Merge pull request #921 from NousResearch/hermes/hermes-ece5a45c

feat(cli): add /reasoning command for effort level and display toggle

cli-config.yaml.example

@@ -674,6 +674,11 @@ display:
   # Works over SSH. Most terminals can be configured to flash the taskbar or play a sound.
   bell_on_complete: false
 
+  # Show model reasoning/thinking before each response.
+  # When enabled, a dim box shows the model's thought process above the response.
+  # Toggle at runtime with /reasoning show or /reasoning hide.
+  show_reasoning: false
+
   # ───────────────────────────────────────────────────────────────────────────
   # Skin / Theme
   # ───────────────────────────────────────────────────────────────────────────

cli.py

@@ -205,6 +205,7 @@ def load_cli_config() -> Dict[str, Any]:
         "display": {
             "compact": False,
             "resume_display": "full",
+            "show_reasoning": False,
             "skin": "default",
         },
         "clarify": {
@@ -1123,6 +1124,8 @@ class HermesCLI:
         self.resume_display = CLI_CONFIG["display"].get("resume_display", "full")
         # bell_on_complete: play terminal bell (\a) when agent finishes a response
         self.bell_on_complete = CLI_CONFIG["display"].get("bell_on_complete", False)
+        # show_reasoning: display model thinking/reasoning before the response
+        self.show_reasoning = CLI_CONFIG["display"].get("show_reasoning", False)
         self.verbose = verbose if verbose is not None else (self.tool_progress_mode == "verbose")
         
         # Configuration - priority: CLI args > env vars > config file
@@ -1497,6 +1500,7 @@ class HermesCLI:
                 platform="cli",
                 session_db=self._session_db,
                 clarify_callback=self._clarify_callback,
+                reasoning_callback=self._on_reasoning if self.show_reasoning else None,
                 honcho_session_key=self.session_id,
                 fallback_model=self._fallback_model,
                 thinking_callback=self._on_thinking,
@@ -2850,6 +2854,8 @@ class HermesCLI:
             self._show_gateway_status()
         elif cmd_lower == "/verbose":
             self._toggle_verbose()
+        elif cmd_lower.startswith("/reasoning"):
+            self._handle_reasoning_command(cmd_original)
         elif cmd_lower == "/compress":
             self._manual_compress()
         elif cmd_lower == "/usage":
@@ -3075,6 +3081,75 @@ class HermesCLI:
         }
         self.console.print(labels.get(self.tool_progress_mode, ""))
 
