Release v0.2.46

feat: add You.com tools (migrated from praisonaiagents core)

.github/automation.meta.json

@@ -3,7 +3,7 @@
   "stack": "claude",
   "profile": "tools",
   "mode": "hub",
-  "hubRef": "v1.1.11",
+  "hubRef": "v1.1.15",
   "templateVersion": "1.1.6",
   "installedAt": "2026-09-07T12:54:25Z"
 }

.github/workflows/auto-pr-comment.yml

@@ -10,7 +10,7 @@ on:
   pull_request_target:
     types: [opened, synchronize]
   schedule:
-    - cron: '30 3,9,15,21 * * *'
+    - cron: '30 * * * *'
   workflow_dispatch:
 
 env:
@@ -27,7 +27,7 @@ jobs:
     permissions:
       issues: write
       pull-requests: write
-    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].11
+    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].20
     secrets: inherit
     with:
-      hub_ref: v1.1.11
+      hub_ref: v1.1.20

.github/workflows/bot-pr-recovery.yml

@@ -16,8 +16,8 @@ permissions:
 
 jobs:
   recover:
-    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].11
+    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].20
     secrets: inherit
     with:
-      hub_ref: v1.1.11
+      hub_ref: v1.1.20
       pr_number: ${{ github.event.inputs.pr_number || '' }}

.github/workflows/ci-failure-claude.yml

@@ -25,8 +25,8 @@ permissions:
 
 jobs:
   detect-and-trigger:
-    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].11
+    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].20
     secrets: inherit
     with:
-      hub_ref: v1.1.11
+      hub_ref: v1.1.20
       pr_number: ${{ github.event.inputs.pr_number || '' }}

.github/workflows/claude-merge-gate.yml

@@ -43,9 +43,9 @@ jobs:
       id-token: write
     steps:
       - uses: actions/checkout@v4
-      - uses: MervinPraison/github-automation-template/.github/actions/[email protected].11
+      - uses: MervinPraison/github-automation-template/.github/actions/[email protected].20
         with:
-          hub_ref: v1.1.11
+          hub_ref: v1.1.20
       - name: Generate GitHub App token
         id: app-token
         uses: actions/create-github-app-token@v1
@@ -87,9 +87,10 @@ jobs:
       issues: write
       actions: read
       id-token: write
-    uses: MervinPraison/github-automation-template/.github/workflows/[email protected]
+      statuses: write   # the assess job records security/outsider-review
+    uses: MervinPraison/github-automation-template/.github/workflows/[email protected]
     secrets: inherit
     with:
-      hub_ref: v1.1.11
+      hub_ref: v1.1.20
       pr_number: ${{ github.event.inputs.pr_number || github.event.client_payload.pr_number || '' }}
       merge_method: ${{ github.event.inputs.merge_method || 'merge' }}

.github/workflows/claude.yml

@@ -18,7 +18,7 @@ jobs:
       issues: write
       actions: read
       id-token: write
-    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].11
+    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].20
     secrets: inherit
     with:
-      hub_ref: v1.1.11
+      hub_ref: v1.1.20

.github/workflows/merge-conflict-claude.yml

@@ -25,9 +25,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: MervinPraison/github-automation-template/.github/actions/[email protected].11
+      - uses: MervinPraison/github-automation-template/.github/actions/[email protected].20
         with:
-          hub_ref: v1.1.11
+          hub_ref: v1.1.20
       - name: Detect conflicting PRs and trigger Claude
         uses: actions/github-script@v7
         with:

.github/workflows/pipeline-status-sync.yml

@@ -13,7 +13,7 @@ permissions:
 
 jobs:
   sync:
-    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].11
+    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].20
     secrets: inherit
     with:
-      hub_ref: v1.1.11
+      hub_ref: v1.1.20

