fix(facts): seed phase B backfill row_nums past the DB max (#2044 class)

phaseBFenceFacts appended at fence-max+1 with no DB seeding, so on a
diverged page (stamped DB rows + missing fence at the resolved path —
the same divergence class the writeFactsToFence fix handles) the
post-rename UPDATE hit idx_facts_fence_key, the page failed, and the
already-renamed fence disagreed with the DB while the row_num-NULL
backlog persisted. Seed appended row_nums from MAX(fence max, DB max)
per (source_id, slug), mirroring the fence-write fix. Repro test added.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-07-22 11:46:22 -07:00
co-authored by Claude Fable 5
parent 039b97df36
commit 52fffc7ecc
2 changed files with 47 additions and 0 deletions
+16
View File
@@ -281,6 +281,21 @@ export async function phaseBFenceFacts(
const existingFence = parseFactsFence(body);
const existingKeySet = new Set(existingFence.facts.map(f => `${f.claim}\0${f.source ?? ''}`));
// Seed appended row_nums from MAX(fence max, DB max) — same #2044
// divergence guard as writeFactsToFence. When the fence at the
// resolved path is missing/behind but the DB already holds stamped
// rows for this slug (legacy wrong-path fence writes), fence-max+1
// collides with idx_facts_fence_key on the post-rename UPDATE,
// failing the page and leaving fence and DB disagreeing.
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 = $2`,
[sourceId, entitySlug],
);
const dbMaxRowNum = Number(dbMaxRows[0]?.max ?? 0) || 0;
const fenceMaxRowNum = existingFence.facts.reduce((m, f) => Math.max(m, f.rowNum), 0);
let nextRowNum = Math.max(fenceMaxRowNum, dbMaxRowNum) + 1;
const assignments: Array<{ id: string; row_num: number }> = [];
for (const row of group) {
const key = `${row.fact}\0${row.source ?? ''}`;
@@ -303,6 +318,7 @@ export async function phaseBFenceFacts(
.toISOString().slice(0, 10)
: undefined;
const { body: updated, rowNum } = upsertFactRow(body, {
rowNum: nextRowNum++,
claim: row.fact,
kind: row.kind,
confidence: row.confidence,
+31
View File
@@ -14,6 +14,7 @@ import { join } from 'node:path';
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
import { runFactsCommand } from '../src/commands/facts.ts';
import { phaseBFenceFacts } from '../src/commands/migrations/v0_32_2.ts';
let engine: PGLiteEngine;
let brainDir: string;
@@ -99,4 +100,34 @@ describe('gbrain facts fence-backfill', () => {
);
expect(rows.rows[0].row_num).toBeNull();
});
test('diverged page: appends past the DB row_num max instead of colliding (#2044 class)', async () => {
// The #2044 divergence shape the backfill must survive: the DB already
// holds stamped rows 1..3 for the slug (legacy wrong-path fence write),
// but the fence at the resolved path is missing. Fence-max+1 (= 1) would
// collide with the stamped rows on the post-rename UPDATE, failing the
// page and leaving the renamed fence disagreeing with the DB.
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/alice', $1, 'fact', 'private', 'medium',
now(), 'mcp:extract_facts', 1.0, $2, 'people/alice')`,
[`stamped ${n}`, n],
);
}
await seedLegacyFact('Deposited remotely');
const result = await phaseBFenceFacts(engine, { dryRun: false });
expect(result.status).toBe('complete');
// eslint-disable-next-line @typescript-eslint/no-explicit-any
const rows = await (engine as any).db.query(
`SELECT row_num FROM facts WHERE fact = 'Deposited remotely'`,
);
expect(rows.rows[0].row_num).toBe(4);
const body = readFileSync(join(brainDir, 'people/alice.md'), 'utf-8');
expect(body).toContain('| 4 | Deposited remotely |');
});
});