+    def _handle_reasoning_command(self, cmd: str):
+        """Handle /reasoning — manage effort level and display toggle.
+
+        Usage:
+            /reasoning              Show current effort level and display state
+            /reasoning <level>      Set reasoning effort (none, low, medium, high, xhigh)
+            /reasoning show|on      Show model thinking/reasoning in output
+            /reasoning hide|off     Hide model thinking/reasoning from output
+        """
+        parts = cmd.strip().split(maxsplit=1)
+
+        if len(parts) < 2:
+            # Show current state
+            rc = self.reasoning_config
+            if rc is None:
+                level = "medium (default)"
+            elif rc.get("enabled") is False:
+                level = "none (disabled)"
+            else:
+                level = rc.get("effort", "medium")
+            display_state = "on" if self.show_reasoning else "off"
+            _cprint(f"  {_GOLD}Reasoning effort: {level}{_RST}")
+            _cprint(f"  {_GOLD}Reasoning display: {display_state}{_RST}")
+            _cprint(f"  {_DIM}Usage: /reasoning <none|low|medium|high|xhigh|show|hide>{_RST}")
+            return
+
+        arg = parts[1].strip().lower()
+
+        # Display toggle
+        if arg in ("show", "on"):
+            self.show_reasoning = True
+            if self.agent:
+                self.agent.reasoning_callback = self._on_reasoning
+            _cprint(f"  {_GOLD}Reasoning display: ON{_RST}")
+            _cprint(f"  {_DIM}Model thinking will be shown during and after each response.{_RST}")
+            return
+        if arg in ("hide", "off"):
+            self.show_reasoning = False
+            if self.agent:
+                self.agent.reasoning_callback = None
+            _cprint(f"  {_GOLD}Reasoning display: OFF{_RST}")
+            return
+
+        # Effort level change
+        parsed = _parse_reasoning_config(arg)
+        if parsed is None:
+            _cprint(f"  {_DIM}(._.) Unknown argument: {arg}{_RST}")
+            _cprint(f"  {_DIM}Valid levels: none, low, minimal, medium, high, xhigh{_RST}")
+            _cprint(f"  {_DIM}Display:      show, hide{_RST}")
+            return
+
+        self.reasoning_config = parsed
+        self.agent = None  # Force agent re-init with new reasoning config
+
+        if save_config_value("agent.reasoning_effort", arg):
+            _cprint(f"  {_GOLD}Reasoning effort set to '{arg}' (saved to config){_RST}")
+        else:
+            _cprint(f"  {_GOLD}Reasoning effort set to '{arg}' (session only){_RST}")
+
+    def _on_reasoning(self, reasoning_text: str):
+        """Callback for intermediate reasoning display during tool-call loops."""
+        lines = reasoning_text.strip().splitlines()
+        if len(lines) > 5:
+            preview = "\n".join(lines[:5])
+            preview += f"\n  ... ({len(lines) - 5} more lines)"
+        else:
+            preview = reasoning_text.strip()
+        _cprint(f"  {_DIM}[thinking] {preview}{_RST}")
+
     def _manual_compress(self):
         """Manually trigger context compression on the current conversation."""
         if not self.conversation_history or len(self.conversation_history) < 4:
@@ -3544,6 +3619,24 @@ class HermesCLI:
                 if response and pending_message:
                     response = response + "\n\n---\n_[Interrupted - processing new message]_"
             
+            # Display reasoning (thinking) box if enabled and available
+            if self.show_reasoning and result:
+                reasoning = result.get("last_reasoning")
+                if reasoning:
+                    w = shutil.get_terminal_size().columns
+                    r_label = " Reasoning "
+                    r_fill = w - 2 - len(r_label)
+                    r_top = f"{_DIM}┌─{r_label}{'─' * max(r_fill - 1, 0)}┐{_RST}"
+                    r_bot = f"{_DIM}└{'─' * (w - 2)}┘{_RST}"
+                    # Collapse long reasoning: show first 10 lines
+                    lines = reasoning.strip().splitlines()
+                    if len(lines) > 10:
+                        display_reasoning = "\n".join(lines[:10])
+                        display_reasoning += f"\n{_DIM}  ... ({len(lines) - 10} more lines){_RST}"
+                    else:
+                        display_reasoning = reasoning.strip()
+                    _cprint(f"\n{r_top}\n{_DIM}{display_reasoning}{_RST}\n{r_bot}")
+
             if response:
                 # Use a Rich Panel for the response box — adapts to terminal
                 # width at render time instead of hard-coding border length.

hermes_cli/commands.py

@@ -35,6 +35,7 @@ COMMANDS_BY_CATEGORY = {
         "/prompt": "View/set custom system prompt",
         "/personality": "Set a predefined personality",
         "/verbose": "Cycle tool progress display: off → new → all → verbose",
+        "/reasoning": "Manage reasoning effort and display (usage: /reasoning [level|show|hide])",
         "/skin": "Show or change the display skin/theme",
     },
     "Tools & Skills": {

hermes_cli/config.py

@@ -143,6 +143,7 @@ DEFAULT_CONFIG = {
         "personality": "kawaii",
         "resume_display": "full",
         "bell_on_complete": False,
+        "show_reasoning": False,
         "skin": "default",
     },
     
@@ -1034,6 +1035,14 @@ def show_config():
     print(f"  Max turns:    {config.get('agent', {}).get('max_turns', DEFAULT_CONFIG['agent']['max_turns'])}")
     print(f"  Toolsets:     {', '.join(config.get('toolsets', ['all']))}")
     
