Compare commits

..
Author SHA1 Message Date
b05ebf6e4a fix(doctor): scope timeline labels to disambiguate entity coverage vs brain-score component (#2298)
doctor and the get_health CLI surface printed two different timeline
metrics under one ambiguous 'timeline' label: the entity-scoped
timeline_coverage fraction (eligible entity pages with a timeline entry)
and the whole-brain timeline_coverage_score brain-score component (all
pages with a timeline entry, 0-15). Different numerators AND
denominators, indistinguishable in output.

Label-only fix, scoring unchanged:
- graph_coverage check: 'entity timeline coverage N%'
- brain_score breakdown: 'timeline density (all pages) N/15'
- get_health CLI: 'Timeline coverage (entity pages)' plus a new
  'Timeline density (all pages): N/15' line when the score is present

Adds test/doctor-timeline-metric-labels-2298.test.ts pinning the
denominator semantics, the rendered doctor messages, and the CLI
guard matrix (fails on master, passes here).

Takeover of #2761.

Co-authored-by: TurgutKural <TurgutKural@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:18:54 -07:00
8 changed files with 174 additions and 137 deletions
+5 -8
View File
@@ -21,17 +21,14 @@ GBrain is tuned for the Supabase **Transaction pooler** (port 6543): it
auto-disables prepared statements there and routes `engine.transaction()`
(migrations, DDL, sync imports) to a derived **direct** connection
(`db.<ref>.supabase.co:5432`). That direct host is IPv6-only, so on an
IPv4-only host it is unreachable. When that happens gbrain now falls back to
the pooler automatically (one stderr warning, then single-pool mode for the
rest of the process) — but the pooler's ~2-min statement timeout can truncate
very long migrations or bulk imports.
IPv4-only host, reads work but sync **silently skips most pages**. This is the
number one cause of "sync ran but nothing happened."
Fix: make the direct connection reachable over IPv4. Either set
`GBRAIN_DIRECT_DATABASE_URL` to the **Session pooler** string (port 5432 on the
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on.
`GBRAIN_DISABLE_DIRECT_POOL=1` skips the direct pool (and the fallback warning)
entirely. Verify by running `gbrain sync` and checking that the page count in
`gbrain stats` matches the syncable file count in the repo.
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on. Verify by
running `gbrain sync` and checking that the page count in `gbrain stats` matches
the syncable file count in the repo.
### The Primitives
+5 -8
View File
@@ -2720,17 +2720,14 @@ GBrain is tuned for the Supabase **Transaction pooler** (port 6543): it
auto-disables prepared statements there and routes `engine.transaction()`
(migrations, DDL, sync imports) to a derived **direct** connection
(`db.<ref>.supabase.co:5432`). That direct host is IPv6-only, so on an
IPv4-only host it is unreachable. When that happens gbrain now falls back to
the pooler automatically (one stderr warning, then single-pool mode for the
rest of the process) — but the pooler's ~2-min statement timeout can truncate
very long migrations or bulk imports.
IPv4-only host, reads work but sync **silently skips most pages**. This is the
number one cause of "sync ran but nothing happened."
Fix: make the direct connection reachable over IPv4. Either set
`GBRAIN_DIRECT_DATABASE_URL` to the **Session pooler** string (port 5432 on the
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on.
`GBRAIN_DISABLE_DIRECT_POOL=1` skips the direct pool (and the fallback warning)
entirely. Verify by running `gbrain sync` and checking that the page count in
`gbrain stats` matches the syncable file count in the repo.
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on. Verify by
running `gbrain sync` and checking that the page count in `gbrain stats` matches
the syncable file count in the repo.
