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/autopilot.ts

@@ -38,7 +38,6 @@ import { logSelfUpgrade } from '../core/audit/self-upgrade-audit.ts';
 import { detectInstallMethod } from './upgrade.ts';
 import { evaluateQuietHours } from '../core/minions/quiet-hours.ts';
 import { inspectLock } from '../core/db-lock.ts';
-import { registerCleanup } from '../core/process-cleanup.ts';
 
 /**
  * v0.37.7.0 #1162 — classify autopilot reconnect-loop errors.
@@ -434,37 +433,6 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
   let stopping = false;
   let childSupervisor: ChildWorkerSupervisor | null = null;
 
-  // #1872: graceful engine shutdown. On PGLite the cycle steps run INLINE in
-  // this process, so a hard `process.exit` mid-write (systemctl stop →
-  // SIGTERM) kills WASM Postgres with the WAL dirty and can corrupt the
-  // brain. Two exit paths must both close the engine:
-  //   - autopilot's own shutdown() below (owns SIGINT + internal stops like
-  //     max_crashes / cycle-failure-cap), and
-  //   - process-cleanup's SIGTERM handler (installed at cli.ts module load;
-  //     it runs the cleanup registry with a 3s deadline and then exits) —
-  //     which is why closeEngine is ALSO registered there.
-  // closeEngine aborts the in-flight inline cycle (runCycle checks the
-  // signal between phases and threads it into phase sub-work), gives it a
-  // short bounded window to wind down, then disconnects. PGLite's
-  // disconnect() drains the pending query and checkpoints before closing;
-  // a second call is a no-op (disconnect snapshots + nulls the handle), so
-  // both paths firing is safe.
-  const shutdownAbort = new AbortController();
-  let inflightInlineCycle: Promise<unknown> | null = null;
-  const closeEngine = async () => {
-    shutdownAbort.abort(new Error('autopilot shutdown'));
-    if (inflightInlineCycle) {
-      // ponytail: 2s cap keeps us inside process-cleanup's 3s deadline; a
-      // between-phase abort resolves instantly, a mid-phase one may not.
-      await Promise.race([
-        inflightInlineCycle.catch(() => { /* cycle errors already logged by the loop */ }),
-        new Promise((r) => setTimeout(r, 2_000)),
-      ]);
-    }
-    try { await engine.disconnect(); } catch { /* best-effort */ }
-  };
-  const deregisterEngineClose = registerCleanup('autopilot-engine-close', closeEngine);
-
   if (spawnManagedWorker) {
     const cliPath = resolveGbrainCliPath();
     // Cgroup-aware auto-sized RSS watchdog cap (issue #1678). The old flat
@@ -552,10 +520,6 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
         childSupervisor.killChild('SIGKILL');
       }
     }
-    // #1872: abort the in-flight inline cycle and close the engine BEFORE
-    // process.exit — a hard exit mid-write corrupts PGLite's WASM Postgres.
-    await closeEngine();
-    deregisterEngineClose();
     try { unlinkSync(lockPath); } catch { /* already gone */ }
     process.exit(0);
   };
@@ -1044,21 +1008,16 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
       // path's phase set). Now both converge on the same primitive.
       try {
         const { runCycle } = await import('../core/cycle.ts');
-        // #1872: track the promise so closeEngine can drain it on shutdown,
-        // and pass the abort signal so the cycle winds down between phases.
-        const cyclePromise = runCycle(engine, {
+        const report = await runCycle(engine, {
           brainDir: repoPath,
           // Autopilot daemon path: pulls by default (matches
           // pre-v0.17 autopilot behavior). CLI dream defaults false
           // for cron safety; that choice is scoped to dream only.
           pull: true,
-          signal: shutdownAbort.signal,
           yieldBetweenPhases: async () => {
             await new Promise(r => setImmediate(r));
           },
         });
-        inflightInlineCycle = cyclePromise;
-        const report = await cyclePromise.finally(() => { inflightInlineCycle = null; });
         // Only 'failed' (every attempted phase failed) trips the autopilot
         // circuit breaker. 'partial' means at least one phase warned or
         // failed while others ran — that's a soft signal, not a fatal

src/commands/dream.ts

@@ -26,7 +26,6 @@
 import type { BrainEngine } from '../core/engine.ts';
 import {
   runCycle,
-  resolveSourceForDir,
   ALL_PHASES,
   type CyclePhase,
   type CycleReport,
@@ -381,9 +380,9 @@ Options:
 
