mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 22:15:33 +00:00
fix(doctor): distinguish entity timeline coverage from whole-brain density (#2761)
Issue #2298: 'gbrain doctor' surfaced two distinct timeline metrics under the same user-facing 'timeline' label: 1. Entity timeline coverage (graph_coverage metric) - numerator: eligible entity pages WITH a timeline entry - denominator: eligible entity pages - 0-1 fraction, surfaced by graph_coverage check 2. Whole-brain timeline density (brain-score 0-15 component) - numerator: all pages WITH a timeline entry - denominator: all pages - 0-15 scale, surfaced by brain_score breakdown These have DIFFERENT numerators/denominators. The old single 'timeline X%' label let a reader mistake the entity-scoped percentage for whole-brain density. Presentation/contract clarity only — scoring formula, health weights, takes, source routing, extraction UNCHANGED. - doctor.ts graph_coverage: 'timeline X%' -> 'entity timeline coverage X%' - doctor.ts brain_score: 'timeline X/15' -> 'timeline density (all pages) X/15' - cli.ts get_health: 'Timeline coverage (entity pages)' -> 'Timeline density (all pages): X/15 (whole-brain brain-score component)' Test: test/doctor-timeline-metric-labels-2298.test.ts uses a synthetic in-memory PGLite fixture (NO private EriadorMu data): 4 total pages, 2 eligible entity pages, 1 entity page with a timeline entry, 1 total page with a timeline entry. Expected: entity coverage 1/2 = 50%; whole-brain density 1/4 -> round(25% * 15) = 4/15. Asserts the two metrics render with distinct scoped labels and the brain-score component is explicitly whole-brain (no 'entity' in its label). 5/5 pass. Addresses #2298
This commit is contained in:
+4
-1
@@ -937,7 +937,10 @@ 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): ${h.timeline_coverage_score}/15 (whole-brain brain-score component)`);
|
||||
}
|
||||
if (Array.isArray(h.most_connected) && h.most_connected.length > 0) {
|
||||
lines.push('Most connected entities:');
|
||||
|
||||
@@ -6011,12 +6011,12 @@ export async function buildChecks(
|
||||
message: `Only code/test fixture entity pages found (${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`,
|
||||
});
|
||||
}
|
||||
|
||||
@@ -6028,7 +6028,7 @@ 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`,
|
||||
];
|
||||
|
||||
@@ -0,0 +1,155 @@
|
||||
/**
|
||||
* Issue #2298 — timeline metric presentation contract.
|
||||
*
|
||||
* Authoritative upstream semantics (src/core/types.ts):
|
||||
* - Metric A `timeline_coverage` (entity-scoped, fraction 0–1):
|
||||
* 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, 0–15 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');
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user