(`${SEGMENTS_PREFIX}/manifest.json`)) as any
// Declare 1..5 while holding frames for 1..3 — generations 4 and 5 become
// holes inside a sealed range.
manifest.segments[0].lastGeneration = 5
await storage.writeRawObject(`${SEGMENTS_PREFIX}/manifest.json`, manifest)
}
it('a pre-existing sparse segment reports its holes as UNPACKED, not as damage', async () => {
await sealSparseSegment()
const reopened = new GenerationSegmentStore(storage as any)
await reopened.open()
// The frames it really holds still serve, byte-faithfully.
expect((await reopened.readDelta(2))?.timestamp).toBe(1_700_000_000_002)
expect(await reopened.readRecords(3)).toHaveLength(2)
// The holes answer "not packed" instead of throwing. This is the fix for
// the wedge: the old reader threw here on EVERY maintenance pass.
expect(await reopened.readDelta(4)).toBeNull()
expect(await reopened.readRecords(5)).toBeNull()
})
it('actualRanges() excludes the holes so they are never re-admitted as committed', async () => {
await sealSparseSegment()
const reopened = new GenerationSegmentStore(storage as any)
await reopened.open()
// Declared 1..5; actually holds 1..3. The store seeds committedRanges from
// THIS, so generations 4 and 5 never become committed history again.
expect(await reopened.actualRanges()).toEqual([[1, 3]])
})
it('a DENSE segment missing a frame is still loud damage', async () => {
// The other side of the branch: when the manifest claims a complete span,
// a missing frame means the manifest and sidecar disagree — real damage,
// and it must not be quietly downgraded to "unpacked".
await store.fold([gen(1), gen(2), gen(3)])
const idxPath = `${SEGMENTS_PREFIX}/seg-${String(1).padStart(20, '0')}.idx`
const raw = (await storage.readRawBytes(idxPath))!
const { decode, encode } = await import('@msgpack/msgpack')
const idx = decode(raw) as any
// Drop generation 2's entry while the manifest still declares 3 frames.
idx.generations = idx.generations.filter(([g]: [number]) => g !== 2)
await storage.writeRawBytes(idxPath, encode(idx))
const reopened = new GenerationSegmentStore(storage as any)
await reopened.open()
await expect(reopened.readDelta(2)).rejects.toThrow(
/manifest and the sidecar disagree; packed history is damaged/
)
})
})