diff --git a/.claude/skills/architecture.md b/.claude/skills/architecture.md index de046b17..4de3c287 100644 --- a/.claude/skills/architecture.md +++ b/.claude/skills/architecture.md @@ -2,7 +2,7 @@ ## What Is Brainy -@soulcraft/brainy (v7.17.0) is a Universal Knowledge Protocol -- a Triple Intelligence database combining vector search, graph traversal, and metadata filtering in a single library. Published to npm as a public MIT-licensed package. +@soulcraftlabs/brainy (v7.17.0) is a Universal Knowledge Protocol -- a Triple Intelligence database combining vector search, graph traversal, and metadata filtering in a single library. Published to npm as a public MIT-licensed package. ## Core Architecture diff --git a/.forgejo/workflows/publish-source.yml b/.forgejo/workflows/publish-source.yml index a08875ae..58cb1d30 100644 --- a/.forgejo/workflows/publish-source.yml +++ b/.forgejo/workflows/publish-source.yml @@ -32,7 +32,7 @@ jobs: run: | set -eo pipefail - SOURCE_NPM_REG="https://source.soulcraft.com/api/packages/soulcraft/npm/" + SOURCE_NPM_REG="https://source.soulcraft.com/api/packages/soulcraftlabs/npm/" VERSION="$(node -p "require('./package.json').version")" # The dist-tag follows the version: a prerelease (any hyphen — # 10.4.0-rc.1) publishes under 'rc' and must NEVER move 'latest' — @@ -43,13 +43,13 @@ jobs: case "$VERSION" in *-*) NPM_TAG="rc" ;; esac - echo "Publishing @soulcraft/brainy@${VERSION} to The Source registry (dist-tag: ${NPM_TAG})..." + echo "Publishing @soulcraftlabs/brainy@${VERSION} to The Source registry (dist-tag: ${NPM_TAG})..." TMPRC="$(mktemp)" chmod 600 "$TMPRC" { - echo "@soulcraft:registry=${SOURCE_NPM_REG}" - echo "//source.soulcraft.com/api/packages/soulcraft/npm/:_authToken=${FORGE_NPM_TOKEN}" + echo "@soulcraftlabs:registry=${SOURCE_NPM_REG}" + echo "//source.soulcraft.com/api/packages/soulcraftlabs/npm/:_authToken=${FORGE_NPM_TOKEN}" } > "$TMPRC" # The release script bumps package.json's version before it tags, so @@ -64,7 +64,7 @@ jobs: # exit code: a benign duplicate publish (a prior run, or a mirror, already # landed this exact version) reports failure even though the registry # already holds the right content. - LANDED_VERSION="$(npm view "@soulcraft/brainy@${VERSION}" version --userconfig "$TMPRC" 2>/dev/null || echo "")" + LANDED_VERSION="$(npm view "@soulcraftlabs/brainy@${VERSION}" version --userconfig "$TMPRC" 2>/dev/null || echo "")" rm -f "$TMPRC" if [ "$LANDED_VERSION" != "$VERSION" ]; then @@ -73,7 +73,7 @@ jobs: fi if [ "$PUBLISH_OK" = true ]; then - echo "Published and verified @soulcraft/brainy@${VERSION} on The Source registry." + echo "Published and verified @soulcraftlabs/brainy@${VERSION} on The Source registry." else - echo "::warning::npm publish reported failure, but readback confirms @soulcraft/brainy@${VERSION} is already live on The Source (a prior run or mirror landed it) — treating this run as successful, since the registry content is correct. Any OTHER failure mode would have failed the readback check above instead." + echo "::warning::npm publish reported failure, but readback confirms @soulcraftlabs/brainy@${VERSION} is already live on The Source (a prior run or mirror landed it) — treating this run as successful, since the registry content is correct. Any OTHER failure mode would have failed the readback check above instead." fi diff --git a/CHANGELOG.md b/CHANGELOG.md index ec925642..a54d609e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,23 +2,81 @@ 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. -### [10.4.1](https://source.soulcraft.com/soulcraft/brainy/compare/v10.4.0...v10.4.1) (2026-08-26) +### [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) +- chore: rename to @soulcraftlabs/brainy for Open Brainy on The Source (a99b1e83) +- docs(releases): 10.4.3 — Open Brainy's first release under the new name, same engine as 10.4.2; The Source is the one registry (9f248b24) + + +### [10.4.2](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.4.2-rc.1...v10.4.2) (2026-08-27) + +- docs(releases): 10.4.1 and 10.4.2 consumer notes; 10.4.2 is the last MIT release under this name, Open Brainy continues at @soulcraftlabs/brainy (a082e0ef) + + +### [10.4.2-rc.1](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.4.1...v10.4.2-rc.1) (2026-08-27) + +- Merge branch 'next/zero-norm-unvector-door' (9b84ef5b) +- fix(vectors): a zero-norm vector is not a vector, canonical side included, plus the sanctioned unvector door (0de76659) +- fix(hnsw): skip unvectored rows on rebuild; refuse empty vectors in the index (8fc553b1) +- fix(storage): derive the canonical count ledger from identity records, stamp the derivation rule, and mark legacy-derived ledgers suspect at load (fd6b4ce4) +- Merge branch 'next/enumeration-identity-rekey' (204d74c1) +- fix(storage): enumeration re-keys on the identity record, not the vector leg (f8d8ce16) +- fix(init): rethrow plugin activation failures with the original error as cause so the originating frame survives to the caller (2496e09a) +- Merge branch 'next/vfs-root-zero-norm' (4c7b0fab) +- fix(vfs): the VFS root never persists a zero-norm vector (c6cc0de9) +- build: derive generated-file stamps from git commit time, not wall clock (8a5c1245) +- Merge remote-tracking branch 'origin/release/10.4.1' (aad9e2ee) +- docs(concepts): the serving law — a failure is graded by whether an answer could be wrong, never by the cost of the fix; reads refuse per family (2914e0eb) +- chore(release): 10.4.1-rc.1 (7870dc40) + + +### [10.4.1](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.4.0...v10.4.1) (2026-08-26) - fix(reads): the read gate is per-family; a write carrying unchanged data never re-embeds (c039411e) - docs(guide): the docs pipeline publishes through the ingest API — the separate deploy step is retired (21e506e8) -### [10.4.0](https://source.soulcraft.com/soulcraft/brainy/compare/v10.4.0-rc.4...v10.4.0) (2026-08-26) +### [10.4.0](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.4.0-rc.4...v10.4.0) (2026-08-26) - docs(releases): the 10.4.0 entry catches up to the late trains — repair routing, the vector ledger and open-gate leg, the loud config guard, the JSON-safe crossing (834149ed) -### [10.4.0-rc.4](https://source.soulcraft.com/soulcraft/brainy/compare/v10.4.0-rc.3...v10.4.0-rc.4) (2026-08-25) +### [10.4.0-rc.4](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.4.0-rc.3...v10.4.0-rc.4) (2026-08-25) - feat(vector): the vectored-noun scalar joins the count ledger; the open gate closes the vector leg (9730835b) -### [10.4.0-rc.3](https://source.soulcraft.com/soulcraft/brainy/compare/v10.4.0-rc.2...v10.4.0-rc.3) (2026-08-25) +### [10.4.0-rc.3](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.4.0-rc.2...v10.4.0-rc.3) (2026-08-25) - fix(update-seam): the metadata crossing never carries BigInt endpoint ints (f4780c8e) - Merge branch 'worktree-agent-ad3aff0dffd17a6eb' (f14da34b) @@ -27,7 +85,7 @@ All notable changes to this project will be documented in this file. See [standa - feat(open-path): init never gates on the embedding model; open goes concurrent; slow opens narrate (96624f40) -### [10.4.0-rc.2](https://source.soulcraft.com/soulcraft/brainy/compare/v10.4.0-rc.1...v10.4.0-rc.2) (2026-08-25) +### [10.4.0-rc.2](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.4.0-rc.1...v10.4.0-rc.2) (2026-08-25) - test(readiness): the report helper's clock freezes — two independently-built reports compared across a millisecond tick made the plant lane red (39b916a3) - feat(repair): a heal:'repair' verdict routes to the provider's own incremental repair() (553e0d97) @@ -38,7 +96,7 @@ All notable changes to this project will be documented in this file. See [standa - feat(health): the gate reads the named report — reads refuse loudly, never rebuild; open serves before it returns; the ceremony door (f8f64780) -### [10.4.0-rc.1](https://source.soulcraft.com/soulcraft/brainy/compare/v10.3.1...v10.4.0-rc.1) (2026-08-24) +### [10.4.0-rc.1](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.3.1...v10.4.0-rc.1) (2026-08-24) - ci(publish): the home dist-tag follows the version — a prerelease publishes under 'rc' and never moves 'latest' (a1376e4a) - chore(release): --source-only — a home-only prerelease mode (The Source, never the storefront) (dcbad176) @@ -51,13 +109,13 @@ All notable changes to this project will be documented in this file. See [standa - ci(gate): the machine-health preflight and the truncation verdict guard (1e046aa1) -### [10.3.1](https://source.soulcraft.com/soulcraft/brainy/compare/v10.3.0...v10.3.1) (2026-08-18) +### [10.3.1](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.3.0...v10.3.1) (2026-08-18) - docs(releases): the 10.3.1 consumer entry — the fold that behaves (900cc895) - fix(recovery): the fold streams and narrates; the checkpoint chain arms at the flip (ed7d1db9) -### [10.3.0](https://source.soulcraft.com/soulcraft/brainy/compare/v10.2.0...v10.3.0) (2026-08-18) +### [10.3.0](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.2.0...v10.3.0) (2026-08-18) - docs(releases): the 10.3.0 consumer entry — the trust-and-provenance release (97d75649) - fix(locks): the fence keys ownership on pid+hostname — a same-process re-open never fences its predecessor (0991cf28) @@ -66,14 +124,14 @@ All notable changes to this project will be documented in this file. See [standa - feat(log): system commits carry their origin; the attested per-id reconcile door (9ac9e706) -### [10.2.0](https://source.soulcraft.com/soulcraft/brainy/compare/v10.1.0...v10.2.0) (2026-08-17) +### [10.2.0](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.1.0...v10.2.0) (2026-08-17) - docs(releases): the 10.2.0 consumer entry — adoption completes in one call (97538e1f) - ci: the correctness plant runs integration + conformance on every push — a release never waits on a second machine (b17fdc8e) - fix(adoption): the baseline backfill runs to completion — one call adopts a pre-log baseline of any size (a5a18838) -### [10.1.0](https://source.soulcraft.com/soulcraft/brainy/compare/v10.0.0...v10.1.0) (2026-08-13) +### [10.1.0](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v10.0.0...v10.1.0) (2026-08-13) - docs(releases): the 10.1.0 consumer entry — bounded recovery, restore founding, the two write-path cures (7d3c8696) - fix(restore): a restore is an unclean event — the swap runs quiesced and the snapshot's durability stamps never survive it (9ca80667) @@ -82,7 +140,7 @@ All notable changes to this project will be documented in this file. See [standa - feat(query): the sparse-store cut — where on a never-carried field serves operator truth, never a refusal (7b67db4d) -### [10.0.0](https://source.soulcraft.com/soulcraft/brainy/compare/v9.0.0...v10.0.0) (2026-08-12) +### [10.0.0](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v9.0.0...v10.0.0) (2026-08-12) - fix(adoption): the baseline backfill cures hydration-law drift — existing brains reach the crash-safe default with zero operator steps (25f0dd96) - fix(adoption): the reserved-root mint exemption — int 0 is legitimate for exactly one id (2abe8b38) @@ -114,7 +172,7 @@ All notable changes to this project will be documented in this file. See [standa - test: version-coupling pins go major-agnostic — the 8.x literals broke at the 9.0.0 bump while the coupling law itself behaved correctly (8a6807e8) -### [9.0.0](https://source.soulcraft.com/soulcraft/brainy/compare/v8.11.0...v9.0.0) (2026-08-04) +### [9.0.0](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v8.11.0...v9.0.0) (2026-08-04) - docs: 9.0 namespace-migration guide — the simple story + the mechanical sweep checklist, published for humans and tooling alike (61ab9db2) - fix(release): storefront leg republishes CI's exact forge artifact — byte-identity by construction, verified by cross-registry shasum before the ceremony reports success (d89df2ed) @@ -149,7 +207,7 @@ All notable changes to this project will be documented in this file. See [standa - feat: scanFacts liveness contract — first batch or loud failure within a documented bound (f8e6da2b) -### [8.11.0](https://source.soulcraft.com/soulcraft/brainy/compare/v8.10.1...v8.11.0) (2026-07-27) +### [8.11.0](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v8.10.1...v8.11.0) (2026-07-27) - docs: the last two archived-host links point home (91ef1c8b) - feat: includeHidden — export carries every visibility tier for migration-grade canon completeness (63c1eeb9) @@ -158,19 +216,19 @@ All notable changes to this project will be documented in this file. See [standa - ci: run the pipeline on the forge (999d0ebb) -### [8.10.3](https://source.soulcraft.com/soulcraft/brainy/compare/v8.10.2...v8.10.3) (2026-08-03) +### [8.10.3](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v8.10.2...v8.10.3) (2026-08-03) - docs: dedupe the 8.10.2 release-notes entry the cherry doubled onto the branch (8c956608) - fix: user metadata named 'level' is a real field everywhere — the engine-internal node layer no longer shadows it in sort/filter/aggregation, and the indexing views stop stamping a phantom 0 into its column; index epoch 2 rebuilds existing brains at first open (958a0859) -### [8.10.2](https://source.soulcraft.com/soulcraft/brainy/compare/v8.10.1...v8.10.2) (2026-07-29) +### [8.10.2](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v8.10.1...v8.10.2) (2026-07-29) - docs: 8.10.2 consumer release notes — update() write granularity, PathResolver idle-log fix, graph-lsm key recognition (a0123b5b) - fix: metadata-only update() never rewrites the noun record — the unconditional whole-vector save turned per-entity stat touches into full rewrites+fsync, amplifying read-heavy sweeps into disk saturation on a production deployment (5b65eb82) -### [8.10.1](https://source.soulcraft.com/soulcraft/brainy/compare/v8.10.0...v8.10.1) (2026-07-24) +### [8.10.1](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v8.10.0...v8.10.1) (2026-07-24) - refactor: remove the orphaned transaction-result type left behind by the dead-path removal (edf123a5) - fix: warm() metadata surface routes through the active provider (warm hook added to the metadata contract); add maintenanceDebt() observability surface (5b2cbf74) diff --git a/CLAUDE.md b/CLAUDE.md index 6acd0e0d..56df0b72 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -12,13 +12,13 @@ Handoff file: `/home/dpsifr/.strategy/PLATFORM-HANDOFF.md` **Brainy's current open actions:** None. MIT open-source — no platform-specific actions. -**Current version:** run `npm view @soulcraft/brainy version` (never trust a hardcoded number here — this line went stale for months); consumer-facing changes tracked in `RELEASES.md` +**Current version:** run `npm view @soulcraftlabs/brainy version --registry https://source.soulcraft.com/api/packages/soulcraftlabs/npm/` (never trust a hardcoded number here — this line went stale for months); consumer-facing changes tracked in `RELEASES.md` --- ## Project Overview -Brainy is a Universal Knowledge Protocol -- a Triple Intelligence database that combines vector similarity search, graph traversal, and metadata filtering into a single TypeScript library. Published as `@soulcraft/brainy` on npm under the MIT license. +Brainy is a Universal Knowledge Protocol -- a Triple Intelligence database that combines vector similarity search, graph traversal, and metadata filtering into a single TypeScript library. Published as `@soulcraftlabs/brainy` on The Source (source.soulcraft.com registry) under the MIT license. ## Getting Started diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index d277091d..54d4f784 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -6,7 +6,7 @@ may find elsewhere in the repo's history. ## Where the project lives -The source of truth is a self-hosted forge: **source.soulcraft.com/soulcraft/brainy**. +The source of truth is a self-hosted forge: **source.soulcraft.com/soulcraftlabs/open-brainy**. It's anonymously readable and cloneable — no account needed to browse, clone, or build. @@ -31,7 +31,7 @@ fine) to talk through the approach saves everyone rework. ## Development setup ```bash -git clone https://source.soulcraft.com/soulcraft/brainy.git +git clone https://source.soulcraft.com/soulcraftlabs/open-brainy.git cd brainy npm install npm run build @@ -57,6 +57,17 @@ see `package.json` for `test:integration`, `test:coverage`, and friends. description states a number, cite the benchmark that produced it (see [docs/performance-envelopes.md](docs/performance-envelopes.md) for the pattern). Don't state an estimate as if it were measured. +- **Measurements carry numbers, not provenance.** Public commit messages and + docs give the SHAPE a number was taken at and never where it was taken: no + hostnames, no store or deployment identities, no operational anecdotes about + someone's running system. "A 14,056-noun / 72,679-verb production-shaped + store, measured solo under an exclusive lock" tells a reader everything the + number depends on; the machine it ran on and whose data it was tell them + nothing except where somebody's infrastructure lives. +- **Documents that answer or reference a confidential specification never enter + this repository, even summarized.** The public docs describe THIS engine and + the published contract, and nothing else — a summary of a private document is + still that document's contents. ## License diff --git a/README.md b/README.md index ca558340..762c9ec3 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,5 @@

- Brainy + Brainy

Brainy

@@ -11,9 +11,9 @@

- npm version - npm downloads - CI + Package on The Source + Repository + CI Documentation MIT License TypeScript @@ -30,6 +30,8 @@ --- +**Open Brainy** is the MIT engine — the open API, client library, types, and protocol; an openly specified canonical on-disk format; and this TypeScript reference engine, scoped as a single-node engine for stores up to roughly one million rows. `@soulcraft/brainy` 10.4.2 was the last release under the old package name — the name passes to the native engine, **Brainy**, at 11.0.0: the same API over the same open format at production scale, and it requires a license. + Built because we were tired of stitching a vector store to a graph database to a document store — and spending weeks on plumbing before writing a line of business logic. Brainy indexes every fact **three ways at once** and lets one call query them together: | You write | Brainy indexes it as | You query it with | @@ -45,12 +47,14 @@ It runs **inside your process** — no server, no Docker, nothing to operate — ## Quick start ```bash -bun add @soulcraft/brainy # Bun ≥ 1.1 — recommended -npm install @soulcraft/brainy # Node.js ≥ 22 +bun add @soulcraftlabs/brainy # Bun ≥ 1.1 — recommended +npm install @soulcraftlabs/brainy # Node.js ≥ 22 ``` +> **Registry**: add `@soulcraftlabs:registry=https://source.soulcraft.com/api/packages/soulcraftlabs/npm/` to your `.npmrc` (anonymous read). + ```javascript -import { Brainy, NounType, VerbType } from '@soulcraft/brainy' +import { Brainy, NounType, VerbType } from '@soulcraftlabs/brainy' const brain = new Brainy() // in-memory; one line swaps to disk await brain.init() diff --git a/RELEASES.md b/RELEASES.md index bc400412..e8833b80 100644 --- a/RELEASES.md +++ b/RELEASES.md @@ -1,7 +1,7 @@ # @soulcraft/brainy — Release Notes for Consumers This file is the **quick reference for downstream sessions** tracking Brainy changes. -Full auto-generated changelog: `CHANGELOG.md` · Releases: https://source.soulcraft.com/soulcraft/brainy/releases +Full auto-generated changelog: `CHANGELOG.md` · Releases: https://source.soulcraft.com/soulcraftlabs/open-brainy/releases **How to use:** Brainy is the underlying data engine for downstream applications. Read this when: - Upgrading `@soulcraft/brainy` in your application @@ -31,6 +31,227 @@ is sometimes cited as a 7.x removal — those methods never existed on 7.x; the --- +## v10.4.4 — 2026-08-28 + +**A correctness and observability release.** The headline is not speed: it is that a +restart now tells you the truth about itself, a store stops lying about how much it +holds, and the engine stops doing work nobody asked for. There is a performance +improvement and it is modest; it is stated exactly below rather than rounded up. + +### The dark restart — fixed at the root + +A service could stop cleanly, exit 0, having awaited `close()` on every store it held, +and its next boot would announce `Overwriting stale writer lock … appears dead` for +every one of them. Nothing had crashed. Two deployments hit this; the same defect also +made those boots pay a crash-recovery fold they did not owe. + +The cause was not the lock. `close()` released it correctly — when it got there. A +failure part-way through close skipped both the release AND the clean-shutdown marker, +and "the recorded pid is gone" reads identically for an orderly restart and a crash. + +- `close()` is now two parts and the second is unconditional: the flush-request watcher, + the **writer lock**, the VFS timers and the terminal `closed` flag are released whether + the durable steps succeeded or not. The original failure is narrated with what it costs + the next open, then rethrown. +- Releasing the lock writes a **clean-close record** naming the lock generation it gave + up. The next open reads that record instead of guessing: recorded → nothing to recover; + absent → it says so, and names the recovery it is about to run. This also ends two + long-standing false alarms — a recycled pid locking a store out of its own reopen, and + `Re-acquiring writer lock … this is a bug` after a perfectly clean close. +- The signal path stopped failing in a batch. One store's failing flush used to strand + every remaining store's lock and markers — at exit code 0. Now: per-store isolation, the + generation store's close (the marker) is part of shutdown, the lock goes in a `finally`, + and the handler no longer calls `process.exit()` when the host application has its own + signal handler, a race that truncated the host's own shutdown mid-flight. + +### The count ledger stops lying, and `counts.json` is written atomically + +The all-tier scalars are the denominator a coverage check subtracts against. A ledger +derived under the old rule — one entity per id DIRECTORY — counted ghost and scar +containers as rows, and was only FLAGGED suspect: it went on serving wrong numbers for +the life of the store. Two copies of one archive could disagree, and a downstream index +heal reported remaining work that did not exist. + +- Such a ledger now derives itself honestly **in the background** after the open, counting + identity records, and persists the correction stamped. Nothing waits for it, because no + read is served from a denominator. +- A derivation that raced a write refuses to stamp its number: one retry on a quiet store, + then the ledger stays SUSPECT and names `repairIndex()` as the door that recounts under + a barrier. +- `counts.json` is written temp+rename. A truncating write left a window in which a + concurrent reader saw the file EMPTY — and an unparseable ledger sends the next open + down the full-rescan path, so the cheapest file in the store was buying the most + expensive recovery. + +### An open and a repair narrate themselves — on a channel a log level cannot silence + +A store could open for three minutes and print nothing at all. The phase timings existed; +they were written to a channel that every production-looking environment clamps away. + +- Narration moved to an always-visible channel. An open now heartbeats the phase it is in, + names each phase as it ends with what it was paying for, and names the expensive STEP + inside a phase. `repairIndex()` does the same and its receipt carries a per-family + `durationMs` — a repair that ran for half an hour with no output could only be watched + through `top`. +- A brain nobody has written to now does nothing: a flush over a clean store is a no-op + and says nothing, the graph index's auto-flush asks before it acts, and the + cross-process flush-request watch is **event-driven** (`fs.watch`) instead of polling a + directory every 500 ms per store forever, with a slow safety sweep behind it and a + narrated fall back to polling where a filesystem cannot be watched. +- A provider that is REBUILDING ITSELF is no longer confused with a broken one. `init()` + does not wait for it, every other family serves, and that family's doors refuse **by + name, carrying the provider's own progress**, saying plainly that they open by + themselves and no action is needed. Health narration dedupes by content, so an unchanged + verdict is silent however a provider's generation counter moves. + +### For operators — one behaviour change + +**Four `where` operators that previously returned an empty page now raise +`INVALID_QUERY`:** `startsWith`, `endsWith`, `matches` and `length`. An equality/range +posting index cannot evaluate a substring, a pattern or an array length without reading +every row, and it now refuses by name instead of answering with an empty result that +looks like an answer. + +**Three that previously returned an empty page are now SERVED:** `hasAll`, `noneOf` and +`excludes`. All 25 accepted operator tokens now agree between this engine and its +accelerated counterpart. + +### Performance — stated exactly + +Measured on a 14,056-noun / 72,679-verb production-shaped store, both builds solo under +an exclusive lock: + +- **Warm reopen after a clean close: 85.7 s → 77.0 s (−10.2%).** The whole of that gain is + one fix — generation discovery reads directory NAMES instead of recursively walking the + entire generation log (−9.2 s, and it scales with history rather than row count). The + VFS phase is **unchanged**. +- **Cold open: −31.4 s** (518.1 s → 486.7 s), of which the count-ledger derivation moving + off the critical path accounts for storage-init dropping 5,941 ms → 25 ms. +- **A dominant ~38 s remains, diagnosed and NOT fixed.** It is not the VFS — the VFS's own + init is under 2 s of that phase. It is the log-authority adoption and/or the + pending-embed log recovery, both now instrumented so the next measurement names the + culprit outright. + +Continuing work, named so nobody has to rediscover it: that ~38 s term; making the +generation store's committed-range set lazy; the hydration path that substitutes +`Date.now()` for an unreadable stored timestamp (inventing data); and a VFS path-prefix +filter built with a `$startsWith` spelling no operator set accepts, so +`searchFiles({ path })` throws today. + +--- + +## v10.4.3 — 2026-08-27 (Open Brainy's first release) + +**`@soulcraftlabs/brainy` 10.4.3 is the same engine as `@soulcraft/brainy` 10.4.2, byte for +byte — only the name, the registry, and the pointers changed.** Install: + +```bash +npm install @soulcraftlabs/brainy +``` + +with the registry line in your `.npmrc` (anonymous read): + +``` +@soulcraftlabs:registry=https://source.soulcraft.com/api/packages/soulcraftlabs/npm/ +``` + +- **The Source is the one registry.** Open Brainy publishes to source.soulcraft.com only; the + npmjs republish step is retired from the release rail. Existing npmjs versions of + `@soulcraft/brainy` stay as they are and receive no new versions. +- **The repository moved** to `soulcraftlabs/open-brainy` on The Source; the old path redirects. +- **No engine change.** Everything in the 10.4.2 notes applies unchanged; adoption is one + install-line change (`@soulcraft/brainy` → `@soulcraftlabs/brainy`), which downstream + applications make together with their native-engine bump. + +## v10.4.2 — 2026-08-27 (a zero-norm vector is not a vector) + +**This is the last release of the MIT engine under the `@soulcraft/brainy` name.** +The MIT package continues as **Open Brainy** — `@soulcraftlabs/brainy`: the open API, +client library, types and protocol, an openly specified canonical format, and the TypeScript +reference engine, scoped honestly as a single-node engine for stores up to roughly one +million rows. The `@soulcraft/brainy` name passes to the native engine, **Brainy**, at a +major version bump; that engine implements the same API over the same open format at +production scale, requires a license, and refuses loudly without one. Nothing changes +for existing installs until that major ships; the move is announced with it. + +Six fixes, one law: a vector with no magnitude carries no information, so it must +never reach a vector index — in any engine — and the canonical store must say so. + +- **The permanently-unvectored row.** `add({ ..., vector: [] })` (and the same item + shape in `addMany` / `transact`) is now the sanctioned "no vector" row: persisted + with an empty vector leg, never embedded, never indexed, counted as unvectored in + the canonical ledger. Metadata-only rows — telemetry tallies, counters, plumbing — + no longer need a placeholder vector and never enter the vector leg. `vector: []` + together with `deferEmbedding: true` is refused with a typed error (a supplied + vector has nothing to defer). Previously `vector: []` threw a dimension error. +- **The unvector door.** `update({ id, vector: [] })` (and its `transact()` twin) is + the sanctioned way to strip a vector from an existing row: canonical vector → `[]`, + removal from the vector index, the vectored ledger decremented exactly once — and + idempotent, so a resumed cleanup pass may simply re-issue. It never re-embeds, and + it clears a pending deferred-embed marker durably so the background worker cannot + re-vector the row later. Note that a rebuild never sheds vectors (it re-derives the + index from canonical rows); shedding historical vectors needs this door. +- **Zero-norm vectors are normalized at the write.** An explicit all-zero vector on + any write path is persisted as unvectored (`[]`) with one warning naming the row; + the vector-index operations keep their own refusal as a second line. The engine's + own VFS root, which used to persist a deliberate all-zero placeholder (harmless + under cosine distance, a false attractor under a downstream engine's + squared-euclidean serving — a production incident this week), is now created + unvectored, and an existing store's legacy root is migrated on open by a single + fixed-path read before the health gate runs — never a walk. +- **Enumeration keys on the identity record.** `getNouns()` / `getVerbs()` and the + cursor walks behind them enumerate by the metadata record, the same key the + canonical ledger counts by — previously the walk keyed on the vector file, so a + row holding metadata but no vector was counted yet never yielded (a permanent + "missing" phantom in coverage math), while an orphaned vector-only directory + could be yielded as a phantom id. The recovery fold also never deletes an existing + vector when it replays a metadata-only after-image (preserve-if-absent). One + documented gap remains: a verb's endpoints live only in its vector leg, so a + metadata-only verb is counted and loudly skipped, never fabricated — the fix is a + canonical-format change and lands with the open format. +- **The ledger's one-time derivation counts identity records.** Stores upgraded from + pre-ledger versions derived their ALL-visibility scalars once by counting id + directories, which included ghost and scar containers left by an old partial-delete + defect — an inflated denominator whose coverage row could never reach exact. The + derivation now counts only directories holding a metadata record, `counts.json` + carries a derivation-rule stamp, and a ledger derived under the old rule is marked + `suspect` at open (one O(1) field read, one warning) so the online `repairIndex()` + path clears it with a real recount. +- **The vector index refuses what it cannot hold.** `rebuild()` skips unvectored and + zero-norm rows (one summary line), re-pins the vector dimension from the first real + vector after a restart (previously a restart left the pin unset, so a wrong-length + insert became the new pin instead of being rejected), and `addItem` / `updateItem` + throw a typed `EmptyVectorIndexError` on a length-0 vector instead of ever storing + a vector-less node. +- **Smaller:** a failing plugin activation now rethrows with the original error as + `cause` (the originating file and line survive to the caller's log); build + generators stamp from the repository history of their inputs instead of wall clock, + so two builds of the same tree are byte-identical. + +Adoption: one restart, paired with its native-engine release. The first open of an +existing store runs the legacy-root migration (one narrated line) and, on stores that +upgraded from pre-ledger versions, marks the ledger suspect until the next sanctioned +recount — no rebuild in either case. + +## v10.4.1 — 2026-08-26 (reads refuse per family; an unchanged write never re-embeds) + +Two production defects from the same week, fixed together as a patch to 10.4.0. + +- **The read gate is per family.** A read now refuses only when the index family it + actually consults is unhealthy: a metadata filter is served while the vector leg is + rebuilding; a semantic query is refused only by the vector family; a graph + traversal only by the graph family. Previously any unhealthy family refused every + read on the brain — under a long vector rebuild, a production deployment's + metadata-only reads were refused for the duration, and the retries became a write + pump of their own. +- **Unchanged data never re-embeds.** `update()` compares the incoming `data` + structurally with the stored record; an update carrying identical data (a common + shape for periodic upserts) no longer embeds again and no longer churns the vector + leg. Previously every such update re-embedded and re-inserted, which under load + saturated the vector index with near-identical vectors. + +Adoption: one restart, paired with its native-engine release. + ## v10.4.0 — 2026-08-25 (the health report has a name) Three related cures, one root cause: an index deciding whether it could be trusted diff --git a/SECURITY.md b/SECURITY.md index 1f3c4732..91d40d49 100644 --- a/SECURITY.md +++ b/SECURITY.md @@ -30,7 +30,7 @@ commit to backporting fixes to unsupported lines. ## Scope -This policy covers the `@soulcraft/brainy` package itself — the code in +This policy covers the `@soulcraftlabs/brainy` package itself — the code in this repository. If you're evaluating a deployment that also uses `@soulcraft/cor`, report issues in that package the same way, to the same address; we'll route internally. diff --git a/bin/brainy-ts.js b/bin/brainy-ts.js index 4e9aedb8..90a35e98 100644 --- a/bin/brainy-ts.js +++ b/bin/brainy-ts.js @@ -3,7 +3,7 @@ /** * Modern TypeScript CLI Runner * - * This is the entry point after npm install @soulcraft/brainy + * This is the entry point after npm install @soulcraftlabs/brainy * It runs the compiled TypeScript CLI code */ diff --git a/bun.lock b/bun.lock index c31b3865..1e3e66e2 100644 --- a/bun.lock +++ b/bun.lock @@ -3,7 +3,7 @@ "configVersion": 0, "workspaces": { "": { - "name": "@soulcraft/brainy", + "name": "@soulcraftlabs/brainy", "dependencies": { "@aws-sdk/client-s3": "^3.540.0", "@azure/identity": "^4.0.0", diff --git a/docs/DEVELOPER_LEARNING_PATH.md b/docs/DEVELOPER_LEARNING_PATH.md index 4134ae63..b2d22fb1 100644 --- a/docs/DEVELOPER_LEARNING_PATH.md +++ b/docs/DEVELOPER_LEARNING_PATH.md @@ -25,13 +25,13 @@ ### Prerequisites ```bash -npm install @soulcraft/brainy +npm install @soulcraftlabs/brainy ``` ### Your First Neural Database ```typescript -import { Brainy, NounType } from '@soulcraft/brainy' +import { Brainy, NounType } from '@soulcraftlabs/brainy' // Step 1: Create and initialize Brainy const brain = new Brainy({ @@ -143,7 +143,7 @@ Once you're comfortable with basic operations, move to **Level 2** to learn abou ### Building a Knowledge Graph ```typescript -import { Brainy, NounType, VerbType } from '@soulcraft/brainy' +import { Brainy, NounType, VerbType } from '@soulcraftlabs/brainy' const brain = new Brainy({ storage: { type: 'memory' } }) await brain.init() @@ -314,7 +314,7 @@ Ready for AI-powered search and clustering? Move to **Level 3**. ### Triple Intelligence in Action ```typescript -import { Brainy, NounType, VerbType } from '@soulcraft/brainy' +import { Brainy, NounType, VerbType } from '@soulcraftlabs/brainy' const brain = new Brainy({ storage: { type: 'memory' } }) await brain.init() @@ -529,7 +529,7 @@ Want to treat files as intelligent entities? Learn the **Virtual Filesystem** in ### Files as Intelligent Entities ```typescript -import { Brainy, NounType, VerbType } from '@soulcraft/brainy' +import { Brainy, NounType, VerbType } from '@soulcraftlabs/brainy' const brain = new Brainy({ storage: { type: 'memory' } }) await brain.init() @@ -832,7 +832,7 @@ Ready for production deployment? Level 5 covers **planet-scale architecture**. ### Production-Ready Deployment ```typescript -import { Brainy, NounType } from '@soulcraft/brainy' +import { Brainy, NounType } from '@soulcraftlabs/brainy' // 1. PRODUCTION STORAGE - Filesystem with off-site snapshots console.log('Initializing production storage...\n') diff --git a/docs/FIND_SYSTEM.md b/docs/FIND_SYSTEM.md index 1cc38ce9..77fbbd79 100644 --- a/docs/FIND_SYSTEM.md +++ b/docs/FIND_SYSTEM.md @@ -1217,7 +1217,7 @@ where: { await brain.find({ type: 'Document' }) // ✅ Correct: Use NounType enum -import { NounType } from '@soulcraft/brainy' +import { NounType } from '@soulcraftlabs/brainy' await brain.find({ type: NounType.Document }) // ❌ Error: Operator not recognized diff --git a/docs/MIGRATION-V3-TO-V4.md b/docs/MIGRATION-V3-TO-V4.md index 29c409ac..680b6928 100644 --- a/docs/MIGRATION-V3-TO-V4.md +++ b/docs/MIGRATION-V3-TO-V4.md @@ -153,13 +153,13 @@ brainy-data/ ### Step 1: Update Brainy Package ```bash -npm install @soulcraft/brainy@latest +npm install @soulcraftlabs/brainy@latest ``` **Check your version:** ```bash -npm list @soulcraft/brainy -# Should show: @soulcraft/brainy@4.0.0 +npm list @soulcraftlabs/brainy +# Should show: @soulcraftlabs/brainy@4.0.0 ``` ### Step 2: No Code Changes Required! ✅ @@ -374,7 +374,7 @@ If you encounter issues, you can rollback: ```bash # Reinstall v3 -npm install @soulcraft/brainy@^3.50.0 +npm install @soulcraftlabs/brainy@^3.50.0 # Restart application ``` @@ -389,7 +389,7 @@ rm -rf ./data cp -r ./data-backup ./data # Reinstall v3 -npm install @soulcraft/brainy@^3.50.0 +npm install @soulcraftlabs/brainy@^3.50.0 ``` ## Common Migration Scenarios @@ -539,7 +539,7 @@ console.log('Storage type:', status.type) **Migration Checklist:** - ✅ Backup data -- ✅ Update npm package (`npm install @soulcraft/brainy@latest`) +- ✅ Update npm package (`npm install @soulcraftlabs/brainy@latest`) - ✅ Restart application (automatic migration) - ✅ Verify data integrity - ✅ Enable lifecycle policies diff --git a/docs/PLUGINS.md b/docs/PLUGINS.md index 3078c239..238d2252 100644 --- a/docs/PLUGINS.md +++ b/docs/PLUGINS.md @@ -46,7 +46,7 @@ If no plugin provides a given key, brainy uses its built-in JavaScript implement ### 1. Implement the `BrainyPlugin` interface ```typescript -import type { BrainyPlugin, BrainyPluginContext } from '@soulcraft/brainy/plugin' +import type { BrainyPlugin, BrainyPluginContext } from '@soulcraftlabs/brainy/plugin' const myPlugin: BrainyPlugin = { name: 'my-brainy-plugin', // Must be unique (typically your npm package name) @@ -90,7 +90,7 @@ await brain.init() **Programmatic registration:** For plugins not installed as npm packages, use `brain.use()`: ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' import myPlugin from './my-plugin.js' const brain = new Brainy() @@ -272,10 +272,10 @@ When provided by an optional native acceleration plugin (such as `@soulcraft/cor #### `cache` **Type:** `UnifiedCache` -Replaces the global `UnifiedCache` singleton used for VFS path resolution, semantic caching, and vector index caching. Must implement the `UnifiedCache` interface (available from `@soulcraft/brainy/internals`). +Replaces the global `UnifiedCache` singleton used for VFS path resolution, semantic caching, and vector index caching. Must implement the `UnifiedCache` interface (available from `@soulcraftlabs/brainy/internals`). ```typescript -import type { UnifiedCache } from '@soulcraft/brainy/internals' +import type { UnifiedCache } from '@soulcraftlabs/brainy/internals' context.registerProvider('cache', myNativeCache) ``` @@ -325,8 +325,8 @@ Plugins can register custom storage backends that users reference by name. ### Implementing a Storage Adapter ```typescript -import type { StorageAdapterFactory } from '@soulcraft/brainy/plugin' -import type { StorageAdapter } from '@soulcraft/brainy' +import type { StorageAdapterFactory } from '@soulcraftlabs/brainy/plugin' +import type { StorageAdapter } from '@soulcraftlabs/brainy' class MyStorageAdapter implements StorageAdapter { async init(): Promise { /* ... */ } @@ -360,9 +360,9 @@ Brainy provides three entry points for plugin developers: | Import Path | Contents | Stability | |-------------|----------|-----------| -| `@soulcraft/brainy` | Public API, types, StorageAdapter | Stable (semver) | -| `@soulcraft/brainy/plugin` | BrainyPlugin, BrainyPluginContext, StorageAdapterFactory | Stable (semver) | -| `@soulcraft/brainy/internals` | UnifiedCache, EntityIdMapper, logger utilities | Internal (may change between minor versions) | +| `@soulcraftlabs/brainy` | Public API, types, StorageAdapter | Stable (semver) | +| `@soulcraftlabs/brainy/plugin` | BrainyPlugin, BrainyPluginContext, StorageAdapterFactory | Stable (semver) | +| `@soulcraftlabs/brainy/internals` | UnifiedCache, EntityIdMapper, logger utilities | Internal (may change between minor versions) | ## Diagnostics @@ -440,7 +440,7 @@ A minimal but useful plugin that provides SIMD-accelerated distance calculations ```typescript // simd-distance-plugin/src/plugin.ts -import type { BrainyPlugin, BrainyPluginContext } from '@soulcraft/brainy/plugin' +import type { BrainyPlugin, BrainyPluginContext } from '@soulcraftlabs/brainy/plugin' // Hypothetical native module import { simdCosineDistance } from './native.js' @@ -470,7 +470,7 @@ export default simdDistancePlugin "main": "./dist/plugin.js", "types": "./dist/plugin.d.ts", "peerDependencies": { - "@soulcraft/brainy": ">=7.0.0" + "@soulcraftlabs/brainy": ">=7.0.0" } } ``` @@ -478,7 +478,7 @@ export default simdDistancePlugin Usage: ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const brain = new Brainy({ plugins: ['brainy-simd-distance'] }) await brain.init() diff --git a/docs/PRODUCTION_SERVICE_ARCHITECTURE.md b/docs/PRODUCTION_SERVICE_ARCHITECTURE.md index 4568cd31..ad4a4a40 100644 --- a/docs/PRODUCTION_SERVICE_ARCHITECTURE.md +++ b/docs/PRODUCTION_SERVICE_ARCHITECTURE.md @@ -54,7 +54,7 @@ After 40 API calls: ```typescript // server.ts -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' // SINGLETON INSTANCE let brainInstance: Brainy | null = null @@ -174,7 +174,7 @@ process.on('SIGTERM', async () => { ```typescript // server.ts - Clean Bun implementation -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' let brain: Brainy | null = null diff --git a/docs/README.md b/docs/README.md index 3290001f..ddb37d20 100644 --- a/docs/README.md +++ b/docs/README.md @@ -5,7 +5,7 @@ ## Quick Start ```typescript -import { Brainy, NounType, VerbType } from '@soulcraft/brainy' +import { Brainy, NounType, VerbType } from '@soulcraftlabs/brainy' const brain = new Brainy() await brain.init() diff --git a/docs/RELEASE-GUIDE.md b/docs/RELEASE-GUIDE.md index 94c6a6cb..4b120bd8 100644 --- a/docs/RELEASE-GUIDE.md +++ b/docs/RELEASE-GUIDE.md @@ -99,7 +99,7 @@ Examples: ```bash # 1. Deprecate wrong version on npm -npm deprecate @soulcraft/brainy@X.X.X "Incorrect version - use Y.Y.Y" +npm deprecate @soulcraftlabs/brainy@X.X.X "Incorrect version - use Y.Y.Y" # 2. Fix version in package.json # 3. Republish correct version diff --git a/docs/SCALING.md b/docs/SCALING.md index e9ae1136..054d2096 100644 --- a/docs/SCALING.md +++ b/docs/SCALING.md @@ -13,7 +13,7 @@ ### In-Memory ```typescript -import Brainy from '@soulcraft/brainy' +import Brainy from '@soulcraftlabs/brainy' const brain = new Brainy({ storage: { type: 'memory' } }) ``` @@ -43,7 +43,7 @@ The native vector provider (via the optional `@soulcraft/cor` package) extends t Numbers below are **measured** by `tests/benchmarks/find-composition-scale.js` (a single Node 22 process, in-memory storage, 384-dim vectors, `balanced` recall). They are the -open-core (pure-TypeScript) path — what you get from `@soulcraft/brainy` with no native +open-core (pure-TypeScript) path — what you get from `@soulcraftlabs/brainy` with no native provider installed. Run it yourself: `node --max-old-space-size=8192 tests/benchmarks/find-composition-scale.js 100000`. `find()` query latency, p50 / p95 (200 queries each): diff --git a/docs/api-contract.json b/docs/api-contract.json new file mode 100644 index 00000000..aafd838a --- /dev/null +++ b/docs/api-contract.json @@ -0,0 +1,1544 @@ +{ + "contractVersion": 1, + "engine": "@soulcraftlabs/brainy", + "compatibility": { + "minor": "additive — a new optional door, a new served operator, a new error class; every existing implementation still conforms", + "major": "breaking — a door removed, an answer narrowed, an ordering law changed, an optional door promoted to required, or an operator moved from served to refused" + }, + "doors": [ + { + "name": "adaptiveHistoryBudgetBytes", + "kind": "method", + "arity": 1 + }, + { + "name": "add", + "kind": "method", + "arity": 1 + }, + { + "name": "addMany", + "kind": "method", + "arity": 1 + }, + { + "name": "adoptLogAuthority", + "kind": "method", + "arity": 0 + }, + { + "name": "adoptLogAuthorityInner", + "kind": "method", + "arity": 0 + }, + { + "name": "aggViewFromEntity", + "kind": "method", + "arity": 1 + }, + { + "name": "anyProviderMigrating", + "kind": "method", + "arity": 0 + }, + { + "name": "applyFusionScoring", + "kind": "method", + "arity": 2 + }, + { + "name": "applyGraphConstraints", + "kind": "method", + "arity": 2 + }, + { + "name": "armIdleFlushTimer", + "kind": "method", + "arity": 2 + }, + { + "name": "asOf", + "kind": "method", + "arity": 2 + }, + { + "name": "assertGenerationStoreReady", + "kind": "method", + "arity": 1 + }, + { + "name": "assertWritable", + "kind": "method", + "arity": 1 + }, + { + "name": "audit", + "kind": "method", + "arity": 0 + }, + { + "name": "auditGraph", + "kind": "method", + "arity": 0 + }, + { + "name": "autoAdoptLegacyVfsBlobsIfNeeded", + "kind": "method", + "arity": 0 + }, + { + "name": "autoAlpha", + "kind": "method", + "arity": 1 + }, + { + "name": "autoCompactHistory", + "kind": "method", + "arity": 0 + }, + { + "name": "awaitMigrationLock", + "kind": "method", + "arity": 1 + }, + { + "name": "awaitPendingEmbeds", + "kind": "method", + "arity": 0 + }, + { + "name": "backfillAggregateIfNeeded", + "kind": "method", + "arity": 1 + }, + { + "name": "batchGet", + "kind": "method", + "arity": 2 + }, + { + "name": "brainWideStrictRequiresSubtype", + "kind": "method", + "arity": 1 + }, + { + "name": "bridgeLegacyPendingEmbedSidecars", + "kind": "method", + "arity": 0 + }, + { + "name": "buildAtGenerationVectors", + "kind": "method", + "arity": 2 + }, + { + "name": "buildGraphView", + "kind": "method", + "arity": 4 + }, + { + "name": "buildMetadataFilter", + "kind": "method", + "arity": 1 + }, + { + "name": "buildMigrationUpdate", + "kind": "method", + "arity": 5 + }, + { + "name": "buildRelationMigrationUpdate", + "kind": "method", + "arity": 5 + }, + { + "name": "cacheVerbInt", + "kind": "method", + "arity": 2 + }, + { + "name": "canServeVectorAtGeneration", + "kind": "method", + "arity": 1 + }, + { + "name": "checkHealth", + "kind": "method", + "arity": 0 + }, + { + "name": "checkMigrations", + "kind": "method", + "arity": 0 + }, + { + "name": "clear", + "kind": "method", + "arity": 0 + }, + { + "name": "clearPendingEmbed", + "kind": "method", + "arity": 1 + }, + { + "name": "close", + "kind": "method", + "arity": 0 + }, + { + "name": "closeDurableSteps", + "kind": "method", + "arity": 0 + }, + { + "name": "cluster", + "kind": "method", + "arity": 1 + }, + { + "name": "collectProviderInvariants", + "kind": "method", + "arity": 0 + }, + { + "name": "compactHistory", + "kind": "method", + "arity": 1 + }, + { + "name": "consumeMetadataWatermarkVerdict", + "kind": "method", + "arity": 1 + }, + { + "name": "convertMetadataToEntity", + "kind": "method", + "arity": 2 + }, + { + "name": "convertNounToEntity", + "kind": "method", + "arity": 1 + }, + { + "name": "counts", + "kind": "accessor" + }, + { + "name": "createIndex", + "kind": "method", + "arity": 0 + }, + { + "name": "createMigrationBackupIfNeeded", + "kind": "method", + "arity": 0 + }, + { + "name": "createPinnedDb", + "kind": "method", + "arity": 1 + }, + { + "name": "createResult", + "kind": "method", + "arity": 4 + }, + { + "name": "dbFinalizationRegistry", + "kind": "accessor" + }, + { + "name": "dbHost", + "kind": "accessor" + }, + { + "name": "defineAggregate", + "kind": "method", + "arity": 