fix: remove <think> wrappers from think messages

Messages in reasoning_content should be plain text, not wrapped
in <think> tags. Removed wrappers from:
- delegation.py household think messages
- orchestration.py status messages

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

CHANGELOG.md

@@ -7,6 +7,22 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.8.4] - 2025-12-16
+
+### Fixed
+
+- **Remove `<think>` wrappers from think messages** - Messages in `reasoning_content` should be plain text
+- Removed `<think>` wrappers from delegation.py household think messages
+- Removed `<think>` wrappers from orchestration.py status messages
+- Think messages now appear cleanly in Open WebUI's reasoning block
+
+## [1.8.3] - 2025-12-16
+
+### Fixed
+
+- **Open WebUI streaming rendering** - Use `reasoning_content` field for thinking (DeepSeek R1 format) instead of `<think>` tags in `content`
+- Open WebUI now renders thinking as proper collapsible blocks instead of broken HTML
+
 ## [1.8.2] - 2025-12-16
 
 ### Fixed

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tatlock"
-version = "1.8.2"
+version = "1.8.4"
 description = "OpenAI-compatible API with Ollama backend"
 requires-python = ">=3.12"
 dependencies = []

src/agents/delegation.py

@@ -40,45 +40,46 @@ class ActionType(Enum):
 # =============================================================================
 
 HOUSEHOLD_THINK_MESSAGES: dict[str, dict[ActionType, dict[str, str]]] = {
+    # Note: No <think> wrappers needed - these go to reasoning_content field
     "librarian": {
         ActionType.RETRIEVE: {
-            "start": "<think>Allow me to consult the archives, sir.</think>",
+            "start": "Allow me to consult the archives, sir.",
-            "success": "<think>The Librarian has compiled the relevant findings.</think>",
+            "success": "The Librarian has compiled the relevant findings.",
-            "error": "<think>I'm afraid the archives proved difficult to access.</think>",
+            "error": "I'm afraid the archives proved difficult to access.",
         },
         ActionType.RESEARCH: {
-            "start": "<think>I've dispatched the Librarian to conduct some fresh research.</think>",
+            "start": "I've dispatched the Librarian to conduct some fresh research.",
-            "success": "<think>The Librarian has returned with findings, sir.</think>",
+            "success": "The Librarian has returned with findings, sir.",
-            "error": "<think>The research proved inconclusive, I'm afraid.</think>",
+            "error": "The research proved inconclusive, I'm afraid.",
         },
         ActionType.CREATE: {
-            "start": "<think>I'm having the Librarian prepare a new entry.</think>",
+            "start": "I'm having the Librarian prepare a new entry.",
-            "success": "<think>The new material has been properly catalogued, sir.</think>",
+            "success": "The new material has been properly catalogued, sir.",
-            "error": "<think>I'm afraid there was difficulty filing the entry.</think>",
+            "error": "I'm afraid there was difficulty filing the entry.",
         },
     },
     "biographer": {
         ActionType.RETRIEVE: {
-            "start": "<think>Let me consult the household records.</think>",
+            "start": "Let me consult the household records.",
-            "success": "<think>The Biographer has located the relevant information, sir.</think>",
+            "success": "The Biographer has located the relevant information, sir.",
-            "error": "<think>I'm unable to locate those particular records.</think>",
+            "error": "I'm unable to locate those particular records.",
         },
         ActionType.RECORD: {
-            "start": "<think>I've asked the Biographer to take note of this, sir.</think>",
+            "start": "I've asked the Biographer to take note of this, sir.",
-            "success": "<think>The household records have been updated accordingly.</think>",
+            "success": "The household records have been updated accordingly.",
-            "error": "<think>I'm afraid there was difficulty recording the entry.</think>",
+            "error": "I'm afraid there was difficulty recording the entry.",
         },
     },
     "housekeeper": {
         ActionType.RETRIEVE: {
-            "start": "<think>Allow me to inquire with the household staff.</think>",
+            "start": "Allow me to inquire with the household staff.",
-            "success": "<think>The staff reports the current status, sir.</think>",
+            "success": "The staff reports the current status, sir.",
-            "error": "<think>The household staff is momentarily unavailable, I'm afraid.</think>",
+            "error": "The household staff is momentarily unavailable, I'm afraid.",
         },
         ActionType.CONTROL: {
-            "start": "<think>I'm instructing the household staff now, sir.</think>",
+            "start": "I'm instructing the household staff now, sir.",
-            "success": "<think>The household has been configured as requested.</think>",
+            "success": "The household has been configured as requested.",
-            "error": "<think>I'm afraid the staff reports an issue with that request.</think>",
+            "error": "I'm afraid the staff reports an issue with that request.",
         },
     },
 }
@@ -139,7 +140,7 @@ def get_think_message(expert: str, task: str, phase: str) -> str:
     action_type = _detect_action_type(expert, task)
     expert_messages = HOUSEHOLD_THINK_MESSAGES.get(expert, {})
     action_messages = expert_messages.get(action_type, expert_messages.get(ActionType.RETRIEVE, {}))
-    return action_messages.get(phase, f"<think>Consulting {expert}...</think>")
+    return action_messages.get(phase, f"Consulting {expert}...")
 
