fix(cli): keep trace output under assistant header

Co-authored-by: Cursor <cursoragent@cursor.com>

nanobot/cli/commands.py

@@ -176,13 +176,15 @@ def _print_agent_response(
     response: str,
     render_markdown: bool,
     metadata: dict | None = None,
+    show_header: bool = True,
 ) -> None:
     """Render assistant response with consistent terminal styling."""
     console = _make_console()
     content = response or ""
     body = _response_renderable(content, render_markdown, metadata)
-    console.print()
-    console.print(f"[cyan]{__logo__} nanobot[/cyan]")
+    if show_header:
+        console.print()
+        console.print(f"[cyan]{__logo__} nanobot[/cyan]")
     console.print(body)
     console.print()
 
@@ -235,6 +237,8 @@ def _print_cli_progress_line(text: str, thinking: ThinkingSpinner | None, render
     target = renderer.console if renderer else console
     pause = renderer.pause_spinner() if renderer else (thinking.pause() if thinking else nullcontext())
     with pause:
+        if renderer:
+            renderer.ensure_header()
         target.print(f"  [dim]↳ {text}[/dim]")
 
 
@@ -245,6 +249,8 @@ def _print_cli_reasoning(text: str, thinking: ThinkingSpinner | None, renderer:
     target = renderer.console if renderer else console
     pause = renderer.pause_spinner() if renderer else (thinking.pause() if thinking else nullcontext())
     with pause:
+        if renderer:
+            renderer.ensure_header()
         target.print(f"[dim italic]✻ {text}[/dim italic]")
 
 
@@ -254,6 +260,7 @@ async def _print_interactive_progress_line(text: str, thinking: ThinkingSpinner
         return
     if renderer:
         with renderer.pause_spinner():
+            renderer.ensure_header()
             renderer.console.print(f"  [dim]↳ {text}[/dim]")
     else:
         with thinking.pause() if thinking else nullcontext():
@@ -275,7 +282,7 @@ async def _maybe_print_interactive_progress(
         return False
 
     is_tool_hint = metadata.get("_tool_hint", False)
-    is_reasoning = metadata.get("_reasoning", False)
+    is_reasoning = metadata.get("_reasoning", False) or metadata.get("_reasoning_delta", False)
     if is_reasoning:
         if channels_config and not channels_config.show_reasoning:
             return True
@@ -1118,10 +1125,14 @@ def agent(
             )
             if not renderer.streamed:
                 await renderer.close()
+                print_kwargs: dict[str, Any] = {}
+                if renderer.header_printed:
+                    print_kwargs["show_header"] = False
                 _print_agent_response(
                     response.content if response else "",
                     render_markdown=markdown,
                     metadata=response.metadata if response else None,
+                    **print_kwargs,
                 )
             await agent_loop.close_mcp()
 
@@ -1246,8 +1257,14 @@ def agent(
                             if content and not meta.get("_streamed"):
                                 if renderer:
                                     await renderer.close()
+                                print_kwargs: dict[str, Any] = {}
+                                if renderer and renderer.header_printed:
+                                    print_kwargs["show_header"] = False
                                 _print_agent_response(
-                                    content, render_markdown=markdown, metadata=meta,
+                                    content,
+                                    render_markdown=markdown,
+                                    metadata=meta,
+                                    **print_kwargs,
                                 )
                         elif renderer and not renderer.streamed:
                             await renderer.close()

nanobot/cli/stream.py

@@ -10,6 +10,7 @@ that plagued earlier approaches.
 from __future__ import annotations
 
 import sys
+from contextlib import contextmanager, nullcontext
 
 from rich.console import Console
 from rich.live import Live
@@ -93,6 +94,7 @@ class StreamRenderer:
         self._console = _make_console()
         self._live: Live | None = None
         self._spinner: ThinkingSpinner | None = None
+        self._header_printed = False
         self._start_spinner()
 
     def _renderable(self):
@@ -122,12 +124,41 @@ class StreamRenderer:
         """Expose the Live's console so external print functions can use it."""
         return self._console
 