1 + }, + { + "name": "detectIdKind", + "kind": "method", + "arity": 3 + }, + { + "name": "diagnostics", + "kind": "method", + "arity": 0 + }, + { + "name": "diff", + "kind": "method", + "arity": 2 + }, + { + "name": "embed", + "kind": "method", + "arity": 1 + }, + { + "name": "embedBatch", + "kind": "method", + "arity": 2 + }, + { + "name": "emitCommitted", + "kind": "method", + "arity": 4 + }, + { + "name": "enforceSubtypeOnAdd", + "kind": "method", + "arity": 4 + }, + { + "name": "enforceSubtypeOnRelate", + "kind": "method", + "arity": 4 + }, + { + "name": "enforceTrackedFieldValues", + "kind": "method", + "arity": 2 + }, + { + "name": "enhanceNLPResult", + "kind": "method", + "arity": 2 + }, + { + "name": "enqueuePendingEmbed", + "kind": "method", + "arity": 1 + }, + { + "name": "ensureAggregationIndex", + "kind": "method", + "arity": 0 + }, + { + "name": "ensureIndexesLoaded", + "kind": "method", + "arity": 0 + }, + { + "name": "ensureInitialized", + "kind": "method", + "arity": 1 + }, + { + "name": "entityForAggFromRawRecord", + "kind": "method", + "arity": 1 + }, + { + "name": "entityFromGenerationRecord", + "kind": "method", + "arity": 3 + }, + { + "name": "entityIntsToUuids", + "kind": "method", + "arity": 1 + }, + { + "name": "entityViewFromRawRecord", + "kind": "method", + "arity": 2 + }, + { + "name": "excludedVisibilityTiers", + "kind": "method", + "arity": 1 + }, + { + "name": "executeGraphSearch", + "kind": "method", + "arity": 2 + }, + { + "name": "executeProximitySearch", + "kind": "method", + "arity": 1 + }, + { + "name": "executeTextSearch", + "kind": "method", + "arity": 2 + }, + { + "name": "executeVectorSearch", + "kind": "method", + "arity": 3 + }, + { + "name": "explain", + "kind": "method", + "arity": 1 + }, + { + "name": "export", + "kind": "method", + "arity": 0 + }, + { + "name": "extract", + "kind": "method", + "arity": 2 + }, + { + "name": "extractConcepts", + "kind": "method", + "arity": 2 + }, + { + "name": "extractEntities", + "kind": "method", + "arity": 2 + }, + { + "name": "factSegmentPaths", + "kind": "method", + "arity": 1 + }, + { + "name": "fieldCountsAggregateName", + "kind": "method", + "arity": 1 + }, + { + "name": "fillSubtypes", + "kind": "method", + "arity": 1 + }, + { + "name": "filterIdsBelted", + "kind": "method", + "arity": 2 + }, + { + "name": "find", + "kind": "method", + "arity": 1 + }, + { + "name": "findAggregate", + "kind": "method", + "arity": 1 + }, + { + "name": "findDuplicates", + "kind": "method", + "arity": 1 + }, + { + "name": "findMatchingWords", + "kind": "method", + "arity": 3 + }, + { + "name": "flush", + "kind": "method", + "arity": 0 + }, + { + "name": "formatInfo", + "kind": "method", + "arity": 0 + }, + { + "name": "formatSubtypeError", + "kind": "method", + "arity": 1 + }, + { + "name": "generation", + "kind": "method", + "arity": 0 + }, + { + "name": "generationDigest", + "kind": "method", + "arity": 1 + }, + { + "name": "get", + "kind": "method", + "arity": 2 + }, + { + "name": "getActivePlugins", + "kind": "method", + "arity": 0 + }, + { + "name": "getAvailableFields", + "kind": "method", + "arity": 0 + }, + { + "name": "getBackgroundDeduplicator", + "kind": "method", + "arity": 0 + }, + { + "name": "getFieldsForType", + "kind": "method", + "arity": 1 + }, + { + "name": "getFieldStatistics", + "kind": "method", + "arity": 0 + }, + { + "name": "getFieldsWithCardinality", + "kind": "method", + "arity": 0 + }, + { + "name": "getFieldValues", + "kind": "method", + "arity": 1 + }, + { + "name": "getIndexStats", + "kind": "method", + "arity": 0 + }, + { + "name": "getIndexStatus", + "kind": "method", + "arity": 0 + }, + { + "name": "getMemoryStats", + "kind": "method", + "arity": 0 + }, + { + "name": "getNeighborUuids", + "kind": "method", + "arity": 2 + }, + { + "name": "getNounCount", + "kind": "method", + "arity": 0 + }, + { + "name": "getOptimalQueryPlan", + "kind": "method", + "arity": 1 + }, + { + "name": "getStats", + "kind": "method", + "arity": 1 + }, + { + "name": "getStorageType", + "kind": "method", + "arity": 0 + }, + { + "name": "getSubtypeRule", + "kind": "method", + "arity": 1 + }, + { + "name": "getTripleIntelligence", + "kind": "method", + "arity": 0 + }, + { + "name": "getTypedNeighbors", + "kind": "method", + "arity": 4 + }, + { + "name": "getVerbCount", + "kind": "method", + "arity": 0 + }, + { + "name": "graph", + "kind": "accessor" + }, + { + "name": "graphAccelerationProvider", + "kind": "method", + "arity": 0 + }, + { + "name": "graphCommunities", + "kind": "method", + "arity": 1 + }, + { + "name": "graphCommunitiesFallback", + "kind": "method", + "arity": 1 + }, + { + "name": "graphCommunitiesNative", + "kind": "method", + "arity": 2 + }, + { + "name": "graphEntityInt", + "kind": "method", + "arity": 1 + }, + { + "name": "graphExport", + "kind": "method", + "arity": 1 + }, + { + "name": "graphExportFallback", + "kind": "method", + "arity": 1 + }, + { + "name": "graphExportNative", + "kind": "method", + "arity": 2 + }, + { + "name": "graphPath", + "kind": "method", + "arity": 3 + }, + { + "name": "graphPathFallback", + "kind": "method", + "arity": 3 + }, + { + "name": "graphPathNative", + "kind": "method", + "arity": 4 + }, + { + "name": "graphRank", + "kind": "method", + "arity": 1 + }, + { + "name": "graphRankFallback", + "kind": "method", + "arity": 1 + }, + { + "name": "graphRankNative", + "kind": "method", + "arity": 2 + }, + { + "name": "graphSubgraph", + "kind": "method", + "arity": 2 + }, + { + "name": "graphSubgraphFallback", + "kind": "method", + "arity": 4 + }, + { + "name": "graphSubgraphFromQuery", + "kind": "method", + "arity": 5 + }, + { + "name": "graphSubgraphNative", + "kind": "method", + "arity": 5 + }, + { + "name": "groupByLabel", + "kind": "method", + "arity": 2 + }, + { + "name": "hasStorageMethod", + "kind": "method", + "arity": 1 + }, + { + "name": "hasVectorOrTextCriteria", + "kind": "method", + "arity": 1 + }, + { + "name": "health", + "kind": "method", + "arity": 0 + }, + { + "name": "highlight", + "kind": "method", + "arity": 1 + }, + { + "name": "highlightSemanticPhase", + "kind": "method", + "arity": 5 + }, + { + "name": "history", + "kind": "method", + "arity": 2 + }, + { + "name": "historyStats", + "kind": "method", + "arity": 0 + }, + { + "name": "hub", + "kind": "accessor" + }, + { + "name": "hydrateIdMapperForGraphRebuild", + "kind": "method", + "arity": 0 + }, + { + "name": "hydrateNativeSubgraph", + "kind": "method", + "arity": 2 + }, + { + "name": "import", + "kind": "method", + "arity": 2 + }, + { + "name": "importPluginPackage", + "kind": "method", + "arity": 1 + }, + { + "name": "incidentEdges", + "kind": "method", + "arity": 3 + }, + { + "name": "indexStats", + "kind": "method", + "arity": 0 + }, + { + "name": "init", + "kind": "method", + "arity": 1 + }, + { + "name": "insights", + "kind": "method", + "arity": 0 + }, + { + "name": "isEmbeddingReady", + "kind": "method", + "arity": 0 + }, + { + "name": "isInfrastructureWrite", + "kind": "method", + "arity": 1 + }, + { + "name": "isInitialized", + "kind": "accessor" + }, + { + "name": "isReadOnly", + "kind": "accessor" + }, + { + "name": "kickBackgroundFlush", + "kind": "method", + "arity": 1 + }, + { + "name": "kickEmbedWorker", + "kind": "method", + "arity": 0 + }, + { + "name": "legacyLayoutMigrationPhase", + "kind": "method", + "arity": 0 + }, + { + "name": "loadAnalyticsGraph", + "kind": "method", + "arity": 1 + }, + { + "name": "loadPlugins", + "kind": "method", + "arity": 0 + }, + { + "name": "logAuthority", + "kind": "method", + "arity": 0 + }, + { + "name": "maintenanceDebt", + "kind": "method", + "arity": 0 + }, + { + "name": "materializeAtGeneration", + "kind": "method", + "arity": 1 + }, + { + "name": "metadataIndexRetractionOp", + "kind": "method", + "arity": 3 + }, + { + "name": "migrate", + "kind": "method", + "arity": 1 + }, + { + "name": "migrateField", + "kind": "method", + "arity": 1 + }, + { + "name": "migrateInternal", + "kind": "method", + "arity": 2 + }, + { + "name": "migrateLegacyZeroNormVfsRootIfNeeded", + "kind": "method", + "arity": 0 + }, + { + "name": "migrationSnapshot", + "kind": "method", + "arity": 0 + }, + { + "name": "neededFamiliesMigrating", + "kind": "method", + "arity": 1 + }, + { + "name": "neighbors", + "kind": "method", + "arity": 2 + }, + { + "name": "newId", + "kind": "method", + "arity": 0 + }, + { + "name": "nlp", + "kind": "method", + "arity": 0 + }, + { + "name": "normalizeConfig", + "kind": "method", + "arity": 1 + }, + { + "name": "noteWriteForPersistence", + "kind": "method", + "arity": 0 + }, + { + "name": "now", + "kind": "method", + "arity": 0 + }, + { + "name": "onChange", + "kind": "method", + "arity": 1 + }, + { + "name": "pagination", + "kind": "accessor" + }, + { + "name": "parseMigrationPath", + "kind": "method", + "arity": 1 + }, + { + "name": "parseNaturalQuery", + "kind": "method", + "arity": 1 + }, + { + "name": "pathExists", + "kind": "method", + "arity": 2 + }, + { + "name": "pendingEmbedCount", + "kind": "method", + "arity": 0 + }, + { + "name": "performInit", + "kind": "method", + "arity": 1 + }, + { + "name": "persistPinnedGeneration", + "kind": "method", + "arity": 2 + }, + { + "name": "persistSingleOp", + "kind": "method", + "arity": 6 + }, + { + "name": "pickMetadataProbe", + "kind": "method", + "arity": 1 + }, + { + "name": "pickVectorProbe", + "kind": "method", + "arity": 0 + }, + { + "name": "pinGeneration", + "kind": "method", + "arity": 1 + }, + { + "name": "planGetEntity", + "kind": "method", + "arity": 3 + }, + { + "name": "planTransact", + "kind": "method", + "arity": 1 + }, + { + "name": "planTxAdd", + "kind": "method", + "arity": 3 + }, + { + "name": "planTxRelate", + "kind": "method", + "arity": 3 + }, + { + "name": "planTxRemove", + "kind": "method", + "arity": 3 + }, + { + "name": "planTxUnrelate", + "kind": "method", + "arity": 3 + }, + { + "name": "planTxUpdate", + "kind": "method", + "arity": 3 + }, + { + "name": "projectionGauges", + "kind": "method", + "arity": 0 + }, + { + "name": "providerForFamily", + "kind": "method", + "arity": 1 + }, + { + "name": "providerIsMigrating", + "kind": "method", + "arity": 1 + }, + { + "name": "providerMigrationStatus", + "kind": "method", + "arity": 0 + }, + { + "name": "queryAggregate", + "kind": "method", + "arity": 2 + }, + { + "name": "queryIndexFamilies", + "kind": "method", + "arity": 1 + }, + { + "name": "readPath", + "kind": "method", + "arity": 2 + }, + { + "name": "ready", + "kind": "accessor" + }, + { + "name": "rebuildIndexesIfNeeded", + "kind": "method", + "arity": 0 + }, + { + "name": "rebuildMetadataIndexOnline", + "kind": "method", + "arity": 0 + }, + { + "name": "reconcileLogDivergence", + "kind": "method", + "arity": 2 + }, + { + "name": "reconstructPath", + "kind": "method", + "arity": 4 + }, + { + "name": "recordStateAt", + "kind": "method", + "arity": 3 + }, + { + "name": "recoverPendingEmbedsFromLog", + "kind": "method", + "arity": 0 + }, + { + "name": "registerShutdownHooks", + "kind": "method", + "arity": 0 + }, + { + "name": "relate", + "kind": "method", + "arity": 1 + }, + { + "name": "related", + "kind": "method", + "arity": 1 + }, + { + "name": "relateMany", + "kind": "method", + "arity": 1 + }, + { + "name": "relationFromGenerationRecord", + "kind": "method", + "arity": 2 + }, + { + "name": "relationshipSubtypesOf", + "kind": "method", + "arity": 1 + }, + { + "name": "releaseGeneration", + "kind": "method", + "arity": 1 + }, + { + "name": "remove", + "kind": "method", + "arity": 1 + }, + { + "name": "removeAggregate", + "kind": "method", + "arity": 1 + }, + { + "name": "removeMany", + "kind": "method", + "arity": 1 + }, + { + "name": "removeMigrationBackupSafe", + "kind": "method", + "arity": 0 + }, + { + "name": "repackHistory", + "kind": "method", + "arity": 1 + }, + { + "name": "repairIndex", + "kind": "method", + "arity": 1 + }, + { + "name": "requestFlush", + "kind": "method", + "arity": 1 + }, + { + "name": "requireProviders", + "kind": "method", + "arity": 1 + }, + { + "name": "requireSubtype", + "kind": "method", + "arity": 1 + }, + { + "name": "resolveAsOfGeneration", + "kind": "method", + "arity": 2 + }, + { + "name": "resolveDiffEndpoint", + "kind": "method", + "arity": 1 + }, + { + "name": "resolveHiddenIds", + "kind": "method", + "arity": 1 + }, + { + "name": "resolveHNSWPersistMode", + "kind": "method", + "arity": 0 + }, + { + "name": "resolveRawGeneration", + "kind": "method", + "arity": 1 + }, + { + "name": "resolveRetentionPolicy", + "kind": "method", + "arity": 0 + }, + { + "name": "resolveVerbEndpointInts", + "kind": "method", + "arity": 1 + }, + { + "name": "resolveVerbIntsToIds", + "kind": "method", + "arity": 1 + }, + { + "name": "restore", + "kind": "method", + "arity": 2 + }, + { + "name": "rrfFusion", + "kind": "method", + "arity": 4 + }, + { + "name": "runAggregationBackfillWalk", + "kind": "method", + "arity": 0 + }, + { + "name": "runAggregationCatchUp", + "kind": "method", + "arity": 0 + }, + { + "name": "runEmbedWorker", + "kind": "method", + "arity": 0 + }, + { + "name": "runOracle", + "kind": "method", + "arity": 1 + }, + { + "name": "runRepairIndexPhases", + "kind": "method", + "arity": 5 + }, + { + "name": "scanFacts", + "kind": "method", + "arity": 1 + }, + { + "name": "seedIdsToInts", + "kind": "method", + "arity": 1 + }, + { + "name": "selectorToSeedIds", + "kind": "method", + "arity": 1 + }, + { + "name": "setRetentionBudget", + "kind": "method", + "arity": 1 + }, + { + "name": "setupEmbedder", + "kind": "method", + "arity": 0 + }, + { + "name": "setupIndex", + "kind": "method", + "arity": 0 + }, + { + "name": "setupStorage", + "kind": "method", + "arity": 0 + }, + { + "name": "similar", + "kind": "method", + "arity": 1 + }, + { + "name": "similarity", + "kind": "method", + "arity": 2 + }, + { + "name": "splitForHighlighting", + "kind": "method", + "arity": 2 + }, + { + "name": "stampBrainFormat", + "kind": "method", + "arity": 0 + }, + { + "name": "stampBrainFormatIfNeeded", + "kind": "method", + "arity": 0 + }, + { + "name": "stampEntityTree", + "kind": "method", + "arity": 0 + }, + { + "name": "stampProjectionWatermarks", + "kind": "method", + "arity": 0 + }, + { + "name": "stats", + "kind": "method", + "arity": 0 + }, + { + "name": "storageAdapter", + "kind": "accessor" + }, + { + "name": "stream", + "kind": "method", + "arity": 0 + }, + { + "name": "streaming", + "kind": "accessor" + }, + { + "name": "subtypesOf", + "kind": "method", + "arity": 1 + }, + { + "name": "trackField", + "kind": "method", + "arity": 1 + }, + { + "name": "transact", + "kind": "method", + "arity": 2 + }, + { + "name": "transactionLog", + "kind": "method", + "arity": 1 + }, + { + "name": "unrelate", + "kind": "method", + "arity": 1 + }, + { + "name": "unvectorNounForRootMigration", + "kind": "method", + "arity": 1 + }, + { + "name": "update", + "kind": "method", + "arity": 1 + }, + { + "name": "updateMany", + "kind": "method", + "arity": 1 + }, + { + "name": "updateRelation", + "kind": "method", + "arity": 1 + }, + { + "name": "upsertMergeParams", + "kind": "method", + "arity": 2 + }, + { + "name": "use", + "kind": "method", + "arity": 1 + }, + { + "name": "usesDefaultWasmEmbedder", + "kind": "method", + "arity": 0 + }, + { + "name": "validateIndexConsistency", + "kind": "method", + "arity": 0 + }, + { + "name": "vectorSearchAtGeneration", + "kind": "method", + "arity": 4 + }, + { + "name": "verbsToRelations", + "kind": "method", + "arity": 1 + }, + { + "name": "verbToRelationLike", + "kind": "method", + "arity": 1 + }, + { + "name": "verifyEntityTreeStamp", + "kind": "method", + "arity": 0 + }, + { + "name": "verifyGraphAdjacencyLive", + "kind": "method", + "arity": 0 + }, + { + "name": "verifyLogAuthority", + "kind": "method", + "arity": 0 + }, + { + "name": "verifyMetadataLive", + "kind": "method", + "arity": 0 + }, + { + "name": "verifyVectorLive", + "kind": "method", + "arity": 0 + }, + { + "name": "versionedIndexProviders", + "kind": "method", + "arity": 0 + }, + { + "name": "vfs", + "kind": "accessor" + }, + { + "name": "waitForIndexed", + "kind": "method", + "arity": 2 + }, + { + "name": "warm", + "kind": "method", + "arity": 0 + }, + { + "name": "warmupEmbeddings", + "kind": "method", + "arity": 0 + }, + { + "name": "warnIfReadsDegraded", + "kind": "method", + "arity": 1 + }, + { + "name": "wireConnectionsCodec", + "kind": "method", + "arity": 0 + }, + { + "name": "wireGraphIdResolver", + "kind": "method", + "arity": 0 + } + ], + "errors": [ + "BrainyError", + "DerivedArtifactMissingError", + "GraphIndexNotReadyError", + "MetadataIndexNotReadyError", + "MigrationInProgressError", + "ProtectedArtifactError", + "VectorIndexNotReadyError" + ], + "operators": { + "accepted": [ + "between", + "contains", + "endsWith", + "eq", + "equals", + "excludes", + "exists", + "greaterThan", + "greaterThanOrEqual", + "gt", + "gte", + "hasAll", + "in", + "length", + "lessThan", + "lessThanOrEqual", + "lt", + "lte", + "matches", + "missing", + "ne", + "noneOf", + "notEquals", + "oneOf", + "startsWith" + ], + "servedOnIndexPath": [ + "between", + "contains", + "eq", + "equals", + "excludes", + "exists", + "greaterThan", + "greaterThanOrEqual", + "gt", + "gte", + "hasAll", + "in", + "lessThan", + "lessThanOrEqual", + "lt", + "lte", + "missing", + "ne", + "noneOf", + "notEquals", + "oneOf" + ], + "refusedByIndexPath": [ + "endsWith", + "length", + "matches", + "startsWith" + ], + "combinators": [ + "allOf", + "anyOf", + "not" + ] + }, + "fieldAddressing": { + "systemKeyPrefix": "system.", + "systemEntityScalars": [ + "confidence", + "createdAt", + "createdBy", + "id", + "service", + "subtype", + "type", + "updatedAt", + "visibility", + "weight" + ], + "systemRelationScalars": [ + "confidence", + "createdAt", + "createdBy", + "service", + "sourceId", + "subtype", + "targetId", + "updatedAt", + "verb", + "visibility", + "weight" + ], + "plumbingFields": [ + "_rev", + "connections", + "data", + "level", + "vector" + ] + }, + "health": { + "verdicts": [ + "pass", + "warn", + "fail" + ], + "healKinds": [ + "none", + "repair", + "rebuild" + ], + "servingWithholdingInvariants": [ + "index-initialized", + "durable-state-present", + "manifest-residency", + "replay-clean", + "strand-latch" + ] + } +} diff --git a/docs/api/README.md b/docs/api/README.md index 82f48c91..ba49ff48 100644 --- a/docs/api/README.md +++ b/docs/api/README.md @@ -24,7 +24,7 @@ next: ## Quick Start ```typescript -import { Brainy, NounType, VerbType } from '@soulcraft/brainy' +import { Brainy, NounType, VerbType } from '@soulcraftlabs/brainy' const brain = new Brainy() // Zero config! await brain.init() // VFS auto-initialized! @@ -1010,7 +1010,7 @@ await db.release() // unpin + free cached materialization ### Db API errors -All exported from `@soulcraft/brainy`: +All exported from `@soulcraftlabs/brainy`: | Error | Thrown by | Meaning | |---|---|---| @@ -1918,11 +1918,11 @@ isn't serving throws instead of rebuilding mid-query: | `MetadataIndexNotReadyError` | `find({ where })` | Metadata/field index isn't serving | | `VectorIndexNotReadyError` | `find({ query })`, `similar()` | Vector index isn't serving | -All three are exported from `@soulcraft/brainy`. Catch them to distinguish +All three are exported from `@soulcraftlabs/brainy`. Catch them to distinguish "index not ready" from a genuine empty result: ```typescript -import { MetadataIndexNotReadyError } from '@soulcraft/brainy' +import { MetadataIndexNotReadyError } from '@soulcraftlabs/brainy' try { const rows = await brain.find({ where: { status: 'active' } }) @@ -2208,7 +2208,7 @@ For the full taxonomy with all 169 types and their descriptions, see: - **📖 Documentation:** [Full Documentation](../) - **🐛 Issues:** [GitHub Issues](https://github.com/soulcraftlabs/brainy/issues) - **💬 Discussions:** [GitHub Discussions](https://github.com/soulcraftlabs/brainy/discussions) -- **📦 NPM:** [@soulcraft/brainy](https://www.npmjs.com/package/@soulcraft/brainy) +- **📦 NPM:** [@soulcraftlabs/brainy](https://www.npmjs.com/package/@soulcraftlabs/brainy) - **⭐ GitHub:** [Star us](https://github.com/soulcraftlabs/brainy) --- diff --git a/docs/architecture/data-storage-architecture.md b/docs/architecture/data-storage-architecture.md index 48064757..83b9e23a 100644 --- a/docs/architecture/data-storage-architecture.md +++ b/docs/architecture/data-storage-architecture.md @@ -268,7 +268,7 @@ locks/_flush_responses/ # writer answers with .ack | **Counts/statistics** | Per-type and per-subtype maps | `_system/{type,subtype,verb-subtype}-statistics.json.gz`, `counts.json` | Recomputable by scanning entities (`brainy inspect repair`) | A pluggable index provider (the 8.0 plugin contract in -`@soulcraft/brainy/plugin`) may replace any of the JS implementations; the +`@soulcraftlabs/brainy/plugin`) may replace any of the JS implementations; the persisted formats above are contract-bound so JS and native implementations can interleave on the same directory. diff --git a/docs/architecture/finite-type-system.md b/docs/architecture/finite-type-system.md index 76492ee5..48a8b1fe 100644 --- a/docs/architecture/finite-type-system.md +++ b/docs/architecture/finite-type-system.md @@ -126,7 +126,7 @@ class TypeAwareMetadataIndex { **The Design**: Specify types clearly in your API calls: ```typescript -import { Brainy, NounType, VerbType } from '@soulcraft/brainy' +import { Brainy, NounType, VerbType } from '@soulcraftlabs/brainy' // Add entity with explicit type await brain.add({ @@ -231,7 +231,7 @@ class OrgEnrichmentAugmentation { **Brainy's Approach**: Extract **typed** concepts: ```typescript -import { NaturalLanguageProcessor } from '@soulcraft/brainy' +import { NaturalLanguageProcessor } from '@soulcraftlabs/brainy' const nlp = new NaturalLanguageProcessor() const concepts = await nlp.extractConcepts("Alice works at Google in San Francisco") @@ -382,7 +382,7 @@ import { getVerbTypes, BrainyTypes, suggestType -} from '@soulcraft/brainy' +} from '@soulcraftlabs/brainy' // Get all available noun types const nounTypes = getNounTypes() diff --git a/docs/architecture/multiprocess-storage-mixin.md b/docs/architecture/multiprocess-storage-mixin.md index 46f98398..1593bf8f 100644 --- a/docs/architecture/multiprocess-storage-mixin.md +++ b/docs/architecture/multiprocess-storage-mixin.md @@ -127,7 +127,7 @@ For reference, a clean migration path: `isMultiProcessSafe` type-guard. Keep `hasStorageMethod` for build/install artifact protection. 5. Document the new contract in `concepts/storage-adapters.md`. -6. Major-version-bump the `@soulcraft/brainy` peerDep range expected by +6. Major-version-bump the `@soulcraftlabs/brainy` peerDep range expected by plugins. Estimated work: ~half a day of code, ~2 hours of doc/example updates, diff --git a/docs/architecture/noun-verb-taxonomy.md b/docs/architecture/noun-verb-taxonomy.md index 286464be..3dac6892 100644 --- a/docs/architecture/noun-verb-taxonomy.md +++ b/docs/architecture/noun-verb-taxonomy.md @@ -20,7 +20,7 @@ next: Every example on this page is written against the real Brainy 8.0 API. The setup is always the same: ```typescript -import { Brainy, NounType, VerbType } from '@soulcraft/brainy' +import { Brainy, NounType, VerbType } from '@soulcraftlabs/brainy' const brain = new Brainy() await brain.init() @@ -40,7 +40,7 @@ Brainy's **Noun-Verb Taxonomy** achieves broad coverage of human knowledge throu - **Multi-hop Graph Traversals = Relationship Complexity** - **Result: Model data across virtually any industry** -Every piece of information can be represented as entities (nouns) connected by relationships (verbs) carrying properties (metadata). The standardized type system from `@soulcraft/brainy` (`NounType`, `VerbType`) gives those nouns and verbs a stable, shared name. +Every piece of information can be represented as entities (nouns) connected by relationships (verbs) carrying properties (metadata). The standardized type system from `@soulcraftlabs/brainy` (`NounType`, `VerbType`) gives those nouns and verbs a stable, shared name. ## The Power of Standardization: Universal Interoperability diff --git a/docs/architecture/zero-config.md b/docs/architecture/zero-config.md index d42d6784..a35e6416 100644 --- a/docs/architecture/zero-config.md +++ b/docs/architecture/zero-config.md @@ -35,7 +35,7 @@ constructor and `init()`. ## Instant Start ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' // That's it. No config needed. const brain = new Brainy() diff --git a/docs/concepts/field-addressing.md b/docs/concepts/field-addressing.md index c459021b..d24dd66b 100644 --- a/docs/concepts/field-addressing.md +++ b/docs/concepts/field-addressing.md @@ -167,7 +167,7 @@ await brain.find({ orderBy: 'createdAt' }) `UnresolvableFieldError` is exported from the package root: ```typescript -import { UnresolvableFieldError } from '@soulcraft/brainy' +import { UnresolvableFieldError } from '@soulcraftlabs/brainy' try { await brain.find({ orderBy: 'createdAt' }) diff --git a/docs/concepts/index-health.md b/docs/concepts/index-health.md index 96199f11..923267df 100644 --- a/docs/concepts/index-health.md +++ b/docs/concepts/index-health.md @@ -95,7 +95,7 @@ catchable error naming the reason: | `MetadataIndexNotReadyError` | `find({ where })` | The metadata/field index isn't serving — a filtered read would otherwise return `[]` indistinguishable from "no matches" | | `VectorIndexNotReadyError` | `find({ query })`, `similar()` | The vector index isn't serving — a semantic search would otherwise return `[]` indistinguishable from "nothing similar" | -All three are exported from `@soulcraft/brainy`. Catch them where your application +All three are exported from `@soulcraftlabs/brainy`. Catch them where your application needs to distinguish "this index isn't ready yet" from "there's genuinely nothing here" — a health dashboard, a retry policy, an operator alert. The fix is always the same: reconcile the index, either by reopening the brain (which brings every diff --git a/docs/concepts/storage-adapters.md b/docs/concepts/storage-adapters.md index af6d068f..82aa01e8 100644 --- a/docs/concepts/storage-adapters.md +++ b/docs/concepts/storage-adapters.md @@ -61,7 +61,7 @@ The only required override is the capability flag. Returning `true` from to call `acquireWriterLock()` at init. ```typescript -import { FileSystemStorage } from '@soulcraft/brainy' +import { FileSystemStorage } from '@soulcraftlabs/brainy' export class MmapFileSystemStorage extends FileSystemStorage { public supportsMultiProcessLocking(): boolean { @@ -79,7 +79,7 @@ If your storage is **not filesystem-backed** (a custom network backend), extend `BaseStorage` directly: ```typescript -import { BaseStorage } from '@soulcraft/brainy' +import { BaseStorage } from '@soulcraftlabs/brainy' export class MyCloudStorage extends BaseStorage { // BaseStorage's default no-op implementations of the multi-process @@ -101,7 +101,7 @@ The defensive check at every new-storage-method call site (`brainy.ts`, `hasStorageMethod(name)`) does **not** exist to handle "plugin bundles a stale BaseStorage." Plugins ship a dist that preserves the dynamic ESM import (verify in your plugin's `dist/`: `import { FileSystemStorage } from -'@soulcraft/brainy'` is not rewritten to a vendored copy). The prototype +'@soulcraftlabs/brainy'` is not rewritten to a vendored copy). The prototype chain at runtime resolves to whatever Brainy version your consumer has installed. @@ -109,8 +109,8 @@ installed. the prototype chain at the consumer-app level: - **Stale `node_modules`** — a lingering install from before the consumer - upgraded Brainy. The package.json says `@soulcraft/brainy@7.22.0` but - `node_modules/@soulcraft/brainy` is still 7.20.x. + upgraded Brainy. The package.json says `@soulcraftlabs/brainy@7.22.0` but + `node_modules/@soulcraftlabs/brainy` is still 7.20.x. - **Lockfile drift** — `bun.lockb` / `package-lock.json` pins a brainy version older than the package.json range, and `bun install` honors the lockfile. @@ -131,7 +131,7 @@ and the warning names the adapter class plus a remediation hint: methods on its prototype chain. Writer locking and the flush-request RPC are disabled for this directory. Likely fix: clean install (`rm -rf node_modules bun.lockb && bun install`) or rebuild your container image to refresh -`@soulcraft/brainy` to ≥7.21. See docs/concepts/storage-adapters.md. +`@soulcraftlabs/brainy` to ≥7.21. See docs/concepts/storage-adapters.md. ``` ## Authoring a new storage adapter — minimum checklist @@ -168,7 +168,7 @@ bun.lockb && bun install`) or rebuild your container image to refresh install time — fix install, not your plugin. 6. **Pin your peer dep generously.** `"peerDependencies": { - "@soulcraft/brainy": "^7.21.0" }` accepts any compatible 7.x. Don't pin + "@soulcraftlabs/brainy": "^7.21.0" }` accepts any compatible 7.x. Don't pin to an exact patch unless you're tracking a known regression. ## Future direction @@ -185,5 +185,5 @@ follow-up; consumers don't need to anticipate the change. heartbeat semantics, what the lock protects. - [`guides/inspection`](../guides/inspection.md) — `brainy inspect` and the read-only mode. -- `node_modules/@soulcraft/brainy/dist/storage/baseStorage.d.ts` — the +- `node_modules/@soulcraftlabs/brainy/dist/storage/baseStorage.d.ts` — the authoritative type signatures for every method this page references. diff --git a/docs/guides/aggregation.md b/docs/guides/aggregation.md index 11d86ec8..616c8fc4 100644 --- a/docs/guides/aggregation.md +++ b/docs/guides/aggregation.md @@ -22,7 +22,7 @@ they share a single scan. ## Quick Start ```typescript -import { Brainy, NounType } from '@soulcraft/brainy' +import { Brainy, NounType } from '@soulcraftlabs/brainy' const brain = new Brainy() await brain.init() diff --git a/docs/guides/framework-integration.md b/docs/guides/framework-integration.md index 984466c5..8f85da00 100644 --- a/docs/guides/framework-integration.md +++ b/docs/guides/framework-integration.md @@ -8,7 +8,7 @@ Brainy is **framework-friendly** - designed to drop into the server side of any Brainy embeds an HNSW vector index, a graph engine, and a filesystem-backed persistence layer. These belong on the server: -- **Zero configuration**: Just `import { Brainy } from '@soulcraft/brainy'` +- **Zero configuration**: Just `import { Brainy } from '@soulcraftlabs/brainy'` - **Auto storage detection**: `new Brainy()` auto-selects filesystem persistence on Node - **Cleaner code**: No browser polyfills, no conditional client/server imports - **Better DX**: One instance shared across your server routes @@ -18,13 +18,13 @@ Brainy embeds an HNSW vector index, a graph engine, and a filesystem-backed pers ### Install Brainy ```bash -npm install @soulcraft/brainy +npm install @soulcraftlabs/brainy ``` ### Basic Integration ```javascript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' // Run on the server (API route, server component, backend service) // new Brainy() auto-detects filesystem persistence on Node @@ -105,7 +105,7 @@ On the server, create one Brainy instance and reuse it across requests. This mod ```javascript // lib/brain.server.js -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' let brainPromise @@ -163,7 +163,7 @@ On the server, create one Brainy instance and reuse it across requests: ```javascript // server/brain.js (server-only module) -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' let brainPromise @@ -248,7 +248,7 @@ The matching backend endpoint uses Brainy directly (Node/Bun): ```typescript // server: api/search -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const brain = new Brainy() // auto-detects filesystem persistence on Node await brain.init() @@ -266,7 +266,7 @@ In Next.js, Brainy lives in server code only: API routes, server components, or ```javascript // lib/brain.server.js (imported only by server code) -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' let brainPromise @@ -318,7 +318,7 @@ Brainy runs in a server-only module (`*.server.js`); the component fetches resul ```javascript // src/lib/server/brain.js (server-only — note the .server suffix) -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' let brainPromise @@ -432,7 +432,7 @@ import { defineConfig } from 'vite' export default defineConfig({ ssr: { - external: ['@soulcraft/brainy'] + external: ['@soulcraftlabs/brainy'] } }) ``` @@ -440,7 +440,7 @@ export default defineConfig({ ```javascript // rollup.config.js (server bundle) export default { - external: ['@soulcraft/brainy', 'node:fs', 'node:path', 'node:crypto'] + external: ['@soulcraftlabs/brainy', 'node:fs', 'node:path', 'node:crypto'] } ``` @@ -466,7 +466,7 @@ export async function load({ url }) { ```javascript // For build-time usage (runs in Node during the build) -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' export async function generateStaticProps() { const brain = new Brainy({ @@ -513,7 +513,7 @@ export async function generateStaticProps() { ### Issue: Large client bundle size **Cause**: A client module is pulling in Brainy. -**Solution**: Move the `import { Brainy } from '@soulcraft/brainy'` into a server-only module so it never reaches the browser bundle. +**Solution**: Move the `import { Brainy } from '@soulcraftlabs/brainy'` into a server-only module so it never reaches the browser bundle. ### Issue: SSR hydration mismatch **Solution**: Run the search on the server (loader / server action / API route) and pass the results down as props, so server and client render the same markup. diff --git a/docs/guides/import-anything.md b/docs/guides/import-anything.md index b1bb15ef..ffabe55c 100644 --- a/docs/guides/import-anything.md +++ b/docs/guides/import-anything.md @@ -9,7 +9,7 @@ Brainy's import is **ONE magical method** that understands EVERYTHING: ## The Ultimate Simplicity ```javascript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const brain = new Brainy() await brain.init() diff --git a/docs/guides/import-progress-examples.md b/docs/guides/import-progress-examples.md index 66f50713..18c3cb9a 100644 --- a/docs/guides/import-progress-examples.md +++ b/docs/guides/import-progress-examples.md @@ -13,7 +13,7 @@ Brainy provides real-time progress tracking for **all 7 supported file formats** ### Basic Progress Tracking ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' import * as fs from 'fs' const brain = await Brainy.create() diff --git a/docs/guides/import-quick-reference.md b/docs/guides/import-quick-reference.md index 7837d49e..3bc26dae 100644 --- a/docs/guides/import-quick-reference.md +++ b/docs/guides/import-quick-reference.md @@ -7,7 +7,7 @@ ## Basic Import ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const brain = new Brainy() await brain.init() @@ -187,7 +187,7 @@ await brain.import(file, { ## Complete Example ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' import * as fs from 'fs' async function importCatalog() { diff --git a/docs/guides/inspection.md b/docs/guides/inspection.md index 240e81ae..8560b543 100644 --- a/docs/guides/inspection.md +++ b/docs/guides/inspection.md @@ -108,7 +108,7 @@ check fails — useful for piping into monitoring or CI. ## Programmatic inspection ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const reader = await Brainy.openReadOnly({ storage: { type: 'filesystem', path: '/data/brain' } diff --git a/docs/guides/installation.md b/docs/guides/installation.md index 0a36f632..20d40ea2 100644 --- a/docs/guides/installation.md +++ b/docs/guides/installation.md @@ -21,21 +21,21 @@ next: ## Install ```bash -npm install @soulcraft/brainy +npm install @soulcraftlabs/brainy ``` Or with your preferred package manager: ```bash -bun add @soulcraft/brainy -yarn add @soulcraft/brainy -pnpm add @soulcraft/brainy +bun add @soulcraftlabs/brainy +yarn add @soulcraftlabs/brainy +pnpm add @soulcraftlabs/brainy ``` ## Verify ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const brain = new Brainy() await brain.init() @@ -52,7 +52,7 @@ npm install @soulcraft/cor ``` ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const brain = new Brainy({ plugins: ['@soulcraft/cor'] }) await brain.init() // native providers registered during init @@ -71,7 +71,7 @@ remains available on npm if you need it. Brainy ships with full TypeScript types. No `@types/` package needed: ```typescript -import { Brainy, NounType, VerbType } from '@soulcraft/brainy' +import { Brainy, NounType, VerbType } from '@soulcraftlabs/brainy' const brain = new Brainy() await brain.init() diff --git a/docs/guides/migration-3.36.0.md b/docs/guides/migration-3.36.0.md index 8b1f239e..5f00534a 100644 --- a/docs/guides/migration-3.36.0.md +++ b/docs/guides/migration-3.36.0.md @@ -66,7 +66,7 @@ const results = await brain.search("query") **New diagnostics for capacity planning and performance tuning.** ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const brain = new Brainy() await brain.init() @@ -112,7 +112,7 @@ Recommendations: ${stats.recommendations.join(', ')} ### Step 1: Update Package ```bash -npm install @soulcraft/brainy@latest +npm install @soulcraftlabs/brainy@latest ``` ### Step 2: Restart Your Application @@ -134,7 +134,7 @@ npm run start ### Check Adaptive Sizing is Working ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const brain = new Brainy() await brain.init() @@ -218,7 +218,7 @@ For debugging or compatibility testing: If you need to rollback to v3.35.0: ```bash -npm install @soulcraft/brainy@3.35.0 +npm install @soulcraftlabs/brainy@3.35.0 ``` **Note:** We don't anticipate any issues, but rollback is straightforward if needed. @@ -367,7 +367,7 @@ if (stats.fairness.fairnessViolation) { ## Next Steps -1. ✅ **Upgrade:** `npm install @soulcraft/brainy@latest` +1. ✅ **Upgrade:** `npm install @soulcraftlabs/brainy@latest` 2. 📊 **Monitor:** Use `getCacheStats()` to verify performance improvements 3. 🎯 **Tune:** Adjust based on recommendations (if needed) 4. 📖 **Read:** [Operations Guide](../operations/capacity-planning.md) for capacity planning diff --git a/docs/guides/model-loading.md b/docs/guides/model-loading.md index e5b7b1d6..cc1b2b6a 100644 --- a/docs/guides/model-loading.md +++ b/docs/guides/model-loading.md @@ -37,7 +37,7 @@ This single WASM file contains everything needed for sentence embeddings. ```bash # Bun as a runtime — supported and recommended -bun add @soulcraft/brainy +bun add @soulcraftlabs/brainy bun run server.ts ``` diff --git a/docs/guides/namespace-migration.md b/docs/guides/namespace-migration.md index fad3c766..f7d2c7f7 100644 --- a/docs/guides/namespace-migration.md +++ b/docs/guides/namespace-migration.md @@ -80,7 +80,7 @@ If you read raw stored records (fact-log scanners, export tooling), use the exported shape-aware splitters — they handle both record eras: ```typescript -import { splitNounMetadataRecord } from '@soulcraft/brainy' +import { splitNounMetadataRecord } from '@soulcraftlabs/brainy' const { reserved, custom } = splitNounMetadataRecord(rawRecord) // reserved = engine fields · custom = the user's bag, ANY names ``` @@ -88,7 +88,7 @@ const { reserved, custom } = splitNounMetadataRecord(rawRecord) Feature detection (never version-sniff): ```typescript -import * as brainy from '@soulcraft/brainy' +import * as brainy from '@soulcraftlabs/brainy' const lawActive = 'FIELD_ADDRESSING_CAPABILITY' in brainy // 'field-addressing/v1' ``` diff --git a/docs/guides/nextjs-integration.md b/docs/guides/nextjs-integration.md index ab55e51f..25d6062d 100644 --- a/docs/guides/nextjs-integration.md +++ b/docs/guides/nextjs-integration.md @@ -9,7 +9,7 @@ Complete guide to integrating Brainy with Next.js applications, covering App Rou ```bash npx create-next-app@latest my-brainy-app cd my-brainy-app -npm install @soulcraft/brainy +npm install @soulcraftlabs/brainy ``` ### Basic Setup @@ -18,7 +18,7 @@ npm install @soulcraft/brainy // app/components/BrainyProvider.jsx 'use client' import { createContext, useContext, useEffect, useState } from 'react' -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const BrainyContext = createContext() @@ -271,7 +271,7 @@ export default function SearchPage() { ```javascript // app/api/search/route.js (App Router) -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' let brain = null @@ -332,7 +332,7 @@ export async function GET() { ```javascript // pages/api/search.js (Pages Router) -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' let brain = null @@ -374,7 +374,7 @@ export default async function handler(req, res) { ```javascript // app/api/data/route.js -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' let brain = null @@ -418,7 +418,7 @@ export async function POST(request) { ```jsx // app/actions/brainy.js 'use server' -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' let brain = null @@ -630,7 +630,7 @@ CMD ["npm", "start"] /** @type {import('next').NextConfig} */ const nextConfig = { experimental: { - serverComponentsExternalPackages: ['@soulcraft/brainy'] + serverComponentsExternalPackages: ['@soulcraftlabs/brainy'] }, webpack: (config, { isServer }) => { if (!isServer) { @@ -797,7 +797,7 @@ export function rateLimit(req, limit = 100, window = 60000) { // app/contexts/BrainyContext.jsx 'use client' import { createContext, useContext, useReducer, useEffect } from 'react' -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const BrainyContext = createContext() @@ -873,7 +873,7 @@ import { BrainyProvider } from '../app/components/BrainyProvider' import { Search } from '../app/components/Search' // Mock Brainy -jest.mock('@soulcraft/brainy', () => ({ +jest.mock('@soulcraftlabs/brainy', () => ({ Brainy: jest.fn().mockImplementation(() => ({ init: jest.fn().mockResolvedValue(undefined), find: jest.fn().mockResolvedValue([ diff --git a/docs/guides/optimistic-concurrency.md b/docs/guides/optimistic-concurrency.md index 268bc5fa..2984998b 100644 --- a/docs/guides/optimistic-concurrency.md +++ b/docs/guides/optimistic-concurrency.md @@ -32,7 +32,7 @@ Brainy 7.31.0 adds a per-entity revision counter so multiple writers can coordin Every distributed-job scheduler eventually wants this exact loop: ```ts -import { Brainy, RevisionConflictError } from '@soulcraft/brainy' +import { Brainy, RevisionConflictError } from '@soulcraftlabs/brainy' const LOCK_ID = '...uuid for this job slot...' @@ -137,7 +137,7 @@ await brain.addIfMissing({ // ← not a real API It's race-prone as a plain read-then-write: two concurrent imports both see "not found," both insert, you get duplicates. Without a unique-index primitive (which Brainy doesn't have today), close the race with whole-store CAS — read at a pinned generation, then commit only if nothing moved: ```ts -import { GenerationConflictError } from '@soulcraft/brainy' +import { GenerationConflictError } from '@soulcraftlabs/brainy' async function addIfMissingByEmail(email: string, data: string) { for (let attempt = 0; attempt < 5; attempt++) { diff --git a/docs/guides/quick-start.md b/docs/guides/quick-start.md index 097c55fe..d9a4e896 100644 --- a/docs/guides/quick-start.md +++ b/docs/guides/quick-start.md @@ -18,13 +18,13 @@ Get Brainy running in under a minute. ## 1. Install ```bash -npm install @soulcraft/brainy +npm install @soulcraftlabs/brainy ``` ## 2. Initialize ```typescript -import { Brainy, NounType, VerbType } from '@soulcraft/brainy' +import { Brainy, NounType, VerbType } from '@soulcraftlabs/brainy' const brain = new Brainy() await brain.init() @@ -67,7 +67,7 @@ await brain.relate({ ## 5. Query with Triple Intelligence ```typescript -import type { Result } from '@soulcraft/brainy' +import type { Result } from '@soulcraftlabs/brainy' // All three search paradigms in one call const results: Result[] = await brain.find({ diff --git a/docs/guides/standard-import-progress.md b/docs/guides/standard-import-progress.md index 9f2e2e5b..27dabe75 100644 --- a/docs/guides/standard-import-progress.md +++ b/docs/guides/standard-import-progress.md @@ -11,7 +11,7 @@ ### One Interface for Everything ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const brain = await Brainy.create() @@ -78,7 +78,7 @@ interface ImportProgress { ```typescript import { useState } from 'react' -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' function UniversalImportProgress({ file }: { file: File }) { const [progress, setProgress] = useState({ @@ -177,7 +177,7 @@ function UniversalImportProgress({ file }: { file: File }) { ```typescript import ora from 'ora' -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' async function importWithProgress(filePath: string) { const spinner = ora('Starting import...').start() diff --git a/docs/guides/storage-adapters.md b/docs/guides/storage-adapters.md index 06ec9f3a..a4224bc8 100644 --- a/docs/guides/storage-adapters.md +++ b/docs/guides/storage-adapters.md @@ -28,7 +28,7 @@ on-disk layout (memory's "disk" is a JS Map). ## Quick start ```ts -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' // Filesystem (recommended for any persistent workload): const brain = new Brainy({ @@ -134,7 +134,7 @@ config; the `type` is optional. If you want to skip the factory: ```ts -import { FileSystemStorage, MemoryStorage } from '@soulcraft/brainy' +import { FileSystemStorage, MemoryStorage } from '@soulcraftlabs/brainy' const fsStorage = new FileSystemStorage('./brainy-data') const memStorage = new MemoryStorage() diff --git a/docs/guides/subtypes-and-facets.md b/docs/guides/subtypes-and-facets.md index ff5de320..74311528 100644 --- a/docs/guides/subtypes-and-facets.md +++ b/docs/guides/subtypes-and-facets.md @@ -34,7 +34,7 @@ Three layers solve this: ### Write ```typescript -import { Brainy, NounType } from '@soulcraft/brainy' +import { Brainy, NounType } from '@soulcraftlabs/brainy' const brain = new Brainy() await brain.init() @@ -240,7 +240,7 @@ await brain.migrateField({ A realistic adoption sequence for a brain that started without these primitives: ```typescript -import { Brainy, NounType } from '@soulcraft/brainy' +import { Brainy, NounType } from '@soulcraftlabs/brainy' const brain = new Brainy({ storage: { type: 'filesystem', path: './brain-data' } }) await brain.init() diff --git a/docs/guides/upgrading-7-to-8.md b/docs/guides/upgrading-7-to-8.md index a3c64fb9..53aa2a5c 100644 --- a/docs/guides/upgrading-7-to-8.md +++ b/docs/guides/upgrading-7-to-8.md @@ -25,7 +25,7 @@ content — and how 8.0 recovers it for you. ## TL;DR -- **Just upgrade to `@soulcraft/brainy@8.0.12` (or later) and open the store.** +- **Just upgrade to `@soulcraftlabs/brainy@8.0.12` (or later) and open the store.** If a previous upgrade left VFS content stranded, 8.0.12 **heals it on open**, with no operator action. - Want to force or script it? Call **`await brain.vfs.adoptOrphanedBlobs()`**. @@ -90,7 +90,7 @@ So the operator action for a stranded store is simply: **upgrade to 8.0.12 and open it.** ```ts -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' // Opening the store is all that is required — recovery runs during init(). const brain = new Brainy({ storage: { type: 'filesystem', path: '/data/my-store' } }) @@ -182,5 +182,5 @@ and opening each store is sufficient. The recovery is copy-only, so no rollback of the recovery itself is ever needed. If you need to roll back the **whole** 7→8 upgrade, restore the directory from your pre-upgrade backup (retained automatically while recovery is incomplete, or -your own snapshot) and pin `@soulcraft/brainy@7.x`. 8.0 does not keep the old +your own snapshot) and pin `@soulcraftlabs/brainy@7.x`. 8.0 does not keep the old branch layout in place, so a directory-level restore is the rollback path. diff --git a/docs/guides/vue-integration.md b/docs/guides/vue-integration.md index 7f7c6a06..34d18ebf 100644 --- a/docs/guides/vue-integration.md +++ b/docs/guides/vue-integration.md @@ -12,7 +12,7 @@ Complete guide to integrating Brainy with Vue.js applications, covering Vue 3, N npm create vue@latest my-brainy-app cd my-brainy-app npm install -npm install @soulcraft/brainy +npm install @soulcraftlabs/brainy ``` ### Basic Setup @@ -574,7 +574,7 @@ Nuxt's server engine (Nitro) is the natural home for Brainy: it runs on Node/Bun ```javascript // server/utils/brain.js (server-only — Nitro never bundles this into the client) -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' let brainPromise @@ -1201,7 +1201,7 @@ import vue from '@vitejs/plugin-vue' export default defineConfig({ plugins: [vue()], ssr: { - external: ['@soulcraft/brainy'] + external: ['@soulcraftlabs/brainy'] } }) ``` diff --git a/docs/neural-extraction.md b/docs/neural-extraction.md index 989b1b60..cfb6d764 100644 --- a/docs/neural-extraction.md +++ b/docs/neural-extraction.md @@ -24,7 +24,7 @@ Brainy's neural extraction system uses a **4-signal ensemble architecture** to c ### Method 1: Brain Instance (Recommended) ```typescript -import { Brainy, NounType } from '@soulcraft/brainy' +import { Brainy, NounType } from '@soulcraftlabs/brainy' const brain = new Brainy() await brain.init() @@ -62,9 +62,9 @@ const people = await brain.extractEntities('...', { import { SmartExtractor, SmartRelationshipExtractor -} from '@soulcraft/brainy' +} from '@soulcraftlabs/brainy' // Or use subpath imports: -import { SmartExtractor } from '@soulcraft/brainy/neural/SmartExtractor' +import { SmartExtractor } from '@soulcraftlabs/brainy/neural/SmartExtractor' const brain = new Brainy() await brain.init() @@ -176,7 +176,7 @@ const withVectors = await brain.extractEntities(text, { **Direct entity type classifier.