 
 @dataclass

src/agents/orchestration.py

@@ -176,19 +176,19 @@ async def orchestrate_with_think_updates(
     if delegation_task.expert_name == "librarian":
         expert_display_name = "The Librarian"
 
-    yield f"<think>🤝 Consulting {expert_display_name}...</think>\n"
+    yield f"🤝 Consulting {expert_display_name}...\n"
 
     # Execute delegation (uses run() internally)
     result = await execute_delegation(delegation_task)
 
     if result.success:
-        yield f"<think>✅ {expert_display_name} completed research.</think>\n"
+        yield f"✅ {expert_display_name} completed research.\n"
 
         # Yield the expert's findings
         if result.output:
             yield f"\n{result.output}"
     else:
-        yield f"<think>⚠️ {expert_display_name} encountered an issue: {result.error}</think>\n"
+        yield f"⚠️ {expert_display_name} encountered an issue: {result.error}\n"
 
     logger.info(
         "orchestration_complete",
@@ -449,12 +449,12 @@ async def orchestrate_multi_expert(
         return
 
     # Stream: Starting multi-expert coordination
-    yield f"<think>🎯 Starting multi-expert coordination ({len(tasks)} tasks, {mode.value})...</think>\n"
+    yield f"🎯 Starting multi-expert coordination ({len(tasks)} tasks, {mode.value})...\n"
 
     if mode == ExecutionMode.PARALLEL:
         # Parallel execution - emit one update then run all at once
         expert_names = ", ".join(_get_display_name(t.expert_name) for t in tasks)
-        yield f"<think>🔄 Consulting in parallel: {expert_names}...</think>\n"
+        yield f"🔄 Consulting in parallel: {expert_names}...\n"
 
         result = await execute_parallel(tasks)
 
@@ -462,9 +462,9 @@ async def orchestrate_multi_expert(
         for expert_name, expert_result in result.results.items():
             display_name = _get_display_name(expert_name)
             if expert_result.success:
-                yield f"<think>✅ {display_name} completed.</think>\n"
+                yield f"✅ {display_name} completed.\n"
             else:
-                yield f"<think>⚠️ {display_name} failed: {expert_result.error}</think>\n"
+                yield f"⚠️ {display_name} failed: {expert_result.error}\n"
 
     else:
         # Sequential execution - emit updates for each task
@@ -472,27 +472,27 @@ async def orchestrate_multi_expert(
 
         for task in tasks:
             display_name = _get_display_name(task.expert_name)
-            yield f"<think>🤝 Consulting {display_name}...</think>\n"
+            yield f"🤝 Consulting {display_name}...\n"
 
             task_result = await execute_delegation(task)
             result.add_result(task_result)
 
             if task_result.success:
-                yield f"<think>✅ {display_name} completed.</think>\n"
+                yield f"✅ {display_name} completed.\n"
             else:
-                yield f"<think>⚠️ {display_name} failed: {task_result.error}</think>\n"
+                yield f"⚠️ {display_name} failed: {task_result.error}\n"
                 if stop_on_failure:
-                    yield "<think>🛑 Stopping due to failure.</think>\n"
+                    yield "🛑 Stopping due to failure.\n"
                     break
 
         result.aggregate_outputs()
 
     # Stream: Summary
     if result.all_succeeded:
-        yield "<think>🎉 All experts completed successfully.</think>\n"
+        yield "🎉 All experts completed successfully.\n"
     else:
         failed_names = ", ".join(_get_display_name(e) for e in result.failed_experts)
-        yield f"<think>⚠️ Some experts failed: {failed_names}</think>\n"
+        yield f"⚠️ Some experts failed: {failed_names}\n"
 
     # Yield combined output
     if result.combined_output:

src/chat/schemas.py

@@ -55,6 +55,7 @@ class ChatCompletionChunkDelta(CustomBaseModel):
     """Delta in streaming chunk."""
     role: str | None = None
     content: str | None = None
+    reasoning_content: str | None = None  # For thinking/reasoning (DeepSeek R1 format)
 
 
 class ChatCompletionChunkChoice(CustomBaseModel):

src/chat/service.py

@@ -172,24 +172,9 @@ async def create_chat_completion_stream(
 
     async for event in stream_generator:
         if event.event == StreamEventType.REASONING_SUMMARY_DELTA:
-            # Start <think> block if needed
+            # Stream reasoning via reasoning_content field (DeepSeek R1 format)
-            if not in_reasoning:
+            # Open WebUI renders this as collapsible thinking block
-                yield ChatCompletionChunk(
+            in_reasoning = True
-                    id=completion_id,
-                    object=constants.CHAT_COMPLETION_CHUNK_OBJECT,
-                    created=created_at,
-                    model=request.model,
-                    choices=[
-                        ChatCompletionChunkChoice(
-                            index=0,
-                            delta=ChatCompletionChunkDelta(content="<think>\n"),
-                            finish_reason=None,
-                        )
-                    ],
-                )
-                in_reasoning = True
-
-            # Stream reasoning delta
             yield ChatCompletionChunk(
                 id=completion_id,
                 object=constants.CHAT_COMPLETION_CHUNK_OBJECT,
@@ -198,29 +183,15 @@ async def create_chat_completion_stream(
                 choices=[
                     ChatCompletionChunkChoice(
                         index=0,
-                        delta=ChatCompletionChunkDelta(content=event.delta),
+                        delta=ChatCompletionChunkDelta(reasoning_content=event.delta),
                         finish_reason=None,
                     )
                 ],
             )
 
         elif event.event == StreamEventType.REASONING_SUMMARY_DONE:
-            # Close <think> block
+            # Signal end of reasoning block (no content needed)
-            if in_reasoning:
+            in_reasoning = False
-                yield ChatCompletionChunk(
-                    id=completion_id,
-                    object=constants.CHAT_COMPLETION_CHUNK_OBJECT,
-                    created=created_at,
-                    model=request.model,
-                    choices=[
-                        ChatCompletionChunkChoice(
-                            index=0,
-                            delta=ChatCompletionChunkDelta(content="</think>\n\n"),
-                            finish_reason=None,
-                        )
-                    ],
-                )
-                in_reasoning = False
 
         elif event.event == StreamEventType.OUTPUT_TEXT_DELTA:
             # Stream message content

tests/agents/test_delegation.py

@@ -248,13 +248,16 @@ class TestHouseholdThinkMessages:
                 assert "success" in messages, f"{expert}/{action_type} missing 'success'"
                 assert "error" in messages, f"{expert}/{action_type} missing 'error'"
 
-    def test_messages_are_think_tags(self):
+    def test_messages_are_plain_text(self):
-        """Test messages are wrapped in <think> tags."""
+        """Test messages are plain text (no <think> wrappers - those go to reasoning_content)."""
         for expert, action_types in HOUSEHOLD_THINK_MESSAGES.items():
             for action_type, messages in action_types.items():
                 for phase, msg in messages.items():
-                    assert msg.startswith("<think>"), f"{expert}/{action_type}/{phase}"
+                    # Messages should NOT have <think> wrappers - they go to reasoning_content field
-                    assert msg.endswith("</think>"), f"{expert}/{action_type}/{phase}"
+                    assert "<think>" not in msg, f"{expert}/{action_type}/{phase} should not have <think> wrapper"
+                    assert "</think>" not in msg, f"{expert}/{action_type}/{phase} should not have </think> wrapper"
+                    # Messages should be non-empty strings
+                    assert isinstance(msg, str) and len(msg) > 0, f"{expert}/{action_type}/{phase}"
 
 
 @pytest.mark.unit
@@ -310,31 +313,32 @@ class TestGetThinkMessage:
     def test_librarian_retrieve_start(self):
         """Test getting librarian retrieve start message."""
         msg = get_think_message("librarian", "search for Docker", "start")
-        assert "<think>" in msg
+        # No <think> wrappers - messages go to reasoning_content field
-        assert "</think>" in msg
+        assert "<think>" not in msg
+        assert "archives" in msg.lower() or "consult" in msg.lower()
 
     def test_librarian_create_success(self):
         """Test getting librarian create success message."""
         msg = get_think_message("librarian", "create a wiki page", "success")
-        assert "<think>" in msg
+        assert "<think>" not in msg
         assert "catalogued" in msg.lower()
 
     def test_biographer_record_start(self):
         """Test getting biographer record start message."""
         msg = get_think_message("biographer", "remember my preference", "start")
-        assert "<think>" in msg
+        assert "<think>" not in msg
         assert "note" in msg.lower() or "biographer" in msg.lower()
 
     def test_housekeeper_control_success(self):
         """Test getting housekeeper control success message."""
         msg = get_think_message("housekeeper", "turn on the lights", "success")
-        assert "<think>" in msg
+        assert "<think>" not in msg
         assert "configured" in msg.lower()
 
     def test_unknown_expert_fallback(self):
         """Test unknown expert gets fallback message."""
         msg = get_think_message("unknown_expert", "some task", "start")
-        assert "<think>" in msg
+        assert "<think>" not in msg
         assert "unknown_expert" in msg.lower()
 
 

tests/agents/test_orchestration.py

@@ -208,8 +208,8 @@ class TestOrchestrateWithThinkUpdates:
             ):
                 updates.append(update)
 
-            # First update should be think tag about consulting
+            # First update should be about consulting (no <think> wrappers anymore)
-            assert any("<think>" in u and "Consulting" in u for u in updates)
+            assert any("Consulting" in u for u in updates)
 
     @pytest.mark.asyncio
     async def test_orchestrate_emits_think_after_delegation(self):
@@ -233,8 +233,8 @@ class TestOrchestrateWithThinkUpdates:
             ):
                 updates.append(update)
 
-            # Should have think tag about completion
+            # Should have message about completion (no <think> wrappers anymore)
-            assert any("<think>" in u and "completed" in u for u in updates)
+            assert any("completed" in u for u in updates)
 
     @pytest.mark.asyncio
     async def test_orchestrate_yields_expert_output(self):

tests/chat/test_streaming_wrapper.py

@@ -4,7 +4,7 @@ Tests for chat completions streaming wrapper.
 Tests that the wrapper correctly:
 - Wraps Responses API
 - Enables reasoning automatically
-- Converts reasoning to <think> tags
+- Streams reasoning via reasoning_content field (DeepSeek R1 format)
 - Streams both reasoning and content
 """
 import json
@@ -17,7 +17,7 @@ from src.chat import constants
 @pytest.mark.unit
 @pytest.mark.asyncio
 async def test_streaming_wrapper_enables_reasoning(async_client: AsyncClient):
-    """Test that streaming wrapper automatically enables reasoning."""
+    """Test that streaming wrapper automatically enables reasoning via reasoning_content."""
     request_data = {
         "model": "lorem-tester",
         "messages": [
@@ -27,7 +27,7 @@ async def test_streaming_wrapper_enables_reasoning(async_client: AsyncClient):
     }
 