praisonai_tools/tools/youdotcom_tool.py

@@ -0,0 +1,484 @@
+"""You.com search and content tools for PraisonAI Agents.
+
+Migrated from ``praisonaiagents.tools.youdotcom_tools`` (MervinPraison/PraisonAI#6168).
+
+You.com provides AI-powered web search, news search, content extraction, and image search.
+This module requires the YDC_API_KEY environment variable to be set.
+
+Usage:
+    from praisonai_tools.tools.youdotcom_tool import ydc_search, ydc_news, ydc_contents
+    
+    # Search the web (unified web + news)
+    results = ydc_search("AI news 2024")
+    
+    # Get live news
+    news = ydc_news("technology trends")
+    
+    # Extract content from URLs
+    content = ydc_contents(["https://example.com"])
+    
+    # Or use the class directly
+    from praisonai_tools.tools.youdotcom_tool import YouTools
+    you = YouTools()
+    results = you.search("AI news")
+"""
+
+from typing import List, Dict, Any, Optional, Union
+import logging
+import os
+from importlib import util
+
+
+class YouTools:
+    """Comprehensive tools for web search and content using You.com API.
+    
+    You.com provides AI-powered search capabilities optimized for LLM applications.
+    
+    Features:
+    - Unified web and news search with LLM-ready snippets
+    - Live news search from authoritative sources
+    - Content extraction from URLs (HTML/Markdown)
+    - Image search
+    - Advanced search operators support
+    - Geographic and language targeting
+    - Freshness controls
+    
+    Requires:
+    - youdotcom package: pip install youdotcom
+    - YDC_API_KEY environment variable
+    """
+    
+    def __init__(self, api_key: Optional[str] = None):
+        """Initialize YouTools.
+        
+        Args:
+            api_key: Optional API key. If not provided, uses YDC_API_KEY env var.
+        """
+        self._api_key = api_key
+        self._client = None
+    
+    def _get_api_key(self) -> Optional[str]:
+        """Get API key from instance or environment."""
+        return self._api_key or os.environ.get("YDC_API_KEY")
+    
+    def _get_client(self):
+        """Get or create You.com client."""
+        if self._client is None:
+            if util.find_spec("youdotcom") is None:
+                return None, "youdotcom package is not installed. Please install it using: pip install youdotcom"
+            api_key = self._get_api_key()
+            if not api_key:
+                return None, "YDC_API_KEY environment variable is not set. Please set it to use You.com tools."
+            
+            from youdotcom import You
+            self._client = You(api_key_auth=api_key)
+        return self._client, None
+    
+    def search(
+        self,
+        query: str,
+        count: int = 10,
+        freshness: Optional[str] = None,
+        country: Optional[str] = None,
+        language: Optional[str] = None,
+        offset: int = 0,
+        safesearch: str = "moderate",
+        livecrawl: Optional[str] = None,
+        livecrawl_formats: Optional[str] = None,
+    ) -> Dict[str, Any]:
+        """Search the web using You.com's unified search API.
+        
+        Returns both web and news results in a single call with LLM-ready snippets.
+        
+        Args:
+            query: Search query (supports operators like site:, filetype:, +term, -term)
+            count: Max results per section (default 10, max 100)
+            freshness: Filter by recency - "day", "week", "month", "year" or "YYYY-MM-DDtoYYYY-MM-DD"
+            country: ISO country code (e.g., "US", "GB", "FR")
+            language: BCP 47 language code (e.g., "EN", "JP", "DE")
+            offset: Pagination offset (0-9), results = offset * count
+            safesearch: Content filter - "off", "moderate", "strict"
+            livecrawl: Fetch full content - "web", "news", or "all"
+            livecrawl_formats: Content format - "html" or "markdown"
+            
+        Returns:
+            Dict containing:
+            - results: {web: [...], news: [...]}
+            - metadata: {query, search_uuid, latency}
+            
+        Search Operators:
+            - site:domain.com - Search within specific domain
+            - filetype:pdf - Filter by file type
+            - +term - Must include term
+            - -term - Exclude term
+            - AND, OR, NOT - Boolean operators
+        """
+        client, error = self._get_client()
+        if error:
+            logging.error(error)
+            return {"error": error}
+        
+        try:
+            kwargs = {"query": query, "count": count, "offset": offset}
+            
+            if freshness:
+                kwargs["freshness"] = freshness
+            if country:
+                kwargs["country"] = country
+            if language:
+                kwargs["language"] = language
+            if safesearch:
+                kwargs["safesearch"] = safesearch
+            if livecrawl:
+                kwargs["livecrawl"] = livecrawl
+            if livecrawl_formats:
+                kwargs["livecrawl_formats"] = livecrawl_formats
+            
+            response = client.search.unified(**kwargs)
+            
+            # Convert response to dict if it's a model object
+            if hasattr(response, 'model_dump'):
+                return response.model_dump()
+            elif hasattr(response, 'to_dict'):
+                return response.to_dict()
+            elif hasattr(response, '__dict__'):
+                return self._convert_response(response)
+            return response
+            
+        except Exception as e:
+            error_msg = f"You.com search error: {str(e)}"
+            logging.error(error_msg)
+            return {"error": error_msg}
+    
+    def _convert_response(self, response) -> Dict[str, Any]:
+        """Convert SDK response object to dictionary."""
+        result = {}
+        
+        if hasattr(response, 'results'):
+            results = response.results
+            result['results'] = {}
+            if hasattr(results, 'web') and results.web:
