Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 3fa01a4538 fix(cycle): ambiguous local_path resolves no source — don't stamp an arbitrary pick
resolveSourceForDir used LIMIT 1, so when two sources share a local_path
the dir-keyed freshness stamp (new in this PR) fired for a
nondeterministic one — exactly the 'freshness stamp that lies' the
cycleSourceId comment warns against, and the CI failure in
test/dream.test.ts ('gbrain dream (no --source) leaves all sources
untouched'). Require exactly one match; ambiguous or no match falls back
to the pre-v0.18 behavior (undefined), same as before this PR for the
no-match case.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 11:06:41 -07:00
ded4aeaeae fix(cycle): stamp last_full_cycle_at for the resolved source; stale freshness forces autopilot fanout (#1993, #2060)
Two fixes to the per-source cycle freshness loop:

1. runCycle's freshness stamp now keys off cycleSourceId (opts.sourceId ??
   the source resolved from brainDir) — the same id the cycle locked and
   scoped its phases to — instead of raw opts.sourceId. The autopilot's
   inline cycle passes brainDir with no explicit sourceId, so the stamp
   never fired and cycle_freshness stayed stale forever. Keeps master's
   !aborted guard and the last_source_cycle_at write. (takeover of #1993)

2. autopilot's dispatch decision now consults per-source cycle staleness:
   countStaleSources (new pure helper in autopilot-fanout.ts) over
   listAllSources({ localPathOnly: true }). A stale source forces the
   fanout path and blocks the healthy-sleep gate, so a brain sitting at
   score 70-94 with a small targeted plan can no longer starve per-source
   cycle dispatch indefinitely. Fail-open to 0 on read errors;
   dispatchPerSource's existing throttles (skipped_fresh / fanoutMax /
   failure cooldown) bound the work. (#2060)

Tests: cycle-last-full-cycle-at gains the brainDir-resolves-source and
brainDir-matches-nothing cases (first one fails without fix 1);
autopilot-fanout unit tests cover countStaleSources; the fanout wiring
guard pins the staleCycleSources terms in shouldFullCycle/shouldSleep.

Co-authored-by: 100menotu001 <100menotu001@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:24:01 -07:00
9 changed files with 121 additions and 182 deletions
+1 -4
View File
@@ -935,10 +935,7 @@ 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 (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)`);
lines.push(`Timeline coverage (entities): ${(h.timeline_coverage * 100).toFixed(1)}%`);
}
if (Array.isArray(h.most_connected) && h.most_connected.length > 0) {
lines.push('Most connected entities:');
+12
View File
@@ -186,6 +186,18 @@ export function isSourceStale(src: SourceRow, now = Date.now(), floorMin = FULL_
return ageMin >= floorMin;
}
/**
* #2060: count sources past the per-source cycle freshness floor. Consumed
* by autopilot's dispatch decision — a stale source forces the fanout path
* even when the doctor plan is small (score 7094, plan ≤ 3, est < 300s),
* so targeted mode can't leave cycle_freshness stale indefinitely.
* dispatchPerSource's own throttles (skipped_fresh / fanoutMax / failure
* cooldown) bound the resulting work.
*/
export function countStaleSources(sources: SourceRow[], now = Date.now(), floorMin = FULL_CYCLE_FLOOR_MIN): number {
return sources.filter((s) => isSourceStale(s, now, floorMin)).length;
}
/**
* Most recent SUCCESSFUL cycle for a source. Prefers `last_source_cycle_at`
* (per-source phases, written by the split cycle) and falls back to the legacy
+16 -2
View File
@@ -901,13 +901,27 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
const FULL_CYCLE_FLOOR_MIN = 60;
const minutesSinceLastFull = (Date.now() - lastFullCycleAt) / 60000;
// #2060: stale per-source cycle freshness is a dispatch input. Without
// it, a brain sitting at score 7094 with a small targeted plan (≤3
// steps, <300s) stays in targeted mode indefinitely and no per-source
// cycle is ever dispatched — cycle_freshness never advances. A stale
// source forces the fanout path; dispatchPerSource's throttles
// (skipped_fresh / fanoutMax / failure cooldown) bound the work.
// Fail-open to 0: a read failure must not block dispatch.