     chunks_received = []
-    think_tags_found = False
+    reasoning_content_found = False
 
     async with async_client.stream(
         "POST",
@@ -51,12 +51,12 @@ async def test_streaming_wrapper_enables_reasoning(async_client: AsyncClient):
                     chunk = json.loads(data_str)
                     chunks_received.append(chunk)
 
-                    # Check for <think> tags in delta content
+                    # Check for reasoning_content in delta (DeepSeek R1 format)
                     if "choices" in chunk and len(chunk["choices"]) > 0:
                         delta = chunk["choices"][0].get("delta", {})
-                        content = delta.get("content")
+                        reasoning = delta.get("reasoning_content")
-                        if content and ("<think>" in content or "</think>" in content):
+                        if reasoning:
-                            think_tags_found = True
+                            reasoning_content_found = True
 
                 except json.JSONDecodeError:
                     pass
@@ -64,14 +64,14 @@ async def test_streaming_wrapper_enables_reasoning(async_client: AsyncClient):
     # Should have received chunks
     assert len(chunks_received) > 0
 
-    # Should have found <think> tags (reasoning enabled automatically)
+    # Should have found reasoning_content (reasoning enabled automatically)
-    assert think_tags_found, "Expected <think> tags in streaming output"
+    assert reasoning_content_found, "Expected reasoning_content in streaming output"
 
 
 @pytest.mark.unit
 @pytest.mark.asyncio
 async def test_streaming_wrapper_reasoning_before_content(async_client: AsyncClient):
-    """Test that reasoning (<think> tags) comes before actual content."""
+    """Test that reasoning_content comes before regular content."""
     request_data = {
         "model": "lorem-tester",
         "messages": [
@@ -80,10 +80,7 @@ async def test_streaming_wrapper_reasoning_before_content(async_client: AsyncCli
         "stream": True
     }
 
-    all_content = []
+    chunk_types = []  # Track order: 'reasoning' or 'content'
-    found_think_opening = False
-    found_think_closing = False
-    found_content_after_think = False
 
     async with async_client.stream(
         "POST",
@@ -106,28 +103,22 @@ async def test_streaming_wrapper_reasoning_before_content(async_client: AsyncCli
                     chunk = json.loads(data_str)
                     if "choices" in chunk and len(chunk["choices"]) > 0:
                         delta = chunk["choices"][0].get("delta", {})
-                        content = delta.get("content", "")
+                        reasoning = delta.get("reasoning_content")
-                        if content:
+                        content = delta.get("content")
-                            all_content.append(content)
 
-                            if "<think>" in content:
+                        if reasoning:
-                                found_think_opening = True
+                            chunk_types.append("reasoning")
-                            if "</think>" in content:
+                        if content:
-                                found_think_closing = True
+                            chunk_types.append("content")
-                            # Content after closing think tag
-                            if found_think_closing and content.strip() and "<think>" not in content and "</think>" not in content:
-                                found_content_after_think = True
 
                 except json.JSONDecodeError:
                     pass
 
-    # Verify ordering
+    # Verify reasoning comes before content
-    full_text = "".join(all_content)
+    if "reasoning" in chunk_types and "content" in chunk_types:
-    if found_think_opening and found_think_closing:
+        first_reasoning = chunk_types.index("reasoning")
-        # Reasoning should come before main content
+        first_content = chunk_types.index("content")
-        think_start = full_text.index("<think>")
+        assert first_reasoning < first_content, "reasoning_content should come before content"
-        think_end = full_text.index("</think>")
-        assert think_start < think_end, "Opening <think> should come before closing </think>"
 
 
 @pytest.mark.unit