diff --git a/cli.py b/cli.py
index c82e85dc..87f1c1a7 100755
--- a/cli.py
+++ b/cli.py
@@ -45,6 +45,11 @@ from prompt_toolkit.widgets import TextArea
 from prompt_toolkit.key_binding import KeyBindings
 from prompt_toolkit import print_formatted_text as _pt_print
 from prompt_toolkit.formatted_text import ANSI as _PT_ANSI
+try:
+    from prompt_toolkit.cursor_shapes import CursorShape
+    _STEADY_CURSOR = CursorShape.BLOCK  # Non-blinking block cursor
+except (ImportError, AttributeError):
+    _STEADY_CURSOR = None
 import threading
 import queue
 
@@ -1187,6 +1192,7 @@ class HermesCLI:
         # History file for persistent input recall across sessions
         self._history_file = Path.home() / ".hermes_history"
         self._last_invalidate: float = 0.0  # throttle UI repaints
+        self._spinner_text: str = ""  # thinking spinner text for TUI
 
     def _invalidate(self, min_interval: float = 0.25) -> None:
         """Throttled UI repaint — prevents terminal blinking on slow/SSH connections."""
@@ -1250,6 +1256,11 @@ class HermesCLI:
 
         return changed
 
+    def _on_thinking(self, text: str) -> None:
+        """Called by agent when thinking starts/stops. Updates TUI spinner."""
+        self._spinner_text = text or ""
+        self._invalidate()
+
     def _ensure_runtime_credentials(self) -> bool:
         """
         Ensure runtime credentials are resolved before agent use.
@@ -1388,6 +1399,7 @@ class HermesCLI:
                 clarify_callback=self._clarify_callback,
                 honcho_session_key=self.session_id,
                 fallback_model=self._fallback_model,
+                thinking_callback=self._on_thinking,
             )
             # Apply any pending title now that the session exists in the DB
             if self._pending_title and self._session_db:
@@ -3666,6 +3678,20 @@ class HermesCLI:
             # right up against the top rule of the input area
             return 1 if cli_ref._agent_running else 0
 
+        def get_spinner_text():
+            txt = cli_ref._spinner_text
+            if not txt:
+                return []
+            return [('class:hint', f'  {txt}')]
+
+        def get_spinner_height():
+            return 1 if cli_ref._spinner_text else 0
+
+        spinner_widget = Window(
+            content=FormattedTextControl(get_spinner_text),
+            height=get_spinner_height,
+        )
+
         spacer = Window(
             content=FormattedTextControl(get_hint_text),
             height=get_hint_height,
@@ -3848,6 +3874,7 @@ class HermesCLI:
                 sudo_widget,
                 approval_widget,
                 clarify_widget,
+                spinner_widget,
                 spacer,
                 input_rule_top,
                 image_bar,
@@ -3902,6 +3929,7 @@ class HermesCLI:
             style=style,
             full_screen=False,
             mouse_support=False,
+            **({'cursor': _STEADY_CURSOR} if _STEADY_CURSOR is not None else {}),
         )
         self._app = app  # Store reference for clarify_callback
         
@@ -3970,6 +3998,7 @@ class HermesCLI:
                         self.chat(user_input, images=submit_images or None)
                     finally:
                         self._agent_running = False
+                        self._spinner_text = ""
                         app.invalidate()  # Refresh status line
                     
                 except Exception as e:
diff --git a/run_agent.py b/run_agent.py
index f03d3cb1..cd6be255 100644
--- a/run_agent.py
+++ b/run_agent.py
@@ -172,6 +172,7 @@ class AIAgent:
         provider_data_collection: str = None,
         session_id: str = None,
         tool_progress_callback: callable = None,
+        thinking_callback: callable = None,
         clarify_callback: callable = None,
         step_callback: callable = None,
         max_tokens: int = None,
@@ -256,6 +257,7 @@ class AIAgent:
             self.api_mode = "chat_completions"
 
         self.tool_progress_callback = tool_progress_callback
+        self.thinking_callback = thinking_callback
         self.clarify_callback = clarify_callback
         self.step_callback = step_callback
         self._last_reported_tool = None  # Track for "new tool" mode
@@ -3325,9 +3327,13 @@ class AIAgent:
                 # Animated thinking spinner in quiet mode
                 face = random.choice(KawaiiSpinner.KAWAII_THINKING)
                 verb = random.choice(KawaiiSpinner.THINKING_VERBS)
-                spinner_type = random.choice(['brain', 'sparkle', 'pulse', 'moon', 'star'])
-                thinking_spinner = KawaiiSpinner(f"{face} {verb}...", spinner_type=spinner_type)
-                thinking_spinner.start()
+                if self.thinking_callback:
+                    # CLI TUI mode: use prompt_toolkit widget instead of raw spinner
+                    self.thinking_callback(f"{face} {verb}...")
+                else:
+                    spinner_type = random.choice(['brain', 'sparkle', 'pulse', 'moon', 'star'])
+                    thinking_spinner = KawaiiSpinner(f"{face} {verb}...", spinner_type=spinner_type)
+                    thinking_spinner.start()
             
             # Log request details if verbose
             if self.verbose_logging:
@@ -3364,6 +3370,8 @@ class AIAgent:
                     if thinking_spinner:
                         thinking_spinner.stop("")
                         thinking_spinner = None
+                    if self.thinking_callback:
+                        self.thinking_callback("")
                     
                     if not self.quiet_mode:
                         print(f"{self.log_prefix}⏱️  API call completed in {api_duration:.2f}s")
@@ -3404,6 +3412,8 @@ class AIAgent:
                         if thinking_spinner:
                             thinking_spinner.stop(f"(´;ω;`) oops, retrying...")
                             thinking_spinner = None
+                        if self.thinking_callback:
+                            self.thinking_callback("")
                         
                         # This is often rate limiting or provider returning malformed response
                         retry_count += 1
@@ -3573,6 +3583,8 @@ class AIAgent:
                     if thinking_spinner:
                         thinking_spinner.stop("")
                         thinking_spinner = None
+                    if self.thinking_callback:
+                        self.thinking_callback("")
                     api_elapsed = time.time() - api_start_time
                     print(f"{self.log_prefix}⚡ Interrupted during API call.")
                     self._persist_session(messages, conversation_history)
@@ -3585,6 +3597,8 @@ class AIAgent:
                     if thinking_spinner:
                         thinking_spinner.stop(f"(╥_╥) error, retrying...")
                         thinking_spinner = None
+                    if self.thinking_callback:
+                        self.thinking_callback("")
 
                     status_code = getattr(api_error, "status_code", None)
                     if (