+                result['results']['web'] = [
+                    {
+                        'url': getattr(r, 'url', ''),
+                        'title': getattr(r, 'title', ''),
+                        'description': getattr(r, 'description', ''),
+                        'snippets': getattr(r, 'snippets', []),
+                        'thumbnail_url': getattr(r, 'thumbnail_url', None),
+                        'page_age': getattr(r, 'page_age', None),
+                        'favicon_url': getattr(r, 'favicon_url', None),
+                        'authors': getattr(r, 'authors', []),
+                    }
+                    for r in results.web
+                ]
+            if hasattr(results, 'news') and results.news:
+                result['results']['news'] = [
+                    {
+                        'url': getattr(r, 'url', ''),
+                        'title': getattr(r, 'title', ''),
+                        'description': getattr(r, 'description', ''),
+                        'thumbnail_url': getattr(r, 'thumbnail_url', None),
+                        'page_age': getattr(r, 'page_age', None),
+                    }
+                    for r in results.news
+                ]
+        
+        if hasattr(response, 'metadata'):
+            meta = response.metadata
+            result['metadata'] = {
+                'query': getattr(meta, 'query', ''),
+                'search_uuid': getattr(meta, 'search_uuid', ''),
+                'latency': getattr(meta, 'latency', 0),
+            }
+        
+        return result
+    
+    def get_contents(
+        self,
+        urls: Union[str, List[str]],
+        format: str = "markdown",
+    ) -> Dict[str, Any]:
+        """Fetch content from URLs using You.com's content extraction API.
+        
+        Args:
+            urls: Single URL or list of URLs to fetch content from
+            format: Content format - "html" or "markdown" (default: markdown)
+            
+        Returns:
+            Dict containing array of results with:
+            - url: The fetched URL
+            - title: Page title
+            - html: HTML content (if format="html")
+            - markdown: Markdown content (if format="markdown")
+            - metadata: {site_name, favicon_url}
+        """
+        client, error = self._get_client()
+        if error:
+            logging.error(error)
+            return {"error": error}
+        
+        try:
+            if isinstance(urls, str):
+                urls = [urls]
+            
+            # Use the contents endpoint
+            response = client.search.contents(urls=urls, format=format)
+            
+            # Convert response
+            if hasattr(response, 'model_dump'):
+                return {"results": response.model_dump()}
+            elif isinstance(response, list):
+                return {"results": [
+                    {
+                        'url': getattr(r, 'url', ''),
+                        'title': getattr(r, 'title', ''),
+                        'html': getattr(r, 'html', None),
+                        'markdown': getattr(r, 'markdown', None),
+                        'metadata': {
+                            'site_name': getattr(getattr(r, 'metadata', None), 'site_name', None) if hasattr(r, 'metadata') else None,
+                            'favicon_url': getattr(getattr(r, 'metadata', None), 'favicon_url', None) if hasattr(r, 'metadata') else None,
+                        }
+                    }
+                    for r in response
+                ]}
+            return {"results": response}
+            
+        except Exception as e:
+            error_msg = f"You.com contents error: {str(e)}"
+            logging.error(error_msg)
+            return {"error": error_msg}
+    
+    def live_news(
+        self,
+        query: str,
+        count: Optional[int] = None,
+    ) -> Dict[str, Any]:
+        """Search for live news using You.com's news API.
+        
+        Note: This API may require early access. Contact [email protected] for access.
+        
+        Args:
+            query: News search query
+            count: Maximum number of news results to return
+            
+        Returns:
+            Dict containing:
+            - news: {query, results: [...], metadata}
+            - Each result has: title, description, url, page_age, source_name, thumbnail
+        """
+        client, error = self._get_client()
+        if error:
+            logging.error(error)
+            return {"error": error}
+        
+        try:
+            kwargs = {"q": query}
+            if count:
+                kwargs["count"] = count
+            
+            # Try to access live news endpoint
+            if hasattr(client, 'livenews'):
+                response = client.livenews.get(**kwargs)
+            else:
+                # Fallback: use unified search with news focus
+                return self.search(query=query, count=count or 10)
+            
+            if hasattr(response, 'model_dump'):
+                return response.model_dump()
+            elif hasattr(response, 'news'):
+                news = response.news
+                return {
+                    'news': {
+                        'query': getattr(getattr(news, 'query', None), 'original', query) if hasattr(news, 'query') else query,
+                        'results': [
+                            {
+                                'title': getattr(r, 'title', ''),
+                                'description': getattr(r, 'description', ''),
+                                'url': getattr(r, 'url', ''),
+                                'page_age': getattr(r, 'page_age', None),
+                                'age': getattr(r, 'age', None),
+                                'source_name': getattr(r, 'source_name', None),
+                                'thumbnail': getattr(getattr(r, 'thumbnail', None), 'src', None) if hasattr(r, 'thumbnail') else None,
+                            }
+                            for r in getattr(news, 'results', [])