   --source <id>       Scope the cycle to one source so doctor's
                       cycle_freshness check sees a fresh stamp on
-                      completion. When omitted, gbrain derives the
-                      source from --dir / the configured checkout
-                      when it matches a source's local_path (#1869).
+                      completion. Without this, gbrain dream's
+                      timestamp never lands and federated brains
+                      see "stale cycle" forever.
   --source-id <id>    Alias for --source. Matches the v0.37.7.0+
                       naming used by import/extract/graph-query.
 
@@ -635,25 +634,6 @@ export async function runDream(engine: BrainEngine | null, args: string[]): Prom
     );
     process.exit(1);
   }
-
-  // #1869: a path-scoped run (--dir, or the configured sync.repo_path) whose
-  // directory matches a registered source's local_path IS that source's cycle
-  // — derive the source id so runCycle writes last_source_cycle_at /
-  // last_full_cycle_at on success and doctor's cycle_freshness check stops
-  // reading perpetually stale. Explicit --source still wins (resolved above).
-  // Fixed here at the command level, NOT in runCycle's stamp gate, so legacy
-  // global callers (autopilot-global-maintenance runs GLOBAL_PHASES with a
-  // brainDir and no sourceId) can't falsely stamp per-source freshness.
-  // A derived match on an archived source is skipped silently (falls back to
-  // legacy unscoped behavior) — stamping it would mask staleness on restore,
-  // mirroring the explicit --source archived guard above.
-  if (resolvedSourceId === undefined && engine !== null && brainDir !== null) {
-    const derived = await resolveSourceForDir(engine, brainDir);
-    if (derived !== undefined) {
-      const src = await fetchSource(engine, derived);
-      if (src?.archived !== true) resolvedSourceId = derived;
-    }
-  }
   // ─── issue #1678: bounded single-hold extract_atoms drain ──────────
   if (opts.drain) {
     if (engine === null) {

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.ts

@@ -855,16 +855,8 @@ 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).
- *
- * Exported for dream.ts (#1869): a `gbrain dream --dir <path>` run whose
- * path matches a registered source's local_path is a per-source cycle in
- * everything but name, so dream derives the source id up front and passes
- * it as opts.sourceId — landing the freshness stamp without changing
- * runCycle's stamp/lock semantics for legacy global callers (the
- * autopilot-global-maintenance handler runs GLOBAL_PHASES with a brainDir
- * and MUST NOT stamp per-source freshness; see rejected PR #2549).
  */
-export async function resolveSourceForDir(
+async function resolveSourceForDir(
   engine: BrainEngine,
   brainDir: string | null,
 ): Promise<string | undefined> {

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/autopilot-shutdown-engine-close.test.ts

