janito 0.13.0__py3-none-any.whl → 0.14.0__py3-none-any.whl

{janito-0.13.0.dist-info → janito-0.14.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: janito
-Version: 0.13.0
+Version: 0.14.0
 Summary: Janito CLI tool
 Project-URL: Homepage, https://github.com/joaompinto/janito
 Author-email: João Pinto <lamego.pinto@gmail.com>
@@ -31,12 +31,13 @@ Janito is a powerful AI-assisted command-line interface (CLI) tool built with Py
 - 🔍 Smart code search and editing
 - 💻 Interactive terminal interface with rich formatting
 - 📊 Detailed token usage tracking and cost reporting with cache savings analysis
-- 🛑 Token and tool usage reporting even when interrupted with Ctrl+C
 - 🌐 Web page fetching with content extraction capabilities
 - 🔄 Parameter profiles for optimizing Claude's behavior for different tasks
 - 📋 Line delta tracking to monitor net changes in files
-- 💬 Conversation history with ability to resume previous conversations
+- 💬 Enhanced conversation history with browsing and management
 - 🔇 Trust mode for concise output without tool details
+- 🚫 No-tools mode for pure AI interactions without file system access
+- 📝 Custom system instructions for specialized assistant behavior
 
 ## 🛠️ System Requirements
 
@@ -115,19 +116,35 @@ janito --trust "Optimize the HTML code"
 # Or use the short alias
 janito -t "Optimize the HTML code"
 
+# Disable all tools for pure AI interaction
+janito --no-tools "Explain how HTML works"
+
+# View your conversation history
+janito --history
+
+# View a specific number of recent conversations
+janito --history 10
+
 # Continue the most recent conversation
 janito --continue "Please add one more line"
 
 # Continue a specific conversation using its message ID
 # (Janito displays the message ID after each conversation)
-janito --continue abc123def "Let's refine that code"
+janito --continue 'abc123def' 'Let's refine that code'
+
+# Alternative way to continue a specific conversation
+janito --continue-id abc123def "Let's refine that code"
+
+# Provide custom system instructions
+janito --system "You are a poetry expert who speaks in rhymes" "Write about coding"
+# Or use the short alias
+janito -s "You are a poetry expert who speaks in rhymes" "Write about coding"
 
 # Show current configuration and available profiles
 janito --show-config
 
 # You can press Ctrl+C at any time to interrupt a query
-# Janito will still display token and tool usage information
-# Even interrupted conversations can be continued with --continue
+# Interrupted conversations can be continued with --continue
 ```
 
 ## 🔧 Available Tools
@@ -213,9 +230,58 @@ This feature is particularly useful for:
 - Focusing on results rather than the process
 - Creating cleaner output for documentation or sharing
 
+## 🚫 No-Tools Mode
+
+Janito provides a no-tools mode that disables all file system and external tools for pure AI interactions:
+
+### How It Works
+
+- When enabled with `--no-tools`, Janito disables all tools for the current session
+- Claude will respond based purely on its knowledge without accessing or modifying files
+- This mode is a per-session setting and not saved to your configuration
+
+### Using No-Tools Mode
+
+```bash
+# Enable no-tools mode
+janito --no-tools "Explain how Docker containers work"
+```
+
+This feature is particularly useful for:
+- Getting general information or explanations without file system access
+- Brainstorming sessions where you don't need file operations
+- Safer operation in sensitive environments
+- Faster responses for queries that don't require tools
+
+## 📝 Custom System Instructions
+
+Janito allows you to provide custom system instructions to change Claude's behavior:
+
+### How It Works
+
+- When provided with `--system` or `-s`, Janito uses your custom instructions instead of the default
+- This allows you to create specialized assistant personalities or behaviors
+- Custom instructions are a per-session setting and not saved to your configuration
+
+### Using Custom System Instructions
+
+```bash
+# Provide custom system instructions
+janito --system "You are a poetry expert who speaks in rhymes" "Write about coding"
+
+# Or use the short alias
+janito -s "You are a cybersecurity expert" "Review this authentication code"
+```
+
+This feature is particularly useful for:
+- Creating specialized assistant personalities
+- Focusing Claude on specific domains or expertise
+- Setting up specific response formats or styles
+- Educational scenarios where you need different expert perspectives
+
 ## 💬 Conversation History
 
-Janito automatically saves your conversation history, allowing you to continue previous discussions:
+Janito automatically saves your conversation history, allowing you to browse, manage, and continue previous discussions:
 
 ### How It Works
 
@@ -223,6 +289,23 @@ Janito automatically saves your conversation history, allowing you to continue p
 - The most recent conversation is also saved as `.janito/last_message.json` for backward compatibility
 - After each conversation, Janito displays the command to continue that specific conversation
 
+### Browsing Your History
+
+You can view your conversation history with the `--history` flag:
+
+```bash
+# Show the 20 most recent conversations (default)
+janito --history
+
+# Show a specific number of recent conversations
+janito --history 10
+```
+
+This displays a table with:
+- Conversation ID
+- Date and time
+- First query from each conversation
+
 ### Using the Continue Feature
 
