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

@@ -22,12 +22,27 @@ 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
   * Example: `curl http://localhost:3002/jpmschweitzer/library-desk/raw/branch/main/README.md`
   * Public repos are readable without authentication
-  * Related repos: `library-desk`, `scheduler`
+  * Related repos: `library-desk`, `scheduler`, `core-api`, `portainer-core`
+
+### 🐳 Deployment & Infrastructure
+* **Full stack documentation**: Available in the `portainer-core` repo
+  * Access: `curl http://localhost:3002/jpmschweitzer/portainer-core/raw/branch/main/CONTAINERS.md`
+  * Contains: All service ports, URLs, Redis DB allocations, external domains
+* **Tatlock deployment**:
+  * LAN: `http://192.168.86.149:8000`
+  * External: `tatlock.schweitz.net` (behind Authentik SSO)
+  * Redis DBs: 1 (memory), 6 (benchmarks)
+* **Health check**: `curl http://192.168.86.149:8000/health`
 
 ### 🛡️ Git Discipline
 * **NEVER commit to `main` or `master` directly.** Always create a feature branch: `feature/your-feature-name` or `fix/issue-description`.
@@ -41,6 +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 +7,103 @@ 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
+
+- **HybridRAG keywords schema mismatch** - library-desk now returns `keywords` as dict with `core_keywords`, client now handles both formats
+
+## [1.8.1] - 2025-12-16
+
+### Fixed
+
+#### Ollama Message Sanitization
+- **Fixed `invalid message content type: <nil>` error** from Ollama
+- Created custom `TatlockOllamaProvider` that sanitizes messages before sending to Ollama
+- Ollama rejects assistant messages with `content: null` (tool-only messages from PydanticAI)
+- Provider converts `null` content to empty string `""` for compatibility
+- Updated all agents (Librarian, Biographer, Housekeeper, Tatlock) to use sanitized provider
+- Added `src/ollama/provider.py` with reusable provider pattern
+
+#### Streaming Think Message Accumulation
+- **Fixed repeating think messages in frontend** (e.g., 10x "The Librarian has compiled...")
+- Frontend was accumulating `ReasoningSummaryDelta` events expecting concatenation
+- Added `ReasoningSummaryDone()` signal after each think message to indicate completion
+- Each think slug is now treated as a complete message, not a continuation
+
+## [1.8.0] - 2025-12-15
+
+### Fixed
+
+#### Steward Routing for Web Search
+- Updated Steward guidelines to route web searches, weather, news → Librarian with `search_web`
+- Added URL/article reading → Librarian with `read_url` to routing guidelines
+- Added examples showing `search_web` and `read_url` tool usage
+
+#### Librarian Agent Tool Registration
+- Registered `search_web`, `read_url`, `read_urls_batch` tools with the Librarian PydanticAI agent
+- Updated Librarian system prompt with Web Search & Content Extraction section
+- Fixed tool count in agent logger (11 → 14 tools)
+
+#### Query Enrichment Integration
+- Fixed enriched query (with location/timezone context) not being passed to delegations
+- Response service now uses `enriched_query` from Steward recommendation for all delegations
+- Weather queries now automatically include user's stored location
+
+#### Action Type Detection
+- Added "read", "fetch", "url", "http" keywords to RESEARCH action type for Librarian
+- Ensures proper think messages for URL reading tasks
+
+## [1.7.0] - 2025-12-15
+
+### Added
+
+#### Web Search Migration to Librarian
+- **`search_web()`** tool in Librarian for web search via library-desk `/rag/search` endpoint
+- **`read_url()`** tool for single URL content extraction via Trafilatura
+- **`read_urls_batch()`** tool for parallel batch URL extraction (max 20 URLs)
+- `WebSearchResult`, `WebSearchResponse` models in LibraryDeskClient
+- `ContentExtractionResult`, `BatchExtractionResponse` models for content extraction
+- `search_web()`, `extract_content()`, `extract_content_batch()` methods in LibraryDeskClient
+- Comprehensive unit tests for new Librarian tools (`tests/agents/librarian/test_tools.py`)
+
+### Changed
+
+- Librarian capability updated with web search domains: "web", "url", "internet"
+- Tatlock system prompt now delegates web search to Librarian
+- `tatlock_core` capability reduced to computation/datetime only (no longer requires network)
+
+### Removed
+
+- `search_web` function from `src/agents/tatlock_core/tools.py`
+- `web_search_tool` from `tatlock_core_tools` list
+- `search_web` from legacy `src/agents/tools.py`
+- Search tests from `tests/agents/test_tools.py` (moved to Librarian tests)
+
 ## [1.6.0] - 2025-12-15
 
 ### Added

docs/rag_search_implementation.md

@@ -0,0 +1,348 @@
+# Tatlock Integration Guide
+
+Implementation instructions for integrating Library Desk search and content extraction endpoints into the Tatlock project.
+
+## Base Configuration
+
+```
+BASE_URL: http://library-desk:8089  (or your deployment URL)
+AUTH_HEADER: Authorization: Bearer <LIBRARY_API_KEY>
+```
+
+---
+
+## 1. RAG Search Endpoint
+
+**Use case:** Librarian needs to research a topic by searching the web.
+
+### Endpoint
+
+```
+POST /rag/search
+```
+
+### Request
+
+```json
+{
+  "query": "Python async programming best practices",
+  "search_type": "web",
+  "limit": 10,
+  "user": "tatlock-librarian"
+}
+```
+
+| Field | Type | Default | Description |
+|-------|------|---------|-------------|
+| `query` | string | required | Search query (1-500 chars) |
+| `search_type` | enum | `"web"` | `"web"`, `"news"`, or `"images"` |
+| `limit` | int | 10 | Results to return (1-20) |
+| `user` | string | `"default"` | User identifier for tracking |
+
+### Response
+
+```json
+{
+  "query": "Python async programming best practices",
+  "search_type": "web",
+  "results": [
+    {
+      "title": "Async IO in Python: A Complete Walkthrough",
+      "url": "https://realpython.com/async-io-python/",
+      "content": "Full extracted article text via Trafilatura (~2000 chars max)...",
+      "snippet": "Original search engine snippet (150-300 chars)...",
+      "source": "realpython.com",
+      "published_date": "2023-05-15"
+    }
+  ],
+  "total_results": 10,
+  "search_time_ms": 2340,
+  "sources_summary": "## Sources\n- [Async IO in Python](https://realpython.com/async-io-python/)\n- ..."
+}
+```
+
+### Key Fields for Tatlock
+
+| Field | Usage |
+|-------|-------|
+| `results[].content` | Full extracted text - use this for LLM context |
+| `results[].snippet` | Fallback if content extraction failed |
+| `sources_summary` | Pre-formatted markdown for citations |
+
+### Error Handling
+
+| HTTP Code | Meaning | Action |
+|-----------|---------|--------|
+| 400 | Invalid query | Check query length/format |
+| 502 | SearXNG unavailable | Retry with backoff |
+| 504 | Search timeout | Retry or reduce limit |
+| 500 | Internal error | Log and notify |
+
+### Example Usage (Python)
+
+```python
+import httpx
+
+async def search_web(query: str, limit: int = 10) -> dict:
+    async with httpx.AsyncClient() as client:
+        response = await client.post(
+            f"{BASE_URL}/rag/search",
+            headers={"Authorization": f"Bearer {API_KEY}"},
+            json={
+                "query": query,
+                "search_type": "web",
+                "limit": limit,
+                "user": "tatlock-librarian"
+            },
+            timeout=30.0
+        )
+        response.raise_for_status()
+        return response.json()
+
+# Usage
+results = await search_web("machine learning transformers")
+for r in results["results"]:
+    # Prefer full content, fall back to snippet
+    text = r["content"] or r["snippet"]
+    print(f"{r['title']}: {len(text)} chars")
+```
+
+---
+
+## 2. Content Extraction Endpoint
+
+**Use case:** Librarian has a specific URL and needs to read its content.
+
+### Single URL Extraction
+
+```
+POST /content/extract
+```
+
+#### Request
+
+```json
+{
+  "url": "https://example.com/article",
+  "include_metadata": true,
+  "max_length": 2000
+}
+```
+
+#### Response
+
+```json
+{
+  "result": {
+    "url": "https://example.com/article",
+    "title": "Article Title",
+    "content": "Extracted main text content...",
+    "author": "John Doe",
+    "date": "2024-01-15",
+    "language": "en",
+    "success": true,
+    "error": null
+  },
+  "extraction_time_ms": 1250
+}
+```
+
+### Batch URL Extraction
+
+```
+POST /content/extract/batch
+```
+
+#### Request
+
+```json
+{
+  "urls": [
+    "https://example.com/article1",
+    "https://example.com/article2",
+    "https://example.com/article3"
+  ],
+  "include_metadata": true,
+  "max_length": 2000
+}
+```
+
+#### Response
+
+```json
+{
+  "results": [
+    {
+      "url": "https://example.com/article1",
+      "title": "Article 1",
+      "content": "Extracted content...",
+      "success": true,
+      "error": null
+    },
+    {
+      "url": "https://example.com/article2",
+      "title": null,
+      "content": "",
+      "success": false,
+      "error": "Connection timeout"
+    }
+  ],
+  "total_urls": 3,
+  "successful": 2,
+  "failed": 1,
+  "extraction_time_ms": 3500
+}
+```
+
+---
+
+## 3. Error Pattern: Soft Failures
+
+> **Important:** Content extraction uses a **soft failure pattern** - individual URL failures do NOT throw HTTP errors.
+
+### Why Soft Failures?
+
+When extracting content from multiple URLs (batch) or even single URLs:
+- Some sites block bots
+- Some URLs are temporarily down
+- Some pages have no extractable content
+
+Instead of failing the entire request, we return:
+- `success: true/false` per result
+- `error: "reason"` when failed
+- Empty `content: ""` on failure
+
+### Handling Soft Failures
+
+```python
+async def extract_with_fallback(url: str) -> str:
+    response = await client.post(
+        f"{BASE_URL}/content/extract",
+        headers={"Authorization": f"Bearer {API_KEY}"},
+        json={"url": url}
+    )
+    response.raise_for_status()  # Only throws on 4xx/5xx
+
+    data = response.json()
+    result = data["result"]
+
+    if result["success"]:
+        return result["content"]
+    else:
+        # Log the failure, return empty or handle gracefully
+        logger.warning(f"Extraction failed for {url}: {result['error']}")
+        return ""  # Or raise, or use cached version, etc.
+```
+
+### Batch Processing Example
+
+```python
+async def extract_batch_with_stats(urls: list[str]) -> dict:
+    response = await client.post(
+        f"{BASE_URL}/content/extract/batch",
+        headers={"Authorization": f"Bearer {API_KEY}"},
+        json={"urls": urls, "max_length": 3000}
+    )
+    response.raise_for_status()
+
+    data = response.json()
+
+    # Separate successful and failed
+    successful = [r for r in data["results"] if r["success"]]
+    failed = [r for r in data["results"] if not r["success"]]
+
+    if failed:
+        logger.warning(f"{len(failed)} URLs failed extraction:")
+        for f in failed:
+            logger.warning(f"  {f['url']}: {f['error']}")
+
+    return {
+        "contents": {r["url"]: r["content"] for r in successful},
+        "failed_urls": [f["url"] for f in failed],
+        "success_rate": data["successful"] / data["total_urls"]
+    }
+```
+
+---
+
+## 4. Recommended Patterns for Tatlock
+
+### Research Flow
+
+```python
+async def librarian_research(topic: str) -> dict:
+    """
+    Full research flow: search + extract additional context.
+    """
+    # 1. Search for relevant pages
+    search_results = await search_web(topic, limit=10)
+
+    # 2. RAG search already includes extracted content
+    #    Only extract more if you need deeper content
+
+    # 3. Build context for LLM
+    context_parts = []
+    for r in search_results["results"]:
+        content = r["content"] or r["snippet"]
+        if content:
+            context_parts.append(f"## {r['title']}\nSource: {r['url']}\n\n{content}")
+
+    return {
+        "context": "\n\n---\n\n".join(context_parts),
+        "sources": search_results["sources_summary"],
+        "result_count": search_results["total_results"]
+    }
+```
+
+### Reading a Specific Page
+
+```python
+async def librarian_read_page(url: str) -> str:
+    """
+    Read a specific URL the user provided.
+    """
+    response = await client.post(
+        f"{BASE_URL}/content/extract",
+        headers={"Authorization": f"Bearer {API_KEY}"},
+        json={"url": url, "max_length": 5000}  # Longer for deep reads
+    )
+    response.raise_for_status()
+
+    result = response.json()["result"]
+
+    if not result["success"]:
+        raise ValueError(f"Could not read page: {result['error']}")
+
+    # Format for LLM
+    header = f"# {result['title'] or 'Untitled'}\n"
+    if result["author"]:
+        header += f"Author: {result['author']}\n"
+    if result["date"]:
+        header += f"Date: {result['date']}\n"
+
+    return header + "\n" + result["content"]
+```
+
+---
+
+## 5. Rate Limits & Best Practices
+
+| Recommendation | Reason |
+|----------------|--------|
+| Use `limit: 5-10` for searches | More results = longer extraction time |
+| Batch URLs when possible | More efficient than sequential calls |
+| Max 20 URLs per batch | Server limit |
+| Set reasonable timeouts (30s) | Content extraction can be slow |
+| Cache results client-side | Same URL rarely changes content |
+| Use `user` parameter | Helps with debugging and rate limiting |
+
+---
+
+## 6. Quick Reference
+
+| Endpoint | Method | Use Case |
+|----------|--------|----------|
+| `/rag/search` | POST | Search web + get extracted content |
+| `/content/extract` | POST | Read a single URL |
+| `/content/extract/batch` | POST | Read multiple URLs |
+| `/health` | GET | Check service status |

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tatlock"
-version = "1.6.0"
+version = "1.8.5"
 description = "OpenAI-compatible API with Ollama backend"
 requires-python = ">=3.12"
 dependencies = []

src/agents/biographer/agent.py

@@ -102,18 +102,15 @@ _biographer_agent: Optional[Agent[None, str]] = None
 
 def _create_biographer_agent() -> Agent[None, str]:
     """Create The Biographer PydanticAI agent."""
-    # Import required classes for Ollama configuration
     from pydantic_ai.models.openai import OpenAIChatModel
-    from pydantic_ai.providers.ollama import OllamaProvider
 
-    # PydanticAI expects Ollama base URL to end with /v1
-    clean_host = str(config.OLLAMA_HOST).rstrip('/')
-    base_url = f"{clean_host}/v1"
+    from src.ollama.provider import get_ollama_provider
 
-    # Create Ollama model with provider
+    # Create Ollama model with sanitized provider
+    # (fixes 'content: null' issue with tool calls)
     model = OpenAIChatModel(
         model_name=config.OLLAMA_DEFAULT_MODEL,
-        provider=OllamaProvider(base_url=base_url)
+        provider=get_ollama_provider(),
     )
 
     agent: Agent[None, str] = Agent(

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>",
-            "success": "<think>The Librarian has compiled the relevant findings.</think>",
-            "error": "<think>I'm afraid the archives proved difficult to access.</think>",
+            "start": "Allow me to consult the archives, sir.",
+            "success": "The Librarian has compiled the relevant findings.",
+            "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>",
-            "success": "<think>The Librarian has returned with findings, sir.</think>",
-            "error": "<think>The research proved inconclusive, I'm afraid.</think>",
+            "start": "I've dispatched the Librarian to conduct some fresh research.",
+            "success": "The Librarian has returned with findings, sir.",
+            "error": "The research proved inconclusive, I'm afraid.",
         },
         ActionType.CREATE: {
-            "start": "<think>I'm having the Librarian prepare a new entry.</think>",
-            "success": "<think>The new material has been properly catalogued, sir.</think>",
-            "error": "<think>I'm afraid there was difficulty filing the entry.</think>",
+            "start": "I'm having the Librarian prepare a new entry.",
+            "success": "The new material has been properly catalogued, sir.",
+            "error": "I'm afraid there was difficulty filing the entry.",
         },
     },
     "biographer": {
         ActionType.RETRIEVE: {
-            "start": "<think>Let me consult the household records.</think>",
-            "success": "<think>The Biographer has located the relevant information, sir.</think>",
-            "error": "<think>I'm unable to locate those particular records.</think>",
+            "start": "Let me consult the household records.",
+            "success": "The Biographer has located the relevant information, sir.",
+            "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>",
-            "success": "<think>The household records have been updated accordingly.</think>",
-            "error": "<think>I'm afraid there was difficulty recording the entry.</think>",
+            "start": "I've asked the Biographer to take note of this, sir.",
+            "success": "The household records have been updated accordingly.",
+            "error": "I'm afraid there was difficulty recording the entry.",
         },
     },
     "housekeeper": {
         ActionType.RETRIEVE: {
-            "start": "<think>Allow me to inquire with the household staff.</think>",
-            "success": "<think>The staff reports the current status, sir.</think>",
-            "error": "<think>The household staff is momentarily unavailable, I'm afraid.</think>",
+            "start": "Allow me to inquire with the household staff.",
+            "success": "The staff reports the current status, sir.",
+            "error": "The household staff is momentarily unavailable, I'm afraid.",
         },
         ActionType.CONTROL: {
-            "start": "<think>I'm instructing the household staff now, sir.</think>",
-            "success": "<think>The household has been configured as requested.</think>",
-            "error": "<think>I'm afraid the staff reports an issue with that request.</think>",
+            "start": "I'm instructing the household staff now, sir.",
+            "success": "The household has been configured as requested.",
+            "error": "I'm afraid the staff reports an issue with that request.",
         },
     },
 }
@@ -100,10 +101,13 @@ def _detect_action_type(expert: str, task: str) -> ActionType:
     task_lower = task.lower()
 
     if expert == "librarian":
+        # Web search, URL reading = RESEARCH (fresh external data)
         if any(w in task_lower for w in ["search", "find", "look up", "research"]):
             if any(w in task_lower for w in ["web", "online", "internet"]):
                 return ActionType.RESEARCH
             return ActionType.RETRIEVE
+        if any(w in task_lower for w in ["read", "fetch", "url", "http"]):
+            return ActionType.RESEARCH  # Reading URLs is research
         if any(w in task_lower for w in ["create", "write", "add", "make", "new"]):
             return ActionType.CREATE
         return ActionType.RETRIEVE
@@ -136,7 +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/housekeeper/agent.py

@@ -113,18 +113,15 @@ _housekeeper_agent: Optional[Agent[None, str]] = None
 
 def _create_housekeeper_agent() -> Agent[None, str]:
     """Create the Housekeeper PydanticAI agent."""
-    # Import required classes for Ollama configuration
     from pydantic_ai.models.openai import OpenAIChatModel
-    from pydantic_ai.providers.ollama import OllamaProvider
 
-    # PydanticAI expects Ollama base URL to end with /v1
-    clean_host = str(config.OLLAMA_HOST).rstrip("/")
-    base_url = f"{clean_host}/v1"
+    from src.ollama.provider import get_ollama_provider
 
-    # Create Ollama model with provider
+    # Create Ollama model with sanitized provider
+    # (fixes 'content: null' issue with tool calls)
     model = OpenAIChatModel(
         model_name=config.OLLAMA_DEFAULT_MODEL,
-        provider=OllamaProvider(base_url=base_url),
+        provider=get_ollama_provider(),
     )
 
     agent: Agent[None, str] = Agent(

src/agents/librarian/agent.py

@@ -19,6 +19,9 @@ from src.agents.librarian.tools import (
     get_wiki_page,
     hybrid_search,
     list_dossiers,
+    read_url,
+    read_urls_batch,
+    search_web,
     search_wiki,
     semantic_search,
     smart_create_wiki_page,
@@ -47,8 +50,17 @@ Your role is to help users find, understand, synthesize, and manage information
 
 ## Your Tools
 
-### Research Tools
-- **hybrid_search**: Your primary research tool - searches all sources at once
+### Web Search & Content Extraction
+- **search_web**: Search the internet for current information (weather, news, facts)
+  - Use for: weather forecasts, current events, recent developments, external facts
+  - Returns extracted content from search results, not just snippets
+- **read_url**: Read and extract content from a specific URL
+  - Use when: user provides a URL or you need to read a specific webpage
+- **read_urls_batch**: Read multiple URLs in parallel (up to 20)
+  - Use for: comparing multiple sources, gathering info from several pages
+
+### Internal Research Tools
+- **hybrid_search**: Your primary research tool - searches wiki, graph, and web at once
 - **search_wiki**: Find specific wiki pages by keyword
 - **semantic_search**: Find conceptually similar content
 - **explore_knowledge_graph** / **find_related_entities**: Discover connections
@@ -110,18 +122,15 @@ _librarian_agent: Optional[Agent[None, str]] = None
 
 def _create_librarian_agent() -> Agent[None, str]:
     """Create the Librarian PydanticAI agent."""
-    # Import required classes for Ollama configuration
     from pydantic_ai.models.openai import OpenAIChatModel
-    from pydantic_ai.providers.ollama import OllamaProvider
 
-    # PydanticAI expects Ollama base URL to end with /v1
-    clean_host = str(config.OLLAMA_HOST).rstrip('/')
-    base_url = f"{clean_host}/v1"
+    from src.ollama.provider import get_ollama_provider
 
-    # Create Ollama model with provider
+    # Create Ollama model with sanitized provider
+    # (fixes 'content: null' issue with tool calls)
     model = OpenAIChatModel(
         model_name=config.OLLAMA_DEFAULT_MODEL,
-        provider=OllamaProvider(base_url=base_url)
+        provider=get_ollama_provider(),
     )
 
     agent: Agent[None, str] = Agent(
@@ -130,7 +139,7 @@ def _create_librarian_agent() -> Agent[None, str]:
         retries=2,
     )
 
-    # Register research tools
+    # Register research tools (internal knowledge)
     agent.tool_plain(hybrid_search)
     agent.tool_plain(search_wiki)
     agent.tool_plain(semantic_search)
@@ -139,6 +148,11 @@ def _create_librarian_agent() -> Agent[None, str]:
     agent.tool_plain(explore_knowledge_graph)
     agent.tool_plain(find_related_entities)
 
+    # Register web search & content extraction tools
+    agent.tool_plain(search_web)
+    agent.tool_plain(read_url)
+    agent.tool_plain(read_urls_batch)
+
     # Register wiki read tools
     agent.tool_plain(get_wiki_page)
 
@@ -150,7 +164,7 @@ def _create_librarian_agent() -> Agent[None, str]:
     logger.info(
         "librarian_agent_created",
         model=config.OLLAMA_DEFAULT_MODEL,
-        tool_count=11,
+        tool_count=14,  # 7 research + 3 web + 1 wiki read + 3 wiki write
     )
 
     return agent

src/agents/librarian/capability.py

@@ -21,10 +21,11 @@ LIBRARIAN_CAPABILITY = HouseholdCapability(
     role="The Librarian",
     category="research",
     description=(
-        "Research and wiki management: can CREATE wiki pages about topics "
+        "Research, web search, and wiki management: can SEARCH the web for current "
+        "information, READ URLs/articles, CREATE wiki pages about topics "
         "(with automatic HybridRAG research), UPDATE existing pages, "
-        "SEARCH wiki/knowledge graph/web, and synthesize information. "
-        "Use for: 'create a page about X', 'update wiki', 'find info on X'"
+        "and synthesize information from multiple sources. "
+        "Use for: 'search for X', 'what is X', 'create a page about X', 'read this URL'"
     ),
     domains=[
         "research",
@@ -33,6 +34,9 @@ LIBRARIAN_CAPABILITY = HouseholdCapability(
         "wiki",
         "documents",
         "search",
+        "web",
+        "url",
+        "internet",
         "synthesis",
         "create",
         "write",

src/agents/librarian/client.py

@@ -98,6 +98,47 @@ class ResearchSummary(BaseModel):
     timing_ms: int = 0
 
 
+class WebSearchResult(BaseModel):
+    """Result from web search via /rag/search."""
+    title: str
+    url: str
+    content: str = ""  # Full extracted text via Trafilatura
+    snippet: str = ""  # Original search engine snippet
+    source: str = ""  # Domain name
+    published_date: Optional[str] = None
+
+
+class WebSearchResponse(BaseModel):
+    """Response from /rag/search endpoint."""
+    query: str
+    search_type: str
+    results: list[WebSearchResult] = Field(default_factory=list)
+    total_results: int = 0
+    search_time_ms: int = 0
+    sources_summary: str = ""  # Pre-formatted markdown citations
+
+
+class ContentExtractionResult(BaseModel):
+    """Result from content extraction."""
+    url: str
+    title: Optional[str] = None
+    content: str = ""
+    author: Optional[str] = None
+    date: Optional[str] = None
+    language: Optional[str] = None
+    success: bool = True
+    error: Optional[str] = None
+
+
+class BatchExtractionResponse(BaseModel):
+    """Response from batch content extraction."""
+    results: list[ContentExtractionResult] = Field(default_factory=list)
+    total_urls: int = 0
+    successful: int = 0
+    failed: int = 0
+    extraction_time_ms: int = 0
+
+
 class EntityLinking(BaseModel):
     """Entity linking results from smart-create."""
     forward_links: int = 0
@@ -240,9 +281,16 @@ class LibraryDeskClient:
                 metadata=r.get("metadata", {}),
             ))
 
+        # Handle keywords being either a list or a dict with core_keywords
+        raw_keywords = data.get("keywords", [])
+        if isinstance(raw_keywords, dict):
+            keywords = raw_keywords.get("core_keywords", [])
+        else:
+            keywords = raw_keywords
+
         return HybridRAGResponse(
             results=results,
-            keywords=data.get("keywords", []),
+            keywords=keywords,
             synonyms=data.get("synonyms", []),
             related_dossiers=data.get("related_dossiers", []),
             formatted_context=data.get("formatted_context", ""),
@@ -685,6 +733,186 @@ class LibraryDeskClient:
             logger.warning("library_desk_health_check_failed", error=str(e))
             return False
 
+    # ========================================================================
+    # RAG Search (Web Search with Content Extraction)
+    # ========================================================================
+
+    async def search_web(
+        self,
+        query: str,
+        user: str | None = None,
+        search_type: str = "web",
+        limit: int = 10,
+    ) -> WebSearchResponse:
+        """
+        Search the web and extract content from results.
+
+        Uses SearXNG for search and Trafilatura for content extraction.
+        Returns both snippets and full extracted text.
+
+        Args:
+            query: Search query (1-500 chars)
+            user: User identifier for tracking
+            search_type: "web", "news", or "images"
+            limit: Number of results (1-20)
+
+        Returns:
+            WebSearchResponse with results and pre-formatted sources
+        """
+        user = user or get_user()
+        client = self._ensure_client()
+
+        payload = {
+            "query": query,
+            "search_type": search_type,
+            "limit": limit,
+            "user": user or "tatlock-librarian",
+        }
+
+        logger.info("library_desk_web_search", query=query, limit=limit)
+
+        response = await client.post("/rag/search", json=payload, timeout=30.0)
+        response.raise_for_status()
+
+        data = response.json()
+
+        results = [
+            WebSearchResult(
+                title=r.get("title", ""),
+                url=r.get("url", ""),
+                content=r.get("content", ""),
+                snippet=r.get("snippet", ""),
+                source=r.get("source", ""),
+                published_date=r.get("published_date"),
+            )
+            for r in data.get("results", [])
+        ]
+
+        return WebSearchResponse(
+            query=data.get("query", query),
+            search_type=data.get("search_type", search_type),
+            results=results,
+            total_results=data.get("total_results", len(results)),
+            search_time_ms=data.get("search_time_ms", 0),
+            sources_summary=data.get("sources_summary", ""),
+        )
+
+    # ========================================================================
+    # Content Extraction
+    # ========================================================================
+
+    async def extract_content(
+        self,
+        url: str,
+        include_metadata: bool = True,
+        max_length: int = 5000,
+    ) -> ContentExtractionResult:
+        """
+        Extract main content from a URL.
+
+        Uses Trafilatura for intelligent content extraction,
+        removing boilerplate, ads, and navigation.
+
+        Note: Uses soft failure pattern - check result.success field.
+
+        Args:
+            url: URL to extract content from
+            include_metadata: Whether to extract author, date, etc.
+            max_length: Maximum content length
+
+        Returns:
+            ContentExtractionResult (check .success and .error fields)
+        """
+        client = self._ensure_client()
+
+        payload = {
+            "url": url,
+            "include_metadata": include_metadata,
+            "max_length": max_length,
+        }
+
+        logger.debug("library_desk_extract_content", url=url)
+
+        response = await client.post("/content/extract", json=payload, timeout=30.0)
+        response.raise_for_status()
+
+        data = response.json()
+        result = data.get("result", {})
+
+        return ContentExtractionResult(
+            url=result.get("url", url),
+            title=result.get("title"),
+            content=result.get("content", ""),
+            author=result.get("author"),
+            date=result.get("date"),
+            language=result.get("language"),
+            success=result.get("success", False),
+            error=result.get("error"),
+        )
+
+    async def extract_content_batch(
+        self,
+        urls: list[str],
+        include_metadata: bool = True,
+        max_length: int = 2000,
+    ) -> BatchExtractionResponse:
+        """
+        Extract content from multiple URLs in parallel.
+
+        More efficient than sequential calls. Max 20 URLs per batch.
+
+        Note: Uses soft failure pattern - individual failures don't
+        throw errors, check each result's .success field.
+
+        Args:
+            urls: List of URLs to extract (max 20)
+            include_metadata: Whether to extract author, date, etc.
+            max_length: Maximum content length per URL
+
+        Returns:
+            BatchExtractionResponse with results and stats
+        """
+        client = self._ensure_client()
+
+        payload = {
+            "urls": urls[:20],  # Server limit
+            "include_metadata": include_metadata,
+            "max_length": max_length,
+        }
+
+        logger.info("library_desk_extract_batch", url_count=len(urls))
+
+        response = await client.post(
+            "/content/extract/batch",
+            json=payload,
+            timeout=60.0,  # Longer timeout for batch
+        )
+        response.raise_for_status()
+
+        data = response.json()
+
+        results = [
+            ContentExtractionResult(
+                url=r.get("url", ""),
+                title=r.get("title"),
+                content=r.get("content", ""),
+                author=r.get("author"),
+                date=r.get("date"),
+                language=r.get("language"),
+                success=r.get("success", False),
+                error=r.get("error"),
+            )
+            for r in data.get("results", [])
+        ]
+
+        return BatchExtractionResponse(
+            results=results,
+            total_urls=data.get("total_urls", len(urls)),
+            successful=data.get("successful", 0),
+            failed=data.get("failed", 0),
+            extraction_time_ms=data.get("extraction_time_ms", 0),
+        )
+
 
 # Global client factory
 async def get_library_client() -> LibraryDeskClient:

src/agents/librarian/tools.py

@@ -432,6 +432,239 @@ async def find_related_entities(
         return f"Error finding related entities: {str(e)}"
 
 
+# ============================================================================
+# Web Search & Content Extraction
+# ============================================================================
+
+async def search_web(
+    query: str,
+    limit: int = 10,
+    search_type: str = "web",
+) -> str:
+    """
+    Search the web and extract content from results.
+
+    This is the primary tool for finding current information online.
+    Results include both snippets and full extracted text from pages.
+
+    Search types:
+    - "web": General web search (default)
+    - "news": News articles
+    - "images": Image search
+
+    Args:
+        query: Search query (1-500 chars)
+        limit: Number of results (1-20, default: 10)
+        search_type: Type of search ("web", "news", or "images")
+
+    Returns:
+        Formatted search results with sources and extracted content
+
+    Examples:
+        search_web("Python 3.12 new features")
+        search_web("latest tech news", search_type="news", limit=5)
+    """
+    try:
+        async with LibraryDeskClient() as client:
+            response = await client.search_web(
+                query=query,
+                limit=limit,
+                search_type=search_type,
+            )
+
+            if not response.results:
+                return f"No results found for '{query}'"
+
+            output_parts = [f"## Web Search: {query}\n"]
+            output_parts.append(f"*Found {response.total_results} results in {response.search_time_ms}ms*\n")
+
+            for i, result in enumerate(response.results, 1):
+                output_parts.append(f"### {i}. {result.title}")
+                output_parts.append(f"**Source:** {result.source}")
+                output_parts.append(f"**URL:** {result.url}")
+
+                if result.published_date:
+                    output_parts.append(f"**Date:** {result.published_date}")
+
+                # Use full content if available, otherwise snippet
+                content = result.content or result.snippet
+                if content:
+                    # Truncate for readability
+                    if len(content) > 500:
+                        content = content[:500] + "..."
+                    output_parts.append(f"\n{content}")
+
+                output_parts.append("")
+
+            # Add pre-formatted sources for citations
+            if response.sources_summary:
+                output_parts.append("---")
+                output_parts.append(response.sources_summary)
+
+            logger.info(
+                "librarian_web_search",
+                query=query,
+                result_count=response.total_results,
+                search_type=search_type,
+            )
+
+            return "\n".join(output_parts)
+
+    except Exception as e:
+        logger.error("librarian_web_search_error", error=str(e), query=query)
+        return f"Error searching web: {str(e)}"
+
+
+async def read_url(
+    url: str,
+    max_length: int = 5000,
+) -> str:
+    """
+    Read and extract the main content from a URL.
+
+    Use this when you have a specific URL to read, such as:
+    - A link the user provided
+    - A URL from search results you want to read in full
+    - Documentation or article pages
+
+    Extracts the main content, removing ads, navigation, and boilerplate.
+
+    Args:
+        url: The URL to read
+        max_length: Maximum content length (default: 5000)
+
+    Returns:
+        Extracted page content with metadata
+
+    Examples:
+        read_url("https://docs.python.org/3/library/asyncio.html")
+        read_url("https://example.com/article", max_length=10000)
+    """
+    try:
+        async with LibraryDeskClient() as client:
+            result = await client.extract_content(
+                url=url,
+                include_metadata=True,
+                max_length=max_length,
+            )
+
+            if not result.success:
+                return f"Could not read page: {result.error or 'Unknown error'}"
+
+            output_parts = []
+
+            # Header with metadata
+            if result.title:
+                output_parts.append(f"# {result.title}")
+            else:
+                output_parts.append(f"# Content from {url}")
+
+            output_parts.append(f"**URL:** {url}")
+
+            if result.author:
+                output_parts.append(f"**Author:** {result.author}")
+
+            if result.date:
+                output_parts.append(f"**Date:** {result.date}")
+
+            if result.language and result.language != "en":
+                output_parts.append(f"**Language:** {result.language}")
+
+            output_parts.append("")
+
+            # Main content
+            if result.content:
+                output_parts.append(result.content)
+            else:
+                output_parts.append("(No content could be extracted)")
+
+            logger.info(
+                "librarian_read_url",
+                url=url,
+                content_length=len(result.content) if result.content else 0,
+            )
+
+            return "\n".join(output_parts)
+
+    except Exception as e:
+        logger.error("librarian_read_url_error", error=str(e), url=url)
+        return f"Error reading URL: {str(e)}"
+
+
+async def read_urls_batch(
+    urls: list[str],
+    max_length: int = 2000,
+) -> str:
+    """
+    Read and extract content from multiple URLs in parallel.
+
+    More efficient than calling read_url multiple times.
+    Max 20 URLs per batch.
+
+    Note: Individual failures don't fail the entire batch -
+    failed URLs are reported but other content is still returned.
+
+    Args:
+        urls: List of URLs to read (max 20)
+        max_length: Maximum content length per URL (default: 2000)
+
+    Returns:
+        Extracted content from all successful URLs with failure report
+
+    Examples:
+        read_urls_batch(["https://example.com/1", "https://example.com/2"])
+    """
+    try:
+        async with LibraryDeskClient() as client:
+            response = await client.extract_content_batch(
+                urls=urls,
+                include_metadata=True,
+                max_length=max_length,
+            )
+
+            output_parts = [
+                f"## Batch Content Extraction",
+                f"*Extracted {response.successful}/{response.total_urls} URLs in {response.extraction_time_ms}ms*\n",
+            ]
+
+            # Show successful extractions
+            for result in response.results:
+                if result.success:
+                    title = result.title or result.url
+                    output_parts.append(f"### {title}")
+                    output_parts.append(f"**URL:** {result.url}")
+
+                    if result.content:
+                        # Truncate for readability in batch mode
+                        content = result.content
+                        if len(content) > max_length:
+                            content = content[:max_length] + "..."
+                        output_parts.append(f"\n{content}")
+
+                    output_parts.append("")
+
+            # Report failures
+            failed = [r for r in response.results if not r.success]
+            if failed:
+                output_parts.append("---")
+                output_parts.append("### Failed Extractions")
+                for result in failed:
+                    output_parts.append(f"- {result.url}: {result.error}")
+
+            logger.info(
+                "librarian_read_urls_batch",
+                total=response.total_urls,
+                successful=response.successful,
+                failed=response.failed,
+            )
+
+            return "\n".join(output_parts)
+
+    except Exception as e:
+        logger.error("librarian_read_urls_batch_error", error=str(e))
+        return f"Error reading URLs: {str(e)}"
+
+
 # ============================================================================
 # Wiki Write Operations
 # ============================================================================
@@ -685,7 +918,7 @@ async def smart_create_wiki_page(
 
 # All tools available to The Librarian
 LIBRARIAN_TOOLS = [
-    # Research tools
+    # Research tools (internal knowledge)
     hybrid_search,
     search_wiki,
     get_wiki_page,
@@ -694,6 +927,10 @@ LIBRARIAN_TOOLS = [
     semantic_search,
     explore_knowledge_graph,
     find_related_entities,
+    # Web search & content extraction
+    search_web,
+    read_url,
+    read_urls_batch,
     # Write tools
     create_wiki_page,
     update_wiki_page,

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/agents/steward/agent.py

@@ -58,8 +58,9 @@ GUIDELINES:
 - Simple greetings/chat → no capabilities needed (conversational response only)
 - Questions about prior conversation ("what did I say", "my name", "what we discussed") → no capabilities (Tatlock has full history)
 - Math/calculations → tatlock_core
-- Quick web searches → tatlock_core
 - Time/date queries → tatlock_core
+- Web searches, weather, news, current information → librarian with search_web
+- Read a URL or article → librarian with read_url
 - Wiki creation ("create a page about X", "add X to wiki") → librarian with smart_create
 - Wiki updates ("update the page", "add to dossier") → librarian with update
 - Research queries ("find info", "what do we know about", "search for") → librarian with hybrid_search
@@ -74,8 +75,10 @@ COMPLEXITY: [simple/moderate/complex]
 CONTEXT: [any relevant conversation context, or "none"]
 
 EXAMPLES:
+- "DELEGATE: librarian to search_web for tomorrow's weather forecast"
 - "DELEGATE: librarian to create a wiki page about CI/CD pipelines"
-- "DELEGATE: librarian to search for information about Docker networking"
+- "DELEGATE: librarian to hybrid_search for information about Docker networking"
+- "DELEGATE: librarian to read_url https://example.com/article"
 - "DELEGATE: tatlock_core to calculate the result"
 - "DELEGATE: none (conversational response only)"
 

src/agents/tatlock.py

@@ -17,7 +17,6 @@ from src.agents.tatlock_core.tools import (
     get_current_datetime,
     calculate_time_offset,
     time_difference,
-    search_web,
 )
 from src.core.config import config
 from src.core.logging_config import get_logger
@@ -76,18 +75,17 @@ You have direct access to several permanent tools that you should USE whenever a
    - time_difference: Calculate the time between two dates
    - Use these for ANY date/time queries - never guess at dates or times
 
-3. **Web Search** (search_web): Search for current, volatile, or factual information
-   - Use this for ANY information that might be current, factual, or outside your training data
+3. **Web Search** (via Librarian): For current, volatile, or factual information
+   - Delegate to the Librarian for web searches and research
    - Examples: news, current events, recent developments, specific facts, technical documentation
-   - Always prefer searching over guessing or using potentially outdated knowledge
-   - For extensive research questions, note that this will later be delegated to the librarian
+   - Use: delegate_to_librarian(task="search the web for ...")
 
 ## Tool Usage Guidelines
 
 - **Mathematics**: ALWAYS use the calculator tool, even for simple arithmetic
 - **Dates/Times**: ALWAYS use the date/time tools, never guess or estimate
-- **Current Information**: ALWAYS search for facts, news, or volatile information
-- **Verification**: When facts are important, use search to verify rather than rely on memory alone
+- **Current Information**: Delegate web searches to the Librarian
+- **Verification**: When facts are important, delegate to Librarian for research
 - When you use a tool, explain what you're doing in a butler-appropriate manner
 - Present tool results naturally in your response
 
@@ -145,7 +143,7 @@ class TatlockAgent(AgentInterface):
 
         # Import required classes for Ollama configuration
         from pydantic_ai.models.openai import OpenAIChatModel
-        from pydantic_ai.providers.ollama import OllamaProvider
+        from src.ollama.provider import get_ollama_provider
 
         # PydanticAI expects Ollama base URL to end with /v1
         # Remove trailing slash from ollama_host if present
@@ -155,7 +153,7 @@ class TatlockAgent(AgentInterface):
         # Create Ollama model with provider
         ollama_model = OpenAIChatModel(
             model_name=self.model_name,
-            provider=OllamaProvider(base_url=base_url)
+            provider=get_ollama_provider()
         )
 
         # Create PydanticAI agent with Ollama model
@@ -238,28 +236,8 @@ class TatlockAgent(AgentInterface):
                 ctx.deps.log_call(f"🕐 Calculating time difference between {date1_str} and {date2_str}")
             return time_difference(date1_str, date2_str)
 
-        # Web search tool
-        @self._agent.tool
-        async def web_search(ctx: RunContext[ToolCallTracker], query: str, num_results: int = 5) -> str:
-            """
-            Search the web using SearXNG for current information.
-
-            Use this tool for ANY information that might be:
-            - Current or time-sensitive (news, events, recent developments)
-            - Factual and verifiable (statistics, technical specs, definitions)
-            - Outside your training data or knowledge cutoff
-
-            Args:
-                query: Search query string
-                num_results: Number of results to return (default: 5, max: 10)
-
-            Returns:
-                Formatted search results with titles, URLs, and snippets
-            """
-            # Log the search query to reasoning output
-            if ctx.deps:
-                ctx.deps.log_call(f"🔍 Searching for: '{query}'")
-            return await search_web(query, num_results)
+        # NOTE: Web search has been moved to The Librarian agent.
+        # Use delegate_to_librarian(task="search web for ...") for web search.
 
     @property
     def agent(self):
@@ -470,7 +448,7 @@ class TatlockAgent(AgentInterface):
             ... )
         """
         from pydantic_ai.models.openai import OpenAIChatModel
-        from pydantic_ai.providers.ollama import OllamaProvider
+        from src.ollama.provider import get_ollama_provider
 
         logger.info(
             "tatlock_run_with_scoped_tools",
@@ -486,7 +464,7 @@ class TatlockAgent(AgentInterface):
 
         ollama_model = OpenAIChatModel(
             model_name=self.model_name,
-            provider=OllamaProvider(base_url=base_url)
+            provider=get_ollama_provider()
         )
 
         # Create agent with scoped tools
@@ -564,7 +542,7 @@ class TatlockAgent(AgentInterface):
             Text chunks from the streaming response
         """
         from pydantic_ai.models.openai import OpenAIChatModel
-        from pydantic_ai.providers.ollama import OllamaProvider
+        from src.ollama.provider import get_ollama_provider
 
         logger.info(
             "tatlock_run_with_scoped_tools_stream",
@@ -579,7 +557,7 @@ class TatlockAgent(AgentInterface):
 
         ollama_model = OpenAIChatModel(
             model_name=self.model_name,
-            provider=OllamaProvider(base_url=base_url)
+            provider=get_ollama_provider()
         )
 
         # Create agent with scoped tools
@@ -659,7 +637,7 @@ class TatlockAgent(AgentInterface):
                 - raw_output: The agent's raw text output
         """
         from pydantic_ai.models.openai import OpenAIChatModel
-        from pydantic_ai.providers.ollama import OllamaProvider
+        from src.ollama.provider import get_ollama_provider
         from pydantic_ai.settings import ModelSettings
         from pydantic_ai.messages import (
             ModelRequest,
@@ -683,7 +661,7 @@ class TatlockAgent(AgentInterface):
 
         ollama_model = OpenAIChatModel(
             model_name=self.model_name,
-            provider=OllamaProvider(base_url=base_url)
+            provider=get_ollama_provider()
         )
 
         # Create agent with scoped tools
@@ -781,7 +759,7 @@ class TatlockAgent(AgentInterface):
             str: Butler-toned response synthesized from all results
         """
         from pydantic_ai.models.openai import OpenAIChatModel
-        from pydantic_ai.providers.ollama import OllamaProvider
+        from src.ollama.provider import get_ollama_provider
         from pydantic_ai.messages import ModelRequest, ModelResponse, UserPromptPart, TextPart
 
         logger.info(
@@ -824,7 +802,7 @@ class TatlockAgent(AgentInterface):
 
         ollama_model = OpenAIChatModel(
             model_name=self.model_name,
-            provider=OllamaProvider(base_url=base_url)
+            provider=get_ollama_provider()
         )
 
         # Synthesis agent uses butler prompt but no tools

src/agents/tatlock_core/__init__.py

@@ -1,7 +1,8 @@
 """
 Tatlock's core tools package.
 
-Provides calculator, date/time, and web search capabilities.
+Provides calculator and date/time capabilities.
+Web search has been moved to The Librarian agent.
 Organized as a household member with toolset and capability registration.
 """
 from .capability import TATLOCK_CORE_CAPABILITY, get_capability
@@ -10,7 +11,6 @@ from .tools import (
     calculate,
     calculate_time_offset,
     get_current_datetime,
-    search_web,
     time_difference,
 )
 
@@ -20,7 +20,6 @@ __all__ = [
     "get_current_datetime",
     "calculate_time_offset",
     "time_difference",
-    "search_web",
     # Toolset
     "tatlock_core_tools",
     "get_core_tools",

src/agents/tatlock_core/capability.py

@@ -11,10 +11,10 @@ TATLOCK_CORE_CAPABILITY = HouseholdCapability(
     name="tatlock_core",
     role="Butler's Core Tools",
     category="core",
-    description="Essential tools for computation, date/time operations, and web searches",
-    domains=["computation", "datetime", "information", "research"],
+    description="Essential tools for computation and date/time operations",
+    domains=["computation", "datetime", "math", "calculator"],
     cost="low",
-    requires_network=True,  # For web search
+    requires_network=False,  # Web search moved to Librarian
 )
 
 

src/agents/tatlock_core/tools.py

@@ -256,96 +256,5 @@ def time_difference(date1_str: str, date2_str: str = "now") -> str:
         return f"Error calculating time difference: {str(e)}"
 
 
-# ============================================================================
-# SearXNG Search Tool
-# ============================================================================
-
-async def search_web(query: str, num_results: int = 5) -> str:
-    """
-    Search the web using SearXNG.
-
-    Args:
-        query: Search query string
-        num_results: Number of results to return (default: 5, max: 10)
-
-    Returns:
-        Formatted search results as a string with titles, URLs, and snippets
-
-    Examples:
-        search_web("Python async programming") -> "1. Title: ...\n   URL: ...\n   ..."
-    """
-    try:
-        # Limit results
-        num_results = min(num_results, 10)
-
-        # Get SearXNG host with fallback logic
-        searxng_host = str(config.SEARXNG_HOST)
-
-        # Try production host first, fall back to localhost in development
-        hosts_to_try = [searxng_host]
-        if config.ENVIRONMENT.value == "development" and "localhost" not in searxng_host:
-            # Add localhost fallback for development
-            hosts_to_try.append("http://localhost:8087")
-
-        last_error = None
-
-        for host in hosts_to_try:
-            try:
-                logger.debug("searxng_search_attempt", host=host, query=query)
-
-                async with httpx.AsyncClient(timeout=config.SEARXNG_TIMEOUT) as client:
-                    response = await client.get(
-                        f"{host}/search",
-                        params={
-                            "q": query,
-                            "format": "json",
-                            "pageno": 1,
-                        }
-                    )
-
-                    if response.status_code == 200:
-                        data = response.json()
-                        results = data.get("results", [])
-
-                        if not results:
-                            return f"No results found for '{query}'"
-
-                        # Format results
-                        formatted_results = []
-                        for i, result in enumerate(results[:num_results], 1):
-                            title = result.get("title", "No title")
-                            url = result.get("url", "")
-                            content = result.get("content", "No description available")
-
-                            formatted_results.append(
-                                f"{i}. {title}\n"
-                                f"   URL: {url}\n"
-                                f"   {content}\n"
-                            )
-
-                        logger.info(
-                            "searxng_search_success",
-                            host=host,
-                            query=query,
-                            result_count=len(results),
-                        )
-                        return "\n".join(formatted_results)
-                    else:
-                        last_error = f"SearXNG returned status {response.status_code}"
-
-            except httpx.ConnectError:
-                last_error = f"Cannot connect to SearXNG at {host}"
-                logger.warning("searxng_connection_failed", host=host)
-                continue
-            except Exception as e:
-                last_error = str(e)
-                logger.warning("searxng_error", host=host, error=str(e))
-                continue
-
-        # All hosts failed
-        logger.error("searxng_all_hosts_failed", error=last_error)
-        return f"Error searching: {last_error}. Please check that SearXNG is running."
-
-    except Exception as e:
-        logger.error("searxng_unexpected_error", error=str(e), exc_info=True)
-        return f"Error searching: {str(e)}"
+# NOTE: Web search has been moved to The Librarian agent.
+# Use delegate_to_librarian(task="search web for ...") for web search.

src/agents/tatlock_core/toolset.py

@@ -55,17 +55,8 @@ time_difference_tool = Tool(
     ),
 )
 
-web_search_tool = Tool(
-    function=tools.search_web,
-    name="search_web",
-    description=(
-        "Search the web using SearXNG for current information. "
-        "Use this to find recent events, current data, or verify facts. "
-        "Returns formatted results with titles, URLs, and snippets. "
-        "Useful for information that may have changed since training data."
-    ),
-    takes_ctx=False,
-)
+# NOTE: Web search has been moved to The Librarian agent.
+# Use delegate_to_librarian(task="search web for ...") for web search.
 
 
 # Combined toolset of all core tools
@@ -74,7 +65,6 @@ tatlock_core_tools = [
     current_datetime_tool,
     time_offset_tool,
     time_difference_tool,
-    web_search_tool,
 ]
 
 

src/agents/tools.py

@@ -4,20 +4,14 @@ Tatlock's permanent tools.
 These tools are always available to the butler agent:
 - Calculator: For all mathematical operations
 - Date/Time toolkit: For current time and time calculations
-- SearXNG search: For searching the web for current information
+
+Note: Web search has been moved to The Librarian agent.
+See src/agents/librarian/tools.py for search_web functionality.
 """
 
-import logging
 import math
 import re
 from datetime import datetime, timedelta
-from typing import Any
-
-import httpx
-
-from src.core.config import config
-
-logger = logging.getLogger(__name__)
 
 
 # ============================================================================
@@ -256,91 +250,3 @@ def time_difference(date1_str: str, date2_str: str = "now") -> str:
 
     except Exception as e:
         return f"Error calculating time difference: {str(e)}"
-
-
-# ============================================================================
-# SearXNG Search Tool
-# ============================================================================
-
-async def search_web(query: str, num_results: int = 5) -> str:
-    """
-    Search the web using SearXNG.
-
-    Args:
-        query: Search query string
-        num_results: Number of results to return (default: 5, max: 10)
-
-    Returns:
-        Formatted search results as a string with titles, URLs, and snippets
-
-    Examples:
-        search_web("Python async programming") -> "1. Title: ...\n   URL: ...\n   ..."
-    """
-    try:
-        # Limit results
-        num_results = min(num_results, 10)
-
-        # Get SearXNG host with fallback logic
-        searxng_host = str(config.SEARXNG_HOST)
-
-        # Try production host first, fall back to localhost in development
-        hosts_to_try = [searxng_host]
-        if config.ENVIRONMENT.value == "development" and "localhost" not in searxng_host:
-            # Add localhost fallback for development
-            hosts_to_try.append("http://localhost:8087")
-
-        last_error = None
-
-        for host in hosts_to_try:
-            try:
-                logger.info(f"Attempting SearXNG search at {host}")
-
-                async with httpx.AsyncClient(timeout=config.SEARXNG_TIMEOUT) as client:
-                    response = await client.get(
-                        f"{host}/search",
-                        params={
-                            "q": query,
-                            "format": "json",
-                            "pageno": 1,
-                        }
-                    )
-
-                    if response.status_code == 200:
-                        data = response.json()
-                        results = data.get("results", [])
-
-                        if not results:
-                            return f"No results found for '{query}'"
-
-                        # Format results
-                        formatted_results = []
-                        for i, result in enumerate(results[:num_results], 1):
-                            title = result.get("title", "No title")
-                            url = result.get("url", "")
-                            content = result.get("content", "No description available")
-
-                            formatted_results.append(
-                                f"{i}. {title}\n"
-                                f"   URL: {url}\n"
-                                f"   {content}\n"
-                            )
-
-                        return "\n".join(formatted_results)
-                    else:
-                        last_error = f"SearXNG returned status {response.status_code}"
-
-            except httpx.ConnectError:
-                last_error = f"Cannot connect to SearXNG at {host}"
-                logger.warning(f"SearXNG connection failed at {host}, trying next host if available")
-                continue
-            except Exception as e:
-                last_error = str(e)
-                logger.warning(f"SearXNG error at {host}: {e}")
-                continue
-
-        # All hosts failed
-        return f"Error searching: {last_error}. Please check that SearXNG is running."
-
-    except Exception as e:
-        logger.error(f"Unexpected error in search_web: {e}", exc_info=True)
-        return f"Error searching: {str(e)}"

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
-            if not in_reasoning:
-                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"),
-                            finish_reason=None,
-                        )
-                    ],
-                )
-                in_reasoning = True
-
-            # Stream reasoning delta
+            # Stream reasoning via reasoning_content field (DeepSeek R1 format)
+            # Open WebUI renders this as collapsible thinking block
+            in_reasoning = True
             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
-            if in_reasoning:
-                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
+            # Signal end of reasoning block (no content needed)
+            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
-        was_recommended = tool_name in self.recommended_capabilities
+        # Check if tool was recommended (normalize tool name to capability)
+        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
                 ),
             },
         }

src/ollama/provider.py

@@ -0,0 +1,130 @@
+"""
+PydanticAI provider for Ollama with message sanitization.
+
+Ollama's OpenAI-compatible API rejects messages with `content: null`,
+which PydanticAI sends for assistant messages that only contain tool calls.
+This provider sanitizes messages to use empty strings instead of null.
+"""
+from typing import Any
+
+from openai import AsyncOpenAI
+from pydantic_ai.providers.ollama import OllamaProvider
+
+from src.core.config import config
+from src.core.logging_config import get_logger
+
+logger = get_logger(__name__)
+
+
+class TatlockOllamaProvider(OllamaProvider):
+    """
+    Custom OllamaProvider with message sanitization for Tatlock agents.
+
+    Fixes the 'invalid message content type: <nil>' error that occurs
+    when assistant messages have `content: null` with tool calls.
+    """
+
+    def __init__(self, base_url: str | None = None):
+        """
+        Initialize provider with Ollama base URL.
+
+        Args:
+            base_url: Ollama API URL (defaults to config.OLLAMA_HOST/v1)
+        """
+        if base_url is None:
+            clean_host = str(config.OLLAMA_HOST).rstrip("/")
+            base_url = f"{clean_host}/v1"
+
+        super().__init__(base_url=base_url)
+
+        # Override the client with our sanitized version
+        self._openai_client = _SanitizedAsyncOpenAI(base_url=base_url)
+
+        logger.debug("tatlock_ollama_provider_created", base_url=base_url)
+
+
+class _SanitizedAsyncOpenAI(AsyncOpenAI):
+    """AsyncOpenAI client that sanitizes messages before sending."""
+
+    def __init__(self, **kwargs: Any):
+        # Ollama doesn't need an API key
+        super().__init__(api_key="ollama", **kwargs)
+
+    @property
+    def chat(self) -> "_SanitizedChat":
+        """Return sanitized chat interface."""
+        return _SanitizedChat(self)
+
+
+class _SanitizedChat:
+    """Chat interface wrapper with sanitized completions."""
+
+    def __init__(self, client: _SanitizedAsyncOpenAI):
+        self._client = client
+        self._original_chat = AsyncOpenAI.chat.fget(client)  # type: ignore
+
+    @property
+    def completions(self) -> "_SanitizedCompletions":
+        """Return sanitized completions interface."""
+        return _SanitizedCompletions(self._original_chat.completions)
+
+
+class _SanitizedCompletions:
+    """Completions wrapper that sanitizes messages before API calls."""
+
+    def __init__(self, original_completions: Any):
+        self._original = original_completions
+
+    async def create(self, **kwargs: Any) -> Any:
+        """
+        Create chat completion with sanitized messages.
+
+        Converts `content: null` to `content: ""` in assistant messages
+        to prevent Ollama's 'invalid message content type: <nil>' error.
+        """
+        if "messages" in kwargs:
+            kwargs["messages"] = _sanitize_messages(kwargs["messages"])
+
+        return await self._original.create(**kwargs)
+
+
+def _sanitize_messages(messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
+    """
+    Sanitize messages to fix null content issues.
+
+    When an assistant message has tool_calls but no text content,
+    PydanticAI sets content to None. Ollama rejects this.
+    We convert None to empty string.
+
+    Args:
+        messages: List of chat messages
+
+    Returns:
+        Sanitized messages with null content replaced by empty strings
+    """
+    sanitized = []
+    for msg in messages:
+        msg_copy = dict(msg)
+
+        # Fix null content in assistant messages with tool calls
+        if msg_copy.get("role") == "assistant":
+            if msg_copy.get("content") is None and msg_copy.get("tool_calls"):
+                msg_copy["content"] = ""
+                logger.debug(
+                    "sanitized_null_content",
+                    tool_call_count=len(msg_copy["tool_calls"]),
+                )
+
+        sanitized.append(msg_copy)
+
+    return sanitized
+
+
+def get_ollama_provider() -> TatlockOllamaProvider:
+    """
+    Get a configured Ollama provider for PydanticAI agents.
+
+    Returns:
+        TatlockOllamaProvider configured with sanitization
+    """
+    return TatlockOllamaProvider()

src/responses/service.py

@@ -515,15 +515,18 @@ async def create_response_with_steward(request: ResponseRequest) -> Response:
     from src.agents.tatlock import TatlockAgent
     tatlock = TatlockAgent()
 
+    # Use enriched query (with location/timezone context) if available
+    effective_query = enriched.recommendation.enriched_query or user_message
+
     if delegation_only:
         # Direct delegation path - collect results then synthesize
         orchestration_results = await _direct_delegation_with_results(
-            user_message, enriched.recommendation, tracker, conversation_id
+            effective_query, enriched.recommendation, tracker, conversation_id
         )
     else:
         # Phase 1: Orchestrate tool calls
         orchestration_results = await tatlock.orchestrate_tool_calls(
-            user_message=user_message,
+            user_message=effective_query,
             steward_note=enriched.steward_note,
             scoped_tools=enriched.scoped_tools,
             message_history=conversation_history,

src/responses/streaming.py

@@ -211,8 +211,10 @@ class StreamingCoordinator:
                 )
 
                 # Stream think slugs that were collected during delegation
+                # Each think message is complete, so we signal done after each
                 for think_msg in orchestration_results.get("think_messages", []):
                     yield ReasoningSummaryDelta(delta=think_msg)
+                    yield ReasoningSummaryDone()
                     await asyncio.sleep(0.05)
 
             else:

tests/agents/librarian/test_tools.py

@@ -0,0 +1,426 @@
+"""
+Tests for Librarian tools.
+
+Tests the tool functions that wrap the Library-Desk API,
+including the new web search and content extraction tools.
+"""
+
+import pytest
+from unittest.mock import AsyncMock, MagicMock, patch
+
+from src.agents.librarian.tools import (
+    search_web,
+    read_url,
+    read_urls_batch,
+    hybrid_search,
+    search_wiki,
+)
+from src.agents.librarian.client import (
+    WebSearchResult,
+    WebSearchResponse,
+    ContentExtractionResult,
+    BatchExtractionResponse,
+)
+
+
+@pytest.fixture
+def mock_client():
+    """Create a mock LibraryDeskClient."""
+    client = AsyncMock()
+    return client
+
+
+# ============================================================================
+# Web Search Tests
+# ============================================================================
+
+@pytest.mark.unit
+class TestSearchWeb:
+    """Tests for search_web tool."""
+
+    @pytest.mark.asyncio
+    async def test_search_web_success(self, mock_client):
+        """Test successful web search."""
+        mock_response = WebSearchResponse(
+            query="Python async programming",
+            search_type="web",
+            results=[
+                WebSearchResult(
+                    title="Async Python Tutorial",
+                    url="https://example.com/async",
+                    content="Full content about async programming...",
+                    snippet="Learn async programming in Python",
+                    source="example.com",
+                ),
+                WebSearchResult(
+                    title="AsyncIO Documentation",
+                    url="https://docs.python.org/asyncio",
+                    content="Official asyncio docs content...",
+                    snippet="Python asyncio library reference",
+                    source="docs.python.org",
+                ),
+            ],
+            total_results=2,
+            search_time_ms=150,
+            sources_summary="**Sources:**\n- example.com\n- docs.python.org",
+        )
+        mock_client.search_web.return_value = mock_response
+
+        with patch(
+            "src.agents.librarian.tools.LibraryDeskClient"
+        ) as mock_client_class:
+            mock_client_class.return_value.__aenter__.return_value = mock_client
+            mock_client_class.return_value.__aexit__.return_value = None
+
+            result = await search_web("Python async programming")
+
+            assert "Python async programming" in result
+            assert "Async Python Tutorial" in result
+            assert "https://example.com/async" in result
+            assert "example.com" in result
+            assert "150ms" in result or "2 results" in result
+
+    @pytest.mark.asyncio
+    async def test_search_web_no_results(self, mock_client):
+        """Test web search with no results."""
+        mock_response = WebSearchResponse(
+            query="nonexistent query xyz123",
+            search_type="web",
+            results=[],
+            total_results=0,
+            search_time_ms=50,
+        )
+        mock_client.search_web.return_value = mock_response
+
+        with patch(
+            "src.agents.librarian.tools.LibraryDeskClient"
+        ) as mock_client_class:
+            mock_client_class.return_value.__aenter__.return_value = mock_client
+            mock_client_class.return_value.__aexit__.return_value = None
+
+            result = await search_web("nonexistent query xyz123")
+
+            assert "No results found" in result
+
+    @pytest.mark.asyncio
+    async def test_search_web_error_handling(self, mock_client):
+        """Test web search error handling."""
+        mock_client.search_web.side_effect = Exception("Connection failed")
+
+        with patch(
+            "src.agents.librarian.tools.LibraryDeskClient"
+        ) as mock_client_class:
+            mock_client_class.return_value.__aenter__.return_value = mock_client
+            mock_client_class.return_value.__aexit__.return_value = None
+
+            result = await search_web("test query")
+
+            assert "Error" in result
+            assert "Connection failed" in result
+
+    @pytest.mark.asyncio
+    async def test_search_web_with_news_type(self, mock_client):
+        """Test web search with news search type."""
+        mock_response = WebSearchResponse(
+            query="latest tech news",
+            search_type="news",
+            results=[
+                WebSearchResult(
+                    title="Tech News Today",
+                    url="https://news.example.com/tech",
+                    snippet="Breaking tech news",
+                    source="news.example.com",
+                    published_date="2024-01-15",
+                ),
+            ],
+            total_results=1,
+            search_time_ms=100,
+        )
+        mock_client.search_web.return_value = mock_response
+
+        with patch(
+            "src.agents.librarian.tools.LibraryDeskClient"
+        ) as mock_client_class:
+            mock_client_class.return_value.__aenter__.return_value = mock_client
+            mock_client_class.return_value.__aexit__.return_value = None
+
+            result = await search_web("latest tech news", search_type="news")
+
+            assert "Tech News Today" in result
+            mock_client.search_web.assert_called_with(
+                query="latest tech news",
+                limit=10,
+                search_type="news",
+            )
+
+
+# ============================================================================
+# Read URL Tests
+# ============================================================================
+
+@pytest.mark.unit
+class TestReadUrl:
+    """Tests for read_url tool."""
+
+    @pytest.mark.asyncio
+    async def test_read_url_success(self, mock_client):
+        """Test successful URL content extraction."""
+        mock_result = ContentExtractionResult(
+            url="https://example.com/article",
+            title="Great Article Title",
+            content="This is the full article content extracted from the page.",
+            author="John Doe",
+            date="2024-01-10",
+            language="en",
+            success=True,
+        )
+        mock_client.extract_content.return_value = mock_result
+
+        with patch(
+            "src.agents.librarian.tools.LibraryDeskClient"
+        ) as mock_client_class:
+            mock_client_class.return_value.__aenter__.return_value = mock_client
+            mock_client_class.return_value.__aexit__.return_value = None
+
+            result = await read_url("https://example.com/article")
+
+            assert "Great Article Title" in result
+            assert "https://example.com/article" in result
+            assert "John Doe" in result
+            assert "full article content" in result
+
+    @pytest.mark.asyncio
+    async def test_read_url_failure(self, mock_client):
+        """Test URL extraction failure."""
+        mock_result = ContentExtractionResult(
+            url="https://example.com/blocked",
+            success=False,
+            error="403 Forbidden",
+        )
+        mock_client.extract_content.return_value = mock_result
+
+        with patch(
+            "src.agents.librarian.tools.LibraryDeskClient"
+        ) as mock_client_class:
+            mock_client_class.return_value.__aenter__.return_value = mock_client
+            mock_client_class.return_value.__aexit__.return_value = None
+
+            result = await read_url("https://example.com/blocked")
+
+            assert "Could not read page" in result
+            assert "403 Forbidden" in result
+
+    @pytest.mark.asyncio
+    async def test_read_url_with_max_length(self, mock_client):
+        """Test URL extraction with custom max length."""
+        mock_result = ContentExtractionResult(
+            url="https://example.com/long",
+            title="Long Article",
+            content="X" * 10000,
+            success=True,
+        )
+        mock_client.extract_content.return_value = mock_result
+
+        with patch(
+            "src.agents.librarian.tools.LibraryDeskClient"
+        ) as mock_client_class:
+            mock_client_class.return_value.__aenter__.return_value = mock_client
+            mock_client_class.return_value.__aexit__.return_value = None
+
+            result = await read_url("https://example.com/long", max_length=2000)
+
+            mock_client.extract_content.assert_called_with(
+                url="https://example.com/long",
+                include_metadata=True,
+                max_length=2000,
+            )
+
+
+# ============================================================================
+# Batch URL Tests
+# ============================================================================
+
+@pytest.mark.unit
+class TestReadUrlsBatch:
+    """Tests for read_urls_batch tool."""
+
+    @pytest.mark.asyncio
+    async def test_batch_success(self, mock_client):
+        """Test successful batch extraction."""
+        mock_response = BatchExtractionResponse(
+            results=[
+                ContentExtractionResult(
+                    url="https://example.com/1",
+                    title="Article 1",
+                    content="Content from article 1",
+                    success=True,
+                ),
+                ContentExtractionResult(
+                    url="https://example.com/2",
+                    title="Article 2",
+                    content="Content from article 2",
+                    success=True,
+                ),
+            ],
+            total_urls=2,
+            successful=2,
+            failed=0,
+            extraction_time_ms=300,
+        )
+        mock_client.extract_content_batch.return_value = mock_response
+
+        with patch(
+            "src.agents.librarian.tools.LibraryDeskClient"
+        ) as mock_client_class:
+            mock_client_class.return_value.__aenter__.return_value = mock_client
+            mock_client_class.return_value.__aexit__.return_value = None
+
+            result = await read_urls_batch([
+                "https://example.com/1",
+                "https://example.com/2",
+            ])
+
+            assert "Article 1" in result
+            assert "Article 2" in result
+            assert "2/2" in result or "Extracted 2" in result
+
+    @pytest.mark.asyncio
+    async def test_batch_partial_failure(self, mock_client):
+        """Test batch extraction with some failures."""
+        mock_response = BatchExtractionResponse(
+            results=[
+                ContentExtractionResult(
+                    url="https://example.com/good",
+                    title="Good Article",
+                    content="Content extracted successfully",
+                    success=True,
+                ),
+                ContentExtractionResult(
+                    url="https://example.com/bad",
+                    success=False,
+                    error="Connection timeout",
+                ),
+            ],
+            total_urls=2,
+            successful=1,
+            failed=1,
+            extraction_time_ms=500,
+        )
+        mock_client.extract_content_batch.return_value = mock_response
+
+        with patch(
+            "src.agents.librarian.tools.LibraryDeskClient"
+        ) as mock_client_class:
+            mock_client_class.return_value.__aenter__.return_value = mock_client
+            mock_client_class.return_value.__aexit__.return_value = None
+
+            result = await read_urls_batch([
+                "https://example.com/good",
+                "https://example.com/bad",
+            ])
+
+            # Should contain successful result
+            assert "Good Article" in result
+            # Should report failure
+            assert "Failed" in result
+            assert "Connection timeout" in result
+
+
+# ============================================================================
+# Response Model Tests
+# ============================================================================
+
+@pytest.mark.unit
+class TestWebSearchModels:
+    """Tests for web search response models."""
+
+    def test_web_search_result_model(self):
+        """Test WebSearchResult model."""
+        result = WebSearchResult(
+            title="Test Title",
+            url="https://example.com",
+            content="Full content here",
+            snippet="Short snippet",
+            source="example.com",
+            published_date="2024-01-15",
+        )
+
+        assert result.title == "Test Title"
+        assert result.url == "https://example.com"
+        assert result.content == "Full content here"
+        assert result.source == "example.com"
+
+    def test_web_search_result_defaults(self):
+        """Test WebSearchResult default values."""
+        result = WebSearchResult(
+            title="Title",
+            url="https://example.com",
+        )
+
+        assert result.content == ""
+        assert result.snippet == ""
+        assert result.source == ""
+        assert result.published_date is None
+
+    def test_web_search_response_model(self):
+        """Test WebSearchResponse model."""
+        response = WebSearchResponse(
+            query="test query",
+            search_type="web",
+            results=[
+                WebSearchResult(title="R1", url="https://example.com/1"),
+                WebSearchResult(title="R2", url="https://example.com/2"),
+            ],
+            total_results=2,
+            search_time_ms=100,
+            sources_summary="**Sources:** example.com",
+        )
+
+        assert response.query == "test query"
+        assert len(response.results) == 2
+        assert response.total_results == 2
+
+    def test_content_extraction_result_model(self):
+        """Test ContentExtractionResult model."""
+        result = ContentExtractionResult(
+            url="https://example.com",
+            title="Title",
+            content="Content",
+            author="Author",
+            date="2024-01-01",
+            language="en",
+            success=True,
+        )
+
+        assert result.url == "https://example.com"
+        assert result.success is True
+        assert result.author == "Author"
+
+    def test_content_extraction_failure(self):
+        """Test ContentExtractionResult for failed extraction."""
+        result = ContentExtractionResult(
+            url="https://example.com",
+            success=False,
+            error="404 Not Found",
+        )
+
+        assert result.success is False
+        assert result.error == "404 Not Found"
+        assert result.content == ""
+
+    def test_batch_extraction_response_model(self):
+        """Test BatchExtractionResponse model."""
+        response = BatchExtractionResponse(
+            results=[
+                ContentExtractionResult(url="https://1.com", success=True),
+                ContentExtractionResult(url="https://2.com", success=False),
+            ],
+            total_urls=2,
+            successful=1,
+            failed=1,
+            extraction_time_ms=500,
+        )
+
+        assert response.total_urls == 2
+        assert response.successful == 1
+        assert response.failed == 1

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):
-        """Test messages are wrapped in <think> tags."""
+    def test_messages_are_plain_text(self):
+        """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}"
-                    assert msg.endswith("</think>"), f"{expert}/{action_type}/{phase}"
+                    # Messages should NOT have <think> wrappers - they go to reasoning_content field
+                    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
-        assert "</think>" in msg
+        # No <think> wrappers - messages go to reasoning_content field
+        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
-            assert any("<think>" in u and "Consulting" in u for u in updates)
+            # First update should be about consulting (no <think> wrappers anymore)
+            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
-            assert any("<think>" in u and "completed" in u for u in updates)
+            # Should have message about completion (no <think> wrappers anymore)
+            assert any("completed" in u for u in updates)
 
     @pytest.mark.asyncio
     async def test_orchestrate_yields_expert_output(self):

tests/agents/test_tools.py

@@ -1,17 +1,18 @@
 """
-Tests for Tatlock's permanent tools (calculator, date/time, search).
+Tests for Tatlock's permanent tools (calculator, date/time).
+
+Note: Web search has been moved to The Librarian agent.
+See tests/agents/librarian/test_tools.py for search tests.
 """
 
 import pytest
 from datetime import datetime
-from unittest.mock import AsyncMock, patch
 
 from src.agents.tools import (
     calculate,
     get_current_datetime,
     calculate_time_offset,
     time_difference,
-    search_web,
 )
 
 
@@ -188,184 +189,3 @@ class TestDateTime:
         """Test error handling for invalid dates."""
         result = time_difference("invalid-date", "now")
         assert "Error" in result
-
-
-# ============================================================================
-# Search Tests
-# ============================================================================
-
-class TestSearch:
-    """Tests for web search tool."""
-
-    @pytest.mark.asyncio
-    async def test_search_web_success(self):
-        """Test successful web search."""
-        mock_response = {
-            "results": [
-                {
-                    "title": "Test Result 1",
-                    "url": "https://example.com/1",
-                    "content": "This is a test result"
-                },
-                {
-                    "title": "Test Result 2",
-                    "url": "https://example.com/2",
-                    "content": "Another test result"
-                }
-            ]
-        }
-
-        with patch("src.agents.tools.httpx.AsyncClient") as mock_client_class:
-            # Create mock response
-            mock_response_obj = type('MockResponse', (), {
-                'status_code': 200,
-                'json': lambda *args, **kwargs: mock_response
-            })()
-
-            # Create mock client with async get method
-            async def mock_get(*args, **kwargs):
-                return mock_response_obj
-
-            mock_client_instance = type('MockClient', (), {
-                'get': mock_get
-            })()
-
-            # Setup async context manager
-            async def mock_aenter(*args, **kwargs):
-                return mock_client_instance
-
-            async def mock_aexit(*args, **kwargs):
-                return None
-
-            mock_client_class.return_value.__aenter__ = mock_aenter
-            mock_client_class.return_value.__aexit__ = mock_aexit
-
-            result = await search_web("test query", num_results=2)
-
-            assert "Test Result 1" in result
-            assert "https://example.com/1" in result
-            assert "Test Result 2" in result
-            assert "https://example.com/2" in result
-
-    @pytest.mark.asyncio
-    async def test_search_web_no_results(self):
-        """Test web search with no results."""
-        mock_response_data = {"results": []}
-
-        with patch("src.agents.tools.httpx.AsyncClient") as mock_client_class:
-            mock_response_obj = type('MockResponse', (), {
-                'status_code': 200,
-                'json': lambda *args, **kwargs: mock_response_data
-            })()
-
-            async def mock_get(*args, **kwargs):
-                return mock_response_obj
-
-            mock_client_instance = type('MockClient', (), {
-                'get': mock_get
-            })()
-
-            async def mock_aenter(*args, **kwargs):
-                return mock_client_instance
-
-            async def mock_aexit(*args, **kwargs):
-                return None
-
-            mock_client_class.return_value.__aenter__ = mock_aenter
-            mock_client_class.return_value.__aexit__ = mock_aexit
-
-            result = await search_web("test query")
-
-            assert "No results found" in result
-
-    @pytest.mark.asyncio
-    async def test_search_web_connection_error(self):
-        """Test web search with connection error."""
-        with patch("httpx.AsyncClient") as mock_client:
-            mock_client_instance = AsyncMock()
-            mock_client_instance.get.side_effect = Exception("Connection failed")
-            mock_client.return_value.__aenter__.return_value = mock_client_instance
-
-            result = await search_web("test query")
-
-            assert "Error searching" in result
-
-    @pytest.mark.asyncio
-    async def test_search_web_limits_results(self):
-        """Test that search limits results to max 10."""
-        mock_response_data = {
-            "results": [
-                {"title": f"Result {i}", "url": f"https://example.com/{i}", "content": "Test"}
-                for i in range(20)
-            ]
-        }
-
-        with patch("src.agents.tools.httpx.AsyncClient") as mock_client_class:
-            mock_response_obj = type('MockResponse', (), {
-                'status_code': 200,
-                'json': lambda *args, **kwargs: mock_response_data
-            })()
-
-            async def mock_get(*args, **kwargs):
-                return mock_response_obj
-
-            mock_client_instance = type('MockClient', (), {
-                'get': mock_get
-            })()
-
-            async def mock_aenter(*args, **kwargs):
-                return mock_client_instance
-
-            async def mock_aexit(*args, **kwargs):
-                return None
-
-            mock_client_class.return_value.__aenter__ = mock_aenter
-            mock_client_class.return_value.__aexit__ = mock_aexit
-
-            result = await search_web("test query", num_results=15)
-
-            # Should only return 10 results (max limit)
-            result_count = result.count("URL:")
-            assert result_count == 10
-
-    @pytest.mark.asyncio
-    async def test_search_web_formats_results(self):
-        """Test that search results are properly formatted."""
-        mock_response_data = {
-            "results": [
-                {
-                    "title": "Test Title",
-                    "url": "https://example.com",
-                    "content": "Test content description"
-                }
-            ]
-        }
-
-        with patch("src.agents.tools.httpx.AsyncClient") as mock_client_class:
-            mock_response_obj = type('MockResponse', (), {
-                'status_code': 200,
-                'json': lambda *args, **kwargs: mock_response_data
-            })()
-
-            async def mock_get(*args, **kwargs):
-                return mock_response_obj
-
-            mock_client_instance = type('MockClient', (), {
-                'get': mock_get
-            })()
-
-            async def mock_aenter(*args, **kwargs):
-                return mock_client_instance
-
-            async def mock_aexit(*args, **kwargs):
-                return None
-
-            mock_client_class.return_value.__aenter__ = mock_aenter
-            mock_client_class.return_value.__aexit__ = mock_aexit
-
-            result = await search_web("test query")
-
-            # Check formatting
-            assert "1. Test Title" in result
-            assert "URL: https://example.com" in result
-            assert "Test content description" in result

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")
-                        if content and ("<think>" in content or "</think>" in content):
-                            think_tags_found = True
+                        reasoning = delta.get("reasoning_content")
+                        if reasoning:
+                            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)
-    assert think_tags_found, "Expected <think> tags in streaming output"
+    # Should have found reasoning_content (reasoning enabled automatically)
+    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 = []
-    found_think_opening = False
-    found_think_closing = False
-    found_content_after_think = False
+    chunk_types = []  # Track order: 'reasoning' or 'content'
 
     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", "")
-                        if content:
-                            all_content.append(content)
+                        reasoning = delta.get("reasoning_content")
+                        content = delta.get("content")
 
-                            if "<think>" in content:
-                                found_think_opening = True
-                            if "</think>" in content:
-                                found_think_closing = True
-                            # 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
+                        if reasoning:
+                            chunk_types.append("reasoning")
+                        if content:
+                            chunk_types.append("content")
 
                 except json.JSONDecodeError:
                     pass
 
-    # Verify ordering
-    full_text = "".join(all_content)
-    if found_think_opening and found_think_closing:
-        # Reasoning should come before main content
-        think_start = full_text.index("<think>")
-        think_end = full_text.index("</think>")
-        assert think_start < think_end, "Opening <think> should come before closing </think>"
+    # Verify reasoning comes before content
+    if "reasoning" in chunk_types and "content" in chunk_types:
+        first_reasoning = chunk_types.index("reasoning")
+        first_content = chunk_types.index("content")
+        assert first_reasoning < first_content, "reasoning_content should come before content"
 
 
 @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_actually_used": data["was_actually_used"] == "True",
+                "was_recommended": data["was_recommended"],  # Already strings
+                "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")
-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")
+@pytest_asyncio.fixture(loop_scope="module", 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: