fix: prevent reasoning box from rendering 3x during tool-calling loops (#3405)

Two independent bugs caused the reasoning box to appear three times when
the model produced reasoning + tool_calls:

Bug A: _build_assistant_message() re-fired reasoning_callback with the full
reasoning text even when streaming had already displayed it. The original
guard only checked structured reasoning_content deltas, but reasoning also
arrives via content tag extraction (<REASONING_SCRATCHPAD>/<think> tags
in delta.content), which went through _fire_stream_delta not
_fire_reasoning_delta. Fix: skip the callback entirely when streaming is
active — both paths display reasoning during the stream. Any reasoning not
shown during streaming is caught by the CLI post-response fallback.

Bug B: The post-response reasoning display checked _reasoning_stream_started,
but that flag was reset by _reset_stream_state() during intermediate turn
boundaries (when stream_delta_callback(None) fires between tool calls).
Introduced _reasoning_shown_this_turn flag that persists across the tool
loop and is only reset at the start of each user turn.

Live-tested in PTY: reasoning now shows exactly once per API call, no
duplicates across tool-calling loops.

cli.py

@@ -1625,6 +1625,7 @@ class HermesCLI:
         if not text:
             return
         self._reasoning_stream_started = True
+        self._reasoning_shown_this_turn = True
         if getattr(self, "_stream_box_opened", False):
             return
 
@@ -5545,6 +5546,10 @@ class HermesCLI:
 
             # Reset streaming display state for this turn
             self._reset_stream_state()
+            # Separate from _reset_stream_state because this must persist
+            # across intermediate turn boundaries (tool-calling loops) — only
+            # reset at the start of each user turn.
+            self._reasoning_shown_this_turn = False
 
             # --- Streaming TTS setup ---
             # When ElevenLabs is the TTS provider and sounddevice is available,
@@ -5759,8 +5764,13 @@ class HermesCLI:
             response_previewed = result.get("response_previewed", False) if result else False
 
             # Display reasoning (thinking) box if enabled and available.
-            # Skip when streaming already showed reasoning live.
-            if self.show_reasoning and result and not self._reasoning_stream_started:
+            # Skip when streaming already showed reasoning live.  Use the
+            # turn-persistent flag (_reasoning_shown_this_turn) instead of
+            # _reasoning_stream_started — the latter gets reset during
+            # intermediate turn boundaries (tool-calling loops), which caused
+            # the reasoning box to re-render after the final response.
+            _reasoning_already_shown = getattr(self, '_reasoning_shown_this_turn', False)
+            if self.show_reasoning and result and not _reasoning_already_shown:
                 reasoning = result.get("last_reasoning")
                 if reasoning:
                     w = shutil.get_terminal_size().columns