 ```bash
@@ -231,6 +314,13 @@ janito --continue "Add more details to your previous response"
 
 # Continue a specific conversation using its ID
 janito --continue abc123def "Let's modify that code you suggested"
+
+# Just use --continue without arguments to continue the most recent conversation
+# and be prompted for your next query
+janito --continue
+
+# Alternative way to continue a specific conversation
+janito --continue-id abc123def "Let's modify that code you suggested"
 ```
 
 The `--continue` flag (or `-c` for short) allows you to:
@@ -266,11 +356,17 @@ Janito offers a variety of command-line options to customize its behavior:
 --set-api-key TEXT            Set the Anthropic API key globally in the user's home directory
 --ask                         Enable ask mode which disables tools that perform changes
 --trust, -t                   Enable trust mode which suppresses tool outputs for concise execution
+--no-tools                    Disable all tools for this session (pure AI interaction)
 --temperature FLOAT           Set the temperature for model generation (0.0 to 1.0)
 --profile TEXT                Use a predefined parameter profile (precise, balanced, conversational, creative, technical)
 --role TEXT                   Set the assistant's role (default: 'software engineer')
+--system, -s TEXT             Provide custom system instructions, bypassing the default file load method
 --version                     Show the version and exit
---continue, -c TEXT           Continue a previous conversation, optionally with a specific message ID
+--continue, -c TEXT           Continue a conversation. Can be used as: 1) --continue (to continue most recent), 
+                              2) --continue 123 (to continue conversation with ID 123), or 
+                              3) --continue "query" (to continue most recent with new query)
+--continue-id TEXT            Continue a specific conversation with the given ID
+--history                     Show a summary of conversations. Use --history for default (20) or --history n to specify count
 --help                        Show the help message and exit
 ```
 