** Use when you have pre-detected candidates or need custom configuration. ```typescript -import { SmartExtractor, FormatContext } from '@soulcraft/brainy' +import { SmartExtractor, FormatContext } from '@soulcraftlabs/brainy' const extractor = new SmartExtractor(brain, { minConfidence: 0.7, // Threshold @@ -229,7 +229,7 @@ interface ExtractionResult { **Relationship type classifier.** Determines verb/relationship types between entities. ```typescript -import { SmartRelationshipExtractor } from '@soulcraft/brainy' +import { SmartRelationshipExtractor } from '@soulcraftlabs/brainy' const relExtractor = new SmartRelationshipExtractor(brain, { minConfidence: 0.6, @@ -286,7 +286,7 @@ const rel = await relExtractor.infer( **Full extraction orchestrator.** Handles candidate detection, classification, and deduplication. ```typescript -import { NeuralEntityExtractor } from '@soulcraft/brainy' +import { NeuralEntityExtractor } from '@soulcraftlabs/brainy' const extractor = new NeuralEntityExtractor(brain) @@ -607,7 +607,7 @@ const locations = entities.filter(e => e.type === NounType.Location) ### Example 2: Excel Data Classification ```typescript -import { SmartExtractor } from '@soulcraft/brainy' +import { SmartExtractor } from '@soulcraftlabs/brainy' const extractor = new SmartExtractor(brain) @@ -629,7 +629,7 @@ for (let i = 0; i < cells.length; i++) { ### Example 3: Relationship Extraction ```typescript -import { SmartRelationshipExtractor } from '@soulcraft/brainy' +import { SmartRelationshipExtractor } from '@soulcraftlabs/brainy' const relExtractor = new SmartRelationshipExtractor(brain) diff --git a/docs/transactions.md b/docs/transactions.md index fce7d10e..cbea39c0 100644 --- a/docs/transactions.md +++ b/docs/transactions.md @@ -204,8 +204,8 @@ await brain.add({ data: { name: 'Entity' }, type: NounType.Thing }) ### Basic Add Operation ```typescript -import { Brainy } from '@soulcraft/brainy' -import { NounType } from '@soulcraft/brainy/types' +import { Brainy } from '@soulcraftlabs/brainy' +import { NounType } from '@soulcraftlabs/brainy/types' const brain = new Brainy() await brain.init() @@ -428,7 +428,7 @@ await brain.relate({ ... }) // a crash here leaves the entity unlinked ```typescript import { describe, it, expect } from 'vitest' -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' describe('Transaction Tests', () => { it('should rollback on failure', async () => { diff --git a/docs/universal-display-augmentation.md b/docs/universal-display-augmentation.md index da42874c..464b91fb 100644 --- a/docs/universal-display-augmentation.md +++ b/docs/universal-display-augmentation.md @@ -23,7 +23,7 @@ The Universal Display Augmentation is a powerful AI-powered system that automati ### Basic Usage ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const brainy = new Brainy() await brainy.init() diff --git a/docs/vfs/PROJECTION_STRATEGY_API.md b/docs/vfs/PROJECTION_STRATEGY_API.md index 380862e1..f1319d5b 100644 --- a/docs/vfs/PROJECTION_STRATEGY_API.md +++ b/docs/vfs/PROJECTION_STRATEGY_API.md @@ -71,9 +71,9 @@ Let's build a projection that organizes files by priority (high, medium, low): ### Step 1: Create the Strategy Class ```typescript -import { BaseProjectionStrategy } from '@soulcraft/brainy/vfs/semantic' -import { Brainy } from '@soulcraft/brainy' -import { VirtualFileSystem, VFSEntity } from '@soulcraft/brainy/vfs' +import { BaseProjectionStrategy } from '@soulcraftlabs/brainy/vfs/semantic' +import { Brainy } from '@soulcraftlabs/brainy' +import { VirtualFileSystem, VFSEntity } from '@soulcraftlabs/brainy/vfs' export class PriorityProjection extends BaseProjectionStrategy { readonly name = 'priority' @@ -141,7 +141,7 @@ export class PriorityProjection extends BaseProjectionStrategy { ### Step 2: Register the Strategy ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' import { PriorityProjection } from './PriorityProjection' const brain = new Brainy() @@ -537,7 +537,7 @@ Use the projection's resolve cache: ```typescript import { describe, it, expect, beforeAll } from 'vitest' -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' import { PriorityProjection } from './PriorityProjection' describe('PriorityProjection', () => { @@ -714,7 +714,7 @@ async resolve(brain, vfs, value: string) { 3. Use appropriate limits: Don't fetch more than needed ### Type errors -1. Import correct types: `import { Brainy, VirtualFileSystem } from '@soulcraft/brainy'` +1. Import correct types: `import { Brainy, VirtualFileSystem } from '@soulcraftlabs/brainy'` 2. Use `as VFSEntity` when mapping results 3. Check BaseProjectionStrategy import diff --git a/docs/vfs/QUICK_START.md b/docs/vfs/QUICK_START.md index 8b0efce6..4a1f83dc 100644 --- a/docs/vfs/QUICK_START.md +++ b/docs/vfs/QUICK_START.md @@ -14,11 +14,11 @@ A file explorer that: ## ⚡ Step 1: Basic Setup (1 minute) ```bash -npm install @soulcraft/brainy +npm install @soulcraftlabs/brainy ``` ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' // ✅ CORRECT: Use filesystem storage for production const brain = new Brainy({ @@ -115,7 +115,7 @@ Here's a complete React component using the correct patterns: ```tsx import React, { useState, useEffect } from 'react' -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' export function FileExplorer() { const [brain, setBrain] = useState(null) @@ -288,8 +288,8 @@ Your file explorer is now working! Here's what to explore next: ### "Module not found" errors ```bash # Make sure you're using the right import -npm ls @soulcraft/brainy # Check version -npm install @soulcraft/brainy@latest # Update if needed +npm ls @soulcraftlabs/brainy # Check version +npm install @soulcraftlabs/brainy@latest # Update if needed ``` ### "VFS not initialized" errors diff --git a/docs/vfs/README.md b/docs/vfs/README.md index b95f0d7b..a94910c9 100644 --- a/docs/vfs/README.md +++ b/docs/vfs/README.md @@ -24,7 +24,7 @@ Brainy VFS is a revolutionary virtual filesystem that runs on top of Brainy's ne ## Quick Start ```javascript -import { VirtualFileSystem } from '@soulcraft/brainy/vfs' +import { VirtualFileSystem } from '@soulcraftlabs/brainy/vfs' // Initialize the VFS const vfs = new VirtualFileSystem({ @@ -381,7 +381,7 @@ Brainy VFS fully leverages Brainy's revolutionary Triple Intelligence system: ## Installation ```bash -npm install @soulcraft/brainy +npm install @soulcraftlabs/brainy ``` ## Requirements diff --git a/docs/vfs/ROADMAP.md b/docs/vfs/ROADMAP.md index 93c5b901..c8d15cd2 100644 --- a/docs/vfs/ROADMAP.md +++ b/docs/vfs/ROADMAP.md @@ -135,7 +135,7 @@ Mount VFS as a native filesystem on Linux/Mac/Windows. ```typescript // Planned (research phase) -import { mountVFS } from '@soulcraft/brainy/vfs/fuse' +import { mountVFS } from '@soulcraftlabs/brainy/vfs/fuse' await mountVFS(vfs, { mountPoint: '/mnt/brainy', @@ -160,7 +160,7 @@ These features would benefit from community contributions. If you're interested ### Express.js Static Middleware ```typescript // Wanted: Community contribution -import { createStaticMiddleware } from '@soulcraft/brainy/vfs/express' +import { createStaticMiddleware } from '@soulcraftlabs/brainy/vfs/express' app.use('/files', createStaticMiddleware(vfs, { index: ['index.html', 'index.md'], @@ -172,7 +172,7 @@ app.use('/files', createStaticMiddleware(vfs, { ### VSCode Extension ```typescript // Wanted: Community contribution -import { VFSProvider } from '@soulcraft/brainy/vfs/vscode' +import { VFSProvider } from '@soulcraftlabs/brainy/vfs/vscode' const provider = new VFSProvider(vfs) vscode.workspace.registerFileSystemProvider('brainy', provider) diff --git a/docs/vfs/SEMANTIC_VFS.md b/docs/vfs/SEMANTIC_VFS.md index 9298c822..f34ee9ae 100644 --- a/docs/vfs/SEMANTIC_VFS.md +++ b/docs/vfs/SEMANTIC_VFS.md @@ -327,7 +327,7 @@ console.log(id1 === id2 && id2 === id3) // true Create your own semantic dimensions: ```typescript -import { BaseProjectionStrategy } from '@soulcraft/brainy/vfs/semantic' +import { BaseProjectionStrategy } from '@soulcraftlabs/brainy/vfs/semantic' class PriorityProjection extends BaseProjectionStrategy { readonly name = 'priority' diff --git a/docs/vfs/VFS_API_GUIDE.md b/docs/vfs/VFS_API_GUIDE.md index e0c6a94c..5dcaaeb8 100644 --- a/docs/vfs/VFS_API_GUIDE.md +++ b/docs/vfs/VFS_API_GUIDE.md @@ -7,7 +7,7 @@ Brainy's Virtual Filesystem (VFS) provides a POSIX-like filesystem interface tha ## Quick Start ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' // Initialize Brainy const brain = new Brainy({ @@ -598,7 +598,7 @@ const user = await store.findById('users', 'user123') VFS uses standard POSIX-style errors: ```typescript -import { VFSError, VFSErrorCode } from '@soulcraft/brainy' +import { VFSError, VFSErrorCode } from '@soulcraftlabs/brainy' try { await vfs.readFile('/nonexistent.txt') diff --git a/docs/vfs/VFS_CORE.md b/docs/vfs/VFS_CORE.md index 1eeaf9f8..c1d502c0 100644 --- a/docs/vfs/VFS_CORE.md +++ b/docs/vfs/VFS_CORE.md @@ -280,7 +280,7 @@ GitBridge provides Git import/export capabilities: #### GitBridge Usage ```javascript // Import and instantiate GitBridge -import { GitBridge } from '@soulcraft/brainy' +import { GitBridge } from '@soulcraftlabs/brainy' const gitBridge = new GitBridge(vfs, brain) // Export VFS to Git repository structure @@ -452,7 +452,7 @@ This ordering prevents race conditions where file writes might fail because pare ## Complete Example ```javascript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' async function vfsExample() { // Initialize diff --git a/docs/vfs/VFS_GRAPH_TYPES.md b/docs/vfs/VFS_GRAPH_TYPES.md index 3c1f30f0..478bef7f 100644 --- a/docs/vfs/VFS_GRAPH_TYPES.md +++ b/docs/vfs/VFS_GRAPH_TYPES.md @@ -196,5 +196,5 @@ await brain.relate({ Always import and use the type enums: ```javascript -import { NounType, VerbType } from '@soulcraft/brainy' +import { NounType, VerbType } from '@soulcraftlabs/brainy' ``` \ No newline at end of file diff --git a/docs/vfs/VFS_INITIALIZATION.md b/docs/vfs/VFS_INITIALIZATION.md index 97e6b0bf..fd12fc71 100644 --- a/docs/vfs/VFS_INITIALIZATION.md +++ b/docs/vfs/VFS_INITIALIZATION.md @@ -5,7 +5,7 @@ The Brainy VFS is automatically initialized during `brain.init()`. No separate initialization needed! ```javascript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' // Create and initialize Brainy const brain = new Brainy({ @@ -71,7 +71,7 @@ VFS stores files as entities and relationships in the same graph as everything e ## Complete Example ```javascript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' async function useVFS() { // Initialize Brainy @@ -100,7 +100,7 @@ useVFS().catch(console.error) ## TypeScript Usage ```typescript -import { Brainy, VirtualFileSystem } from '@soulcraft/brainy' +import { Brainy, VirtualFileSystem } from '@soulcraftlabs/brainy' class FileManager { private brain: Brainy diff --git a/docs/vfs/building-file-explorers.md b/docs/vfs/building-file-explorers.md index 6bb31871..7514c12e 100644 --- a/docs/vfs/building-file-explorers.md +++ b/docs/vfs/building-file-explorers.md @@ -37,7 +37,7 @@ Brainy VFS provides safe, tree-aware methods that prevent these issues: ### Method 1: Use `getDirectChildren()` (Recommended) ```typescript -import { Brainy, VirtualFileSystem } from '@soulcraft/brainy' +import { Brainy, VirtualFileSystem } from '@soulcraftlabs/brainy' const brain = new Brainy() await brain.init() @@ -97,7 +97,7 @@ Here's a complete example using React: ```tsx import React, { useState, useEffect } from 'react' -import { VirtualFileSystem } from '@soulcraft/brainy' +import { VirtualFileSystem } from '@soulcraftlabs/brainy' interface FileNode { name: string @@ -177,7 +177,7 @@ function TreeView({ node, onToggle, expanded }) { If you must build trees manually from flat lists, use the `VFSTreeUtils`: ```typescript -import { VFSTreeUtils } from '@soulcraft/brainy/vfs' +import { VFSTreeUtils } from '@soulcraftlabs/brainy/vfs' // Get all entities somehow const allEntities = await vfs.getDescendants('/root') diff --git a/examples/bluesky-distributed-setup.js b/examples/bluesky-distributed-setup.js index 9e83cf25..e3b33506 100644 --- a/examples/bluesky-distributed-setup.js +++ b/examples/bluesky-distributed-setup.js @@ -7,7 +7,7 @@ * the Bluesky firehose with Brainy's distributed architecture */ -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' import { WebSocket } from 'ws' // ===================================================== diff --git a/examples/monitor-cache-performance.ts b/examples/monitor-cache-performance.ts index 9d50d476..87c965a2 100644 --- a/examples/monitor-cache-performance.ts +++ b/examples/monitor-cache-performance.ts @@ -14,7 +14,7 @@ * ts-node examples/monitor-cache-performance.ts */ -import { Brainy, NounType } from '@soulcraft/brainy' +import { Brainy, NounType } from '@soulcraftlabs/brainy' // ANSI color codes for pretty output const colors = { diff --git a/integrations/README.md b/integrations/README.md index aa3d795b..de156623 100644 --- a/integrations/README.md +++ b/integrations/README.md @@ -5,7 +5,7 @@ Connect Brainy to spreadsheets, BI tools, and external systems with zero configu ## Quick Start ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const brain = new Brainy({ integrations: true }) await brain.init() @@ -178,7 +178,7 @@ Webhooks include `X-Brainy-Signature` header with HMAC-SHA256 signature. ### Minimal (in-memory): ```typescript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const brain = new Brainy({ integrations: true }) await brain.init() @@ -194,7 +194,7 @@ console.log(brain.hub.getInstructions()) ```typescript import express from 'express' -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const app = express() const brain = new Brainy({ @@ -232,7 +232,7 @@ app.listen(3000, () => { ```typescript import { Hono } from 'hono' -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const app = new Hono() diff --git a/integrations/google-sheets/README.md b/integrations/google-sheets/README.md index b2b0af3a..8309a30a 100644 --- a/integrations/google-sheets/README.md +++ b/integrations/google-sheets/README.md @@ -99,7 +99,7 @@ Add the `BRAINY_URL` script property in Apps Script settings. The simplest way to enable all integrations: ```javascript -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const brain = new Brainy({ integrations: true }) await brain.init() @@ -112,7 +112,7 @@ With Express: ```javascript import express from 'express' -import { Brainy } from '@soulcraft/brainy' +import { Brainy } from '@soulcraftlabs/brainy' const app = express() const brain = new Brainy({ integrations: true }) diff --git a/package-lock.json b/package-lock.json index 70635835..c4f66561 100644 --- a/package-lock.json +++ b/package-lock.json @@ -1,12 +1,12 @@ { - "name": "@soulcraft/brainy", - "version": "10.4.1", + "name": "@soulcraftlabs/brainy", + "version": "10.4.4", "lockfileVersion": 3, "requires": true, "packages": { "": { - "name": "@soulcraft/brainy", - "version": "10.4.1", + "name": "@soulcraftlabs/brainy", + "version": "10.4.4", "license": "MIT", "dependencies": { "@msgpack/msgpack": "^3.1.2", diff --git a/package.json b/package.json index 4125b073..06ce0253 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,7 @@ { - "name": "@soulcraft/brainy", - "version": "10.4.1", + "name": "@soulcraftlabs/brainy", + "version": "10.4.4", + "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", "module": "dist/index.js", @@ -126,15 +127,16 @@ "license": "MIT", "private": false, "publishConfig": { - "access": "public" + "access": "public", + "registry": "https://source.soulcraft.com/api/packages/soulcraftlabs/npm/" }, - "homepage": "https://source.soulcraft.com/soulcraft/brainy", + "homepage": "https://source.soulcraft.com/soulcraftlabs/open-brainy", "bugs": { - "url": "https://source.soulcraft.com/soulcraft/brainy/issues" + "url": "https://source.soulcraft.com/soulcraftlabs/open-brainy/issues" }, "repository": { "type": "git", - "url": "git+https://source.soulcraft.com/soulcraft/brainy.git" + "url": "git+https://source.soulcraft.com/soulcraftlabs/open-brainy.git" }, "files": [ "dist/**/*.js", diff --git a/releases/brainy.json b/releases/brainy.json new file mode 100644 index 00000000..8f61c7f2 --- /dev/null +++ b/releases/brainy.json @@ -0,0 +1,76 @@ +{ + "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, 3–4× faster imports", + "items": [ + "Every runtime embeds with the same full-precision model — search quality no longer depends on where you run.", + "Bulk embedding measured 3.1–4.2× 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." +} diff --git a/releases/open-brainy.json b/releases/open-brainy.json new file mode 100644 index 00000000..582f4847 --- /dev/null +++ b/releases/open-brainy.json @@ -0,0 +1,110 @@ +{ + "product": "open-brainy", + "entries": [ + { + "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." +} diff --git a/scripts/emit-contract-manifest.mjs b/scripts/emit-contract-manifest.mjs new file mode 100644 index 00000000..be73d4ca --- /dev/null +++ b/scripts/emit-contract-manifest.mjs @@ -0,0 +1,128 @@ +#!/usr/bin/env node +/** + * Emit this build's API-contract manifest to docs/api-contract.json. + * + * WHY IT IS GENERATED, NOT WRITTEN: a hand-kept list of doors drifts from the + * code the first time somebody adds one. This reads the surface the build + * actually exposes — the prototype's own methods and accessors, the exported + * error classes, the `where` operator sets, the field-addressing vocabulary, + * the health verdicts — so a diff between two engines' manifests is a diff + * between two engines, never between two authors. + * + * Requirement marking (required / optional per door) is NOT derivable from the + * surface — it is a commitment, recorded with the contract's owner rather than + * here. This manifest carries the surface; the promise lives with the contract. + * + * Usage: node scripts/emit-contract-manifest.mjs [--check] + * --check exits non-zero when the committed manifest is stale. + */ + +import { writeFileSync, readFileSync, existsSync } from 'node:fs' +import { join, dirname } from 'node:path' +import { fileURLToPath } from 'node:url' + +const ROOT = join(dirname(fileURLToPath(import.meta.url)), '..') +const OUT = join(ROOT, 'docs', 'api-contract.json') + +const { Brainy } = await import(join(ROOT, 'dist', 'brainy.js')) +const errorsModule = await import(join(ROOT, 'dist', 'errors', 'brainyError.js')) +const versionModule = await import(join(ROOT, 'dist', 'utils', 'version.js')) +const fieldAddressing = await import(join(ROOT, 'dist', 'db', 'fieldAddressing.js')) + +/** Every own method and accessor on the class's prototype, minus the private ones. */ +function surfaceOf(ctor) { + const doors = [] + for (const name of Object.getOwnPropertyNames(ctor.prototype)) { + if (name === 'constructor' || name.startsWith('_')) continue + const descriptor = Object.getOwnPropertyDescriptor(ctor.prototype, name) + if (!descriptor) continue + if (typeof descriptor.value === 'function') { + doors.push({ name, kind: 'method', arity: descriptor.value.length }) + } else if (descriptor.get) { + doors.push({ name, kind: 'accessor' }) + } + } + return doors.sort((a, b) => a.name.localeCompare(b.name)) +} + +const errors = Object.entries(errorsModule) + .filter(([name, value]) => typeof value === 'function' && /Error$/.test(name)) + .map(([name]) => name) + .sort() + +// The operator sets, read from the engine's own refusal message so the +// manifest can never disagree with the validator. +const filterSource = readFileSync(join(ROOT, 'src', 'utils', 'metadataFilter.ts'), 'utf-8') +const acceptedMatch = filterSource.match(/const VALUE_OPERATORS = new Set\(\[([\s\S]*?)\]\)/) +if (!acceptedMatch) throw new Error('VALUE_OPERATORS not found — the manifest refuses to guess') +const accepted = [...acceptedMatch[1].matchAll(/'([^']+)'/g)].map((m) => m[1]).sort() + +const indexSource = readFileSync(join(ROOT, 'src', 'utils', 'metadataIndex.ts'), 'utf-8') +const refusedByIndex = ['endsWith', 'length', 'matches', 'startsWith'].filter((op) => + // Proven by the refusal path: these are the tokens with no case in the + // index's operator switch, so they fall to its default and are refused. + !new RegExp(`case '${op}':`).test(indexSource) +) +const servedOnIndex = accepted.filter((op) => !refusedByIndex.includes(op)) + +const manifest = { + contractVersion: versionModule.contractVersion(), + engine: '@soulcraftlabs/brainy', + compatibility: { + minor: + 'additive — a new optional door, a new served operator, a new error class; every existing implementation still conforms', + major: + 'breaking — a door removed, an answer narrowed, an ordering law changed, an optional door promoted to required, or an operator moved from served to refused' + }, + doors: surfaceOf(Brainy), + errors, + operators: { + accepted, + servedOnIndexPath: servedOnIndex, + refusedByIndexPath: refusedByIndex, + combinators: ['allOf', 'anyOf', 'not'] + }, + fieldAddressing: { + systemKeyPrefix: 'system.', + systemEntityScalars: [...(fieldAddressing.SYSTEM_ENTITY_SCALARS ?? [])].sort(), + systemRelationScalars: [...(fieldAddressing.SYSTEM_RELATION_SCALARS ?? [])].sort(), + plumbingFields: [...(fieldAddressing.PLUMBING_FIELDS ?? [])].sort() + }, + health: { + verdicts: ['pass', 'warn', 'fail'], + healKinds: ['none', 'repair', 'rebuild'], + servingWithholdingInvariants: [ + 'index-initialized', + 'durable-state-present', + 'manifest-residency', + 'replay-clean', + 'strand-latch' + ] + } +} + +const rendered = `${JSON.stringify(manifest, null, 2)}\n` + +if (process.argv.includes('--check')) { + if (!existsSync(OUT)) { + console.error(`docs/api-contract.json is missing — run: node scripts/emit-contract-manifest.mjs`) + process.exit(1) + } + if (readFileSync(OUT, 'utf-8') !== rendered) { + console.error( + `docs/api-contract.json is STALE — the public surface changed. Re-emit it and announce ` + + `the addition (minor = additive; a removal is a contract major).` + ) + process.exit(1) + } + console.log(`docs/api-contract.json is current (${manifest.doors.length} doors, contract ${manifest.contractVersion}).`) + process.exit(0) +} + +writeFileSync(OUT, rendered) +console.log( + `Wrote docs/api-contract.json — contract ${manifest.contractVersion}, ` + + `${manifest.doors.length} doors, ${manifest.errors.length} error classes, ` + + `${manifest.operators.accepted.length} operators ` + + `(${manifest.operators.refusedByIndexPath.length} refused by the index path).` +) diff --git a/scripts/release.sh b/scripts/release.sh index 5d03e66b..5d434320 100755 --- a/scripts/release.sh +++ b/scripts/release.sh @@ -15,11 +15,11 @@ NC='\033[0m' # No Color RELEASE_TYPE="${1:-patch}" # patch, minor, or major SKIP_TESTS=false DRY_RUN=false -# --source-only: the HOME leg only — tag, CI's publish to The Source, and the -# release page; NO storefront (npmjs) publish, NO pair verification, NO docs -# push. The pair-gate shape: a prerelease the fleet's other engine devDeps -# from our own registry while the pair is proven, never a public artifact. -# Refused for a non-prerelease version — a public floor is always a pair. +# --source-only is now a no-op: The Source is the one registry, so every +# release already ships Source-only — tag, CI's publish to The Source, the +# release page, and the docs push, with no separate storefront leg to skip. +# The flag is still accepted (for backward-compatible invocations) and just +# prints a notice; it no longer changes behavior. SOURCE_ONLY=false for arg in "$@"; do @@ -109,7 +109,7 @@ else ;; *) echo -e "${RED}❌ Invalid release type: ${RELEASE_TYPE}${NC}" - echo "Usage: ./scripts/release.sh [patch|minor|major|] [--dry-run] [--source-only (prereleases only)]" + echo "Usage: ./scripts/release.sh [patch|minor|major|] [--dry-run] [--source-only (no-op; The Source is the one registry)]" exit 1 ;; esac @@ -129,11 +129,7 @@ if [ "$PRERELEASE" = true ]; then echo -e "${YELLOW}⚠️ Prerelease → npm dist-tag '${NPM_TAG}', GitHub prerelease${NC}" fi if [ "$SOURCE_ONLY" = true ]; then - if [ "$PRERELEASE" != true ]; then - echo -e "${RED}❌ --source-only is for prereleases only: a non-prerelease version is a public floor and always ships as the byte-identical pair.${NC}" - exit 1 - fi - echo -e "${YELLOW}⚠️ --source-only → The Source (home) ONLY: no npmjs publish, no pair verification, no docs push${NC}" + echo -e "${YELLOW}⚠️ The Source is the one registry; --source-only is implied${NC}" fi echo "" @@ -158,7 +154,7 @@ else fi # Create new changelog entry -CHANGELOG_ENTRY="### [${NEW_VERSION}](https://source.soulcraft.com/soulcraft/brainy/compare/v${CURRENT_VERSION}...v${NEW_VERSION}) ($(date +%Y-%m-%d)) +CHANGELOG_ENTRY="### [${NEW_VERSION}](https://source.soulcraft.com/soulcraftlabs/open-brainy/compare/v${CURRENT_VERSION}...v${NEW_VERSION}) ($(date +%Y-%m-%d)) ${COMMITS} " @@ -209,9 +205,9 @@ echo -e "${GREEN}✅ Pushed to origin${NC}\n" # .forgejo/workflows/publish-source.yml, which builds and publishes on The # Source's own runner (datacenter-side: seconds, not the laptop's WAN timing # out on an 87MB tarball PUT). The laptop holds no home-registry publish -# credential anymore; it only waits for CI's result before trusting the -# home/npmjs pair enough to publish the storefront leg. -SOURCE_NPM_REG="https://source.soulcraft.com/api/packages/soulcraft/npm/" +# credential anymore; it only waits for CI's result before continuing on to +# the release page and the docs push. +SOURCE_NPM_REG="https://source.soulcraft.com/api/packages/soulcraftlabs/npm/" SOURCE_POLL_INTERVAL_S=15 SOURCE_POLL_MAX_ATTEMPTS=200 # 200 × 15s = 50 minutes — the runner is sequential and a busy day's ci.yml # backlog has twice exceeded the old 20-minute window (8.10.3, 9.0.0); @@ -219,7 +215,7 @@ SOURCE_POLL_MAX_ATTEMPTS=200 # 200 × 15s = 50 minutes — the runner is sequen echo -e "${BLUE}9️⃣ Waiting for CI to publish v${NEW_VERSION} to The Source registry (home)...${NC}" SOURCE_LANDED=false for ((attempt = 1; attempt <= SOURCE_POLL_MAX_ATTEMPTS; attempt++)); do - LANDED_VERSION=$(npm view "@soulcraft/brainy@${NEW_VERSION}" version "--@soulcraft:registry=${SOURCE_NPM_REG}" 2>/dev/null || echo "") + LANDED_VERSION=$(npm view "@soulcraftlabs/brainy@${NEW_VERSION}" version "--@soulcraftlabs:registry=${SOURCE_NPM_REG}" 2>/dev/null || echo "") if [ "$LANDED_VERSION" = "$NEW_VERSION" ]; then SOURCE_LANDED=true break @@ -232,62 +228,16 @@ if [ "$SOURCE_LANDED" = true ]; then echo -e "${GREEN}✅ CI published v${NEW_VERSION} to The Source${NC}\n" else echo -e "${RED}❌ CI's home publish did not land — check the workflow run on The Source; the pair must not diverge.${NC}" - echo -e "${RED} v${NEW_VERSION} was tagged and pushed, but @soulcraft/brainy@${NEW_VERSION} never became visible on the${NC}" - echo -e "${RED} Source registry after ${SOURCE_POLL_MAX_ATTEMPTS} attempts, ${SOURCE_POLL_INTERVAL_S}s apart. Aborting before npmjs.${NC}" + echo -e "${RED} v${NEW_VERSION} was tagged and pushed, but @soulcraftlabs/brainy@${NEW_VERSION} never became visible on the${NC}" + echo -e "${RED} Source registry after ${SOURCE_POLL_MAX_ATTEMPTS} attempts, ${SOURCE_POLL_INTERVAL_S}s apart. Aborting.${NC}" exit 1 fi -if [ "$SOURCE_ONLY" = true ]; then - echo -e "${YELLOW}9️⃣½ Storefront (npmjs) leg SKIPPED — --source-only: v${NEW_VERSION} lives on The Source under dist-tag '${NPM_TAG}' only${NC}\n" -else - echo -e "${BLUE}9️⃣½ Publishing to npmjs (storefront, dist-tag: ${NPM_TAG})...${NC}" - # BYTE-IDENTITY LAW: the storefront republishes CI's EXACT artifact — download - # the tarball The Source serves and publish that file, never a fresh local pack - # (a local rebuild can differ byte-wise, and the fleet verifies the pair by - # shasum across registries). - STOREFRONT_TMP="$(mktemp -d)" - (cd "$STOREFRONT_TMP" && npm pack "@soulcraft/brainy@${NEW_VERSION}" "--@soulcraft:registry=${SOURCE_NPM_REG}" >/dev/null) - SOURCE_TARBALL="$(ls "$STOREFRONT_TMP"/soulcraft-brainy-*.tgz)" - echo -e "${BLUE} home artifact: $(sha256sum "$SOURCE_TARBALL" | cut -d' ' -f1)${NC}" - npm publish "$SOURCE_TARBALL" --tag "$NPM_TAG" "--@soulcraft:registry=https://registry.npmjs.org/" - rm -rf "$STOREFRONT_TMP" - # Brainy is the only PUBLIC @soulcraft package — verify visibility after every publish. - npm access get status @soulcraft/brainy "--@soulcraft:registry=https://registry.npmjs.org/" || true - # Verify the pair is byte-identical by registry-reported shasum — divergence - # here means the storefront leg must be treated as failed, loudly. RETRIED - # with raw curl: npmjs metadata propagates with a lag measured in minutes, - # and a one-shot npm-view probe fired a false DIVERGENCE on 10.0.0 while a - # raw curl of the registry document already confirmed byte-identity. The - # probe now reads the registry JSON directly (no npm cache in the path) and - # gives propagation up to 5 minutes before calling the pair divergent. - NPMJS_VERIFY_ATTEMPTS=20 - NPMJS_VERIFY_INTERVAL_S=15 # 20 × 15s = 5 minutes of propagation grace - SOURCE_SHA=$(npm view "@soulcraft/brainy@${NEW_VERSION}" dist.shasum "--@soulcraft:registry=${SOURCE_NPM_REG}" 2>/dev/null || echo "source-unavailable") - PAIR_IDENTICAL=false - for ((attempt = 1; attempt <= NPMJS_VERIFY_ATTEMPTS; attempt++)); do - NPMJS_SHA=$(curl -fsSL "https://registry.npmjs.org/@soulcraft%2Fbrainy" 2>/dev/null \ - | node -e "let d='';process.stdin.on('data',c=>d+=c).on('end',()=>{try{const v=JSON.parse(d).versions[process.argv[1]];console.log(v?v.dist.shasum:'')}catch{console.log('')}})" "${NEW_VERSION}" \ - || echo "") - if [ -n "$NPMJS_SHA" ] && [ "$SOURCE_SHA" = "$NPMJS_SHA" ]; then - PAIR_IDENTICAL=true - break - fi - echo -e "${YELLOW} … npmjs metadata not settled (attempt ${attempt}/${NPMJS_VERIFY_ATTEMPTS}: '${NPMJS_SHA:-absent}' vs '${SOURCE_SHA}'); retrying in ${NPMJS_VERIFY_INTERVAL_S}s${NC}" - sleep "$NPMJS_VERIFY_INTERVAL_S" - done - if [ "$PAIR_IDENTICAL" = true ]; then - echo -e "${GREEN}✅ Published to npmjs — byte-identical pair (shasum ${NPMJS_SHA})${NC}\n" - else - echo -e "${RED}❌ REGISTRY DIVERGENCE: The Source shasum ${SOURCE_SHA} != npmjs shasum ${NPMJS_SHA} after ${NPMJS_VERIFY_ATTEMPTS} attempts — investigate before announcing${NC}\n" - exit 1 - fi -fi - # Step 11: Release object on The Source (presentational — the tag, CHANGELOG, # 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/soulcraft/brainy/releases" \ + if curl -sf -X POST "https://source.soulcraft.com/api/v1/repos/soulcraftlabs/open-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" @@ -298,29 +248,15 @@ else echo -e "${RED}⚠️ FORGEJO_RELEASE_TOKEN unset — no release page created; tag + CHANGELOG remain the record${NC}\n" fi -# 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. -if [ "$SOURCE_ONLY" = true ]; then - echo -e "${YELLOW}1️⃣2️⃣ Docs push SKIPPED — --source-only (a home-only prerelease publishes no public docs)${NC}\n" -else - echo -e "${BLUE}1️⃣2️⃣ 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${NC}\n" - fi -fi +# Step 12 RETIRED (2026-08-31, CORTEX-SITE-BRAINY-RENAME round 12, David-ruled): +# soulcraft.com/docs carries the paid product's documentation only. This +# engine's documentation home is THIS repository — README and docs/ — and the +# site serves 301s for the slugs this rail used to push. The push script stays +# in the tree for history; the rail no longer calls it. +echo -e "${BLUE}Docs step: this engine documents itself in its own repo (site push retired 2026-08-31)${NC}" echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}" echo -e "${GREEN}🎉 Release ${NEW_VERSION} complete!${NC}" echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}" echo "" -if [ "$SOURCE_ONLY" = true ]; then - echo -e "📦 npmjs: ${YELLOW}not published (--source-only)${NC}" -else - echo -e "📦 npm: ${BLUE}https://www.npmjs.com/package/@soulcraft/brainy/v/${NEW_VERSION}${NC}" -fi -echo -e "🏠 The Source: ${BLUE}https://source.soulcraft.com/soulcraft/brainy/releases/tag/v${NEW_VERSION}${NC}" +echo -e "🏠 The Source: ${BLUE}https://source.soulcraft.com/soulcraftlabs/open-brainy/releases/tag/v${NEW_VERSION}${NC}" diff --git a/src/brainy.ts b/src/brainy.ts index bfac8c08..da04577e 100644 --- a/src/brainy.ts +++ b/src/brainy.ts @@ -198,7 +198,12 @@ import { import { isDeterministicEmbedMode } from './embeddings/deterministicEmbedMode.js' import { GenerationConflictError, StoreInconsistentError } from './db/errors.js' import { BrainyError, GraphIndexNotReadyError, MetadataIndexNotReadyError, MigrationInProgressError, VectorIndexNotReadyError } from './errors/brainyError.js' -import { assessIndexReadiness, assessProviderHealth } from './utils/indexReadiness.js' +import { + assessIndexReadiness, + assessProviderHealth, + assessProviderRebuild, + describeRebuildProgress +} from './utils/indexReadiness.js' import { reconstructNounWrapper } from './db/factLog.js' import { asBrainyFieldRefusal } from './db/fieldAddressing.js' import { @@ -396,6 +401,15 @@ interface PlannedTransact { * marker outlives its write. */ markerRecords: FactMarkerRecord[] + /** + * Ids the batch's `{ op: 'update' }` unvector door (`vector: []`) needs to + * decrement on the vectored-noun ledger — consumed by `transact()` with a + * proper `await this.storage.noteVectorUnlanded?.(id)` per id, AFTER + * `commitTransaction` resolves (never for a rejected batch). Kept separate + * from `postCommit` (`Array<() => void>`, called synchronously, fire-and- + * forget) because the ledger hook is async and must be awaited. + */ + vectorUnlands: string[] } /** @@ -731,6 +745,24 @@ export class Brainy implements BrainyInterface { // Write acks NEVER await it; a failed background flush is LOUD and re-armed. private _persistDirtyWrites = 0 private _persistLastFlushAt = Date.now() + /** + * Whether a write has been committed since the last flush that ran. THE + * ENGINE DOES NO PERIODIC WORK WITHOUT A CAUSE: a brain nobody has written + * to has nothing to make durable, and a flush over it must cost nothing and + * say nothing. Before this, a flush called every provider, stamped the + * watermarks, persisted the generation counter and re-stamped the entity + * tree whether or not anything had changed — roughly 28 writes for a store + * that had not moved. + * + * WHAT THIS DOES NOT EXPLAIN, stated so nobody reads it as solved: a + * production process holding 21 brains printed "All indexes flushed to disk + * in 216-601ms" per brain every ~35s and idled at 1.26 cores with no writes + * for ten minutes. This engine's cadence is WRITE-DRIVEN — every trigger + * runs through noteWriteForPersistence, which only a committed write calls — + * so something was calling flush() on those brains, and this gate makes such + * a call free rather than accounting for it. The caller is still unidentified. + */ + private _dirtySinceLastFlush = false private _persistIdleTimer: ReturnType | null = null private _persistBackgroundFlight: Promise | null = null @@ -825,7 +857,18 @@ export class Brainy implements BrainyInterface { // Read-gate narration dedup: a degraded-but-serving or not-ready health // report narrates via prodLog.warn ONCE per (provider, report.generation) — // never once per read. Keyed on the provider instance itself. - private _lastNarratedHealthGeneration = new Map() + /** + * The last health narration emitted per provider, keyed by its CONTENT. + * + * This used to dedupe on the provider's `generation` counter, which bumps on + * every ledger mutation and every rebuild boundary — so a provider that + * bumps its generation on routine work re-emitted the same unchanged health + * line on every read that consulted it, and a provider that never bumped + * could suppress a line whose reasons had genuinely changed. The dedupe key + * is now what the line SAYS: an unchanged verdict is silent however the + * generation moves, and a changed verdict is always heard. + */ + private _lastNarratedHealth = new Map() constructor(config?: BrainyConfig) { // The reserved-field write policy died with the field-addressing law: @@ -943,14 +986,14 @@ export class Brainy implements BrainyInterface { * extends FileSystemStorage`) inherit new methods Brainy adds to * `FileSystemStorage` / `BaseStorage` automatically — `typeof` walks the * prototype chain, so there's no in-package version skew to worry about as - * long as the plugin's own dist resolves `@soulcraft/brainy` dynamically + * long as the plugin's own dist resolves `@soulcraftlabs/brainy` dynamically * (which Cortex 2.2.x onward does — see * `node_modules/@soulcraft/cor/dist/storage/mmapFileSystemStorage.js`). * * This helper exists for the **build/install** failure modes the import * resolution can't catch: * - Stale `node_modules` left over from a prior `bun install` against - * `@soulcraft/brainy ≤7.20.x`. + * `@soulcraftlabs/brainy ≤7.20.x`. * - Lockfile drift pinning brainy below the version that introduced the * method. * - Docker layer caches that reuse a `node_modules` from an earlier image. @@ -1089,21 +1132,84 @@ export class Brainy implements BrainyInterface { configureLogger({ level: LogLevel.DEBUG }) // Enable verbose logging } - // OPEN-PATH NARRATION: lightweight phase timing across the five - // named stretches of init — storage init / generation-store open+fold / - // index init+gate / VFS bootstrap / embedding-warm-started. Each - // `markPhase()` call records elapsed ms SINCE THE PREVIOUS checkpoint, - // so the buckets always sum to the pre-integration/warmOnOpen total. - // Silent under 2s; one `prodLog.warn` line naming every phase's ms - // above it, so the operator's next restart storm names its own slow - // phase instead of re-deriving it from a stack of raw timestamps. + // OPEN-PATH NARRATION: phase timing across the five named stretches of + // init — storage init / generation-store open+fold / index init+gate / + // VFS bootstrap / embedding-warm-started. Each `markPhase()` call records + // elapsed ms SINCE THE PREVIOUS checkpoint, so the buckets always sum to + // the pre-integration/warmOnOpen total. + // + // THE LAW THIS ENFORCES: an open is never silent for more than + // OPEN_HEARTBEAT_MS. A production service opening a 16 GB store logged + // NOTHING for three minutes and then began work — the operator could not + // tell a slow open from a hung one, and restarted into the same wall. + // Two mechanisms, both on the always-visible narration channel (the old + // breakdown used `prodLog.warn`, which production clamps away — that is + // why the three minutes were silent): + // - a heartbeat that names the phase currently running and its elapsed + // wall, every OPEN_HEARTBEAT_MS, for as long as the open lasts; + // - one line per phase AS IT ENDS, naming its wall and its cause, for + // any phase over OPEN_PHASE_NARRATE_MS. + // The heartbeat is unref'd and cleared in the `finally` below, so it can + // neither hold the process open nor outlive a failed init. It cannot fire + // inside a phase that blocks the event loop synchronously; such a phase + // must narrate its own progress (the generation-log fold does). + const OPEN_HEARTBEAT_MS = 5_000 + const OPEN_PHASE_NARRATE_MS = 2_000 + /** Phase order + what each one is paying for, quoted in its narration. */ + const OPEN_PHASES: ReadonlyArray<{ name: string; cause: string }> = [ + { name: 'storage-init', cause: 'opening the store and loading its count ledger' }, + { + name: 'generation-store-open-fold', + cause: 'opening the generation store: crash-recovery replay/fold, derived-family registration, format handshake' + }, + { name: 'index-init-gate', cause: 'constructing the derived indexes and gating them for serving' }, + { name: 'vfs-bootstrap', cause: 'bootstrapping the virtual filesystem' }, + { name: 'embedding-warm-started', cause: 'starting the background embedding warm' } + ] const initStart = Date.now() let lastPhaseCheckpoint = initStart + let currentPhaseIndex = 0 const phaseTimingsMs: Record = {} + const openHeartbeat: ReturnType = setInterval(() => { + const phase = OPEN_PHASES[currentPhaseIndex] + if (!phase) return + prodLog.narrate( + `[Brainy] open: still in phase ${currentPhaseIndex + 1}/${OPEN_PHASES.length} ` + + `"${phase.name}" after ${Math.round((Date.now() - lastPhaseCheckpoint) / 1000)}s ` + + `(${Math.round((Date.now() - initStart) / 1000)}s into the open) — ${phase.cause}` + ) + }, OPEN_HEARTBEAT_MS) + if (typeof openHeartbeat.unref === 'function') openHeartbeat.unref() + /** + * Narrate one STEP inside a phase when it turns out to be expensive. + * A phase that costs a minute and names only itself tells an operator + * where to look but not what to look at; this names the step. Silent + * under OPEN_PHASE_NARRATE_MS, so a fast open says nothing extra. + */ + const step = async (name: string, cause: string, run: () => Promise): Promise => { + const startedAt = Date.now() + try { + return await run() + } finally { + const elapsed = Date.now() - startedAt + if (elapsed >= OPEN_PHASE_NARRATE_MS) { + prodLog.narrate(`[Brainy] open: step "${name}" took ${elapsed}ms — ${cause}`) + } + } + } const markPhase = (name: string): void => { const now = Date.now() - phaseTimingsMs[name] = now - lastPhaseCheckpoint + const elapsed = now - lastPhaseCheckpoint + phaseTimingsMs[name] = elapsed lastPhaseCheckpoint = now + const finished = OPEN_PHASES[currentPhaseIndex] + if (elapsed >= OPEN_PHASE_NARRATE_MS && finished && finished.name === name) { + prodLog.narrate( + `[Brainy] open: phase ${currentPhaseIndex + 1}/${OPEN_PHASES.length} ` + + `"${name}" finished in ${elapsed}ms — ${finished.cause}` + ) + } + currentPhaseIndex++ } try { @@ -1166,7 +1272,7 @@ export class Brainy implements BrainyInterface { `and the flush-request RPC are disabled for this directory. ` + `Likely fix: clean install (\`rm -rf node_modules bun.lockb && ` + `bun install\`) or rebuild your container image to refresh ` + - `\`@soulcraft/brainy\` to ≥7.21. See docs/concepts/storage-adapters.md.` + `\`@soulcraftlabs/brainy\` to ≥7.21. See docs/concepts/storage-adapters.md.` ) } else { console.warn( @@ -1191,9 +1297,12 @@ export class Brainy implements BrainyInterface { // instances skip recovery (readers never write; the next writer // repairs). this.generationStore = new GenerationStore(this.storage) - const generationOpenResult = await this.generationStore.open({ - readOnly: this.config.mode === 'reader' - }) + const generationOpenResult = await step( + 'generation-store.open', + 'reading the generation manifest and committed ranges, opening the fact log and the ' + + 'packed segment tier, and folding any crash-recovery replay', + () => this.generationStore.open({ readOnly: this.config.mode === 'reader' }) + ) // The generation fact log is CANONICAL state, not a derived index — no // sweeper, GC, or blob-lifecycle path may ever delete under it. Declare @@ -1231,7 +1340,11 @@ export class Brainy implements BrainyInterface { // rollup invariants against the log head + live counters. Loud on // genuine incoherence (repairIndex heals), silent on absent/coherent, // benign-behind refreshes at the next flush. Never blocks open. - await this.verifyEntityTreeStamp() + await step( + 'verify-entity-tree-stamp', + 'comparing the entity tree\'s stamped generation and rollups against the store', + () => this.verifyEntityTreeStamp() + ) // 8.0 ⇄ native-provider version handshake: load the on-disk brain-format // marker (`_system/brain-format.json`) into an in-memory field NOW — @@ -1243,7 +1356,11 @@ export class Brainy implements BrainyInterface { // them from the canonical records and then re-stamps the marker AFTER the // rebuild verifies (non-destructive: a crash mid-rebuild leaves the old / // absent marker, so the next open idempotently re-rebuilds). - this._brainFormat = await readBrainFormat(this.storage) + this._brainFormat = await step( + 'read-brain-format', + 'reading the on-disk format marker that decides whether the derived indexes are stale', + () => readBrainFormat(this.storage) + ) this._indexEpochStale = this._brainFormat === null || this._brainFormat.indexEpoch !== EXPECTED_INDEX_EPOCH @@ -1254,7 +1371,11 @@ export class Brainy implements BrainyInterface { // upgrade verifies + stamps; retained on failure. No-op for a reader, for // non-filesystem storage, or for a brain with no persisted data. if (this._indexEpochStale && this.config.migrationBackup && !this.isReadOnly) { - await this.createMigrationBackupIfNeeded() + await step( + 'pre-upgrade-backup', + 'snapshotting the brain directory before a one-time format rebuild (migrationBackup)', + () => this.createMigrationBackupIfNeeded() + ) } // PHASE 2 of 5 — "generation-store open+fold": GenerationStore @@ -1417,10 +1538,27 @@ export class Brainy implements BrainyInterface { `[Brainy] Rebuilding indexes after crash recovery rolled back ` + `${generationOpenResult.rolledBackGenerations} uncommitted transaction(s)` ) + // SELF-REBUILD DEFERENCE, same law as the open gate: a provider that + // is already rebuilding itself from canonical is doing exactly this + // work. Kicking a second rebuild on top of it is redundant at best. + // Safe by ordering: the crash-recovery fold ran in the generation + // store's open, BEFORE any provider was constructed, so a provider + // rebuilding now is reading the repaired canonical records. + const kick = async (leg: string, provider: { rebuild: () => Promise }) => { + const rebuilding = assessProviderRebuild(provider) + if (rebuilding) { + prodLog.narrate( + `[Brainy] crash-recovery rebuild: the ${leg} provider is already ` + + `${describeRebuildProgress(rebuilding)} from canonical — not kicking a second one.` + ) + return + } + await provider.rebuild() + } await Promise.all([ - this.metadataIndex.rebuild(), - this.index.rebuild(), - this.graphIndex.rebuild() + kick('metadata', this.metadataIndex), + kick('vector', this.index as unknown as { rebuild: () => Promise }), + kick('graph', this.graphIndex) ]) } @@ -1504,11 +1642,24 @@ export class Brainy implements BrainyInterface { }).backfillBlobHistoryRefCountsIfNeeded() } + // LEG C (zero-norm/unvector-door law): migrate a legacy zero-norm VFS + // root BEFORE the vector-leg open gate below ever compares the + // canonical vectored-noun count against the vector index's size — see + // migrateLegacyZeroNormVfsRootIfNeeded's JSDoc for why this is a safe + // O(1) exception to "nothing at open may scale with brain size", and + // why it must run here rather than waiting on VirtualFileSystem's own + // (VFS-instance-gated) lazy migration. + await this.migrateLegacyZeroNormVfsRootIfNeeded() + // Rebuild indexes if needed for existing data. Runs to completion before // init() returns — there is no more first-query lazy path, so the flag // below (kept for getIndexStatus() API compatibility) simply flips true // once this open-time step has run. - await this.rebuildIndexesIfNeeded() + await step( + 'rebuild-indexes-if-needed', + 'the derived-index gate: each family\'s readiness verdict, and any build it asks for', + () => this.rebuildIndexesIfNeeded() + ) this.lazyRebuildCompleted = true // Check for pending data migrations @@ -1518,8 +1669,9 @@ export class Brainy implements BrainyInterface { // cache, roaring, msgpack, sort:topK, distance), HNSW/metadata/graph // index construction, the eager cold-load, id-resolver + connections- // codec wiring, crash-recovery index rebuild, the replay-gap check, - // legacy VFS blob adoption, blob-history backfill, and the - // rebuildIndexesIfNeeded() gate + migration check. + // legacy VFS blob adoption, blob-history backfill, the legacy + // zero-norm VFS root migration, and the rebuildIndexesIfNeeded() gate + // + migration check. markPhase('index-init-gate') // Register shutdown hooks for graceful count flushing (once globally) @@ -1580,7 +1732,11 @@ export class Brainy implements BrainyInterface { // Initialize VFS: Ensure VFS is ready when accessed as property // This eliminates need for separate vfs.init() calls - zero additional complexity this._vfs = new VirtualFileSystem(this) - await this._vfs.init() + await step( + 'vfs.init', + 'creating or adopting the VFS root and wiring the path resolver', + () => this._vfs!.init() + ) this._vfsInitialized = true // Mark VFS as fully initialized // 8.0 MVCC: infrastructure bootstrap (VFS root, etc.) is now the @@ -1604,7 +1760,11 @@ export class Brainy implements BrainyInterface { const storedArtifact = await this.storage .readRawObject(LOG_AUTHORITY_PATH) .catch(() => null) - const authority = await readLogAuthority(this.storage) + const authority = await step( + 'read-log-authority', + 'reading the stored storage-authority artifact', + () => readLogAuthority(this.storage) + ) this._logAuthority = authority if (authority.authority === 'log') { this.generationStore.setLogDurability('at-ack') @@ -1615,7 +1775,12 @@ export class Brainy implements BrainyInterface { this.generationStore.getFactLog() !== null ) { try { - await this.adoptLogAuthority() + await step( + 'adopt-log-authority', + 'the adoption oracle: verifying the log against canonical before flipping this ' + + 'brain to durable-at-ack, and backfilling any curable divergence', + () => this.adoptLogAuthority() + ) prodLog.info( '[Brainy] storage authority adopted at open: generation log ' + '(fleet default; oracle green; durable-at-ack enabled)' @@ -1655,8 +1820,16 @@ export class Brainy implements BrainyInterface { // this is where it lands. if (!this.isReadOnly) { try { - await this.bridgeLegacyPendingEmbedSidecars() - await this.recoverPendingEmbedsFromLog() + await step( + 'bridge-pending-embed-sidecars', + 'migrating any pre-log deferred-embed marker files into the generation log', + () => this.bridgeLegacyPendingEmbedSidecars() + ) + await step( + 'recover-pending-embeds', + 'folding the generation log\'s deferred-embed markers back into the pending set', + () => this.recoverPendingEmbedsFromLog() + ) if (this._pendingEmbedIds.size > 0) { prodLog.info( `[Brainy] ${this._pendingEmbedIds.size} deferred embed(s) pending from a previous ` + @@ -1758,7 +1931,7 @@ export class Brainy implements BrainyInterface { const phaseList = Object.entries(phaseTimingsMs) .map(([name, ms]) => `${name}=${ms}ms`) .join(', ') - prodLog.warn( + prodLog.narrate( `[Brainy] slow open: ${totalOpenMs}ms total (${phaseList}) — see the ` + `phase breakdown above to find which one to investigate first` ) @@ -1820,6 +1993,10 @@ export class Brainy implements BrainyInterface { // log — a plain string interpolation discards both stack and cause. const message = error instanceof Error ? error.message : String(error) throw new Error(`Failed to initialize Brainy: ${message}`, { cause: error }) + } finally { + // The open is over — succeeded or failed. Stop the heartbeat here so a + // failed init never leaves a timer narrating a phase nobody is running. + clearInterval(openHeartbeat) } } @@ -1837,76 +2014,112 @@ export class Brainy implements BrainyInterface { * NOTE: Registers globally (once for all instances) to avoid MaxListenersExceededWarning */ private registerShutdownHooks(): void { + /** + * The signal-path shutdown. THREE LAWS, each written by a production + * shutdown that looked clean and wasn't: + * + * 1. PER-INSTANCE ISOLATION. This used to be one `try` around a loop over + * every open brain: the first instance whose flush rejected aborted the + * loop, so every remaining brain kept its writer lock and its unwritten + * markers — and the process still exited 0. A pool of brains failed in + * a batch, not one at a time. + * 2. THE MARKER IS PART OF SHUTDOWN. Flushing the indexes without closing + * the generation store leaves the clean-shutdown marker unwritten, so + * the NEXT open reads the store as crashed and folds the whole + * generation log — measured in tens of seconds on a real store, paid on + * every restart, after a shutdown the operator saw exit 0. + * 3. THE LOCK IS ALWAYS GIVEN UP. In a `finally`, per instance: a process + * on its way out holds nothing. + */ const flushOnShutdown = async () => { console.log('Shutdown signal received - flushing pending data...') - try { - let flushedCount = 0 - for (const instance of Brainy.instances) { - if (instance.initialized) { - // Flush all buffered data, then close to release resources (timers, handles) - await Promise.all([ - (async () => { - if (instance.storage && typeof instance.storage.flushCounts === 'function') { - await instance.storage.flushCounts() - } - })(), - (async () => { - if (instance.metadataIndex && typeof instance.metadataIndex.flush === 'function') { - await instance.metadataIndex.flush() - } - })(), - (async () => { - if (instance.graphIndex && typeof instance.graphIndex.flush === 'function') { - await instance.graphIndex.flush() - } - })(), - (async () => { - if (instance.index && typeof instance.index.flush === 'function') { - await instance.index.flush() - } - })() - ]) - // Close components to stop timers that would prevent clean process exit - await Promise.all([ - (async () => { - if (instance.graphIndex && typeof instance.graphIndex.close === 'function') { - await instance.graphIndex.close() - } - })(), - (async () => { - const index = instance.index as JsHnswVectorIndex & VectorIndexOptionalHooks - if (index && typeof index.close === 'function') { - await index.close() - } - })(), - (async () => { - const metadataIndex = instance.metadataIndex as MetadataIndexManager & MetadataIndexOptionalHooks - if (metadataIndex && typeof metadataIndex.close === 'function') { - await metadataIndex.close() - } - })(), - // Release the writer lock so a successor process can take over. - // No-op for readers and for backends without locking. - (async () => { - if (instance.storage && typeof instance.storage.releaseWriterLock === 'function') { - await instance.storage.releaseWriterLock() - } - })(), - // Stop the flush-request watcher to release its interval timer. - (async () => { - if (instance.storage && typeof instance.storage.stopFlushRequestWatcher === 'function') { - instance.storage.stopFlushRequestWatcher() - } - })(), - ]) - flushedCount++ + let flushedCount = 0 + let failedCount = 0 + // Snapshot: close() splices Brainy.instances while we iterate. + for (const instance of [...Brainy.instances]) { + if (!instance.initialized) continue + try { + // Flush all buffered data (parallel across components, this brain only). + await Promise.all([ + (async () => { + if (instance.storage && typeof instance.storage.flushCounts === 'function') { + await instance.storage.flushCounts() + } + })(), + (async () => { + if (instance.metadataIndex && typeof instance.metadataIndex.flush === 'function') { + await instance.metadataIndex.flush() + } + })(), + (async () => { + if (instance.graphIndex && typeof instance.graphIndex.flush === 'function') { + await instance.graphIndex.flush() + } + })(), + (async () => { + if (instance.index && typeof instance.index.flush === 'function') { + await instance.index.flush() + } + })() + ]) + + // Close the generation store: persists the counter, advances the + // fold checkpoint, and stamps the clean-shutdown marker LAST — the + // one step that decides whether the next open adopts or folds. Law 2. + if (instance.generationStore && !instance.isReadOnly) { + await instance.generationStore.close() + } + + // Close components to stop timers that would prevent clean process exit + await Promise.all([ + (async () => { + if (instance.graphIndex && typeof instance.graphIndex.close === 'function') { + await instance.graphIndex.close() + } + })(), + (async () => { + const index = instance.index as JsHnswVectorIndex & VectorIndexOptionalHooks + if (index && typeof index.close === 'function') { + await index.close() + } + })(), + (async () => { + const metadataIndex = instance.metadataIndex as MetadataIndexManager & MetadataIndexOptionalHooks + if (metadataIndex && typeof metadataIndex.close === 'function') { + await metadataIndex.close() + } + })() + ]) + flushedCount++ + } catch (error) { + failedCount++ + console.error('Failed to flush one Brainy instance on shutdown:', error) + } finally { + // Law 3 — the lock and the watcher go regardless. + try { + if (instance.storage && typeof instance.storage.stopFlushRequestWatcher === 'function') { + instance.storage.stopFlushRequestWatcher() + } + } catch (error) { + console.error('Failed to stop the flush-request watcher on shutdown:', error) + } + try { + if (instance.storage && typeof instance.storage.releaseWriterLock === 'function') { + await instance.storage.releaseWriterLock() + } + } catch (error) { + console.error('Failed to release the writer lock on shutdown:', error) } } - if (flushedCount > 0) { - console.log(`Flushed successfully (${flushedCount} instance${flushedCount > 1 ? 's' : ''})`) - } - } catch (error) { - console.error('Failed to flush on shutdown:', error) + } + if (flushedCount > 0) { + console.log(`Flushed successfully (${flushedCount} instance${flushedCount > 1 ? 's' : ''})`) + } + if (failedCount > 0) { + console.error( + `${failedCount} Brainy instance${failedCount > 1 ? 's' : ''} did not complete shutdown — ` + + `their writer locks were released, but their next open will run crash recovery.` + ) } } @@ -1914,13 +2127,32 @@ export class Brainy implements BrainyInterface { // kept as statics so the last live instance's close() can deregister them // — the signal handles they hold are ref'd and would otherwise keep the // process alive forever after every brain is closed. + /** + * Exit the process ONLY when Brainy is the sole handler for this signal. + * + * Registering a signal listener suppresses Node's default terminate + * behaviour, so a library that attaches one must either exit or be sure + * someone else will. Brainy attaching one AND exiting was the wrong half + * of that choice for every host application with its own graceful + * shutdown: both handlers run concurrently, and whichever finishes first + * wins — a library flush finishing before an application's close() + * terminated that close mid-flight, at exit code 0, with locks and + * markers unwritten. When the host has its own handler (listener count + * above our own), the host owns the exit; Brainy only makes its data + * durable and steps aside. + */ + const exitIfSoleShutdownOwner = (signal: 'SIGTERM' | 'SIGINT'): void => { + if (process.listenerCount(signal) <= 1) { + process.exit(0) + } + } Brainy.sigtermListener = async () => { await flushOnShutdown() - process.exit(0) + exitIfSoleShutdownOwner('SIGTERM') } Brainy.sigintListener = async () => { await flushOnShutdown() - process.exit(0) + exitIfSoleShutdownOwner('SIGINT') } Brainy.beforeExitListener = async () => { // Self-deregister FIRST: Node re-emits 'beforeExit' after every event- @@ -2544,6 +2776,12 @@ export class Brainy implements BrainyInterface { * engine's own cadence (callers never call flush() in hot paths). */ private noteWriteForPersistence(): void { + // THE DIRTY WITNESS. Set on every committed write — both commit paths + // (single-op and transaction) end here, and the deferred-embed worker + // lands its vectors through the single-op path — BEFORE the policy check, + // so a `'manual'` consumer's explicit flush() is never skipped either. + // Cleared by a flush that actually runs; see flush(). + this._dirtySinceLastFlush = true const cfg = this.config.persistence if (this.isReadOnly || cfg?.policy === 'manual') return this._persistDirtyWrites++ @@ -2912,10 +3150,34 @@ export class Brainy implements BrainyInterface { // vector shape, is structurally impossible). The background worker // embeds + inserts. const deferringEmbed = params.deferEmbedding === true && !params.vector - const vector = deferringEmbed + let vector = deferringEmbed ? [] : params.vector || (await this.embed(params.data)) + // THE ZERO-NORM LAW (canonical write side): a zero-norm vector is not a + // vector — it never crosses an engine boundary (the engine pair's seam + // law). This engine's own cosine distance treats an all-zero vector + // safely (a zero-norm operand always scores MAXIMUM distance — see + // isZeroNormVector's JSDoc), but a downstream engine serving squared- + // euclidean distance cannot tell it apart from a legitimate origin + // point — a false attractor that silently darkened 150+ rows in a + // production deployment. The index belt (AddToVectorIndexOperation) + // already refuses to INDEX a zero-norm vector, but until now the + // CANONICAL write still persisted it and the vectored-noun ledger + // counted it — so a near-empty store whose only vectored row was + // zero-norm read "canonical vectored > 0, index size 0" and threw a + // not-ready error at open. Normalize HERE, before the dimension pin, + // the vectored-ledger flag (`SaveNounMetadataOperation`'s `hasVector`), + // and the index ops below ever see it, so it persists as the sanctioned + // "unvectored" `[]` shape instead — the canonical write still succeeds. + if (!deferringEmbed && vector.length > 0 && isZeroNormVector(vector)) { + prodLog.warn( + `[Brainy] add(): entity ${id} was given an explicit all-zero vector — ` + + `a zero-norm vector is not a vector; persisted unvectored ([]) instead.` + ) + vector = [] + } + // Ensure dimensions are set (a deferred-embed stub carries no dimension // information — the worker's real vector goes through the same guard). // Gated on `vector.length > 0`, not `!deferringEmbed`: ANY insert whose @@ -3623,25 +3885,53 @@ export class Brainy implements BrainyInterface { // often the host writes. const dataUnchanged = rawHasNewData && Brainy.sameEntityData(params.data, existing.data) const hasNewData = rawHasNewData && !dataUnchanged + + // THE ZERO-NORM LAW (canonical write side) — see add()'s matching + // comment: an explicit REAL all-zero vector is not a vector. Normalize + // to the sanctioned "unvectored" `[]` shape BEFORE the dimension + // check, the unvector-door decision below, and the index ops ever see + // it — a local copy; `params.vector` itself is never mutated. + let explicitVector = params.vector + if (explicitVector && explicitVector.length > 0 && isZeroNormVector(explicitVector)) { + prodLog.warn( + `[Brainy] update(): entity ${params.id} was given an explicit all-zero vector — ` + + `a zero-norm vector is not a vector; persisted unvectored ([]) instead.` + ) + explicitVector = [] + } + + // THE SANCTIONED UNVECTOR DOOR: `explicitVector` at length 0 (an + // explicit `vector: []`, or a real all-zero vector just normalized + // above) is an instruction to remove the vector NOW — never "please + // embed". `validateUpdateParams` already refuses combining it with + // `deferEmbedding: true` (an empty array is truthy, so that guard + // fires unconditionally on any explicit `vector`). Idempotent on an + // already-unvectored row: the ledger decrement near the end of this + // method is gated on the PRIOR vector actually having been real. + const isExplicitUnvector = explicitVector !== undefined && explicitVector.length === 0 + // MT5 deferred re-embedding: the OLD vector keeps serving semantic // search — stale-but-present, never absent (the flicker law) — until // the background worker embeds the new data and swaps it atomically. const deferringEmbed = - params.deferEmbedding === true && hasNewData && !params.vector - if (params.vector) { - if (this.dimensions && params.vector.length !== this.dimensions) { + params.deferEmbedding === true && hasNewData && !explicitVector + if (explicitVector) { + // A length-0 explicit vector (the unvector door) carries no + // dimension information — exempt from the check, mirroring add()'s + // own `vector.length > 0` gate on the dimension pin. + if (explicitVector.length > 0 && this.dimensions && explicitVector.length !== this.dimensions) { throw new Error( - `Vector dimension mismatch: expected ${this.dimensions}, got ${params.vector.length}` + `Vector dimension mismatch: expected ${this.dimensions}, got ${explicitVector.length}` ) } - vector = params.vector + vector = explicitVector } else if (hasNewData && !deferringEmbed) { vector = await this.embed(params.data) } // A deferred data change does NOT reindex now (the vector is unchanged; // the worker's atomic swap carries the real reindex later). const needsReindexing = Boolean( - (hasNewData && !deferringEmbed) || params.type || params.vector + (hasNewData && !deferringEmbed) || params.type || explicitVector ) // Always update the noun with new metadata @@ -3735,6 +4025,22 @@ export class Brainy implements BrainyInterface { ? [this.enqueuePendingEmbed(params.id)] : undefined + // Leg D — the unvector door clears a PENDING deferred-embed marker: + // without this, the worker would later embed this row's current data + // and silently re-vector it, defeating the caller's explicit "remove + // the vector now" instruction. The clear rides THIS SAME commit fact + // (an `embed.landed` record with an empty vector — the recovery fold + // disarms a pending marker on ANY `embed.landed` for the id, + // regardless of the vector it carries), so a crash between the write + // and the in-memory clear below still recovers disarmed. Mutually + // exclusive with `embedMarkers` above: `deferringEmbed` requires an + // ABSENT `explicitVector`, so the two branches never both apply. + const clearsPendingEmbed = isExplicitUnvector && this._pendingEmbedIds.has(params.id) + const commitRecords: FactMarkerRecord[] | undefined = + embedMarkers ?? (clearsPendingEmbed + ? [{ type: 'embed.landed', id: params.id, vector: [] }] + : undefined) + // Execute atomically with transaction system, generation-stamped as one // immutable Model-B generation (before-image = the entity's prior state). await this.persistSingleOp({ nouns: [params.id] }, async (tx) => { @@ -3823,7 +4129,33 @@ export class Brainy implements BrainyInterface { } } ] - : undefined, embedMarkers) + : undefined, commitRecords) + + // Leg D continued — the in-memory pending-embed clear runs only AFTER + // the commit above actually succeeded (an aborted update must not + // disarm a marker whose durable `embed.landed` twin was never + // written). + if (clearsPendingEmbed) { + this.clearPendingEmbed(params.id) + prodLog.warn( + `[Brainy] update(): entity ${params.id} had a pending deferred embed — ` + + `the unvector door cleared it ('vector: []' is an explicit instruction, ` + + `never "please embed").` + ) + } + + // Leg D — vectored-ledger decrement for the sanctioned unvector door. + // update()'s own metadata write goes through UpdateNounMetadataOperation + // (isNew=false), so the saveNounMetadata(..., hasVector) seam never + // fires here — noteVectorUnlanded is the ONLY seam, the same + // sanctioned hook unvectorNounForRootMigration() uses. Gated on the + // PRIOR vector having actually been real (non-empty, non-zero-norm): + // an already-unvectored row's second call is a true no-op — no + // decrement, matching the ledger-exactness law (never double-count, + // never drift negative). + if (isExplicitUnvector && existing.vector.length > 0 && !isZeroNormVector(existing.vector)) { + await this.storage.noteVectorUnlanded?.(params.id) + } // Aggregation hook (outside transaction — derived data). `existing` is // the full get() view — every reserved field top-level — and must be @@ -4304,6 +4636,19 @@ export class Brainy implements BrainyInterface { this._graphAdjacencyVerified = true return 'live' } + // A provider that is REBUILDING ITSELF gets a refusal that says so, + // with its own progress: open deliberately did not wait for it (see + // rebuildIndexesIfNeeded), so this door is temporarily closed and will + // open on its own. Anything else is a broken index needing a repair. + const rebuilding = assessProviderRebuild(this.graphIndex) + if (rebuilding) { + throw new GraphIndexNotReadyError( + `Graph adjacency index is ${describeRebuildProgress(rebuilding)} and is not serving ` + + `yet. find({ connected }), neighbors() and related() refuse rather than serve an ` + + `empty result. The brain is open and every other family is serving; this door opens ` + + `by itself when the provider reports serving — no action is needed.` + ) + } throw new GraphIndexNotReadyError( `Graph adjacency index is not serving (via ${assessment.via}): ` + `${assessment.reasons.join('; ') || 'not ready'}. find({ connected }), neighbors() and ` + @@ -4407,6 +4752,15 @@ export class Brainy implements BrainyInterface { this._metadataVerified = true return 'live' } + const rebuilding = assessProviderRebuild(this.metadataIndex) + if (rebuilding) { + throw new MetadataIndexNotReadyError( + `Metadata field index is ${describeRebuildProgress(rebuilding)} and is not serving ` + + `yet. find({ where }) and other filtered reads refuse rather than serve an empty ` + + `result. The brain is open and every other family is serving; this door opens by ` + + `itself when the provider reports serving — no action is needed.` + ) + } throw new MetadataIndexNotReadyError( `Metadata field index is not serving (via ${assessment.via}): ` + `${assessment.reasons.join('; ') || 'not ready'}. find({ where }) and other filtered ` + @@ -4536,6 +4890,15 @@ export class Brainy implements BrainyInterface { this._vectorVerified = true return 'live' } + const rebuilding = assessProviderRebuild(this.index) + if (rebuilding) { + throw new VectorIndexNotReadyError( + `Vector index is ${describeRebuildProgress(rebuilding)} and is not serving yet. ` + + `Semantic find({ query }) and proximity search refuse rather than serve an empty ` + + `result. The brain is open and every other family is serving; this door opens by ` + + `itself when the provider reports serving — no action is needed.` + ) + } throw new VectorIndexNotReadyError( `Vector index is not serving (via ${assessment.via}): ` + `${assessment.reasons.join('; ') || 'not ready'}. Semantic find({ query }) and ` + @@ -8194,6 +8557,11 @@ export class Brainy implements BrainyInterface { */ async clear(): Promise { await this.ensureInitialized() + // A clear mutates durable state without going through a commit path, so + // it must set the dirty witness itself — otherwise a `clear()` followed by + // `flush()` would find the brain "clean" and skip the entity-tree stamp, + // leaving a stamp that describes the population this call just removed. + this._dirtySinceLastFlush = true // Clear storage await this.storage.clear() @@ -9179,6 +9547,15 @@ export class Brainy implements BrainyInterface { hook() } + // Leg D — vectored-ledger decrements for this batch's unvector-door + // updates (see planTxUpdate's matching comment), applied after the + // commit point and properly awaited (unlike `postCommit`'s synchronous + // fire-and-forget hooks) — each is the same sanctioned hook + // unvectorNounForRootMigration() uses. + for (const id of plan.vectorUnlands) { + await this.storage.noteVectorUnlanded?.(id) + } + // Change feed: the batch's events share its single committed generation. // A rejected batch throws at commitTransaction and never reaches here. this.emitCommitted(plan.changeEvents, undefined, generation, timestamp) @@ -10422,7 +10799,8 @@ export class Brainy implements BrainyInterface { casUpdates: [], createdNouns: new Set(), changeEvents: [], - markerRecords: [] + markerRecords: [], + vectorUnlands: [] } for (const op of ops) { @@ -10544,9 +10922,22 @@ export class Brainy implements BrainyInterface { // marker-less committed row would be a silently missing vector, which is // the disallowed direction). The background worker embeds + inserts. const deferringEmbed = params.deferEmbedding === true && !params.vector - const vector = deferringEmbed + let vector = deferringEmbed ? [] : params.vector || (await this.embed(params.data)) + + // THE ZERO-NORM LAW — see the single-add() insert path's matching + // comment (a zero-norm vector is not a vector; never crosses an engine + // boundary). Normalized here BEFORE the dimension pin and the + // vectored-ledger `hasVector` flag below ever see it. + if (!deferringEmbed && vector.length > 0 && isZeroNormVector(vector)) { + prodLog.warn( + `[Brainy] transact add: entity ${id} was given an explicit all-zero vector — ` + + `a zero-norm vector is not a vector; persisted unvectored ([]) instead.` + ) + vector = [] + } + // Gated on `vector.length > 0` — see the single-add() insert path's // matching comment: an explicit `vector: []` carries no dimension // information either, deferred or not. @@ -10717,17 +11108,62 @@ export class Brainy implements BrainyInterface { const dataUnchanged = rawHasNewData && Brainy.sameEntityData(params.data, existing.data) const hasNewData = rawHasNewData && !dataUnchanged let vector = existing.vector - if (params.vector) { - if (this.dimensions && params.vector.length !== this.dimensions) { + + // THE ZERO-NORM LAW + THE SANCTIONED UNVECTOR DOOR — transact() mirror + // of update()'s matching block: an explicit REAL all-zero vector + // normalizes to `[]` (never crosses an engine boundary), and an + // explicit `vector: []` (post-normalization) is the sanctioned unvector + // instruction, exempt from the dimension check. `validateUpdateParams` + // already refuses combining it with `deferEmbedding: true`. + let explicitVector = params.vector + if (explicitVector && explicitVector.length > 0 && isZeroNormVector(explicitVector)) { + prodLog.warn( + `[Brainy] transact update: entity ${params.id} was given an explicit all-zero ` + + `vector — a zero-norm vector is not a vector; persisted unvectored ([]) instead.` + ) + explicitVector = [] + } + const isExplicitUnvector = explicitVector !== undefined && explicitVector.length === 0 + + if (explicitVector) { + if (explicitVector.length > 0 && this.dimensions && explicitVector.length !== this.dimensions) { throw new Error( - `Vector dimension mismatch: expected ${this.dimensions}, got ${params.vector.length}` + `Vector dimension mismatch: expected ${this.dimensions}, got ${explicitVector.length}` ) } - vector = params.vector + vector = explicitVector } else if (hasNewData) { vector = await this.embed(params.data) } - const needsReindexing = Boolean(hasNewData || params.type || params.vector) + const needsReindexing = Boolean(hasNewData || params.type || explicitVector) + + // Leg D — the unvector door clears a PENDING deferred-embed marker (see + // update()'s matching comment for the full rationale): the durable + // clear (an `embed.landed` record, empty vector) rides the batch's ONE + // commit fact via `plan.markerRecords`; the in-memory clear is deferred + // to `plan.postCommit` so an aborted batch never disarms a marker whose + // durable twin was never written. + const clearsPendingEmbed = isExplicitUnvector && this._pendingEmbedIds.has(params.id) + if (clearsPendingEmbed) { + plan.markerRecords.push({ type: 'embed.landed', id: params.id, vector: [] }) + plan.postCommit.push(() => { + this.clearPendingEmbed(params.id) + prodLog.warn( + `[Brainy] transact update: entity ${params.id} had a pending deferred embed — ` + + `the unvector door cleared it ('vector: []' is an explicit instruction, ` + + `never "please embed").` + ) + }) + } + + // Leg D — vectored-ledger decrement for the sanctioned unvector door, + // deferred to `plan.vectorUnlands` (consumed with a proper `await` in + // `transact()`, AFTER the commit succeeds — see its matching comment). + // Gated on the PRIOR vector having actually been real (non-empty, + // non-zero-norm): idempotent on an already-unvectored row. + if (isExplicitUnvector && existing.vector.length > 0 && !isZeroNormVector(existing.vector)) { + plan.vectorUnlands.push(params.id) + } const newMetadata = params.merge !== false @@ -11960,6 +12396,27 @@ export class Brainy implements BrainyInterface { return } + // A CLEAN BRAIN FLUSHES NOTHING, AND SAYS NOTHING. No write has been + // committed since the last flush, so every step below would re-persist + // state identical to what is already on disk — provider flushes, the + // watermark stamps, the generation counter, the entity-tree stamp — and + // print two lines announcing it. The witness is set by every committed + // write (see noteWriteForPersistence) and cleared here; a write landing + // DURING this flush sets it again, so it is never lost — the next flush + // does that write's work. This makes an unexplained flush FREE; it does + // not explain one (see _dirtySinceLastFlush). + if (!this._dirtySinceLastFlush) { + return + } + this._dirtySinceLastFlush = false + // An explicit flush IS a flush: tell the cadence so, or the very next + // write sees "30s since the last flush" (the cadence only counted its + // own) and kicks a background flush that has nothing left to do, and the + // idle timer fires two seconds later over writes this flush already + // persisted. + this._persistLastFlushAt = Date.now() + this._persistDirtyWrites = 0 + console.log('Flushing Brainy indexes and caches to disk...') const startTime = Date.now() @@ -12040,6 +12497,18 @@ export class Brainy implements BrainyInterface { * 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 { if (this.isReadOnly) return @@ -12050,7 +12519,7 @@ export class Brainy implements BrainyInterface { ]) await writeFamilyStamp(this.storage, ENTITY_TREE_STAMP_PATH, { family: 'entity-tree', - sourceGeneration: this.generationStore.generation(), + sourceGeneration: this.generationStore.committedGeneration(), members: { mode: 'rollup', invariants: { nounCount, verbCount } } }) } catch (error) { @@ -12063,16 +12532,24 @@ export class Brainy implements BrainyInterface { /** * @description Open-time coherence check for the entity tree's family stamp: - * compare `sourceGeneration` against the log head and the stamped rollup - * invariants against the live counters. Verdicts: + * compare `sourceGeneration` against the store's COMMITTED generation 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 { let stamp: FamilyStamp | null @@ -12089,11 +12566,16 @@ export class Brainy implements BrainyInterface { this.storage.getNounCount(), this.storage.getVerbCount() ]) - const verdict = verifyFamilyStamp(stamp, this.generationStore.generation(), { + const verdict = verifyFamilyStamp(stamp, this.generationStore.committedGeneration(), { nounCount, verbCount }) - if (verdict.state === 'incoherent') { + if (verdict.state === 'torn') { + await this.demoteTornEntityTreeStamp(stamp as FamilyStamp, verdict.stampSource, verdict.head, { + nounCount, + verbCount + }) + } else 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 ` + @@ -12107,6 +12589,92 @@ export class Brainy implements BrainyInterface { } } + /** + * @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 { + 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. @@ -12431,21 +12999,49 @@ export class Brainy implements BrainyInterface { const metadataStats = await this.metadataIndex.getStats() const graphSize = await this.graphIndex.size() - // 1. Index size parity. HNSW must hold at least one node per indexed entity. - if (hnswSize === metadataStats.totalEntries) { + // 1. Index size parity. HNSW must hold one node per VECTORED noun — the + // vectored-noun ledger (`getCanonicalCounts().vectors.all`), NOT the raw + // metadata-entry count: every store's VFS root is PERMANENTLY unvectored + // (`vector: []` by design — a zero-norm/empty vector never crosses into + // the index, see AddToVectorIndexOperation/JsHnswVectorIndex.rebuild()'s + // matching belts), and a not-yet-landed deferred embed is unvectored + // too. Comparing against total entries counted the always-unvectored + // root as a permanent 1-node "drift" on every VFS-having store — a false + // warn on an otherwise perfectly healthy handoff. `vectors.all` is + // already the documented coverage denominator for exactly this + // comparison (see `CanonicalCounts.vectors`'s JSDoc). Falls back to the + // metadata-entry count when the ledger is unavailable or suspect (a + // storage adapter without the optional hook, or an unrecounted store) — + // never worse than the prior behavior in that case. + const vectorLedgerForParity = await this.storage.getCanonicalCounts?.() + const vectorParityTarget = + vectorLedgerForParity && !vectorLedgerForParity.suspect + ? vectorLedgerForParity.vectors.all + : metadataStats.totalEntries + if (hnswSize === vectorParityTarget) { checks.push({ name: 'index-parity', status: 'pass', - message: `HNSW (${hnswSize}) and metadata index (${metadataStats.totalEntries}) agree.`, - details: { hnswSize, metadataEntries: metadataStats.totalEntries, graphRelationships: graphSize } + message: `HNSW (${hnswSize}) and the vectored-noun ledger (${vectorParityTarget}) agree.`, + details: { + hnswSize, + vectoredNouns: vectorParityTarget, + metadataEntries: metadataStats.totalEntries, + graphRelationships: graphSize + } }) } else { - const drift = Math.abs(hnswSize - metadataStats.totalEntries) + const drift = Math.abs(hnswSize - vectorParityTarget) checks.push({ name: 'index-parity', - status: drift > Math.max(10, metadataStats.totalEntries * 0.01) ? 'fail' : 'warn', - message: `HNSW (${hnswSize}) and metadata (${metadataStats.totalEntries}) differ by ${drift}. Run a rebuild if the gap is unexpected.`, - details: { hnswSize, metadataEntries: metadataStats.totalEntries, drift } + status: drift > Math.max(10, vectorParityTarget * 0.01) ? 'fail' : 'warn', + message: `HNSW (${hnswSize}) and the vectored-noun ledger (${vectorParityTarget}) differ by ${drift}. Run a rebuild if the gap is unexpected.`, + details: { + hnswSize, + vectoredNouns: vectorParityTarget, + metadataEntries: metadataStats.totalEntries, + drift + } }) } @@ -16066,6 +16662,79 @@ export class Brainy implements BrainyInterface { return !this.pluginRegistry.hasProvider('embeddings') } + /** + * @description LEG C of the zero-norm/unvector-door law — migrate a + * legacy zero-norm VFS root BEFORE the vector-leg open gate + * ({@link rebuildIndexesIfNeeded}'s `vectorCoverageGap` check) ever + * compares the canonical vectored-noun count against the vector index's + * size. A pre-fix store may have persisted the VFS root (the fixed + * all-zeros UUID) with a REAL all-zero placeholder vector — lawful inside + * brainy (`cosineDistance` treats a zero-norm operand as MAXIMUM distance, + * see {@link isZeroNormVector}'s JSDoc) but never indexed (the index belt + * refuses to insert a zero-norm vector) and never meant to cross an + * engine boundary. Left unmigrated, the canonical ledger still counts it + * as vectored while the vector index correctly holds nothing for it — a + * near-empty store whose ONLY vectored row is this zero-norm root reads + * "canonical vectored 1, index size 0" and throws + * `VectorIndexNotReadyError` at open, going DARK instead of serving. + * + * THE LIFECYCLE LAW: nothing at open may scale with brain size. This step + * is safe under that law BECAUSE the VFS root lives at a FIXED, + * well-known id (`00000000-0000-0000-0000-000000000000` — mirrors + * `VirtualFileSystem.VFS_ROOT_ID`; kept as a literal here, the same + * convention as the other reserved-root literals in this file and in + * `db/factLog.ts`/`db/portableGraph.ts` — `brainy.ts` cannot import + * `VirtualFileSystem.ts`, which itself imports `Brainy`) — this is ONE + * direct canonical read by id (`storage.getNoun`, the same O(1) + * fixed-path lookup {@link unvectorNounForRootMigration} itself uses + * internally), NEVER a listing or a walk over `entities/nouns/**`. An + * absent root (a store that has never used the VFS) is a no-op, no error. + * + * Runs UNCONDITIONALLY at every open, independent of whether a + * `VirtualFileSystem` is ever constructed this session — the vector-leg + * gate this fixes runs during Brainy's OWN init, before any + * `VirtualFileSystem` instance exists to run its own lazy migration at + * `doInitializeRoot()` (kept in place as the second line of defense for a + * VFS actually opened this session — belt AND suspenders, never either + * alone). + */ + private async migrateLegacyZeroNormVfsRootIfNeeded(): Promise { + const VFS_ROOT_ID = '00000000-0000-0000-0000-000000000000' + // TORN-TOLERANT: a torn root record is a recovery-walk healer's job + // (see tests/integration/recovery-walk-tolerance.test.ts — an init-time + // walk that meets a torn record narrates+counts, via the adapter's own + // loud floor at the read site, and heals PAST it; the open itself must + // still succeed), not this O(1) migration check's. Skip this open's + // migration attempt rather than aborting init(): this leg is a + // defensive EXTRA (the index belt + VirtualFileSystem's own + // doInitializeRoot() migration still stand as the other lines of + // defense), and it retries harmlessly at a later open once the root + // heals. + let root: HNSWNounWithMetadata | null + try { + root = await this.storage.getNoun(VFS_ROOT_ID) + } catch (err) { + if ((err as { code?: string }).code !== 'TORN_RECORD') throw err + prodLog.warn( + `[Brainy] open(): the VFS root's record is TORN — skipping the zero-norm root ` + + `migration check this open (the recovery walk is the healer; this migration ` + + `retries harmlessly once the root heals).` + ) + return + } + if (!root || !Array.isArray(root.vector) || root.vector.length === 0) return + if (!isZeroNormVector(root.vector)) return + const migrated = await this.unvectorNounForRootMigration(VFS_ROOT_ID) + if (migrated) { + prodLog.warn( + `[Brainy] open(): migrated the VFS root's legacy all-zero placeholder vector to ` + + `the unvectored shape (zero-norm vectors never cross an engine boundary) — run ` + + `before the vector-leg open gate compares canonical-vectored-count against the ` + + `vector index, so a near-empty store never reads a false coverage gap.` + ) + } + } + /** * SANCTIONED, ONE-TIME MIGRATION HOOK — rewrite a canonical noun's * persisted vector from a real (non-empty) vector to the "unvectored" @@ -16075,13 +16744,18 @@ export class Brainy implements BrainyInterface { * sanctioned {@link StorageAdapter.noteVectorUnlanded} hook — so the * coverage ledger never silently drifts. * - * Exists SOLELY for the VFS root zero-norm migration (see - * `VirtualFileSystem.doInitializeRoot()`, which detects a persisted root - * whose vector is the legacy all-zero placeholder and calls this once per - * store). This is NOT a general-purpose "clear my vector" API — ordinary - * application data has no sanctioned path from vectored back to - * unvectored (`update()` refuses an empty vector as a dimension mismatch, - * by design). Never call this outside the VFS root migration. + * Exists SOLELY for the VFS root zero-norm migration, called from two + * sites that detect the same legacy shape (a persisted root whose vector + * is the legacy all-zero placeholder): {@link migrateLegacyZeroNormVfsRootIfNeeded} + * (this brain's own init sequence, BEFORE the vector-leg open gate — Leg + * C of the zero-norm/unvector-door law) and + * `VirtualFileSystem.doInitializeRoot()` (the second line of defense, for + * a VFS actually constructed this session). This is NOT the general- + * purpose unvector API — ordinary application data uses the sanctioned + * unvector DOOR instead (`update({ id, vector: [] })` / the same op inside + * `transact()`), which decrements the ledger and clears any pending + * deferred-embed marker inline; it does not call this method. Never call + * this outside a VFS root migration. * * Idempotent: a noun already unvectored (`vector.length === 0`) or absent * is a no-op — safe to call on every `init()`. @@ -16203,8 +16877,19 @@ export class Brainy implements BrainyInterface { if (legacyEntityPaths.length === 0) { // Already flat (root entities, no head-branch entities) → stamp the marker // so future opens short-circuit. A genuinely empty/fresh dir gets no marker. - const rootEntities = await probe.listRawObjects('entities') - if (rootEntities.length > 0) { + // "Are there any entities?" is answered by ONE directory read, not by a + // recursive listing of every file in the tree: this runs on the open path + // of every store that does not yet carry the marker (a restore, a store + // built by an older release), and on a large store that listing walks the + // whole canonical tree to learn a boolean. + const oneLevel = ( + probe as unknown as { listRawPrefixes?: (prefix: string) => Promise } + ).listRawPrefixes + const hasRootEntities = + typeof oneLevel === 'function' + ? (await oneLevel.call(probe, 'entities')).length > 0 + : (await probe.listRawObjects('entities')).length > 0 + if (hasRootEntities) { await probe.writeRawObject('_system/migration-layout.json', { layout: 'flat-v8', version: 8, @@ -16703,16 +17388,34 @@ export class Brainy implements BrainyInterface { if (assessment.reasons.length > 0 && assessment.report != null) { const generation = assessment.report.generation - if (this._lastNarratedHealthGeneration.get(provider) !== generation) { - this._lastNarratedHealthGeneration.set(provider, generation) - prodLog.warn( - `[Brainy] ${assessment.report.provider} health (generation ${generation}): ` + - assessment.reasons.join('; ') - ) + // Dedupe by CONTENT, not by the provider's generation counter — see + // _lastNarratedHealth. The generation is still REPORTED (an operator + // wants to know which generation produced the verdict); it just no + // longer decides whether the line is worth saying. + const line = + `[Brainy] ${assessment.report.provider} health (generation ${generation}): ` + + assessment.reasons.join('; ') + const key = `${assessment.report.provider}\u0000${assessment.reasons.join('; ')}` + if (this._lastNarratedHealth.get(provider) !== key) { + this._lastNarratedHealth.set(provider, key) + prodLog.warn(line) } } if (assessment.readiness === 'not-ready') { + // A provider REBUILDING ITSELF gets a refusal that says so, with its + // own progress: open deliberately did not wait for it, this door is + // temporarily closed, and it opens by itself. Distinct from a broken + // index, which needs an operator. + const rebuilding = assessProviderRebuild(provider) + if (rebuilding) { + throw new ErrorClass( + `${name} index is ${describeRebuildProgress(rebuilding)} and is not serving yet. ` + + `Reads of this family refuse rather than serve an empty result. The brain is open ` + + `and every other family is serving; this door opens by itself when the provider ` + + `reports serving — no action is needed.` + ) + } throw new ErrorClass( `${name} index is not serving (via ${assessment.via}): ` + `${assessment.reasons.join('; ') || 'not ready'}. Reads refuse rather than serve an ` + @@ -17035,9 +17738,37 @@ export class Brainy implements BrainyInterface { // by awaitMigrationLock meanwhile (nothing serves from a half-built index). // Gated per-index, so a non-migrating sibling still rebuilds when it needs // to; a migrating provider is skipped even under epoch-drift or size()===0. - const metadataMigrating = this.providerIsMigrating(this.metadataIndex) - const vectorMigrating = this.providerIsMigrating(this.index) - const graphMigrating = this.providerIsMigrating(this.graphIndex) + // SELF-REBUILD DEFERENCE (the sibling of the migration lock, and the + // reason a production open took 641 seconds): a provider that reports + // `rebuildInProgress()` is ALREADY rebuilding its own index. Brainy must + // neither start a second rebuild nor WAIT for the provider's — init() + // returns, every other family serves, and that family's own doors refuse + // by name (carrying this progress) until the provider reports serving. + // A provider without the hook behaves exactly as before. + const metadataRebuilding = assessProviderRebuild(this.metadataIndex) + const vectorRebuilding = assessProviderRebuild(this.index) + const graphRebuilding = assessProviderRebuild(this.graphIndex) + for (const [leg, progress] of [ + ['metadata', metadataRebuilding], + ['vector', vectorRebuilding], + ['graph', graphRebuilding] + ] as const) { + if (progress) { + prodLog.narrate( + `[Brainy] open(): the ${leg} provider is ${describeRebuildProgress(progress)} — ` + + `open does NOT wait for it. The brain opens now, every other family serves, and ` + + `${leg} reads refuse by name until the provider reports itself serving.` + ) + } + } + + const metadataMigrating = + this.providerIsMigrating(this.metadataIndex) || metadataRebuilding !== null + const vectorMigrating = this.providerIsMigrating(this.index) || vectorRebuilding !== null + const graphMigrating = this.providerIsMigrating(this.graphIndex) || graphRebuilding !== null + // The epoch stamp certifies EVERY derived index, so it must not advance + // while any family is still being built — by a migration lock or by the + // provider itself. const anyMigrating = metadataMigrating || vectorMigrating || graphMigrating // Per-leg decision, in precedence order: a migrating provider owns its @@ -17249,6 +17980,15 @@ export class Brainy implements BrainyInterface { // when the metadata provider holds the migration lock: a 0 count there // reflects its in-place rebuild in progress, not a missed rebuild, so // forcing a second rebuild would collide with the provider's own. + // THREE states, not two. `metadataMigrating` above is true for a + // provider holding the migration lock AND for one that reports it is + // rebuilding itself — a provider whose rebuild() returns once the + // rebuild is OWNED AND RUNNING (online, its doors refusing by name) + // legitimately reports 0 entries here, and calling that CRITICAL would + // print a false alarm and kick a redundant second rebuild on every + // first contact. The check's real class — a rebuild that ran to + // completion and produced nothing — is untouched: a provider reporting + // 0 entries with NO rebuild in progress still trips it. if (metadataCountAfter === 0 && totalCount > 0 && !metadataMigrating) { console.error( `[Brainy] CRITICAL: Metadata index has 0 entries but storage has ${totalCount} entities. ` + @@ -17807,17 +18547,93 @@ export class Brainy implements BrainyInterface { * invariant-driven pass (it was already rebuilt unconditionally — a second, * report-driven pass over the same family would be redundant at best). * + * NARRATION IS PART OF THE CONTRACT. A repair on a production store ran for + * more than thirty minutes at a full core with NOT ONE log line between its + * start and its end while the doors kept serving; the operator could tell it + * was alive only from `top`. Every phase now announces itself before it + * works, a heartbeat names the phase still running every five seconds, and + * each phase reports its own wall — carried in the receipt as + * `durationMs` per family, so nobody has to infer progress from CPU. + * * @param options.rebuild - Family name(s) to unconditionally rebuild, or `'all'` for all three (`'metadata' | 'graph' | 'vector'`). - * @returns The full per-family receipt (see {@link RepairReport}); also narrated via `prodLog.warn`. + * @returns The full per-family receipt (see {@link RepairReport}); also narrated as it goes. */ async repairIndex(options?: { rebuild?: Array<'metadata' | 'graph' | 'vector'> | 'all' }): Promise { await this.ensureInitialized() + // A repair recounts, prunes and rebuilds outside the commit paths; the + // dirty witness is set so a caller's flush after a repair does its normal + // work rather than finding the brain "clean". + this._dirtySinceLastFlush = true const startedAt = Date.now() const families: RepairFamilyReport[] = [] - const record = (family: string, entry: Omit): void => { - families.push({ family, ...entry }) + + // THE REPAIR HEARTBEAT — the same law the open obeys: no stretch of work + // may be silent for more than REPAIR_HEARTBEAT_MS. Unref'd (it never holds + // a process open) and cleared in the `finally` below. + const REPAIR_HEARTBEAT_MS = 5_000 + let currentPhase = 'starting' + let currentPhaseCause = 'preparing the repair' + let phaseStartedAt = Date.now() + const heartbeat = setInterval(() => { + prodLog.narrate( + `[Brainy] repairIndex: still in "${currentPhase}" after ` + + `${Math.round((Date.now() - phaseStartedAt) / 1000)}s ` + + `(${Math.round((Date.now() - startedAt) / 1000)}s into the repair) — ${currentPhaseCause}` + ) + }, REPAIR_HEARTBEAT_MS) + if (typeof heartbeat.unref === 'function') heartbeat.unref() + + /** Announce a phase before it does any work, and start its clock. */ + const beginPhase = (name: string, cause: string): void => { + currentPhase = name + currentPhaseCause = cause + phaseStartedAt = Date.now() + prodLog.narrate(`[Brainy] repairIndex: "${name}" started — ${cause}`) } + /** + * Close the current phase: stamp its wall into the receipt row and say + * what it did. Every family row carries its own `durationMs`. + */ + const record = (family: string, entry: Omit): void => { + const durationMs = Date.now() - phaseStartedAt + families.push({ family, ...entry, durationMs }) + prodLog.narrate( + `[Brainy] repairIndex: "${family}" finished in ${durationMs}ms — ` + + (entry.checked + ? `${entry.healed} heal(s)${entry.rebuilt ? ', rebuilt' : ''}` + + (entry.detail ? ` (${entry.detail})` : '') + : `skipped (${entry.skipped ?? entry.reason ?? 