### The Primitives
+4 -1
View File
@@ -935,7 +935,10 @@ export function formatResult(opName: string, result: unknown): string {
lines.push(`Link coverage (entities): ${(h.link_coverage * 100).toFixed(1)}%`);
}
if (h.timeline_coverage !== undefined) {
lines.push(`Timeline coverage (entities): ${(h.timeline_coverage * 100).toFixed(1)}%`);
lines.push(`Timeline coverage (entity pages): ${(h.timeline_coverage * 100).toFixed(1)}%`);
}
if (h.timeline_coverage_score !== undefined) {
lines.push(`Timeline density (all pages): ${h.timeline_coverage_score}/15 (whole-brain brain-score component)`);
}
if (Array.isArray(h.most_connected) && h.most_connected.length > 0) {
lines.push('Most connected entities:');
+3 -3
View File
@@ -5868,12 +5868,12 @@ export async function buildChecks(
message: `Only code/test fixture entity pages found (${entityCount}); graph_coverage not applicable`,
});
} else if (linkCoverage >= 0.5 && timelineCoverage >= 0.5) {
checks.push({ name: 'graph_coverage', status: 'ok', message: `Entity link coverage ${linkPct}%, timeline ${timelinePct}%` });
checks.push({ name: 'graph_coverage', status: 'ok', message: `Entity link coverage ${linkPct}%, entity timeline coverage ${timelinePct}%` });
} else {
checks.push({
name: 'graph_coverage',
status: 'warn',
message: `Entity link coverage ${linkPct}%, timeline ${timelinePct}% (${eligibleEntityCount} entity pages). Run: gbrain extract all`,
message: `Entity link coverage ${linkPct}%, entity timeline coverage ${timelinePct}% (${eligibleEntityCount} entity pages). Run: gbrain extract all`,
});
}
@@ -5885,7 +5885,7 @@ export async function buildChecks(
const parts = [
`embed ${health.embed_coverage_score}/35`,
`links ${health.link_density_score}/25`,
`timeline ${health.timeline_coverage_score}/15`,
`timeline density (all pages) ${health.timeline_coverage_score}/15`,
`orphans ${health.no_orphans_score}/15`,
`dead-links ${health.no_dead_links_score}/10`,
];
-6
View File
@@ -1078,9 +1078,6 @@ async function initPostgres(opts: {
console.warn(' Direct connections are IPv6 only and fail in many environments.');
console.warn(' Use the Transaction pooler connection string instead (port 6543):');
console.warn(' Supabase Dashboard > Connect (top bar) > Connection String > Transaction pooler');
console.warn(' (With a pooler URL, gbrain derives a direct connection for DDL and falls back');
console.warn(' to the pooler automatically if that host is unreachable. Power users:');
console.warn(' GBRAIN_DIRECT_DATABASE_URL overrides the derived URL; GBRAIN_DISABLE_DIRECT_POOL=1 disables it.)');
console.warn('');
}
@@ -1094,9 +1091,6 @@ async function initPostgres(opts: {
if (databaseUrl.includes('supabase.co') && (msg.includes('ECONNREFUSED') || msg.includes('ETIMEDOUT'))) {
console.error('Connection failed. Supabase direct connections (db.*.supabase.co:5432) are IPv6 only.');
console.error('Use the Transaction pooler connection string instead (port 6543).');
console.error('(gbrain derives its own direct connection from pooler URLs for DDL; if that host is');
console.error('unreachable it falls back to the pooler. GBRAIN_DIRECT_DATABASE_URL overrides the');
console.error('derived URL; GBRAIN_DISABLE_DIRECT_POOL=1 disables the direct pool entirely.)');
}
throw e;
}
+2 -48
View File
@@ -167,25 +167,6 @@ export function deriveDirectUrl(url: string): string | null {
}
}
/**
* Error codes that mean "the direct host is unreachable from this network"
* (#1641). The auto-derived db.<ref>.supabase.co host is IPv6-only without
* the paid IPv4 add-on, so ENOTFOUND/ECONNREFUSED here is expected on
* IPv4-only networks — we fall back to the pooler instead of failing init.
*/
const NETWORK_UNREACHABLE_CODES = [
'ENOTFOUND', 'ECONNREFUSED', 'ENETUNREACH', 'EHOSTUNREACH',
'ETIMEDOUT', 'CONNECT_TIMEOUT',
];
/** True when err looks like a network-unreachable failure (not auth/SQL). */
export function isNetworkUnreachableError(err: unknown): boolean {
const code = (err as { code?: unknown } | null)?.code;
if (typeof code === 'string' && NETWORK_UNREACHABLE_CODES.includes(code)) return true;
const msg = err instanceof Error ? err.message : String(err);
return NETWORK_UNREACHABLE_CODES.some(c => msg.includes(c));
}
/**
* Read kill-switch state from env. Subordinate to parent manager's state
* when present (A2 inheritance).