{janito-0.13.0.dist-info → janito-0.14.0.dist-info}/RECORD

@@ -1,17 +1,26 @@
-janito/__init__.py,sha256=5Cnu7sPJURDSY1cnxtGvzs0MpwHUsh5zYZRNQ2LkM8k,53
+janito/__init__.py,sha256=7oWOSdYGAlxA75CpzMThFPrXL2oWwJw60hTnRBxIo1A,53
 janito/__main__.py,sha256=Oy-Nc1tZkpyvTKuq1R8oHSuJTkvptN6H93kIHBu7DKY,107
 janito/callbacks.py,sha256=E1FPXYHZUgiEGMabYuf999PSf_Su4ByHOWlc1-hMqWE,915
-janito/config.py,sha256=MHfloii_OnOVcV4pbunfdnAv8uJzxu_ytDK34Rj8yZ8,13221
-janito/test_file.py,sha256=c6GWGdTYG3z-Y5XBao9Tmhmq3G-v0L37OfwLgBo8zIU,126
+janito/config.py,sha256=XZYVjHPTv41l0NyGHaeq3UKB5FyRNHSEuLui-_mv5BU,13821
 janito/token_report.py,sha256=Mks7o2yTxPChgQyBJNoQ5eMmrhSgEM4LKCKi2tHJbVo,9580
 janito/cli/__init__.py,sha256=dVi9l3E86YyukjxQ-XSUnMZkghnNasXex-X5XAOBiwk,85
-janito/cli/agent.py,sha256=iFwzbZupkpXQVO0YrQmCGKKQGcqCRdAY3JLg6tZaJiQ,15940
-janito/cli/app.py,sha256=czgOEWCsWlKeLWMHxPv6fxOStoL2wcC8_QZs6mMtTp8,4643
-janito/cli/commands.py,sha256=pgassnKENr0DGcZT3tFXtz8MCVuEZwHgxiBktgAik6g,12682
+janito/cli/agent.py,sha256=gIkbQZHNcg8hH52ziqklhKY6EDSyl6URUbtRvQQHqyI,414
+janito/cli/app.py,sha256=QkH14BhnFQ2RgavLwxMKa9m_7C8KGoSuSjRNS3iYR1o,9477
+janito/cli/commands.py,sha256=M0DKCFZMS1mXA-s9Lm_4Ug7LJFlNg12fBdcDOhCnIWg,380
 janito/cli/output.py,sha256=mo3hUokhrD4SWexUjCbLGGQeCDUf0369DA_i9BW7HjU,933
 janito/cli/utils.py,sha256=gO4NtCNwtEzYDsQesrFlqB5FtYuw87yGwo4iG3nINgw,661
-janito/data/instructions_template.txt,sha256=FlyGpNjl2LRBjPWLTK40oKOSH6sveHp5ud35nf_lfs8,1716
-janito/tools/__init__.py,sha256=hio75FRkxLSQB13We-SCCM7Qa9lMqWCfWhEonHlTr8M,1405
+janito/cli/agent/__init__.py,sha256=3O3b_MnwX_-qApYlyXzXhdjT4-dHzfxpOAy1lK_ZAIE,250
+janito/cli/agent/conversation.py,sha256=iif8ciIbsb_HZaZ6qvK40s0PyW3QmriZ1Q7PtUqKfI4,5644
+janito/cli/agent/initialization.py,sha256=-7APIAk0gawVVrxd1AdeBwffEuudvy1bIhDE6LMXfw4,6583
+janito/cli/agent/query.py,sha256=Sly1k-cVOydTPraUmdSPKxFYrScmCOd8BfAqFUvWwkg,4612
+janito/cli/commands/__init__.py,sha256=4zGGB0x-TeBetSArBV38SZQo0T1K59vJofhXhLiD3g0,331
+janito/cli/commands/config.py,sha256=U1Bnc_YSMwFkX-1dcksmdgsoH2_yrO8MSYTaESxR-sQ,9819
