diff --git a/nanobot/channels/wecom.py b/nanobot/channels/wecom.py
index 910f02489..a7d7f1fe2 100644
--- a/nanobot/channels/wecom.py
+++ b/nanobot/channels/wecom.py
@@ -513,23 +513,21 @@ class WecomChannel(BaseChannel):
                 return
 
             if frame:
-                if is_progress:
-                    # Progress messages (thinking text): send as plain reply, no streaming
-                    await self._client.reply(frame, {
-                        "msgtype": "text",
-                        "text": {"content": content},
-                    })
-                    logger.debug("WeCom progress sent to {}", msg.chat_id)
-                else:
-                    # Final response: use streaming reply for better UX
-                    stream_id = self._generate_req_id("stream")
-                    await self._client.reply_stream(
-                        frame,
-                        stream_id,
-                        content,
-                        finish=True,
-                    )
-                    logger.debug("WeCom message sent to {}", msg.chat_id)
+                # Both progress and final messages must use reply_stream (cmd="aibot_respond_msg").
+                # The plain reply() uses cmd="reply" which does not support "text" msgtype
+                # and causes errcode=40008 from WeCom API.
+                stream_id = self._generate_req_id("stream")
+                await self._client.reply_stream(
+                    frame,
+                    stream_id,
+                    content,
+                    finish=not is_progress,
+                )
+                logger.debug(
+                    "WeCom {} sent to {}",
+                    "progress" if is_progress else "message",
+                    msg.chat_id,
+                )
             else:
                 # No frame (e.g. cron push): proactive send only supports markdown
                 await self._client.send_message(msg.chat_id, {
diff --git a/tests/channels/test_wecom_channel.py b/tests/channels/test_wecom_channel.py
index 164c01ea2..b79c023ba 100644
--- a/tests/channels/test_wecom_channel.py
+++ b/tests/channels/test_wecom_channel.py
@@ -317,20 +317,21 @@ async def test_send_text_with_frame() -> None:
 
 @pytest.mark.asyncio
 async def test_send_progress_with_frame() -> None:
-    """When metadata has _progress, send uses reply (not reply_stream)."""
+    """When metadata has _progress, send uses reply_stream with finish=False."""
     channel = WecomChannel(WecomConfig(bot_id="b", secret="s", allow_from=["*"]), MessageBus())
     client = _FakeWeComClient()
     channel._client = client
+    channel._generate_req_id = lambda x: f"req_{x}"
     channel._chat_frames["chat1"] = _FakeFrame()
 
     await channel.send(
         OutboundMessage(channel="wecom", chat_id="chat1", content="thinking...", metadata={"_progress": True})
     )
 
-    client.reply.assert_called_once()
-    client.reply_stream.assert_not_called()
-    call_args = client.reply.call_args
-    assert call_args[0][1]["text"]["content"] == "thinking..."
+    client.reply_stream.assert_called_once()
+    call_args = client.reply_stream.call_args
+    assert call_args[0][2] == "thinking..."  # content arg
+    assert call_args[1]["finish"] is False
 
 
 @pytest.mark.asyncio