@@ -338,30 +319,7 @@ export class ConnectionManager {
throw err;
});
}
let pool: Sql | null;
try {
pool = await this._directInit;
} catch (err) {
// #1641: the derived direct host (db.<ref>.supabase.co) is IPv6-only
// without Supabase's IPv4 add-on. On IPv4-only networks the direct
// pool can never connect — permanently fall back to the read pool
// (self-activating kill-switch) instead of failing init/migrations.
// Non-network errors (auth, SQL) still throw: they mean misconfig,
// not unreachability.
if (isNetworkUnreachableError(err)) {
const alreadyWarned = this._killSwitch;
this._killSwitch = true;
const msg = err instanceof Error ? err.message : String(err);
if (!alreadyWarned) console.error(
`gbrain: direct connection to ${this._directUrl ? this.hostOnly(this._directUrl) : 'unknown host'} unreachable (${msg}); ` +
'falling back to the pooler for DDL/bulk (long migrations may hit the pooler statement timeout). ' +
'Set GBRAIN_DIRECT_DATABASE_URL to a reachable direct URL (e.g. the Session pooler, port 5432) or enable the Supabase IPv4 add-on; ' +
'GBRAIN_DISABLE_DIRECT_POOL=1 silences this.',
);
return this.getReadPool();
}
throw err;
}
const pool = await this._directInit;
if (!pool) {
// Defensive — initDirectPool should have thrown.
throw new Error('connection-manager: direct pool init returned null');
@@ -392,9 +350,8 @@ export class ConnectionManager {
},
};
const t0 = Date.now();
let pool: Sql | null = null;
try {
pool = postgres(this._directUrl, opts);
const pool = postgres(this._directUrl, opts);
// Probe to validate connectivity early.
await pool`SELECT 1`;
logConnectionEvent({
@@ -405,9 +362,6 @@ export class ConnectionManager {
});
return pool;
} catch (err) {
// Don't leak the failed pool's sockets/timers (#1641 fallback keeps
// the process running afterward).
if (pool) await endPoolBounded(pool);
logConnectionEvent({
pool: 'ddl',
op: 'error',
-63
View File
@@ -3,7 +3,6 @@ import {
isSupabasePoolerUrl,
deriveDirectUrl,
readKillSwitchEnv,
isNetworkUnreachableError,
resolveDirectPoolSize,
ConnectionManager,
DEFAULT_DIRECT_POOL_SIZE,
@@ -239,65 +238,3 @@ describe('ConnectionManager — parent inheritance (A2)', () => {
}
});
});
describe('isNetworkUnreachableError (#1641)', () => {
test('classifies network codes as unreachable', () => {
for (const code of ['ENOTFOUND', 'ECONNREFUSED', 'ENETUNREACH', 'EHOSTUNREACH', 'ETIMEDOUT', 'CONNECT_TIMEOUT']) {
const err = Object.assign(new Error('connect failed'), { code });
expect(isNetworkUnreachableError(err)).toBe(true);
}
});
test('classifies by message when code absent', () => {
expect(isNetworkUnreachableError(new Error('getaddrinfo ENOTFOUND db.abc.supabase.co'))).toBe(true);
});
test('auth/SQL errors are NOT unreachable', () => {
expect(isNetworkUnreachableError(new Error('password authentication failed for user "postgres"'))).toBe(false);
expect(isNetworkUnreachableError(new Error('syntax error at or near "SELEC"'))).toBe(false);
expect(isNetworkUnreachableError(null)).toBe(false);
});
});
describe('ConnectionManager — direct-pool fallback on unreachable host (#1641)', () => {
let originalKillSwitch: string | undefined;
let originalError: typeof console.error;
let errLines: string[];
beforeEach(() => {
originalKillSwitch = process.env.GBRAIN_DISABLE_DIRECT_POOL;
delete process.env.GBRAIN_DISABLE_DIRECT_POOL;
originalError = console.error;
errLines = [];
console.error = (...args: unknown[]) => { errLines.push(args.join(' ')); };
});
afterEach(() => {
console.error = originalError;
if (originalKillSwitch === undefined) delete process.env.GBRAIN_DISABLE_DIRECT_POOL;
else process.env.GBRAIN_DISABLE_DIRECT_POOL = originalKillSwitch;
});
test('ddl() falls back to the read pool when the direct host is unreachable', async () => {
const cm = new ConnectionManager({
url: 'postgresql://postgres.abc:p@aws.pooler.supabase.com:6543/db',
// 127.0.0.1:9 (discard) → instant ECONNREFUSED, the IPv4-only-network shape.
