fix: Redis bool storage, tool tracking matching, e2e fixture scope

- Convert booleans to strings for Redis hset (Redis doesn't accept bool)
- Extract capability from delegate_to_X tool names for tracking
- Use loop_scope="module" for pytest-asyncio module-scoped fixtures
- Add note about using venv for tests in AGENTS.md

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

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

AGENTS.md

@@ -22,6 +22,11 @@ This document contains instructions and documentation references for AI assistan
 * **Test REST endpoints** against `http://localhost:8777` using curl or similar tools
 * **Only deploy** when a phase or feature is complete and tested locally
 * **Environment**: Copy `.env.example` to `.env` and configure for your local setup (Ollama, Redis, Qdrant hosts)
+* **Running tests**: Always use the venv explicitly to avoid environment mismatches:
+  ```bash
+  .venv/bin/python -m pytest tests/           # All tests
+  .venv/bin/python -m pytest tests/core/ -v   # Core tests only
+  ```
 
 ### 🌐 Internal Service Access
 * **git.schweitz.net**: Access via `http://localhost:3002` (direct Gitea) to bypass Authentik SSO
@@ -51,6 +56,32 @@ This document contains instructions and documentation references for AI assistan
 * **Update `CHANGELOG.md`** with every user-facing change.
 * Format: `## [Unreleased] - YYYY-MM-DD` followed by `### Added`, `### Changed`, or `### Fixed`.
 
+### 🚀 Release Flow
+When changes are ready for deployment:
+
+1. **Ask user if deploy cycle is desired**
+
+2. **Update version** in `pyproject.toml`:
+   - Bug fixes: bump patch version (1.8.3 → 1.8.4)
+   - New features: bump minor version (1.8.4 → 1.9.0)
+
+3. **Update CHANGELOG.md**:
+   - Move items from `[Unreleased]` to new version section
+   - Add release date: `## [1.8.4] - 2025-12-16`
+
+4. **Commit and tag**:
+   ```bash
+   git add -A
+   git commit -m "fix: description of changes"
+   git tag v1.8.4
+   git push origin main --tags
+   ```
+
+5. **CI/CD triggers automatically**:
+   - Gitea CI builds Docker image on new tag
+   - Watchtower pulls and deploys to production
+   - Verify deployment: `curl http://192.168.86.149:8000/health`
+
 ---
 
 ## 2. FastAPI Architecture & Best Practices

CHANGELOG.md

@@ -7,6 +7,30 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.8.5] - 2025-12-16
+
+### Fixed
+
+- **Redis benchmark boolean storage** - Convert booleans to strings for Redis `hset` (Redis doesn't accept bool type directly)
+- **Tool tracking capability matching** - `delegate_to_librarian` now correctly recognized as using "librarian" capability when checking Steward recommendations
+- **E2E test fixture scope** - Fixed pytest-asyncio ScopeMismatch error by using `loop_scope="module"` for module-scoped async fixtures
+
+## [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 = "1.8.5"
 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

src/core/benchmarks.py

@@ -47,6 +47,10 @@ class PerformanceBenchmark(BaseModel):
         data = self.model_dump()
         data["timestamp"] = self.timestamp.isoformat()
         data["metadata"] = json.dumps(self.metadata)
+        # Convert booleans to strings (Redis doesn't accept bool type)
+        for key, value in data.items():
+            if isinstance(value, bool):
+                data[key] = str(value)
         return data
 
     @classmethod
@@ -54,6 +58,10 @@ class PerformanceBenchmark(BaseModel):
         """Reconstruct from Redis dict."""
         data["timestamp"] = datetime.fromisoformat(data["timestamp"])
         data["metadata"] = json.loads(data.get("metadata", "{}"))
+        # Convert string booleans back to bool
+        for key in ["success", "was_recommended", "was_actually_used"]:
+            if key in data and isinstance(data[key], str):
+                data[key] = data[key] == "True"
         return cls(**data)
 
 

src/core/tool_tracking.py

@@ -43,6 +43,16 @@ class ToolCallTracker:
             conversation_id=conversation_id,
         )
 
+    def _extract_capability(self, tool_name: str) -> str:
+        """
+        Extract capability name from tool name.
+
+        Tool names like 'delegate_to_librarian' map to capability 'librarian'.
+        """
+        if tool_name.startswith("delegate_to_"):
+            return tool_name.replace("delegate_to_", "")
+        return tool_name
+
     async def track_call(self, tool_name: str, duration: float):
         """
         Record a tool call with timing.
@@ -56,8 +66,9 @@ class ToolCallTracker:
             self.actual_calls[tool_name] = []
         self.actual_calls[tool_name].append(duration)
 