'no reason given'})`) + ) + phaseStartedAt = Date.now() + } + + try { + return await this.runRepairIndexPhases(options, families, record, beginPhase, startedAt) + } finally { + clearInterval(heartbeat) + } + } + + /** + * @description The phases of {@link repairIndex}, separated so its heartbeat + * can live in a `finally` around them. Not a public door — see `repairIndex` + * for the contract. + * @param options - As `repairIndex`. + * @param families - The receipt rows being accumulated. + * @param record - Closes a phase: stamps its wall and narrates its outcome. + * @param beginPhase - Announces a phase before it works. + * @param startedAt - When the repair began, for the closing line. + * @returns The full receipt. + */ + private async runRepairIndexPhases( + options: { rebuild?: Array<'metadata' | 'graph' | 'vector'> | 'all' } | undefined, + families: RepairFamilyReport[], + record: (family: string, entry: Omit) => void, + beginPhase: (name: string, cause: string) => void, + startedAt: number + ): Promise { + // Prune orphaned canonical containers left by the pre-8.3.1 partial-delete // defect: a delete that removed the metadata (content) leg but left the // vector leg + the entity directory (a "ghost"), or left an empty directory @@ -17831,6 +18647,10 @@ export class Brainy implements BrainyInterface { rebuildSubtypeCounts?: () => Promise } if (typeof pruner.pruneOrphanedEntities === 'function') { + beginPhase( + 'orphaned-containers', + 'walking every canonical id directory for ghost/scar containers left by a partial delete' + ) const orphans = await pruner.pruneOrphanedEntities() const pruned = orphans.nouns.length + orphans.verbs.length record('orphaned-containers', { @@ -17841,7 +18661,7 @@ export class Brainy implements BrainyInterface { : {}) }) if (pruned > 0) { - prodLog.warn( + prodLog.narrate( `[Brainy] repairIndex() pruned ${orphans.nouns.length} orphaned noun + ` + `${orphans.verbs.length} orphaned verb container(s) left by a pre-8.3.1 ` + `partial delete.` @@ -17857,6 +18677,10 @@ export class Brainy implements BrainyInterface { // correct itself. rebuildTypeCounts() recomputes EVERY counter rollup // (scalar totals + per-type maps + type-statistics arrays) from one // canonical walk and persists them. + beginPhase( + 'count-rollups', + 'ONE canonical walk recomputing every counter rollup — scalar totals, per-type maps, type statistics' + ) await pruner.rebuildTypeCounts?.() await pruner.rebuildSubtypeCounts?.() record('count-rollups', { @@ -17879,6 +18703,10 @@ export class Brainy implements BrainyInterface { // concurrent writers. Canonical metadata.path is the truth; only VFS // containment edges are touched. Loud per repair. if (this._vfsInitialized && this._vfs) { + beginPhase( + 'vfs-containment', + 'reconciling VFS containment edges against canonical metadata.path' + ) const containment = await this._vfs.repairContainment() record('vfs-containment', { checked: true, @@ -17888,7 +18716,7 @@ export class Brainy implements BrainyInterface { : {}) }) if (containment.removed + containment.restored > 0) { - prodLog.warn( + prodLog.narrate( `[Brainy] repairIndex() reconciled VFS containment: removed ${containment.removed} ` + `stale/duplicate edge(s), restored ${containment.restored} missing edge(s).` ) @@ -17899,17 +18727,25 @@ export class Brainy implements BrainyInterface { record('vfs-containment', { checked: false, healed: 0, skipped: 'VFS not initialized' }) } + beginPhase( + 'metadata-corruption', + 'detect-and-repair pass over the metadata index' + ) await this.metadataIndex.detectAndRepairCorruption() record('metadata-corruption', { checked: true, healed: 0, detail: 'detect-and-repair pass ran (see its own narration for repairs)' }) // Lift a failed-rollback write-quarantine: force a full rebuild so the // derived indexes are provably reconciled with canonical, then clear the // flag so writes resume. if (this.storeInconsistency) { + beginPhase( + 'write-quarantine', + 'full derived-index rebuild to lift the quarantine set by a failed transaction rollback' + ) await this.rebuildIndexesIfNeeded(true) const cleared = this.storeInconsistency record('write-quarantine', { checked: true, healed: 1, detail: `lifted (${cleared.records.length} record(s) reconciled)` }) this.storeInconsistency = null - prodLog.warn( + prodLog.narrate( `[Brainy] repairIndex() reconciled the store and LIFTED the write-quarantine ` + `set by a failed transaction rollback (${cleared.records.length} record(s) affected). ` + `Writes are re-enabled.` @@ -17940,9 +18776,9 @@ export class Brainy implements BrainyInterface { record(`provider:${familyName}`, { checked: false, healed: 0, skipped: 'no rebuild() contract' }) continue } - prodLog.warn( - `[Brainy] repairIndex(): explicit rebuild requested for '${familyName}' — ` + - `rebuilding unconditionally (no invariant consulted).` + beginPhase( + `provider:${familyName}`, + `explicit rebuild requested — rebuilding '${familyName}' unconditionally, no invariant consulted` ) // The metadata family routes through the online build-beside // orchestrator (B3 D3) instead of the provider's own rebuild() — @@ -17959,7 +18795,7 @@ export class Brainy implements BrainyInterface { rebuilt: true, reason: 'explicit rebuild requested' }) - prodLog.warn(`[Brainy] repairIndex(): '${familyName}' rebuild complete.`) + prodLog.narrate(`[Brainy] repairIndex(): '${familyName}' rebuild complete.`) continue } @@ -17968,11 +18804,16 @@ export class Brainy implements BrainyInterface { rebuild?: () => Promise } | null if (!p || typeof p.validateInvariants !== 'function' || typeof p.rebuild !== 'function') { + beginPhase(`provider:${familyName}`, 'checking the provider contract') record(`provider:${familyName}`, { checked: false, healed: 0, skipped: 'no validateInvariants/rebuild contract' }) continue } + beginPhase( + `provider:${familyName}`, + `reading the '${familyName}' provider's own invariant report, then healing only what it asks for` + ) let report: ProviderInvariantReport try { report = await p.validateInvariants() @@ -17989,7 +18830,7 @@ export class Brainy implements BrainyInterface { checked: true, healed: 1, detail: `rebuilt from canonical (failing: ${report.invariants.filter((i) => !i.holds).map((i) => i.name).join(', ')})` }) - prodLog.warn( + prodLog.narrate( `[Brainy] repairIndex(): provider '${report.provider}' has a failing invariant ` + `requiring a rebuild — reconciling its derived state from canonical.` ) @@ -18013,7 +18854,7 @@ export class Brainy implements BrainyInterface { const failingRepairs = report.invariants .filter((i) => !i.holds && i.heal === 'repair') .map((i) => i.name) - prodLog.warn( + prodLog.narrate( `[Brainy] repairIndex(): provider '${report.provider}' asks for an incremental ` + `repair (${failingRepairs.join(', ')}) — running its own repair().` ) @@ -18052,6 +18893,7 @@ export class Brainy implements BrainyInterface { // rebuild failure are now reconciled — clear the queryable degraded state // and re-arm the read-path warning. if (this._indexDegradedIds.size > 0 || this._indexRebuildFailed) { + beginPhase('degraded-read-state', 'clearing degraded ids and re-arming the read-path warning') this._indexDegradedIds.clear() this._indexRebuildFailed = null this._degradedReadWarned = false @@ -18060,11 +18902,13 @@ export class Brainy implements BrainyInterface { const healedTotal = families.reduce((n, f) => n + f.healed, 0) const report: RepairReport = { families, healedTotal, durationMs: Date.now() - startedAt } - prodLog.warn( + prodLog.narrate( `[Brainy] repairIndex complete in ${report.durationMs}ms — ` + `${families.filter((f) => f.checked).length}/${families.length} families checked, ` + `${healedTotal} heal(s): ` + - families.map((f) => `${f.family}=${f.checked ? f.healed : 'skipped'}`).join(', ') + families + .map((f) => `${f.family}=${f.checked ? f.healed : 'skipped'}@${f.durationMs ?? 0}ms`) + .join(', ') ) return report } @@ -18590,12 +19434,105 @@ export class Brainy implements BrainyInterface { } /** - * Close and cleanup + * @description Close and clean up: flush every buffered component, stamp + * the durability markers, release resources, then give up the writer lock. * - * Now flushes HNSW dirty nodes before closing - * This ensures deferred persistence mode data is saved + * TWO PARTS, AND THE SECOND IS UNCONDITIONAL. Everything that persists data + * runs in {@link closeDurableSteps}; the terminal releases — the flush-request + * watcher, the WRITER LOCK, the VFS timers, and the terminal `closed` flag — + * run whether those steps succeeded or not, in a `finally`. A close that + * threw halfway used to strand the writer lock on disk with this process's + * (soon dead) pid in it, so the next boot of every affected store announced + * `Overwriting stale writer lock … appears dead` after an orderly exit and + * an operator had to decide whether their database had crashed. A closed + * brain holds no lock — there is no failure for which the opposite is the + * safer answer. + * + * The original failure is never swallowed: it is narrated with what it costs + * the next open, then rethrown to the caller. + * @returns Nothing. + * @throws The first failure from the durable close steps, after the + * terminal releases have run. */ async close(): Promise { + let closeFailure: unknown = null + try { + await this.closeDurableSteps() + } catch (error) { + closeFailure = error + } + + // ---- TERMINAL RELEASES: always, even after a failure above ---- + + // Stop the cross-process flush-request watcher (no-op if never started). + try { + if (this.storage && typeof this.storage.stopFlushRequestWatcher === 'function') { + this.storage.stopFlushRequestWatcher() + } + } catch (error) { + console.warn('[Brainy] close: stopping the flush-request watcher failed:', error) + } + + // Release the writer lock. Runs after the metadata buffer drain in + // closeDurableSteps() — otherwise a pending write could land after a + // successor writer claimed the lock — and runs even if that drain threw: + // holding a lock from a process that is about to exit locks the store's + // next boot out of a clean verdict. + try { + if (this.storage && typeof this.storage.releaseWriterLock === 'function') { + await this.storage.releaseWriterLock() + } + } catch (error) { + console.warn('[Brainy] close: releasing the writer lock failed:', error) + } + + // Shut down the VFS: stops its background maintenance interval and the + // PathResolver's — both are ref'd timers that would keep the process + // alive after the last brain closes (consumer-reported hang). + try { + if (this._vfs) { + await this._vfs.close() + } + } catch (error) { + console.warn('[Brainy] close: VFS shutdown failed:', error) + } + + this.initialized = false + // close() is terminal: block lazy re-initialization on any subsequent + // operation (ensureInitialized() throws once this is set). Set even when + // the durable steps failed — a half-closed brain must not keep serving. + this.closed = true + + // Drop this instance from the global registry, and when it was the last + // one, deregister the global shutdown hooks — their ref'd signal handles + // would otherwise keep the process alive after every brain is closed. + const instanceIndex = Brainy.instances.indexOf(this) + if (instanceIndex !== -1) { + Brainy.instances.splice(instanceIndex, 1) + } + Brainy.deregisterShutdownHooksIfIdle() + + if (closeFailure !== null) { + console.error( + `[Brainy] close FAILED partway: ` + + `${closeFailure instanceof Error ? closeFailure.message : String(closeFailure)}\n` + + ` This brain is closed and holds no writer lock, but the clean-shutdown ` + + `marker may not have been written — the next open will run crash recovery ` + + `(a generation-log fold) and report its wall.` + ) + throw closeFailure + } + } + + /** + * @description The durable half of {@link close}: flush every component, + * persist the generation counter and its markers, close the components, + * deactivate plugins, drain the metadata write buffer. Separated from + * `close()` so the terminal releases there can run in a `finally` — see that + * method's contract. + * @returns Nothing. + */ + private async closeDurableSteps(): Promise { // Persistence cadence teardown: no background flush may fire after close // begins (close() runs its own final flush). if (this._persistIdleTimer) { @@ -18746,38 +19683,6 @@ export class Brainy implements BrainyInterface { } } - // Stop the cross-process flush-request watcher (no-op if never started). - if (this.storage && typeof this.storage.stopFlushRequestWatcher === 'function') { - this.storage.stopFlushRequestWatcher() - } - - // Release the writer lock (no-op for readers and for backends that don't - // hold a lock). Must run after the metadata buffer drain — otherwise a - // pending write could land after a successor writer claimed the lock. - if (this.storage && typeof this.storage.releaseWriterLock === 'function') { - await this.storage.releaseWriterLock() - } - - // Shut down the VFS: stops its background maintenance interval and the - // PathResolver's — both are ref'd timers that would keep the process - // alive after the last brain closes (consumer-reported hang). - if (this._vfs) { - await this._vfs.close() - } - - this.initialized = false - // close() is terminal: block lazy re-initialization on any subsequent - // operation (ensureInitialized() throws once this is set). - this.closed = true - - // Drop this instance from the global registry, and when it was the last - // one, deregister the global shutdown hooks — their ref'd signal handles - // would otherwise keep the process alive after every brain is closed. - const instanceIndex = Brainy.instances.indexOf(this) - if (instanceIndex !== -1) { - Brainy.instances.splice(instanceIndex, 1) - } - Brainy.deregisterShutdownHooksIfIdle() } } diff --git a/src/db/errors.ts b/src/db/errors.ts index e20488f8..3b4c1af6 100644 --- a/src/db/errors.ts +++ b/src/db/errors.ts @@ -28,7 +28,7 @@ * speculative `with()` overlay; the canonical storage walk only ever answers * "what is live right now." * - * All are exported from the package root (`@soulcraft/brainy`). + * All are exported from the package root (`@soulcraftlabs/brainy`). */ /** diff --git a/src/db/familyStamp.ts b/src/db/familyStamp.ts index 98342884..2f01e935 100644 --- a/src/db/familyStamp.ts +++ b/src/db/familyStamp.ts @@ -12,9 +12,11 @@ * the verified surface is a small set of rollup invariants (entity/ * relationship counts) plus `sourceGeneration`. * - * `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: + * `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: * * - equal + invariants hold → coherent, serve. * - behind → the projection missed the tail (crash between commit and stamp); @@ -24,6 +26,9 @@ * - 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. @@ -70,6 +75,12 @@ 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 @@ -118,12 +129,15 @@ export function verifyFamilyStamp( ): StampVerdict { if (stamp === null) return { state: 'absent' } if (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}`] - } + // 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 } } if (stamp.sourceGeneration < head) { return { state: 'behind', stampSource: stamp.sourceGeneration, head } diff --git a/src/db/generationSegments.ts b/src/db/generationSegments.ts index 0c14b60c..91451281 100644 --- a/src/db/generationSegments.ts +++ b/src/db/generationSegments.ts @@ -147,6 +147,60 @@ 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> { + 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 @@ -164,6 +218,38 @@ 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( @@ -364,12 +450,37 @@ export class GenerationSegmentStore { return this.decodeFrame(payload) } } - // 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. + // 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 + } throw new Error( `[GenerationSegments] generation ${gen} is inside sealed segment ${meta.file}'s declared ` + - `range but has no frame — packed history is damaged` + `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` ) } diff --git a/src/db/generationStore.ts b/src/db/generationStore.ts index 81bed338..da21dc61 100644 --- a/src/db/generationStore.ts +++ b/src/db/generationStore.ts @@ -96,6 +96,35 @@ 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. @@ -537,12 +566,29 @@ export class GenerationStore { this.horizonGen = finiteGen(manifest?.horizon, 'manifest horizon') this.counter = Math.max(finiteGen(counterFile?.generation, 'generation counter'), this.committed) - // Discover existing generation record directories. - const recordPaths = await this.storage.listRawObjects(GENERATIONS_PREFIX) + // Discover existing generation record directories — BY DIRECTORY NAME. + // This used to call listRawObjects(), which recurses the whole + // `_generations/` tree and returns every file in every generation, to + // extract a set of integers the top-level directory names already spell. + // MEASURED on a real store with an 11 GB generation history: the phase + // this sits in cost 55,538 ms of a WARM REOPEN after a clean close, with + // no fold to blame — this walk is what it was doing. An adapter without + // the one-level door falls back to the recursive listing, unchanged. const seenGens = new Set() - for (const p of recordPaths) { - const gen = parseGenerationFromPath(p) - if (gen !== null) seenGens.add(gen) + const oneLevel = ( + this.storage as { listRawPrefixes?: (prefix: string) => Promise } + ).listRawPrefixes + if (typeof oneLevel === 'function') { + for (const name of await oneLevel.call(this.storage, GENERATIONS_PREFIX)) { + const gen = Number(name) + if (Number.isSafeInteger(gen) && gen >= 0) seenGens.add(gen) + } + } else { + const recordPaths = await this.storage.listRawObjects(GENERATIONS_PREFIX) + for (const p of recordPaths) { + const gen = parseGenerationFromPath(p) + if (gen !== null) seenGens.add(gen) + } } let rolledBack = 0 @@ -652,6 +698,7 @@ export class GenerationStore { : 'WHOLE-LOG fold' : 'above-manifest replay' let replayed = 0 + const foldStartedAt = Date.now() const replayFact = async (fact: CommitFact): Promise => { for (const op of fact.ops) { let image: { metadata: unknown | null; vector: unknown | null } @@ -697,9 +744,10 @@ export class GenerationStore { } replayed++ if (replayed % 1000 === 0) { - prodLog.warn( + prodLog.narrate( `[GenerationStore] recovery fold in progress — ${replayed} fact(s) folded ` + - `(at generation ${fact.generation}); do not restart, the fold is finite` + `in ${Date.now() - foldStartedAt}ms (at generation ${fact.generation}); ` + + `do not restart, the fold is finite` ) } if (fact.generation > this.committed) { @@ -714,7 +762,7 @@ export class GenerationStore { } } if (uncleanOpen) { - prodLog.warn( + prodLog.narrate( `[GenerationStore] log-authority recovery: ${foldKind} beginning ` + `(unclean shutdown detected) — streaming replay, bounded memory, ` + `progress every 1000 facts. Do not restart the process; a restart ` + @@ -737,9 +785,10 @@ export class GenerationStore { } await this.storage.writeRawObject(MANIFEST_PATH, manifest) await this.storage.syncRawObjects([MANIFEST_PATH]) - prodLog.warn( + prodLog.narrate( `[GenerationStore] log-authority recovery replayed ${replayed} fact(s) into ` + - `canonical (${foldKind}; committed at ${this.committed}) — an acked write is never lost` + `canonical in ${Date.now() - foldStartedAt}ms (${foldKind}; committed at ` + + `${this.committed}) — an acked write is never lost` ) } // A recovery fold re-applied (and the barrier below re-syncs) every @@ -764,9 +813,15 @@ export class GenerationStore { if (storageSupportsFactLog(this.storage)) { this.segments = new GenerationSegmentStore(this.storage) await this.segments.open() - const packedRanges = this.segments - .segments() - .map((s): [number, number] => [s.firstGeneration, Math.min(s.lastGeneration, this.committed)]) + // ACTUAL ranges, not declared ones. A segment sealed by a pre-density-law + // writer can declare a span wider than the frames it holds; seeding + // committedRanges from the declared span re-admits those holes as + // committed generations, and every later maintenance pass then asks for a + // frame that was never written. `actualRanges()` reads the real + // generation list from the sidecar for exactly those segments (and does + // no I/O for the dense ones, which is all of them on a healthy store). + const packedRanges = (await this.segments.actualRanges()) + .map((r): [number, number] => [r[0], Math.min(r[1], this.committed)]) .filter(([lo, hi]) => lo <= hi) if (packedRanges.length > 0) { // Merge packed (older) + live (newer) interval sets — both ascending; @@ -3101,13 +3156,26 @@ export class GenerationStore { foldInput.push({ generation: gen, timestamp: delta.timestamp, delta, records }) } if (foldInput.length === 0) continue - await segments.fold(foldInput) - segmentsCreated++ - // Segment + manifest durable → the live copies retire. - for (const g of foldInput) { - await this.storage.removeRawPrefix(`${GENERATIONS_PREFIX}/${g.generation}`) + // SPLIT AT DISCONTINUITIES. `eligible` is NOT contiguous — three + // filters above punch holes in it: a generation missing from + // committedRanges never appears, one still in the pending buffer is + // skipped, and one whose tx.json will not read is skipped. A sealed + // segment declares a DENSE range, so folding across such a hole makes + // the segment claim a generation it does not hold; the next open + // merges that mis-declared range into committedRanges, and every + // subsequent auto-compaction pass then asks for the missing frame and + // fails with "packed history is damaged". Fold each contiguous RUN as + // its own segment instead — same bytes, honest ranges. + for (const run of contiguousRuns(foldInput)) { + if (deadline !== undefined && Date.now() >= deadline) break + await segments.fold(run) + segmentsCreated++ + // Segment + manifest durable → the live copies retire. + for (const g of run) { + await this.storage.removeRawPrefix(`${GENERATIONS_PREFIX}/${g.generation}`) + } + folded += run.length } - folded += foldInput.length } if (folded > 0) { prodLog.info( diff --git a/src/db/types.ts b/src/db/types.ts index 363de086..56bdef11 100644 --- a/src/db/types.ts +++ b/src/db/types.ts @@ -450,6 +450,21 @@ export interface GenerationStorage { deleteRawObject(path: string): Promise /** List raw object paths under a prefix (normalized, `.gz`-stripped). */ listRawObjects(prefix: string): Promise + /** + * OPTIONAL: the IMMEDIATE child directory names under a prefix — one level, + * no recursion, no file paths. + * + * Why it exists: discovering which generations are on disk needs only the + * top-level directory NAMES under `_generations/`, but the only door for it + * was `listRawObjects`, which recurses the whole tree and returns every file + * in every generation. On a store with a long history that is a full walk of + * the entire generation log, paid on EVERY open, to learn a set of integers + * the directory names already spell out. + * + * An adapter without this door keeps working — the caller falls back to the + * recursive listing. + */ + listRawPrefixes?(prefix: string): Promise /** Remove every object under a prefix (and the directory itself on disk). */ removeRawPrefix(prefix: string): Promise /** Durability barrier: fsync the given object paths (no-op in memory). */ diff --git a/src/embeddings/wasm/modelLoader.ts b/src/embeddings/wasm/modelLoader.ts index 45ffc4d3..b39d90ea 100644 --- a/src/embeddings/wasm/modelLoader.ts +++ b/src/embeddings/wasm/modelLoader.ts @@ -128,7 +128,7 @@ async function loadBunAssets(): Promise { } // Strategy 2: node_modules path relative to CWD (for installed packages) - const nmPath = './node_modules/@soulcraft/brainy/assets/models/all-MiniLM-L6-v2' + const nmPath = './node_modules/@soulcraftlabs/brainy/assets/models/all-MiniLM-L6-v2' pathsToTry.push([ `${nmPath}/model.safetensors`, `${nmPath}/tokenizer.json`, @@ -168,9 +168,9 @@ async function loadBunAssets(): Promise { // If all strategies fail, provide helpful error message throw new Error( 'Could not load model assets. For bun --compile, ensure model files are accessible:\n' + - ' Option 1: Keep node_modules/@soulcraft/brainy/assets/ alongside your binary\n' + + ' Option 1: Keep node_modules/@soulcraftlabs/brainy/assets/ alongside your binary\n' + ' Option 2: Copy assets/ folder to your working directory\n' + - ' Option 3: Use --asset flag: bun build --compile --asset="./node_modules/@soulcraft/brainy/assets/**/*"' + ' Option 3: Use --asset flag: bun build --compile --asset="./node_modules/@soulcraftlabs/brainy/assets/**/*"' ) } @@ -190,7 +190,7 @@ async function loadNodeAssets(): Promise { if (!fs.existsSync(assetsDir)) { throw new Error( `Model assets not found: ${assetsDir}\n` + - `Ensure @soulcraft/brainy is installed correctly.` + `Ensure @soulcraftlabs/brainy is installed correctly.` ) } diff --git a/src/errors/notFound.ts b/src/errors/notFound.ts index 8eca9b2e..628797a6 100644 --- a/src/errors/notFound.ts +++ b/src/errors/notFound.ts @@ -14,7 +14,7 @@ * - {@link RelationNotFoundError} — a referenced relationship (verb) does * not exist. * - * Both are exported from the package root (`@soulcraft/brainy`). + * Both are exported from the package root (`@soulcraftlabs/brainy`). */ /** diff --git a/src/graph/graphAdjacencyIndex.ts b/src/graph/graphAdjacencyIndex.ts index d002164e..ebd3b90c 100644 --- a/src/graph/graphAdjacencyIndex.ts +++ b/src/graph/graphAdjacencyIndex.ts @@ -1052,6 +1052,17 @@ export class GraphAdjacencyIndex implements GraphIndexProvider { */ private startAutoFlush(): void { this.flushTimer = setInterval(async () => { + // NO PERIODIC WORK WITHOUT A CAUSE. Ask first, in two O(1) reads: an + // index nobody has written to since the last flush has nothing to + // write, and calling into the trees (and their logging) on a cadence + // over a quiet store is exactly the idle cost this law exists to + // remove. + if ( + !this.lsmTreeVerbsBySource.hasPendingWrites() && + !this.lsmTreeVerbsByTarget.hasPendingWrites() + ) { + return + } await this.flush() }, this.config.flushInterval) // Background maintenance must never keep the host process alive — diff --git a/src/graph/lsm/LSMTree.ts b/src/graph/lsm/LSMTree.ts index e19ec145..b4f6052f 100644 --- a/src/graph/lsm/LSMTree.ts +++ b/src/graph/lsm/LSMTree.ts @@ -687,6 +687,17 @@ export class LSMTree { } } + /** + * @description Whether this tree holds anything a flush would write — + * the MemTable is non-empty. Synchronous and O(1), so a background cadence + * can ask before it does anything at all: the engine does no periodic work + * without a cause. + * @returns true when a flush would write; false when it would be a no-op. + */ + hasPendingWrites(): boolean { + return !this.memTable.isEmpty() + } + async close(): Promise { this.stopCompactionTimer() diff --git a/src/hnsw/hnswIndex.ts b/src/hnsw/hnswIndex.ts index 77e4f84d..8b9badc1 100644 --- a/src/hnsw/hnswIndex.ts +++ b/src/hnsw/hnswIndex.ts @@ -10,7 +10,7 @@ import { Vector, VectorDocument } from '../coreTypes.js' -import { euclideanDistance, calculateDistancesBatch } from '../utils/index.js' +import { euclideanDistance, calculateDistancesBatch, isZeroNormVector } from '../utils/index.js' import type { BaseStorage } from '../storage/baseStorage.js' import { getGlobalCache, UnifiedCache } from '../utils/unifiedCache.js' import { prodLog } from '../utils/logger.js' @@ -64,6 +64,34 @@ export class HnswFlushError extends Error { } } +/** + * @description Thrown by {@link JsHnswVectorIndex.addItem} / {@link + * JsHnswVectorIndex.updateItem} when handed a length-0 vector. A length-0 + * vector is the sanctioned "unvectored" shape for a canonical noun record + * (class-J: a VFS-system row, a deferred embed not yet landed, or any other + * legitimately-vector-less row) — but it is NEVER a legal INDEX insert. The + * index itself has no concept of "unvectored"; deciding that a row is + * unvectored and therefore skippable is the FILL/REBUILD/LOAD consumer's job + * (see {@link JsHnswVectorIndex.rebuild}), done BEFORE ever calling addItem. + * A length-0 vector reaching this point is a caller bug: silently accepting + * it would pin `this.dimension = 0` on an empty index (poisoning every real + * insert thereafter with a dimension mismatch) or store a vector-less node + * that a distance calculation can never safely compare against. Loud errors, + * never quiet losses — this throws instead of either. + */ +export class EmptyVectorIndexError extends Error { + constructor(public readonly id: string, operation: 'addItem' | 'updateItem') { + super( + `${operation}(${id}): refusing to index a length-0 vector — a length-0 vector is the ` + + `sanctioned "unvectored" shape for a canonical row, but it is never a legal index ` + + `insert. Callers that fill/rebuild/load the index must skip vector.length === 0 rows ` + + `themselves (unvectored = nothing to index, not an error at that layer); reaching ` + + `here with one is a caller bug.` + ) + this.name = 'EmptyVectorIndexError' + } +} + /** * Implements {@link VectorIndexProvider}: the vector-index surface Brainy calls * on whatever the `'vector'` factory returns (its own `JsHnswVectorIndex`, or a native @@ -580,6 +608,15 @@ export class JsHnswVectorIndex implements VectorIndexProvider { throw new Error('Vector is undefined or null') } + // THE INDEX REFUSES A LENGTH-0 VECTOR (see EmptyVectorIndexError's JSDoc): + // an empty vector is the sanctioned "unvectored" shape at the canonical + // layer, never a legal index member. Refusing here — loudly, before the + // dimension pin below — means no future fill/rebuild/load path can ever + // poison `this.dimension` to 0 or park a vector-less node in the graph. + if (vector.length === 0) { + throw new EmptyVectorIndexError(id, 'addItem') + } + // Set dimension on first insert if (this.dimension === null) { this.dimension = vector.length @@ -954,6 +991,13 @@ export class JsHnswVectorIndex implements VectorIndexProvider { return } + // Same refusal as addItem (see EmptyVectorIndexError's JSDoc) — an + // in-place relink must never rewrite an already-indexed node down to the + // unvectored shape or poison the pinned dimension. + if (vector.length === 0) { + throw new EmptyVectorIndexError(id, 'updateItem') + } + if (this.dimension === null) { this.dimension = vector.length } else if (vector.length !== this.dimension) { @@ -1555,7 +1599,15 @@ export class JsHnswVectorIndex implements VectorIndexProvider { } const loaded = await this.storage.getNounVector(noun.id) - if (!loaded) { + // `loaded` is a length-0 array (not null/undefined) for a canonical row + // that is legitimately unvectored — `![]` is FALSE (an empty array is + // truthy), so the bare `!loaded` check below would silently accept it + // as "found" and hand a dimension-0 vector to a distance calculation. + // A node only reaches this lazy-load path because it is a MEMBER of + // the live index (rebuild() now refuses to admit unvectored rows — see + // its JSDoc), so an empty vector here is never legitimate: treat it + // exactly like "not found", loudly. + if (!loaded || loaded.length === 0) { throw new Error(`Vector not found for noun ${noun.id}`) } @@ -1765,9 +1817,56 @@ export class JsHnswVectorIndex implements VectorIndexProvider { totalCount = result.totalCount || result.items.length + // UNVECTORED ROWS ARE NOT AN INDEX MEMBER (the class-J law): a canonical + // noun whose vector leg is `[]` (a VFS-root-style system row, a + // deferred embed not yet landed, or a best-effort fallback for an + // unreadable vector leg) is a normal, enumerable, countable row — it + // is simply not indexed. `storage.getVectorIndexData()` derives its + // {level, connections} answer straight from the noun's OWN record, so + // it returns non-null for every existing noun regardless of whether + // that noun ever actually reached `addItem()` — it cannot be used to + // decide indexability. `nounData.vector.length === 0` is the one + // truthful signal (mirrors the `noun.vector.length > 0` guards in + // {@link getVectorSafe} / {@link getVectorSync}): skip here, counted + // once in a summary line, never per-row spam. + let skippedUnvectored = 0 + // Process all nouns at once for (const nounData of result.items) { try { + if (!Array.isArray(nounData.vector) || nounData.vector.length === 0) { + skippedUnvectored++ + continue + } + // THE ZERO-NORM LAW — bulk-rebuild leg: a persisted zero-norm + // vector (a pre-10.4.2 row the canonical write has not yet + // normalized) must never enter the index either, mirroring the + // belt AddToVectorIndexOperation enforces on the live write path. + // Only the canonical vector is authoritative here — persisted + // HNSW graph metadata (level/connections) can outlive an unvector. + if (isZeroNormVector(nounData.vector)) { + prodLog.warn( + `[HNSW] rebuild(): skipping entity ${nounData.id} — persisted vector is ` + + `zero-norm (a zero-norm vector is not a vector and never crosses an ` + + `engine boundary)` + ) + continue + } + + // Restore the pinned dimension from the first real vector this + // rebuild loads. `addItem`/`updateItem` only pin `this.dimension` + // on a LIVE insert — a fresh rebuild from storage never goes + // through either, so without this the pin stays `null` across a + // restart. A `null` pin means the very next insert (correct OR + // wrong length) silently BECOMES the new pin instead of being + // checked against the store's real dimension — the wrong-length + // case then fails much later and less clearly, inside a distance + // calculation against an already-loaded node, instead of here, + // immediately, with a named expected-vs-got mismatch. + if (this.dimension === null) { + this.dimension = nounData.vector.length + } + // Load HNSW graph data for this entity const hnswData = await this.storage.getVectorIndexData(nounData.id) @@ -1815,7 +1914,10 @@ export class JsHnswVectorIndex implements VectorIndexProvider { options.onProgress(loadedCount, totalCount) } - prodLog.info(`HNSW: Loaded ${loadedCount.toLocaleString()} nodes (${storageType})`) + prodLog.info( + `HNSW: Loaded ${loadedCount.toLocaleString()} nodes (${storageType})` + + (skippedUnvectored > 0 ? ` — ${skippedUnvectored.toLocaleString()} unvectored row(s) skipped` : '') + ) } // Step 5: CRITICAL - Recover entry point if missing) diff --git a/src/index.ts b/src/index.ts index 973136a5..edc21809 100644 --- a/src/index.ts +++ b/src/index.ts @@ -184,6 +184,7 @@ export { // Export version utilities export { getBrainyVersion } from './utils/version.js' +export { contractVersion, BRAINY_CONTRACT_VERSION } from './utils/version.js' // Export plugin system export type { BrainyPlugin, BrainyPluginContext, StorageAdapterFactory } from './plugin.js' diff --git a/src/integrations/index.ts b/src/integrations/index.ts index 757a9fe5..6a6734d9 100644 --- a/src/integrations/index.ts +++ b/src/integrations/index.ts @@ -9,7 +9,7 @@ * * @example Enable integrations (recommended) * ```typescript - * import { Brainy } from '@soulcraft/brainy' + * import { Brainy } from '@soulcraftlabs/brainy' * * const brain = new Brainy({ integrations: true }) * await brain.init() diff --git a/src/mcp/README.md b/src/mcp/README.md index c69a3b24..092534a1 100644 --- a/src/mcp/README.md +++ b/src/mcp/README.md @@ -41,7 +41,7 @@ The `BrainyMCPService` has been refactored to separate the core functionality fr ### In Any Environment (Browser, Node.js, Server) ```typescript -import { Brainy, BrainyMCPAdapter, MCPAugmentationToolset } from '@soulcraft/brainy' +import { Brainy, BrainyMCPAdapter, MCPAugmentationToolset } from '@soulcraftlabs/brainy' // Create a Brainy instance const brainyData = new Brainy() @@ -81,7 +81,7 @@ const toolResponse = await toolset.handleRequest({ ### In Browser Environment (Core Functionality Only) ```typescript -import { Brainy, BrainyMCPService } from '@soulcraft/brainy' +import { Brainy, BrainyMCPService } from '@soulcraftlabs/brainy' // Create a Brainy instance const brainyData = new Brainy() diff --git a/src/plugin.ts b/src/plugin.ts index bfdc403a..b1aef8e0 100644 --- a/src/plugin.ts +++ b/src/plugin.ts @@ -22,7 +22,7 @@ import type { GraphIndexStats } from './graph/graphAdjacencyIndex.js' // Re-export the provider contracts that already live closer to their // implementations so a plugin author (Cor) can import the *entire* -// provider surface from one stable entrypoint: `@soulcraft/brainy/plugin`. +// provider surface from one stable entrypoint: `@soulcraftlabs/brainy/plugin`. export type { ColumnStoreProvider } from './indexes/columnStore/types.js' export type { AggregationProvider, @@ -41,7 +41,7 @@ export interface BrainyPlugin { name: string /** - * Optional semver range of `@soulcraft/brainy` this plugin supports + * Optional semver range of `@soulcraftlabs/brainy` this plugin supports * (e.g. `'>=8.0.0 <9.0.0'` or `'^8.0.0'`). When set and the running brainy is * OUTSIDE the range, `init()` THROWS rather than silently falling back to the * default JS engine. This is the version-coupling guard for the native diff --git a/src/storage/adapters/fileSystemStorage.ts b/src/storage/adapters/fileSystemStorage.ts index 817e5e36..5ec1d88e 100644 --- a/src/storage/adapters/fileSystemStorage.ts +++ b/src/storage/adapters/fileSystemStorage.ts @@ -14,11 +14,13 @@ import { StorageBatchConfig, SYSTEM_DIR, STATISTICS_KEY, - WriterLockInfo + WriterLockInfo, + WriterCloseRecord } from '../baseStorage.js' import { getBrainyVersion } from '../../utils/index.js' import { isAbsentError } from '../../utils/errorClassification.js' import { prodLog } from '../../utils/logger.js' +import { isZeroNormVector } from '../../utils/distance.js' import { TornRecordError, isUnparseablePayloadError, @@ -98,7 +100,30 @@ export class FileSystemStorage extends BaseStorage { // timer rewrites the lock every 10s so stale-lock detection can tell a dead // writer from a slow one. The constant name matches the file path used. private static readonly WRITER_LOCK_FILE = '_writer.lock' - private static readonly WRITER_HEARTBEAT_MS = 10_000 + /** + * The clean-close record at `locks/_writer.close` (see + * {@link WriterCloseRecord}). Written when the lock is released, consumed by + * the next claim, so an open can distinguish "the previous writer left" from + * "the previous writer died" without inferring either from a pid. + */ + private static readonly WRITER_CLOSE_FILE = '_writer.close' + /** + * How often the lock file's `lastHeartbeat` is rewritten. + * + * THIS IS OBSERVABILITY ONLY, and the cadence follows from that. Staleness + * is decided by PID LIVENESS alone (see isWriterLockStale) and the fence + * compares pid + hostname — no decision anywhere reads this timestamp. It + * exists so an operator inspecting a lock file, or reading the + * BRAINY_WRITER_LOCKED error, can judge liveness themselves. + * + * At 10s it was a lock-file WRITE every ten seconds per brain, forever: 2.1 + * writes/s across a production process holding 21 idle brains, for a + * human-readable timestamp nothing computes with. At 60s an operator still + * sees a heartbeat inside the minute, at a sixth of the cost. With the + * clean-close record now recording orderly releases explicitly, the + * heartbeat carries even less weight than it did. + */ + private static readonly WRITER_HEARTBEAT_MS = 60_000 private static readonly WRITER_STALE_THRESHOLD_MS = 60_000 private writerLockHeartbeat?: NodeJS.Timeout private writerLockInfo?: WriterLockInfo @@ -111,6 +136,13 @@ export class FileSystemStorage extends BaseStorage { */ private writerHeartbeatInFlight?: Promise + /** + * The in-flight background count-ledger derivation, if one was needed at + * open. See {@link scheduleCountLedgerDerivation} — awaited only by + * {@link whenCountLedgerSettled}, never by a read. + */ + private countLedgerDerivation?: Promise + // Flush-request RPC state. The writer polls `locks/_flush_requests/` for // new `.req` files and emits `.ack` files in `locks/_flush_responses/` after // flushing. Inspectors call `requestFlushOverFilesystem` to drop a request @@ -119,9 +151,16 @@ export class FileSystemStorage extends BaseStorage { private static readonly FLUSH_REQUEST_DIR = '_flush_requests' private static readonly FLUSH_RESPONSE_DIR = '_flush_responses' private static readonly FLUSH_WATCH_INTERVAL_MS = 500 + /** + * The safety sweep behind the fs.watch: catches events an exotic filesystem + * dropped, and runs the stale-request GC. See startFlushRequestWatcher. + */ + private static readonly FLUSH_SAFETY_SWEEP_MS = 30_000 private static readonly FLUSH_POLL_INTERVAL_MS = 100 private static readonly FLUSH_REQUEST_TTL_MS = 60_000 private flushWatcherInterval?: NodeJS.Timeout + /** The inotify-backed watch on the request directory, when the FS supports one. */ + private flushWatcher?: import('node:fs').FSWatcher private flushWatcherInFlight = false private flushWatcherOnRequest?: () => Promise @@ -670,6 +709,30 @@ export class FileSystemStorage extends BaseStorage { return pruned } + /** + * @description The IMMEDIATE child directory names under a prefix — ONE + * `readdir`, no recursion, no file paths. See the seam's JSDoc + * (`src/db/types.ts`) for what this replaced: discovering the generations on + * disk walked the entire generation log on every open, reading out every + * file in every generation, to learn the set of integers the top-level + * directory names already spell. + * @param prefix - Storage-root-relative directory prefix. + * @returns The child directory names (not paths); empty when the prefix does + * not exist. + */ + public override async listRawPrefixes(prefix: string): Promise { + await this.ensureInitialized() + const fullPath = path.join(this.rootDir, prefix) + try { + const entries = await fs.promises.readdir(fullPath, { withFileTypes: true }) + return entries.filter((e: { isDirectory: () => boolean }) => e.isDirectory()) + .map((e: { name: string }) => e.name) + } catch (error: any) { + if (error?.code === 'ENOENT') return [] + throw error + } + } + /** * Primitive operation: List objects under path prefix * All metadata operations use this internally via base class routing @@ -1880,18 +1943,41 @@ export class FileSystemStorage extends BaseStorage { } } + // THE CLEAN-CLOSE RECORD IS READ BEFORE ANY VERDICT (see + // WriterCloseRecord). A lock file whose release was RECORDED is + // bookkeeping left by an orderly shutdown, not evidence of anything — + // and that is true whether the previous holder was another process or + // an earlier instance in THIS one. A production restart reported + // "Re-acquiring writer lock ... this is a bug" immediately after a clean + // close, sending an operator hunting for a leak that did not exist. + const closeRecord = existing ? await this.readWriterCloseRecord() : null + const releasedCleanly = + existing !== null && + closeRecord !== null && + this.closeRecordVouchesFor(closeRecord, existing) + if (existing) { // Same-process re-open: a second Brainy instance in this Node process // (e.g. test "simulate server restart" patterns, or a consumer that // explicitly re-instantiates without closing first). This isn't the // dangerous cross-process case the lock exists to prevent — the two // instances share a memory space and can't silently diverge from each - // other beyond what their callers already see. Warn and take over. + // other beyond what their callers already see. Warn and take over — + // unless the record proves the previous instance already let go, in + // which case there is nothing to warn about. if (existing.pid === myPid && existing.hostname === hostname && !options?.force) { - console.warn( - `[brainy] Re-acquiring writer lock for ${this.rootDir} held by the same process (PID ${existing.pid}). ` + - `If you intended to keep the previous Brainy instance alive, this is a bug — close it first.` - ) + if (releasedCleanly) { + console.warn( + `[brainy] Clearing the leftover writer lock for ${this.rootDir} — an earlier ` + + `instance in this process (PID ${existing.pid}) RELEASED it cleanly at ` + + `${closeRecord!.closedAt} but could not remove the file. Nothing to recover.` + ) + } else { + console.warn( + `[brainy] Re-acquiring writer lock for ${this.rootDir} held by the same process (PID ${existing.pid}). ` + + `If you intended to keep the previous Brainy instance alive, this is a bug — close it first.` + ) + } const info: WriterLockInfo = { pid: myPid, hostname, @@ -1901,11 +1987,18 @@ export class FileSystemStorage extends BaseStorage { rootDir: this.rootDir } await this.writeFileAtomic(lockFile, JSON.stringify(info, null, 2)) + await this.clearWriterCloseRecord() this.installWriterLock(info) return info } - const stale = !options?.force && (await this.isWriterLockStale(existing)) + // A cleanly-released lock is stale by RECORD, not by inference. Only + // when no record vouches for this lock do we fall back to pid + // liveness, and then we say THAT honestly too: an unrecorded lock + // means the writer did not complete its close, so the store was not + // closed cleanly and this open pays recovery. + const stale = + releasedCleanly || (!options?.force && (await this.isWriterLockStale(existing))) if (!options?.force && !stale) { // Consumer-facing error contract: callers detect this case via // err.code and read the holder's details from err.lockInfo. @@ -1916,8 +2009,16 @@ export class FileSystemStorage extends BaseStorage { options?.force ? `[brainy] Force-overwriting writer lock for ${this.rootDir} ` + `(was held by PID ${existing.pid} on ${existing.hostname}).` - : `[brainy] Overwriting stale writer lock for ${this.rootDir} ` + - `(PID ${existing.pid} on ${existing.hostname} appears dead).` + : releasedCleanly + ? `[brainy] Clearing the leftover writer lock for ${this.rootDir} — ` + + `PID ${existing.pid} on ${existing.hostname} RELEASED it cleanly at ` + + `${closeRecord!.closedAt} but could not remove the file. ` + + `Nothing to recover.` + : `[brainy] Overwriting stale writer lock for ${this.rootDir} ` + + `(PID ${existing.pid} on ${existing.hostname} is gone and left NO ` + + `clean-close record — that writer did not finish closing, so this ` + + `store was not closed cleanly; open will run crash recovery and ` + + `report its wall).` ) // Takeover: verify the file still holds the lock we judged (a live // successor may have claimed meanwhile), then remove it and fall @@ -1971,6 +2072,12 @@ export class FileSystemStorage extends BaseStorage { await fs.promises.unlink(claimTmp).catch(() => {}) } + // CONSUME the previous writer's clean-close record. It described the + // lock generation that just ended; leaving it in place would let it + // vouch for OUR lock if this process later dies without closing — + // turning a real crash into a "closed cleanly" verdict. One unlink. + await this.clearWriterCloseRecord() + this.installWriterLock(info) return info } @@ -2094,13 +2201,27 @@ export class FileSystemStorage extends BaseStorage { return } const lockFile = path.join(this.lockDir, FileSystemStorage.WRITER_LOCK_FILE) + const released = this.writerLockInfo try { // Only delete if we still own it — avoid clobbering a successor that // claimed the lock via force-override. const current = await this.readWriterLock() - if (current && current.pid === this.writerLockInfo.pid && current.hostname === this.writerLockInfo.hostname) { + const ours = + current === null || + (current.pid === released.pid && current.hostname === released.hostname) + if (current && ours) { await fs.promises.unlink(lockFile) } + // THE CLEAN-CLOSE RECORD (see WriterCloseRecord). Written whenever this + // instance gives up a lock nobody else has taken — the unlink above + // having succeeded OR the file already being gone. The next open reads + // it instead of guessing from pid liveness: a recorded release is an + // orderly shutdown, an absent record is a writer that never finished + // closing. Not written when a successor holds the lock: our release is + // then a no-op and a record would slander their live lock. + if (ours) { + await this.writeWriterCloseRecord(released) + } } catch (err: any) { if (err.code !== 'ENOENT') { console.warn('[brainy] Failed to release writer lock file:', err) @@ -2110,6 +2231,97 @@ export class FileSystemStorage extends BaseStorage { } } + /** + * @description Read the clean-close record at `locks/_writer.close`, or + * `null` when it is absent or unparseable. A torn record is treated as + * absent — the conservative direction, since an unreadable record can + * vouch for nothing. + * @returns The record, or null. + */ + public async readWriterCloseRecord(): Promise { + await this.ensureInitialized() + const recordFile = path.join(this.lockDir, FileSystemStorage.WRITER_CLOSE_FILE) + try { + const raw = await fs.promises.readFile(recordFile, 'utf-8') + const parsed = JSON.parse(raw) as WriterCloseRecord + if ( + typeof parsed?.pid !== 'number' || + typeof parsed?.hostname !== 'string' || + typeof parsed?.startedAt !== 'string' || + typeof parsed?.closedAt !