+    # Display
+    print()
+    print(color("◆ Display", Colors.CYAN, Colors.BOLD))
+    display = config.get('display', {})
+    print(f"  Personality:  {display.get('personality', 'kawaii')}")
+    print(f"  Reasoning:    {'on' if display.get('show_reasoning', False) else 'off'}")
+    print(f"  Bell:         {'on' if display.get('bell_on_complete', False) else 'off'}")
+
     # Terminal
     print()
     print(color("◆ Terminal", Colors.CYAN, Colors.BOLD))

run_agent.py

@@ -173,6 +173,7 @@ class AIAgent:
         session_id: str = None,
         tool_progress_callback: callable = None,
         thinking_callback: callable = None,
+        reasoning_callback: callable = None,
         clarify_callback: callable = None,
         step_callback: callable = None,
         max_tokens: int = None,
@@ -260,6 +261,7 @@ class AIAgent:
 
         self.tool_progress_callback = tool_progress_callback
         self.thinking_callback = thinking_callback
+        self.reasoning_callback = reasoning_callback
         self.clarify_callback = clarify_callback
         self.step_callback = step_callback
         self._last_reported_tool = None  # Track for "new tool" mode
@@ -2420,6 +2422,12 @@ class AIAgent:
             preview = reasoning_text[:100] + "..." if len(reasoning_text) > 100 else reasoning_text
             logging.debug(f"Captured reasoning ({len(reasoning_text)} chars): {preview}")
 
+        if reasoning_text and self.reasoning_callback:
+            try:
+                self.reasoning_callback(reasoning_text)
+            except Exception:
+                pass
+
         msg = {
             "role": "assistant",
             "content": assistant_message.content or "",
@@ -4470,9 +4478,17 @@ class AIAgent:
         if final_response and not interrupted:
             self._honcho_sync(original_user_message, final_response)
 
+        # Extract reasoning from the last assistant message (if any)
+        last_reasoning = None
+        for msg in reversed(messages):
+            if msg.get("role") == "assistant" and msg.get("reasoning"):
+                last_reasoning = msg["reasoning"]
+                break
+
         # Build result with interrupt info if applicable
         result = {
             "final_response": final_response,
+            "last_reasoning": last_reasoning,
             "messages": messages,
             "api_calls": api_call_count,
             "completed": completed,

tests/hermes_cli/test_commands.py

@@ -11,7 +11,7 @@ EXPECTED_COMMANDS = {
     "/help", "/tools", "/toolsets", "/model", "/provider", "/prompt",
     "/personality", "/clear", "/history", "/new", "/reset", "/retry",
     "/undo", "/save", "/config", "/cron", "/skills", "/platforms",
-    "/verbose", "/compress", "/title", "/usage", "/insights", "/paste",
+    "/verbose", "/reasoning", "/compress", "/title", "/usage", "/insights", "/paste",
     "/reload-mcp", "/rollback", "/background", "/skin", "/quit",
 }
 

