fix(streaming): preserve recovered segments across channels

nanobot/channels/weixin/runtime.py

@@ -1257,6 +1257,10 @@ class WeixinChannel(BaseChannel):
             return
         is_end = stream_end or bool(meta.get("_stream_end"))
         buffer_key = stream_id or chat_id
+        if is_end and merge_next:
+            if delta:
+                self._stream_buffers.setdefault(buffer_key, []).append(delta)
+            return
         # Accumulate intermediate deltas. The stream_end message's own content
         # (present when the manager coalesces deltas into the end message) is
         # folded into `full` below instead of appended here, so a send retry

nanobot/channels/weixin/tests/test_weixin_channel.py

@@ -1824,6 +1824,29 @@ async def test_stream_end_flushes_buffered_answer() -> None:
     assert "wx-user" not in channel._stream_buffers
 
 
+@pytest.mark.asyncio
+async def test_stream_end_merge_next_preserves_buffer_until_final_end() -> None:
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel._context_tokens["wx-user"] = "ctx-1"
+    channel._context_token_at["wx-user"] = time.time()
+    channel._send_text = AsyncMock()
+
+    await channel.send_delta(
+        "wx-user",
+        "first-",
+        stream_id="s1",
+        stream_end=True,
+        merge_next=True,
+    )
+    await channel.send_delta("wx-user", "second", stream_id="s1")
+    await channel.send_delta("wx-user", "", stream_id="s1", stream_end=True)
+
+    channel._send_text.assert_awaited_once_with("wx-user", "first-second", "ctx-1")
+    assert "s1" not in channel._stream_buffers
+
+
 @pytest.mark.asyncio
 async def test_stream_end_send_failure_keeps_buffer_for_retry() -> None:
     channel, _bus = _make_channel()