fix: /reasoning command output ordering, display, and inline think extraction
Three issues with the /reasoning command: 1. Output interleaving: The command echo used print() while feedback used _cprint(), causing them to render out-of-order under prompt_toolkit's patch_stdout. Changed echo to use _cprint() so all output renders through the same path in correct order. 2. Reasoning display not working: /reasoning show toggled a flag but reasoning never appeared for models that embed thinking in inline <think> blocks rather than structured API fields. Added fallback extraction in _build_assistant_message to capture <think> block content as reasoning when no structured reasoning fields (reasoning, reasoning_content, reasoning_details) are present. This feeds into both the reasoning callback (during tool loops) and the post-response reasoning box display. 3. Feedback clarity: Added checkmarks to confirm actions, persisted show/hide to config (was session-only before), and aligned the status display for readability. Tests: 7 new tests for inline think block extraction (41 total).
This commit is contained in:
teknium1
@@ -3120,8 +3120,8 @@ class HermesCLI:
|
||||
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}")
|
||||
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
|
||||
@@ -3133,14 +3133,16 @@ class HermesCLI:
|
||||
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}")
|
||||
save_config_value("display.show_reasoning", True)
|
||||
_cprint(f" {_GOLD}✓ Reasoning display: ON (saved){_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}")
|
||||
save_config_value("display.show_reasoning", False)
|
||||
_cprint(f" {_GOLD}✓ Reasoning display: OFF (saved){_RST}")
|
||||
return
|
||||
|
||||
# Effort level change
|
||||
@@ -3155,9 +3157,9 @@ class HermesCLI:
|
||||
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}")
|
||||
_cprint(f" {_GOLD}✓ Reasoning effort set to '{arg}' (saved to config){_RST}")
|
||||
else:
|
||||
_cprint(f" {_GOLD}Reasoning effort set to '{arg}' (session only){_RST}")
|
||||
_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."""
|
||||
@@ -4544,7 +4546,7 @@ class HermesCLI:
|
||||
|
||||
# Check for commands
|
||||
if isinstance(user_input, str) and user_input.startswith("/"):
|
||||
print(f"\n⚙️ {user_input}")
|
||||
_cprint(f"\n⚙️ {user_input}")
|
||||
if not self.process_command(user_input):
|
||||
self._should_exit = True
|
||||
# Schedule app exit
|
||||
|
||||
@@ -2442,6 +2442,16 @@ class AIAgent:
|
||||
"""
|
||||
reasoning_text = self._extract_reasoning(assistant_message)
|
||||
|
||||
# Fallback: extract inline <think> blocks from content when no structured
|
||||
# reasoning fields are present (some models/providers embed thinking
|
||||
# directly in the content rather than returning separate API fields).
|
||||
if not reasoning_text:
|
||||
content = assistant_message.content or ""
|
||||
think_blocks = re.findall(r'<think>(.*?)</think>', content, flags=re.DOTALL)
|
||||
if think_blocks:
|
||||
combined = "\n\n".join(b.strip() for b in think_blocks if b.strip())
|
||||
reasoning_text = combined or None
|
||||
|
||||
if reasoning_text and self.verbose_logging:
|
||||
preview = reasoning_text[:100] + "..." if len(reasoning_text) > 100 else reasoning_text
|
||||
logging.debug(f"Captured reasoning ({len(reasoning_text)} chars): {preview}")
|
||||
|
||||
@@ -342,6 +342,90 @@ class TestExtractReasoningFormats(unittest.TestCase):
|
||||
self.assertIsNone(result)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Inline <think> block extraction fallback
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class TestInlineThinkBlockExtraction(unittest.TestCase):
|
||||
"""Test _build_assistant_message extracts inline <think> blocks as reasoning
|
||||
when no structured API-level reasoning fields are present."""
|
||||
|
||||
def _build_msg(self, content, reasoning=None, reasoning_content=None, reasoning_details=None, tool_calls=None):
|
||||
"""Create a mock API response message."""
|
||||
msg = SimpleNamespace(content=content, tool_calls=tool_calls)
|
||||
if reasoning is not None:
|
||||
msg.reasoning = reasoning
|
||||
if reasoning_content is not None:
|
||||
msg.reasoning_content = reasoning_content
|
||||
if reasoning_details is not None:
|
||||
msg.reasoning_details = reasoning_details
|
||||
return msg
|
||||
|
||||
def _make_agent(self):
|
||||
"""Create a minimal agent with _build_assistant_message."""
|
||||
from run_agent import AIAgent
|
||||
agent = MagicMock(spec=AIAgent)
|
||||
agent._build_assistant_message = AIAgent._build_assistant_message.__get__(agent)
|
||||
agent._extract_reasoning = AIAgent._extract_reasoning.__get__(agent)
|
||||
agent.verbose_logging = False
|
||||
agent.reasoning_callback = None
|
||||
return agent
|
||||
|
||||
def test_single_think_block_extracted(self):
|
||||
agent = self._make_agent()
|
||||
api_msg = self._build_msg("<think>Let me calculate 2+2=4.</think>The answer is 4.")
|
||||
result = agent._build_assistant_message(api_msg, "stop")
|
||||
self.assertEqual(result["reasoning"], "Let me calculate 2+2=4.")
|
||||
|
||||
def test_multiple_think_blocks_extracted(self):
|
||||
agent = self._make_agent()
|
||||
api_msg = self._build_msg("<think>First thought.</think>Some text<think>Second thought.</think>More text")
|
||||
result = agent._build_assistant_message(api_msg, "stop")
|
||||
self.assertIn("First thought.", result["reasoning"])
|
||||
self.assertIn("Second thought.", result["reasoning"])
|
||||
|
||||
def test_no_think_blocks_no_reasoning(self):
|
||||
agent = self._make_agent()
|
||||
api_msg = self._build_msg("Just a plain response.")
|
||||
result = agent._build_assistant_message(api_msg, "stop")
|
||||
# No structured reasoning AND no inline think blocks → None
|
||||
self.assertIsNone(result["reasoning"])
|
||||
|
||||
def test_structured_reasoning_takes_priority(self):
|
||||
"""When structured API reasoning exists, inline think blocks should NOT override."""
|
||||
agent = self._make_agent()
|
||||
api_msg = self._build_msg(
|
||||
"<think>Inline thought.</think>Response text.",
|
||||
reasoning="Structured reasoning from API.",
|
||||
)
|
||||
result = agent._build_assistant_message(api_msg, "stop")
|
||||
self.assertEqual(result["reasoning"], "Structured reasoning from API.")
|
||||
|
||||
def test_empty_think_block_ignored(self):
|
||||
agent = self._make_agent()
|
||||
api_msg = self._build_msg("<think></think>Hello!")
|
||||
result = agent._build_assistant_message(api_msg, "stop")
|
||||
# Empty think block should not produce reasoning
|
||||
self.assertIsNone(result["reasoning"])
|
||||
|
||||
def test_multiline_think_block(self):
|
||||
agent = self._make_agent()
|
||||
api_msg = self._build_msg("<think>\nStep 1: Analyze.\nStep 2: Solve.\n</think>Done.")
|
||||
result = agent._build_assistant_message(api_msg, "stop")
|
||||
self.assertIn("Step 1: Analyze.", result["reasoning"])
|
||||
self.assertIn("Step 2: Solve.", result["reasoning"])
|
||||
|
||||
def test_callback_fires_for_inline_think(self):
|
||||
"""Reasoning callback should fire when reasoning is extracted from inline think blocks."""
|
||||
agent = self._make_agent()
|
||||
captured = []
|
||||
agent.reasoning_callback = lambda t: captured.append(t)
|
||||
api_msg = self._build_msg("<think>Deep analysis here.</think>Answer.")
|
||||
agent._build_assistant_message(api_msg, "stop")
|
||||
self.assertEqual(len(captured), 1)
|
||||
self.assertIn("Deep analysis", captured[0])
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Config defaults
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
Reference in New Issue
Block a user