tests/test_reasoning_command.py

@@ -0,0 +1,422 @@
+"""Tests for the combined /reasoning command.
+
+Covers both reasoning effort level management and reasoning display toggle,
+plus the reasoning extraction and display pipeline from run_agent through CLI.
+
+Combines functionality from:
+- PR #789 (Aum08Desai): reasoning effort level management
+- PR #790 (0xbyt4): reasoning display toggle and rendering
+"""
+
+import unittest
+from types import SimpleNamespace
+from unittest.mock import MagicMock, patch
+
+
+# ---------------------------------------------------------------------------
+# Effort level parsing
+# ---------------------------------------------------------------------------
+
+class TestParseReasoningConfig(unittest.TestCase):
+    """Verify _parse_reasoning_config handles all effort levels."""
+
+    def _parse(self, effort):
+        from cli import _parse_reasoning_config
+        return _parse_reasoning_config(effort)
+
+    def test_none_disables(self):
+        result = self._parse("none")
+        self.assertEqual(result, {"enabled": False})
+
+    def test_valid_levels(self):
+        for level in ("low", "medium", "high", "xhigh", "minimal"):
+            result = self._parse(level)
+            self.assertIsNotNone(result)
+            self.assertTrue(result.get("enabled"))
+            self.assertEqual(result["effort"], level)
+
+    def test_empty_returns_none(self):
+        self.assertIsNone(self._parse(""))
+        self.assertIsNone(self._parse("  "))
+
+    def test_unknown_returns_none(self):
+        self.assertIsNone(self._parse("ultra"))
+        self.assertIsNone(self._parse("turbo"))
+
+    def test_case_insensitive(self):
+        result = self._parse("HIGH")
+        self.assertIsNotNone(result)
+        self.assertEqual(result["effort"], "high")
+
+
+# ---------------------------------------------------------------------------
+# /reasoning command handler (combined effort + display)
+# ---------------------------------------------------------------------------
+
+class TestHandleReasoningCommand(unittest.TestCase):
+    """Test the combined _handle_reasoning_command method."""
+
+    def _make_cli(self, reasoning_config=None, show_reasoning=False):
+        """Create a minimal CLI stub with the reasoning attributes."""
+        stub = SimpleNamespace(
+            reasoning_config=reasoning_config,
+            show_reasoning=show_reasoning,
+            agent=MagicMock(),
+        )
+        return stub
+
+    def test_show_enables_display(self):
+        stub = self._make_cli(show_reasoning=False)
+        # Simulate /reasoning show
+        arg = "show"
+        if arg in ("show", "on"):
+            stub.show_reasoning = True
+            stub.agent.reasoning_callback = lambda x: None
+        self.assertTrue(stub.show_reasoning)
+
+    def test_hide_disables_display(self):
+        stub = self._make_cli(show_reasoning=True)
+        # Simulate /reasoning hide
+        arg = "hide"
+        if arg in ("hide", "off"):
+            stub.show_reasoning = False
+            stub.agent.reasoning_callback = None
+        self.assertFalse(stub.show_reasoning)
+        self.assertIsNone(stub.agent.reasoning_callback)
+
+    def test_on_enables_display(self):
+        stub = self._make_cli(show_reasoning=False)
+        arg = "on"
+        if arg in ("show", "on"):
+            stub.show_reasoning = True
+        self.assertTrue(stub.show_reasoning)
+
+    def test_off_disables_display(self):
+        stub = self._make_cli(show_reasoning=True)
+        arg = "off"
+        if arg in ("hide", "off"):
+            stub.show_reasoning = False
+        self.assertFalse(stub.show_reasoning)
+
+    def test_effort_level_sets_config(self):
+        """Setting an effort level should update reasoning_config."""
+        from cli import _parse_reasoning_config
+        stub = self._make_cli()
+        arg = "high"
+        parsed = _parse_reasoning_config(arg)
+        stub.reasoning_config = parsed
+        self.assertEqual(stub.reasoning_config, {"enabled": True, "effort": "high"})
+
+    def test_effort_none_disables_reasoning(self):
+        from cli import _parse_reasoning_config
+        stub = self._make_cli()
+        parsed = _parse_reasoning_config("none")
+        stub.reasoning_config = parsed
+        self.assertEqual(stub.reasoning_config, {"enabled": False})
+
+    def test_invalid_argument_rejected(self):
+        """Invalid arguments should be rejected (parsed returns None)."""
+        from cli import _parse_reasoning_config
+        parsed = _parse_reasoning_config("turbo")
+        self.assertIsNone(parsed)
+
+    def test_no_args_shows_status(self):
+        """With no args, should show current state (no crash)."""
+        stub = self._make_cli(reasoning_config=None, show_reasoning=False)
+        rc = stub.reasoning_config
+        if rc is None:
+            level = "medium (default)"
+        elif rc.get("enabled") is False:
+            level = "none (disabled)"
+        else:
+            level = rc.get("effort", "medium")
+        display_state = "on" if stub.show_reasoning else "off"
+        self.assertEqual(level, "medium (default)")
+        self.assertEqual(display_state, "off")
+
+    def test_status_with_disabled_reasoning(self):
+        stub = self._make_cli(reasoning_config={"enabled": False}, show_reasoning=True)