@@ -1,63 +0,0 @@
-/**
- * #1872 — autopilot SIGTERM/SIGINT must close the engine before exit.
- *
- * On PGLite the cycle steps run INLINE in the autopilot process, so a hard
- * `process.exit` mid-write (systemctl stop → SIGTERM) kills WASM Postgres
- * with the WAL dirty and can corrupt the brain. Two exit paths must both
- * close the engine:
- *
- *   - autopilot's own shutdown() (owns SIGINT + internal stops like
- *     max_crashes / cycle-failure-cap), and
- *   - process-cleanup's SIGTERM handler (installed at cli.ts module load,
- *     which exits within its 3s cleanup deadline) — reached via the
- *     registered 'autopilot-engine-close' cleanup callback.
- *
- * Because the shutdown path is deep inside `runAutopilot()` (a long-running
- * daemon loop that ends in process.exit), a behavioral test would have to
- * spawn + signal a real daemon. Following the established precedent
- * (test/autopilot-supervisor-wiring.test.ts, test/autopilot-fanout-wiring.test.ts),
- * these static-shape regressions pin the load-bearing wiring instead.
- */
-import { describe, expect, it } from 'bun:test';
-import { readFileSync } from 'fs';
-import { join } from 'path';
-
-const AUTOPILOT_SRC = readFileSync(
-  join(import.meta.dir, '..', 'src', 'commands', 'autopilot.ts'),
-  'utf8',
-);
-
-describe('autopilot.ts graceful engine shutdown (#1872)', () => {
-  it('registers an engine-close callback in the process-cleanup registry (SIGTERM path)', () => {
-    // process-cleanup owns SIGTERM (installed at cli.ts:10) and hard-exits
-    // after its cleanup pass; without this registration the engine is never
-    // closed on `systemctl stop`.
-    expect(AUTOPILOT_SRC).toContain(
-      "import { registerCleanup } from '../core/process-cleanup.ts';",
-    );
-    expect(AUTOPILOT_SRC).toContain(
-      "registerCleanup('autopilot-engine-close', closeEngine)",
-    );
-  });
-
-  it('closeEngine aborts the in-flight inline cycle then disconnects the engine', () => {
-    // Abort first (runCycle checks the signal between phases and threads it
-    // into phase sub-work), bounded drain, then disconnect.
-    expect(AUTOPILOT_SRC).toMatch(
-      /const closeEngine = async \(\) => \{[\s\S]{0,900}shutdownAbort\.abort\([\s\S]{0,900}engine\.disconnect\(\)/,
-    );
-  });
-
-  it('the inline runCycle call carries the shutdown abort signal and is tracked as in-flight', () => {
-    // PGLite / --inline path: the cycle runs in-process, so shutdown must be
-    // able to (a) signal it to wind down and (b) await it before closing.
-    expect(AUTOPILOT_SRC).toMatch(/signal:\s*shutdownAbort\.signal/);
-    expect(AUTOPILOT_SRC).toMatch(/inflightInlineCycle\s*=\s*cyclePromise/);
-  });
-
-  it('shutdown() awaits closeEngine() before process.exit(0) (SIGINT + internal-stop path)', () => {
-    expect(AUTOPILOT_SRC).toMatch(
-      /await closeEngine\(\);[\s\S]{0,400}process\.exit\(0\)/,
-    );
-  });
-});

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/dream-dir-source-stamp.test.ts

