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
8 changed files with 133 additions and 83 deletions
+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) {
+15 -33
View File
@@ -107,14 +107,6 @@ export interface EmbedOpts {
* runs lock every source in sorted order. dryRun skips it.
*/
singleFlight?: boolean;
/**
* #394: suppress human stdout summaries (the `[dry-run] Would embed ...` /
* `Embedded N chunks ...` slog lines). Set by structured-output callers —
* the cycle's embed phase (dream --json must keep stdout JSON-clean per
* docs/progress-events.md) reports counts via its own PhaseResult instead.
* Errors/warnings still go to stderr regardless.
*/
quiet?: boolean;
}
/**
@@ -261,7 +253,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
for (const s of opts.slugs) {
if (isAborted(opts.signal)) break; // #1737: stop the per-slug loop on abort
try {
await embedPage(engine, s, !!opts.dryRun, result, opts.sourceId, opts.signal, opts.quiet);
await embedPage(engine, s, !!opts.dryRun, result, opts.sourceId, opts.signal);
} catch (e: unknown) {
serr(` Error embedding ${s}: ${e instanceof Error ? e.message : e}`);
}
@@ -355,7 +347,6 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
catchUp: opts.catchUp,
pacer,
paceMaxConcurrency,
quiet: opts.quiet,
}, opts.signal);
} finally {
// E1: surface pacing telemetry (human + structured) when pacing was on.
@@ -385,7 +376,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
return result;
}
if (opts.slug) {
await embedPage(engine, opts.slug, !!opts.dryRun, result, opts.sourceId, opts.signal, opts.quiet);
await embedPage(engine, opts.slug, !!opts.dryRun, result, opts.sourceId, opts.signal);
return result;
}
throw new Error('No embed target specified. Pass { slug }, { slugs }, { all }, or { stale }.');
@@ -530,7 +521,6 @@ async function embedPage(
result: EmbedResult,
sourceId?: string,
signal?: AbortSignal,
quiet?: boolean,
) {
const opts = sourceId ? { sourceId } : undefined;
const page = await engine.getPage(slug, opts);
@@ -575,7 +565,7 @@ async function embedPage(
result.skipped += chunks.length - toEmbed.length;
if (toEmbed.length === 0) {
if (!quiet) slog(`${slug}: all ${chunks.length} chunks already embedded`);
slog(`${slug}: all ${chunks.length} chunks already embedded`);
result.pages_processed++;
return;
}
@@ -612,7 +602,7 @@ async function embedPage(
}
result.embedded += toEmbed.length;
result.pages_processed++;
if (!quiet) slog(`${slug}: embedded ${toEmbed.length} chunks`);
slog(`${slug}: embedded ${toEmbed.length} chunks`);
}
async function embedAll(
@@ -630,8 +620,6 @@ async function embedAll(
pacer?: DbPacer;
/** Resolved concurrency cap (E-1: the worker count, no separate permit). */
paceMaxConcurrency?: number;
/** #394: suppress human stdout summaries (structured-output callers). */
quiet?: boolean;
},
signal?: AbortSignal,
) {
@@ -775,12 +763,10 @@ async function embedAll(
});
// Stdout summary preserved for scripts/tests that grep for counts.
if (!staleOpts?.quiet) {
if (dryRun) {
slog(`[dry-run] Would embed ${result.would_embed} chunks across ${pages.length} pages`);
} else {
slog(`Embedded ${result.embedded} chunks across ${pages.length} pages`);
}
if (dryRun) {
slog(`[dry-run] Would embed ${result.would_embed} chunks across ${pages.length} pages`);
} else {
slog(`Embedded ${result.embedded} chunks across ${pages.length} pages`);
}
}
@@ -816,8 +802,6 @@ async function embedAllStale(
pacer?: DbPacer;
/** Resolved concurrency cap (E-1: the worker count, no separate permit). */
paceMaxConcurrency?: number;
/** #394: suppress human stdout summaries (structured-output callers). */
quiet?: boolean;
},
signature?: string,
externalSignal?: AbortSignal,
@@ -835,7 +819,7 @@ async function embedAllStale(
signature,
...(sourceId && { sourceId }),
});
if (invalidated > 0 && !staleOpts?.quiet) {
if (invalidated > 0) {
slog(`[embed] invalidated ${invalidated} chunk(s) embedded under a prior model signature`);
}
}
@@ -846,12 +830,10 @@ async function embedAllStale(
dryRun && signature ? { ...sourceOpt, signature } : sourceOpt,
);
if (staleCount === 0) {
if (!staleOpts?.quiet) {
if (dryRun) {
slog('[dry-run] Would embed 0 chunks (0 stale found)');
} else {
slog('Embedded 0 chunks (0 stale found)');
}
if (dryRun) {
slog('[dry-run] Would embed 0 chunks (0 stale found)');
} else {
slog('Embedded 0 chunks (0 stale found)');
}
return;
}
@@ -860,7 +842,7 @@ async function embedAllStale(
result.would_embed += staleCount;
result.total_chunks += staleCount;
if (onProgress) onProgress(1, 1, 0);
if (!staleOpts?.quiet) slog(`[dry-run] Would embed ${staleCount} stale chunks`);
slog(`[dry-run] Would embed ${staleCount} stale chunks`);
return;
}
@@ -1100,7 +1082,7 @@ async function embedAllStale(
if (budgetTimer) clearTimeout(budgetTimer);
}
if (!staleOpts?.quiet) slog(`Embedded ${result.embedded} chunks across ${totalProcessedPages} pages`);
slog(`Embedded ${result.embedded} chunks across ${totalProcessedPages} pages`);
// #1946 (OV2a): a catch-up pass that completed without being aborted but left
// chunks unembedded means those chunks are stuck (a non-transient embed
+20 -13
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;
@@ -1214,9 +1217,7 @@ async function runPhaseEmbed(engine: BrainEngine, dryRun: boolean, signal?: Abor
// 10-15 min one) bails within a batch instead of running to completion
// after the job was killed — which left gbrain_cycle_locks held and
// wedged every subsequent autopilot cycle.
// #394: quiet — the cycle reports embed counts via its own PhaseResult;
// raw `[dry-run] Would embed ...` stdout lines would corrupt `dream --json`.
const result = await runEmbedCore(engine, { stale: true, dryRun, signal, quiet: true });
const result = await runEmbedCore(engine, { stale: true, dryRun, signal });
const embeddedCount = dryRun ? result.would_embed : result.embedded;
return {
phase: 'embed',
@@ -2367,17 +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
@@ -2387,13 +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();
});
});
-27
View File
@@ -292,33 +292,6 @@ describe('runDream — output format', () => {
expect(parsed).toHaveProperty('totals');
});
// #394 / takeover of #854: the embed phase's `[dry-run] Would embed ...`
// summary must not leak onto stdout ahead of the JSON CycleReport.
test('--dry-run --json emits only JSON even when embed has stale chunks', async () => {
await engine.putPage('concepts/testing', {
type: 'concept',
title: 'Testing',
compiled_truth: 'Testing keeps JSON contracts honest.',
timeline: '',
});
await engine.upsertChunks('concepts/testing', [
{ chunk_index: 0, chunk_text: 'Testing keeps JSON contracts honest.', chunk_source: 'compiled_truth' },
]);
const lines: string[] = [];
const logSpy = spyOn(console, 'log').mockImplementation((msg: string) => { lines.push(String(msg)); });
await runDream(engine, ['--dir', repo, '--phase', 'embed', '--dry-run', '--json']);
logSpy.mockRestore();
const output = lines.join('\n');
expect(output.trimStart().startsWith('{')).toBe(true);
const parsed = JSON.parse(output);
expect(parsed.schema_version).toBe('1');
expect(parsed.phases[0].phase).toBe('embed');
// The stale chunk was still counted in the structured report.
expect(parsed.phases[0].details.would_embed).toBe(1);
});
test('human output for clean status mentions "Brain is healthy"', async () => {
const lines: string[] = [];
const logSpy = spyOn(console, 'log').mockImplementation((msg: string) => { lines.push(String(msg)); });