== 'string' + ) { + return null + } + return parsed + } catch (err: any) { + if (err.code === 'ENOENT') return null + return null + } + } + + /** + * @description Whether a clean-close record describes the very lock + * generation `lock` represents. The match is pid + hostname + `startedAt`: + * `startedAt` is the lock generation's identity, so a record can never + * vouch for a LATER lock taken by the same pid on the same host (the + * same-process re-open path mints a fresh `startedAt`). + * @param record - The clean-close record read from disk. + * @param lock - The lock file's contents. + */ + private closeRecordVouchesFor(record: WriterCloseRecord, lock: WriterLockInfo): boolean { + return ( + record.pid === lock.pid && + record.hostname === lock.hostname && + record.startedAt === lock.startedAt + ) + } + + /** + * @description Write the clean-close record for a lock this instance just + * released. Atomic (temp + rename) so a concurrent opener never reads half + * a record. A failure here costs the next open nothing but the honest + * fallback (pid liveness), so it warns rather than failing the close. + * @param released - The lock info this instance held. + */ + private async writeWriterCloseRecord(released: WriterLockInfo): Promise { + const record: WriterCloseRecord = { + pid: released.pid, + hostname: released.hostname, + startedAt: released.startedAt, + closedAt: new Date().toISOString(), + version: released.version + } + const recordFile = path.join(this.lockDir, FileSystemStorage.WRITER_CLOSE_FILE) + try { + await this.writeFileAtomic(recordFile, JSON.stringify(record, null, 2)) + } catch (err) { + // ENOENT = the lock directory is gone, i.e. the whole store was removed + // under us. There is no next open to inform. + if ((err as NodeJS.ErrnoException)?.code === 'ENOENT') return + console.warn( + `[brainy] Failed to write the writer clean-close record for ${this.rootDir} — ` + + `the next open will fall back to pid liveness and may report this orderly ` + + `shutdown as a crash:`, + err + ) + } + } + + /** + * @description Remove the clean-close record. Called by every successful + * lock claim so a record never outlives the lock generation it describes. + */ + private async clearWriterCloseRecord(): Promise { + const recordFile = path.join(this.lockDir, FileSystemStorage.WRITER_CLOSE_FILE) + try { + await fs.promises.unlink(recordFile) + } catch (err: any) { + if (err.code !== 'ENOENT') { + console.warn('[brainy] Failed to clear the writer clean-close record:', err) + } + } + } + public override async readWriterLock(): Promise { await this.ensureInitialized() const lockFile = path.join(this.lockDir, FileSystemStorage.WRITER_LOCK_FILE) @@ -2196,36 +2408,115 @@ export class FileSystemStorage extends BaseStorage { /** * Start watching for cross-process flush requests. Called by Brainy.init() - * in writer mode. Polls `locks/_flush_requests/` every - * FLUSH_WATCH_INTERVAL_MS — each new `.req` file triggers the supplied - * callback (`brain.flush()`), after which an `.ack` is written to - * `locks/_flush_responses/` with the same request ID. Stale `.req` files - * (>FLUSH_REQUEST_TTL_MS) are garbage-collected on every tick. + * in writer mode. Each new `.req` file in `locks/_flush_requests/` triggers + * the supplied callback (`brain.flush()`), after which an `.ack` is written + * to `locks/_flush_responses/` with the same request ID. Stale `.req` files + * (>FLUSH_REQUEST_TTL_MS) are garbage-collected on each sweep. + * + * THE WATCH IS EVENT-DRIVEN, NOT A POLL. It used to `readdir` the request + * directory every 500 ms, per brain, for the entire life of every writer — + * armed on every non-reader brain whether or not any inspector process + * existed. MEASURED on a production process holding 21 brains: 42 directory + * reads per second on a completely idle service, plus a stale-request GC + * pass on every one of them. The engine does no periodic work without a + * cause, and a request that has not been made is not a cause. + * + * `fs.watch` (inotify on Linux) delivers the arrival itself, so a request is + * seen SOONER than the old poll saw it. Two honest concessions ride with it: + * - a slow SAFETY SWEEP (FLUSH_SAFETY_SWEEP_MS) still runs, because + * `fs.watch` can miss events on network and fuse filesystems and because + * the stale-request GC needs some tick of its own. At 30s that is 0.7 + * reads/s across 21 brains where the poll cost 42. + * - a filesystem that cannot watch at all falls back to the ORIGINAL + * 500 ms poll, narrated once, because correctness outranks idle cost: + * an inspector whose request is never seen waits forever. */ public override startFlushRequestWatcher(onRequest: () => Promise): void { - if (this.flushWatcherInterval) return // already watching + // Already watching — or already ARMING. The arm is asynchronous (the + // request directory is created before it can be watched), so neither the + // watcher nor the interval exists yet during that window; the callback is + // the flag that covers it. Without this a second call in the window would + // leave two watchers and two sweeps running for the life of the store. + if (this.flushWatcherInterval || this.flushWatcher || this.flushWatcherOnRequest) return this.flushWatcherOnRequest = onRequest const reqDir = path.join(this.lockDir, FileSystemStorage.FLUSH_REQUEST_DIR) const ackDir = path.join(this.lockDir, FileSystemStorage.FLUSH_RESPONSE_DIR) - // Ensure both dirs exist up front so the first .req drop doesn't race with mkdir. - this.ensureDirectoryExists(reqDir).catch(() => {}) - this.ensureDirectoryExists(ackDir).catch(() => {}) - - this.flushWatcherInterval = setInterval(() => { - if (this.flushWatcherInFlight) return // skip overlapping tick + const sweep = (): void => { + if (this.flushWatcherInFlight) return // skip overlapping sweep this.flushWatcherInFlight = true this.processFlushRequests(reqDir, ackDir).finally(() => { this.flushWatcherInFlight = false }) - }, FileSystemStorage.FLUSH_WATCH_INTERVAL_MS) + } + + // Ensure both dirs exist up front so the first .req drop doesn't race with + // mkdir — and so there is a directory to watch. + void this.ensureDirectoryExists(reqDir) + .then(() => this.ensureDirectoryExists(ackDir)) + .then(() => { + if (this.flushWatcherOnRequest !== onRequest) return // stopped meanwhile + try { + const watcher = fs.watch(reqDir, () => sweep()) + this.flushWatcher = watcher + watcher.on('error', (err: Error) => { + // A watch that dies mid-life must not leave the door deaf. + console.warn( + `[brainy] Flush-request watch failed (${err.message}) — falling back to polling.` + ) + this.flushWatcher?.close() + this.flushWatcher = undefined + // The SAFETY sweep must go first. It is already armed at 30s, and + // startFlushRequestPolling() declines to arm over an existing + // interval — so leaving it would quietly leave this store answering + // flush requests on a 30s cadence instead of the 500ms one the door + // promises. A degrade nobody asked for is still a degrade. + if (this.flushWatcherInterval) { + clearInterval(this.flushWatcherInterval) + this.flushWatcherInterval = undefined + } + this.startFlushRequestPolling(sweep) + }) + if (typeof watcher.unref === 'function') watcher.unref() + // The safety sweep: missed events on exotic filesystems, and the + // stale-request GC. + this.flushWatcherInterval = setInterval(sweep, FileSystemStorage.FLUSH_SAFETY_SWEEP_MS) + if (typeof this.flushWatcherInterval.unref === 'function') { + this.flushWatcherInterval.unref() + } + // One sweep now: a request may have been dropped before the watch armed. + sweep() + } catch (err) { + console.warn( + `[brainy] Flush-request directory cannot be watched on this filesystem ` + + `(${(err as Error).message}) — polling every ` + + `${FileSystemStorage.FLUSH_WATCH_INTERVAL_MS}ms instead.` + ) + this.startFlushRequestPolling(sweep) + } + }) + .catch(() => { + // The request directory could not be created; nothing to watch. A + // cross-process flush request cannot be made either, so there is + // nothing to miss. + }) + } + + /** The original 500 ms poll — the fallback when a directory cannot be watched. */ + private startFlushRequestPolling(sweep: () => void): void { + if (this.flushWatcherInterval) return + this.flushWatcherInterval = setInterval(sweep, FileSystemStorage.FLUSH_WATCH_INTERVAL_MS) if (typeof this.flushWatcherInterval.unref === 'function') { this.flushWatcherInterval.unref() } } public override stopFlushRequestWatcher(): void { + if (this.flushWatcher) { + this.flushWatcher.close() + this.flushWatcher = undefined + } if (this.flushWatcherInterval) { clearInterval(this.flushWatcherInterval) this.flushWatcherInterval = undefined @@ -2622,25 +2913,29 @@ export class FileSystemStorage extends BaseStorage { this.allCountsDerivedBy = undefined this.allCountsSuspect = true needsPersist = true - prodLog.warn( + prodLog.narrate( '[FileSystemStorage] canonical count ledger was derived under the legacy ' + - 'container rule — marked suspect; a sanctioned recount (repairIndex) restores ' + - 'exact denominators' + 'container rule — it counts one entity per id DIRECTORY, so every ghost/scar ' + + 'container inflates it. Marked suspect, and an honest recount is scheduled to ' + + 'run in the background after this open; until it lands, do not subtract ' + + 'against these ALL scalars.' ) + // A suspect ledger used to stay wrong for the life of the store, + // waiting for an operator to run repairIndex. A downstream index + // heal took its "remaining" figure from these inflated + // denominators and reported work that did not exist. The ledger + // now HEALS ITSELF — in the background, because a denominator is + // a derived scalar and no read is ever served from it. + this.scheduleCountLedgerDerivation('legacy container-rule ledger') } } else { - const nouns = await this.scanCanonicalEntities('nouns') - const verbs = await this.scanCanonicalEntities('verbs') - this.totalNounCountAll = nouns.count - this.totalVerbCountAll = verbs.count - this.allCountsSuspect = false - this.allCountsDerivedBy = 'identity-record' - console.warn( - `[FileSystemStorage] counts.json predates the ALL-visibility count ledger — ` + - `derived once from the canonical id tree (${nouns.count} nouns, ${verbs.count} verbs, ` + - `every tier) and persisted; no further scan.` - ) - needsPersist = true + // No ALL scalars at all. There is nothing to serve in the meantime — + // a zero would read as an empty store — so the scalars stay unknown + // and SUSPECT until the background derivation lands. The open does + // not wait for it: an id-tree walk is O(ids) and this file has been + // the whole reason a 24k-id store opened in silence. + this.allCountsSuspect = true + this.scheduleCountLedgerDerivation('counts.json predates the ALL-visibility ledger') } // The vectored-noun scalar (shipped after the ALL scalars above — a @@ -2653,14 +2948,12 @@ export class FileSystemStorage extends BaseStorage { if (typeof counts.totalVectoredNounCount === 'number') { this.totalVectoredNounCount = counts.totalVectoredNounCount } else { - const vectored = await this.scanVectoredNounCount() - this.totalVectoredNounCount = vectored - console.warn( - `[FileSystemStorage] counts.json predates the vectored-noun count ledger — ` + - `derived once by reading every noun's vectors.json (${vectored} vectored) and ` + - `persisted; no further scan.` - ) - needsPersist = true + // O(nouns) CONTENT reads — the most expensive derivation of the + // three, and the one most likely to have been the silent minutes at + // the front of a large store's open. Background, suspect until it + // lands, same as the ALL scalars. + this.allCountsSuspect = true + this.scheduleCountLedgerDerivation('counts.json predates the vectored-noun ledger') } if (needsPersist) { await this.persistCounts() @@ -2689,6 +2982,22 @@ export class FileSystemStorage extends BaseStorage { * Initialize counts by scanning disk (only done once) */ private async initializeCountsFromDisk(): Promise { + const startedAt = Date.now() + // THIS ONE CANNOT LEAVE THE FOREGROUND, and the reason is worth stating: + // it derives `totalNounCount` / `totalVerbCount`, the scalars + // `getNounCount()` and `getVerbCount()` RETURN. Backgrounding it would + // make a populated store answer "0 entities" until the walk landed — a + // wrong answer, not a slow one, and the serving law grades a failure by + // whether an answer could be wrong. The ALL-visibility denominators, which + // no read is served from, DO run in the background (see + // scheduleCountLedgerDerivation). What this walk owes the operator instead + // is narration: it announces itself, and reports its wall. + prodLog.narrate( + `[FileSystemStorage] no usable counts.json — deriving the entity counters from ` + + `the canonical id tree now. This is O(ids) listings plus one vectors.json read ` + + `per noun, and it BLOCKS the open because getNounCount()/getVerbCount() are ` + + `served from it. It runs once; the result is persisted.` + ) try { // Count the CANONICAL 8.0 layout (`entities////…`) — // the tree saveNoun/getNouns actually read and write. The previous scan @@ -2736,6 +3045,11 @@ export class FileSystemStorage extends BaseStorage { } await this.persistCounts() + prodLog.narrate( + `[FileSystemStorage] counter derivation from the canonical id tree finished in ` + + `${Date.now() - startedAt}ms: ${this.totalNounCount} nouns, ${this.totalVerbCount} verbs, ` + + `${this.totalVectoredNounCount} vectored nouns — persisted, stamped identity-record.` + ) } catch (error) { console.error('Error initializing counts from disk:', error) } @@ -2757,6 +3071,118 @@ export class FileSystemStorage extends BaseStorage { * directories (absolute paths) — nouns feed the type-distribution estimate * above. An absent tree (fresh store) counts zero. */ + /** + * @description Derive the ALL-visibility count ledger honestly — one entity + * per IDENTITY RECORD, never per id directory — IN THE BACKGROUND, once, + * and persist the result stamped `identity-record`. + * + * Why background: these scalars are DENOMINATORS. No read is served from + * them, so deriving them cannot be allowed to hold an open hostage — a + * store with 24,898 ids spent minutes of a production restart inside walks + * exactly like these, in silence, before serving anything. Why at all: a + * ledger derived under the old container rule stayed wrong for the life of + * the store, and a downstream index heal subtracted against it and reported + * remaining work that did not exist (measured on a real store: 14,231 + * derived against 14,056 identity records — precisely the store's 25 noun + * scar directories; verbs 72,729 against 72,679, its 50 verb scars). + * + * Idempotent: a second call while one is in flight joins the first. + * @param reason - What made the ledger untrustworthy, quoted in narration. + * @returns Nothing; observe completion with {@link whenCountLedgerSettled}. + */ + private scheduleCountLedgerDerivation(reason: string): void { + if (this.countLedgerDerivation) return + this.countLedgerDerivation = (async () => { + const startedAt = Date.now() + prodLog.narrate( + `[FileSystemStorage] count-ledger derivation started in the background ` + + `(${reason}) — counting identity records, not id directories; the open does ` + + `not wait for it and no read is served from these scalars.` + ) + try { + const beforeNouns = this.totalNounCountAll + const beforeVerbs = this.totalVerbCountAll + const beforeVectored = this.totalVectoredNounCount + // A walk that RACED A WRITE cannot prove its number: a row that landed + // mid-walk may or may not have been in the shard the walk had already + // passed. Rather than persist a figure that might be off by one and + // stamp it "exact", the walk is repeated once on a quiet store, and if + // the store is never quiet the ledger stays SUSPECT and says so. One + // retry, never a spin. + let attempt = 0 + let derived: { nouns: number; verbs: number; vectored: number } | null = null + while (attempt < 2 && derived === null) { + attempt++ + const activityBefore = this.ledgerActivityStamp() + const nouns = await this.scanCanonicalEntities('nouns') + const verbs = await this.scanCanonicalEntities('verbs') + const vectored = await this.scanVectoredNounCount() + if (this.ledgerActivityStamp() === activityBefore) { + derived = { nouns: nouns.count, verbs: verbs.count, vectored } + } + } + if (derived === null) { + this.allCountsSuspect = true + prodLog.narrate( + `[FileSystemStorage] count-ledger derivation could not finish on a quiet store ` + + `after ${attempt} attempts (${Date.now() - startedAt}ms) — writes landed during ` + + `every walk. The ALL-visibility scalars stay SUSPECT and must not be subtracted ` + + `against; brain.repairIndex() derives them under a recount barrier.` + ) + return + } + this.totalNounCountAll = derived.nouns + this.totalVerbCountAll = derived.verbs + this.totalVectoredNounCount = derived.vectored + this.allCountsDerivedBy = 'identity-record' + this.allCountsSuspect = false + await this.persistCounts() + prodLog.narrate( + `[FileSystemStorage] count-ledger derivation finished in ${Date.now() - startedAt}ms: ` + + `${derived.nouns} nouns / ${derived.verbs} verbs / ${derived.vectored} vectored nouns` + + (beforeNouns !== derived.nouns || + beforeVerbs !== derived.verbs || + beforeVectored !== derived.vectored + ? ` (corrected from ${beforeNouns} / ${beforeVerbs} / ${beforeVectored} — the ` + + `difference is ghost and scar containers the old rule counted as entities)` + : ' (unchanged)') + + ` — persisted, stamped identity-record, no longer suspect.` + ) + } catch (error) { + // The ledger stays suspect and the next open retries. Loud: a + // denominator nobody can derive is a fact an operator must have. + this.allCountsSuspect = true + prodLog.error( + `[FileSystemStorage] count-ledger derivation FAILED after ` + + `${Date.now() - startedAt}ms — the ALL-visibility scalars remain SUSPECT ` + + `and must not be subtracted against; the next open retries:`, + error + ) + } + })() + } + + /** + * @description A cheap witness that the ledger changed while a walk was + * running. Every landed write moves one of these live counters, so an + * unchanged stamp across a walk means no write landed during it. + * @returns A value that differs whenever the live ALL scalars have moved. + */ + private ledgerActivityStamp(): string { + return `${this.totalNounCountAll}:${this.totalVerbCountAll}:${this.totalVectoredNounCount}` + } + + /** + * @description Resolve once any background count-ledger derivation has + * settled (succeeded or failed). Resolves immediately when none was needed. + * Exists so tests and operators can observe the ledger's honest value rather + * than race it; nothing in the read path waits on this. + * @returns A promise that settles with the derivation. + */ + public async whenCountLedgerSettled(): Promise { + await this.countLedgerDerivation + } + private async scanCanonicalEntities( kind: 'nouns' | 'verbs' ): Promise<{ count: number; sampleDirs: string[] }> { @@ -2841,14 +3267,20 @@ export class FileSystemStorage extends BaseStorage { } /** - * Count canonical nouns holding a REAL (non-empty) vector — the vectored- - * noun ledger scalar. UNLIKE {@link scanCanonicalEntities}, presence - * cannot be decided from the id-directory listing alone: a deferred-embed - * noun's `vectors.json` EXISTS (written at `add()` time with `vector: []`) - * until its embed LANDS, so this walk reads every noun's `vectors.json` - * CONTENT — O(nouns) reads, not O(ids) listing. Used ONLY for a one-time - * legacy-counts.json derivation or a lost/corrupted counts.json recovery; - * the result is persisted so this scan never repeats. + * Count canonical nouns holding a REAL (non-empty, non-zero-norm) vector — + * the vectored-noun ledger scalar. UNLIKE {@link scanCanonicalEntities}, + * presence cannot be decided from the id-directory listing alone: a + * deferred-embed noun's `vectors.json` EXISTS (written at `add()` time + * with `vector: []`) until its embed LANDS, so this walk reads every + * noun's `vectors.json` CONTENT — O(nouns) reads, not O(ids) listing. + * ZERO-NORM LAW: a real all-zero vector is not a vector — it never counts + * here either (Brainy's write paths normalize an explicit zero-norm + * vector to `[]` at write time, but a store created before that fix may + * still carry legacy all-zero rows on disk; this derivation must agree + * with the live ledger's definition of "vectored" regardless of when the + * row was written). Used ONLY for a one-time legacy-counts.json derivation + * or a lost/corrupted counts.json recovery; the result is persisted so + * this scan never repeats. */ private async scanVectoredNounCount(): Promise { const base = path.join(this.rootDir, 'entities', 'nouns') @@ -2862,7 +3294,12 @@ export class FileSystemStorage extends BaseStorage { for (const entry of ids) { if (!entry.isDirectory()) continue const record = await this.readEntityVectorRaw(path.join(shardPath, entry.name)) - if (record && Array.isArray(record.vector) && record.vector.length > 0) { + if ( + record && + Array.isArray(record.vector) && + record.vector.length > 0 && + !isZeroNormVector(record.vector) + ) { vectored++ } } @@ -2904,10 +3341,15 @@ export class FileSystemStorage extends BaseStorage { lastUpdated: new Date().toISOString() } - await fs.promises.writeFile( - this.countsFilePath, - JSON.stringify(counts, null, 2) - ) + // ATOMIC (temp + rename), never a plain writeFile. A direct write + // truncates the file first, so every persist opened a window — measured + // at roughly 750ms after a flush or close on a real store — in which a + // concurrent reader saw counts.json EMPTY. An empty file is unparseable, + // and an unparseable ledger sends the next open down the full-rescan + // path: the cheapest file in the store was costing the most expensive + // recovery. The rename is atomic, so a reader sees the old ledger or the + // new one, never neither. + await this.writeFileAtomic(this.countsFilePath, JSON.stringify(counts, null, 2)) } catch (error) { console.error('Error persisting counts:', error) } diff --git a/src/storage/baseStorage.ts b/src/storage/baseStorage.ts index 5510f93b..d8bcb780 100644 --- a/src/storage/baseStorage.ts +++ b/src/storage/baseStorage.ts @@ -125,6 +125,36 @@ export interface WriterLockInfo { rootDir?: string // Convenience for log lines / error messages } +/** + * THE CLEAN-CLOSE RECORD. Written by `releaseWriterLock()` at the instant it + * gives up the writer lock, naming the lock identity it released. The next + * `acquireWriterLock()` reads it and can then say — from a RECORD, not from a + * guess — whether the previous writer left on purpose. + * + * Why a record and not PID liveness: "the recorded PID is no longer alive" is + * true of every orderly restart AND of every crash, so the two were reported + * identically ("appears dead") and neither could be trusted. Worse, the same + * inference fails the other way when the operating system RECYCLES the pid — + * a live unrelated process makes a long-dead writer's lock look held, and the + * store refuses to open naming a pid that was never Brainy. A record settles + * both: matched → the previous writer closed cleanly, nothing to recover; + * absent → say so, and name what recovery the open will now run. + * + * Lifecycle: written at release, consumed (deleted) by the next successful + * lock claim — a record must never outlive the lock generation it describes, + * or it would vouch for a later crash. + */ +export interface WriterCloseRecord { + pid: number + hostname: string + /** `startedAt` of the lock this close released — the identity match key. */ + startedAt: string + /** ISO timestamp at which the lock was released. */ + closedAt: string + /** Brainy version that performed the close. */ + version: string +} + /** * FNV-1a hash returning a 2-char hex bucket (00-ff). * Distributes system keys across 256 sub-prefixes to avoid @@ -1407,6 +1437,29 @@ export abstract class BaseStorage extends BaseStorageAdapter { return this.listObjectsUnderPath(prefix) } + /** + * @description The IMMEDIATE child directory names under a prefix — one + * level, no recursion. See the seam's JSDoc (`db/types.ts`) for why a + * separate door exists. This default derives them from the recursive + * listing, so it is never WRONG, only never faster; the filesystem adapter + * overrides it with a single directory read. + * @param prefix - Storage-root-relative directory prefix. + * @returns The child directory names (not paths), in listing order. + */ + public async listRawPrefixes(prefix: string): Promise { + await this.ensureInitialized() + const paths = await this.listObjectsUnderPath(prefix) + const normalizedPrefix = prefix.endsWith('/') ? prefix : `${prefix}/` + const names = new Set() + for (const p of paths) { + const rest = p.startsWith(normalizedPrefix) ? p.slice(normalizedPrefix.length) : null + if (rest === null) continue + const slash = rest.search(/[/\\]/) + if (slash > 0) names.add(rest.slice(0, slash)) + } + return [...names] + } + /** * Remove every object under a storage-root-relative prefix. The filesystem * adapter overrides this with a recursive directory removal; this default diff --git a/src/transaction/operations/IndexOperations.ts b/src/transaction/operations/IndexOperations.ts index cfee5074..1bbbca88 100644 --- a/src/transaction/operations/IndexOperations.ts +++ b/src/transaction/operations/IndexOperations.ts @@ -324,8 +324,17 @@ export class ReplaceInVectorIndexOperation implements Operation { return async () => { // Restore the declared before-state in place (see class JSDoc for - // the item-did-not-exist posture). - await index.updateItem!({ id: this.id, vector: this.oldVector }, generation) + // the item-did-not-exist posture). A length-0 oldVector means the row + // was never actually indexed before this op ran (a length-0 vector is + // never a legal index member — see EmptyVectorIndexError) — there is + // no in-place "restore to empty" for the provider to perform, so + // rollback removes the row instead, leaving the same "not indexed" + // state the row was in before execute(). + if (this.oldVector.length > 0) { + await index.updateItem!({ id: this.id, vector: this.oldVector }, generation) + } else { + await this.index.removeItem(this.id, generation) + } } } @@ -336,9 +345,14 @@ export class ReplaceInVectorIndexOperation implements Operation { return async () => { // updateItem-style restore via the same adjacent pair, back to the - // declared before-state. + // declared before-state. Same length-0 carve-out as the updateItem + // path above: an empty oldVector was never a legal index member, so + // rollback just leaves the row removed rather than attempting an + // illegal empty re-add. await this.index.removeItem(this.id, generation) - await this.index.addItem({ id: this.id, vector: this.oldVector }, generation) + if (this.oldVector.length > 0) { + await this.index.addItem({ id: this.id, vector: this.oldVector }, generation) + } } } } diff --git a/src/types/brainy.types.ts b/src/types/brainy.types.ts index 63356828..a0d55c1e 100644 --- a/src/types/brainy.types.ts +++ b/src/types/brainy.types.ts @@ -215,7 +215,7 @@ export interface ScoreExplanation { * * @example * ```ts - * declare module '@soulcraft/brainy' { + * declare module '@soulcraftlabs/brainy' { * interface SubtypeRegistry { * // For NounType.Person, subtype 'employee': * 'person:employee': { employeeId: string; department: string } @@ -1217,6 +1217,13 @@ export interface RepairFamilyReport { skipped?: string /** Why the outcome is what it is when neither `detail` nor `skipped` says it. */ reason?: string + /** + * The phase's own wall, in milliseconds. A repair on a production store ran + * for over thirty minutes without a single line of output; an operator had + * to read `top` to know it was alive. A receipt that cannot say WHERE the + * time went is not a receipt — every row carries its own. + */ + durationMs?: number } /** The full receipt returned by repairIndex(). */ diff --git a/src/types/reservedFields.ts b/src/types/reservedFields.ts index 15b585c5..ce2108f8 100644 --- a/src/types/reservedFields.ts +++ b/src/types/reservedFields.ts @@ -65,7 +65,7 @@ * | `_rev` | system-managed revision counter — pass `ifRev` to `update()` for CAS | * * @example - * import { RESERVED_ENTITY_FIELDS } from '@soulcraft/brainy' + * import { RESERVED_ENTITY_FIELDS } from '@soulcraftlabs/brainy' * const isReserved = (key: string) => * (RESERVED_ENTITY_FIELDS as readonly string[]).includes(key) */ diff --git a/src/utils/brainyTypes.ts b/src/utils/brainyTypes.ts index 7db469bb..a008a5e6 100644 --- a/src/utils/brainyTypes.ts +++ b/src/utils/brainyTypes.ts @@ -6,7 +6,7 @@ * * @example * ```typescript - * import { BrainyTypes } from '@soulcraft/brainy' + * import { BrainyTypes } from '@soulcraftlabs/brainy' * * // Get all available types * const nounTypes = BrainyTypes.nouns // ['Person', 'Organization', ...] diff --git a/src/utils/indexReadiness.ts b/src/utils/indexReadiness.ts index 498f2003..f1b52e3b 100644 --- a/src/utils/indexReadiness.ts +++ b/src/utils/indexReadiness.ts @@ -153,3 +153,83 @@ export function assessProviderHealth(provider: unknown): ProviderHealthAssessmen reasons: readiness === 'not-ready' ? ['isReady() returned false'] : [] } } + +/** + * @description A provider's self-report that it is REBUILDING ITS OWN index + * right now. Returned by the optional `rebuildInProgress()` hook. + * + * The distinction this exists to make: a provider reporting `serving: false` + * because it is BROKEN and a provider reporting `serving: false` because it is + * BUSY BUILDING ITSELF look identical through `healthReport()` alone, and + * brainy treated both the same way — it called `rebuild()` and waited for it, + * on the foreground of `init()`. A production store whose metadata provider + * had to rebuild paid 641 SECONDS of that wait before `init()` returned, with + * every other family idle behind it. + * + * A provider that reports progress here owns its own rebuild: brainy neither + * starts one nor waits for it, `init()` returns, the other families serve, and + * THAT family's doors refuse by name — carrying this progress — until the + * provider reports itself serving. + * + * Every field but `phase` is optional and every field is a MEASUREMENT: a + * provider reports only what it actually tracks, never an estimate dressed as + * a fact. + */ +export interface ProviderRebuildProgress { + /** The provider's own name for what it is doing. Quoted verbatim in refusals. */ + phase: string + /** Units completed so far, if the provider counts them. */ + done?: number + /** Units expected in total, if the provider knows it. */ + total?: number + /** Epoch millis when this rebuild started, if the provider tracks it. */ + startedAt?: number +} + +/** A provider that can report a rebuild it is running itself. */ +interface MaybeRebuildingProvider { + rebuildInProgress?: () => ProviderRebuildProgress | null +} + +/** + * @description Ask a provider whether it is rebuilding itself right now. + * Synchronous, O(1), feature-detected: a provider without the hook reports + * nothing and is treated exactly as before. + * @param provider - Any index provider, or `null`/`undefined`. + * @returns The provider's progress, or `null` when it is not rebuilding (or + * does not implement the hook). + */ +export function assessProviderRebuild(provider: unknown): ProviderRebuildProgress | null { + const p = provider as MaybeRebuildingProvider | null | undefined + if (p == null || typeof p.rebuildInProgress !== 'function') return null + try { + const progress = p.rebuildInProgress() + if (!progress || typeof progress.phase !== 'string' || progress.phase.length === 0) { + return null + } + return progress + } catch { + // A throwing hook says nothing trustworthy about a rebuild; fall through to + // the ordinary health verdict rather than inventing one. + return null + } +} + +/** + * @description Render a rebuild progress report as one operator-facing clause, + * for a refusal message. Includes only what the provider actually measured. + * @param progress - The provider's report. + * @returns A clause such as `rebuilding ("metadata shadow build", 4,096/14,056, 12s elapsed)`. + */ +export function describeRebuildProgress(progress: ProviderRebuildProgress): string { + const parts: string[] = [`"${progress.phase}"`] + if (typeof progress.done === 'number' && typeof progress.total === 'number') { + parts.push(`${progress.done.toLocaleString()}/${progress.total.toLocaleString()}`) + } else if (typeof progress.done === 'number') { + parts.push(`${progress.done.toLocaleString()} done`) + } + if (typeof progress.startedAt === 'number') { + parts.push(`${Math.round((Date.now() - progress.startedAt) / 1000)}s elapsed`) + } + return `rebuilding (${parts.join(', ')})` +} diff --git a/src/utils/logger.ts b/src/utils/logger.ts index 5154d4fd..0d6b6594 100644 --- a/src/utils/logger.ts +++ b/src/utils/logger.ts @@ -266,6 +266,26 @@ export const prodLog = { console.error(message, ...args) }, + /** + * THE NARRATION CHANNEL — always visible, exactly like `error`. + * + * `warn`/`info`/`log` below are clamped to ERROR in any environment that + * looks like production (see isProductionEnvironment), which is the right + * default for chatter and the wrong one for the two things an operator is + * entitled to hear from a database no matter what: WHY IT IS SLOW and WHAT + * IT IS DOING ABOUT IT. A production service opening a 16 GB store spent + * three minutes emitting nothing at all — the phase timings that would have + * named the slow phase were written to `warn` and thrown away by the log + * level. Progress and cost narration goes here; it is never a per-record + * line, always a phase, a wall, or a bounded-cadence heartbeat. + * + * `silent: true` still silences it — that is the consumer's explicit + * request, not a cost default. + */ + narrate: (message?: any, ...args: any[]) => { + console.warn(message, ...args) + }, + // These are suppressed in production unless BRAINY_LOG_LEVEL is set warn: (message?: any, ...args: any[]) => smartConsole.warn(message, ...args), info: (message?: any, ...args: any[]) => smartConsole.info(message, ...args), diff --git a/src/utils/metadataIndex.ts b/src/utils/metadataIndex.ts index 3cc56b2e..3e0e3d17 100644 --- a/src/utils/metadataIndex.ts +++ b/src/utils/metadataIndex.ts @@ -2241,6 +2241,74 @@ export class MetadataIndexManager implements MetadataIndexProvider { break } + // ===== ARRAY SET OPERATORS ===== + // An element-indexed array field makes all three exact on the + // index path. They were previously ABSENT from this switch, so + // `fieldResults` kept its initial `[]` and the whole find() + // returned an empty page — a documented, matcher-implemented + // operator answering silently wrong. Served here instead. + + // hasAll: [a, b] — the field's array contains EVERY operand: + // the intersection of each element's posting set. + case 'hasAll': { + if (!Array.isArray(operand)) { + fieldResults = [] + break + } + if (operand.length === 0) { + // Vacuously true of every row that HAS the field. + const anyBitmap = (this.columnStore && this.columnStore.hasField(field)) + ? await this.columnStore.rangeQuery(field) + : await this.getExistsBitmapLegacy(field) + fieldResults = this.idMapper.intsIterableToUuids(anyBitmap) + break + } + let intersection: Set | null = null + for (const item of operand) { + const ids = new Set(await this.getIds(field, item)) + if (intersection === null) { + intersection = ids + } else { + for (const id of [...intersection]) { + if (!ids.has(id)) intersection.delete(id) + } + } + if (intersection.size === 0) break + } + fieldResults = intersection ? [...intersection] : [] + break + } + + // noneOf: [a, b] — the field's value is NONE of the operands: + // the complement of their union. + case 'noneOf': { + if (!Array.isArray(operand)) { + fieldResults = [] + break + } + const excludeInts: number[] = [] + for (const value of operand) { + for (const uuid of await this.getIds(field, value)) { + const intId = this.idMapper.getInt(uuid) + if (intId !== undefined) excludeInts.push(intId) + } + } + fieldResults = this.complementIds(excludeInts) + break + } + + // excludes: value — the field's array does NOT contain the value: + // the complement of `contains`. + case 'excludes': { + const excludeInts: number[] = [] + for (const uuid of await this.getIds(field, operand)) { + const intId = this.idMapper.getInt(uuid) + if (intId !== undefined) excludeInts.push(intId) + } + fieldResults = this.complementIds(excludeInts) + break + } + // ===== MISSING OPERATOR ===== // missing: boolean - equivalent to exists: !boolean case 'missing': { @@ -2257,6 +2325,27 @@ export class MetadataIndexManager implements MetadataIndexProvider { } break } + + // ===== EVERYTHING ELSE: REFUSED BY NAME, NEVER ANSWERED EMPTY ==== + // An equality/range posting index cannot evaluate a substring, a + // pattern or an array length without reading every row, and this + // path exists precisely to avoid that. It used to fall out of the + // switch with `fieldResults` still `[]`, so `find({ where: { name: + // { startsWith: 'a' } } })` returned an empty page and looked like + // an answer. An accepted operator either works or refuses — the + // matcher's own support for these operators governs in-memory + // filtering, never an index-backed find(). + default: + throw new BrainyError( + `Filter operator "${op}" on field "${rawField}" cannot be served by the ` + + `metadata index: an equality/range posting index cannot evaluate substrings, ` + + `patterns or array lengths without reading every row. It is REFUSED rather ` + + `than answered with an empty page. Filter on an indexable operator ` + + `(equals/eq, notEquals/ne, oneOf/in, noneOf, greaterThan/gt, ` + + `greaterThanOrEqual/gte, lessThan/lt, lessThanOrEqual/lte, between, contains, ` + + `excludes, hasAll, exists, missing) and narrow the rest in your own code.`, + 'INVALID_QUERY' + ) } // Intersect this operator's matches with the running set (AND semantics // for multiple operators on the same field). diff --git a/src/utils/paramValidation.ts b/src/utils/paramValidation.ts index 606516ac..00790a4a 100644 --- a/src/utils/paramValidation.ts +++ b/src/utils/paramValidation.ts @@ -613,6 +613,17 @@ export function validateUpdateParams(params: UpdateParams): void { // null/undefined means "no new data was given". const hasData = params.data !== undefined && params.data !== null if ((params as UpdateParams & { deferEmbedding?: boolean }).deferEmbedding === true) { + if (params.vector && params.vector.length === 0) { + // The nonsensical combination Leg D of the zero-norm/unvector-door law + // refuses: `vector: []` is the SANCTIONED UNVECTOR DOOR — an explicit + // instruction to remove the vector NOW, never "please embed" — so it + // cannot be paired with a request to defer an embed. + throw new Error( + `update(): 'vector: []' (the unvector door) cannot be combined with ` + + `'deferEmbedding: true' — an unvector is an explicit instruction to remove ` + + `the vector now, not a request to defer an embed. Drop one of the two.` + ) + } if (params.vector) { throw new Error( `update(): deferEmbedding cannot be combined with an explicit 'vector' — ` + @@ -649,8 +660,16 @@ export function validateUpdateParams(params: UpdateParams): void { throw new Error(`invalid NounType: ${params.type}`) } - // Validate vector dimensions if provided - if (params.vector) { + // Validate vector dimensions if provided. A length-0 vector is the + // SANCTIONED UNVECTOR DOOR (see brainy.ts update()'s matching comment): an + // explicit `vector: []` — or a real all-zero vector, normalized to `[]` + // upstream by the zero-norm law — carries no dimension information, + // exactly like validateAddParams's identical exemption, so it is exempt + // from the dimension check rather than refused as a "0-dimensional + // vector". (The `deferEmbedding` combination above already refuses + // `vector: []` paired with `deferEmbedding: true` — an empty array is + // truthy, so that guard fires unconditionally on any explicit `vector`.) + if (params.vector && params.vector.length > 0) { const config = ValidationConfig.getInstance() if (params.vector.length !== config.maxVectorDimensions) { throw new Error(`vector must have exactly ${config.maxVectorDimensions} dimensions`) diff --git a/src/utils/version.ts b/src/utils/version.ts index d616cee3..327f923c 100644 --- a/src/utils/version.ts +++ b/src/utils/version.ts @@ -1,6 +1,6 @@ /** * @module utils/version - * @description Resolves the running `@soulcraft/brainy` package version. Brainy 8.0 + * @description Resolves the running `@soulcraftlabs/brainy` package version. Brainy 8.0 * targets Node-like runtimes only (Node.js, Bun, Deno — all expose `node:fs`), so the * version is read **synchronously** from `package.json` on first call and cached. * @@ -83,3 +83,27 @@ export function getAugmentationVersion(service: string): { augmentation: string; version: getBrainyVersion() } } + +/** + * The API-contract version this build implements — a single integer that two + * engines can compare without probing prototypes. + * + * A MINOR release is ADDITIVE: doors and error codes may be added, never + * removed or narrowed, and the contract integer does not move. A MAJOR release + * is what a REQUIRED door's removal or a behavioural narrowing costs, and it + * bumps this integer. A consumer pinning `brainyContract` in a peer range is + * therefore pinning "what I may call", not "which build I run". + * + * Declared in package.json as `"brainyContract"` so a manifest, a tool, or a + * sibling package can read it without importing the engine, and returned here + * so a running process can state its own. + */ +export const BRAINY_CONTRACT_VERSION = 1 as const + +/** + * @description The API-contract version this build implements. + * @returns The contract integer — see {@link BRAINY_CONTRACT_VERSION}. + */ +export function contractVersion(): number { + return BRAINY_CONTRACT_VERSION +} diff --git a/src/vfs/VirtualFileSystem.ts b/src/vfs/VirtualFileSystem.ts index 59a16be4..46c6a12d 100644 --- a/src/vfs/VirtualFileSystem.ts +++ b/src/vfs/VirtualFileSystem.ts @@ -6,6 +6,7 @@ */ import { Readable, Writable } from 'stream' +import { prodLog } from '../utils/logger.js' import crypto from 'crypto' import { v4 as uuidv4 } from '../universal/uuid.js' import { Brainy } from '../brainy.js' @@ -66,6 +67,20 @@ export class VirtualFileSystem implements IVirtualFileSystem { private config: Required> & { rootEntityId?: string } private rootEntityId?: string private initialized = false + /** + * The one-time old-root sweep, in flight. See {@link sweepOldRootsIfNeeded}. + */ + private rootSweep?: Promise + /** + * Where the completed old-root sweep is recorded. Engine plumbing under + * `_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')) @@ -143,8 +158,17 @@ export class VirtualFileSystem implements IVirtualFileSystem { // Create or find root entity this.rootEntityId = await this.initializeRoot() - // Clean up old UUID-based roots (one-time migration) - await this.cleanupOldRoots() + // Clean up old UUID-based roots — ONCE PER STORE, BEHIND THE DOORS. + // This is a migration sweep for roots created before the fixed root id + // existed. It ran on EVERY open, forever: a filtered find over the whole + // store hunting for duplicates that a store has either always had or + // never will. MEASURED on a 14,056-noun / 72,679-verb store: the phase it + // dominates cost 43-53 SECONDS of every open, warm reopens included. + // Now: a durable marker records that the sweep has run, and a store + // carrying it never sweeps again; a store without one sweeps in the + // BACKGROUND (the sweep only removes duplicate roots — nothing serves + // from them — and it was always declared non-critical). + this.rootSweep = this.sweepOldRootsIfNeeded() // Initialize projection registry with auto-discovery of built-in projections this.projectionRegistry = new ProjectionRegistry() @@ -394,7 +418,100 @@ export class VirtualFileSystem implements IVirtualFileSystem { * * This is a one-time migration helper that can be removed in future versions. */ - private async cleanupOldRoots(): Promise { + /** + * @description Run the old-root sweep at most once per store, in the + * background, and record that it ran. See the call site in {@link init} for + * the measurement that made this necessary. + * @returns A promise that settles when the sweep has finished (or was + * skipped); nothing in the read path awaits it. + */ + private async sweepOldRootsIfNeeded(): Promise { + const store = this.rawObjectStore() + if (store === null) { + // A storage adapter with no raw-object door cannot carry the marker. + // Sweep every open, as before — correctness over cost. + await this.cleanupOldRoots() + return + } + try { + const marker = await store.readRawObject(VirtualFileSystem.ROOT_SWEEP_MARKER_PATH) + if (marker !== null && marker !== undefined) return + } 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. + const startedAt = Date.now() + const duplicatesRemoved = await this.cleanupOldRoots() + const elapsedMs = Date.now() - startedAt + try { + await store.writeRawObject(VirtualFileSystem.ROOT_SWEEP_MARKER_PATH, { + sweptAt: new Date().toISOString(), + durationMs: elapsedMs + }) + 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.' + ) + } + } catch (error) { + // Unrecorded sweep = the next open sweeps again. Conservative, and said + // out loud rather than quietly repeated forever. + prodLog.narrate( + `[VFS] old-root sweep finished in ${Date.now() - startedAt}ms but could NOT be ` + + `recorded (${(error as Error).message}) — the next open will sweep again.` + ) + } + } + + /** + * @description Settle once the background old-root sweep has finished. + * Resolves immediately when the store already carried the marker. Exists so + * tests and operators can observe the sweep instead of racing it; no read + * path waits on it. + * @returns A promise that settles with the sweep. + */ + public async whenRootSweepSettled(): Promise { + await this.rootSweep + } + + /** + * @description The brain's storage adapter, narrowed to the raw-object door + * this migration marker needs. Boundary: `Brainy.storage` is private, and + * this is the same reach-in the engine uses elsewhere for exactly this kind + * of engine-internal artifact. Returns null when the adapter has no + * raw-object door. + */ + private rawObjectStore(): { + readRawObject: (key: string) => Promise + writeRawObject: (key: string, value: unknown) => Promise + } | null { + const storage = (this.brain as unknown as { storage?: Record }).storage + if ( + storage && + typeof storage.readRawObject === 'function' && + typeof storage.writeRawObject === 'function' + ) { + return storage as unknown as { + readRawObject: (key: string) => Promise + writeRawObject: (key: string, value: unknown) => Promise + } + } + return null + } + + private async cleanupOldRoots(): Promise { + let removed = 0 try { // Find any old VFS roots with UUID-based IDs (not our fixed ID) const oldRoots = await this.brain.find({ @@ -416,6 +533,7 @@ 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) @@ -428,6 +546,7 @@ export class VirtualFileSystem implements IVirtualFileSystem { // Non-critical error - log and continue console.warn('VFS: Cleanup of old roots failed (non-critical):', error) } + return removed } /** diff --git a/tests/integration/count-ledger-identity-record.test.ts b/tests/integration/count-ledger-identity-record.test.ts new file mode 100644 index 00000000..1066213a --- /dev/null +++ b/tests/integration/count-ledger-identity-record.test.ts @@ -0,0 +1,251 @@ +/** + * @module tests/integration/count-ledger-identity-record + * @description THE COUNT LEDGER COUNTS RECORDS, NOT DIRECTORIES — and heals + * itself when it was derived the other way. + * + * Measured on a real store: the ALL-visibility ledger read 14,231 nouns + * against 14,056 identity records, and 72,729 verbs against 72,679 — exactly + * that store's 25 noun and 50 verb SCAR directories (empty `/` containers + * left by a pre-8.3.1 partial delete). Two copies of the SAME archive derived + * different numbers, because each had been persisted at a different moment + * under the old container rule. A downstream index heal subtracted against + * those denominators and reported remaining work that did not exist. + * + * The membership predicate is the IDENTITY RECORD (the metadata content leg). + * The scan already applies it; what is pinned here is that a ledger persisted + * under the OLD rule does not go on lying — it is corrected in the background, + * without blocking the open, and two copies of one archive agree. + */ + +import { describe, it, expect, afterEach } from 'vitest' +import { + mkdtempSync, + mkdirSync, + rmSync, + writeFileSync, + readFileSync, + cpSync, + existsSync +} from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { Brainy } from '../../src/brainy.js' +import { NounType } from '../../src/types/graphTypes.js' +import { FileSystemStorage as FileSystemStorageClass } from '../../src/storage/adapters/fileSystemStorage.js' +import type { FileSystemStorage } from '../../src/storage/adapters/fileSystemStorage.js' + +const NOUN_COUNT = 6 +const NOUN_SCARS = 3 +const VERB_SCARS = 2 +/** A REAL two-hex shard — the scan skips any directory that is not one. */ +const SCAR_SHARD = 'ab' + +function makeTempDir(): string { + return mkdtempSync(join(tmpdir(), 'brainy-count-ledger-')) +} + +/** The FileSystemStorage behind a brain. */ +function storageOf(brain: Brainy): FileSystemStorage { + return (brain as unknown as { storage: FileSystemStorage }).storage +} + +/** + * Add `count` empty `/` container directories under + * `entities///` — scars, exactly as a partial delete leaves them. + */ +function addScarContainers(dir: string, kind: 'nouns' | 'verbs', count: number): void { + for (let i = 0; i < count; i++) { + const id = `${SCAR_SHARD}5ca4000-0000-0000-0000-00000000000${i}` + mkdirSync(join(dir, 'entities', kind, SCAR_SHARD, id), { recursive: true }) + } +} + +/** Add one GHOST container: a `vectors.json` leg with no identity record. */ +function addGhostContainer(dir: string): void { + const id = `${SCAR_SHARD}9405700-0000-0000-0000-000000000000` + const idDir = join(dir, 'entities', 'nouns', SCAR_SHARD, id) + mkdirSync(idDir, { recursive: true }) + writeFileSync(join(idDir, 'vectors.json'), JSON.stringify({ id, vector: [0.1, 0.2] })) +} + +/** + * Rewrite counts.json into the LEGACY shape: ALL scalars inflated by the + * containers, and no `allCountsDerivedBy` stamp — exactly what a store carried + * when it was last written by a build that counted directories. + */ +function writeLegacyCountsLedger(dir: string, inflateNouns: number, inflateVerbs: number): void { + const file = join(dir, '_system', 'counts.json') + const counts = JSON.parse(readFileSync(file, 'utf-8')) + counts.totalNounCountAll = (counts.totalNounCountAll ?? 