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
6 changed files with 168 additions and 94 deletions
+5 -2
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): ${h.timeline_coverage_score}/15 (whole-brain brain-score component)`);
}
if (Array.isArray(h.most_connected) && h.most_connected.length > 0) {
lines.push('Most connected entities:');
@@ -2387,7 +2390,7 @@ JOBS (Minions)
jobs get <id> Job details + history
jobs cancel <id> Cancel job
jobs retry <id> Re-queue failed/dead job
jobs prune [--older-than 30d] [--status s,..] Clean old terminal jobs (0d = no age floor)
jobs prune [--older-than 30d] Clean old jobs
jobs stats Job health dashboard
jobs work [--queue Q] Start worker daemon (Postgres only)
+3 -3
View File
@@ -5868,12 +5868,12 @@ export async function buildChecks(
message: `Only code/test fixture entity pages found (${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 ${health.no_dead_links_score}/10`,
];
+5 -33
View File
@@ -106,21 +106,6 @@ export function parseMaxRssFlag(args: string[]): number | undefined {
return parsed;
}
/** Terminal statuses `jobs prune --status` accepts (PR #2282). Matches what
* queue.prune can safely delete; anything else (waiting/active/…) is live. */
export const PRUNE_STATUSES = ['completed', 'failed', 'dead', 'cancelled'] as const satisfies readonly MinionJobStatus[];
/** Parse a `--status a,b,c` value into prune statuses. Throws on any value
* outside PRUNE_STATUSES (fail-fast, mirrors parseNiceValue). */
export function parsePruneStatuses(raw: string): MinionJobStatus[] {
const requested = raw.split(',').map(s => s.trim()).filter(Boolean);
const invalid = requested.filter(s => !(PRUNE_STATUSES as readonly string[]).includes(s));
if (requested.length === 0 || invalid.length > 0) {
throw new Error(`--status accepts a comma-separated subset of [${PRUNE_STATUSES.join(', ')}]${invalid.length ? `. Invalid: ${invalid.join(', ')}` : ''}`);
}
return requested as MinionJobStatus[];
}
/** Parse `--nice N` (then `GBRAIN_NICE` env). Returns:
* - undefined if absent (no priority change — inherit)
* - the validated integer in [-20, 19] otherwise
@@ -223,9 +208,7 @@ USAGE
gbrain jobs get <id>
gbrain jobs cancel <id>
gbrain jobs retry <id>
gbrain jobs prune [--older-than 30d] [--status completed,failed,dead,cancelled]
(--older-than 0d = no age floor: deletes ALL
matching terminal jobs; pair with --status)
gbrain jobs prune [--older-than 30d]
gbrain jobs delete <id>
gbrain jobs stats
gbrain jobs smoke
@@ -617,27 +600,16 @@ HANDLER TYPES (built in)
case 'prune': {
const olderThanStr = parseFlag(args, '--older-than') ?? '30d';
const days = parseInt(olderThanStr, 10);
if (isNaN(days) || days < 0) {
console.error('Error: --older-than must be a non-negative number (days). Example: --older-than 30d; --older-than 0d removes the age floor (deletes ALL matching terminal jobs).');
if (isNaN(days) || days <= 0) {
console.error('Error: --older-than must be a positive number (days). Example: --older-than 30d');
process.exit(1);
}
const statusFlag = parseFlag(args, '--status');
let statuses: MinionJobStatus[] | undefined;
if (statusFlag !== undefined) {
try { statuses = parsePruneStatuses(statusFlag); }
catch (e) { console.error(`Error: ${e instanceof Error ? e.message : String(e)}`); process.exit(1); }
}
try { await queue.ensureSchema(); }
catch (e) { console.error(e instanceof Error ? e.message : String(e)); process.exit(1); }
const count = await queue.prune({
olderThan: new Date(Date.now() - days * 86400000),
...(statuses ? { status: statuses } : {}),
});
const statusLabel = statuses ? statuses.join('+') : 'completed+dead+cancelled';
const ageLabel = days === 0 ? 'regardless of age' : `older than ${days} days`;
console.log(`Pruned ${count} ${statusLabel} jobs ${ageLabel}.`);
const count = await queue.prune({ olderThan: new Date(Date.now() - days * 86400000) });
console.log(`Pruned ${count} jobs older than ${days} days.`);
break;
}
@@ -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');
});
});
-30
View File
@@ -1,30 +0,0 @@
/**
* Unit tests for parsePruneStatuses (PR #2282) — `jobs prune --status` parsing.
*/
import { describe, test, expect } from 'bun:test';
import { parsePruneStatuses, PRUNE_STATUSES } from '../src/commands/jobs.ts';
describe('parsePruneStatuses', () => {
test('parses a single status', () => {
expect(parsePruneStatuses('failed')).toEqual(['failed']);
});
test('parses a comma-separated list with whitespace', () => {
expect(parsePruneStatuses(' completed, dead ')).toEqual(['completed', 'dead']);
});
test('accepts every documented terminal status', () => {
expect(parsePruneStatuses(PRUNE_STATUSES.join(','))).toEqual([...PRUNE_STATUSES]);
});
test('throws on non-terminal statuses', () => {
expect(() => parsePruneStatuses('waiting')).toThrow(/Invalid: waiting/);
expect(() => parsePruneStatuses('completed,active')).toThrow(/Invalid: active/);
});
test('throws on empty value', () => {
expect(() => parsePruneStatuses('')).toThrow(/comma-separated subset/);
expect(() => parsePruneStatuses(',')).toThrow(/comma-separated subset/);
});
});
-26
View File
@@ -702,32 +702,6 @@ describe('MinionQueue: Prune', () => {
const count = await queue.prune({ olderThan: new Date(Date.now() + 86400000) }); // future date = prune everything old enough
expect(count).toBe(1); // only the cancelled one
});
// PR #2282: `jobs prune --status` passes an explicit status subset through.
test('status filter prunes only the requested terminal statuses', async () => {
const cancelled = await queue.add('sync', {});
await queue.cancelJob(cancelled.id);
const dead = await queue.add('embed', {}, { max_attempts: 1 });
await queue.claim('tok1', 30000, 'default', ['embed']);
await queue.failJob(dead.id, 'tok1', 'boom', 'dead');
const count = await queue.prune({ olderThan: new Date(Date.now() + 86400000), status: ['dead'] });
expect(count).toBe(1); // only the dead one
const remaining = await queue.getJobs({ status: 'cancelled' });
expect(remaining.length).toBe(1);
});
// PR #2282: `--older-than 0d` = no age floor — olderThan of "now" deletes
// terminal jobs that finished moments ago.
test('olderThan now (0d semantics) prunes just-terminated jobs', async () => {
const job = await queue.add('sync', {});
await queue.cancelJob(job.id);
await new Promise(r => setTimeout(r, 5)); // ensure updated_at < now
const count = await queue.prune({ olderThan: new Date() });
expect(count).toBe(1);
});
});
// --- Stats (1 test) ---