+        rc = stub.reasoning_config
+        if rc is None:
+            level = "medium (default)"
+        elif rc.get("enabled") is False:
+            level = "none (disabled)"
+        else:
+            level = rc.get("effort", "medium")
+        self.assertEqual(level, "none (disabled)")
+
+    def test_status_with_explicit_level(self):
+        stub = self._make_cli(
+            reasoning_config={"enabled": True, "effort": "xhigh"},
+            show_reasoning=True,
+        )
+        rc = stub.reasoning_config
+        level = rc.get("effort", "medium")
+        self.assertEqual(level, "xhigh")
+
+
+# ---------------------------------------------------------------------------
+# Reasoning extraction and result dict
+# ---------------------------------------------------------------------------
+
+class TestLastReasoningInResult(unittest.TestCase):
+    """Verify reasoning extraction from the messages list."""
+
+    def _build_messages(self, reasoning=None):
+        return [
+            {"role": "user", "content": "hello"},
+            {
+                "role": "assistant",
+                "content": "Hi there!",
+                "reasoning": reasoning,
+                "finish_reason": "stop",
+            },
+        ]
+
+    def test_reasoning_present(self):
+        messages = self._build_messages(reasoning="Let me think...")
+        last_reasoning = None
+        for msg in reversed(messages):
+            if msg.get("role") == "assistant" and msg.get("reasoning"):
+                last_reasoning = msg["reasoning"]
+                break
+        self.assertEqual(last_reasoning, "Let me think...")
+
+    def test_reasoning_none(self):
+        messages = self._build_messages(reasoning=None)
+        last_reasoning = None
+        for msg in reversed(messages):
+            if msg.get("role") == "assistant" and msg.get("reasoning"):
+                last_reasoning = msg["reasoning"]
+                break
+        self.assertIsNone(last_reasoning)
+
+    def test_picks_last_assistant(self):
+        messages = [
+            {"role": "user", "content": "hello"},
+            {"role": "assistant", "content": "...", "reasoning": "first thought"},
+            {"role": "tool", "content": "result"},
+            {"role": "assistant", "content": "done!", "reasoning": "final thought"},
+        ]
+        last_reasoning = None
+        for msg in reversed(messages):
+            if msg.get("role") == "assistant" and msg.get("reasoning"):
+                last_reasoning = msg["reasoning"]
+                break
+        self.assertEqual(last_reasoning, "final thought")
+
+    def test_empty_reasoning_treated_as_none(self):
+        messages = self._build_messages(reasoning="")
+        last_reasoning = None
+        for msg in reversed(messages):
+            if msg.get("role") == "assistant" and msg.get("reasoning"):
+                last_reasoning = msg["reasoning"]
+                break
+        self.assertIsNone(last_reasoning)
+
+
+# ---------------------------------------------------------------------------
+# Reasoning display collapse
+# ---------------------------------------------------------------------------
+
+class TestReasoningCollapse(unittest.TestCase):
+    """Verify long reasoning is collapsed to 10 lines in the box."""
+
+    def test_short_reasoning_not_collapsed(self):
+        reasoning = "\n".join(f"Line {i}" for i in range(5))
+        lines = reasoning.strip().splitlines()
+        self.assertLessEqual(len(lines), 10)
+
+    def test_long_reasoning_collapsed(self):
+        reasoning = "\n".join(f"Line {i}" for i in range(25))
+        lines = reasoning.strip().splitlines()
+        self.assertTrue(len(lines) > 10)
+        if len(lines) > 10:
+            display = "\n".join(lines[:10])
+            display += f"\n  ... ({len(lines) - 10} more lines)"
+        display_lines = display.splitlines()
+        self.assertEqual(len(display_lines), 11)
+        self.assertIn("15 more lines", display_lines[-1])
+
+    def test_exactly_10_lines_not_collapsed(self):
+        reasoning = "\n".join(f"Line {i}" for i in range(10))
+        lines = reasoning.strip().splitlines()
+        self.assertEqual(len(lines), 10)
+        self.assertFalse(len(lines) > 10)
+
+    def test_intermediate_callback_collapses_to_5(self):
+        """_on_reasoning shows max 5 lines."""
+        reasoning = "\n".join(f"Step {i}" for i in range(12))
+        lines = reasoning.strip().splitlines()
+        if len(lines) > 5:
+            preview = "\n".join(lines[:5])
+            preview += f"\n  ... ({len(lines) - 5} more lines)"
+        else:
+            preview = reasoning.strip()
+        preview_lines = preview.splitlines()
+        self.assertEqual(len(preview_lines), 6)
+        self.assertIn("7 more lines", preview_lines[-1])
+
+
+# ---------------------------------------------------------------------------
+# Reasoning callback
+# ---------------------------------------------------------------------------
+
+class TestReasoningCallback(unittest.TestCase):
+    """Verify reasoning_callback invocation."""
+
+    def test_callback_invoked_with_reasoning(self):
+        captured = []
+        agent = MagicMock()
+        agent.reasoning_callback = lambda t: captured.append(t)
+        agent._extract_reasoning = MagicMock(return_value="deep thought")
+
