torbjorn/my-pal-mcp-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: cleanup and comprehensive documentation

Browse Source 
Major changes:
- Add comprehensive documentation to all modules with detailed docstrings
- Remove unused THINKING_MODEL config (use single GEMINI_MODEL with thinking_mode param)
- Remove list_models functionality (simplified to single model configuration)
- Rename DEFAULT_MODEL to GEMINI_MODEL for clarity
- Remove unused python-dotenv dependency
- Fix missing pydantic in setup.py dependencies

Documentation improvements:
- Document security measures in file_utils.py (path validation, sandboxing)
- Add detailed comments to critical logic sections
- Document tool creation process in BaseTool
- Explain configuration values and their impact
- Add comprehensive function-level documentation

Code quality:
- Apply black formatting to all files
- Fix all ruff linting issues
- Update tests to match refactored code
- All 63 tests passing

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

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Fahad
2025-06-09 19:04:24 +04:00
parent fd6e2f9b64
commit 783ba73181
12 changed files with 639 additions and 260 deletions
Download Patch File Download Diff File Expand all files Collapse all files

130
utils/file_utils.py
View File

@@ -1,5 +1,21 @@
"""
File reading utilities with directory support and token management
This module provides secure file access functionality for the MCP server.
It implements critical security measures to prevent unauthorized file access
and manages token limits to ensure efficient API usage.
Key Features:
- Path validation and sandboxing to prevent directory traversal attacks
- Support for both individual files and recursive directory reading
- Token counting and management to stay within API limits
- Automatic file type detection and filtering
- Comprehensive error handling with informative messages
Security Model:
- All file access is restricted to PROJECT_ROOT and its subdirectories
- Absolute paths are required to prevent ambiguity
- Symbolic links are resolved to ensure they stay within bounds
"""
import os
@@ -10,9 +26,12 @@ from .token_utils import estimate_tokens, MAX_CONTEXT_TOKENS
# Get project root from environment or use current directory
# This defines the sandbox directory where file access is allowed
# Security: All file operations are restricted to this directory and its children
PROJECT_ROOT = Path(os.environ.get("MCP_PROJECT_ROOT", os.getcwd())).resolve()
# Security: Prevent running with overly permissive root
# Critical Security Check: Prevent running with overly permissive root
# Setting PROJECT_ROOT to "/" would allow access to the entire filesystem,
# which is a severe security vulnerability
if str(PROJECT_ROOT) == "/":
raise RuntimeError(
"Security Error: MCP_PROJECT_ROOT cannot be set to '/'. "
@@ -20,7 +39,8 @@ if str(PROJECT_ROOT) == "/":
)
# Common code file extensions
# Common code file extensions that are automatically included when processing directories
# This set can be extended to support additional file types
CODE_EXTENSIONS = {
".py",
".js",
@@ -75,11 +95,16 @@ def resolve_and_validate_path(path_str: str) -> Path:
"""
Validates that a path is absolute and resolves it.
This is the primary security function that ensures all file access
is properly sandboxed. It enforces two critical security policies:
1. All paths must be absolute (no ambiguity)
2. All paths must resolve to within PROJECT_ROOT (sandboxing)
Args:
path_str: Path string (must be absolute)
Returns:
Resolved Path object
Resolved Path object that is guaranteed to be within PROJECT_ROOT
Raises:
ValueError: If path is not absolute
@@ -88,17 +113,19 @@ def resolve_and_validate_path(path_str: str) -> Path:
# Create a Path object from the user-provided path
user_path = Path(path_str)
# Require absolute paths
# Security Policy 1: Require absolute paths to prevent ambiguity
# Relative paths could be interpreted differently depending on working directory
if not user_path.is_absolute():
raise ValueError(
f"Relative paths are not supported. Please provide an absolute path.\n"
f"Received: {path_str}"
)
