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>

src/cli.ts

@@ -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:');

src/commands/doctor.ts

@@ -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`,
       ];

src/core/cjk.ts

@@ -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 = ['；', '：', '，', '、']; // ；：，、
 

src/core/cycle/synthesize.ts

@@ -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) ─────────────────────────────
 

src/core/operations.ts

@@ -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)`);
   }

src/core/output/slug-registry.ts

@@ -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) {}

test/cycle-dream-output-root.test.ts

@@ -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++) {

test/doctor-timeline-metric-labels-2298.test.ts

@@ -1,155 +0,0 @@
-/**
- * Issue #2298 — timeline metric presentation contract.
- *
- * Authoritative upstream semantics (src/core/types.ts):
- *   - Metric A `timeline_coverage` (entity-scoped, fraction 0–1):
- *       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, 0–15 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');
-  });
-});

test/writer.test.ts

@@ -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({