let staleCycleSources = 0;
try {
const { countStaleSources } = await import('./autopilot-fanout.ts');
staleCycleSources = countStaleSources(await engine.listAllSources({ localPathOnly: true }));
} catch { /* fail-open: freshness is a dispatch hint, not a gate */ }
const shouldFullCycle =
(score >= 95 && plan.length === 0 && minutesSinceLastFull >= FULL_CYCLE_FLOOR_MIN) ||
plan.length > 3 ||
estTotal >= 300 ||
score < 70;
score < 70 ||
staleCycleSources > 0;
const shouldSleep = score >= 95 && plan.length === 0 && minutesSinceLastFull < FULL_CYCLE_FLOOR_MIN;
const shouldSleep = score >= 95 && plan.length === 0 && minutesSinceLastFull < FULL_CYCLE_FLOOR_MIN && staleCycleSources === 0;
if (shouldSleep) {
if (jsonMode) {
+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}%, entity timeline coverage ${timelinePct}%` });
checks.push({ name: 'graph_coverage', status: 'ok', message: `Entity link coverage ${linkPct}%, timeline ${timelinePct}%` });
} else {
checks.push({
name: 'graph_coverage',
status: 'warn',
message: `Entity link coverage ${linkPct}%, entity timeline coverage ${timelinePct}% (${eligibleEntityCount} entity pages). Run: gbrain extract all`,
message: `Entity link coverage ${linkPct}%, timeline ${timelinePct}% (${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 density (all pages) ${health.timeline_coverage_score}/15`,
`timeline ${health.timeline_coverage_score}/15`,
`orphans ${health.no_orphans_score}/15`,
`dead-links ${health.no_dead_links_score}/10`,
];
+19 -10
View File
@@ -854,7 +854,10 @@ interface SyncPhaseResult extends PhaseResult {
/**
* Resolve the source id for a brain directory by looking up the sources
* table. Returns undefined when no registered source matches (falls back
* to pre-v0.18 global config.sync.* keys).
* to pre-v0.18 global config.sync.* keys) OR when MORE than one source
* claims the path — an ambiguous match must not scope phases or stamp
* last_full_cycle_at for an arbitrarily-picked source (the "freshness
* stamp that lies" this resolution exists to prevent).
*/
async function resolveSourceForDir(
engine: BrainEngine,
@@ -865,10 +868,10 @@ async function resolveSourceForDir(
if (brainDir === null) return undefined;
try {
const rows = await engine.executeRaw<{ id: string }>(
`SELECT id FROM sources WHERE local_path = $1 LIMIT 1`,
`SELECT id FROM sources WHERE local_path = $1 LIMIT 2`,
[brainDir],
);
return rows[0]?.id;
return rows.length === 1 ? rows[0]!.id : undefined;
} catch {
// sources table might not exist on very old brains — fall through.
return undefined;
@@ -2365,17 +2368,23 @@ export async function runCycle(
}
// v0.38 (codex r1 P0-5): persist per-source cycle completion timestamp
// when the cycle ran successfully against an explicit source. Read by
// autopilot's per-source freshness gate next tick. Skipped when:
// - opts.sourceId is unset (legacy callers — autopilot still here)
// - engine is null (no-DB path)
// when the cycle ran successfully against a resolvable source. Read by
// autopilot's per-source freshness gate next tick.
//
// #1993: keyed off `cycleSourceId` (opts.sourceId ?? the source resolved
// from brainDir) — the SAME id the cycle locked + scoped its phases to —
// NOT raw opts.sourceId. The autopilot's inline cycle sets brainDir but
// passes no explicit sourceId, so keying off opts.sourceId alone never
// advanced last_full_cycle_at and cycle_freshness stayed stale even while
// the autopilot cycled every interval. Skipped when:
// - no source resolves (engine null, or no checkout AND no opts.sourceId)
// - status is 'failed' or 'skipped' (don't mark a non-run as fresh)
// - dryRun (writes are out of scope)
//
// Best-effort: a write failure does NOT change the CycleReport status.
// The cost of writing the wrong timestamp post-failure is higher than
// the cost of missing a successful write (next cycle will redo work).
if (opts.sourceId && engine && !dryRun && !aborted && (status === 'ok' || status === 'clean' || status === 'partial')) {
if (cycleSourceId && engine && !dryRun && !aborted && (status === 'ok' || status === 'clean' || status === 'partial')) {
try {
const nowIso = new Date().toISOString();
// #2194 fix #3 (the cycle split): `last_source_cycle_at` is the NEW gate
@@ -2385,13 +2394,13 @@ export async function runCycle(
// phases (those gate on autopilot.last_global_at), so writing it on a
// source-only cycle does not re-introduce the freshness poisoning codex
// flagged in the rejected skip-based design.
await engine.updateSourceConfig(opts.sourceId, {
await engine.updateSourceConfig(cycleSourceId, {
last_source_cycle_at: nowIso,
last_full_cycle_at: nowIso,
});
} catch (e) {
// Best-effort; cycle already succeeded by the time we get here.
console.warn(`[cycle] failed to write last_source_cycle_at for source ${opts.sourceId}: ${e instanceof Error ? e.message : String(e)}`);
console.warn(`[cycle] failed to write last_source_cycle_at for source ${cycleSourceId}: ${e instanceof Error ? e.message : String(e)}`);
}
}
+14
View File
@@ -54,6 +54,20 @@ describe('autopilot.ts ↔ dispatchPerSource wiring', () => {
expect(AUTOPILOT_SRC).toMatch(/lastFullCycleAt\s*=\s*Date\.now\(\)/);
});
test('stale per-source cycle freshness is a shouldFullCycle input (#2060)', () => {
// Targeted mode (score 7094, plan ≤3, est <300s) must not be able to
// starve per-source cycle dispatch: a stale source (per countStaleSources
// over listAllSources) forces the fanout path, and the sleep gate must
// not fire while stale sources exist. Without these terms, cycle
// freshness never advances for a brain that always lands in targeted mode.