# Resolve the absolute path
# Resolve the absolute path (follows symlinks, removes .. and .)
resolved_path = user_path.resolve()
# Security check: ensure the resolved path is within PROJECT_ROOT
# Security Policy 2: Ensure the resolved path is within PROJECT_ROOT
# This prevents directory traversal attacks (e.g., /project/../../../etc/passwd)
try:
resolved_path.relative_to(PROJECT_ROOT)
except ValueError:
@@ -115,12 +142,16 @@ def expand_paths(paths: List[str], extensions: Optional[Set[str]] = None) -> Lis
"""
Expand paths to individual files, handling both files and directories.
This function recursively walks directories to find all matching files.
It automatically filters out hidden files and common non-code directories
like __pycache__ to avoid including generated or system files.
Args:
paths: List of file or directory paths
extensions: Optional set of file extensions to include
paths: List of file or directory paths (must be absolute)
extensions: Optional set of file extensions to include (defaults to CODE_EXTENSIONS)
Returns:
List of individual file paths
List of individual file paths, sorted for consistent ordering
"""
if extensions is None:
extensions = CODE_EXTENSIONS
@@ -130,9 +161,10 @@ def expand_paths(paths: List[str], extensions: Optional[Set[str]] = None) -> Lis
for path in paths:
try:
# Validate each path for security before processing
path_obj = resolve_and_validate_path(path)
except (ValueError, PermissionError):
# Skip invalid paths
# Skip invalid paths silently to allow partial success
continue
if not path_obj.exists():
@@ -145,51 +177,61 @@ def expand_paths(paths: List[str], extensions: Optional[Set[str]] = None) -> Lis
seen.add(str(path_obj))
elif path_obj.is_dir():
# Walk directory recursively
# Walk directory recursively to find all files
for root, dirs, files in os.walk(path_obj):
# Skip hidden directories and __pycache__
# Filter directories in-place to skip hidden and cache directories
# This prevents descending into .git, .venv, __pycache__, etc.
dirs[:] = [
d for d in dirs if not d.startswith(".") and d != "__pycache__"
]
for file in files:
# Skip hidden files
# Skip hidden files (e.g., .DS_Store, .gitignore)
if file.startswith("."):
continue
file_path = Path(root) / file
# Check extension
# Filter by extension if specified
if not extensions or file_path.suffix.lower() in extensions:
full_path = str(file_path)
# Use set to prevent duplicates
if full_path not in seen:
expanded_files.append(full_path)
seen.add(full_path)
# Sort for consistent ordering
# Sort for consistent ordering across different runs
# This makes output predictable and easier to debug
expanded_files.sort()
return expanded_files
def read_file_content(file_path: str, max_size: int = 1_000_000) -> Tuple[str, int]:
"""
Read a single file and format it for Gemini.
Read a single file and format it for inclusion in AI prompts.
This function handles various error conditions gracefully and always
returns formatted content, even for errors. This ensures the AI model
gets context about what files were attempted but couldn't be read.
Args:
file_path: Path to file (must be absolute)
max_size: Maximum file size to read
max_size: Maximum file size to read (default 1MB to prevent memory issues)
Returns:
(formatted_content, estimated_tokens)
Tuple of (formatted_content, estimated_tokens)
Content is wrapped with clear delimiters for AI parsing
"""
try:
# Validate path security before any file operations
path = resolve_and_validate_path(file_path)
except (ValueError, PermissionError) as e:
# Return error in a format that provides context to the AI
content = f"\n--- ERROR ACCESSING FILE: {file_path} ---\nError: {str(e)}\n--- END FILE ---\n"
return content, estimate_tokens(content)
try:
# Check if path exists and is a file
# Validate file existence and type
if not path.exists():
content = f"\n--- FILE NOT FOUND: {file_path} ---\nError: File does not exist\n--- END FILE ---\n"
return content, estimate_tokens(content)
@@ -198,17 +240,19 @@ def read_file_content(file_path: str, max_size: int = 1_000_000) -> Tuple[str, i
content = f"\n--- NOT A FILE: {file_path} ---\nError: Path is not a file\n--- END FILE ---\n"
return content, estimate_tokens(content)
# Check file size
# Check file size to prevent memory exhaustion
file_size = path.stat().st_size
