mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 02:12:40 +00:00
Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
3fa01a4538 | ||
|
|
ded4aeaeae |
@@ -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 70–94, 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
|
||||
|
||||
@@ -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 70–94 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) {
|
||||
|
||||
+19
-10
@@ -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)}`);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -18,7 +18,6 @@
|
||||
import type { BrainEngine } from '../engine.ts';
|
||||
import { loadActivePackBestEffort } from './best-effort.ts';
|
||||
import type { OperationContext } from '../operations.ts';
|
||||
import { isUndefinedTableError } from '../utils.ts';
|
||||
|
||||
export interface StatsOpts {
|
||||
/** Single source scope. Omit + omit sourceIds for whole-brain aggregate. */
|
||||
@@ -165,17 +164,9 @@ async function fetchCountRows(engine: BrainEngine, opts: StatsOpts): Promise<Raw
|
||||
`;
|
||||
try {
|
||||
return await engine.executeRaw<RawCountRow>(sql, params);
|
||||
} catch (err) {
|
||||
// ONLY swallow the genuine "pages table doesn't exist yet" case
|
||||
// (empty / pre-init brain). #2466: the old bare `catch {}` masked
|
||||
// EVERY error — so any engine-level failure (connection, version
|
||||
// skew, a query incompatibility) was silently converted to 0 rows,
|
||||
// printing "Total pages: 0" on a populated brain and cascading into
|
||||
// false "100% coverage" + a starved `schema suggest`. Surface
|
||||
// everything that is not a missing-table error so the real failure
|
||||
// is visible instead of hidden behind a fake zero.
|
||||
if (isUndefinedTableError(err)) return [];
|
||||
throw err;
|
||||
} catch {
|
||||
// Empty / pre-init brain: pages table may not exist yet.
|
||||
return [];
|
||||
}
|
||||
}
|
||||
|
||||
@@ -213,11 +204,9 @@ async function detectDeadPrefixes(
|
||||
if (cnt === 0) {
|
||||
hints.push({ type: t.name, prefix });
|
||||
}
|
||||
} catch (err) {
|
||||
// #2466: only skip on the genuine "no pages table yet" case;
|
||||
// rethrow any other engine error so it isn't silently masked.
|
||||
if (isUndefinedTableError(err)) continue;
|
||||
throw err;
|
||||
} catch {
|
||||
// Skip on engine error (no pages table yet, etc.).
|
||||
continue;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -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 70–94, 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 }, {
|
||||
|
||||
@@ -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) =>
|
||||
|
||||
@@ -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();
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@@ -222,89 +222,6 @@ describe('runStatsCore — JSON envelope shape', () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe('runStatsCore — #2466 catch-narrowing (real count + error surfacing)', () => {
|
||||
// #2466: `gbrain schema stats` reported "Total pages: 0" on a populated
|
||||
// PGLite brain. The bug was a bare `catch {}` in fetchCountRows (and a
|
||||
// sibling in detectDeadPrefixes) that converted ANY engine error into 0
|
||||
// rows. The COUNT query itself is valid on PGLite (proven below), so the
|
||||
// regression pins two things: (a) a populated brain reports the real,
|
||||
// non-zero count through the full runStatsCore path; (b) a non-missing-
|
||||
// table engine error is rethrown, not masked into a fake zero.
|
||||
|
||||
it('reports the real non-zero count on a populated PGLite brain (no false 0)', async () => {
|
||||
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
|
||||
// Seed a realistic mix: typed, untyped, multiple types — like the
|
||||
// 169-page brain in the bug report (scaled down).
|
||||
for (let i = 0; i < 12; i++) {
|
||||
const type = i % 3 === 0 ? '' : (i % 3 === 1 ? 'person' : 'company');
|
||||
await seedPage(`notes/p${i}`, { type, sourcePath: `notes/p${i}.md` });
|
||||
}
|
||||
const result = await runStatsCore(ctxOf());
|
||||
// The core regression: NOT zero.
|
||||
expect(result.aggregate.total_pages).toBe(12);
|
||||
expect(result.aggregate.typed_pages).toBe(8);
|
||||
expect(result.aggregate.untyped_pages).toBe(4);
|
||||
// And coverage is the honest ratio, not the vacuous 1.0 a 0/0 prints.
|
||||
expect(result.aggregate.coverage).not.toBe(1.0);
|
||||
});
|
||||
});
|
||||
|
||||
it('fetchCountRows rethrows a non-missing-table engine error instead of masking it as 0 pages', async () => {
|
||||
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
|
||||
// No pack → detectDeadPrefixes is skipped, isolating the throw to the
|
||||
// fetchCountRows catch we narrowed. The count query (the GROUP BY one)
|
||||
// throws a column-level error (SQLSTATE 42703) — the exact class the
|
||||
// old bare `catch {}` swallowed into 0 rows; everything else succeeds.
|
||||
__setPackLocatorForTests(() => null);
|
||||
const boom = Object.assign(new Error('column "type" does not exist'), { code: '42703' });
|
||||
const stubEngine = {
|
||||
executeRaw: async (sql: string) => {
|
||||
if (/GROUP BY source_id/.test(sql)) throw boom; // the fetchCountRows query
|
||||
return [];
|
||||
},
|
||||
} as unknown as PGLiteEngine;
|
||||
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
|
||||
await expect(runStatsCore(ctx)).rejects.toThrow('column "type" does not exist');
|
||||
});
|
||||
});
|
||||
|
||||
it('fetchCountRows still degrades to empty (no throw) on a genuine missing pages table', async () => {
|
||||
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
|
||||
// Pre-init brain shape: the count query hits a missing pages table
|
||||
// (SQLSTATE 42P01). This is the ONLY case the narrowed catch swallows.
|
||||
__setPackLocatorForTests(() => null);
|
||||
const missing = Object.assign(new Error('relation "pages" does not exist'), { code: '42P01' });
|
||||
const stubEngine = {
|
||||
executeRaw: async (sql: string) => {
|
||||
if (/GROUP BY source_id/.test(sql)) throw missing;
|
||||
return [];
|
||||
},
|
||||
} as unknown as PGLiteEngine;
|
||||
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
|
||||
const result = await runStatsCore(ctx);
|
||||
expect(result.aggregate.total_pages).toBe(0);
|
||||
expect(result.per_source).toEqual([]);
|
||||
});
|
||||
});
|
||||
|
||||
it('detectDeadPrefixes rethrows a non-missing-table error (sibling catch)', async () => {
|
||||
await withEnv({ GBRAIN_HOME: tmpDir, GBRAIN_SCHEMA_PACK: 'tiny' }, async () => {
|
||||
seedTinyPack('tiny', [{ name: 'person', prefix: 'people/' }]);
|
||||
// fetchCountRows (the GROUP BY query) succeeds → []; the per-prefix
|
||||
// dead-prefix LIKE query then throws a non-missing-table error, which
|
||||
// must surface through the narrowed sibling catch.
|
||||
const stubEngine = {
|
||||
executeRaw: async (sql: string) => {
|
||||
if (/GROUP BY source_id/.test(sql)) return []; // count query: empty brain, fine
|
||||
throw Object.assign(new Error('division by zero'), { code: '22012' }); // the LIKE query
|
||||
},
|
||||
} as unknown as PGLiteEngine;
|
||||
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
|
||||
await expect(runStatsCore(ctx)).rejects.toThrow('division by zero');
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe('runStatsCore — type/untyped split', () => {
|
||||
it('treats empty-string type as untyped (not its own bucket)', async () => {
|
||||
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
|
||||
|
||||
Reference in New Issue
Block a user