directUrl: 'postgresql://postgres:p@127.0.0.1:9/db',
});
const fakeReadPool = {} as ReturnType<typeof ConnectionManager.prototype.read>;
cm.setReadPool(fakeReadPool);
expect(cm.isDualPoolActive()).toBe(true);
const pool = await cm.ddl(); // without the fix this throws ECONNREFUSED
expect(pool).toBe(fakeReadPool);
// Self-activating kill-switch: subsequent calls skip the direct pool.
expect(cm.isKillSwitchActive()).toBe(true);
expect(cm.isDualPoolActive()).toBe(false);
expect(cm.describeMode().mode).toBe('single (kill-switch)');
// One stderr line mentioning the power-user override.
const warning = errLines.filter(l => l.includes('GBRAIN_DIRECT_DATABASE_URL'));
expect(warning.length).toBe(1);
const again = await cm.ddl();
expect(again).toBe(fakeReadPool);
expect(errLines.filter(l => l.includes('GBRAIN_DIRECT_DATABASE_URL')).length).toBe(1);
}, 20000);
});
@@ -0,0 +1,155 @@
/**
* Issue #2298 — timeline metric presentation contract.
*
* Authoritative upstream semantics (src/core/types.ts):
* - Metric A `timeline_coverage` (entity-scoped, fraction 01):
* eligible entity pages WITH a timeline entry / eligible entity pages
* -> surfaced by `graph_coverage` check AND `get_health` CLI entity line.
* - Metric B `timeline_coverage_score` (whole-brain, 015 brain-score component):
* all pages WITH a timeline entry / all pages
* -> surfaced by `brain_score` component breakdown AND (separately) CLI.
*
* The two have DIFFERENT numerators/denominators. This PR labels each
* explicitly and keeps BOTH the entity CLI line and the whole-brain line.
*
* Tests (no private EriadorMu data, no production/home DB, no network):
* - numeric denominator assertions (Metric A = 50%, Metric B = 4/15)
* - doctor rendered-message assertions (exact labels, no ambiguous old label)
* - CLI rendered-output assertions (exact lines, guard matrix)
* - red/green: same assertions FAIL on origin/master, PASS on this branch
*
* Scoring formula UNCHANGED. Canonical PGLite fixture via resetPgliteState.
*/
import { describe, expect, test, beforeAll, afterAll, beforeEach } from 'bun:test';
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
import { sqlQueryForEngine } from '../src/core/sql-query.ts';
import { resetPgliteState } from './helpers/reset-pglite.ts';
import { buildChecks } from '../src/commands/doctor.ts';
import { formatResult } from '../src/cli.ts';
let engine: PGLiteEngine;
async function seedFourPages(eng: PGLiteEngine): Promise<void> {
const sql = sqlQueryForEngine(eng);
// 2 eligible entity pages, 2 technical/non-entity pages.
// Only ONE entity page has a timeline entry; only ONE total page does.
await sql`
INSERT INTO pages (slug, source_id, type, title, compiled_truth, frontmatter, content_hash, created_at, updated_at)
VALUES
('acme-example', 'default', 'company', 'Acme', '', '{}', 'h1', now(), now()),
('alice-example', 'default', 'person', 'Alice', '', '{}', 'h2', now(), now()),
('technical-a', 'default', 'note', 'Tech A', '', '{}', 'h3', now(), now()),
('technical-b', 'default', 'note', 'Tech B', '', '{}', 'h4', now(), now())
`;
const companyId = (await sql`SELECT id FROM pages WHERE slug='acme-example'`)[0].id as number;
await sql`INSERT INTO timeline_entries (page_id, date, source, summary, detail)
VALUES (${companyId}, CURRENT_DATE, 'test', 'milestone', '{}')`;
}
beforeAll(async () => {
engine = new PGLiteEngine();
await engine.connect({});
await engine.initSchema();
});
afterAll(async () => {
await engine.disconnect();
});
beforeEach(async () => {
await resetPgliteState(engine);
});
describe('issue #2298 — numeric denominator semantics', () => {
test('entity timeline coverage = 1/2 = 50% (2 eligible entities, 1 with timeline)', async () => {
await seedFourPages(engine);
const health = await engine.getHealth();
expect(health.timeline_coverage).toBeDefined();
expect(Math.round((health.timeline_coverage ?? 0) * 100)).toBe(50);
});
test('whole-brain timeline density = 1/4 -> score 4/15 (4 total pages, 1 with timeline)', async () => {
await seedFourPages(engine);
const health = await engine.getHealth();
expect(health.timeline_coverage_score).toBeDefined();
expect(health.timeline_coverage_score).toBe(4);
});
test('the two metrics use independent denominators', async () => {
await seedFourPages(engine);
const health = await engine.getHealth();
expect(Math.round((health.timeline_coverage ?? 0) * 100)).toBe(50);
expect(health.timeline_coverage_score ?? 0).toBe(4);
// 50% (entity, /2) != 26.7% (whole-brain, /4). Provably distinct.
