mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-31 04:07:52 +00:00
fix(facts): idempotent fence deposits + re-runnable fence-backfill command
Two fixes for the remote extract_facts deposit path: #2044 — a second deposit to an already-fenced page could throw idx_facts_fence_key and roll back the whole batch when fence and DB row_nums diverged (e.g. legacy wrong-path fence writes). writeFactsToFence now seeds the next row_num from MAX(fence max, DB max(row_num)) for the (source_id, slug) pair, and insertFacts in BOTH engines adds ON CONFLICT (source_id, source_markdown_slug, row_num) WHERE row_num IS NOT NULL DO NOTHING so a residual collision skips one row instead of failing the batch. #1867 — row_num-NULL backlogs (remote deposits that predate the fence backstop) had no remedy: the fence backfill lived only inside the one-shot v0_32_2 migration, and the cycle guard pointed at `gbrain apply-migrations --yes`, which never re-runs a completed migration. phaseBFenceFacts (already idempotent on row_num IS NULL) is now exported and exposed as `gbrain facts fence-backfill [--dry-run]`; the guard message points at it. The backfill also routes page paths through resolvePageFilePath so non-default sources fence into the same path the fence-write backstop uses. Fixes #2044 Fixes #1867 Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
co-authored by
Claude Fable 5
Claude Fable 5
parent
0612b0daa8
commit
2bb3424863
+12
-1
@@ -54,7 +54,7 @@ export function bigintToStringReplacer(_key: string, value: unknown): unknown {
|
||||
}
|
||||
|
||||
// CLI-only commands that bypass the operation layer
|
||||
export const CLI_ONLY = new Set(['init', 'reinit-pglite', 'upgrade', 'post-upgrade', 'check-update', 'integrations', 'publish', 'check-backlinks', 'lint', 'report', 'import', 'export', 'files', 'embed', 'serve', 'call', 'config', 'doctor', 'migrate', 'eval', 'sync', 'extract', 'extract-conversation-facts', 'enrich', 'features', 'autopilot', 'graph-query', 'jobs', 'agent', 'apply-migrations', 'skillpack-check', 'skillpack', 'resolvers', 'integrity', 'repair-jsonb', 'orphans', 'sources', 'mounts', 'dream', 'check-resolvable', 'routing-eval', 'skillify', 'smoke-test', 'providers', 'storage', 'repos', 'code-def', 'code-refs', 'reindex', 'reindex-code', 'reindex-frontmatter', 'code-callers', 'code-callees', 'reconcile-links', 'frontmatter', 'auth', 'friction', 'claw-test', 'book-mirror', 'takes', 'think', 'salience', 'anomalies', 'calibration', 'transcripts', 'models', 'remote', 'recall', 'forget', 'edges-backfill', 'cache', 'ze-switch', 'founder', 'brainstorm', 'lsd', 'schema', 'capture', 'onboard', 'conversation-parser', 'status', 'connect', 'skillopt', 'quarantine', 'self-upgrade', 'advisor', 'watch', 'reindex-search-vector']);
|
||||
export const CLI_ONLY = new Set(['init', 'reinit-pglite', 'upgrade', 'post-upgrade', 'check-update', 'integrations', 'publish', 'check-backlinks', 'lint', 'report', 'import', 'export', 'files', 'embed', 'serve', 'call', 'config', 'doctor', 'migrate', 'eval', 'sync', 'extract', 'extract-conversation-facts', 'enrich', 'features', 'autopilot', 'graph-query', 'jobs', 'agent', 'apply-migrations', 'skillpack-check', 'skillpack', 'resolvers', 'integrity', 'repair-jsonb', 'orphans', 'sources', 'mounts', 'dream', 'check-resolvable', 'routing-eval', 'skillify', 'smoke-test', 'providers', 'storage', 'repos', 'code-def', 'code-refs', 'reindex', 'reindex-code', 'reindex-frontmatter', 'code-callers', 'code-callees', 'reconcile-links', 'frontmatter', 'auth', 'friction', 'claw-test', 'book-mirror', 'takes', 'think', 'salience', 'anomalies', 'calibration', 'transcripts', 'models', 'remote', 'recall', 'forget', 'edges-backfill', 'facts', 'cache', 'ze-switch', 'founder', 'brainstorm', 'lsd', 'schema', 'capture', 'onboard', 'conversation-parser', 'status', 'connect', 'skillopt', 'quarantine', 'self-upgrade', 'advisor', 'watch', 'reindex-search-vector']);
|
||||
// CLI-only commands whose handlers print their own --help text. These are
|
||||
// excluded from the generic short-circuit so detailed per-command and
|
||||
// per-subcommand usage stays reachable.