0) + inflateNouns + counts.totalVerbCountAll = (counts.totalVerbCountAll ?? 0) + inflateVerbs + delete counts.allCountsDerivedBy + delete counts.allCountsSuspect + writeFileSync(file, JSON.stringify(counts, null, 2)) +} + +/** + * Seed a store and return the HONEST ledger it holds when freshly written — + * the baseline the correction must return to. Read from the engine rather than + * hardcoded: an open creates its own rows (the VFS root), and a pin that + * asserts a literal would be pinning that incidental fact instead of the rule. + */ +async function seedStore(dir: string): Promise<{ nouns: number; verbs: number }> { + const brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await brain.init() + const ids: string[] = [] + for (let i = 0; i < NOUN_COUNT; i++) { + ids.push(await brain.add({ data: `entity number ${i}`, type: NounType.Concept })) + } + await brain.relate({ from: ids[0], to: ids[1], type: 'relatedTo' } as never) + await brain.relate({ from: ids[1], to: ids[2], type: 'relatedTo' } as never) + await brain.flush() + const ledger = await storageOf(brain).getCanonicalCounts() + const baseline = { nouns: ledger.nouns.all, verbs: ledger.verbs.all } + await brain.close() + return baseline +} + +/** + * Make the ledger walk take `ms` so a test can observe the open completing + * WITHOUT it. Patches the prototype before any brain is constructed; returns + * the restore function. + */ +function slowTheLedgerWalk(ms: number): () => void { + const proto = ( + FileSystemStorageClass as unknown as { + prototype: Record Promise> + } + ).prototype + const real = proto.scanCanonicalEntities + proto.scanCanonicalEntities = async function slow(this: unknown, ...args: unknown[]) { + await new Promise((r) => setTimeout(r, ms)) + return real.apply(this, args) + } + return () => { proto.scanCanonicalEntities = real } +} + +describe('the canonical count ledger', () => { + const dirs: string[] = [] + + afterEach(() => { + for (const d of dirs.splice(0)) { + try { rmSync(d, { recursive: true, force: true }) } catch { /* ignore */ } + } + }) + + function trackDir(): string { + const dir = makeTempDir() + dirs.push(dir) + return dir + } + + it('corrects a legacy container-rule ledger in the background, counting identity records', async () => { + const dir = trackDir() + const baseline = await seedStore(dir) + + // Scars and a ghost: containers with no identity record. + addScarContainers(dir, 'nouns', NOUN_SCARS) + addScarContainers(dir, 'verbs', VERB_SCARS) + addGhostContainer(dir) + // The ledger as the old rule left it: every container counted. + writeLegacyCountsLedger(dir, NOUN_SCARS + 1, VERB_SCARS) + + const restore = slowTheLedgerWalk(1_500) + let brain: Brainy + try { + const openStarted = Date.now() + brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await brain.init() + const openMs = Date.now() - openStarted + const storage = storageOf(brain) + + // THE OPEN DID NOT WAIT. Two walks of 1.5s each would have added 3s. + expect(openMs).toBeLessThan(2_500) + // And while it runs, the scalars say so instead of being subtracted against. + const atOpen = await storage.getCanonicalCounts() + expect(atOpen.suspect).toBe(true) + expect(atOpen.nouns.all).toBe(baseline.nouns + NOUN_SCARS + 1) + + await storage.whenCountLedgerSettled() + } finally { + restore() + } + const storage = storageOf(brain!) + + const healed = await storage.getCanonicalCounts() + expect(healed.nouns.all).toBe(baseline.nouns) + expect(healed.verbs.all).toBe(baseline.verbs) + expect(healed.suspect).toBe(false) + + // And it is PERSISTED with the honest stamp — the correction survives a + // reopen instead of being re-derived (or re-lost) every time. + await brain!.close() + const persisted = JSON.parse(readFileSync(join(dir, '_system', 'counts.json'), 'utf-8')) + expect(persisted.totalNounCountAll).toBe(baseline.nouns) + expect(persisted.totalVerbCountAll).toBe(baseline.verbs) + expect(persisted.allCountsDerivedBy).toBe('identity-record') + + const reopened = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await reopened.init() + const afterReopen = await storageOf(reopened).getCanonicalCounts() + expect(afterReopen.nouns.all).toBe(baseline.nouns) + expect(afterReopen.suspect).toBe(false) + await reopened.close() + }, 180_000) + + it('derives the same number from two copies of one archive', async () => { + const source = trackDir() + const baseline = await seedStore(source) + addScarContainers(source, 'nouns', NOUN_SCARS) + addGhostContainer(source) + + // Two copies of the SAME bytes, each carrying a DIFFERENT legacy ledger — + // the situation that made one archive report 14,231 and its twin 14,081. + const copyA = trackDir() + const copyB = trackDir() + cpSync(source, copyA, { recursive: true }) + cpSync(source, copyB, { recursive: true }) + writeLegacyCountsLedger(copyA, NOUN_SCARS + 1, 0) + writeLegacyCountsLedger(copyB, 1, 0) + + const derived: number[] = [] + for (const dir of [copyA, copyB]) { + const brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await brain.init() + const storage = storageOf(brain) + await storage.whenCountLedgerSettled() + derived.push((await storage.getCanonicalCounts()).nouns.all) + await brain.close() + } + expect(derived[0]).toBe(derived[1]) + expect(derived[0]).toBe(baseline.nouns) + }, 180_000) + + it('writes counts.json atomically — no reader ever sees it empty', async () => { + const dir = trackDir() + await seedStore(dir) + const file = join(dir, '_system', 'counts.json') + expect(existsSync(file)).toBe(true) + + const brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await brain.init() + const storage = storageOf(brain) + + // Watch the ledger across many persists. A truncating write leaves a + // window in which the file parses as nothing; a temp+rename never does. + let sawUnparseable = 0 + const watcher = setInterval(() => { + try { + JSON.parse(readFileSync(file, 'utf-8')) + } catch { + sawUnparseable++ + } + }, 1) + for (let i = 0; i < 40; i++) { + await (storage as unknown as { persistCounts: () => Promise }).persistCounts() + } + clearInterval(watcher) + await brain.close() + expect(sawUnparseable).toBe(0) + }, 180_000) +}) diff --git a/tests/integration/entity-tree-stamp.test.ts b/tests/integration/entity-tree-stamp.test.ts index deefc5e6..23cc0a15 100644 --- a/tests/integration/entity-tree-stamp.test.ts +++ b/tests/integration/entity-tree-stamp.test.ts @@ -57,7 +57,11 @@ 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()) - expect(stamp.sourceGeneration).toBe(brain.generation()) + // 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.generation).toBeGreaterThanOrEqual(1) }) @@ -112,6 +116,96 @@ 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', @@ -127,7 +221,13 @@ describe('entity-tree family stamp', () => { stampSource: 5, head: 9 }) - expect(verifyFamilyStamp(rollup, 3, { nounCount: 10 }).state).toBe('incoherent') // ahead of head + // 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(null, 5, {})).toEqual({ state: 'absent' }) const enumerated: FamilyStamp = { diff --git a/tests/integration/filter-operator-conformance.test.ts b/tests/integration/filter-operator-conformance.test.ts new file mode 100644 index 00000000..628017e7 --- /dev/null +++ b/tests/integration/filter-operator-conformance.test.ts @@ -0,0 +1,151 @@ +/** + * @module tests/integration/filter-operator-conformance + * @description THE OPERATOR SET, AND WHAT EACH TOKEN DOES ON THE INDEX PATH. + * + * The contract-1 manifest splits this engine's `where` operators three ways — + * served, served-beyond-baseline, refused-by-name — and two engines must agree + * token for token. This lane is the machine-checkable side of that agreement: + * it asserts the EXACT accepted set (so a manifest can be diffed against a run + * rather than against prose), and it pins each of the three classes. + * + * The defect it closes: the metadata index's operator switch had no default + * case, so an operator it does not implement — `hasAll`, `noneOf`, `excludes`, + * `startsWith`, `endsWith`, `matches`, `length` — left the field's match set at + * its initial `[]` and `find()` returned an empty page. A documented operator, + * implemented in the in-memory matcher, answering silently wrong. Three of the + * seven are now SERVED on the index path; the other four are REFUSED BY NAME, + * because an equality/range posting index cannot evaluate a substring, a + * pattern or an array length without reading every row. + */ + +import { describe, it, expect, afterEach } from 'vitest' +import { mkdtempSync, rmSync, readFileSync } from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { Brainy } from '../../src/brainy.js' +import { NounType } from '../../src/types/graphTypes.js' +import { contractVersion, BRAINY_CONTRACT_VERSION } from '../../src/utils/version.js' + +/** The accepted `where` value-operator tokens, as a sorted list. */ +const ACCEPTED_OPERATORS = [ + 'between', 'contains', 'endsWith', 'eq', 'equals', 'excludes', 'exists', + 'greaterThan', 'greaterThanOrEqual', 'gt', 'gte', 'hasAll', 'in', 'length', + 'lessThan', 'lessThanOrEqual', 'lt', 'lte', 'matches', 'missing', 'ne', + 'noneOf', 'notEquals', 'oneOf', 'startsWith' +] as const + +/** Served on the index path with exact posting-set semantics. */ +const SERVED_ON_INDEX = [ + 'between', 'contains', 'eq', 'equals', 'exists', 'greaterThan', + 'greaterThanOrEqual', 'gt', 'gte', 'in', 'lessThan', 'lessThanOrEqual', + 'lt', 'lte', 'missing', 'ne', 'notEquals', 'oneOf', + 'excludes', 'hasAll', 'noneOf' +] as const + +/** Accepted by name, refused by the index path — never answered empty. */ +const REFUSED_BY_INDEX = ['endsWith', 'length', 'matches', 'startsWith'] as const + +describe('filter operator conformance', () => { + const dirs: string[] = [] + const brains: Brainy[] = [] + + afterEach(async () => { + for (const b of brains.splice(0)) { + try { await b.close() } catch { /* already closed */ } + } + for (const d of dirs.splice(0)) { + try { rmSync(d, { recursive: true, force: true }) } catch { /* ignore */ } + } + }) + + async function seeded(): Promise { + const dir = mkdtempSync(join(tmpdir(), 'brainy-operators-')) + dirs.push(dir) + const brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + brains.push(brain) + await brain.init() + await brain.add({ + data: 'a document about ferrets', + type: NounType.Document, + metadata: { tags: ['ferret', 'small', 'furry'], team: 'alpha' } + }) + await brain.add({ + data: 'a document about whales', + type: NounType.Document, + metadata: { tags: ['whale', 'large'], team: 'beta' } + }) + await brain.flush() + return brain + } + + it('the accepted operator set is exactly these 25 tokens', async () => { + const brain = await seeded() + // The engine names its own valid set in the refusal it raises for an + // unknown token — the honest place to read it from. + let message = '' + try { + await brain.find({ where: { team: { notIn: ['alpha'] } } } as never) + } catch (err) { + message = (err as Error).message + } + expect(message).toMatch(/Unknown filter operator "notIn"/) + const listed = (message.match(/Valid operators: ([^.]+)\./)?.[1] ?? '') + .split(',') + .map((t) => t.trim()) + .filter(Boolean) + .sort() + expect(listed).toEqual([...ACCEPTED_OPERATORS].sort()) + expect(listed.length).toBe(25) + // Four tokens a sibling manifest listed as served aliases are NOT in this + // engine's set and never have been — they raise INVALID_QUERY. + for (const absent of ['is', 'isNot', 'greaterEqual', 'lessEqual']) { + expect(listed).not.toContain(absent) + await expect( + brain.find({ where: { team: { [absent]: 'alpha' } } } as never) + ).rejects.toThrow(/Unknown filter operator/) + } + }, 120_000) + + it('serves hasAll, noneOf and excludes on the index path — never an empty page', async () => { + const brain = await seeded() + + const hasAll = await brain.find({ where: { tags: { hasAll: ['ferret', 'furry'] } } } as never) + expect(hasAll.length).toBe(1) + expect((hasAll[0] as { metadata?: Record }).metadata?.team).toBe('alpha') + + const noneOf = await brain.find({ where: { team: { noneOf: ['alpha'] } } } as never) + expect(noneOf.length).toBe(1) + expect((noneOf[0] as { metadata?: Record }).metadata?.team).toBe('beta') + + const excludes = await brain.find({ where: { tags: { excludes: 'whale' } } } as never) + expect(excludes.length).toBe(1) + expect((excludes[0] as { metadata?: Record }).metadata?.team).toBe('alpha') + + // hasAll with an operand nothing carries is EMPTY because it is empty — + // the honest zero, reached by evaluating the operator. + const none = await brain.find({ where: { tags: { hasAll: ['ferret', 'whale'] } } } as never) + expect(none.length).toBe(0) + }, 120_000) + + it('refuses the four index-unserveable operators BY NAME', async () => { + const brain = await seeded() + for (const op of REFUSED_BY_INDEX) { + const operand = op === 'length' ? 3 : 'a' + await expect( + brain.find({ where: { team: { [op]: operand } } } as never), + `${op} must refuse, never answer an empty page` + ).rejects.toThrow(new RegExp(`Filter operator "${op}".*cannot be served by the metadata index`, 's')) + } + }, 120_000) + + it('declares its contract version in code and in package.json', async () => { + expect(contractVersion()).toBe(1) + expect(BRAINY_CONTRACT_VERSION).toBe(1) + const pkg = JSON.parse(readFileSync(join(process.cwd(), 'package.json'), 'utf-8')) + expect(pkg.brainyContract).toBe(contractVersion()) + }) + + it('the three classes partition the accepted set', () => { + expect([...SERVED_ON_INDEX, ...REFUSED_BY_INDEX].sort()).toEqual([...ACCEPTED_OPERATORS].sort()) + }) +}) diff --git a/tests/integration/flush-watcher-event-driven.test.ts b/tests/integration/flush-watcher-event-driven.test.ts new file mode 100644 index 00000000..4b2e80c4 --- /dev/null +++ b/tests/integration/flush-watcher-event-driven.test.ts @@ -0,0 +1,94 @@ +/** + * @module tests/integration/flush-watcher-event-driven + * @description THE FLUSH-REQUEST WATCH IS EVENT-DRIVEN. + * + * It used to `readdir` the request directory every 500 ms, per brain, for the + * life of every writer — armed on every non-reader brain whether or not any + * inspector process existed. MEASURED on a production process holding 21 + * brains: 42 directory reads per second on a completely idle service, plus a + * stale-request GC pass on every one of them. + * + * The law: a request that has not been made is not a cause. The arrival itself + * wakes the watcher, so the request is seen SOONER than the poll saw it, and a + * slow safety sweep covers filesystems that drop watch events and the GC. + */ + +import { describe, it, expect, afterEach, vi } from 'vitest' +import { mkdtempSync, rmSync, writeFileSync, mkdirSync } from 'node:fs' +import * as nodeFs from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { Brainy } from '../../src/brainy.js' +import { NounType } from '../../src/types/graphTypes.js' + +describe('the flush-request watcher', () => { + const dirs: string[] = [] + const brains: Brainy[] = [] + + afterEach(async () => { + for (const b of brains.splice(0)) { + try { await b.close() } catch { /* already closed */ } + } + for (const d of dirs.splice(0)) { + try { rmSync(d, { recursive: true, force: true }) } catch { /* ignore */ } + } + vi.restoreAllMocks() + }) + + async function openWriter(): Promise<{ brain: Brainy; dir: string }> { + const dir = mkdtempSync(join(tmpdir(), 'brainy-flush-watch-')) + dirs.push(dir) + const brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + brains.push(brain) + await brain.init() + await brain.add({ data: 'a row', type: NounType.Concept }) + await brain.flush() + return { brain, dir } + } + + it('does not poll the request directory on an idle writer', async () => { + const { dir } = await openWriter() + const reqDir = join(dir, 'locks', '_flush_requests') + + // Count real reads of the request directory over a window far longer than + // the old 500ms poll (which would have made ~16 of them). + const realReaddir = nodeFs.promises.readdir + let requestDirReads = 0 + const spy = vi + .spyOn(nodeFs.promises, 'readdir') + .mockImplementation((async (p: unknown, ...rest: unknown[]) => { + if (String(p) === reqDir) requestDirReads++ + return (realReaddir as unknown as (...a: unknown[]) => Promise)(p, ...rest) + }) as typeof nodeFs.promises.readdir) + + await new Promise((r) => setTimeout(r, 8_000)) + spy.mockRestore() + + // The old poll: 500ms → ~16 reads. The safety sweep is 30s → 0 in this window. + expect(requestDirReads).toBeLessThanOrEqual(1) + }, 120_000) + + it('answers a request that arrives, without waiting for the sweep', async () => { + const { brain, dir } = await openWriter() + const reqDir = join(dir, 'locks', '_flush_requests') + const ackDir = join(dir, 'locks', '_flush_responses') + mkdirSync(reqDir, { recursive: true }) + + // Drop a request exactly as an out-of-process inspector does. + const id = 'test-request-0001' + writeFileSync(join(reqDir, `${id}.req`), JSON.stringify({ at: Date.now() })) + + // The ack must land far sooner than the 30s safety sweep. + const deadline = Date.now() + 10_000 + let acked = false + while (Date.now() < deadline) { + try { + const entries = await nodeFs.promises.readdir(ackDir) + if (entries.some((e) => e.startsWith(id))) { acked = true; break } + } catch { /* dir not created yet */ } + await new Promise((r) => setTimeout(r, 100)) + } + expect(acked, 'the watcher must answer an arriving request').toBe(true) + void brain + }, 120_000) +}) diff --git a/tests/integration/health-gate.test.ts b/tests/integration/health-gate.test.ts index 1c9a642d..f2952116 100644 --- a/tests/integration/health-gate.test.ts +++ b/tests/integration/health-gate.test.ts @@ -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 generation, twice across a generation bump', async () => { + it('a heal:"repair" failure serves; narrates once per DISTINCT VERDICT, not once per generation bump', async () => { const brain = new Brainy(createTestConfig({ silent: true })) await brain.init() brains.push(brain) @@ -197,12 +197,13 @@ 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: 'counter drift' })], + invariants: [invariant({ name: 'stale-vector-counter', holds: false, heal: 'repair', detail })], generation }) @@ -212,11 +213,22 @@ 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 generation both times — one narration + expect(countNarrations()).toBe(1) // same verdict 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(2) // generation bumped — a second narration + 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 delete internals.metadataIndex.healthReport }) diff --git a/tests/integration/history-repacking.test.ts b/tests/integration/history-repacking.test.ts index 2bcee038..bb07268d 100644 --- a/tests/integration/history-repacking.test.ts +++ b/tests/integration/history-repacking.test.ts @@ -16,6 +16,7 @@ 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' @@ -57,6 +58,107 @@ 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 => { + 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() diff --git a/tests/integration/hybrid-search-vfs.test.ts b/tests/integration/hybrid-search-vfs.test.ts index c881fa97..219c4c83 100644 --- a/tests/integration/hybrid-search-vfs.test.ts +++ b/tests/integration/hybrid-search-vfs.test.ts @@ -21,10 +21,16 @@ 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', - options: { basePath: testDir } + path: testDir } }) await brain.init() diff --git a/tests/integration/idle-costs-nothing.test.ts b/tests/integration/idle-costs-nothing.test.ts new file mode 100644 index 00000000..b5c386cf --- /dev/null +++ b/tests/integration/idle-costs-nothing.test.ts @@ -0,0 +1,152 @@ +/** + * @module tests/integration/idle-costs-nothing + * @description AN IDLE BRAIN DOES NO WORK. + * + * A flush used to re-persist state identical to what was already on disk — + * the provider flushes, the watermark stamps, the generation counter, the + * entity-tree stamp, roughly 28 writes — because `flush()` never asked whether + * anything had changed. + * + * The field observation that started this: a production process holding 21 + * brains printed "All indexes flushed to disk in 216–601ms" per brain every + * ~35 seconds and idled at 1.26 cores, with no writes for ten minutes. This + * engine's cadence is WRITE-DRIVEN, so that observation is NOT explained by + * the cadence and is not claimed to be fixed here — what is fixed is that such + * a call now costs nothing. Who was calling flush() remains open. + * + * The laws pinned here: + * (a) the persistence cadence arms only on a write — a brain nobody writes + * to flushes zero times, however long it is left open; + * (b) a flush on a clean brain is O(1): no provider is called, nothing is + * written, and nothing is printed; + * (c) one write earns exactly one flush's worth of work, and no more. + */ + +import { describe, it, expect, afterEach, vi } from 'vitest' +import { mkdtempSync, rmSync } from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { Brainy } from '../../src/brainy.js' +import { NounType } from '../../src/types/graphTypes.js' + +/** Wait for any in-flight background flush, then let the idle timer settle. */ +async function drainCadence(brain: Brainy): Promise { + const inner = brain as unknown as { _persistBackgroundFlight: Promise | null } + await new Promise((r) => setTimeout(r, 3_000)) + await (inner._persistBackgroundFlight ?? Promise.resolve()) + await new Promise((r) => setTimeout(r, 500)) +} + +/** How long an idle brain is watched. Longer than the 30s flush interval. */ +const IDLE_WATCH_MS = 90_000 + +describe('an idle brain costs nothing', () => { + const dirs: string[] = [] + const brains: Brainy[] = [] + + afterEach(async () => { + for (const b of brains.splice(0)) { + try { await b.close() } catch { /* already closed */ } + } + for (const d of dirs.splice(0)) { + try { rmSync(d, { recursive: true, force: true }) } catch { /* ignore */ } + } + vi.restoreAllMocks() + }) + + async function openBrain(): Promise { + const dir = mkdtempSync(join(tmpdir(), 'brainy-idle-')) + dirs.push(dir) + const brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + brains.push(brain) + await brain.init() + return brain + } + + it('flushes zero times over 90 idle seconds, and prints nothing', async () => { + const brain = await openBrain() + // One write and one flush to reach a clean, settled state — then nothing. + await brain.add({ data: 'the only write this test performs', type: NounType.Concept }) + await brain.flush() + + const logged: string[] = [] + const origLog = console.log + console.log = ((...a: unknown[]) => { logged.push(a.map(String).join(' ')) }) as typeof console.log + + // Watch the providers directly: a flush that runs calls all of them. + const storage = (brain as unknown as { storage: { flushCounts: () => Promise } }).storage + const metadataIndex = (brain as unknown as { metadataIndex: { flush: () => Promise } }).metadataIndex + const graphIndex = (brain as unknown as { graphIndex: { flush: () => Promise } }).graphIndex + const countsSpy = vi.spyOn(storage, 'flushCounts') + const metadataSpy = vi.spyOn(metadataIndex, 'flush') + const graphSpy = vi.spyOn(graphIndex, 'flush') + + try { + await new Promise((r) => setTimeout(r, IDLE_WATCH_MS)) + } finally { + console.log = origLog + } + + // (a) + (b): nothing ran, nothing was said. + expect(logged.filter((l) => /All indexes flushed to disk/.test(l))).toEqual([]) + expect(logged.filter((l) => /Flushing Brainy indexes/.test(l))).toEqual([]) + expect(countsSpy).not.toHaveBeenCalled() + expect(metadataSpy).not.toHaveBeenCalled() + expect(graphSpy).not.toHaveBeenCalled() + }, 180_000) + + it('an explicit flush over a clean brain calls no provider and prints nothing', async () => { + const brain = await openBrain() + await brain.add({ data: 'one write', type: NounType.Concept }) + await brain.flush() // this one does the work + + const storage = (brain as unknown as { storage: { flushCounts: () => Promise } }).storage + const metadataIndex = (brain as unknown as { metadataIndex: { flush: () => Promise } }).metadataIndex + const countsSpy = vi.spyOn(storage, 'flushCounts') + const metadataSpy = vi.spyOn(metadataIndex, 'flush') + const logged: string[] = [] + const origLog = console.log + console.log = ((...a: unknown[]) => { logged.push(a.map(String).join(' ')) }) as typeof console.log + try { + await brain.flush() // ...and this one has nothing to do + await brain.flush() + await brain.flush() + } finally { + console.log = origLog + } + + expect(countsSpy).not.toHaveBeenCalled() + expect(metadataSpy).not.toHaveBeenCalled() + expect(logged.filter((l) => /All indexes flushed to disk/.test(l))).toEqual([]) + }, 120_000) + + it('one write earns exactly one flush', async () => { + const brain = await openBrain() + await brain.add({ data: 'first', type: NounType.Concept }) + await brain.flush() + // Settle: the first write also kicked a BACKGROUND flush, which is not + // awaited by design. Drain it before counting, or its provider calls land + // inside this test's window and are attributed to the write below. + await drainCadence(brain) + + // Count the flushes that actually RAN. (Provider spies cannot answer this: + // the storage adapter's own count ledger is write-through, so a write calls + // flushCounts() on its own account, with no flush involved.) + const logged: string[] = [] + const origLog = console.log + console.log = ((...a: unknown[]) => { logged.push(a.map(String).join(' ')) }) as typeof console.log + const ran = () => logged.filter((l) => /All indexes flushed to disk/.test(l)).length + try { + await brain.add({ data: 'second — this is the cause', type: NounType.Concept }) + await brain.flush() + expect(ran()).toBe(1) + + // No further cause, no further work. + await brain.flush() + await brain.flush() + expect(ran()).toBe(1) + } finally { + console.log = origLog + } + }, 120_000) +}) diff --git a/tests/integration/index-skips-unvectored.test.ts b/tests/integration/index-skips-unvectored.test.ts new file mode 100644 index 00000000..c65aaa01 --- /dev/null +++ b/tests/integration/index-skips-unvectored.test.ts @@ -0,0 +1,253 @@ +/** + * @module tests/integration/index-skips-unvectored + * @description THE UNVECTORED-ROW CURE — two integration tests + * (`tests/lifecycle/biography.test.ts`'s Ch4/5/6 chapter and + * `tests/integration/clear-persistence.test.ts`'s multi-cycle test) started + * failing after a canonical-storage change made a vector-less row (the + * class-J shape: `vector: []`, e.g. the VFS root, a deferred embed not yet + * landed, or any other legitimately-unvectored canonical record) VISIBLE to + * the enumeration walk `getNounsWithPagination()` for the first time — before + * that change such rows were simply invisible to the walk. `hnswIndex.ts`'s + * `rebuild()` never guarded against that shape: it inserted every row the + * walk yielded into the live in-memory index, including ones with a length-0 + * vector, because `storage.getVectorIndexData()` derives its {level, + * connections} answer straight from the noun's OWN record — it returns + * non-null for ANY existing noun, whether or not that noun was ever actually + * indexed via `addItem()`. A vector-less node admitted into the graph could + * become the entry point (or occupy any graph position), and the very next + * real-vectored `addItem()` then ran a distance calculation against it — + * `cosineDistance` throws "Vectors must have the same dimensions" the moment + * one operand is a length-0 array. + * + * THE FIX, at two layers (`src/hnsw/hnswIndex.ts`): + * (1) FILL/REBUILD/LOAD consumers treat `vector.length === 0` as "unvectored — + * nothing to index" and skip the row (normal, not an error; one summary + * count line, never per-row spam) — `rebuild()`'s loop now checks this + * BEFORE ever creating a graph node, so an unvectored row can never + * become an index member, entry point, or dimension-setter. + * (2) THE INDEX ITSELF refuses a length-0 vector in `addItem()` / + * `updateItem()` with a typed `EmptyVectorIndexError`, loudly, instead of + * ever pinning `dimension = 0` or storing a vector-less node — so no + * future fill/rebuild/load path can silently poison the index even if it + * forgets law (1). + * + * Four legs pinned here: + * (a) `rebuild()` over a store mixing real-vectored rows and `vector: []` + * rows indexes ONLY the vectored ones — size === vectored count, + * dimension pinned to the real (non-zero) length. + * (b) `clear()` then real adds afterward never trip a dimension mismatch — + * the exact `clear-persistence.test.ts` regression shape, reproduced + * directly against the index/storage seam this module owns. + * (c) `index.addItem({ id, vector: [] })` throws `EmptyVectorIndexError` + * (and `updateItem` does too, for an existing node). + * (d) crash -> repair: the crashed generation's entities survive, the ledger + * recounts honestly, and a fresh real-vectored add afterward never trips + * a dimension mismatch against a leftover vector-less phantom. + */ +import { describe, it, expect, afterEach } from 'vitest' +import * as fs from 'node:fs' +import * as os from 'node:os' +import * as path from 'node:path' +import { Brainy } from '../../src/index.js' +import { NounType } from '../../src/types/graphTypes.js' +import { EmptyVectorIndexError } from '../../src/hnsw/hnswIndex.js' +import { abandonAsCrashed, openBrain as openKillMatrixBrain, uid, vec } from '../helpers/durabilityKillMatrix.js' + +const tmpDirs: string[] = [] +function mkTmp(): string { + const d = fs.mkdtempSync(path.join(os.tmpdir(), 'brainy-index-skips-unvectored-')) + tmpDirs.push(d) + return d +} +afterEach(() => { + for (const d of tmpDirs.splice(0)) { + try { + fs.rmSync(d, { recursive: true, force: true }) + } catch { + /* best-effort cleanup */ + } + } +}) + +/** A filesystem-backed brain with explicit vectors (no embedder needed) and + * manual persistence — mirrors `durabilityKillMatrix.ts`'s `openBrain` so + * every write in this module is explicit and provably durable. */ +function openBrain(dir: string): any { + return new Brainy({ + requireSubtype: false, + storage: { type: 'filesystem', path: dir }, + silent: true, + persistence: { policy: 'manual' } + }) +} + +describe('HNSW index skips unvectored rows', () => { + it('(a) rebuild() indexes only vectored rows: size === vectored count, dimension pinned to the real length', async () => { + const dir = mkTmp() + let brain = openBrain(dir) + await brain.init() + + // 5 real-vectored rows. + const vectoredIds: string[] = [] + for (let i = 0; i < 5; i++) { + const id = uid(`vectored-${i}`) + await brain.add({ id, data: `real entity ${i}`, type: NounType.Document, vector: vec(i) }) + vectoredIds.push(id) + } + // 3 explicit unvectored rows — the class-J "vector: []" shape, a normal, + // enumerable, countable canonical row that must never reach the index. + const unvectoredIds: string[] = [] + for (let i = 0; i < 3; i++) { + const id = uid(`unvectored-${i}`) + await brain.add({ id, data: `unvectored entity ${i}`, type: NounType.Document, vector: [] }) + unvectoredIds.push(id) + } + await brain.flush() + + // The canonical ledger already agrees before any rebuild: nouns.all + // counts every row (8 + the VFS root); vectors.all counts only the real + // ones (5) — the VFS root and the 3 explicit unvectored rows are excluded. + const ledgerBeforeReopen = await brain.storage.getCanonicalCounts() + expect(ledgerBeforeReopen.vectors.all).toBe(5) + expect(ledgerBeforeReopen.nouns.all).toBe(9) // 5 vectored + 3 unvectored + 1 VFS root + + await brain.close() + + // Reopen: open()'s index build IS hnswIndex.rebuild() run fresh from + // storage — this is the exact path that used to admit unvectored rows. + brain = openBrain(dir) + await brain.init() + + const status = await brain.getIndexStatus() + expect(status.hnswIndex.size, 'the rebuilt index must contain ONLY the 5 real-vectored rows').toBe(5) + + // Dimension is pinned to the REAL embedded length (384 via `vec()`), not + // 0 — adding a wrong-length vector must be refused naming that real + // dimension, proving no vector-less row ever set it. + const realDimension = vec(0).length + let mismatchMessage: string | undefined + try { + await brain.index.addItem({ id: uid('dimension-probe'), vector: vec(0).slice(0, realDimension - 1) }) + expect.fail('expected a dimension mismatch error') + } catch (err) { + mismatchMessage = (err as Error).message + } + expect(mismatchMessage).toContain(`expected ${realDimension}`) + + // Every unvectored row is still a normal, enumerable, readable canonical + // record — class-J semantics survive the rebuild fix untouched. + for (const id of unvectoredIds) { + const entity = await brain.get(id, { includeVectors: true }) + expect(entity, `unvectored entity ${id} must remain readable`).not.toBeNull() + expect(entity.vector).toEqual([]) + } + // A correct-dimension add succeeds cleanly against the pinned dimension. + const freshId = uid('post-reopen-fresh') + await expect(brain.add({ id: freshId, data: 'fresh', type: NounType.Document, vector: vec(50) })).resolves.toBe( + freshId + ) + + await brain.close() + }) + + it('(b) clear() then real adds afterward never trip a dimension mismatch (the clear-persistence regression shape)', async () => { + const dir = mkTmp() + let brain = openBrain(dir) + await brain.init() // the VFS root (vector: []) is the store's only row + + await brain.clear() + await brain.close() + + // Reopen over a store whose only surviving row is the recreated, + // unvectored VFS root — this is exactly the shape that used to poison + // the entry point / dimension in `clear-persistence.test.ts`. + brain = openBrain(dir) + await brain.init() + expect((await brain.getIndexStatus()).hnswIndex.size).toBe(0) + + const id1 = uid('after-clear-1') + await expect(brain.add({ id: id1, data: 'after clear 1', type: NounType.Document, vector: vec(1) })).resolves.toBe( + id1 + ) + const id2 = uid('after-clear-2') + await expect(brain.add({ id: id2, data: 'after clear 2', type: NounType.Document, vector: vec(2) })).resolves.toBe( + id2 + ) + expect((await brain.getIndexStatus()).hnswIndex.size).toBe(2) + + await brain.close() + }) + + it('(c) index.addItem/updateItem refuse a length-0 vector with EmptyVectorIndexError', async () => { + const dir = mkTmp() + const brain = openBrain(dir) + await brain.init() + + await expect(brain.index.addItem({ id: uid('empty-add'), vector: [] })).rejects.toThrow(EmptyVectorIndexError) + + // updateItem on an EXISTING (real-vectored) node must refuse the same way. + const existingId = uid('existing-for-update') + await brain.add({ id: existingId, data: 'existing', type: NounType.Document, vector: vec(9) }) + await expect(brain.index.updateItem({ id: existingId, vector: [] })).rejects.toThrow(EmptyVectorIndexError) + + // The index was never disturbed by either refused call. + expect((await brain.getIndexStatus()).hnswIndex.size).toBe(1) + + await brain.close() + }) + + it('(d) crash -> repair: the crashed generation survives, the ledger recounts honestly, and a fresh add afterward never trips a dimension mismatch', async () => { + const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'brainy-index-skips-unvectored-crash-')) + try { + let brain = await openKillMatrixBrain(dir, { logAuthority: 'adopt' }) + + // Baseline: real-vectored entities, durably flushed. + const baselineIds: string[] = [] + for (let i = 0; i < 5; i++) { + const id = uid(`baseline-${i}`) + await brain.add({ id, data: `baseline entity ${i}`, type: NounType.Document, vector: vec(i) }) + baselineIds.push(id) + } + await brain.flush() + + // Crash window: at-ack writes that are never flushed before the crash. + const crashedIds: string[] = [] + for (let i = 0; i < 4; i++) { + const id = uid(`crashed-${i}`) + await brain.add({ id, data: `crash-window entity ${i}`, type: NounType.Document, vector: vec(100 + i) }) + crashedIds.push(id) + } + await abandonAsCrashed(brain) + + // Reopen — logAuthority: 'adopt' replays the at-ack log for the crash window. + brain = await openKillMatrixBrain(dir, { logAuthority: 'adopt' }) + for (const id of [...baselineIds, ...crashedIds]) { + expect(await brain.get(id), `entity ${id} must survive the crash`).not.toBeNull() + } + + // Repair — must not disturb any entity, and must recount the ledger honestly. + const report = await brain.repairIndex() + expect(report.families.length).toBeGreaterThan(0) + for (const id of [...baselineIds, ...crashedIds]) { + expect(await brain.get(id), `entity ${id} must survive repair`).not.toBeNull() + } + + const ledger = await brain.storage.getCanonicalCounts() + expect(ledger.suspect).toBe(false) + expect(ledger.vectors.all).toBe(baselineIds.length + crashedIds.length) + + // Second life: a fresh real-vectored add must never trip a dimension + // mismatch against a vector-less phantom left in the index — the exact + // mechanism `clear-persistence.test.ts` and the biography lane hit. + const secondLifeId = uid('second-life') + await expect( + brain.add({ id: secondLifeId, data: 'second life entity', type: NounType.Document, vector: vec(200) }) + ).resolves.toBe(secondLifeId) + expect(await brain.get(secondLifeId)).not.toBeNull() + + await brain.close() + } finally { + fs.rmSync(dir, { recursive: true, force: true }) + } + }) +}) diff --git a/tests/integration/ledger-derivation-identity.test.ts b/tests/integration/ledger-derivation-identity.test.ts index cb19af4a..7d09e893 100644 --- a/tests/integration/ledger-derivation-identity.test.ts +++ b/tests/integration/ledger-derivation-identity.test.ts @@ -11,14 +11,22 @@ * (1) IDENTITY, NOT CONTAINER — the derivation counts one entity per * metadata content leg (`metadata.json` or `.json.gz`), the same test * `pruneOrphanedEntities()` uses, so the two agree by construction. - * (2) THE STAMP NAMES SUSPECT COUNTS LOUDLY, AT O(1) — a counts.json that - * carries the ALL scalars but no `allCountsDerivedBy: 'identity-record'` - * stamp predates this fix; loading it marks `suspect = true` from a - * single field read alone, never a directory walk, and warns exactly - * once naming the cause. - * (3) THE SANCTIONED RECOUNT CLEARS IT — `repairIndex()` prunes the orphaned - * containers, recounts from the canonical metadata.json walk, and - * re-stamps — suspect clears and the ALL scalar is exact again. + * (2) THE STAMP NAMES SUSPECT COUNTS LOUDLY, AND THE OPEN NEVER WALKS — a + * counts.json that carries the ALL scalars but no + * `allCountsDerivedBy: 'identity-record'` stamp predates this fix; + * loading it marks `suspect = true` from a single field read alone and + * warns exactly once naming the cause. The open itself never pays a + * directory walk. + * (2b) AND IT HEALS ITSELF. The ledger used to stay wrong for the life of the + * store, waiting for an operator to run `repairIndex()` — and a + * downstream index heal subtracted against the inflated denominator and + * reported work that did not exist. An honest derivation now runs in the + * BACKGROUND after the open (never blocking it, observable via + * `whenCountLedgerSettled()`), and refuses to stamp a number it derived + * while writes were landing. + * (3) THE SANCTIONED RECOUNT ALSO CLEARS IT — `repairIndex()` prunes the + * orphaned containers, recounts from the canonical metadata.json walk, + * and re-stamps — the ALL scalar is exact and the containers are gone. * (4) A FRESH STORE IS NEVER SUSPECT — the one-time derivation for a store * with no counts.json stamps as it writes, so a brand-new store never * carries the legacy signature. @@ -115,29 +123,43 @@ describe('ledger derivation identity — the ALL scalar is the identity-record p delete raw.allCountsDerivedBy fs.writeFileSync(countsPath(dir), JSON.stringify(raw, null, 2)) - const warnSpy = vi.spyOn(prodLog, 'warn') - // The two derivation walks live on FileSystemStorage's prototype — - // spying here (rather than on fs.promises.readdir globally) isolates - // THIS code path's behavior from unrelated walks elsewhere in the open - // sequence (a separate, pre-existing engine's own O(store) cost — not - // this fix's concern, and not something this pin should be sensitive - // to). Neither derivation method may run: the stamp check is a field - // read on the already-parsed counts.json, nothing more. - const scanEntitiesSpy = vi.spyOn(FileSystemStorage.prototype as any, 'scanCanonicalEntities') - const scanVectoredSpy = vi.spyOn(FileSystemStorage.prototype as any, 'scanVectoredNounCount') + const narrateSpy = vi.spyOn(prodLog, 'narrate') + // The derivation walks live on FileSystemStorage's prototype. Slow them + // deliberately: the OPEN must not wait for them, and on a two-row store a + // real walk finishes too fast to tell "not awaited" from "instant". + const proto = FileSystemStorage.prototype as any + const realScanEntities = proto.scanCanonicalEntities + let scanEntitiesCalls = 0 + proto.scanCanonicalEntities = async function slow(this: any, ...args: any[]) { + scanEntitiesCalls++ + await new Promise((r) => setTimeout(r, 1_200)) + return realScanEntities.apply(this, args) + } + try { + const openStarted = Date.now() + brain = await open() + const openMs = Date.now() - openStarted - brain = await open() + // THE OPEN DID NOT WALK: two slowed walks would have added 2.4s to it. + expect(openMs).toBeLessThan(2_000) - const ledger = await brain.storage.getCanonicalCounts() - expect(ledger.suspect).toBe(true) + // The stamp check itself is an O(1) field read, and it names the cause. + const atOpen = await brain.storage.getCanonicalCounts() + expect(atOpen.suspect).toBe(true) + const stampWarnings = narrateSpy.mock.calls.filter( + ([msg]: any[]) => String(msg).includes('legacy') && String(msg).includes('container rule') + ) + expect(stampWarnings.length).toBe(1) // exactly one, loud - const stampWarnings = warnSpy.mock.calls.filter( - ([msg]) => String(msg).includes('legacy') && String(msg).includes('container rule') - ) - expect(stampWarnings.length).toBe(1) // exactly one, loud - - expect(scanEntitiesSpy).not.toHaveBeenCalled() // O(1) field read only, no re-derivation walk - expect(scanVectoredSpy).not.toHaveBeenCalled() + // ...and the honest derivation is already running behind the open. + await brain.storage.whenCountLedgerSettled() + expect(scanEntitiesCalls).toBeGreaterThan(0) + const healed = await brain.storage.getCanonicalCounts() + expect(healed.suspect).toBe(false) + expect(healed.nouns.all).toBe(raw.totalNounCountAll) + } finally { + proto.scanCanonicalEntities = realScanEntities + } await brain.close() }) @@ -163,7 +185,14 @@ describe('ledger derivation identity — the ALL scalar is the identity-record p fs.writeFileSync(countsPath(dir), JSON.stringify(raw, null, 2)) brain = await open() - expect((await brain.storage.getCanonicalCounts()).suspect).toBe(true) // named suspect at load + // Named suspect at load, then healed in the background WITHOUT the + // operator asking — the inflated container count is corrected to the + // identity-record population, though the orphaned containers themselves + // are still on disk (only repairIndex() removes those). + await brain.storage.whenCountLedgerSettled() + let healed = await brain.storage.getCanonicalCounts() + expect(healed.suspect).toBe(false) + expect(healed.nouns.all).toBe(realTotal) await brain.repairIndex() diff --git a/tests/integration/open-does-not-wait-for-a-rebuilding-provider.test.ts b/tests/integration/open-does-not-wait-for-a-rebuilding-provider.test.ts new file mode 100644 index 00000000..a46ad6a5 --- /dev/null +++ b/tests/integration/open-does-not-wait-for-a-rebuilding-provider.test.ts @@ -0,0 +1,192 @@ +/** + * @module tests/integration/open-does-not-wait-for-a-rebuilding-provider + * @description OPEN DOES NOT WAIT FOR A PROVIDER THAT IS REBUILDING ITSELF. + * + * Measured on a production store: a metadata provider that had to rebuild made + * `init()` pay the ENTIRE rebuild on the foreground — 641 seconds — with every + * other family idle behind it, because a provider reporting `serving: false` + * because it is BUSY BUILDING and one reporting `serving: false` because it is + * BROKEN were indistinguishable, and both were answered the same way: call + * `rebuild()`, and wait. + * + * The law: a provider that reports `rebuildInProgress()` owns its own rebuild. + * `init()` returns; every other family serves; THAT family's doors refuse by + * name, carrying the provider's own progress; and the doors open by themselves + * when the provider reports serving. Nothing is ever served empty. + */ + +import { describe, it, expect, afterEach } from 'vitest' +import { mkdtempSync, rmSync } from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { Brainy } from '../../src/brainy.js' +import { NounType } from '../../src/types/graphTypes.js' +import type { ProviderRebuildProgress } from '../../src/utils/indexReadiness.js' + +/** How long the stub provider claims to be rebuilding. */ +const REBUILD_MS = 6_000 + +describe('a provider rebuilding itself never blocks open', () => { + const dirs: string[] = [] + const brains: Brainy[] = [] + + afterEach(async () => { + for (const b of brains.splice(0)) { + try { await b.close() } catch { /* already closed */ } + } + for (const d of dirs.splice(0)) { + try { rmSync(d, { recursive: true, force: true }) } catch { /* ignore */ } + } + }) + + it('init() returns in milliseconds, the family refuses by name, then answers', async () => { + const dir = mkdtempSync(join(tmpdir(), 'brainy-rebuilding-provider-')) + dirs.push(dir) + + // Seed a store so the open has something to (not) rebuild. + const seed = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await seed.init() + await seed.add({ data: 'a row with a plain field', type: NounType.Concept, metadata: { kind: 'report' } }) + await seed.flush() + await seed.close() + + const brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + brains.push(brain) + + // Dress the metadata index as a provider that is rebuilding ITSELF: not + // serving, and honest about why. `init()` wires the real index first, so + // the hooks are installed on the instance as soon as it exists — the gate + // reads them by feature detection, exactly as it would a native provider's. + const rebuildStartedAt = Date.now() + const stillRebuilding = () => Date.now() - rebuildStartedAt < REBUILD_MS + let rebuildCalls = 0 + + const inner = brain as unknown as { + metadataIndex: Record + setupIndex?: unknown + } + // Install on the prototype-free instance right after construction by + // patching the property the moment init() assigns it. + const install = (target: Record) => { + const realRebuild = target.rebuild as () => Promise + target.rebuildInProgress = (): ProviderRebuildProgress | null => + stillRebuilding() + ? { phase: 'metadata shadow build', done: 4_096, total: 14_056, startedAt: rebuildStartedAt } + : null + target.healthReport = () => ({ + provider: 'metadata', + healthy: !stillRebuilding(), + serving: !stillRebuilding(), + generation: 1, + invariants: [], + unledgered: [] + }) + target.rebuild = async () => { + rebuildCalls++ + return realRebuild.call(target) + } + } + + // init() constructs the metadata index; patch as soon as it exists, before + // the gate consults it. A microtask hop after the index is assigned is + // enough because the gate runs later in the same init. + const initPromise = (async () => { + const originalEnsure = (brain as unknown as { setupIndex?: () => unknown }).setupIndex + void originalEnsure + return brain.init() + })() + // Patch on the first tick the index exists. + const patcher = setInterval(() => { + if (inner.metadataIndex && !inner.metadataIndex.rebuildInProgress) { + install(inner.metadataIndex) + } + }, 1) + const startedAt = Date.now() + try { + await initPromise + } finally { + clearInterval(patcher) + } + const openMs = Date.now() - startedAt + + // If the patch did not land before the gate ran, this test proves nothing — + // say so loudly rather than passing vacuously. + expect( + typeof inner.metadataIndex.rebuildInProgress, + 'the stub provider was never installed — the test is vacuous' + ).toBe('function') + + // 1. The open did not wait out the rebuild. + expect(openMs).toBeLessThan(REBUILD_MS) + // 2. And brainy did not start a rebuild of its own on top of the provider's. + expect(rebuildCalls).toBe(0) + + // 3. The family's door refuses BY NAME, carrying the provider's progress. + let refusal: Error | null = null + try { + await brain.find({ where: { kind: 'report' } } as never) + } catch (err) { + refusal = err as Error + } + expect(refusal, 'a not-serving metadata family must refuse, never serve empty').not.toBeNull() + expect(refusal!.message).toMatch(/metadata shadow build/i) + expect(refusal!.message).toMatch(/4,096\/14,056/) + expect(refusal!.message).toMatch(/no action is needed/i) + + // 4. Other families keep serving — the brain is open. + const all = await brain.getNouns?.