+    @property
+    def header_printed(self) -> bool:
+        """Whether this turn has already opened the assistant output block."""
+        return self._header_printed
+
+    def ensure_header(self) -> None:
+        """Print the assistant header once, before trace or answer content."""
+        if self._header_printed:
+            return
+        self._stop_spinner()
+        self._console.print()
+        header = f"{self._bot_icon} {self._bot_name}" if self._bot_icon else self._bot_name
+        self._console.print(f"[cyan]{header}[/cyan]")
+        self._header_printed = True
+
     def pause_spinner(self):
-        """Context manager: temporarily stop spinner for clean output."""
-        if self._spinner:
-            return self._spinner.pause()
-        from contextlib import nullcontext
-        return nullcontext()
+        """Context manager: temporarily stop transient output for clean trace lines."""
+        @contextmanager
+        def _pause():
+            live_was_active = self._live is not None
+            if self._live:
+                # Trace/reasoning can arrive after answer streaming has started.
+                # Stop the transient Live view first so it does not leak a raw
+                # partial markdown frame before the trace line.
+                self._live.stop()
+                self._live = None
+            with self._spinner.pause() if self._spinner else nullcontext():
+                yield
+            # If more answer deltas arrive after the trace, on_delta() will
+            # create a fresh Live using the existing buffer. If no deltas arrive,
+            # on_end() prints the final buffered answer once.
+            if live_was_active:
+                return
+
+        return _pause()
 
     async def on_delta(self, delta: str) -> None:
         self.streamed = True
@@ -135,10 +166,7 @@ class StreamRenderer:
         if self._live is None:
             if not self._buf.strip():
                 return
-            self._stop_spinner()
-            self._console.print()
-            header = f"{self._bot_icon} {self._bot_name}" if self._bot_icon else self._bot_name
-            self._console.print(f"[cyan]{header}[/cyan]")
+            self.ensure_header()
             self._live = Live(
                 self._renderable(),
                 console=self._console,
@@ -174,7 +202,6 @@ class StreamRenderer:
 
     def pause(self):
         """Context manager: pause spinner for external output. No-op once streaming has started."""
-        from contextlib import nullcontext
         if self._spinner:
             return self._spinner.pause()
         return nullcontext()

tests/cli/test_cli_input.py

@@ -1,4 +1,5 @@
 import asyncio
+from contextlib import nullcontext
 from unittest.mock import AsyncMock, MagicMock, call, patch
 
 import pytest
@@ -96,6 +97,31 @@ def test_print_cli_progress_line_pauses_spinner_before_printing():
     assert order == ["start", "stop", "print", "start", "stop"]
 
 
+def test_print_cli_progress_line_opens_renderer_header_before_trace():
+    """Trace lines should appear under the assistant header, not under You."""
+    order: list[str] = []
+    renderer = MagicMock()
+    renderer.console.print.side_effect = lambda *_args, **_kwargs: order.append("print")
+    renderer.ensure_header.side_effect = lambda: order.append("header")
+    renderer.pause_spinner.return_value = nullcontext()
+
+    commands._print_cli_progress_line("tool running", None, renderer)
+
+    assert order == ["header", "print"]
+
+
+def test_print_cli_progress_line_stops_live_before_trace():
+    """A trace line should not leak the current transient Live frame."""
+    mock_live = MagicMock()
+    renderer = stream_mod.StreamRenderer(show_spinner=False)
+    renderer._live = mock_live
+
+    commands._print_cli_progress_line("tool running", None, renderer)
+
+    mock_live.stop.assert_called_once()
+    assert renderer._live is None
+
+
 @pytest.mark.asyncio
 async def test_print_interactive_progress_line_pauses_spinner_before_printing():
     """Interactive progress output should also pause spinner cleanly."""

tests/cli/test_interactive_retry_wait.py

@@ -50,6 +50,25 @@ async def test_reasoning_displayed_when_show_reasoning_enabled():
     assert calls == ["Let me think about this..."]
 
 
+@pytest.mark.asyncio
+async def test_reasoning_delta_displayed_when_show_reasoning_enabled():
+    """Streamed reasoning delta frames should use the reasoning renderer."""
+    calls: list[str] = []
+    channels_config = SimpleNamespace(
+        send_progress=True, send_tool_hints=False, show_reasoning=True,
+    )
+    msg = SimpleNamespace(
+        content="I should search first.",
+        metadata={"_progress": True, "_reasoning_delta": True},
+    )
+
+    with patch("nanobot.cli.commands._print_cli_reasoning", side_effect=lambda t, th, r=None: calls.append(t)):
+        handled = await commands._maybe_print_interactive_progress(msg, None, channels_config)
+
+    assert handled is True
+    assert calls == ["I should search first."]
+
+
 @pytest.mark.asyncio
 async def test_reasoning_hidden_when_show_reasoning_disabled():
     """Reasoning content should be suppressed when show_reasoning is False."""