|
||||
@@ -991,6 +991,8 @@ const THIN_CLIENT_REFUSED_COMMANDS = new Set([
|
||||
// hint pointing at the routable MCP tools; per-subcommand splits are
|
||||
// a v0.31.x follow-up TODO.
|
||||
'takes', 'sources',
|
||||
// #1867: fence-backfill edits local .md fences + stamps the local DB.
|
||||
'facts',
|
||||
// v0.32 thin-client routing audit (Codex round 2 findings #2, #4):
|
||||
// - `pages` purge-deleted is admin+localOnly (operations.ts:856-864)
|
||||
// - `files` list / file_url MCP ops are localOnly (operations.ts:1769-1879)
|
||||
@@ -1026,6 +1028,7 @@ const THIN_CLIENT_REFUSE_HINTS: Record<string, string> = {
|
||||
migrate: "migrate runs on the host's local engine. Run on the host machine.",
|
||||
'apply-migrations': 'schema migrations run on the host. SSH and run there.',
|
||||
'repair-jsonb': 'repair-jsonb operates on the local DB only.',
|
||||
facts: 'facts fence-backfill edits local entity-page fences. Run on the host machine.',
|
||||
integrity: 'integrity scans local files. Run on the host machine.',
|
||||
serve: 'serve starts a server. Run on the host, not the thin client.',
|
||||
dream: 'dream runs the autopilot cycle on the host. `gbrain remote ping` queues one. (Native `gbrain dream` thin-client routing planned for v0.31.2.)',
|
||||
@@ -1855,6 +1858,13 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
await runEdgesBackfill(engine, args);
|
||||
break;
|
||||
}
|
||||
case 'facts': {
|
||||
// #1867 — re-runnable fence-backfill for row_num-NULL legacy fact
|
||||
// rows (idempotent v0_32_2 phase B, exposed as an operator command).
|
||||
const { runFactsCommand } = await import('./commands/facts.ts');
|
||||
await runFactsCommand(engine, args);
|
||||
break;
|
||||
}
|
||||
case 'whoknows': {
|
||||
// v0.33 (Issue #?): expertise + relationship-proximity routing.
|
||||
// MCP op `find_experts` (read-scoped) backs the same code path; CLI
|
||||
@@ -2335,6 +2345,7 @@ TOOLS
|
||||
check-backlinks <check|fix> [dir] Find/fix missing back-links across brain
|
||||
lint <dir|file> [--fix] Catch LLM artifacts, placeholder dates, bad frontmatter
|
||||
orphans [--json] [--count] Find pages with no inbound wikilinks
|
||||
facts fence-backfill [--dry-run] Fence legacy fact rows (row_num NULL) onto entity pages
|
||||
salience [--days N] [--kind P] v0.29: pages ranked by emotional + activity salience
|
||||
anomalies [--since D] [--sigma N] v0.29: cohort-based statistical anomalies (tag, type)
|
||||
transcripts recent [--days N] v0.29: recent raw .txt transcripts (local-only)
|
||||
|
||||
@@ -0,0 +1,47 @@
|
||||
/**
|
||||
* gbrain facts — fact-store maintenance surface (#1867).
|
||||
*
|
||||
* `fence-backfill` re-runs the v0_32_2 fence-backfill phase on demand.
|
||||
* Remote `extract_facts` deposits that predate the fence-write backstop
|
||||
* (and any legacy DB-only insert) leave `row_num IS NULL` rows that the
|
||||
* cycle extract_facts guard refuses to reconcile past — previously the
|
||||
* only remedy was the one-shot v0_32_2 migration, which the ledger marks
|
||||
* complete and never re-runs. The phase is idempotent (only touches
|
||||
* `row_num IS NULL` rows), so exposing it as a command is safe to re-run
|
||||
* any time the backlog reappears.