+        reasoning_text = agent._extract_reasoning(MagicMock())
+        if reasoning_text and agent.reasoning_callback:
+            agent.reasoning_callback(reasoning_text)
+        self.assertEqual(captured, ["deep thought"])
+
+    def test_callback_not_invoked_without_reasoning(self):
+        captured = []
+        agent = MagicMock()
+        agent.reasoning_callback = lambda t: captured.append(t)
+        agent._extract_reasoning = MagicMock(return_value=None)
+
+        reasoning_text = agent._extract_reasoning(MagicMock())
+        if reasoning_text and agent.reasoning_callback:
+            agent.reasoning_callback(reasoning_text)
+        self.assertEqual(captured, [])
+
+    def test_callback_none_does_not_crash(self):
+        reasoning_text = "some thought"
+        callback = None
+        if reasoning_text and callback:
+            callback(reasoning_text)
+        # No exception = pass
+
+
+# ---------------------------------------------------------------------------
+# Real provider format extraction
+# ---------------------------------------------------------------------------
+
+class TestExtractReasoningFormats(unittest.TestCase):
+    """Test _extract_reasoning with real provider response formats."""
+
+    def _get_extractor(self):
+        from run_agent import AIAgent
+        return AIAgent._extract_reasoning
+
+    def test_openrouter_reasoning_details(self):
+        extract = self._get_extractor()
+        msg = SimpleNamespace(
+            reasoning=None,
+            reasoning_content=None,
+            reasoning_details=[
+                {"type": "reasoning.summary", "summary": "Analyzing Python lists."},
+            ],
+        )
+        result = extract(None, msg)
+        self.assertIn("Python lists", result)
+
+    def test_deepseek_reasoning_field(self):
+        extract = self._get_extractor()
+        msg = SimpleNamespace(
+            reasoning="Solving step by step.\nx + y = 8.",
+            reasoning_content=None,
+        )
+        result = extract(None, msg)
+        self.assertIn("x + y = 8", result)
+
+    def test_moonshot_reasoning_content(self):
+        extract = self._get_extractor()
+        msg = SimpleNamespace(
+            reasoning_content="Explaining async/await.",
+        )
+        result = extract(None, msg)
+        self.assertIn("async/await", result)
+
+    def test_no_reasoning_returns_none(self):
+        extract = self._get_extractor()
+        msg = SimpleNamespace(content="Hello!")
+        result = extract(None, msg)
+        self.assertIsNone(result)
+
+
+# ---------------------------------------------------------------------------
+# Config defaults
+# ---------------------------------------------------------------------------
+
+class TestConfigDefault(unittest.TestCase):
+    """Verify config default for show_reasoning."""
+
+    def test_default_config_has_show_reasoning(self):
+        from hermes_cli.config import DEFAULT_CONFIG
+        display = DEFAULT_CONFIG.get("display", {})
+        self.assertIn("show_reasoning", display)
+        self.assertFalse(display["show_reasoning"])
+
+
+class TestCommandRegistered(unittest.TestCase):
+    """Verify /reasoning is in the COMMANDS dict."""
+
+    def test_reasoning_in_commands(self):
+        from hermes_cli.commands import COMMANDS
+        self.assertIn("/reasoning", COMMANDS)
+
+
+# ---------------------------------------------------------------------------
+# End-to-end pipeline
+# ---------------------------------------------------------------------------
+
+class TestEndToEndPipeline(unittest.TestCase):
+    """Simulate the full pipeline: extraction -> result dict -> display."""
+
+    def test_openrouter_claude_pipeline(self):
+        from run_agent import AIAgent
+
+        api_message = SimpleNamespace(
+            role="assistant",
+            content="Lists support append().",
+            tool_calls=None,
+            reasoning=None,
+            reasoning_content=None,
+            reasoning_details=[
+                {"type": "reasoning.summary", "summary": "Python list methods."},
+            ],
+        )
+
+        reasoning = AIAgent._extract_reasoning(None, api_message)
+        self.assertIsNotNone(reasoning)
+
+        messages = [
+            {"role": "user", "content": "How do I add items?"},
+            {"role": "assistant", "content": api_message.content, "reasoning": reasoning},
+        ]
+
+        last_reasoning = None
+        for msg in reversed(messages):
+            if msg.get("role") == "assistant" and msg.get("reasoning"):
+                last_reasoning = msg["reasoning"]
+                break
+
+        result = {
+            "final_response": api_message.content,
+            "last_reasoning": last_reasoning,
+        }
+
+        self.assertIn("last_reasoning", result)
+        self.assertIn("Python list methods", result["last_reasoning"])
+
+    def test_no_reasoning_model_pipeline(self):
+        from run_agent import AIAgent
+
+        api_message = SimpleNamespace(content="Paris.", tool_calls=None)
+        reasoning = AIAgent._extract_reasoning(None, api_message)
+        self.assertIsNone(reasoning)
+
+        result = {"final_response": api_message.content, "last_reasoning": reasoning}
+        self.assertIsNone(result["last_reasoning"])
+
+
+if __name__ == "__main__":
+    unittest.main()

