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/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/context-engine.ts

@@ -453,14 +453,7 @@ function resolveActivity(
  * every `assemble()` call. 1 MB is generous for a human-edited task list. */
 const MAX_TASKS_MD_BYTES = 1_000_000;
 
-/** Extract open tasks from ops/tasks.md Today section.
- *
- * The daily-task-manager skill's documented Output Format uses priority
- * headings (`## P1 — Today`) with plain `- [ ] task` lines; older fixtures
- * used a bare `## Today` heading with bold task names. Accept both so the
- * live-context reader matches the documented writer contract instead of
- * silently surfacing no tasks (#2186).
- */
+/** Extract open tasks from ops/tasks.md "## Today" section. */
 function resolveTodayTasks(workspaceDir: string): string[] {
   try {
     const path = join(workspaceDir, 'ops', 'tasks.md');
@@ -468,18 +461,14 @@ function resolveTodayTasks(workspaceDir: string): string[] {
     // statSync throws if the file doesn't exist; that lands in the outer catch.
     if (statSync(path).size > MAX_TASKS_MD_BYTES) return [];
     const raw = readFileSync(path, 'utf8');
-    const todayMatch = raw.match(/^##\s+(?:P\d\s*[—–-]\s*)?Today\b[\s\S]*?(?=\n##\s|$(?![\s\S]))/m);
+    const todayMatch = raw.match(/## Today[\s\S]*?(?=\n## |$)/);
     if (!todayMatch) return [];
 
     const lines = todayMatch[0].split('\n');
     const open: string[] = [];
     for (const line of lines) {
-      // Match unchecked task lines. Legacy bold form first (extracts just
-      // the task name, dropping trailing metadata), then the documented
-      // plain form (whole line body is the task).
-      const m =
-        line.match(/^\s*-\s*\[ \]\s*\*\*(.+?)\*\*/) ??
-        line.match(/^\s*-\s*\[ \]\s*(.+?)\s*$/);
+      // Match unchecked task lines: - [ ] **task name** ...
+      const m = line.match(/^\s*-\s*\[ \]\s*\*\*(.+?)\*\*/);
       if (m) open.push(sanitizeForPrompt(m[1].trim()));
     }
     return open.slice(0, 5); // cap at 5 to keep prompt lean

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/context-engine.test.ts

@@ -322,28 +322,6 @@ describe('gbrain-context engine', () => {
     expect(result.systemPromptAddition).not.toContain('Something later');
   });
 
-  it('injects documented "## P1 — Today" plain tasks from ops/tasks.md (#2186)', async () => {
-    tmpDir = makeWorkspace({
-      heartbeat: { garryAwake: true },
-      tasks: `# Tasks\n\n## P0 — Urgent\n- [ ] **Escalate outage**\n\n## P1 — Today\n- [ ] Call Alice about launch plan\n- [ ] **Review Bob contract** — due Friday\n- [x] Completed item\n\n## P2 — This Week\n- [ ] Should not surface`,
-    });
-    const engine = createGBrainContextEngine({ workspaceDir: tmpDir });
-
-    const result = await engine.assemble({
-      sessionId: 'test-session',
-      messages: [],
-    });
-
-    expect(result.systemPromptAddition).toContain('Open tasks');
-    expect(result.systemPromptAddition).toContain('Call Alice about launch plan');
-    // Bold form still extracts just the task name, not trailing metadata.
-    expect(result.systemPromptAddition).toContain('Review Bob contract');
-    expect(result.systemPromptAddition).not.toContain('due Friday');
-    expect(result.systemPromptAddition).not.toContain('Escalate outage');
-    expect(result.systemPromptAddition).not.toContain('Completed item');
-    expect(result.systemPromptAddition).not.toContain('Should not surface');
-  });
-
   it('no activity section when calendar is empty and no tasks', async () => {
     tmpDir = makeWorkspace({
       heartbeat: { garryAwake: true },

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/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({