|
||||
*/
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { phaseBFenceFacts } from './migrations/v0_32_2.ts';
|
||||
|
||||
function printHelp(): void {
|
||||
process.stderr.write(
|
||||
`Usage: gbrain facts fence-backfill [--dry-run]\n\n` +
|
||||
`Fence-backfill: appends every legacy fact row (row_num IS NULL) to its\n` +
|
||||
`entity page's \`## Facts\` fence and stamps row_num + source_markdown_slug\n` +
|
||||
`back onto the DB row. Idempotent — re-runs only pick up rows still\n` +
|
||||
`missing a fence assignment. Clears the backlog that makes the cycle's\n` +
|
||||
`extract_facts phase skip fence→DB reconciliation.\n\n` +
|
||||
` --dry-run report what would be fenced; no FS or DB writes\n`,
|
||||
);
|
||||
}
|
||||
|
||||
export async function runFactsCommand(engine: BrainEngine, args: string[]): Promise<void> {
|
||||
const sub = args[0];
|
||||
if (!sub || sub === '--help' || sub === '-h') {
|
||||
printHelp();
|
||||
return;
|
||||
}
|
||||
if (sub !== 'fence-backfill') {
|
||||
process.stderr.write(`Unknown facts subcommand: ${sub}\n`);
|
||||
printHelp();
|
||||
process.exitCode = 1;
|
||||
return;
|
||||
}
|
||||
|
||||
const dryRun = args.includes('--dry-run');
|
||||
const result = await phaseBFenceFacts(engine, { dryRun });
|
||||
process.stderr.write(
|
||||
`fence-backfill: ${result.status}${result.detail ? ` — ${result.detail}` : ''}\n`,
|
||||
);
|
||||
if (result.status === 'failed') process.exitCode = 1;
|
||||
}
|
||||
@@ -39,6 +39,7 @@ import type { BrainEngine } from '../../core/engine.ts';
|
||||
import { loadConfig, toEngineConfig } from '../../core/config.ts';
|
||||
import { createEngine } from '../../core/engine-factory.ts';
|
||||
import { upsertFactRow, parseFactsFence } from '../../core/facts-fence.ts';
|
||||
import { resolvePageFilePath } from '../../core/markdown.ts';
|
||||
|
||||
let testEngineOverride: BrainEngine | null = null;
|
||||
export function __setTestEngineOverride(engine: BrainEngine | null): void {
|
||||
@@ -148,9 +149,16 @@ function isLocalPathDirty(localPath: string): boolean {
|
||||
}
|
||||
}
|
||||
|
||||
async function phaseBFenceFacts(
|
||||
/**
|
||||
* Exported (not just via `__testing`) because `gbrain facts fence-backfill`
|
||||
* (#1867) re-runs this phase on demand: remote `extract_facts` deposits that
|
||||
* predate the fence-write backstop leave row_num-NULL rows the cycle guard
|
||||
* refuses to reconcile past. The phase is idempotent (only touches
|
||||
* `row_num IS NULL` rows), so re-running is always safe.
|
||||
*/
|
||||
export async function phaseBFenceFacts(
|
||||
engine: BrainEngine | null,
|
||||
opts: OrchestratorOpts,
|
||||
opts: Pick<OrchestratorOpts, 'dryRun'>,
|
||||
): Promise<OrchestratorPhaseResult> {
|
||||
if (opts.dryRun) {
|
||||
// Dry-run: report what WOULD happen without touching FS or DB.
|
||||
@@ -238,7 +246,11 @@ async function phaseBFenceFacts(
|
||||
for (const [key, group] of groups) {
|
||||
const [sourceId, entitySlug] = key.split('\0');
|
||||
const localPath = localPathById.get(sourceId)!;
|
||||
const filePath = join(localPath, `${entitySlug}.md`);
|
||||
// resolvePageFilePath, NOT a bare join — non-default sources fence
|
||||
// into `<local_path>/.sources/<id>/<slug>.md`, the same path the
|
||||
// fence-write backstop and put_page write-through compute. A bare
|
||||
// join here diverges fence and DB for non-default sources (#2044).