+                        ],
+                        'metadata': {
+                            'request_uuid': getattr(getattr(news, 'metadata', None), 'request_uuid', None) if hasattr(news, 'metadata') else None,
+                        }
+                    }
+                }
+            return response
+            
+        except Exception as e:
+            error_msg = f"You.com live news error: {str(e)}"
+            logging.error(error_msg)
+            return {"error": error_msg}
+    
+    def images(
+        self,
+        query: str,
+    ) -> Dict[str, Any]:
+        """Search for images using You.com's image search API.
+        
+        Note: This API may require early access. Contact [email protected] for access.
+        
+        Args:
+            query: Image search query
+            
+        Returns:
+            Dict containing:
+            - images: {results: [...]}
+            - metadata: {query, search_uuid}
+            - Each result has: title, page_url, image_url
+        """
+        client, error = self._get_client()
+        if error:
+            logging.error(error)
+            return {"error": error}
+        
+        try:
+            if hasattr(client, 'images'):
+                response = client.images.get(q=query)
+            else:
+                return {"error": "Image search not available in this SDK version"}
+            
+            if hasattr(response, 'model_dump'):
+                return response.model_dump()
+            elif hasattr(response, 'images'):
+                images = response.images
+                return {
+                    'images': {
+                        'results': [
+                            {
+                                'title': getattr(r, 'title', ''),
+                                'page_url': getattr(r, 'page_url', ''),
+                                'image_url': getattr(r, 'image_url', ''),
+                            }
+                            for r in getattr(images, 'results', [])
+                        ]
+                    },
+                    'metadata': {
+                        'query': getattr(getattr(response, 'metadata', None), 'query', query) if hasattr(response, 'metadata') else query,
+                        'search_uuid': getattr(getattr(response, 'metadata', None), 'search_uuid', None) if hasattr(response, 'metadata') else None,
+                    }
+                }
+            return response
+            
+        except Exception as e:
+            error_msg = f"You.com images error: {str(e)}"
+            logging.error(error_msg)
+            return {"error": error_msg}
+    
+    def __enter__(self):
+        """Context manager entry."""
+        return self
+    
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        """Context manager exit."""
+        if self._client is not None:
+            # Close client if it has a close method
+            if hasattr(self._client, 'close'):
+                self._client.close()
+            elif hasattr(self._client, '__exit__'):
+                self._client.__exit__(exc_type, exc_val, exc_tb)
+        return False
+
+
+# Standalone functions for direct import
+def ydc_search(
+    query: str,
+    count: int = 10,
+    freshness: Optional[str] = None,
+    country: Optional[str] = None,
+    language: Optional[str] = None,
+    offset: int = 0,
+    safesearch: str = "moderate",
+    livecrawl: Optional[str] = None,
+    livecrawl_formats: Optional[str] = None,
+) -> Dict[str, Any]:
+    """Search the web using You.com's unified search API.
+    
+    This is a convenience function that creates a YouTools instance.
+    For repeated calls, consider using YouTools class directly.
+    
+    Args:
+        query: Search query (supports operators like site:, filetype:, +term, -term)
+        count: Max results per section (default 10, max 100)
+        freshness: Filter by recency - "day", "week", "month", "year"
+        country: ISO country code (e.g., "US", "GB")
+        language: BCP 47 language code (e.g., "EN", "JP")
+        offset: Pagination offset (0-9)
+        safesearch: Content filter - "off", "moderate", "strict"
+        livecrawl: Fetch full content - "web", "news", or "all"
+        livecrawl_formats: Content format - "html" or "markdown"
+        
+    Returns:
+        Dict containing search results with web and news sections
+    """
+    tools = YouTools()
+    return tools.search(
+        query=query,
+        count=count,
+        freshness=freshness,
+        country=country,
+        language=language,
+        offset=offset,
+        safesearch=safesearch,
+        livecrawl=livecrawl,
+        livecrawl_formats=livecrawl_formats,
+    )
+
+
+def ydc_contents(
+    urls: Union[str, List[str]],
+    format: str = "markdown",
+) -> Dict[str, Any]:
+    """Fetch content from URLs using You.com's content extraction API.
+    
+    Args:
+        urls: Single URL or list of URLs to fetch content from
+        format: Content format - "html" or "markdown"
+        
+    Returns:
+        Dict containing extracted content for each URL
+    """
+    tools = YouTools()
+    return tools.get_contents(urls=urls, format=format)
+
+
+def ydc_news(
+    query: str,
+    count: Optional[int] = None,
+) -> Dict[str, Any]:
+    """Search for live news using You.com's news API.
+    
+    Args:
+        query: News search query
+        count: Maximum number of results
+        
+    Returns:
+        Dict containing news results
+    """
+    tools = YouTools()
+    return tools.live_news(query=query, count=count)
+
+
+def ydc_images(
+    query: str,
+) -> Dict[str, Any]:
+    """Search for images using You.com's image search API.
+    
+    Args:
+        query: Image search query
+        
+    Returns:
+        Dict containing image results
+    """
+    tools = YouTools()
+    return tools.images(query=query)
+
+
+# Alias for simple usage
+ydc = ydc_search
+
+__all__ = ["YouTools", "ydc_search", "ydc_contents", "ydc_news", "ydc_images", "ydc"]