if file_size > max_size:
content = f"\n--- FILE TOO LARGE: {file_path} ---\nFile size: {file_size:,} bytes (max: {max_size:,})\n--- END FILE ---\n"
return content, estimate_tokens(content)
# Read the file
# Read the file with UTF-8 encoding, replacing invalid characters
# This ensures we can handle files with mixed encodings
with open(path, "r", encoding="utf-8", errors="replace") as f:
file_content = f.read()
# Format with clear delimiters for Gemini
# Format with clear delimiters that help the AI understand file boundaries
# Using consistent markers makes it easier for the model to parse
formatted = f"\n--- BEGIN FILE: {file_path} ---\n{file_content}\n--- END FILE: {file_path} ---\n"
return formatted, estimate_tokens(formatted)
@@ -226,14 +270,21 @@ def read_files(
"""
Read multiple files and optional direct code with smart token management.
This function implements intelligent token budgeting to maximize the amount
of relevant content that can be included in an AI prompt while staying
within token limits. It prioritizes direct code and reads files until
the token budget is exhausted.
Args:
file_paths: List of file or directory paths
code: Optional direct code to include
file_paths: List of file or directory paths (absolute paths required)
code: Optional direct code to include (prioritized over files)
max_tokens: Maximum tokens to use (defaults to MAX_CONTEXT_TOKENS)
reserve_tokens: Tokens to reserve for prompt and response
reserve_tokens: Tokens to reserve for prompt and response (default 50K)
Returns:
(full_content, brief_summary)
Tuple of (full_content, brief_summary)
- full_content: All file contents formatted for AI consumption
- brief_summary: Human-readable summary of what was processed
"""
if max_tokens is None:
max_tokens = MAX_CONTEXT_TOKENS
@@ -247,7 +298,8 @@ def read_files(
files_skipped = []
dirs_processed = []
# First, handle direct code if provided
# Priority 1: Handle direct code if provided
# Direct code is prioritized because it's explicitly provided by the user
if code:
formatted_code = (
f"\n--- BEGIN DIRECT CODE ---\n{code}\n--- END DIRECT CODE ---\n"
@@ -258,19 +310,23 @@ def read_files(
content_parts.append(formatted_code)
total_tokens += code_tokens
available_tokens -= code_tokens
# Create a preview for the summary
code_preview = code[:50] + "..." if len(code) > 50 else code
summary_parts.append(f"Direct code: {code_preview}")
else:
summary_parts.append("Direct code skipped (too large)")
# Expand all paths to get individual files
# Priority 2: Process file paths
if file_paths:
# Track which paths are directories
# Track which paths are directories for summary
for path in file_paths:
if Path(path).is_dir():
dirs_processed.append(path)
try:
if Path(path).is_dir():
dirs_processed.append(path)
except Exception:
pass # Ignore invalid paths
# Expand to get all files
# Expand directories to get all individual files
all_files = expand_paths(file_paths)
if not all_files and file_paths:
@@ -279,7 +335,7 @@ def read_files(
f"\n--- NO FILES FOUND ---\nProvided paths: {', '.join(file_paths)}\n--- END ---\n"
)
else:
# Read files up to token limit
# Read files sequentially until token limit is reached
for file_path in all_files:
if total_tokens >= available_tokens:
files_skipped.append(file_path)
@@ -293,9 +349,10 @@ def read_files(
total_tokens += file_tokens
files_read.append(file_path)
else:
# File too large for remaining budget
files_skipped.append(file_path)
# Build summary
# Build human-readable summary of what was processed
if dirs_processed:
summary_parts.append(f"Processed {len(dirs_processed)} dir(s)")
if files_read:
@@ -305,11 +362,12 @@ def read_files(
if total_tokens > 0:
summary_parts.append(f"~{total_tokens:,} tokens used")
# Add skipped files note if any were skipped
# Add informative note about skipped files to help users understand
# what was omitted and why
if files_skipped:
skip_note = "\n\n--- SKIPPED FILES (TOKEN LIMIT) ---\n"
skip_note += f"Total skipped: {len(files_skipped)}\n"
# Show first 10 skipped files
# Show first 10 skipped files as examples
for i, file_path in enumerate(files_skipped[:10]):
skip_note += f" - {file_path}\n"
if len(files_skipped) > 10: