Compare commits

..
Author SHA1 Message Date
78cc6d1e84 fix(slugs): CJK slug support in SlugRegistry and dream-cycle summary slug (takeover of #782, #738)
Master already widened slugifySegment (sync.ts) and validatePageSlug
(operations.ts) to CJK in v0.32.7, but the other two validators #782
targeted stayed ASCII-only: SlugRegistry's SLUG_RE rejected any CJK
desiredSlug from BrainWriter, and synthesize.ts's SUMMARY_SLUG_RE (whose
comment claimed it was kept in sync with validatePageSlug) rejected CJK
output roots.

Hoist the segment grammar into cjk.ts as PAGE_SLUG_SEG and compose all
three regex sites from it, so the four slug validators share one grammar.
Each site keeps its own shape (SlugRegistry's >=2-segment dir/name form,
validatePageSlug's case-insensitive flag).

Scope stays CJK (matching v0.32.7), not full \p{L} Unicode as #782
proposed — all-scripts slugs (lookalike/RTL spoofing) is a maintainer
policy call.

Co-authored-by: tamagodo-fu <tamagodo-fu@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:21:39 -07:00
10 changed files with 39 additions and 95 deletions
+1 -1
View File
@@ -2387,7 +2387,7 @@ JOBS (Minions)
jobs get <id> Job details + history
jobs cancel <id> Cancel job
jobs retry <id> Re-queue failed/dead job
jobs prune [--older-than 30d] [--status s,..] Clean old terminal jobs (0d = no age floor)
jobs prune [--older-than 30d] Clean old jobs
jobs stats Job health dashboard
jobs work [--queue Q] Start worker daemon (Postgres only)
+5 -33
View File
@@ -106,21 +106,6 @@ export function parseMaxRssFlag(args: string[]): number | undefined {
return parsed;
}
/** Terminal statuses `jobs prune --status` accepts (PR #2282). Matches what
* queue.prune can safely delete; anything else (waiting/active/…) is live. */
export const PRUNE_STATUSES = ['completed', 'failed', 'dead', 'cancelled'] as const satisfies readonly MinionJobStatus[];
/** Parse a `--status a,b,c` value into prune statuses. Throws on any value
* outside PRUNE_STATUSES (fail-fast, mirrors parseNiceValue). */
export function parsePruneStatuses(raw: string): MinionJobStatus[] {
const requested = raw.split(',').map(s => s.trim()).filter(Boolean);
const invalid = requested.filter(s => !(PRUNE_STATUSES as readonly string[]).includes(s));
if (requested.length === 0 || invalid.length > 0) {
throw new Error(`--status accepts a comma-separated subset of [${PRUNE_STATUSES.join(', ')}]${invalid.length ? `. Invalid: ${invalid.join(', ')}` : ''}`);
}
return requested as MinionJobStatus[];
}
/** Parse `--nice N` (then `GBRAIN_NICE` env). Returns:
* - undefined if absent (no priority change — inherit)
* - the validated integer in [-20, 19] otherwise
@@ -223,9 +208,7 @@ USAGE
gbrain jobs get <id>
gbrain jobs cancel <id>
gbrain jobs retry <id>
gbrain jobs prune [--older-than 30d] [--status completed,failed,dead,cancelled]
(--older-than 0d = no age floor: deletes ALL
matching terminal jobs; pair with --status)
gbrain jobs prune [--older-than 30d]
gbrain jobs delete <id>
gbrain jobs stats
gbrain jobs smoke
@@ -617,27 +600,16 @@ HANDLER TYPES (built in)
case 'prune': {
const olderThanStr = parseFlag(args, '--older-than') ?? '30d';
const days = parseInt(olderThanStr, 10);
if (isNaN(days) || days < 0) {
console.error('Error: --older-than must be a non-negative number (days). Example: --older-than 30d; --older-than 0d removes the age floor (deletes ALL matching terminal jobs).');
if (isNaN(days) || days <= 0) {
console.error('Error: --older-than must be a positive number (days). Example: --older-than 30d');
process.exit(1);
}
const statusFlag = parseFlag(args, '--status');
let statuses: MinionJobStatus[] | undefined;
if (statusFlag !== undefined) {
try { statuses = parsePruneStatuses(statusFlag); }
catch (e) { console.error(`Error: ${e instanceof Error ? e.message : String(e)}`); process.exit(1); }
}
try { await queue.ensureSchema(); }
catch (e) { console.error(e instanceof Error ? e.message : String(e)); process.exit(1); }
const count = await queue.prune({
olderThan: new Date(Date.now() - days * 86400000),
...(statuses ? { status: statuses } : {}),
});
const statusLabel = statuses ? statuses.join('+') : 'completed+dead+cancelled';
const ageLabel = days === 0 ? 'regardless of age' : `older than ${days} days`;
console.log(`Pruned ${count} ${statusLabel} jobs ${ageLabel}.`);
const count = await queue.prune({ olderThan: new Date(Date.now() - days * 86400000) });
console.log(`Pruned ${count} jobs older than ${days} days.`);
break;
}
+8
View File
@@ -20,6 +20,14 @@ export const CJK_SLUG_CHARS = '一-鿿぀-ゟ゠-ヿ가-힯';
export const CJK_RANGES_REGEX = new RegExp(`[${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 = ['', '', '', '、']; // ;:,、
+3 -2
View File
@@ -43,10 +43,11 @@ 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 regex from validatePageSlug — kept in sync.
// Slug grammar from validatePageSlug — shared via PAGE_SLUG_SEG (#738).
// Used for the orchestrator-written summary index slug.
const SUMMARY_SLUG_RE = /^[a-z0-9][a-z0-9\-]*(\/[a-z0-9][a-z0-9\-]*)*$/;
const SUMMARY_SLUG_RE = new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})*$`);
// ── Model context budget (D1, D5, D7, D9) ─────────────────────────────
+1 -2
View File
@@ -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 } from './cjk.ts';
import { CJK_SLUG_CHARS, PAGE_SLUG_SEG } from './cjk.ts';
import * as db from './db.ts';
import { VERSION } from '../version.ts';
import {
@@ -162,7 +162,6 @@ 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: ${slug} (allowed: alphanumeric, CJK, hyphens, forward-slash separated segments)`);
}
+4 -1
View File
@@ -17,6 +17,7 @@
import type { BrainEngine } from '../engine.ts';
import type { PageType } from '../types.ts';
import { PAGE_SLUG_SEG } from '../cjk.ts';
export interface CreateSlugInput {
/**
@@ -71,7 +72,9 @@ export class SlugRegistryError extends Error {
// SlugRegistry
// ---------------------------------------------------------------------------
const SLUG_RE = /^[a-z0-9][a-z0-9\-]*(\/[a-z0-9][a-z0-9\-]*)+$/;
// 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})+$`);
export class SlugRegistry {
constructor(private engine: BrainEngine) {}
+6
View File
@@ -86,6 +86,12 @@ 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++) {
-30
View File
@@ -1,30 +0,0 @@
/**
* Unit tests for parsePruneStatuses (PR #2282) — `jobs prune --status` parsing.
*/
import { describe, test, expect } from 'bun:test';
import { parsePruneStatuses, PRUNE_STATUSES } from '../src/commands/jobs.ts';
describe('parsePruneStatuses', () => {
test('parses a single status', () => {
expect(parsePruneStatuses('failed')).toEqual(['failed']);
});
test('parses a comma-separated list with whitespace', () => {
expect(parsePruneStatuses(' completed, dead ')).toEqual(['completed', 'dead']);
});
test('accepts every documented terminal status', () => {
expect(parsePruneStatuses(PRUNE_STATUSES.join(','))).toEqual([...PRUNE_STATUSES]);
});
test('throws on non-terminal statuses', () => {
expect(() => parsePruneStatuses('waiting')).toThrow(/Invalid: waiting/);
expect(() => parsePruneStatuses('completed,active')).toThrow(/Invalid: active/);
});
test('throws on empty value', () => {
expect(() => parsePruneStatuses('')).toThrow(/comma-separated subset/);
expect(() => parsePruneStatuses(',')).toThrow(/comma-separated subset/);
});
});
-26
View File
@@ -702,32 +702,6 @@ describe('MinionQueue: Prune', () => {
const count = await queue.prune({ olderThan: new Date(Date.now() + 86400000) }); // future date = prune everything old enough
expect(count).toBe(1); // only the cancelled one
});
// PR #2282: `jobs prune --status` passes an explicit status subset through.
test('status filter prunes only the requested terminal statuses', async () => {
const cancelled = await queue.add('sync', {});
await queue.cancelJob(cancelled.id);
const dead = await queue.add('embed', {}, { max_attempts: 1 });
await queue.claim('tok1', 30000, 'default', ['embed']);
await queue.failJob(dead.id, 'tok1', 'boom', 'dead');
const count = await queue.prune({ olderThan: new Date(Date.now() + 86400000), status: ['dead'] });
expect(count).toBe(1); // only the dead one
const remaining = await queue.getJobs({ status: 'cancelled' });
expect(remaining.length).toBe(1);
});
// PR #2282: `--older-than 0d` = no age floor — olderThan of "now" deletes
// terminal jobs that finished moments ago.
test('olderThan now (0d semantics) prunes just-terminated jobs', async () => {
const job = await queue.add('sync', {});
await queue.cancelJob(job.id);
await new Promise(r => setTimeout(r, 5)); // ensure updated_at < now
const count = await queue.prune({ olderThan: new Date() });
expect(count).toBe(1);
});
});
// --- Stats (1 test) ---
+11
View File
@@ -203,6 +203,17 @@ 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({