({ pagination: { limit: 1 } } as never) + expect(all ?? true).toBeTruthy() + + // 5. When the provider reports itself serving, the door opens by itself. + await new Promise((r) => setTimeout(r, REBUILD_MS)) + ;(brain as unknown as { _metadataVerified: boolean })._metadataVerified = false + await expect(brain.find({ where: { kind: 'report' } } as never)).resolves.toBeDefined() + }, 180_000) + + it('a rebuilding provider reporting 0 entries is not a CRITICAL, and gets no second rebuild', async () => { + const dir = mkdtempSync(join(tmpdir(), 'brainy-rebuilding-critical-')) + dirs.push(dir) + const seed = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await seed.init() + await seed.add({ data: 'a stored entity', type: NounType.Concept }) + await seed.flush() + await seed.close() + + const brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + brains.push(brain) + + let rebuildCalls = 0 + const errors: string[] = [] + const origError = console.error + console.error = ((...a: unknown[]) => { errors.push(a.map(String).join(' ')) }) as typeof console.error + + const inner = brain as unknown as { metadataIndex: Record } + const patcher = setInterval(() => { + if (inner.metadataIndex && !inner.metadataIndex.rebuildInProgress) { + const target = inner.metadataIndex + target.rebuildInProgress = () => ({ phase: 'online metadata rebuild', startedAt: Date.now() }) + target.healthReport = () => ({ + provider: 'metadata', healthy: false, serving: false, + generation: 1, invariants: [], unledgered: [] + }) + // The shape the native engine now has: the index reports NOTHING while + // its rebuild runs online behind refusing doors. + target.getStats = async () => ({ totalEntries: 0 }) + target.rebuild = async () => { rebuildCalls++ } + } + }, 1) + try { + await brain.init() + } finally { + clearInterval(patcher) + console.error = origError + } + + expect( + typeof inner.metadataIndex.rebuildInProgress, + 'the stub provider was never installed — the test is vacuous' + ).toBe('function') + expect(errors.filter((l) => /CRITICAL: Metadata index has 0 entries/.test(l))).toEqual([]) + expect(rebuildCalls).toBe(0) + }, 180_000) +}) diff --git a/tests/integration/open-narration.test.ts b/tests/integration/open-narration.test.ts new file mode 100644 index 00000000..95aba9f1 --- /dev/null +++ b/tests/integration/open-narration.test.ts @@ -0,0 +1,114 @@ +/** + * @module tests/integration/open-narration + * @description THE OPEN IS NEVER SILENT. + * + * A production service opened a 16 GB store and logged nothing at all for + * three minutes before its first line of work. Two defects made that possible + * and both are pinned here: + * + * 1. The phase breakdown was written to `prodLog.warn`, which every + * environment that looks like production clamps away. The narration + * channel (`prodLog.narrate`) is always visible, like `error`. + * 2. Nothing spoke DURING a phase — only after the whole open finished, if + * at all. A heartbeat now names the phase currently running and its + * elapsed wall while the open is still happening. + */ + +import { describe, it, expect, beforeEach, afterEach } from 'vitest' +import { mkdtempSync, rmSync } from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { Brainy } from '../../src/brainy.js' +import { NounType } from '../../src/types/graphTypes.js' +import { FileSystemStorage } from '../../src/storage/adapters/fileSystemStorage.js' +import { prodLog, configureLogger, LogLevel } from '../../src/utils/logger.js' + +function makeTempDir(): string { + return mkdtempSync(join(tmpdir(), 'brainy-open-narration-')) +} + +/** Capture console.warn lines emitted while `fn` runs. */ +async function captureWarn(fn: () => Promise): Promise<{ result: T; lines: string[] }> { + const lines: string[] = [] + const orig = console.warn + console.warn = ((...args: unknown[]) => { + lines.push(args.map((a) => String(a)).join(' ')) + }) as typeof console.warn + try { + return { result: await fn(), lines } + } finally { + console.warn = orig + } +} + +describe('open narration', () => { + let dir: string + let brain: Brainy | null = null + + beforeEach(() => { dir = makeTempDir() }) + + afterEach(async () => { + if (brain) { + try { await brain.close() } catch { /* already closed */ } + brain = null + } + try { rmSync(dir, { recursive: true, force: true }) } catch { /* ignore */ } + }) + + it('narrate() survives the production log clamp that silences warn()', async () => { + // Exactly what isProductionEnvironment() does to the logger: level ERROR. + configureLogger({ level: LogLevel.ERROR }) + try { + const { lines } = await captureWarn(async () => { + prodLog.warn('[Brainy] this line is chatter and may be clamped') + prodLog.narrate('[Brainy] this line is why the database is slow') + }) + expect(lines.some((l) => /why the database is slow/.test(l))).toBe(true) + expect(lines.some((l) => /chatter/.test(l))).toBe(false) + } finally { + configureLogger({ level: LogLevel.INFO }) + } + }) + + it('names a slow phase as it ends, and heartbeats while it is still running', async () => { + // Seed a store, then reopen it with a deliberately slow storage init so + // the first phase crosses both the heartbeat and the narrate thresholds. + brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await brain.init() + await brain.add({ data: 'seed entity', type: NounType.Concept }) + await brain.flush() + await brain.close() + brain = null + + const realInit = FileSystemStorage.prototype.init + FileSystemStorage.prototype.init = async function slowInit(this: FileSystemStorage) { + await new Promise((r) => setTimeout(r, 6_500)) + return realInit.call(this) + } + // Clamped to ERROR for the whole open: the narration must survive it. + configureLogger({ level: LogLevel.ERROR }) + try { + const { result, lines } = await captureWarn(async () => { + const next = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await next.init() + return next + }) + brain = result + + // The heartbeat spoke DURING the phase, naming the phase and its cause. + const heartbeats = lines.filter((l) => /open: still in phase 1\/5 "storage-init"/.test(l)) + expect(heartbeats.length).toBeGreaterThanOrEqual(1) + expect(heartbeats[0]).toMatch(/loading its count ledger/) + + // And the phase named its own wall as it ended. + const ended = lines.filter((l) => /open: phase 1\/5 "storage-init" finished in \d+ms/.test(l)) + expect(ended.length).toBe(1) + + // The whole-open breakdown is on the same always-visible channel. + expect(lines.some((l) => /slow open: \d+ms total \(.*storage-init=/.test(l))).toBe(true) + } finally { + FileSystemStorage.prototype.init = realInit + configureLogger({ level: LogLevel.INFO }) + } + }, 120_000) +}) diff --git a/tests/integration/repair-narration.test.ts b/tests/integration/repair-narration.test.ts new file mode 100644 index 00000000..1fbe15e4 --- /dev/null +++ b/tests/integration/repair-narration.test.ts @@ -0,0 +1,119 @@ +/** + * @module tests/integration/repair-narration + * @description A REPAIR NARRATES ITSELF, AND ITS RECEIPT SAYS WHERE THE TIME + * WENT. + * + * On a production store (14,647 nouns / 73,070 verbs) a `repairIndex()` ran + * for more than thirty minutes at roughly a full core with ZERO log lines + * between its start and its end, while the read doors kept serving. The + * operator could tell it was alive only from `top`, and could not tell which + * of its single-threaded walks it was inside. The law pinned here: + * + * - every phase announces itself BEFORE it works, naming what it is about + * to walk; + * - a heartbeat names the phase still running, at a bounded cadence, for as + * long as it runs; + * - every phase reports its own wall, and that wall is carried in the typed + * receipt (`RepairFamilyReport.durationMs`) — not only in a log line. + * + * All of it on the narration channel, which production's log clamp cannot + * silence (see tests/integration/open-narration.test.ts). + */ + +import { describe, it, expect, afterEach, vi } from 'vitest' +import { mkdtempSync, rmSync } from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { Brainy } from '../../src/brainy.js' +import { NounType } from '../../src/types/graphTypes.js' +import { FileSystemStorage } from '../../src/storage/adapters/fileSystemStorage.js' +import { prodLog, configureLogger, LogLevel } from '../../src/utils/logger.js' + +describe('repairIndex narration', () => { + const dirs: string[] = [] + const brains: Brainy[] = [] + + afterEach(async () => { + for (const b of brains.splice(0)) { + try { await b.close() } catch { /* already closed */ } + } + for (const d of dirs.splice(0)) { + try { rmSync(d, { recursive: true, force: true }) } catch { /* ignore */ } + } + configureLogger({ level: LogLevel.INFO }) + }) + + async function seededBrain(): Promise { + const dir = mkdtempSync(join(tmpdir(), 'brainy-repair-narration-')) + dirs.push(dir) + const brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + brains.push(brain) + await brain.init() + for (let i = 0; i < 5; i++) { + await brain.add({ data: `repair subject ${i}`, type: NounType.Concept }) + } + await brain.flush() + return brain + } + + it('announces every phase, reports its wall, and carries that wall in the receipt', async () => { + const brain = await seededBrain() + const narrateSpy = vi.spyOn(prodLog, 'narrate') + + const report = await brain.repairIndex() + + const lines = narrateSpy.mock.calls.map(([m]) => String(m)) + + // Every family that ran has BOTH a start line and a finish line naming it. + for (const family of report.families) { + const started = lines.filter((l) => l.includes(`"${family.family}" started —`)) + const finished = lines.filter((l) => + new RegExp(`"${family.family}" finished in \\d+ms`).test(l) + ) + expect(finished.length, `no finish line for ${family.family}`).toBeGreaterThanOrEqual(1) + // A skipped family may be recorded without a start line only if it never + // began; every family that began must have announced itself. + if (family.checked) { + expect(started.length, `no start line for ${family.family}`).toBeGreaterThanOrEqual(1) + } + // THE RECEIPT CARRIES THE WALL — not only the log. + expect(typeof family.durationMs, `${family.family} has no durationMs`).toBe('number') + expect(family.durationMs).toBeGreaterThanOrEqual(0) + } + + // The closing line accounts for the whole repair, per family. + const closing = lines.filter((l) => /repairIndex complete in \d+ms/.test(l)) + expect(closing.length).toBe(1) + expect(closing[0]).toMatch(/@\d+ms/) + }, 180_000) + + it('heartbeats while a single phase is still walking', async () => { + const brain = await seededBrain() + + // Make one phase long enough to cross the heartbeat cadence, exactly as a + // multi-minute canonical walk does on a real store. + const proto = FileSystemStorage.prototype as unknown as Record< + string, + (...args: unknown[]) => Promise + > + const realPrune = proto.pruneOrphanedEntities + proto.pruneOrphanedEntities = async function slow(this: unknown, ...args: unknown[]) { + await new Promise((r) => setTimeout(r, 6_500)) + return realPrune.apply(this, args) + } + // Clamped as production clamps it: the narration must survive. + configureLogger({ level: LogLevel.ERROR }) + const narrateSpy = vi.spyOn(prodLog, 'narrate') + try { + await brain.repairIndex() + } finally { + proto.pruneOrphanedEntities = realPrune + } + + const beats = narrateSpy.mock.calls + .map(([m]) => String(m)) + .filter((l) => /repairIndex: still in "orphaned-containers" after \d+s/.test(l)) + expect(beats.length).toBeGreaterThanOrEqual(1) + expect(beats[0]).toMatch(/ghost\/scar containers/) + }, 180_000) +}) diff --git a/tests/integration/vfs-root-sweep-once.test.ts b/tests/integration/vfs-root-sweep-once.test.ts new file mode 100644 index 00000000..cac59b70 --- /dev/null +++ b/tests/integration/vfs-root-sweep-once.test.ts @@ -0,0 +1,133 @@ +/** + * @module tests/integration/vfs-root-sweep-once + * @description THE OLD-ROOT SWEEP RUNS ONCE PER STORE, NOT ONCE PER OPEN. + * + * The VFS bootstrap ran a filtered `find()` over the whole store on EVERY + * open, hunting for root directories created before the fixed root id existed + * — duplicates a store has either always had or never will. MEASURED on a + * 14,056-noun / 72,679-verb store: the phase it dominates cost 43–53 SECONDS + * of every open, warm reopens included. + * + * The law: a migration sweep is caused by the store's state, not by the clock + * or the open count. It runs behind the doors, records that it ran, and a + * store carrying that record never sweeps again. + */ + +import { describe, it, expect, afterEach, vi } from 'vitest' +import { mkdtempSync, rmSync, existsSync } from 'node:fs' +import { tmpdir } from 'node:os' +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[] = [] + const brains: Brainy[] = [] + + afterEach(async () => { + for (const b of brains.splice(0)) { + try { await b.close() } catch { /* already closed */ } + } + for (const d of dirs.splice(0)) { + try { rmSync(d, { recursive: true, force: true }) } catch { /* ignore */ } + } + vi.restoreAllMocks() + }) + + async function open(dir: string): Promise { + const brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + brains.push(brain) + await brain.init() + return brain + } + + it('sweeps on the first open, records it, and never sweeps again', async () => { + const dir = mkdtempSync(join(tmpdir(), 'brainy-root-sweep-')) + dirs.push(dir) + + const sweepSpy = vi.spyOn( + VirtualFileSystem.prototype as unknown as { cleanupOldRoots: () => Promise }, + 'cleanupOldRoots' + ) + + const first = await open(dir) + await (first.vfs as unknown as { whenRootSweepSettled: () => Promise }).whenRootSweepSettled() + expect(sweepSpy).toHaveBeenCalledTimes(1) + // The record is durable engine plumbing under _system/, like every other marker. + expect( + existsSync(join(dir, '_system', 'vfs-root-sweep.json')) || + existsSync(join(dir, '_system', 'vfs-root-sweep.json.gz')) + ).toBe(true) + + await first.add({ data: 'a row so the store is not trivially empty', type: NounType.Concept }) + await first.flush() + await first.close() + brains.splice(brains.indexOf(first), 1) + + sweepSpy.mockClear() + const second = await open(dir) + await (second.vfs as unknown as { whenRootSweepSettled: () => Promise }).whenRootSweepSettled() + expect(sweepSpy).not.toHaveBeenCalled() + + await second.close() + brains.splice(brains.indexOf(second), 1) + + // ...and a third open, to prove it is the record and not a one-off. + sweepSpy.mockClear() + const third = await open(dir) + await (third.vfs as unknown as { whenRootSweepSettled: () => Promise }).whenRootSweepSettled() + 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 }).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) + + const proto = VirtualFileSystem.prototype as unknown as Record< + string, + (...args: unknown[]) => Promise + > + const real = proto.cleanupOldRoots + proto.cleanupOldRoots = async function slow(this: unknown, ...args: unknown[]) { + await new Promise((r) => setTimeout(r, 4_000)) + return real.apply(this, args) + } + try { + const startedAt = Date.now() + const brain = await open(dir) + const openMs = Date.now() - startedAt + expect(openMs).toBeLessThan(3_000) + await (brain.vfs as unknown as { whenRootSweepSettled: () => Promise }).whenRootSweepSettled() + } finally { + proto.cleanupOldRoots = real + } + }, 180_000) +}) diff --git a/tests/integration/vfs-root-zero-norm.test.ts b/tests/integration/vfs-root-zero-norm.test.ts index 00260eb4..577ae7ee 100644 --- a/tests/integration/vfs-root-zero-norm.test.ts +++ b/tests/integration/vfs-root-zero-norm.test.ts @@ -18,9 +18,16 @@ * harness reproduces exactly what a pre-fix store looked like on disk) * is rewritten to `[]` on the next `init()`, the ledger is decremented * through the sanctioned path, and a second `init()` is a no-op. - * (c) THE BELT at the live provider-write seam: an entity added with an - * EXPLICIT all-zero vector (any dimension) still lands its canonical - * write, but the vector-index insert is refused loudly. + * (c) THE CANONICAL-WRITE NORMALIZATION (Leg A of the follow-up + * zero-norm/unvector-door fix): an entity added with an EXPLICIT + * all-zero vector (any dimension) is normalized to the "unvectored" + * `[]` shape BEFORE the canonical write, the ledger flag, and the index + * ops ever see it — the canonical write still succeeds, loudly, and the + * vector-index insert never happens (nothing to index). Supersedes the + * original "canonical keeps the zero vector, only the index refuses" + * shape: a downstream engine's health-report gate reads the canonical + * ledger directly, so leaving a zero-norm vector on the canonical side + * re-opened the exact false-attractor risk this whole fix closes. * (d) the migrated root never surfaces in `find()` results (it was already * hidden behind `visibility: 'system'` — this pin holds regardless). */ @@ -142,7 +149,7 @@ describe('VFS root zero-norm cure', () => { await brain.close() }) - it('(c) the live-write belt: an entity added with an explicit all-zero vector lands its canonical write, but the vector-index insert is refused loudly', async () => { + it('(c) canonical-write normalization: an entity added with an explicit all-zero vector persists UNVECTORED ([]), loudly, and never reaches the vector index', async () => { const dir = mkTmp() const brain = openBrain(dir) await brain.init() @@ -150,20 +157,26 @@ describe('VFS root zero-norm cure', () => { const warnSpy = vi.spyOn(prodLog, 'warn') const sizeBefore = (await brain.getIndexStatus()).hnswIndex.size + const ledgerBefore = await brain.storage.getCanonicalCounts() const zeroVector = new Array(384).fill(0) const id = await brain.add({ data: 'poisoned entity', type: NounType.Document, vector: zeroVector }) - // The canonical write succeeded — the entity is fully readable with its - // (real, all-zero) vector intact. + // The canonical write succeeded — but the zero-norm vector was + // normalized to the "unvectored" `[]` shape BEFORE it was persisted + // (Leg A: a zero-norm vector is not a vector — it never crosses an + // engine boundary, canonical side included). const entity = await brain.get(id, { includeVectors: true }) expect(entity).not.toBeNull() - expect(entity.vector).toEqual(zeroVector) + expect(entity.vector).toEqual([]) - // The vector-index insert was skipped — the index size never moved. + // Nothing to index — the vector-index size never moved, and the + // vectored-noun ledger never counted this row. const sizeAfter = (await brain.getIndexStatus()).hnswIndex.size expect(sizeAfter).toBe(sizeBefore) + const ledgerAfter = await brain.storage.getCanonicalCounts() + expect(ledgerAfter.vectors.all).toBe(ledgerBefore.vectors.all) - // The refusal was LOUD and named the entity. + // The normalization was LOUD and named the entity. const loudCall = warnSpy.mock.calls.find( (call) => typeof call[0] === 'string' && call[0].includes(id) && call[0].toLowerCase().includes('zero-norm') ) diff --git a/tests/integration/writer-lock-clean-close.test.ts b/tests/integration/writer-lock-clean-close.test.ts new file mode 100644 index 00000000..7d9c59d6 --- /dev/null +++ b/tests/integration/writer-lock-clean-close.test.ts @@ -0,0 +1,250 @@ +/** + * @module tests/integration/writer-lock-clean-close + * @description THE CLEAN-CLOSE CONTRACT for the writer lock. + * + * A production restart made this lane necessary: a service stopped with exit + * code 0, having awaited `close()` on every pooled brain, and its next boot + * announced `[brainy] Overwriting stale writer lock … appears dead` for every + * store it owned. "The pid is gone" is equally true of an orderly restart and + * of a crash, so the message could not tell an operator which one they had. + * + * The contract pinned here: + * 1. A completed close leaves NO lock file and DOES leave a clean-close + * record; the next open says nothing about staleness. + * 2. The next lock claim CONSUMES that record — it may never outlive the + * lock generation it describes, or a later crash would read as clean. + * 3. A close whose durable steps FAIL still releases the lock (and still + * rethrows the failure). + * 4. A killed process (SIGKILL, no close at all) leaves the lock behind with + * NO record, and the next open says exactly that — crash, recovery ahead. + * 5. A host application with its own SIGTERM handler is never force-exited + * out from under its own shutdown by Brainy's handler. + */ + +import { describe, it, expect, beforeEach, afterEach } from 'vitest' +import { mkdtempSync, rmSync, existsSync, readFileSync, writeFileSync } from 'node:fs' +import { spawn } from 'node:child_process' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { Brainy } from '../../src/brainy.js' +import { NounType } from '../../src/types/graphTypes.js' + +const REPO_ROOT = process.cwd() +const TSX = join(REPO_ROOT, 'node_modules', '.bin', 'tsx') + +function makeTempDir(): string { + return mkdtempSync(join(tmpdir(), 'brainy-clean-close-')) +} + +/** + * Write a child script to disk and start it under tsx. A file (not `tsx -e`) + * because the eval form compiles to CommonJS, which has no top-level await. + * The script imports Brainy by ABSOLUTE path, so its own dependency + * resolution still happens from inside the repository. + */ +function startChild(dir: string, body: string): ReturnType { + const scriptPath = join(dir, 'child-process.mts') + writeFileSync(scriptPath, body) + // `detached` puts the child in its own process GROUP: tsx runs the script in + // a grandchild process, and only a group-wide signal reaches the process + // that actually holds the writer lock. + return spawn(TSX, [scriptPath], { + cwd: REPO_ROOT, + stdio: ['ignore', 'pipe', 'pipe'], + detached: true + }) +} + +/** Capture every console.warn/error line emitted while `fn` runs. */ +async function captureConsole(fn: () => Promise): Promise<{ result: T; lines: string[] }> { + const lines: string[] = [] + const origWarn = console.warn + const origError = console.error + const sink = (...args: unknown[]) => { + lines.push(args.map((a) => String(a)).join(' ')) + } + console.warn = sink as typeof console.warn + console.error = sink as typeof console.error + try { + const result = await fn() + return { result, lines } + } finally { + console.warn = origWarn + console.error = origError + } +} + +/** + * Run a child process that opens `dir`, writes one row, prints `READY`, and + * then waits forever. Resolves with the child once READY is seen. + */ +function spawnHoldingChild(dir: string): Promise<{ + child: ReturnType + output: () => string +}> { + const script = ` + import { Brainy } from ${JSON.stringify(join(REPO_ROOT, 'src', 'brainy.ts'))} + const brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: ${JSON.stringify(dir)} } }) + await brain.init() + await brain.add({ data: 'row from the child', type: 'concept' }) + await brain.flush() + console.log('READY') + setInterval(() => {}, 1000) + ` + const child = startChild(dir, script) + let out = '' + child.stdout.on('data', (d) => { out += String(d) }) + child.stderr.on('data', (d) => { out += String(d) }) + return new Promise((resolvePromise, rejectPromise) => { + const timer = setTimeout(() => rejectPromise(new Error(`child never became READY:\n${out}`)), 120_000) + child.stdout.on('data', () => { + if (out.includes('READY')) { + clearTimeout(timer) + resolvePromise({ child, output: () => out }) + } + }) + child.on('exit', (code) => { + clearTimeout(timer) + if (!out.includes('READY')) rejectPromise(new Error(`child exited ${code} before READY:\n${out}`)) + }) + }) +} + +describe('writer lock — the clean-close contract', () => { + let dir: string + let brain: Brainy | null = null + + beforeEach(() => { dir = makeTempDir() }) + + afterEach(async () => { + if (brain) { + try { await brain.close() } catch { /* may already be closed */ } + brain = null + } + try { rmSync(dir, { recursive: true, force: true }) } catch { /* ignore */ } + }) + + const lockPath = () => join(dir, 'locks', '_writer.lock') + const recordPath = () => join(dir, 'locks', '_writer.close') + + it('a completed close leaves no lock, leaves a record, and the reopen is silent about staleness', async () => { + brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await brain.init() + expect(existsSync(lockPath())).toBe(true) + + await brain.add({ data: 'seed entity', type: NounType.Concept }) + await brain.flush() + await brain.close() + brain = null + + // 1. The lock is gone and the release is RECORDED. + expect(existsSync(lockPath())).toBe(false) + expect(existsSync(recordPath())).toBe(true) + const record = JSON.parse(readFileSync(recordPath(), 'utf-8')) + expect(record.pid).toBe(process.pid) + expect(typeof record.closedAt).toBe('string') + expect(typeof record.startedAt).toBe('string') + + // 2. The reopen says nothing about a stale lock. + const { result: reopened, lines } = await captureConsole(async () => { + const next = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await next.init() + return next + }) + brain = reopened + expect(lines.filter((l) => /stale writer lock|appears dead/i.test(l))).toEqual([]) + + // 3. The claim CONSUMED the record — it must not outlive its lock generation. + expect(existsSync(recordPath())).toBe(false) + expect(existsSync(lockPath())).toBe(true) + }, 120_000) + + it('releases the writer lock even when a durable close step fails — and still rethrows', async () => { + brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await brain.init() + await brain.add({ data: 'seed entity', type: NounType.Concept }) + await brain.flush() + expect(existsSync(lockPath())).toBe(true) + + // Inject a failure into a durable close step (the counts flush). + const storage = (brain as unknown as { storage: { flushCounts: () => Promise } }).storage + const boom = new Error('injected: counts flush failed during close') + storage.flushCounts = async () => { throw boom } + + await expect(brain.close()).rejects.toThrow(/injected: counts flush failed/) + brain = null + + // The lock is released regardless: a process on its way out holds nothing. + expect(existsSync(lockPath())).toBe(false) + + // And the next writer opens without a stale-lock verdict. + const { lines } = await captureConsole(async () => { + const next = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await next.init() + await next.close() + }) + expect(lines.filter((l) => /appears dead/i.test(l))).toEqual([]) + }, 120_000) + + it('a SIGKILLed writer leaves the lock with no record, and the next open names the crash', async () => { + const { child } = await spawnHoldingChild(dir) + expect(existsSync(lockPath())).toBe(true) + expect(existsSync(recordPath())).toBe(false) + + // Group-wide: the lock holder is tsx's grandchild, not the spawned pid. + process.kill(-(child.pid as number), 'SIGKILL') + await new Promise((r) => child.on('exit', () => r())) + // The grandchild's death is asynchronous with the wrapper's exit event. + await new Promise((r) => setTimeout(r, 500)) + + // The lock survives the kill — a dead process releases nothing. + expect(existsSync(lockPath())).toBe(true) + expect(existsSync(recordPath())).toBe(false) + + const { lines } = await captureConsole(async () => { + const next = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: dir } }) + await next.init() + await next.close() + }) + const verdict = lines.filter((l) => /Overwriting stale writer lock/i.test(l)) + expect(verdict.length).toBe(1) + // The verdict must name the ABSENT record and the recovery it implies — + // not merely that a pid is gone. + expect(verdict[0]).toMatch(/NO\s+clean-close record/i) + expect(verdict[0]).toMatch(/crash recovery/i) + }, 180_000) + + it("does not force-exit a host application that owns its own SIGTERM handler", async () => { + const script = ` + import { Brainy } from ${JSON.stringify(join(REPO_ROOT, 'src', 'brainy.ts'))} + const brain = new Brainy({ requireSubtype: false, storage: { type: 'filesystem', path: ${JSON.stringify(dir)} } }) + await brain.init() + await brain.add({ data: 'row from the host app', type: 'concept' }) + await brain.flush() + // The host application's OWN graceful shutdown, registered after Brainy's. + process.on('SIGTERM', async () => { + await new Promise((r) => setTimeout(r, 1500)) + console.log('APP-CLOSE-DONE') + process.exit(0) + }) + console.log('READY') + setInterval(() => {}, 1000) + ` + const child = startChild(dir, script) + let out = '' + child.stdout.on('data', (d) => { out += String(d) }) + child.stderr.on('data', (d) => { out += String(d) }) + await new Promise((r, reject) => { + const timer = setTimeout(() => reject(new Error(`child never became READY:\n${out}`)), 120_000) + child.stdout.on('data', () => { if (out.includes('READY')) { clearTimeout(timer); r() } }) + child.on('exit', () => { clearTimeout(timer); if (!out.includes('READY')) reject(new Error(`child died:\n${out}`)) }) + }) + + process.kill(-(child.pid as number), 'SIGTERM') + const code = await new Promise((r) => child.on('exit', (c) => r(c))) + expect(code).toBe(0) + // The host's own shutdown ran to completion — Brainy's handler did not + // exit the process out from under it. + expect(out).toContain('APP-CLOSE-DONE') + }, 180_000) +}) diff --git a/tests/integration/zero-norm-unvector-door.test.ts b/tests/integration/zero-norm-unvector-door.test.ts new file mode 100644 index 00000000..d3290010 --- /dev/null +++ b/tests/integration/zero-norm-unvector-door.test.ts @@ -0,0 +1,399 @@ +/** + * @module tests/integration/zero-norm-unvector-door + * @description THE SEAM LAW, GENERALIZED: "a zero-norm vector is not a + * vector — it never crosses an engine boundary." `tests/integration/ + * vfs-root-zero-norm.test.ts` pins the VFS-root-specific cure; this file + * pins the follow-up that generalizes it to every write path plus the + * sanctioned door for shedding a vector on purpose. + * + * Four legs pinned here: + * (A) THE CANONICAL WRITE NORMALIZES ZERO-NORM TO `[]` — `add()` (single and + * `transact()`) persists an explicit real all-zero vector as the + * "unvectored" `[]` shape, loudly, before the ledger flag/dimension + * pin/index ops ever see it. The canonical write still succeeds. + * (B) THE LEGACY DERIVATION IS ZERO-NORM-AWARE — a lost/corrupted + * `counts.json`'s one-time re-derivation walk excludes a persisted + * zero-norm row from the vectored-noun scalar, matching the live + * ledger's definition of "vectored". + * (C) THE LEGACY VFS ROOT MIGRATES AT OPEN, BEFORE THE GATE, IN O(1) — a + * store whose ONLY vectored row is a legacy all-zero VFS root opens + * clean (no `VectorIndexNotReadyError`), via one fixed-path read, never + * a listing. + * (D) THE UNVECTOR DOOR — `update({ id, vector: [] })` (and the same op + * inside `transact()`) is the sanctioned, idempotent way to shed a + * vector on purpose: ledger decrement exactly once, index removal, no + * re-embed, and a pending deferred-embed marker is cleared rather than + * left to re-vectorize the row later. + */ +import { describe, it, expect, afterEach, vi } from 'vitest' +import * as fs from 'node:fs' +import * as os from 'node:os' +import * as path from 'node:path' +import { Brainy } from '../../src/index.js' +import { NounType } from '../../src/types/graphTypes.js' +import { prodLog } from '../../src/utils/logger.js' +import { JsHnswVectorIndex } from '../../src/hnsw/hnswIndex.js' +import { BaseStorage } from '../../src/storage/baseStorage.js' + +const ROOT_ID = '00000000-0000-0000-0000-000000000000' + +process.env.BRAINY_DETERMINISTIC_EMBEDDINGS = 'true' + +const tmpDirs: string[] = [] +function mkTmp(): string { + const d = fs.mkdtempSync(path.join(os.tmpdir(), 'brainy-zero-norm-unvector-')) + tmpDirs.push(d) + return d +} +afterEach(() => { + vi.restoreAllMocks() + for (const d of tmpDirs.splice(0)) fs.rmSync(d, { recursive: true, force: true }) +}) + +function openBrain(dir: string): any { + return new Brainy({ + requireSubtype: false, + storage: { type: 'filesystem', path: dir }, + silent: true, + dimensions: 384 + }) +} + +const countsPath = (root: string) => path.join(root, '_system', 'counts.json') + +describe('zero-norm canonical write + the sanctioned unvector door', () => { + it('(A1) add() with an explicit all-zero vector persists [], warns loudly, never indexes, and the ledger is unchanged', async () => { + const dir = mkTmp() + const brain = openBrain(dir) + await brain.init() + + const ledgerBefore = await brain.storage.getCanonicalCounts() + const sizeBefore = (await brain.getIndexStatus()).hnswIndex.size + const warnSpy = vi.spyOn(prodLog, 'warn') + + const zeroVector = new Array(384).fill(0) + const id = await brain.add({ data: 'zero-norm add', type: NounType.Document, vector: zeroVector }) + + const entity = await brain.get(id, { includeVectors: true }) + expect(entity).not.toBeNull() + expect(entity.vector).toEqual([]) + + const ledgerAfter = await brain.storage.getCanonicalCounts() + expect(ledgerAfter.vectors.all).toBe(ledgerBefore.vectors.all) + + const sizeAfter = (await brain.getIndexStatus()).hnswIndex.size + expect(sizeAfter).toBe(sizeBefore) + + const loud = warnSpy.mock.calls.find( + (c) => typeof c[0] === 'string' && c[0].includes(id) && c[0].toLowerCase().includes('zero-norm') + ) + expect(loud).toBeDefined() + + await brain.close() + }) + + it('(A2) transact() add with an explicit all-zero vector — the same canonical normalization', async () => { + const dir = mkTmp() + const brain = openBrain(dir) + await brain.init() + + const ledgerBefore = await brain.storage.getCanonicalCounts() + const warnSpy = vi.spyOn(prodLog, 'warn') + const zeroVector = new Array(384).fill(0) + const id = 'aaaaaaaa-0000-4000-8000-000000000001' + + await brain.transact([ + { op: 'add', id, type: NounType.Document, data: 'zero-norm transact add', vector: zeroVector } + ]) + + const entity = await brain.get(id, { includeVectors: true }) + expect(entity).not.toBeNull() + expect(entity.vector).toEqual([]) + + const ledgerAfter = await brain.storage.getCanonicalCounts() + expect(ledgerAfter.vectors.all).toBe(ledgerBefore.vectors.all) + + const loud = warnSpy.mock.calls.find( + (c) => typeof c[0] === 'string' && c[0].includes(id) && c[0].toLowerCase().includes('zero-norm') + ) + expect(loud).toBeDefined() + + await brain.close() + }) + + it('(B) the legacy counts.json derivation excludes a persisted zero-norm row from the vectored-noun scalar', async () => { + const dir = mkTmp() + let brain = openBrain(dir) + await brain.init() + + // The VFS root alone (unvectored — []) — the floor. + const baseline = (await brain.storage.getCanonicalCounts()).vectors.all + + const realId = await brain.add({ data: 'a real vectored document', type: NounType.Document }) + + // Plant the legacy all-zero shape BY HAND: a genuine identity record + // (via add(), so it has real metadata) whose vector leg is then + // overwritten directly through the raw storage primitive — bypassing + // Leg A's canonical-write normalization entirely (brain.storage.saveNoun + // is not Brainy.add()/update()'s normalized path) — reproducing exactly + // what a pre-fix store could have persisted on disk. + const zeroId = await brain.add({ data: 'a legacy zero-norm document', type: NounType.Document }) + const zeroVector = new Array(384).fill(0) + await brain.storage.saveNoun({ id: zeroId, vector: zeroVector, connections: new Map(), level: 0 }) + + await brain.flush() + await brain.close() + + // Remove counts.json so the next open re-derives from scratch (the + // one-time legacy/lost-file derivation path — Leg B). + fs.rmSync(countsPath(dir), { force: true }) + + brain = openBrain(dir) + await brain.init() + const ledger = await brain.storage.getCanonicalCounts() + // Only realId counts; zeroId's persisted all-zero vector does not. + expect(ledger.vectors.all).toBe(baseline + 1) + + await brain.close() + }) + + it('(C) a legacy all-zero VFS root as the ONLY vectored row: open succeeds with no not-ready error, via an O(1) fixed-path read (no entities-tree readdir), and the ledger is 0 after open', async () => { + const dir = mkTmp() + + // SESSION 1 — build the legacy shape: the root is a REAL all-zero + // 384-dim vector, genuinely indexed and genuinely ledgered — exactly + // what a pre-fix store's root looked like on disk (see + // vfs-root-zero-norm.test.ts pin (b) for the identical harness). + // `index.addItem` is called directly (bypassing the transactional + // zero-norm belt) because the pre-fix code path had no such belt — this + // harness must match history, not the cure. No other entity is added, + // so the root is the store's ONLY vectored row. + let brain = openBrain(dir) + await brain.init() + const oldVector = new Array(384).fill(0) + await brain.storage.saveNoun({ id: ROOT_ID, vector: oldVector, connections: new Map(), level: 0 }) + await brain.index.addItem({ id: ROOT_ID, vector: oldVector }) + await brain.storage.noteVectorLanded(ROOT_ID) + await brain.storage.persistCounts() + await brain.flush() + expect((await brain.storage.getCanonicalCounts()).vectors.all).toBe(1) + await brain.close() + + // SESSION 2 — reopen with a FAKE native vector provider that claims + // `serving: true` at `size()===0` (the exact shape a downstream + // engine's own health report can legitimately carry — same technique as + // tests/integration/vector-leg-open-build.test.ts). This is the ONLY + // codepath where the vector-leg open gate's FAIL-TYPED throw + // (VectorIndexNotReadyError) can fire; the built-in JS engine alone + // never reaches it (the size-heuristic branch just rebuilds instead) — + // so this is the faithful reproduction of the incident Leg C closes. + const readdirCalls: string[] = [] + const originalReaddir = fs.promises.readdir.bind(fs.promises) + vi.spyOn(fs.promises, 'readdir').mockImplementation(((...args: any[]) => { + readdirCalls.push(String(args[0])) + return (originalReaddir as any)(...args) + }) as any) + + // Spy at the PROTOTYPE level (BaseStorage.getNoun) — the new brain's + // storage instance does not exist until init() runs, so an + // instance-level spy cannot be installed beforehand. Records the + // readdir-call delta across the FIRST call made with the root id — + // Leg C's own fixed-path read — proving it needs no directory listing. + let readdirDeltaDuringRootRead: number | null = null + const originalGetNoun = BaseStorage.prototype.getNoun + vi.spyOn(BaseStorage.prototype, 'getNoun').mockImplementation(async function ( + this: unknown, + id: string + ) { + const before = readdirCalls.length + const result = await originalGetNoun.call(this as BaseStorage, id) + if (id === ROOT_ID && readdirDeltaDuringRootRead === null) { + readdirDeltaDuringRootRead = readdirCalls.length - before + } + return result + }) + + brain = openBrain(dir) + brain.use({ + name: 'fake-native-vector-unledgered-coverage', + activate: async (ctx: any) => { + ctx.registerProvider('vector', (config: any, distance: any, options: any) => { + const real = new JsHnswVectorIndex(config, distance, options) + let rebuilt = false + const originalRebuild = real.rebuild.bind(real) + ;(real as any).rebuild = async (...args: any[]) => { + const r = await originalRebuild(...args) + rebuilt = true + return r + } + const originalSize = real.size.bind(real) + ;(real as any).size = () => (rebuilt ? originalSize() : 0) + ;(real as any).healthReport = () => ({ + provider: 'vector', + healthy: true, + serving: true, + invariants: [], + checkedAt: Date.now(), + durationMs: 0, + generation: 1, + unledgered: ['vector-coverage'] + }) + return real + }) + return true + } + }) + + // Must NOT throw VectorIndexNotReadyError (or anything else) — a + // near-empty store whose only vectored row is the zero-norm root must + // never go dark. + await brain.init() + + const migratedRoot = await brain.get(ROOT_ID, { includeVectors: true }) + expect(migratedRoot.vector).toEqual([]) + + const ledgerAfter = await brain.storage.getCanonicalCounts() + expect(ledgerAfter.vectors.all).toBe(0) + + expect(readdirDeltaDuringRootRead).toBe(0) + + await brain.close() + }) + + describe('the sanctioned unvector door', () => { + it('(D1) update({ id, vector: [] }) unvectors a real vectored row — canonical [], removed from the index, ledger decremented by exactly 1, no embed call', async () => { + const dir = mkTmp() + const brain = openBrain(dir) + await brain.init() + + const id = await brain.add({ data: 'a real document', type: NounType.Document }) + await brain.flush() + + const ledgerBefore = await brain.storage.getCanonicalCounts() + const sizeBefore = (await brain.getIndexStatus()).hnswIndex.size + + const embedSpy = vi.spyOn(brain, 'embed') + await brain.update({ id, vector: [] }) + expect(embedSpy).not.toHaveBeenCalled() + + const entity = await brain.get(id, { includeVectors: true }) + expect(entity.vector).toEqual([]) + + const ledgerAfter = await brain.storage.getCanonicalCounts() + expect(ledgerAfter.vectors.all).toBe(ledgerBefore.vectors.all - 1) + + const sizeAfter = (await brain.getIndexStatus()).hnswIndex.size + expect(sizeAfter).toBe(sizeBefore - 1) + + await brain.close() + }) + + it('(D2) idempotent: a second update({ id, vector: [] }) on an already-unvectored row is a true no-op — no error, no further decrement', async () => { + const dir = mkTmp() + const brain = openBrain(dir) + await brain.init() + + const id = await brain.add({ data: 'a real document', type: NounType.Document }) + await brain.flush() + + await brain.update({ id, vector: [] }) + const ledgerAfterFirst = await brain.storage.getCanonicalCounts() + + await brain.update({ id, vector: [] }) + const ledgerAfterSecond = await brain.storage.getCanonicalCounts() + expect(ledgerAfterSecond.vectors.all).toBe(ledgerAfterFirst.vectors.all) + + const entity = await brain.get(id, { includeVectors: true }) + expect(entity.vector).toEqual([]) + + await brain.close() + }) + + it('(D3) a PENDING deferred-embed row: the unvector door clears the marker; awaitPendingEmbeds() then leaves it unvectored', async () => { + const dir = mkTmp() + const brain = openBrain(dir) + await brain.init() + + // Prevent the background worker from ever actually running — it is + // fire-and-forget from add(), and a real run would race this test's + // own assertions (see tests/integration/vector-leg-open-build.test.ts + // for the same concern). This isolates exactly the marker-clearing + // behavior under test. + vi.spyOn(brain as any, 'kickEmbedWorker').mockImplementation(() => {}) + + const id = await brain.add({ + data: 'deferred content, never embedded', + type: NounType.Document, + deferEmbedding: true + }) + expect(brain.pendingEmbedCount()).toBe(1) + + const warnSpy = vi.spyOn(prodLog, 'warn') + await brain.update({ id, vector: [] }) + + expect(brain.pendingEmbedCount()).toBe(0) + const clearedWarn = warnSpy.mock.calls.find( + (c) => typeof c[0] === 'string' && c[0].includes(id) && c[0].toLowerCase().includes('pending') + ) + expect(clearedWarn).toBeDefined() + + // The barrier must not hang and must not re-vectorize the row — the + // worker (still mocked to a no-op) never runs again. + await brain.awaitPendingEmbeds() + + const entity = await brain.get(id, { includeVectors: true }) + expect(entity.vector).toEqual([]) + + await brain.close() + }) + + it('(D4) update({ vector: [], deferEmbedding: true }) is a typed refusal — the unvector door cannot be paired with a deferred embed', async () => { + const dir = mkTmp() + const brain = openBrain(dir) + await brain.init() + + const id = await brain.add({ data: 'a real document', type: NounType.Document }) + const before = await brain.get(id, { includeVectors: true }) + + await expect( + brain.update({ id, vector: [], deferEmbedding: true }) + ).rejects.toThrow(/unvector door/i) + + // Refused before any write — the row is untouched. + const after = await brain.get(id, { includeVectors: true }) + expect(after.vector).toEqual(before.vector) + + await brain.close() + }) + + it('(D5) the transact() twin of the unvector door decrements the ledger exactly once, and is idempotent on a second call', async () => { + const dir = mkTmp() + const brain = openBrain(dir) + await brain.init() + + const id = await brain.add({ data: 'a real document for transact unvector', type: NounType.Document }) + await brain.flush() + + const ledgerBefore = await brain.storage.getCanonicalCounts() + const sizeBefore = (await brain.getIndexStatus()).hnswIndex.size + + await brain.transact([{ op: 'update', id, vector: [] }]) + + const entity = await brain.get(id, { includeVectors: true }) + expect(entity.vector).toEqual([]) + + const ledgerAfter = await brain.storage.getCanonicalCounts() + expect(ledgerAfter.vectors.all).toBe(ledgerBefore.vectors.all - 1) + + const sizeAfter = (await brain.getIndexStatus()).hnswIndex.size + expect(sizeAfter).toBe(sizeBefore - 1) + + // Idempotent through transact() too. + await brain.transact([{ op: 'update', id, vector: [] }]) + const ledgerAfterSecond = await brain.storage.getCanonicalCounts() + expect(ledgerAfterSecond.vectors.all).toBe(ledgerAfter.vectors.all) + + await brain.close() + }) + }) +}) diff --git a/tests/lifecycle/biography.test.ts b/tests/lifecycle/biography.test.ts index 8b274fce..274f0ef0 100644 --- a/tests/lifecycle/biography.test.ts +++ b/tests/lifecycle/biography.test.ts @@ -382,9 +382,17 @@ describe.sequential('lifecycle — the working store', () => { }, // Every noun this biography ever adds carries an explicit/computed // vector (the harness never defers an embed), so the vectored-noun - // scalar tracks nouns.all exactly. + // scalar tracks nouns.all exactly EXCEPT for the VFS root counted + // in `vfsBaselineNouns`: the root is deliberately persisted with + // `vector: []` (the sanctioned "unvectored" shape — see + // VirtualFileSystem.doInitializeRoot()'s zero-norm-avoidance + // comment) so it never pays the WASM engine's cold-compile cost and + // never crosses an engine boundary as a false attractor. It is the + // ONE hidden-tier record `vfsBaselineNouns` represents (see + // biographyHarness's module header), so it is excluded here even + // though it counts toward `nouns.all`. vectors: { - all: aliveEntities.length + model.vfsFileNouns + model.vfsBaselineNouns + all: aliveEntities.length + model.vfsFileNouns }, suspect: false }) diff --git a/tests/unit/brainy/migration-deference.test.ts b/tests/unit/brainy/migration-deference.test.ts index 31b9b216..b5817c3d 100644 --- a/tests/unit/brainy/migration-deference.test.ts +++ b/tests/unit/brainy/migration-deference.test.ts @@ -15,7 +15,7 @@ * - Hook 2: the public `brain.stampBrainFormat()` the provider calls once its * background migration has verified-and-swapped, authoring the shared * `_system/brain-format.json` marker. - * - Hook 3: the marker module is re-exported at `@soulcraft/brainy/brain-format` + * - Hook 3: the marker module is re-exported at `@soulcraftlabs/brainy/brain-format` * so cor reads the SAME `EXPECTED_INDEX_EPOCH` / `CURRENT_DATA_FORMAT` constants * (single source of truth, no duplicated value). * @@ -242,7 +242,7 @@ describe('rc.8 no-freeze migration deference (isMigrating / stampBrainFormat / b // --- Hook 3: marker module export ---------------------------------------- it('the brain-format marker module exports the compiled epoch + data-format constants', () => { - // cor imports these from '@soulcraft/brainy/brain-format' (Hook 3) so both + // cor imports these from '@soulcraftlabs/brainy/brain-format' (Hook 3) so both // sides share ONE source of truth — no duplicated constant to drift. // Epoch 3: the namespace-law key split (bare user keys · literal // 'system.' scalars, 2026-08-03) — every brain rebuilds onto the diff --git a/tests/unit/db/generation-segments.test.ts b/tests/unit/db/generation-segments.test.ts index 27ab85cb..f16e67b3 100644 --- a/tests/unit/db/generation-segments.test.ts +++ b/tests/unit/db/generation-segments.test.ts @@ -147,4 +147,119 @@ 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 => { + 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/ + ) + }) })