|
||||
const filePath = resolvePageFilePath(localPath, entitySlug, sourceId);
|
||||
const tmpPath = `${filePath}.tmp`;
|
||||
|
||||
try {
|
||||
@@ -381,7 +393,7 @@ async function phaseCVerify(
|
||||
for (const g of groups) {
|
||||
const localPath = localPathById.get(g.source_id);
|
||||
if (!localPath) continue;
|
||||
const filePath = join(localPath, `${g.source_markdown_slug}.md`);
|
||||
const filePath = resolvePageFilePath(localPath, g.source_markdown_slug, g.source_id);
|
||||
if (!existsSync(filePath)) {
|
||||
mismatches.push(`${g.source_markdown_slug} (file missing)`);
|
||||
continue;
|
||||
|
||||
@@ -176,9 +176,11 @@ export async function runExtractFacts(
|
||||
if (legacyCount > 0) {
|
||||
result.guardTriggered = true;
|
||||
result.warnings.push(
|
||||
`extract_facts: ${legacyCount} legacy v0.31 fact rows pending fence backfill. ` +
|
||||
`Run \`gbrain apply-migrations --yes\` to complete v0_32_2 before this phase ` +
|
||||
`can safely reconcile fence → DB.`,
|
||||
`extract_facts: ${legacyCount} legacy fact rows pending fence backfill ` +
|
||||
`(row_num IS NULL — v0.31 rows or remote extract_facts deposits that ` +
|
||||
`predate the fence backstop). Run \`gbrain facts fence-backfill\` ` +
|
||||
`(idempotent, re-runnable) before this phase can safely reconcile ` +
|
||||
`fence → DB.`,
|
||||
);
|
||||
return result;
|
||||
}
|
||||
|
||||
+7
-6
@@ -1739,13 +1739,14 @@ export interface BrainEngine {
|
||||
* single-row supersede flow because fence reconciliation is the canonical
|
||||
* source-of-truth direction, not the consolidator path.
|
||||
*
|
||||
* Insertion is atomic per call: all rows commit in a single transaction
|
||||
* or none commit (the transaction rolls back on any constraint
|
||||
* violation, e.g. the v51 partial UNIQUE index on
|
||||
* `(source_id, source_markdown_slug, row_num)`).
|
||||
* Insertion runs in a single transaction. A collision on the v51
|
||||
* partial UNIQUE index `(source_id, source_markdown_slug, row_num)`
|
||||
* skips ONLY that row (ON CONFLICT DO NOTHING, #2044) — the rest of
|
||||
* the batch still commits, so a redundant deposit against an
|
||||
* already-indexed fence row is idempotent instead of a hard failure.
|
||||
*
|
||||
* Returns the inserted ids in input-order so callers can correlate
|
||||
* fence-row → DB-id without a separate lookup.
|
||||
* Returns the inserted ids in input-order (colliding rows omitted) so
|
||||
* callers can correlate fence-row → DB-id without a separate lookup.
|
||||
*/
|
||||
insertFacts(
|
||||
rows: Array<NewFact & { row_num: number; source_markdown_slug: string }>,
|
||||
|
||||
@@ -218,11 +218,27 @@ export async function writeFactsToFence(
|
||||
}
|
||||
|
||||
// 2. Upsert each fact onto the fence in input order. row_num
|
||||
// monotonically increases (max-existing + 1 per call, append-only).
|
||||
// monotonically increases, append-only, seeded from the MAX of
|
||||
// the fence and the DB index (#2044): when fence and DB have
|
||||
// diverged (e.g. legacy writes that stamped DB rows against a
|
||||
// fence at a path this code no longer reads), fence-max+1 can
|
||||
// collide with an existing DB row_num, tripping
|
||||
// idx_facts_fence_key and rolling back the whole batch.
