fix(wecom): treat "@bot /new" in group chats as a command (#8118)

WeCom leaves the bot mention in group message text, so `_publish_ws_inbound`
handed "@RobotA /new" to `is_known_channel_command`, which requires a bare
leading slash. The turn was classified as chat and the command never ran.

Strip leading mentions for the command lookup only, mirroring Feishu (#4229)
and DingTalk (#4724): ordinary chat keeps its mentions, and the stripped form
is what reaches ChannelManager so it parses `/new`. The comment spells out that
this drops any leading mention, not only the bot's -- WeCom text mentions carry
display names, so `aibotid` cannot be matched against them.

Recorded in CHANGELOG.md / CHANGELOG_zh.md under Unreleased -> Fixed.

Fixes #8099

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

CHANGELOG.md

@@ -55,6 +55,13 @@ This section accumulates work toward the **2.3.0** milestone
 
 ### Fixed
 
+- **channels:** A WeCom group command that follows the bot mention now runs as a
+  command. WeCom keeps the mention inside the message text (`@RobotA /new`), and
+  the classifier required a bare leading `/`, so `/new` and `/status` sent in a
+  group became chat turns. Leading mentions are skipped for the command lookup
+  only; ordinary chat keeps them and `/connect` is unchanged. Mirrors the Feishu
+  and DingTalk handling. ([#8118])
+  
 - **frontend:** **Share** in a sidebar chat's menu now copies a link to the
   deployment you are using. On `localhost` and `127.0.0.1`, the default
   `make dev` and Docker addresses, it copied a link to the hosted demo
@@ -16309,5 +16316,6 @@ with **180 merged pull requests** since the first 2.0 milestone tag.
 [#8069]: https://github.com/bytedance/deer-flow/issues/8069
 [#8071]: https://github.com/bytedance/deer-flow/issues/8071
 [#8072]: https://github.com/bytedance/deer-flow/pull/8072
+[#8118]: https://github.com/bytedance/deer-flow/pull/8118
 [#8126]: https://github.com/bytedance/deer-flow/pull/8126
 [#8131]: https://github.com/bytedance/deer-flow/pull/8131

CHANGELOG_zh.md

@@ -26,6 +26,10 @@
 
 ### 修复
 
+- **通道：** WeCom 群聊中 `@机器人 /new` 这类带提及的命令现在按命令执行。WeCom 会把提及保留在
+  正文里，而命令识别要求裸的前导 `/`，于是群里的 `/new`、`/status` 被当成聊天轮次。现在仅在命令
+  识别时跳过前导提及；普通聊天保留提及，`/connect` 行为不变。与飞书、钉钉的处理一致。([#8118])
+  
 - **前端：** 侧边栏对话菜单中的 **分享** 现在复制指向当前部署的链接。此前在 `localhost` 和
   `127.0.0.1`（`make dev` 与 Docker 的默认地址）上，复制的是托管演示站
   （`deer-flow-v2.vercel.app`）的链接：该链接无法打开对话，打开时还会把线程 ID 发送到外部主机。
@@ -12866,4 +12870,5 @@ DeerFlow 2.0 是围绕"超级智能体"框架的彻底重写，核心包含子
 [#8043]: https://github.com/bytedance/deer-flow/pull/8043
 [#8046]: https://github.com/bytedance/deer-flow/pull/8046
 [#8064]: https://github.com/bytedance/deer-flow/pull/8064
+[#8118]: https://github.com/bytedance/deer-flow/pull/8118
 [#8126]: https://github.com/bytedance/deer-flow/pull/8126

backend/app/channels/wecom.py

@@ -9,7 +9,7 @@ from collections.abc import Awaitable, Callable, Mapping
 from typing import Any, cast
 
 from app.channels.base import Channel, ChannelUnavailable, attachment_delivery_text
-from app.channels.commands import is_known_channel_command
+from app.channels.commands import is_known_channel_command, strip_leading_mentions
 from app.channels.connection_identity import attach_connection_identity
 from app.channels.message_bus import (
     InboundMessage,
@@ -583,7 +583,22 @@ class WeComChannel(Channel):
             if handled:
                 return
 
-        inbound_type = InboundMessageType.COMMAND if is_known_channel_command(text) else InboundMessageType.CHAT
+        # WeCom group chats deliver "@bot /new" with the mention left in the text
+        # (Slack/Discord strip their own bot mention upstream). Skip a leading
+        # mention only for the command path so ordinary chat keeps any @mentions
+        # intact for the agent; the stripped form also flows into the inbound so
+        # ChannelManager._handle_command parses the bare command. Mirrors
+        # DingTalkChannel / FeishuChannel.
+        #
+        # This drops *any* leading mention, not only the bot's: WeCom text
+        # mentions carry display names, so the frame's `aibotid` cannot be
+        # matched against them and "@alice /status" is indistinguishable from
+        # "@bot /status". Feishu and DingTalk accept the same tradeoff;
+        # test_member_mention_before_a_command_also_classifies pins it.
+        command_text = strip_leading_mentions(text)
+        inbound_type = InboundMessageType.COMMAND if is_known_channel_command(command_text) else InboundMessageType.CHAT
+        if inbound_type is InboundMessageType.COMMAND:
+            text = command_text
         inbound_metadata: dict[str, Any] = {
             "aibotid": body.get("aibotid"),
             "chattype": body.get("chattype"),