+janito/cli/commands/history.py,sha256=WzWgPRZ7mQwlbDCPw3Hapb-K_Ybk1uKLs-qLams6sO4,5409
+janito/cli/commands/profile.py,sha256=jsGKSqXlaSLE__Xjj9OKNTW68evU0APyK9QYr_OEELQ,2397
+janito/cli/commands/validation.py,sha256=ldtfk0vAOkrto1Ys6G0MDmUOQvYalHsTd_l_0fMVHcI,718
+janito/cli/commands/workspace.py,sha256=nSCrN3SSK4zq10x38uksaOMuzx___rnl-cmyVpvNlqk,909
+janito/data/instructions_template.txt,sha256=Ewfjk_1qRO178WEcRQVONnff6CpRAeKGE8JAydD39Qw,2143
+janito/tools/__init__.py,sha256=mCtmWVFfgrk_SFWcwzw92O9Fb9P-5SYnO2rPMxkT5rM,1624
 janito/tools/decorators.py,sha256=Tp48n5y4LKsjyV3HeOA9wk2dV413RrEG-23kRyQVlKs,2522
 janito/tools/delete_file.py,sha256=UrZ5q59SIxWfuJcqgol6yPBqL-RhO9lFCF4MqAc6o00,2252
 janito/tools/find_files.py,sha256=c_N9ETcRPprQeuZYanwFnl-9E05ZqUYhNVoCRS5uqQg,8300
@@ -19,17 +28,14 @@ janito/tools/move_file.py,sha256=FCs1ghalfHlXmcbAA_IlLcUll9hTOU1MMFGrTWopXvM,274
 janito/tools/prompt_user.py,sha256=OnTiWVBCbL_2MYu7oThlKr8X_pnYdG-dzxXSOgJF41c,1942
 janito/tools/replace_file.py,sha256=i4GoLtS14eKSU5lYI18mJ96S0_ekeHMwlQfazg-fxrM,2296
 janito/tools/rich_console.py,sha256=0zWYRF8qk4N-upuwswUSEfYFAfkEYDYeCgxst-czWtY,6044
-janito/tools/search_text.py,sha256=RxbnNeZ3ErCvevwbl60fQAe55QYtU-D9n13iixeDcqQ,9822
-janito/tools/usage_tracker.py,sha256=IE7GVBDYsX2EDLjsVaVqTeAnT2SAYfcOJvBaH__wHdU,4613
+janito/tools/search_text.py,sha256=GXc8fuqKD6r0dEr2lMs5LrYYMM5RtTApvMXlvdt2ZiY,8839
+janito/tools/think.py,sha256=VsfYzYSfdBz6ayUYE8aoeAsdeN2PFpHjwUkxtaw1YYQ,1204
+janito/tools/usage_tracker.py,sha256=3qHXIs9rzm0oY2iaaFHqlLre6ZoWicZgOc46s6XyGc0,4681
 janito/tools/bash/bash.py,sha256=AFm0w_z-yyYRWxuR744OFpm5iCZaZpE-pWbnKbgajp4,3665
 janito/tools/bash/unix_persistent_bash.py,sha256=I59PPQiXHscPJ6Y7ev_83dLFNFWq1hKwAK9kFXdnbBY,7185
 janito/tools/bash/win_persistent_bash.py,sha256=96xm_yijjc6hBYfNluLahbvR2oUuHug_JkoMah7Hy38,12894
-janito/tools/fetch_webpage/__init__.py,sha256=0RG0ev-yrfo8gPzt-36WMpVdY2qtMhk2Z-mVpq-7m1o,1076
-janito/tools/fetch_webpage/chunking.py,sha256=mMtrZeirZ_GnKOOzeG8BijLVpSUI0-TA5Ioqi2HKb1A,2971
-janito/tools/fetch_webpage/core.py,sha256=3XDvYnC_UbQUNumwWw32hfJhjJUEaPzzoF2yhxhwxos,7764
