fix(streaming): preserve recovered segments across channels

nanobot/agent/runner.py

@@ -613,6 +613,23 @@ class AgentRunner:
                     await hook.after_iteration(context)
                     continue
 
+            # Some streaming providers recover with a complete response but no
+            # content deltas. When an earlier length segment is already visible,
+            # emit this terminal segment into the same stream; otherwise the
+            # regular full response would duplicate the visible prefix.
+            if (
+                length_recovery_parts
+                and hook.wants_streaming()
+                and not context.streamed_content
+                and response.finish_reason != "error"
+                and not is_blank_text(clean)
+            ):
+                await hook.on_stream(
+                    context,
+                    _restore_outer_whitespace(clean, original_content),
+                )
+                context.streamed_content = True
+
             assistant_message: dict[str, Any] | None = None
             if response.finish_reason != "error" and not is_blank_text(clean):
                 assistant_message = build_assistant_message(

nanobot/channels/discord/runtime.py

@@ -497,6 +497,10 @@ class DiscordChannel(BaseChannel):
             self.logger.warning("client not ready; dropping stream delta")
             return
 
+        if stream_end and merge_next:
+            if not delta:
+                return
+            stream_end = False
         if stream_end:
             buf = self._stream_bufs.get(chat_id)
             if not buf or buf.message is None or not buf.text:

nanobot/channels/discord/tests/test_discord_channel.py

@@ -754,6 +754,36 @@ async def test_send_delta_streams_by_editing_message(monkeypatch) -> None:
     assert owner._stream_bufs == {}
 
 
+@pytest.mark.asyncio
+async def test_send_delta_merge_next_keeps_one_message(monkeypatch) -> None:
+    owner = DiscordChannel(DiscordConfig(enabled=True, allow_from=["*"]), MessageBus())
+    client = _FakeDiscordClient(owner, intents=None)
+    owner._client = client
+    owner._running = True
+    target = _FakeChannel(channel_id=123)
+    client.channels[123] = target
+
+    times = iter([1.0, 3.0, 5.0])
+    monkeypatch.setattr("nanobot.channels.discord.runtime.time.monotonic", lambda: next(times, 5.0))
+
+    await owner.send_delta(
+        "123",
+        "first-",
+        stream_id="s1",
+        stream_end=True,
+        merge_next=True,
+    )
+    await owner.send_delta("123", "second", stream_id="s1")
+    await owner.send_delta("123", "", stream_id="s1", stream_end=True)
+
+    assert target.sent_payloads == [{"content": "first-"}]
+    assert target.sent_messages[0].edits == [
+        {"content": "first-second"},
+        {"content": "first-second"},
+    ]
+    assert owner._stream_bufs == {}
+
+
 @pytest.mark.asyncio
 async def test_send_delta_stream_end_splits_oversized_reply(monkeypatch) -> None:
     owner = DiscordChannel(DiscordConfig(enabled=True, allow_from=["*"]), MessageBus())

nanobot/channels/feishu/runtime.py

@@ -2232,6 +2232,10 @@ class FeishuChannel(BaseChannel):
         rid_type = "chat_id" if chat_id.startswith("oc_") else "open_id"
 
         # --- stream end: final update or fallback ---
+        if stream_end and merge_next:
+            if not delta:
+                return
+            stream_end = False
         if stream_end:
             message_id = meta.get("message_id")
             # Only finalize the OnIt -> DONE reaction transition on the truly

nanobot/channels/feishu/tests/test_feishu_streaming.py

@@ -285,6 +285,27 @@ class TestSendDelta:
         settings_call = ch._client.cardkit.v1.card.settings.call_args[0][0]
         assert settings_call.body.sequence == 5  # after final content seq 4
 
+    @pytest.mark.asyncio
+    async def test_stream_end_merge_next_preserves_buffer(self):
+        ch = _make_channel()
+        ch._stream_bufs["oc_chat1"] = _FeishuStreamBuf(
+            text="first-",
+            card_id="card_1",
+            sequence=3,
+            last_edit=time.monotonic(),
+        )
+
+        await ch.send_delta(
+            "oc_chat1",
+            "boundary",
+            stream_end=True,
+            merge_next=True,
+        )
+
+        assert ch._stream_bufs["oc_chat1"].text == "first-boundary"
+        ch._client.cardkit.v1.card_element.content.assert_not_called()
+        ch._client.cardkit.v1.card.settings.assert_not_called()
+
     @pytest.mark.asyncio
     async def test_stream_end_fallback_when_no_card_id(self):
         """If card creation failed, stream_end falls back to a plain card message."""

nanobot/channels/matrix/runtime.py

@@ -602,6 +602,10 @@ class MatrixChannel(BaseChannel):
     ) -> None:
         relates_to = self._build_thread_relates_to(metadata)
 
+        if stream_end and merge_next:
+            if not delta:
+                return
+            stream_end = False
         if stream_end:
             stream_key = _matrix_stream_key(chat_id, stream_id)
             buf = self._stream_bufs.pop(stream_key, None)

nanobot/channels/matrix/tests/test_matrix_channel.py

@@ -1937,6 +1937,29 @@ async def test_send_delta_stream_end_replaces_existing_message() -> None:
     }
 
 
+@pytest.mark.asyncio
+async def test_send_delta_merge_next_preserves_buffer() -> None:
+    channel = MatrixChannel(_make_config(), MessageBus())
+    client = _FakeAsyncClient("", "", "", None)
+    channel.client = client
+    channel._stream_bufs["!room:matrix.org"] = matrix_module._StreamBuf(
+        text="first-",
+        event_id="event-1",
+        last_edit=100.0,
+    )
+    channel.monotonic_time = lambda: 100.1
+
+    await channel.send_delta(
+        "!room:matrix.org",
+        "boundary",
+        stream_end=True,
+        merge_next=True,
+    )
+
+    assert channel._stream_bufs["!room:matrix.org"].text == "first-boundary"
+    assert client.room_send_calls == []
+
+
 @pytest.mark.asyncio
 async def test_send_delta_keeps_same_room_stream_ids_independent(monkeypatch) -> None:
     channel = MatrixChannel(_make_config(), MessageBus())

nanobot/channels/telegram/runtime.py

@@ -931,6 +931,10 @@ class TelegramChannel(BaseChannel):
         meta = metadata or {}
         int_chat_id = int(chat_id)
 
+        if stream_end and merge_next:
+            if not delta:
+                return
+            stream_end = False
         if stream_end:
             buf = self._stream_bufs.get(chat_id)
             if not buf or not buf.message_id or not buf.text:

nanobot/channels/telegram/tests/test_telegram_channel.py

@@ -675,6 +675,33 @@ async def test_send_delta_stream_end_raises_and_keeps_buffer_on_failure() -> Non
     assert "123" in channel._stream_bufs
 
 
+@pytest.mark.asyncio
+async def test_send_delta_merge_next_preserves_buffer() -> None:
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"]),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+    channel._app.bot.edit_message_text = AsyncMock()
+    channel._stream_bufs["123"] = _StreamBuf(
+        text="first-",
+        message_id=7,
+        last_edit=float("inf"),
+        stream_id="s:0",
+    )
+
+    await channel.send_delta(
+        "123",
+        "boundary",
+        stream_id="s:0",
+        stream_end=True,
+        merge_next=True,
+    )
+
+    assert channel._stream_bufs["123"].text == "first-boundary"
+    channel._app.bot.edit_message_text.assert_not_awaited()
+
+
 @pytest.mark.asyncio
 async def test_send_delta_stream_end_treats_not_modified_as_success() -> None:
     from telegram.error import BadRequest

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()

tests/agent/test_loop_progress.py

@@ -580,6 +580,53 @@ class TestToolEventProgress:
         assert [event.merge_next for event in endings] == [True, False]
         assert {event.stream_id for event in [*deltas, *endings]} == {deltas[0].stream_id}
 
+    @pytest.mark.asyncio
+    async def test_length_recovery_streams_non_delta_terminal_segment(
+        self,
+        tmp_path: Path,
+    ) -> None:
+        bus = MessageBus()
+        provider = MagicMock()
+        provider.supports_progress_deltas = True
+        provider.get_default_model.return_value = "test-model"
+        call_count = 0
+
+        async def chat_stream_with_retry(*, on_content_delta, **kwargs):
+            nonlocal call_count
+            call_count += 1
+            if call_count == 1:
+                await on_content_delta("first-")
+                return LLMResponse(content="first-", finish_reason="length")
+            return LLMResponse(content="second", finish_reason="stop")
+
+        provider.chat_stream_with_retry = chat_stream_with_retry
+        provider.chat_with_retry = AsyncMock()
+        loop = AgentLoop(bus=bus, provider=provider, workspace=tmp_path, model="test-model")
+        _attach_webui_runtime_events(loop, bus)
+        loop.tools.get_definitions = MagicMock(return_value=[])
+        loop.consolidator.maybe_consolidate_by_tokens = AsyncMock(return_value=False)  # type: ignore[method-assign]
+
+        await loop._dispatch(InboundMessage(
+            channel="websocket",
+            sender_id="u1",
+            chat_id="chat1",
+            content="give a long answer",
+            metadata={"_wants_stream": True},
+        ))
+
+        outbound = []
+        while bus.outbound_size > 0:
+            outbound.append(await bus.consume_outbound())
+
+        deltas = [m.event for m in outbound if isinstance(m.event, StreamDeltaEvent)]
+        endings = [m.event for m in outbound if isinstance(m.event, StreamEndEvent)]
+        final = [m for m in outbound if m.content == "first-second"]
+
+        assert [event.content for event in deltas] == ["first-", "second"]
+        assert [event.merge_next for event in endings] == [True, False]
+        assert len(final) == 1
+        assert isinstance(final[0].event, StreamedResponseEvent)
+
     @pytest.mark.asyncio
     async def test_length_recovery_at_max_iterations_streams_only_missing_tail(
         self,