expect(AUTOPILOT_SRC).toMatch(/countStaleSources/);
const fullCycleDeclIdx = AUTOPILOT_SRC.indexOf('const shouldFullCycle');
expect(fullCycleDeclIdx).toBeGreaterThan(-1);
const decl = AUTOPILOT_SRC.slice(fullCycleDeclIdx, fullCycleDeclIdx + 700);
expect(decl).toMatch(/staleCycleSources\s*>\s*0/);
expect(decl).toMatch(/const shouldSleep[^;]*staleCycleSources\s*===\s*0/);
});
test('does NOT regress to the single-job dispatch on the full-cycle path', () => {
// Pre-PR: the shouldFullCycle branch did:
// const job = await queue.add('autopilot-cycle', { repoPath }, {
+18
View File
@@ -14,6 +14,7 @@ import { describe, test, expect } from 'bun:test';
import {
readLastFullCycleAt,
isSourceStale,
countStaleSources,
selectSourcesForDispatch,
resolveFanoutMax,
dispatchPerSource,
@@ -74,6 +75,23 @@ describe('isSourceStale', () => {
});
});
describe('countStaleSources (#2060 dispatch-decision input)', () => {
const NOW = Date.parse('2026-05-22T12:00:00.000Z');
test('counts never-cycled + past-floor sources, ignores fresh', () => {
const sources = [
src('never-cycled'), // stale (null)
src('old', new Date(NOW - 2 * 60 * 60_000).toISOString()), // stale (2h)
src('fresh', new Date(NOW - 30 * 60_000).toISOString()), // fresh (30min)
];
expect(countStaleSources(sources, NOW)).toBe(2);
});
test('returns 0 for all-fresh and for empty list', () => {
const fresh = src('a', new Date(NOW - 10 * 60_000).toISOString());
expect(countStaleSources([fresh], NOW)).toBe(0);
expect(countStaleSources([], NOW)).toBe(0);
});
});
describe('selectSourcesForDispatch', () => {
const NOW = Date.parse('2026-05-22T12:00:00.000Z');
const fresh = (id: string, agoMin: number) =>
+38 -8
View File
@@ -3,8 +3,10 @@
* cycles. Closes codex round-1 P0-5 (write site for last_full_cycle_at
* was unspecified pre-PR).
*
* Conditions for write:
* - opts.sourceId is set (legacy callers without sourceId skip the write)
* Conditions for write (keyed off `cycleSourceId` = opts.sourceId ?? the
* source resolved from brainDir, so the autopilot's inline cycle brainDir
* set, no explicit sourceId also advances the timestamp, #1993):
* - a source resolves (explicit sourceId, or brainDir matches a source)
* - engine is non-null (no-DB path skips)
* - status is 'ok' | 'clean' | 'partial' (failed/skipped don't mark fresh)
* - dryRun is false
@@ -90,17 +92,45 @@ describe('runCycle last_full_cycle_at exit hook', () => {
});
});
test('legacy caller (no sourceId) does NOT write any source timestamp', async () => {
test('no explicit sourceId but brainDir resolves a source → writes the resolved source timestamp', async () => {
await withEnv({ GBRAIN_HOME: gbrainHome }, async () => {
await seedSource('default-like');
// No sourceId passed; should remain untouched.
// The autopilot's inline cycle sets brainDir but passes no sourceId.
// runCycle resolves the source from brainDir (local_path match) into
// cycleSourceId and stamps last_full_cycle_at for it — otherwise
// cycle_freshness reports the brain stale even while the autopilot
// cycles every interval (#1993).
await seedSource('resolved-from-dir'); // local_path = brainDir
expect(await readLastFullCycleAt('resolved-from-dir')).toBeNull();
const t0 = Date.now();
const report = await runCycle(engine, {
brainDir,
phases: ['lint'],
});
expect(['ok', 'clean']).toContain(report.status);
const after = await readLastFullCycleAt('resolved-from-dir');
expect(after).not.toBeNull();
expect(new Date(after!).getTime()).toBeGreaterThanOrEqual(t0);
});
});
test('no sourceId and brainDir matches no source → does not write', async () => {
await withEnv({ GBRAIN_HOME: gbrainHome }, async () => {
// A source exists but its local_path does NOT match brainDir, so
// resolveSourceForDir returns undefined, cycleSourceId is undefined,
// and no per-source timestamp is written.
await engine.executeRaw(
`INSERT INTO sources (id, name, local_path, config, archived, created_at)
VALUES ('unmatched', 'unmatched', '/no/such/repo', '{}'::jsonb, false, NOW())
ON CONFLICT (id) DO UPDATE SET local_path = EXCLUDED.local_path`,
[],
);
await runCycle(engine, {
brainDir,
phases: ['lint'],
});
// No per-source write happens; default source's config stays empty.
const after = await readLastFullCycleAt('default-like');
expect(after).toBeNull();
expect(await readLastFullCycleAt('unmatched')).toBeNull();
});
});
@@ -1,155 +0,0 @@
/**
* 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');
});
});