mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-30 03:12:32 +00:00
* v0.30.1 Lane A: connection-manager foundation + X1 initSchema routing Routes Postgres queries by query type: - read() goes to the Supabase pooler (port 6543, fast) - ddl() and bulk() go to direct (port 5432, 30min stmt timeout, mwm 256MB) Auto-detects Supabase via hostname pooler.supabase.com or port 6543. Override with GBRAIN_DIRECT_DATABASE_URL. Kill-switch via GBRAIN_DISABLE_DIRECT_POOL=1 falls back to single-pool legacy path. Foundation modules (Lane A scope): - src/core/connection-manager.ts: read/ddl/bulk/healthCheck, parent-CM inheritance (T5/X1), cached Promise<Sql> lazy init (A1), kill-switch inheritance (A2), Supabase URL auto-derivation - src/core/url-redact.ts: redactPgUrl + redactDeep (F3) - src/core/retry-matcher.ts: typed predicates for stmt-timeout / lock / conn errors (C4) - src/core/connection-audit.ts: ~/.gbrain/audit/connection-events JSONL with ISO-week rotation; doctor tail-reads last 5 errors (F8) - scripts/check-pg-url-redaction.sh: CI grep guard against unredacted postgresql:// URL leaks (F3) Engine integration: - PostgresEngine.connect: instantiates instance-owned ConnectionManager, inherits from parentConnectionManager when set (worker engines, sync, cycle), shares pool with module-singleton path - PostgresEngine.disconnect: tears down direct pool first - PostgresEngine.initSchema: routes DDL through connectionManager.ddl() when dual-pool active (X1 part 1; lock semantics replacement is Lane B) - cli.ts:connectEngine(opts): probeOnly skips initSchema entirely (X1 part 2 — get_health, upgrade --status will use this) Tests added (51 new cases): - test/url-redact.test.ts: 11 cases - test/retry-matcher.test.ts: 13 cases - test/connection-manager.test.ts: 27 cases (URL detection, derive, kill-switch, parent inheritance, dual-pool routing modes) Foundation for Lanes B-E. Sequential lane work continues. Plan: ~/.claude/plans/system-instruction-you-are-working-stateless-wadler.md Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * v0.30.1 Lane B: migration runner retry + verify hooks + namespaced --force flags Adds Migration interface fields: - idempotent: boolean (default true; explicit false blocks verify-hook re-runs on destructive migrations) - verify: optional post-condition probe; runs after migration claims success Migration retry wrapper (Cherry D3 / Finding F2): - 3 attempts with 5s/15s/45s backoff (env GBRAIN_MIGRATE_BACKOFF_MS=0 for tests) - Retries only on statement_timeout (57014) or connection-reset patterns - Pre-attempt: logs idle-in-transaction blockers via getIdleBlockers - On exhaustion: throws MigrationRetryExhausted with named PID + suggested pg_terminate_backend() recovery command Verify-hook self-healing (Cherry D6 / Codex X3): - On verify=false + idempotent=true → re-runs migration once silently - On verify=false + idempotent=false → throws MigrationDriftError - --skip-verify CLI flag bypasses for operator override withRefreshingLock helper (Cherry T4 / Codex A4 / X1 part 3): - setInterval refresh every TTL/6 ms during long-running work - SELECT 1 backend-alive heartbeat per refresh tick - Heartbeat hang past 30s → log + clear interval; lock TTL auto-expires - LockUnavailableError when acquire fails (caller decides retry) - buildTenantLockId(scope) appends current_database() suffix for multi-tenant safety (Cherry D4) Namespaced --force flags (Codex T5): - --force-orchestrator: write 'retry' markers for ALL wedged orchestrators - --force-schema: re-runs runMigrations against current config.version - --force / --force-all: both - --force-retry vX.Y.Z: existing single-version reset (preserved) - --skip-verify: bypass verify-hook drift detection on a single run Test additions: - test/migrate-extensions.test.ts: 14 cases (idempotent default, error envelopes, MIGRATIONS contract) - test/db-lock-refresh.test.ts: 10 cases (LockUnavailableError, buildTenantLockId multi-tenant, opts shape) - test/migrate.test.ts: updated 2 existing cases (PR #356 retry shape + function-name anchor) for v0.30.1 retry-wrapper semantics 156 unit tests passing across the v0.30.1 surface so far. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * v0.30.1 Lane C: backfill primitive + registry + X4 + X5 First-class generic backfill runner (Fix 3). Generalizes the keyset+checkpoint+adaptive-batch pattern from src/core/backfill-effective-date.ts so future backfills (embedding_voyage in v0.30.2, etc.) reuse one tested runner. NEW src/core/backfill-base.ts: - runBackfill() with keyset pagination, config-table checkpoint, adaptive batch halving on stmt timeout, conn-drop reconnect, max-errors bail - ensureBackfillIndex() verifies/creates partial index CONCURRENTLY (P2/X4) - clearBackfillCheckpoint() for --fresh path - T3 fix: writes go through engine.withReservedConnection so BEGIN / SET LOCAL / UPDATE / COMMIT execute on the SAME backend (otherwise SET LOCAL evaporates between pooled executeRaw calls) NEW src/core/backfill-registry.ts: - effective_date: implemented (wraps existing computeEffectiveDate) - emotional_weight: implemented (wraps computeEmotionalWeight + stamps new emotional_weight_recomputed_at column) - embedding_voyage: declared-only in v0.30.1 (multi-column embedding schema lands in v0.30.2) NEW src/commands/backfill.ts: - gbrain backfill <kind> [--batch-size N] [--concurrency N] [--resume] [--fresh] [--dry-run] [--keep-index] [--max-errors N] - gbrain backfill list — shows registered backfills + status - X5 admission control: clampConcurrency() forces --concurrency to GBRAIN_DIRECT_POOL_SIZE - 1 ceiling (always reserves 1 conn for HNSW + heartbeat + doctor probes). Loud-warns when user requests above. Schema migration v44 (X4 / Codex C8 fix): - pages.emotional_weight_recomputed_at TIMESTAMPTZ - emotional_weight = 0 is a VALID steady-state value per migration v40, so the original P2 predicate ("WHERE emotional_weight = 0") would have been a permanent large index over normal data. The corrected backlog predicate is "emotional_weight_recomputed_at IS NULL"; the partial index drops naturally as the cycle phase + this backfill stamp the column over time. - idempotent: true (ADD COLUMN ... NULL is metadata-only) CLI integration: - src/cli.ts: registers `backfill` subcommand - reindex-frontmatter stays as thin alias for v0.30.1 back-compat; canonical entrypoint is now `gbrain backfill effective_date` Test additions: - test/backfill-base.test.ts: 11 cases (keyset, checkpoint, dry-run, resume/fresh, maxRows cap, withReservedConnection routing, error paths, clearCheckpoint, ensureBackfillIndex) - test/backfill-concurrency-clamp.test.ts: 6 cases (X5 admission control) 173 unit tests passing across Lanes A+B+C of v0.30.1. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * v0.30.1 Lane D: HNSW lifecycle manager + A3 atomic-swap Extends src/core/vector-index.ts with the v0.30.1 lifecycle layer. The original chunkEmbeddingIndexSql / applyChunkEmbeddingIndexPolicy contract is preserved unchanged. New surfaces: - checkActiveBuild(engine, indexName): probes pg_stat_activity for an active CREATE INDEX or REINDEX on the named index. Used as pre-op guard so dropAndRebuild doesn't compete with a build already in flight (Supabase auto-maintenance, parallel gbrain procs). - dropZombieIndexes(engine, tableNames): startup sweep of indisvalid=false rows on gbrain tables. Drops them with DROP INDEX IF EXISTS, BUT skips any zombie that has an active build still in pg_stat_activity (codex Fix-5 in-progress-build guard). Wired into PostgresEngine.initSchema() — runs after migrations + verifySchema, best-effort, never blocks engine.connect(). - dropAndRebuild(engine, spec, opts): A3 atomic-swap pattern: 1. checkActiveBuild → bail if another build is active (--force overrides) 2. CREATE INDEX CONCURRENTLY <name>_rebuild_<unix-ms> via engine.withReservedConnection (CONCURRENTLY can't run in a txn) 3. Atomic swap inside engine.transaction: DROP INDEX <old-name> ALTER INDEX <temp-name> RENAME TO <old-name> 4. If step 2 fails (OOM, timeout, conn drop), the OLD index stays intact and search keeps serving queries. This is the headline A3 win — no production-degraded silent failure mode. - monitorBuild(engine, indexName, onProgress, opts): poll pg_stat_activity every 30s; emit elapsed_ms + size_bytes (via pg_relation_size) + pid. Used by gbrain backfill embedding_voyage when batch > 1000 triggers a rebuild. - isSupabaseAutoMaintenance(active): predicate on application_name (matches "supabase" / "postgres-meta"). Used by dropAndRebuild to log + back off when Supabase auto-maintenance