website/docs/reference/cli-commands.md

@@ -147,6 +147,7 @@ Type `/` in the interactive CLI to see an autocomplete dropdown.
 | `/config` | Show current configuration |
 | `/prompt [text]` | View/set custom system prompt |
 | `/personality [name]` | Set a predefined personality |
+| `/reasoning [arg]` | Manage reasoning effort and display. Args: effort level (`none`, `low`, `medium`, `high`, `xhigh`) or display toggle (`show`, `hide`). No args shows current state. |
 
 ### Conversation
 

website/docs/user-guide/cli.md

@@ -104,6 +104,7 @@ Type `/` to see an autocomplete dropdown of all available commands.
 | `/config` | Show current configuration |
 | `/prompt [text]` | View/set/clear custom system prompt |
 | `/personality [name]` | Set a predefined personality |
+| `/reasoning [arg]` | Manage reasoning effort (`none`/`low`/`medium`/`high`/`xhigh`) and display (`show`/`hide`) |
 
 ### Conversation Management
 

website/docs/user-guide/configuration.md

@@ -608,6 +608,16 @@ agent:
 
 When unset (default), reasoning effort defaults to "medium" — a balanced level that works well for most tasks. Setting a value overrides it — higher reasoning effort gives better results on complex tasks at the cost of more tokens and latency.
 
+You can also change the reasoning effort at runtime with the `/reasoning` command:
+
+```
+/reasoning           # Show current effort level and display state
+/reasoning high      # Set reasoning effort to high
+/reasoning none      # Disable reasoning
+/reasoning show      # Show model thinking above each response
+/reasoning hide      # Hide model thinking
+```
+
 ## TTS Configuration
 
 ```yaml
@@ -632,6 +642,7 @@ display:
   compact: false         # Compact output mode (less whitespace)
   resume_display: full   # full (show previous messages on resume) | minimal (one-liner only)
   bell_on_complete: false  # Play terminal bell when agent finishes (great for long tasks)
+  show_reasoning: false    # Show model reasoning/thinking above each response (toggle with /reasoning show|hide)
 ```
 
 | Mode | What you see |