@@ -1,99 +0,0 @@
-/**
- * #1869 — `gbrain dream --dir <path>` stamps cycle freshness when the path
- * matches a registered source's local_path.
- *
- * Pre-fix, only `--source <id>` runs wrote last_source_cycle_at /
- * last_full_cycle_at (runCycle's stamp gate reads opts.sourceId, and dream
- * never derived one from --dir), so a path-scoped brain showed doctor's
- * cycle_freshness as perpetually stale.
- *
- * The fix lives in dream.ts (derive the source id from the resolved brain
- * dir via resolveSourceForDir), NOT in runCycle's stamp gate — a runCycle-
- * wide change would make the autopilot-global-maintenance handler (global
- * phases, brainDir set, no sourceId) falsely stamp per-source freshness
- * (the #2194 poisoning class; see rejected PR #2549).
- *
- * Same real-PGLite/no-mocks discipline as test/dream.test.ts; same
- * GBRAIN_HOME isolation as test/cycle-last-full-cycle-at.test.ts (the
- * cycle's PGLite file lock lives under ~/.gbrain).
- */
-import { describe, test, expect, beforeAll, afterAll, beforeEach, afterEach } from 'bun:test';
-import { mkdtempSync, rmSync } from 'fs';
-import { join } from 'path';
-import { tmpdir } from 'os';
-import { PGLiteEngine } from '../src/core/pglite-engine.ts';
-import { resetPgliteState } from './helpers/reset-pglite.ts';
-import { runDream } from '../src/commands/dream.ts';
-import { withEnv } from './helpers/with-env.ts';
-
-let engine: PGLiteEngine;
-let brainDir: string;
-let gbrainHome: string;
-
-beforeAll(async () => {
-  engine = new PGLiteEngine();
-  await engine.connect({});
-  await engine.initSchema();
-}, 60_000);
-
-afterAll(async () => {
-  await engine.disconnect();
-});
-
-beforeEach(async () => {
-  await resetPgliteState(engine);
-  brainDir = mkdtempSync(join(tmpdir(), 'gbrain-dream-stamp-'));
-  gbrainHome = mkdtempSync(join(tmpdir(), 'gbrain-dream-stamp-home-'));
-}, 60_000);
-
-afterEach(() => {
-  rmSync(brainDir, { recursive: true, force: true });
-  rmSync(gbrainHome, { recursive: true, force: true });
-});
-
-async function seedSource(id: string, archived = false): Promise<void> {
-  await engine.executeRaw(
-    `INSERT INTO sources (id, name, local_path, config, archived, created_at)
-     VALUES ($1, $2, $3, '{}'::jsonb, $4, NOW())`,
-    [id, id, brainDir, archived],
-  );
-}
-
-async function readLastFullCycleAt(sourceId: string): Promise<string | null> {
-  const rows = await engine.executeRaw<{ config: Record<string, unknown> | null }>(
-    `SELECT config FROM sources WHERE id = $1`,
-    [sourceId],
-  );
-  const raw = rows[0]?.config?.last_full_cycle_at;
-  return typeof raw === 'string' ? raw : null;
-}
-
-describe('gbrain dream --dir <path> freshness stamp (#1869)', () => {
-  test('--dir matching a source local_path stamps last_full_cycle_at', async () => {
-    await withEnv({ GBRAIN_HOME: gbrainHome }, async () => {
-      await seedSource('path-scoped');
-      expect(await readLastFullCycleAt('path-scoped')).toBeNull();
-
-      const report = await runDream(engine, ['--dir', brainDir, '--phase', 'lint', '--json']);
-      expect(report).toBeTruthy();
-      if (report) expect(['ok', 'clean']).toContain(report.status);
-
-      // Pre-fix this stays null forever: dream never passed a sourceId, so
-      // runCycle's stamp gate skipped the write.
-      expect(await readLastFullCycleAt('path-scoped')).not.toBeNull();
-    });
-  }, 60_000);
-
-  test('--dir matching an ARCHIVED source does not stamp it', async () => {
-    await withEnv({ GBRAIN_HOME: gbrainHome }, async () => {
-      await seedSource('mothballed', true);
-
-      const report = await runDream(engine, ['--dir', brainDir, '--phase', 'lint', '--json']);
-      expect(report).toBeTruthy();
-
-      // Stamping an archived source would mask data staleness when it is
-      // later restored (mirrors the explicit --source archived guard).
-      expect(await readLastFullCycleAt('mothballed')).toBeNull();
-    });
-  }, 60_000);
-});

test/dream.test.ts

@@ -562,22 +562,12 @@ describe('runDream — --source / --source-id (v0.41.13)', () => {
 
   // ─── Back-compat: bare `gbrain dream` does NOT write per-source stamp ─
 
-  test('gbrain dream (no --source) stamps only the source whose local_path matches --dir (#1869)', async () => {
-    // Pre-#1869 this asserted NO source was ever stamped without an explicit
-    // --source — which is exactly the bug: a path-scoped `gbrain dream --dir`
-    // run never landed a freshness stamp and doctor's cycle_freshness stayed
-    // stale forever. New truth: the source whose local_path matches the
-    // resolved brain dir is derived and stamped; unrelated sources stay
-    // untouched (cross-source isolation).
-    await seedSource('alpha'); // local_path = repo → derived + stamped
-    await engine.executeRaw(
-      `INSERT INTO sources (id, name, local_path, config, archived, created_at)
-       VALUES ($1, $2, $3, '{}'::jsonb, false, NOW())`,
-      ['beta', 'beta', '/somewhere/else'],
-    );
+  test('gbrain dream (no --source) leaves all sources untouched (back-compat regression)', async () => {
+    await seedSource('alpha');
+    await seedSource('beta');
     const report = await runDream(engine, ['--dir', repo, '--phase', 'lint', '--json']);
     expect(report).toBeTruthy();
-    expect(await readLastFullCycleAt('alpha')).not.toBeNull();
+    expect(await readLastFullCycleAt('alpha')).toBeNull();
     expect(await readLastFullCycleAt('beta')).toBeNull();
   }, 60_000);
 

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({