backend/tests/test_wecom_ws_text.py

@@ -10,10 +10,15 @@ with a null value, so chaining ``.get``/``.strip`` on it raised
 from __future__ import annotations
 
 import asyncio
+import sys
+import types
+from types import SimpleNamespace
 from typing import Any
 from unittest.mock import AsyncMock
 
-from app.channels.message_bus import MessageBus
+import pytest
+
+from app.channels.message_bus import InboundMessageType, MessageBus
 from app.channels.wecom import WeComChannel
 
 
@@ -70,3 +75,100 @@ class TestOnWsTextQuoteParsing:
         }
         _run(ch._on_ws_text(frame))
         ch._publish_ws_inbound.assert_called_once_with(frame, "T\nQuote message: Q")
+
+
+class TestGroupMentionBeforeCommand:
+    """WeCom keeps the bot mention in group text, so "@bot /new" has to be
+    classified as a command and reach the dispatcher without the mention.
+
+    Feishu (#4229) and DingTalk (#4724) already strip a leading mention on the
+    command path; ordinary chat must keep its mentions so the agent still sees
+    who was addressed.
+    """
+
+    @staticmethod
+    def _stub_aibot(monkeypatch: pytest.MonkeyPatch) -> None:
+        """Make ``_publish_ws_inbound`` run without the optional WeCom SDK."""
+        sdk = types.ModuleType("aibot")
+        sdk.generate_req_id = lambda prefix="": f"{prefix}-test"
+        monkeypatch.setitem(sys.modules, "aibot", sdk)
+
+    @staticmethod
+    def _live_channel() -> tuple[WeComChannel, MessageBus]:
+        bus = MessageBus()
+        channel = WeComChannel(bus=bus, config={})
+        channel._ws_client = SimpleNamespace(
+            reply=AsyncMock(),
+            reply_stream=AsyncMock(),
+            send_message=AsyncMock(),
+        )
+        return channel, bus
+
+    @staticmethod
+    def _group_frame(text: str) -> dict[str, Any]:
+        return {
+            "body": {
+                "msgid": "msg-mention",
+                "aibotid": "bot-1",
+                "chatid": "wr-team",
+                "chattype": "group",
+                "from": {"userid": "alice"},
+                "msgtype": "text",
+                "text": {"content": text},
+            }
+        }
+
+    @pytest.mark.parametrize(
+        ("text", "expected"),
+        [
+            ("@RobotA /new", "/new"),
+            ("@RobotA @_user_2 /status", "/status"),
+        ],
+    )
+    def test_leading_mention_before_command_is_stripped(
+        self,
+        monkeypatch: pytest.MonkeyPatch,
+        text: str,
+        expected: str,
+    ) -> None:
+        self._stub_aibot(monkeypatch)
+        channel, bus = self._live_channel()
+
+        _run(channel._on_ws_text(self._group_frame(text)))
+
+        inbound = bus.get_inbound_nowait()
+        assert inbound.msg_type is InboundMessageType.COMMAND
+        assert inbound.text == expected
+
+    def test_plain_chat_keeps_its_mention(
+        self,
+        monkeypatch: pytest.MonkeyPatch,
+    ) -> None:
+        self._stub_aibot(monkeypatch)
+        channel, bus = self._live_channel()
+
+        _run(channel._on_ws_text(self._group_frame("@RobotA hello there")))
+
+        inbound = bus.get_inbound_nowait()
+        assert inbound.msg_type is InboundMessageType.CHAT
+        assert inbound.text == "@RobotA hello there"
+
+    def test_member_mention_before_a_command_also_classifies(
+        self,
+        monkeypatch: pytest.MonkeyPatch,
+    ) -> None:
+        """Accepted tradeoff: a member's mention looks the same as the bot's.
+
+        WeCom text mentions are display names, so the frame's ``aibotid`` cannot
+        be matched against them; ``@alice /status`` is therefore classified as
+        the ``/status`` command, exactly as Feishu and DingTalk behave. Pinned
+        here so a future change to mention matching shows up in review.
+        """
+        self._stub_aibot(monkeypatch)
+        channel, bus = self._live_channel()
+
+        _run(channel._on_ws_text(self._group_frame("@alice /status")))
+
+        inbound = bus.get_inbound_nowait()
+        assert inbound.msg_type is InboundMessageType.COMMAND
+        assert inbound.text == "/status"