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/commands/doctor.ts

@@ -1551,24 +1551,6 @@ export async function checkRerankerHealth(engine: BrainEngine): Promise<Check> {
       };
     }
 
-    // Historical #2059 rows were logged as `unknown` before missing reranker
-    // auth was classified at the gateway. Surface repeated unknowns instead of
-    // reporting "ok" while every rerank fails open.
-    const unknownFails = failures.filter((f) => f.reason === 'unknown');
-    if (unknownFails.length >= 3) {
-      const setupHint = unknownFails.some((f) => {
-        const summary = String(f.error_summary ?? '');
-        return summary.includes('ZEROENTROPY_API_KEY') || summary.toLowerCase().includes('api key');
-      })
-        ? ' Fix: verify ZEROENTROPY_API_KEY and run `gbrain models doctor`.'
-        : '';
-      return {
-        name: 'reranker_health',
-        status: 'warn',
-        message: `${unknownFails.length} unknown reranker failure(s) in last 7 days.${setupHint}`,
-      };
-    }
-
     return {
       name: 'reranker_health',
       status: 'ok',

src/core/ai/gateway.ts

@@ -3656,15 +3656,7 @@ export async function rerank(input: RerankInput): Promise<RerankResult[]> {
   // whose request/response shape differs from ZE/llama.cpp (e.g. Voyage with
   // `top_k` / `data[]`) needs separate adapter hooks in a follow-up plan.
   const url = `${compat.baseURL.replace(/\/$/, '')}${tp.path ?? '/models/rerank'}`;
-  let auth: { apiKey?: string; headers?: Record<string, string> };
-  try {
-    auth = applyResolveAuth(recipe, cfg, 'reranker');
-  } catch (err) {
-    if (err instanceof AIConfigError) {
-      throw new RerankError(err.message, 'auth');
-    }
-    throw err;
-  }
+  const auth = applyResolveAuth(recipe, cfg, 'reranker');
   // applyResolveAuth returns { apiKey } for Bearer-style auth (SDK's native
   // path) or { headers } for custom-header providers (Azure). v0.37.6.0:
   // recipes can ALSO declare default_headers (attribution etc.) which flow

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/ai/rerank.test.ts

@@ -154,28 +154,6 @@ describe('gateway.rerank() — happy path', () => {
 describe('gateway.rerank() — error classification', () => {
   beforeEach(() => configureZE());
 
-  test('missing required reranker API key → RerankError(auth) before HTTP call', async () => {
-    configureGateway({
-      reranker_model: 'zeroentropyai:zerank-2',
-      env: {},
-    });
-    let called = false;
-    __setRerankTransportForTests(async () => {
-      called = true;
-      return mockResp({ results: [{ index: 0, relevance_score: 0.5 }] });
-    });
-
-    try {
-      await rerank({ query: 'q', documents: ['d'] });
-      throw new Error('should have thrown');
-    } catch (err) {
-      expect(err).toBeInstanceOf(RerankError);
-      expect((err as RerankError).reason).toBe('auth');
-      expect((err as Error).message).toContain('ZEROENTROPY_API_KEY');
-      expect(called).toBe(false);
-    }
-  });
-
   test('401 → auth', async () => {
     __setRerankTransportForTests(async () => new Response('Unauthorized', { status: 401 }));
     try {

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.test.ts

@@ -2,11 +2,6 @@ import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:tes
 import { mkdirSync, rmSync, writeFileSync } from 'fs';
 import { join } from 'path';
 import { tmpdir } from 'os';
-import * as fs from 'node:fs';
-import * as os from 'node:os';
-import * as path from 'node:path';
-import { withEnv } from './helpers/with-env.ts';
-import { logRerankFailure } from '../src/core/rerank-audit.ts';
 
 describe('doctor command', () => {
   test('doctor module exports runDoctor', async () => {
@@ -52,34 +47,6 @@ describe('doctor command', () => {
     expect(check.issues![0].action).toContain('trigger');
   });
 
-  test('reranker_health warns on repeated unknown rerank failures', async () => {
-    const { checkRerankerHealth } = await import('../src/commands/doctor.ts');
-    const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gbrain-rerank-doctor-'));
-    try {
-      await withEnv({ GBRAIN_AUDIT_DIR: tmpDir }, async () => {
-        for (let i = 0; i < 3; i++) {
-          logRerankFailure({
-            model: 'zeroentropyai:zerank-2',
-            reason: 'unknown',
-            query_hash: `unknown${i}`,
-            doc_count: 30,
-            error_summary: 'ZeroEntropy reranker requires ZEROENTROPY_API_KEY.',
-          });
-        }
-        const check = await checkRerankerHealth({
-          async getConfig(key: string): Promise<string | null> {
-            return key === 'search.reranker.enabled' ? 'true' : null;
-          },
-        } as any);
-        expect(check.status).toBe('warn');
-        expect(check.message).toContain('unknown');
-        expect(check.message).toContain('ZEROENTROPY_API_KEY');
-      });
-    } finally {
-      fs.rmSync(tmpDir, { recursive: true, force: true });
-    }
-  });
-
   test('runDoctor accepts null engine for filesystem-only mode', async () => {
     const { runDoctor } = await import('../src/commands/doctor.ts');
     // runDoctor should accept null engine — it runs filesystem checks only.

test/search/rerank.test.ts

@@ -12,14 +12,9 @@
  */
 
 import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
-import * as fs from 'node:fs';
-import * as os from 'node:os';
-import * as path from 'node:path';
 import { applyReranker, type RerankerOpts } from '../../src/core/search/rerank.ts';
 import { RerankError, type RerankResult } from '../../src/core/ai/gateway.ts';
-import { readRecentRerankFailures } from '../../src/core/rerank-audit.ts';
 import type { SearchResult } from '../../src/core/types.ts';
-import { withEnv } from '../helpers/with-env.ts';
 
 function makeResult(slug: string, score: number, chunk: string): SearchResult {
   return {
@@ -165,36 +160,6 @@ describe('applyReranker — fail-open on every RerankError reason', () => {
     expect(out).toEqual(results);
   });
 
-  test('missing gateway reranker API key fail-opens and audits auth', async () => {
-    const { configureGateway } = await import('../../src/core/ai/gateway.ts');
-    const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gbrain-rerank-search-'));
-    try {
-      await withEnv({ GBRAIN_AUDIT_DIR: tmpDir }, async () => {
-        configureGateway({
-          reranker_model: 'zeroentropyai:zerank-2',
-          env: {},
-        });
-
-        const results = [makeResult('a', 1.0, 'doc a')];
-        const out = await applyReranker('q', results, {
-          enabled: true,
-          topNIn: 1,
-          topNOut: null,
-          model: 'zeroentropyai:zerank-2',
-        });
-
-        expect(out).toEqual(results);
-        const failures = readRecentRerankFailures(1);
-        expect(failures).toHaveLength(1);
-        expect(failures[0]!.reason).toBe('auth');
-        expect(failures[0]!.error_summary).toContain('ZEROENTROPY_API_KEY');
-      });
-    } finally {
-      fs.rmSync(tmpDir, { recursive: true, force: true });
-      configureGateway({ env: { ZEROENTROPY_API_KEY: 'test-key' } });
-    }
-  });
-
   test('fail-open on non-RerankError throw too', async () => {
     const results = [makeResult('a', 1.0, 'a')];
     const opts: RerankerOpts = {

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({