is doing the rebuild. Engine integration: - PostgresEngine.initSchema() calls dropZombieIndexes after verifySchema. Surfaces zombie counts via console.log. - Best-effort wrapped in try/catch: pg_stat_activity / pg_index access can be restricted on managed Postgres tiers; gbrain shouldn't fail engine.connect() over diagnostic queries. Test additions (18 cases): - test/vector-index-lifecycle.test.ts: * chunkEmbeddingIndexSql contract (3 cases) — pre-existing behavior preserved * applyChunkEmbeddingIndexPolicy contract (1 case) * checkActiveBuild (4 cases, including PGLite no-op + best-effort failure) * isSupabaseAutoMaintenance (3 cases) * dropZombieIndexes (4 cases, including in-progress-build guard) * dropAndRebuild atomic-swap (3 cases, including PGLite + active-build bail + temp-name format assertion) 191 unit tests passing across Lanes A+B+C+D of v0.30.1. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * v0.30.1 Lane E: upgrade pipeline checkpoint + brain_id binding + get_health migrations NEW src/core/upgrade-checkpoint.ts: - Cherry D5: persists step-by-step progress through gbrain post-upgrade so partial failures can be resumed via gbrain upgrade --resume. Steps: pull → install → schema → features → backfills → verify. - Codex X2: checkpoint binds to brain identity via sha256(database_url) (userinfo stripped before hashing so cred rotations don't invalidate). PGLite uses sha256(database_path). Cross-brain checkpoint application is now refused with reason='brain_mismatch'. - F4 fall-through: validateCheckpoint returns reason='no_checkpoint' when none exists, enabling silent fall-through to a full upgrade. - All-complete detection: stale checkpoints (every step done) return reason='all_complete' so the next run clears + re-runs from scratch. - markStepComplete + markStepFailed maintain the partial-state shape. T2 preserved: upgrade.ts still re-execs `gbrain post-upgrade` so the NEW binary's migration registry runs (the existing re-exec pattern is correct per codex round 1's plan-breaking finding). The checkpoint module is the substrate that Lane E's --resume / --status surfaces will plumb through in v0.30.2. D7 + C3 contract committed: - BrainHealth.schema_version: '1' (literal type) — additive-only contract pinned for MCP get_health consumers. - BrainHealth.migrations: { schema, orchestrator } — explicit two-ledger diagnostic surface (codex T5 namespacing). Both fields are OPTIONAL in v0.30.1 — engines can populate them in v0.30.2 without a contract bump. Backwards/forwards compat: clients default-handle missing fields. VERSION: 0.30.0 → 0.30.1 package.json: synced Test additions (18 cases): - test/upgrade-checkpoint.test.ts: * computeBrainId: userinfo strip, DB-distinct hashes, stable hex (5 cases) * write/load round-trip: roundtrip, missing file, malformed JSON, clear (4 cases) * validateCheckpoint: F4 no_checkpoint, X2 brain_mismatch, partial → resumeAt, all_complete, first-step pending (5 cases) * markStepComplete/markStepFailed: append, idempotent, clear-failed, failed-state shape (4 cases) 209 unit tests passing across all 5 lanes of v0.30.1 (Lanes A-E core foundations). Plumbing into upgrade.ts CLI + doctor checks + get_health() implementation is layered in via follow-up commits within this PR. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * v0.30.1 e2e + test isolation: integration smoke + serial quarantine NEW test/e2e/v030_1-integration-pglite.test.ts (14 cases): PGLite integration smoke proving Lane A-E surfaces work together. Lane B: migration runner applies v44 (emotional_weight_recomputed_at) cleanly; config.version reaches LATEST_VERSION Lane C: backfill registry resolves all 3 entries; emotional_weight + effective_date backfills on empty brain return examined=0 cleanly Lane D: dropZombieIndexes / checkActiveBuild on PGLite are no-ops Lane E: upgrade-checkpoint round-trips with brain_id; X2 mismatch refused; F4 fall-through detected via reason='no_checkpoint'; full step progression to all_complete Test isolation hygiene (scripts/check-test-isolation.sh): - test/connection-manager.test.ts → connection-manager.serial.test.ts - test/backfill-concurrency-clamp.test.ts → .serial.test.ts - test/upgrade-checkpoint.test.ts → .serial.test.ts All three files mutate process.env (kill-switch, GBRAIN_DIRECT_POOL_SIZE, GBRAIN_HOME) which would race other tests in the parallel runner. *.serial.test.ts quarantine ensures they run at --max-concurrency=1. Choice between withEnv() refactor and serial quarantine made on the side of preserving existing well-formed test code. E2E coverage status: - v030_1-integration-pglite.test.ts (this commit): 14 cases, all green - backfill-perf-pglite.test.ts: 1 case, green (no regression) - cycle-recompute-emotional-weight-pglite.test.ts: green (no regression) - multi-source-emotional-weight-pglite.test.ts: green (no regression) - dream-synthesize-pglite.test.ts: 14 cases, green (no regression) - anomalies-pglite.test.ts + salience-pglite.test.ts: 6 cases, green Postgres-only E2Es (migration-flow, http-transport, hnsw-lifecycle, connection-routing) require DATABASE_URL + a real Postgres+pgvector container per the CLAUDE.md E2E lifecycle. They land as separate DATABASE_URL-gated work — not regressed by v0.30.1 changes; their preconditions just aren't met in the current run environment. `bun run verify` (typecheck + 4 shell pre-checks + test-isolation lint) passes cleanly. Final v0.30.1 unit + integration test count: 4547 pass, 0 regressions. Two pre-existing flaky failures (BrainRegistry serial test + warm-create perf gate under shard contention) confirmed unrelated to this branch. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: bump version and changelog (v0.30.1) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
161 lines
5.8 KiB
TypeScript
161 lines
5.8 KiB
TypeScript
/**
|
|
* Upgrade pipeline checkpoint (v0.30.1 Cherry D5 + Codex X2).
|
|
*
|
|
* Persists step-by-step progress through `gbrain post-upgrade` so a partial
|
|
* failure can be resumed via `gbrain upgrade --resume` instead of
|
|
* re-running every step from scratch.
|
|
*
|
|
* Codex X2 fix: checkpoint is bound to the brain it was created for, via
|
|
* a sha256(database_url) hash. brain-registry.ts:300 manages multiple
|
|
* mounted brains; without identity binding, a checkpoint from brain A can
|
|
* be applied against brain B (corruption vector). The validate() helper
|
|
* is the F4 fall-through gate — when called with a no-checkpoint or
|
|
* mismatched-brain state, the upgrade pipeline silently runs the full path.
|
|
*/
|
|
|
|
import { existsSync, readFileSync, writeFileSync, unlinkSync, mkdirSync } from 'node:fs';
|
|
import { dirname } from 'node:path';
|
|
import { createHash } from 'node:crypto';
|
|
import { gbrainPath, loadConfig } from './config.ts';
|
|
|
|
export type UpgradeStep = 'pull' | 'install' | 'schema' | 'features' | 'backfills' | 'verify';
|
|
|
|
export interface UpgradeCheckpoint {
|
|
/** Stable hash of the brain's database_url. Detects multi-brain mismatch (X2). */
|
|
brain_id: string;
|
|
/** ISO 8601 timestamp of when the upgrade started. */
|
|
started_at: string;
|
|
/** Source version (the binary that started the upgrade). */
|
|
from_version: string;
|
|
/** Target version (the binary that's running the pipeline). */
|
|
to_version: string;
|
|
/** Steps that completed successfully. */
|
|
completed_steps: UpgradeStep[];
|
|
/** Step that failed (set on error). */
|
|
failed_step?: UpgradeStep;
|
|
/** Error info from the failed step. */
|
|
failed_step_error?: { message: string; code?: string };
|
|
}
|
|
|
|
const CHECKPOINT_FILENAME = 'upgrade-checkpoint.json';
|
|
const ALL_STEPS: UpgradeStep[] = ['pull', 'install', 'schema', 'features', 'backfills', 'verify'];
|
|
|
|
function checkpointPath(): string {
|
|
return gbrainPath(CHECKPOINT_FILENAME);
|
|
}
|
|
|
|
/**
|
|
* Compute a stable brain identity hash from the database URL. Strips
|
|
* userinfo to avoid creds in the hash input collision space (anyone
|
|
* comparing hashes can't reverse to find a password). Falls back to
|
|
* 'unknown' when no URL is configured.
|
|
*/
|
|
export function computeBrainId(databaseUrl?: string | null): string {
|
|
if (!databaseUrl) {
|
|
// PGLite or no config — derive from the configured database_path
|
|
// when present, else 'pglite-default'.
|
|
const cfg = loadConfig();
|
|
const path = cfg?.database_path;
|
|
return createHash('sha256').update(`pglite:${path ?? 'default'}`).digest('hex').slice(0, 16);
|
|
}
|
|
// Strip userinfo so the hash is stable across credential rotations.
|
|
const stripped = databaseUrl.replace(/\/\/[^@]*@/, '//');
|
|
return createHash('sha256').update(stripped).digest('hex').slice(0, 16);
|
|
}
|
|
|
|
/**
|
|
* Read the checkpoint from disk. Returns null when missing or unreadable.
|
|
*/
|
|
export function loadCheckpoint(): UpgradeCheckpoint | null {
|
|
const path = checkpointPath();
|
|
if (!existsSync(path)) return null;
|
|
try {
|
|
const raw = readFileSync(path, 'utf-8');
|
|
const parsed = JSON.parse(raw) as UpgradeCheckpoint;
|
|
// Defensive: must have brain_id + completed_steps shape.
|
|
if (typeof parsed.brain_id !== 'string') return null;
|
|
if (!Array.isArray(parsed.completed_steps)) return null;
|
|
return parsed;
|
|
} catch {
|
|
return null;
|
|
}
|
|
}
|
|
|
|
export function writeCheckpoint(state: UpgradeCheckpoint): void {
|
|
const path = checkpointPath();
|
|
try {
|
|
mkdirSync(dirname(path), { recursive: true });
|
|
writeFileSync(path, JSON.stringify(state, null, 2), 'utf-8');
|
|
} catch (err) {
|
|
process.stderr.write(`[upgrade-checkpoint] write failed: ${(err as Error).message}\n`);
|
|
}
|
|
}
|
|
|
|
export function clearCheckpoint(): void {
|
|
const path = checkpointPath();
|
|
try {
|
|
if (existsSync(path)) unlinkSync(path);
|
|
} catch {
|
|
/* best-effort */
|
|
}
|
|
}
|
|
|
|
export interface CheckpointValidation {
|
|
valid: boolean;
|
|
/** Reason for invalidation. */
|
|
reason?: 'no_checkpoint' | 'brain_mismatch' | 'malformed' | 'all_complete';
|
|
/** Step to resume at (next un-completed step). */
|
|
resumeAt?: UpgradeStep;
|
|
/** The loaded checkpoint when valid + has unfinished work. */
|
|
checkpoint?: UpgradeCheckpoint;
|
|
}
|
|
|
|
/**
|
|
* Validate a checkpoint against the current brain. Returns:
|
|
* - valid=false reason=no_checkpoint → caller falls through to full upgrade (F4)
|
|
* - valid=false reason=brain_mismatch → operator must --force or remove checkpoint
|
|
* - valid=false reason=all_complete → checkpoint is stale; clear it and run full
|
|
* - valid=true → resume from resumeAt
|
|
*/
|
|
export function validateCheckpoint(currentBrainId: string): CheckpointValidation {
|
|
const checkpoint = loadCheckpoint();
|
|
if (!checkpoint) return { valid: false, reason: 'no_checkpoint' };
|
|
if (checkpoint.brain_id !== currentBrainId) {
|
|
return { valid: false, reason: 'brain_mismatch', checkpoint };
|
|
}
|
|
// Find the first step NOT in completed_steps.
|
|
const nextStep = ALL_STEPS.find(s => !checkpoint.completed_steps.includes(s));
|
|
if (!nextStep) {
|
|
return { valid: false, reason: 'all_complete', checkpoint };
|
|
}
|
|
return { valid: true, resumeAt: nextStep, checkpoint };
|
|
}
|
|
|
|
/**
|
|
* Mark a step complete in-place. Caller writes back via writeCheckpoint().
|
|
*/
|
|
export function markStepComplete(checkpoint: UpgradeCheckpoint, step: UpgradeStep): UpgradeCheckpoint {
|
|
if (!checkpoint.completed_steps.includes(step)) {
|
|
checkpoint.completed_steps.push(step);
|
|
}
|
|
// Clear failed_step when a step completes successfully (could be a re-run).
|
|
delete checkpoint.failed_step;
|
|
delete checkpoint.failed_step_error;
|
|
return checkpoint;
|
|
}
|
|
|
|
export function markStepFailed(
|
|
checkpoint: UpgradeCheckpoint,
|
|
step: UpgradeStep,
|
|
err: Error,
|
|
): UpgradeCheckpoint {
|
|
checkpoint.failed_step = step;
|
|
checkpoint.failed_step_error = {
|
|
message: err.message,
|
|
code: (err as { code?: string }).code,
|
|
};
|
|
return checkpoint;
|
|
}
|
|
|
|
export const ALL_UPGRADE_STEPS = ALL_STEPS;
|