|
||||
const dbMaxRows = await engine.executeRaw<{ max: number | string | null }>(
|
||||
`SELECT MAX(row_num) AS max FROM facts
|
||||
WHERE source_id = $1 AND source_markdown_slug = $2`,
|
||||
[target.sourceId, target.slug],
|
||||
);
|
||||
const dbMaxRowNum = Number(dbMaxRows[0]?.max ?? 0) || 0;
|
||||
const fenceMaxRowNum = parseFactsFence(body).facts
|
||||
.reduce((m, f) => Math.max(m, f.rowNum), 0);
|
||||
let nextRowNum = Math.max(fenceMaxRowNum, dbMaxRowNum) + 1;
|
||||
|
||||
const assignedRowNums: number[] = [];
|
||||
for (const f of facts) {
|
||||
const validFromStr = (f.validFrom ?? new Date()).toISOString().slice(0, 10);
|
||||
const { body: updated, rowNum } = upsertFactRow(body, {
|
||||
rowNum: nextRowNum++,
|
||||
claim: f.fact,
|
||||
kind: (f.kind ?? 'fact') as 'fact' | 'event' | 'preference' | 'commitment' | 'belief',
|
||||
confidence: f.confidence ?? 1.0,
|
||||
|
||||
@@ -4102,11 +4102,13 @@ export class PGLiteEngine implements BrainEngine {
|
||||
): Promise<{ inserted: number; ids: number[] }> {
|
||||
if (rows.length === 0) return { inserted: 0, ids: [] };
|
||||
|
||||
// Single transaction so the v51 partial UNIQUE index can roll back the
|
||||
// whole batch on constraint violation. Per-row INSERTs (not multi-row
|
||||
// VALUES) keep the embedding-vs-no-embedding branching readable; batch
|
||||
// sizes are small (5-30 rows per page in practice) so the loop overhead
|
||||
// is negligible vs the embedding compute cost.
|
||||
// Single transaction; per-row INSERTs (not multi-row VALUES) keep the
|
||||
// embedding-vs-no-embedding branching readable; batch sizes are small
|
||||
// (5-30 rows per page in practice) so the loop overhead is negligible
|
||||
// vs the embedding compute cost. #2044: ON CONFLICT DO NOTHING on the
|
||||
// v51 partial UNIQUE index makes a residual fence/DB row_num collision
|
||||
// skip that row instead of rolling back the whole batch (parity with
|
||||
// postgres-engine.ts).
|
||||
const ids = await this.db.transaction(async (tx) => {
|
||||
const out: number[] = [];
|
||||
for (const input of rows) {
|
||||
@@ -4149,7 +4151,11 @@ export class PGLiteEngine implements BrainEngine {
|
||||
$14, $15,
|
||||
$16, $17, $18, $19,
|
||||
$20
|
||||
) RETURNING id`
|
||||
)
|
||||
ON CONFLICT (source_id, source_markdown_slug, row_num)
|
||||
WHERE row_num IS NOT NULL
|
||||
DO NOTHING
|
||||
RETURNING id`
|
||||
: `INSERT INTO facts (
|
||||
source_id, entity_slug, fact, kind, visibility, notability, context,
|
||||
valid_from, valid_until, source, source_session, confidence,
|
||||
@@ -4163,12 +4169,16 @@ export class PGLiteEngine implements BrainEngine {
|
||||
$15, $16,
|
||||
$17, $18, $19, $20,
|
||||
$21
|
||||
) RETURNING id`,
|
||||
)
|
||||
ON CONFLICT (source_id, source_markdown_slug, row_num)
|
||||
WHERE row_num IS NOT NULL
|
||||
DO NOTHING
|
||||
RETURNING id`,
|
||||
embedStr === null
|
||||
? [ctx.source_id, entitySlug, input.fact, kind, visibility, notability, context, validFrom, validUntil, input.source, sourceSession, confidence, embeddedAt, input.row_num, input.source_markdown_slug, claimMetric, claimValue, claimUnit, claimPeriod, eventType]
|
||||
: [ctx.source_id, entitySlug, input.fact, kind, visibility, notability, context, validFrom, validUntil, input.source, sourceSession, confidence, embedStr, embeddedAt, input.row_num, input.source_markdown_slug, claimMetric, claimValue, claimUnit, claimPeriod, eventType],
|
||||
);
|
||||
out.push(ins.rows[0].id);
|
||||
if (ins.rows[0]) out.push(ins.rows[0].id);
|
||||
}
|
||||
return out;
|
||||
});
|
||||
|
||||
@@ -4302,10 +4302,12 @@ export class PostgresEngine implements BrainEngine {
|
||||
// ONCE per process so the cast matches the actual column type
|
||||
// (halfvec vs vector). The probe is cached after first call.