-janito/tools/fetch_webpage/extractors.py,sha256=-jrLDRWfWyF2SNOATdRWrqETqnnDLbe2JUWtuyHKFOU,12043
-janito/tools/fetch_webpage/news.py,sha256=Hp0uNTnRzTa-4hyegQbHSmLeSbkiSpx4cP2oP_hKLEQ,5378
-janito/tools/fetch_webpage/utils.py,sha256=mkfwefD7U9HOktIwo1eP63v7dpVY-q06COUjaqnTT5M,3412
+janito/tools/fetch_webpage/__init__.py,sha256=Rnzni75VX1JfmGJ2LHckGWQqr7xC95wahh5Q-1PlncQ,514
+janito/tools/fetch_webpage/core.py,sha256=3Q8dAlWYMU_Mg8DyrNCBaLuriAxItSYIyGAcPZFktcI,7555
 janito/tools/str_replace_editor/__init__.py,sha256=kYmscmQgft3Jzt3oCNz7k2FiRbJvku6OFDDC3Q_zoAA,144
 janito/tools/str_replace_editor/editor.py,sha256=BckYfiMRUYDfDrbu871qMt2AfZexth_02QhwYYOd53g,2489
 janito/tools/str_replace_editor/utils.py,sha256=akiPqCHjky_RwL9OitHJJ7uQ-3fNaA8wt_K_YO1EP6I,954
@@ -39,9 +45,9 @@ janito/tools/str_replace_editor/handlers/insert.py,sha256=eKHodm2ozKUlRMxWMLAsu9
 janito/tools/str_replace_editor/handlers/str_replace.py,sha256=RciLTlA7R2PGljeeyluLcBHUAje9c1OCxm-bFE7j6iY,4473
 janito/tools/str_replace_editor/handlers/undo.py,sha256=3OIdAWkpXC2iDe94_sfx_WxEFh3a1cRzoP0NtPXq1Ks,2491
 janito/tools/str_replace_editor/handlers/view.py,sha256=k8F-n64bomHmDjavr5OJKC4cHhfm4_1-aMIFZdMICQo,6809
-janito/data/instructions_template.txt,sha256=FlyGpNjl2LRBjPWLTK40oKOSH6sveHp5ud35nf_lfs8,1716
-janito-0.13.0.dist-info/METADATA,sha256=06Vh36jWdwTcsUOpIyRkHybxssdksSoWNvPVE41y1jM,10584
-janito-0.13.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-janito-0.13.0.dist-info/entry_points.txt,sha256=JMbF_1jg-xQddidpAYkzjOKdw70fy_ymJfcmerY2wIY,47
-janito-0.13.0.dist-info/licenses/LICENSE,sha256=6-H8LXExbBIAuT4cyiE-Qy8Bad1K4pagQRVTWr6wkhk,1096
-janito-0.13.0.dist-info/RECORD,,
+janito/data/instructions_template.txt,sha256=Ewfjk_1qRO178WEcRQVONnff6CpRAeKGE8JAydD39Qw,2143
+janito-0.14.0.dist-info/METADATA,sha256=VzEC8lrwVeAhFxZDGripkjFcCm8CoHAjJFAh_OchFo0,14074
+janito-0.14.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+janito-0.14.0.dist-info/entry_points.txt,sha256=JMbF_1jg-xQddidpAYkzjOKdw70fy_ymJfcmerY2wIY,47
+janito-0.14.0.dist-info/licenses/LICENSE,sha256=6-H8LXExbBIAuT4cyiE-Qy8Bad1K4pagQRVTWr6wkhk,1096
+janito-0.14.0.dist-info/RECORD,,

janito/test_file.py

@@ -1,4 +0,0 @@
-def add(a, b):
-    return a - b  # This has a bug, it should be a + b
-
-print(add(5, 3))  # Should print 8, but will print 2

janito/tools/fetch_webpage/chunking.py

@@ -1,76 +0,0 @@
-"""
-Functions for chunking large content into manageable pieces.
-"""
-
-from typing import List
-from janito.tools.rich_console import print_info, print_success
-
-
-def chunk_large_content(text: str, chunk_size: int = 4000, overlap: int = 500) -> List[str]:
-    """
-    Split very large text content into manageable chunks suitable for LLM processing.
-    
-    Args:
-        text: The text to chunk
-        chunk_size: Target size for each chunk in characters
-        overlap: Number of characters to overlap between chunks
-        
-    Returns:
-        List of text chunks
-    """
-    if not text or len(text) <= chunk_size:
-        return [text] if text else []
-    
-    print_info(f"Chunking {len(text)} characters of text into ~{chunk_size} character chunks", "Content Chunking")
-    
-    # Try to split on paragraph breaks first
-    paragraphs = text.split('\n\n')
-    chunks = []
-    current_chunk = ""
-    
-    for para in paragraphs:
-        # If adding this paragraph would exceed chunk size
-        if len(current_chunk) + len(para) + 2 > chunk_size:
-            # If current chunk is not empty, add it to chunks
-            if current_chunk:
-                chunks.append(current_chunk)
-                # Start new chunk with overlap from previous chunk
-                if overlap > 0 and len(current_chunk) > overlap:
-                    current_chunk = current_chunk[-overlap:] + "\n\n" + para
-                else:
-                    current_chunk = para
-            else:
-                # If paragraph itself is bigger than chunk size, split it
-                if len(para) > chunk_size:
-                    words = para.split()
-                    temp_chunk = ""
-                    for word in words:
-                        if len(temp_chunk) + len(word) + 1 > chunk_size:
-                            chunks.append(temp_chunk)
-                            # Start new chunk with overlap
-                            if overlap > 0 and len(temp_chunk) > overlap:
-                                temp_chunk = temp_chunk[-overlap:] + " " + word
-                            else:
-                                temp_chunk = word
-                        else:
-                            if temp_chunk:
-                                temp_chunk += " " + word
-                            else:
-                                temp_chunk = word
-                    if temp_chunk:
-                        current_chunk = temp_chunk
-                else:
-                    chunks.append(para)
-        else:
-            # Add paragraph to current chunk
-            if current_chunk:
-                current_chunk += "\n\n" + para
-            else:
-                current_chunk = para
-    
-    # Don't forget the last chunk
-    if current_chunk:
-        chunks.append(current_chunk)
-    
-    print_success(f"Text chunked into {len(chunks)} segments", "Content Chunking")
-    return chunks

janito/tools/fetch_webpage/extractors.py

@@ -1,276 +0,0 @@
-"""
-Content extraction methods for web pages.
-"""
-
-from typing import List, Dict, Union, Optional
-from bs4 import BeautifulSoup
-import trafilatura
-from newspaper import Article
-import re
-
-from janito.tools.rich_console import print_info, print_success, print_warning
-from janito.tools.fetch_webpage.utils import clean_text, similar_text
-
-
-def extract_clean_text(html_content: str, method: str = 'trafilatura', 
-                       url: Optional[str] = None, target_strings: List[str] = None) -> str:
-    """
-    Extract clean, relevant text from HTML content using various methods.
-    
-    Args:
-        html_content: The HTML content to extract text from
-        method: The extraction method to use ('trafilatura', 'newspaper', 'beautifulsoup', 'all')
-        url: Optional URL for methods that require it (like newspaper)
-        target_strings: Optional list of strings to target specific content sections
-        
-    Returns:
-        Extracted text content
-    """
-    print_info(f"Extracting content using method: {method}", "Content Extraction")
-    
-    extracted_text = ""
-    
-    if method == 'trafilatura' or method == 'all':
-        try:
-            traf_text = trafilatura.extract(html_content, include_links=False, 
-                                           include_tables=False, include_images=False,
-                                           favor_precision=True)
-            if traf_text and len(traf_text) > 100:
-                if method == 'trafilatura':
-                    print_success("Successfully extracted content with Trafilatura", "Content Extraction")
-                    return clean_text(traf_text)
-                extracted_text = traf_text
-                print_success("Successfully extracted content with Trafilatura", "Content Extraction")
-        except Exception as e:
-            print_warning(f"Content Extraction: Trafilatura extraction error: {str(e)}")
-    
-    if method == 'newspaper' or method == 'all':
-        if not url:
-            print_warning("Content Extraction: URL required for newspaper extraction but not provided")
-        else:
-            try:
-                article = Article(url)
-                article.download(html_content)
-                article.parse()
-                np_text = article.text
-                if np_text and len(np_text) > 100:
-                    if method == 'newspaper':
-                        print_success("Successfully extracted content with Newspaper3k", "Content Extraction")
-                        return clean_text(np_text)
-                    if not extracted_text or len(np_text) > len(extracted_text):
-                        extracted_text = np_text
-                        print_success("Successfully extracted content with Newspaper3k", "Content Extraction")
-            except Exception as e:
-                print_warning(f"Content Extraction: Newspaper extraction error: {str(e)}")
-    
-    if method == 'beautifulsoup' or method == 'all':
-        try:
-            soup = BeautifulSoup(html_content, 'html.parser')
-            
-            # Remove script, style, and other non-content elements
-            for element in soup(['script', 'style', 'header', 'footer', 'nav', 'aside']):
-                element.decompose()
-            
-            # Extract text from paragraph and heading tags
-            paragraphs = []
-            for tag in soup.find_all(['p', 'h1', 'h2', 'h3', 'h4', 'article']):
-                text = tag.get_text(strip=True)
-                if text and len(text) > 20:  # Skip very short pieces that might be UI elements
-                    paragraphs.append(text)
-            
-            bs_text = "\n\n".join(paragraphs)
-            if bs_text and len(bs_text) > 100:
-                if method == 'beautifulsoup':
-                    print_success("Successfully extracted content with BeautifulSoup", "Content Extraction")
-                    return clean_text(bs_text)
-                if not extracted_text or len(bs_text) > len(extracted_text):
-                    extracted_text = bs_text
-                    print_success("Successfully extracted content with BeautifulSoup", "Content Extraction")
-        except Exception as e:
-            print_warning(f"Content Extraction: BeautifulSoup extraction error: {str(e)}")
-    
-    if not extracted_text:
-        print_warning("Content Extraction: Could not extract meaningful content with any method")
-        # Fall back to the raw text with HTML tags removed
-        extracted_text = BeautifulSoup(html_content, 'html.parser').get_text(separator='\n')
-    
-    return clean_text(extracted_text)
-
-
-def extract_targeted_content(html_content: str, target_strings: List[str], 
-                          context_size: int = 500) -> str:
-    """
-    Extract content sections that contain specific target strings.
-    
-    Args:
-        html_content: The HTML content to search within
-        target_strings: List of strings to search for in the content
-        context_size: Number of characters to include before and after each match
-        
-    Returns:
-        Extracted content focusing on sections containing target strings
-    """
-    if not target_strings:
-        return ""
-    
-    print_info(f"Extracting content targeted around {len(target_strings)} search strings", "Targeted Extraction")
-    
-    # First clean the HTML to make text extraction easier
-    soup = BeautifulSoup(html_content, 'html.parser')
-    
-    # Remove script, style, and other non-content elements
-    for element in soup(['script', 'style', 'header', 'footer', 'nav']):
-        element.decompose()
-    
-    # Get the full text content
-    full_text = soup.get_text(' ', strip=True)
-    full_text = re.sub(r'\s+', ' ', full_text)  # Normalize whitespace
-    
-    matched_sections = []
-    for target in target_strings:
-        if not target or len(target) < 3:
-            continue
-            
-        # Try exact match first
-        if target in full_text:
-            indices = [m.start() for m in re.finditer(re.escape(target), full_text)]
-            for idx in indices:
-                start = max(0, idx - context_size)
-                end = min(len(full_text), idx + len(target) + context_size)
-                section = full_text[start:end]
-                # Add ellipsis if we're showing a fragment
-                if start > 0:
-                    section = "..." + section
-                if end < len(full_text):
-                    section = section + "..."
-                matched_sections.append(section)
-        else:
-            # Try fuzzy search if no exact match (looking for words in the target string)
-            words = [w for w in target.lower().split() if len(w) > 3]
-            if words:
-                for word in words:
-                    pattern = r'\b' + re.escape(word) + r'\b'
-                    matches = list(re.finditer(pattern, full_text.lower()))
-                    for match in matches[:3]:  # Limit to first 3 matches per word
-                        idx = match.start()
-                        start = max(0, idx - context_size)
-                        end = min(len(full_text), idx + len(word) + context_size)
-                        section = full_text[start:end]
-                        if start > 0:
-                            section = "..." + section
-                        if end < len(full_text):
-                            section = section + "..."
-                        matched_sections.append(section)
-    
-    # Deduplicate similar sections
-    unique_sections = []
-    for section in matched_sections:
-        if not any(similar_text(section, existing, threshold=0.7) for existing in unique_sections):
-            unique_sections.append(section)
-    
-    if not unique_sections:
-        print_warning("Targeted Extraction: No content sections found matching the target strings")
-        return ""
-    
-    # Join the sections with paragraph breaks
-    result = "\n\n".join(unique_sections)
-    print_success(f"Found {len(unique_sections)} relevant content sections", "Targeted Extraction")
-    
-    return clean_text(result)
-
-
-def extract_structured_content(html_content: str, url: str = None, 
-                              target_strings: List[str] = None) -> Dict[str, Union[str, List[str]]]:
-    """
-    Extract structured content from a webpage, including title, main text, and key points.
-    
-    Args:
-        html_content: The HTML content to extract from
-        url: Optional URL for methods that require it
-        target_strings: Optional list of strings to target specific content sections
-        
-    Returns:
-        Dictionary with structured content elements
-    """
-    soup = BeautifulSoup(html_content, 'html.parser')
-    
-    # Extract title
-    title = ""
-    if soup.title:
-        title = soup.title.text.strip()
-    
-    # Try to get more specific title from h1 if title looks generic
-    if not title or len(title) < 10:
-        h1_tags = soup.find_all('h1')
-        if h1_tags and len(h1_tags[0].text.strip()) > 10:
-            title = h1_tags[0].text.strip()
-    
-    # Extract main content using trafilatura (our primary extractor)
-    main_text = extract_clean_text(html_content, method='trafilatura', url=url)
-    
-    # If target strings are provided, prioritize content around those strings
-    targeted_text = ""
-    if target_strings:
-        targeted_text = extract_targeted_content(html_content, target_strings)
-        if targeted_text:
-            main_text = targeted_text
-    
-    # Extract key points (using headers)
-    key_points = []
-    for header in soup.find_all(['h1', 'h2', 'h3']):
-        text = header.text.strip()
-        if text and len(text) > 5 and text not in key_points:
-            key_points.append(text)
-    
-    # For news aggregators like Google News, look for news article titles specifically
-    if url and ('news.google.com' in url or 'news.yahoo.com' in url or 'msn.com/news' in url):
-        print_info("Detected news aggregator site, searching for article titles", "Content Extraction")
-        
-        # Look for common news article title patterns
-        article_titles = []
-        
-        # Google News specific article elements
-        articles = soup.find_all('article')
-        for article in articles[:20]:  # Limit to first 20 articles
-            # Try to find the headline
-            headline = article.find(['h3', 'h4'])
-            if headline:
-                title = headline.text.strip()
-                if title and len(title) > 15 and title not in article_titles:  # Skip short titles
-                    article_titles.append(title)
-                    
-        # Add these to our key points
-        if article_titles:
-            key_points = article_titles + key_points
-            
-    # Limit key points to most important ones
-    key_points = key_points[:15]
-    
-    # Extract potential highlights (often in <strong>, <b>, <em> tags)
-    highlights = []
-    for tag in soup.find_all(['strong', 'b', 'em']):
-        text = tag.text.strip()
-        if text and len(text) > 15 and text not in highlights:
-            highlights.append(text)
-    
-    # Limit highlights to most important ones
-    highlights = highlights[:5]
-    
-    # Create a summary of the extracted content
-    summary = ""
-    if len(main_text) > 200:
-        # Extract first paragraph or two for summary
-        paragraphs = main_text.split('\n\n')
-        summary = '\n\n'.join(paragraphs[:2])
-        if len(summary) > 500:
-            summary = summary[:500] + "..."
-    
-    return {
-        "title": title,
-        "main_text": main_text,
-        "key_points": key_points,
-        "highlights": highlights,
-        "summary": summary,
-        "word_count": len(main_text.split()),
-        "targeted_extraction": bool(target_strings and targeted_text)
-    }