From e3bc985a6ea2d8ab89c08ce9f64ae25fdef876f2 Mon Sep 17 00:00:00 2001
From: Ke He <koendrunk@gmail.com>
Date: Wed, 29 Apr 2026 12:56:56 +0800
Subject: [PATCH] fix(shared): preserve unicode slug labels

Fixes #58932.

Carries forward #58942 and #58995.

Thanks @fengqing-git, @Starhappysh, and @koen666.
---
 CHANGELOG.md                            |  1 +
 src/shared/string-normalization.test.ts | 41 +++++++++++++++++++++++++
 src/shared/string-normalization.ts      | 12 +++++---
 3 files changed, 50 insertions(+), 4 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 000aa66e78c..d58e0a29a44 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -14,6 +14,7 @@ Docs: https://docs.openclaw.ai
 ### Fixes
 
 - Plugin SDK: add tracked Discord component-message helpers and a Telegram account-resolution compatibility facade, so existing plugins using those subpaths resolve while new plugins stay on generic channel SDK contracts. Thanks @vincentkoc.
+- Shared labels: preserve Unicode combining marks and NFC-equivalent accented text in group/channel slug normalization so non-Latin labels no longer lose meaningful characters. Fixes #58932; carries forward #58942 and #58995. Thanks @fengqing-git, @Starhappysh, and @koen666.
 - Docs/Hetzner: clarify that SSH tunnel access requires `AllowTcpForwarding local` before running `ssh -L`, so hardened VPS sshd configs do not block loopback Gateway access. Fixes #54557; carries forward #54564; refs #54954. Thanks @satishkc7, @blackstrype, and @Aftabbs.
 - Gateway/shutdown: report structured shutdown warnings and HTTP close timeout warnings through `ShutdownResult` while preserving lifecycle hook hardening. Carries forward #41296. Thanks @edenfunf.
 - Plugins/QA: prebuild the private QA channel runtime before plugin gauntlet source runs so wrapper CPU/RSS measurements are not polluted by private QA dist rebuild work. Thanks @vincentkoc.
diff --git a/src/shared/string-normalization.test.ts b/src/shared/string-normalization.test.ts
index e0f8c8ae900..5e49c36ed14 100644
--- a/src/shared/string-normalization.test.ts
+++ b/src/shared/string-normalization.test.ts
@@ -45,4 +45,45 @@ describe("shared/string-normalization", () => {
     expect(normalizeAtHashSlug("###__Room  Name__")).toBe("room-name");
     expect(normalizeAtHashSlug("@@@___")).toBe("");
   });
+
+  it.each([
+    ["技术讨论组", "技术讨论组"],
+    ["  AI 助手群  ", "ai-助手群"],
+    ["友達グループ", "友達グループ"],
+    ["개발자 모임", "개발자-모임"],
+    ["Team 技术讨论", "team-技术讨论"],
+    ["#OpenClaw中文群", "#openclaw中文群"],
+    ["Команда разработки", "команда-разработки"],
+    ["فريق التطوير", "فريق-التطوير"],
+  ])("preserves Unicode letters in normalizeHyphenSlug: %s", (input, expected) => {
+    expect(normalizeHyphenSlug(input)).toBe(expected);
+  });
+
+  it.each([
+    ["Cafe\u0301 Team", "café-team"],
+    ["हिन्दी चर्चा", "हिन्दी-चर्चा"],
+    ["ห้อง แช็ต", "ห้อง-แช็ต"],
+  ])("preserves combining marks in normalizeHyphenSlug: %s", (input, expected) => {
+    expect(normalizeHyphenSlug(input)).toBe(expected);
+  });
+
+  it.each([
+    ["#技术频道", "技术频道"],
+    ["@中文群组", "中文群组"],
+    ["#日本語チャンネル", "日本語チャンネル"],
+    ["#한국어채널", "한국어채널"],
+    ["#Команда разработки", "команда-разработки"],
+    ["@فريق التطوير", "فريق-التطوير"],
+    ["#OpenClaw中文群", "openclaw中文群"],
+  ])("preserves Unicode letters in normalizeAtHashSlug: %s", (input, expected) => {
+    expect(normalizeAtHashSlug(input)).toBe(expected);
+  });
+
+  it.each([
+    ["#Cafe\u0301_Team", "café-team"],
+    ["@हिन्दी चर्चा", "हिन्दी-चर्चा"],
+    ["#ห้อง แช็ต", "ห้อง-แช็ต"],
+  ])("preserves combining marks in normalizeAtHashSlug: %s", (input, expected) => {
+    expect(normalizeAtHashSlug(input)).toBe(expected);
+  });
 });
diff --git a/src/shared/string-normalization.ts b/src/shared/string-normalization.ts
index f9e8eec03ec..ea09ebdf0a5 100644
--- a/src/shared/string-normalization.ts
+++ b/src/shared/string-normalization.ts
@@ -51,23 +51,27 @@ export function normalizeCsvOrLooseStringList(value: unknown): string[] {
   return [];
 }
 
+function normalizeSlugInput(raw?: string | null) {
+  return (normalizeOptionalLowercaseString(raw) ?? "").normalize("NFC");
+}
+
 export function normalizeHyphenSlug(raw?: string | null) {
-  const trimmed = normalizeOptionalLowercaseString(raw) ?? "";
+  const trimmed = normalizeSlugInput(raw);
   if (!trimmed) {
     return "";
   }
   const dashed = trimmed.replace(/\s+/g, "-");
-  const cleaned = dashed.replace(/[^a-z0-9#@._+-]+/g, "-");
+  const cleaned = dashed.replace(/[^\p{L}\p{M}\p{N}#@._+-]+/gu, "-");
   return cleaned.replace(/-{2,}/g, "-").replace(/^[-.]+|[-.]+$/g, "");
 }
 
 export function normalizeAtHashSlug(raw?: string | null) {
-  const trimmed = normalizeOptionalLowercaseString(raw) ?? "";
+  const trimmed = normalizeSlugInput(raw);
   if (!trimmed) {
     return "";
   }
   const withoutPrefix = trimmed.replace(/^[@#]+/, "");
   const dashed = withoutPrefix.replace(/[\s_]+/g, "-");
-  const cleaned = dashed.replace(/[^a-z0-9-]+/g, "-");
+  const cleaned = dashed.replace(/[^\p{L}\p{M}\p{N}-]+/gu, "-");
   return cleaned.replace(/-{2,}/g, "-").replace(/^-+|-+$/g, "");
 }