expect(Math.round(((health.timeline_coverage_score ?? 0) / 15) * 100)).not.toBe(50);
});
});
describe('issue #2298 — doctor rendered-message contract', () => {
test('graph_coverage renders entity-scoped label with 50%', async () => {
await seedFourPages(engine);
const checks = await buildChecks(engine, [], null);
const graph = checks.find((c) => c.name === 'graph_coverage');
expect(graph, 'graph_coverage check must be present').toBeDefined();
expect(graph!.message).toContain('entity timeline coverage 50%');
// ambiguous old label must NOT be present
expect(graph!.message).not.toMatch(/timeline 50%/);
expect(graph!.message).not.toMatch(/timeline \(entity, brain score\)/);
});
test('brain_score renders whole-brain density label 4/15', async () => {
await seedFourPages(engine);
const checks = await buildChecks(engine, [], null);
const brain = checks.find((c) => c.name === 'brain_score');
expect(brain, 'brain_score check must be present').toBeDefined();
expect(brain!.message).toContain('timeline density (all pages) 4/15');
// wrong labels must NOT be present
expect(brain!.message).not.toMatch(/timeline 4\/15/);
expect(brain!.message).not.toMatch(/timeline \(entity, brain score\)/);
// brain-score component must NOT carry the word "entity" (it is whole-brain)
const timelinePart = brain!.message.split('timeline density (all pages) 4/15')[0] + 'timeline density (all pages) 4/15';
expect(timelinePart).not.toMatch(/entity/);
});
});
describe('issue #2298 — CLI get_health rendered-output contract', () => {
function fakeHealth(overrides: Record<string, unknown>): any {
return {
embed_coverage: 1, missing_embeddings: 0, stale_pages: 0, orphan_pages: 0,
link_coverage: 1, timeline_coverage: 0.5, timeline_coverage_score: 4,
most_connected: [], ...overrides,
};
}
test('both entity and whole-brain lines render, no undefined/15', () => {
const out = formatResult('get_health', fakeHealth({}));
expect(out).toContain('Timeline coverage (entity pages): 50.0%');
expect(out).toContain('Timeline density (all pages): 4/15');
expect(out).not.toContain('undefined/15');
expect(out).not.toContain('Timeline coverage (entities)');
expect(out).not.toMatch(/timeline \(entity, brain score\)/);
expect(out).not.toMatch(/bare "timeline 4\/15"/);
});
test('guard matrix: entity present, whole-brain absent -> only entity line', () => {
const out = formatResult('get_health', fakeHealth({ timeline_coverage_score: undefined }));
expect(out).toContain('Timeline coverage (entity pages): 50.0%');
expect(out).not.toContain('Timeline density (all pages)');
expect(out).not.toContain('undefined/15');
});
test('guard matrix: whole-brain present, entity absent -> only whole-brain line', () => {
const out = formatResult('get_health', fakeHealth({ timeline_coverage: undefined }));
expect(out).toContain('Timeline density (all pages): 4/15');
expect(out).not.toContain('Timeline coverage (entity pages)');
expect(out).not.toContain('undefined/15');
});
test('guard matrix: both absent -> neither timeline line, never undefined/15', () => {
const out = formatResult('get_health', fakeHealth({ timeline_coverage: undefined, timeline_coverage_score: undefined }));
expect(out).not.toContain('Timeline coverage (entity pages)');
expect(out).not.toContain('Timeline density (all pages)');
expect(out).not.toContain('undefined/15');
});
});