|
||||
const castSuffix = await this.resolveFactsEmbeddingCast();
|
||||
// Single transaction so the v51 partial UNIQUE index can roll back
|
||||
// the whole batch on constraint violation. Per-row INSERTs (not
|
||||
// multi-row VALUES) keep the embedding-vs-no-embedding branching
|
||||
// readable; batch sizes are small (5-30 rows per page in practice).
|
||||
// Single transaction; per-row INSERTs (not multi-row VALUES) keep the
|
||||
// embedding-vs-no-embedding branching readable; batch sizes are small
|
||||
// (5-30 rows per page in practice). #2044: ON CONFLICT DO NOTHING on
|
||||
// the v51 partial UNIQUE index makes a residual fence/DB row_num
|
||||
// collision skip that row instead of rolling back the whole batch —
|
||||
// the fence stays system-of-record and reconciliation catches up.
|
||||
// No supersede flow in this path — fence reconciliation is the
|
||||
// canonical source-of-truth direction, not the consolidator path.
|
||||
const ids = await sql.begin(async (tx) => {
|
||||
@@ -4346,9 +4348,13 @@ export class PostgresEngine implements BrainEngine {
|
||||
${input.row_num}, ${input.source_markdown_slug},
|
||||
${claimMetric}, ${claimValue}, ${claimUnit}, ${claimPeriod},
|
||||
${eventType}
|
||||
) RETURNING id
|
||||
)
|
||||
ON CONFLICT (source_id, source_markdown_slug, row_num)
|
||||
WHERE row_num IS NOT NULL
|
||||
DO NOTHING
|
||||
RETURNING id
|
||||
`;
|
||||
out.push(Number(ins[0].id));
|
||||
if (ins[0]) out.push(Number(ins[0].id));
|
||||
}
|
||||
return out;
|
||||
});
|
||||
|
||||
@@ -304,7 +304,9 @@ describe('runExtractFacts — empty-fence guard (Codex R2-#7)', () => {
|
||||
expect(r.legacyRowsPending).toBe(1);
|
||||
expect(r.factsInserted).toBe(0);
|
||||
expect(r.factsDeleted).toBe(0);
|
||||
expect(r.warnings.some(w => w.includes('apply-migrations'))).toBe(true);
|
||||
// #1867: the remedy hint points at the re-runnable backfill command,
|
||||
// not the one-shot v0_32_2 migration (which the ledger never re-runs).
|
||||
expect(r.warnings.some(w => w.includes('gbrain facts fence-backfill'))).toBe(true);
|
||||
|
||||
// Legacy row was NOT touched.
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
|
||||
@@ -0,0 +1,102 @@
|
||||
/**
|
||||
* #1867 — `gbrain facts fence-backfill` command tests.
|
||||
*
|
||||
* The command re-runs the (idempotent) v0_32_2 phase B on demand so
|
||||
* row_num-NULL backlogs — remote extract_facts deposits that predate
|
||||
* the fence-write backstop — can be cleared without re-running the
|
||||
* one-shot migration. Real PGLite + real tempdir filesystem.
|
||||
*/
|
||||
|
||||
import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:test';
|
||||
import { mkdtempSync, rmSync, existsSync, readFileSync } from 'node:fs';
|
||||
import { tmpdir } from 'node:os';
|
||||
import { join } from 'node:path';
|
||||
|
||||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||||
import { runFactsCommand } from '../src/commands/facts.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
let brainDir: string;
|
||||
|
||||
beforeAll(async () => {
|
||||
engine = new PGLiteEngine();
|
||||
await engine.connect({});
|
||||
await engine.initSchema();
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await engine.disconnect();
|
||||
try {
|
||||
if (brainDir) rmSync(brainDir, { recursive: true, force: true });
|
||||
} catch { /* best-effort */ }
|
||||
});
|
||||
|
||||
beforeEach(async () => {
|
||||
brainDir = mkdtempSync(join(tmpdir(), 'facts-backfill-cmd-test-'));
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query('DELETE FROM facts');
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query(
|
||||
`UPDATE sources SET local_path = $1 WHERE id = 'default'`,
|
||||
[brainDir],
|
||||
);
|
||||
});
|
||||
|
||||
async function seedLegacyFact(fact: string): Promise<void> {
|
||||
// The row_num-NULL shape a remote extract_facts deposit leaves behind
|
||||
// when it lands via the legacy DB-only path.
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query(
|
||||
`INSERT INTO facts (source_id, entity_slug, fact, kind, visibility, notability,
|
||||
valid_from, source, confidence)
|
||||
VALUES ('default', 'people/alice', $1, 'fact', 'private', 'medium',
|
||||
now(), 'mcp:extract_facts', 1.0)`,
|
||||
[fact],
|
||||
);
|
||||
}
|
||||
|
||||
describe('gbrain facts fence-backfill', () => {
|
||||
test('fences row_num-NULL rows and stamps the DB', async () => {
|
||||
await seedLegacyFact('Deposited remotely');
|
||||
|
||||
await runFactsCommand(engine, ['fence-backfill']);
|
||||
|
||||
// The fence exists on disk with the claim.
|
||||
const filePath = join(brainDir, 'people/alice.md');
|
||||
expect(existsSync(filePath)).toBe(true);
|
||||
expect(readFileSync(filePath, 'utf-8')).toContain('Deposited remotely');
|
||||
|
||||
// The backlog is cleared: no row_num-NULL rows remain.
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query(
|
||||
'SELECT row_num, source_markdown_slug FROM facts',
|
||||
);
|
||||
expect(rows.rows).toHaveLength(1);
|
||||
expect(rows.rows[0].row_num).toBe(1);
|
||||
expect(rows.rows[0].source_markdown_slug).toBe('people/alice');
|
||||
});
|
||||
|
||||
test('re-run is a no-op (idempotent)', async () => {
|
||||
await seedLegacyFact('Deposited remotely');
|
||||
await runFactsCommand(engine, ['fence-backfill']);
|
||||
await runFactsCommand(engine, ['fence-backfill']);
|
||||
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query('SELECT id FROM facts');
|
||||
expect(rows.rows).toHaveLength(1);
|
||||
const body = readFileSync(join(brainDir, 'people/alice.md'), 'utf-8');
|
||||
expect(body.match(/Deposited remotely/g)).toHaveLength(1);
|
||||
});
|
||||
|
||||
test('--dry-run reports without writing', async () => {
|
||||
await seedLegacyFact('Deposited remotely');
|
||||
await runFactsCommand(engine, ['fence-backfill', '--dry-run']);
|
||||
|
||||
expect(existsSync(join(brainDir, 'people/alice.md'))).toBe(false);
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query(
|
||||
'SELECT row_num FROM facts',
|
||||
);
|
||||
expect(rows.rows[0].row_num).toBeNull();
|
||||
});
|
||||
});
|
||||
@@ -292,6 +292,49 @@ describe('lookupSourceLocalPath', () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe('writeFactsToFence — fence/DB divergence (#2044)', () => {
|
||||
test('seeds row_num past the DB max when the fence lags the DB', async () => {
|
||||
// Simulate the divergence class from #2044: DB rows were stamped with
|
||||
// row_nums against a fence written at a path this code no longer reads
|
||||
// (e.g. the pre-"Local patch 2026-06-11" wrong-path writes). The page
|
||||
// on disk has NO fence, but the DB already holds row_num 1..3 for the
|
||||
// slug. Pre-fix, the next deposit re-assigned row_num=1 from fence
|
||||
// text alone and the whole insertFacts batch failed on
|
||||
// idx_facts_fence_key.
|
||||
for (let n = 1; n <= 3; n++) {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query(
|
||||
`INSERT INTO facts (source_id, entity_slug, fact, kind, visibility, notability,
|
||||
valid_from, source, confidence, row_num, source_markdown_slug)
|
||||
VALUES ('default', 'people/dana', $1, 'fact', 'private', 'medium',
|
||||
now(), 'mcp:extract_facts', 1.0, $2, 'people/dana')`,
|
||||
[`old claim ${n}`, n],
|
||||
);
|
||||
}
|
||||
|
||||
const result = await writeFactsToFence(
|
||||
engine,
|
||||
{ sourceId: 'default', localPath: brainDir, slug: 'people/dana' },
|
||||
[baseInput({ fact: 'second deposit' })],
|
||||
);
|
||||
|
||||
expect(result.fenceWriteFailed).toBeUndefined();
|
||||
expect(result.inserted).toBe(1);
|
||||
|
||||
// The new row landed PAST the DB max, not at fence-max+1 (= 1).
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query(
|
||||
'SELECT row_num FROM facts WHERE id = $1',
|
||||
[result.ids[0]],
|
||||
);
|
||||
expect(rows.rows[0].row_num).toBe(4);
|
||||
|
||||
// And the on-disk fence carries the same row_num — fence and DB agree.
|
||||
const body = readFileSync(join(brainDir, 'people/dana.md'), 'utf-8');
|
||||
expect(body).toContain('| 4 | second deposit |');
|
||||
});
|
||||
});
|
||||
|
||||
// Cleanup any leftover tempdirs after the whole suite.
|
||||
afterAll(() => {
|
||||
// No-op: each test cleaned up via the beforeEach; this is a safety net.
|
||||
|
||||
@@ -5,7 +5,7 @@
|
||||
* - Batch insert N rows persists row_num + source_markdown_slug
|
||||
* - Empty batch is a no-op
|
||||
* - Returns ids in input-order
|
||||
* - v51 partial UNIQUE index rolls back the whole batch on a collision
|
||||
* - v51 partial UNIQUE collision skips only the colliding row (#2044)
|
||||
* - deleteFactsForPage scopes by (source_id, source_markdown_slug);
|
||||
* never touches other pages or pre-v51 NULL-source_markdown_slug rows
|
||||
* - deleteFactsForPage on an empty page returns deleted:0 (idempotent)
|
||||
@@ -135,30 +135,29 @@ describe('engine.insertFacts — batch insert', () => {
|
||||
});
|
||||
});
|
||||
|
||||
test('v51 partial UNIQUE index rolls back the whole batch on collision', async () => {
|
||||
test('v51 partial UNIQUE collision skips ONLY the colliding row (#2044)', async () => {
|
||||
// Seed row #1 first.
|
||||
await engine.insertFacts([fixtureFact(1, { fact: 'seeded' })], { source_id: 'default' });
|
||||
|
||||
// Now try to batch-insert rows that include a colliding row_num=1.
|
||||
let threw = false;
|
||||
try {
|
||||
await engine.insertFacts(
|
||||
[
|
||||
fixtureFact(2, { fact: 'second' }),
|
||||
fixtureFact(1, { fact: 'collides' }), // row_num=1 on same (source_id, source_markdown_slug)
|
||||
fixtureFact(3, { fact: 'third' }),
|
||||
],
|
||||
{ source_id: 'default' },
|
||||
);
|
||||
} catch {
|
||||
threw = true;
|
||||
}
|
||||
expect(threw).toBe(true);
|
||||
// Batch-insert rows that include a colliding row_num=1. Pre-#2044 this
|
||||
// threw and rolled back the whole batch, making a second remote
|
||||
// extract_facts deposit to an already-fenced page a hard failure. Now
|
||||
// ON CONFLICT DO NOTHING skips the colliding row and keeps the rest.
|
||||
const result = await engine.insertFacts(
|
||||
[
|
||||
fixtureFact(2, { fact: 'second' }),
|
||||
fixtureFact(1, { fact: 'collides' }), // row_num=1 on same (source_id, source_markdown_slug)
|
||||
fixtureFact(3, { fact: 'third' }),
|
||||
],
|
||||
{ source_id: 'default' },
|
||||
);
|
||||
expect(result.inserted).toBe(2);
|
||||
expect(result.ids).toHaveLength(2);
|
||||
|
||||
// Verify the transaction rolled back — only the seeded row should remain.
|
||||
// The seeded row survives untouched; the colliding claim is skipped.
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query('SELECT fact FROM facts ORDER BY id');
|
||||
expect(rows.rows.map((r: { fact: string }) => r.fact)).toEqual(['seeded']);
|
||||
expect(rows.rows.map((r: { fact: string }) => r.fact)).toEqual(['seeded', 'second', 'third']);
|
||||
});
|
||||
|
||||
test('different source_markdown_slug values DO NOT collide on the same row_num', async () => {
|
||||
|
||||
Reference in New Issue
Block a user