-        # Check if tool was recommended
+        # Check if tool was recommended (normalize tool name to capability)
-        was_recommended = tool_name in self.recommended_capabilities
+        capability = self._extract_capability(tool_name)
+        was_recommended = capability in self.recommended_capabilities
 
         if not was_recommended:
             logger.warning(
@@ -98,8 +109,12 @@ class ToolCallTracker:
         Called after Tatlock completes its response to identify
         tools that were recommended but never used.
         """
+        # Normalize actual tool names to capabilities for comparison
+        used_capabilities = {
+            self._extract_capability(tool) for tool in self.actual_calls.keys()
+        }
         # Find tools that were recommended but not used
-        unused_tools = self.recommended_capabilities - set(self.actual_calls.keys())
+        unused_tools = self.recommended_capabilities - used_capabilities
 
         if unused_tools:
             logger.info(
@@ -145,7 +160,11 @@ class ToolCallTracker:
             Dict with tracking statistics
         """
         total_calls = sum(len(durations) for durations in self.actual_calls.values())
-        unused = self.recommended_capabilities - set(self.actual_calls.keys())
+        # Normalize actual tool names to capabilities for comparison
+        used_capabilities = {
+            self._extract_capability(tool) for tool in self.actual_calls.keys()
+        }
+        unused = self.recommended_capabilities - used_capabilities
 
         return {
             "recommended_capabilities": list(self.recommended_capabilities),
@@ -154,11 +173,11 @@ class ToolCallTracker:
             "total_calls": total_calls,
             "accuracy": {
                 "recommended_and_used": len(
-                    self.recommended_capabilities & set(self.actual_calls.keys())
+                    self.recommended_capabilities & used_capabilities
                 ),
                 "recommended_but_unused": len(unused),
                 "not_recommended_but_used": len(
-                    set(self.actual_calls.keys()) - self.recommended_capabilities
+                    used_capabilities - self.recommended_capabilities
                 ),
             },
         }

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

tests/core/test_benchmarks.py

@@ -61,7 +61,7 @@ class TestPerformanceBenchmark:
         redis_dict = benchmark.to_redis_dict()
         assert redis_dict["operation"] == "test_op"
         assert redis_dict["duration_seconds"] == 1.0
-        assert redis_dict["success"] is True
+        assert redis_dict["success"] == "True"  # Booleans stored as strings in Redis
         assert isinstance(redis_dict["timestamp"], str)
         assert isinstance(redis_dict["metadata"], str)
 
@@ -72,7 +72,7 @@ class TestPerformanceBenchmark:
             "timestamp": now.isoformat(),
             "operation": "test_op",
             "duration_seconds": 1.5,
-            "success": True,
+            "success": "True",  # Booleans stored as strings in Redis
             "metadata": json.dumps({"test": "data"}),
             "recommendation_count": None,
             "confidence": None,
@@ -85,6 +85,7 @@ class TestPerformanceBenchmark:
         benchmark = PerformanceBenchmark.from_redis_dict(redis_dict)
         assert benchmark.operation == "test_op"
         assert benchmark.duration_seconds == 1.5
+        assert benchmark.success is True  # Converted back to bool
         assert benchmark.metadata == {"test": "data"}
 
 
@@ -162,12 +163,12 @@ class TestBenchmarkStore:
         mock_key = f"benchmark:test_op:{int(now.timestamp() * 1000)}"
         mock_redis.zrevrangebyscore.return_value = [mock_key]
 
-        # Mock hgetall to return proper data
+        # Mock hgetall to return proper data (booleans as strings, like Redis)
         mock_redis.hgetall.return_value = {
             "timestamp": now.isoformat(),
             "operation": "test_op",
             "duration_seconds": 1.5,  # Numeric, not string
-            "success": True,
+            "success": "True",  # Booleans stored as strings in Redis
             "metadata": "{}",
             "recommendation_count": None,
             "confidence": None,
@@ -237,7 +238,7 @@ class TestBenchmarkStore:
                 "timestamp": now.isoformat(),
                 "operation": "test_op",
                 "duration_seconds": float(data["duration_seconds"]),
-                "success": data["success"] == "True",
+                "success": data["success"],  # Pass string through, from_redis_dict converts
                 "metadata": "{}",
                 "recommendation_count": None,
                 "confidence": None,
@@ -296,14 +297,14 @@ class TestBenchmarkStore:
                 "timestamp": now.isoformat(),
                 "operation": "tool_call",
                 "duration_seconds": 1.0,
-                "success": True,
+                "success": "True",  # Booleans stored as strings in Redis
                 "metadata": "{}",
                 "recommendation_count": None,
                 "confidence": None,
                 "tool_name": "test_tool",
                 "conversation_id": None,
-                "was_recommended": data["was_recommended"] == "True",
+                "was_recommended": data["was_recommended"],  # Already strings
-                "was_actually_used": data["was_actually_used"] == "True",
+                "was_actually_used": data["was_actually_used"],  # Already strings
             }
 
         mock_redis.hgetall.side_effect = mock_hgetall

tests/core/test_tool_tracking.py

@@ -0,0 +1,101 @@
+"""
+Tests for tool call tracking.
+
+Tests capability extraction and recommendation matching.
+"""
+from unittest.mock import AsyncMock, patch
+
+import pytest
+
+from src.core.tool_tracking import ToolCallTracker
+
+
+class TestToolCallTracker:
+    """Test ToolCallTracker functionality."""
+
+    def test_extract_capability_delegation_tool(self):
+        """Test extracting capability from delegation tool name."""
+        tracker = ToolCallTracker(recommended_capabilities=["librarian"])
+
+        assert tracker._extract_capability("delegate_to_librarian") == "librarian"
+        assert tracker._extract_capability("delegate_to_biographer") == "biographer"
+        assert tracker._extract_capability("delegate_to_housekeeper") == "housekeeper"
+
+    def test_extract_capability_non_delegation_tool(self):
+        """Test that non-delegation tools return unchanged."""
+        tracker = ToolCallTracker(recommended_capabilities=[])
+
+        assert tracker._extract_capability("calculate") == "calculate"
+        assert tracker._extract_capability("search_web") == "search_web"
+
+    @pytest.mark.asyncio
+    async def test_track_call_recognizes_delegation_as_recommended(self):
+        """Test that delegate_to_X is recognized when X is recommended."""
+        tracker = ToolCallTracker(
+            recommended_capabilities=["librarian", "biographer"]
+        )
+
+        with patch("src.core.tool_tracking.get_benchmark_store") as mock_store:
+            mock_store.return_value.record = AsyncMock()
+
+            await tracker.track_call("delegate_to_librarian", 1.0)
+
+            # Should NOT log warning since librarian was recommended
+            call_args = mock_store.return_value.record.call_args
+            benchmark = call_args[0][0]
+            assert benchmark.was_recommended is True
+
+    @pytest.mark.asyncio
+    async def test_track_call_detects_not_recommended(self):
+        """Test that unrecommended tools are flagged."""
+        tracker = ToolCallTracker(
+            recommended_capabilities=["librarian"]
+        )
+
+        with patch("src.core.tool_tracking.get_benchmark_store") as mock_store:
+            mock_store.return_value.record = AsyncMock()
+
+            await tracker.track_call("delegate_to_housekeeper", 1.0)
+
+            call_args = mock_store.return_value.record.call_args
+            benchmark = call_args[0][0]
+            assert benchmark.was_recommended is False
+
+    def test_get_summary_with_delegation_tools(self):
+        """Test summary correctly maps delegation tools to capabilities."""
+        tracker = ToolCallTracker(
+            recommended_capabilities=["librarian", "biographer"]
+        )
+        tracker.actual_calls = {
+            "delegate_to_librarian": [1.0, 2.0],
+            "delegate_to_housekeeper": [0.5],  # Not recommended
+        }
+
+        summary = tracker.get_summary()
+
+        assert summary["accuracy"]["recommended_and_used"] == 1  # librarian
+        assert summary["accuracy"]["recommended_but_unused"] == 1  # biographer
+        assert summary["accuracy"]["not_recommended_but_used"] == 1  # housekeeper
+
+    @pytest.mark.asyncio
+    async def test_finalize_with_delegation_tools(self):
+        """Test finalize correctly identifies unused recommendations."""
+        tracker = ToolCallTracker(
+            recommended_capabilities=["librarian", "biographer"]
+        )
+        tracker.actual_calls = {
+            "delegate_to_librarian": [1.0],
+        }
+
+        with patch("src.core.tool_tracking.get_benchmark_store") as mock_store:
+            mock_store.return_value.record = AsyncMock()
+
+            await tracker.finalize()
+
+            # Should record benchmark for unused biographer
+            assert mock_store.return_value.record.called
+            call_args = mock_store.return_value.record.call_args
+            benchmark = call_args[0][0]
+            assert benchmark.tool_name == "biographer"
+            assert benchmark.was_recommended is True
+            assert benchmark.was_actually_used is False

tests/e2e/test_api_endpoints.py

@@ -8,8 +8,8 @@ These tests hit the actual running server and test the full stack:
 - Response formatting
 """
 import pytest
+import pytest_asyncio
 import httpx
-import asyncio
 from typing import AsyncGenerator
 
 # Test server base URL (assumes server is running on localhost:8777 via ./wakeup.sh)
@@ -17,15 +17,7 @@ BASE_URL = "http://localhost:8777"
 API_TIMEOUT = 120.0  # 120 second timeout for LLM calls
 
 
-@pytest.fixture(scope="module")
+@pytest_asyncio.fixture(loop_scope="module", scope="module")
-def event_loop():
-    """Create event loop for async tests."""
-    loop = asyncio.get_event_loop_policy().new_event_loop()
-    yield loop
-    loop.close()
-
-
-@pytest.fixture(scope="module")
 async def client() -> AsyncGenerator[httpx.AsyncClient, None]:
     """HTTP client for making requests."""
     async with httpx.AsyncClient(base_url=BASE_URL, timeout=API_TIMEOUT) as client: