feat: migrate web search from tatlock_core to Librarian

Move web search functionality to The Librarian agent, integrating with
the library-desk /rag/search endpoint for enhanced search capabilities.

Changes:
- Add search_web, read_url, read_urls_batch tools to Librarian
- Add WebSearchResult, ContentExtractionResult models to client
- Add search_web, extract_content, extract_content_batch client methods
- Update Librarian capability with web/url/internet domains
- Remove search_web from tatlock_core tools and toolset
- Update Tatlock system prompt to delegate web search to Librarian
- Add comprehensive unit tests for new Librarian tools
- Clean up legacy src/agents/tools.py

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
2025-12-15 18:30:16 +01:00
co-authored by Claude Opus 4.5
parent 3e432d662e
commit 100ebeae52
13 changed files with 1287 additions and 425 deletions
+3 -97
View File
@@ -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)}"