mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 10:22:34 +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) {
|
||||
|
||||
@@ -20,14 +20,6 @@ export const CJK_SLUG_CHARS = '一-鿿-ゟ゠-ヿ가-';
|
||||
|
||||
export const CJK_RANGES_REGEX = new RegExp(`[${CJK_SLUG_CHARS}]`);
|
||||
|
||||
/**
|
||||
* Page-slug segment grammar (no anchors): alnum-or-CJK lead char, then
|
||||
* alnum/CJK/hyphen continuation. Single source for validatePageSlug
|
||||
* (operations.ts), SlugRegistry's SLUG_RE, and the dream-cycle
|
||||
* SUMMARY_SLUG_RE so every slug validator shares one grammar (#738).
|
||||
*/
|
||||
export const PAGE_SLUG_SEG = `[a-z0-9${CJK_SLUG_CHARS}][a-z0-9${CJK_SLUG_CHARS}\\-]*`;
|
||||
|
||||
export const CJK_SENTENCE_DELIMITERS = ['。', '!', '?']; // 。!?
|
||||
export const CJK_CLAUSE_DELIMITERS = [';', ':', ',', '、']; // ;:,、
|
||||
|
||||
|
||||
+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}: ${e instanceof Error ? e.message : String(e)}`);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -43,11 +43,10 @@ import { serializeMarkdown, serializePageToMarkdown } from '../markdown.ts';
|
||||
import type { Page, PageType } from '../types.ts';
|
||||
import { validateSourceId } from '../utils.ts';
|
||||
import { safeSplitIndex } from '../text-safe.ts';
|
||||
import { PAGE_SLUG_SEG } from '../cjk.ts';
|
||||
|
||||
// Slug grammar from validatePageSlug — shared via PAGE_SLUG_SEG (#738).
|
||||
// Slug regex from validatePageSlug — kept in sync.
|
||||
// Used for the orchestrator-written summary index slug.
|
||||
const SUMMARY_SLUG_RE = new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})*$`);
|
||||
const SUMMARY_SLUG_RE = /^[a-z0-9][a-z0-9\-]*(\/[a-z0-9][a-z0-9\-]*)*$/;
|
||||
|
||||
// ── Model context budget (D1, D5, D7, D9) ─────────────────────────────
|
||||
|
||||
|
||||
@@ -25,7 +25,7 @@ import { bumpLastRetrievedAt } from './last-retrieved.ts';
|
||||
import { isSearchMode } from './search/mode.ts';
|
||||
import { stampEvidence } from './search/evidence.ts';
|
||||
import type { SearchResult } from './types.ts';
|
||||
import { CJK_SLUG_CHARS, PAGE_SLUG_SEG } from './cjk.ts';
|
||||
import { CJK_SLUG_CHARS } from './cjk.ts';
|
||||
import * as db from './db.ts';
|
||||
import { VERSION } from '../version.ts';
|
||||
import {
|
||||
@@ -162,6 +162,7 @@ export function validatePageSlug(slug: string): void {
|
||||
}
|
||||
// v0.32.7: CJK ranges (Han / Hiragana / Katakana / Hangul Syllables) allowed
|
||||
// in segments. ASCII shape rules (lead char, hyphen continuation) preserved.
|
||||
const PAGE_SLUG_SEG = `[a-z0-9${CJK_SLUG_CHARS}][a-z0-9${CJK_SLUG_CHARS}\\-]*`;
|
||||
if (!new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})*$`, 'i').test(slug)) {
|
||||
throw new OperationError('invalid_params', `Invalid page_slug: ${slug} (allowed: alphanumeric, CJK, hyphens, forward-slash separated segments)`);
|
||||
}
|
||||
|
||||
@@ -17,7 +17,6 @@
|
||||
|
||||
import type { BrainEngine } from '../engine.ts';
|
||||
import type { PageType } from '../types.ts';
|
||||
import { PAGE_SLUG_SEG } from '../cjk.ts';
|
||||
|
||||
export interface CreateSlugInput {
|
||||
/**
|
||||
@@ -72,9 +71,7 @@ export class SlugRegistryError extends Error {
|
||||
// SlugRegistry
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
// Shares the page-slug segment grammar (incl. CJK ranges, #738) with
|
||||
// validatePageSlug; keeps this site's dir/name shape (>= 2 segments).
|
||||
const SLUG_RE = new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})+$`);
|
||||
const SLUG_RE = /^[a-z0-9][a-z0-9\-]*(\/[a-z0-9][a-z0-9\-]*)+$/;
|
||||
|
||||
export class SlugRegistry {
|
||||
constructor(private engine: BrainEngine) {}
|
||||
|
||||
@@ -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) =>
|
||||
|
||||
@@ -86,12 +86,6 @@ describe('#2415: loadOutputRoot validation + patterns gather scope', () => {
|
||||
expect(await loadOutputRoot(engine)).toBe('wiki');
|
||||
});
|
||||
|
||||
test('CJK root passes the slug grammar (#738)', async () => {
|
||||
await engine.setConfig('dream.synthesize.output_root', '知识/笔记');
|
||||
expect(await loadOutputRoot(engine)).toBe('知识/笔记');
|
||||
await engine.setConfig('dream.synthesize.output_root', '');
|
||||
});
|
||||
|
||||
test('patterns phase gathers reflections under the configured root', async () => {
|
||||
await engine.setConfig('dream.synthesize.output_root', 'notes');
|
||||
for (let i = 0; i < 3; i++) {
|
||||
|
||||
@@ -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();
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@@ -203,17 +203,6 @@ describe('SlugRegistry', () => {
|
||||
})).rejects.toThrow(SlugRegistryError);
|
||||
});
|
||||
|
||||
test('create accepts CJK slugs (#738)', async () => {
|
||||
const reg = new SlugRegistry(engine);
|
||||
const r = await reg.create({
|
||||
desiredSlug: '知识/品牌圣经',
|
||||
displayName: '品牌圣经',
|
||||
type: 'note',
|
||||
});
|
||||
expect(r.slug).toBe('知识/品牌圣经');
|
||||
expect(r.exact).toBe(true);
|
||||
});
|
||||
|
||||
test('create throws on invalid slug', async () => {
|
||||
const reg = new SlugRegistry(engine);
|
||||
await expect(reg.create({
|
||||
|
||||
Reference in New Issue
Block a user