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "praisonai-tools"
-version = "0.2.45"
+version = "0.2.46"
 description = "Extended tools for PraisonAI Agents"
 authors = [
     {name = "Mervin Praison"}

tests/unit/tools/test_youdotcom_tool.py

@@ -0,0 +1,81 @@
+"""Unit tests for You.com tools (no network, no API key required)."""
+
+from unittest.mock import MagicMock, patch
+
+from praisonai_tools.tools.youdotcom_tool import (
+    YouTools,
+    ydc,
+    ydc_search,
+    ydc_contents,
+    ydc_news,
+    ydc_images,
+)
+
+
+_FIND_SPEC = "praisonai_tools.tools.youdotcom_tool.util.find_spec"
+
+
+def test_missing_api_key_returns_error(monkeypatch):
+    monkeypatch.delenv("YDC_API_KEY", raising=False)
+    with patch(_FIND_SPEC, return_value=object()):
+        for fn, arg in (
+            (ydc_search, "q"),
+            (ydc_contents, "https://example.com"),
+            (ydc_news, "q"),
+            (ydc_images, "q"),
+        ):
+            result = fn(arg)
+            assert result == {
+                "error": "YDC_API_KEY environment variable is not set. Please set it to use You.com tools."
+            }
+
+
+def test_explicit_api_key_used_without_env(monkeypatch):
+    monkeypatch.delenv("YDC_API_KEY", raising=False)
+    fake_module = MagicMock()
+    with patch(_FIND_SPEC, return_value=object()), patch.dict(
+        "sys.modules", {"youdotcom": fake_module}
+    ):
+        client, error = YouTools(api_key="k")._get_client()
+
+    assert error is None
+    assert client is fake_module.You.return_value
+    fake_module.You.assert_called_once_with(api_key_auth="k")
+
+
+def test_ydc_alias():
+    assert ydc is ydc_search
+
+
+def test_search_uses_client_and_returns_dict():
+    response = MagicMock()
+    response.model_dump.return_value = {"results": {"web": [], "news": []}}
+    client = MagicMock()
+    client.search.unified.return_value = response
+
+    with patch.object(YouTools, "_get_client", return_value=(client, None)):
+        result = YouTools().search("ai", count=3, freshness="week")
+
+    assert result == {"results": {"web": [], "news": []}}
+    kwargs = client.search.unified.call_args.kwargs
+    assert kwargs["query"] == "ai"
+    assert kwargs["count"] == 3
+    assert kwargs["freshness"] == "week"
+
+
+def test_search_exception_is_reported_as_error():
+    client = MagicMock()
+    client.search.unified.side_effect = RuntimeError("boom")
+
+    with patch.object(YouTools, "_get_client", return_value=(client, None)):
+        result = YouTools().search("ai")
+
+    assert "boom" in result["error"]
+
+
+def test_discovered_via_package():
+    import praisonai_tools.tools as tools_pkg
+
+    assert tools_pkg.YouTools is YouTools
+    assert tools_pkg.ydc_search is ydc_search
+    assert tools_pkg.ydc is ydc_search