gitflow-analytics 1.3.11__py3-none-any.whl → 3.3.0__py3-none-any.whl

gitflow_analytics/core/data_fetcher.py

@@ -8,10 +8,14 @@ without performing any LLM-based classification.
 import logging
 import os
 import subprocess
+import threading
+import time
+from concurrent.futures import ThreadPoolExecutor, as_completed
 from datetime import datetime, timedelta, timezone
 from pathlib import Path
 from typing import Any, Optional
 
+from sqlalchemy import func
 from sqlalchemy.orm import Session
 
 from ..extractors.story_points import StoryPointExtractor
@@ -25,11 +29,17 @@ from ..models.database import (
 )
 from .branch_mapper import BranchToProjectMapper
 from .cache import GitAnalysisCache
+from .git_timeout_wrapper import GitOperationTimeout, GitTimeoutWrapper, HeartbeatLogger
 from .identity import DeveloperIdentityResolver
 from .progress import get_progress_service
 
 logger = logging.getLogger(__name__)
 
+# THREAD SAFETY: Module-level thread-local storage for repository instances
+# Each thread gets its own isolated storage to prevent thread-safety issues
+# when GitDataFetcher is called from ThreadPoolExecutor
+_thread_local = threading.local()
+
 
 class GitDataFetcher:
     """Fetches raw Git commit data and organizes it by day for efficient batch processing.
@@ -48,6 +58,7 @@ class GitDataFetcher:
         branch_mapping_rules: Optional[dict[str, list[str]]] = None,
         allowed_ticket_platforms: Optional[list[str]] = None,
         exclude_paths: Optional[list[str]] = None,
+        skip_remote_fetch: bool = False,
     ):
         """Initialize the data fetcher.
 
@@ -56,8 +67,11 @@ class GitDataFetcher:
             branch_mapping_rules: Rules for mapping branches to projects
             allowed_ticket_platforms: List of allowed ticket platforms
             exclude_paths: List of file paths to exclude from analysis
+            skip_remote_fetch: If True, skip git fetch/pull operations
         """
         self.cache = cache
+        self.skip_remote_fetch = skip_remote_fetch
+        self.repository_status = {}  # Track status of each repository
         # CRITICAL FIX: Use the same database instance as the cache to avoid session conflicts
         self.database = cache.db
         self.story_point_extractor = StoryPointExtractor()
@@ -65,10 +79,35 @@ class GitDataFetcher:
         self.branch_mapper = BranchToProjectMapper(branch_mapping_rules)
         self.exclude_paths = exclude_paths or []
 
+        # Log exclusion configuration
+        if self.exclude_paths:
+            logger.info(
+                f"GitDataFetcher initialized with {len(self.exclude_paths)} exclusion patterns:"
+            )
+            for pattern in self.exclude_paths[:5]:  # Show first 5 patterns
+                logger.debug(f"  - {pattern}")
+            if len(self.exclude_paths) > 5:
+                logger.debug(f"  ... and {len(self.exclude_paths) - 5} more patterns")
+        else:
+            logger.info("GitDataFetcher initialized with no file exclusions")
+
         # Initialize identity resolver
         identity_db_path = cache.cache_dir / "identities.db"
         self.identity_resolver = DeveloperIdentityResolver(identity_db_path)
 
+        # Initialize git timeout wrapper for safe operations
+        self.git_wrapper = GitTimeoutWrapper(default_timeout=30)
+
+        # Statistics for tracking repository processing
+        self.processing_stats = {
+            "total": 0,
+            "processed": 0,
+            "success": 0,
+            "failed": 0,
+            "timeout": 0,
+            "repositories": {},
+        }
+
     def fetch_repository_data(
         self,
         repo_path: Path,
@@ -118,19 +157,37 @@ class GitDataFetcher:
         # Get progress service for top-level progress tracking
         progress = get_progress_service()
 
+        # Start Rich display for this repository if enabled
+        if hasattr(progress, "_use_rich") and progress._use_rich:
+            # Count total commits for progress estimation
+            try:
+                import git
+
+                git.Repo(repo_path)
+                # Check if we need to clone or pull
+                if not repo_path.exists() or not (repo_path / ".git").exists():
+                    logger.info(f"📥 Repository {project_key} needs cloning")
+                    progress.start_repository(f"{project_key} (cloning)", 0)
+                else:
+                    # Rough estimate based on weeks
+                    estimated_commits = weeks_back * 50  # Estimate ~50 commits per week
+                    progress.start_repository(project_key, estimated_commits)
+            except Exception:
+                progress.start_repository(project_key, 100)  # Default estimate
+
         # Step 1: Collect all commits organized by day with enhanced progress tracking
         logger.info("🔍 DEBUG: About to fetch commits by day")
-        logger.info("Fetching commits organized by day...")
+        logger.info(f"Fetching commits organized by day for repository: {project_key}")
 
         # Create top-level progress for this repository
         with progress.progress(
             total=3,  # Three main steps: fetch commits, extract tickets, store data
-            description=f"Processing {project_key}",
+            description=f"📊 Processing repository: {project_key}",
             unit="steps",
         ) as repo_progress_ctx:
 
             # Step 1: Fetch commits
-            progress.set_description(repo_progress_ctx, f"{project_key}: Fetching commits")
+            progress.set_description(repo_progress_ctx, f"🔍 {project_key}: Fetching commits")
             daily_commits = self._fetch_commits_by_day(
                 repo_path, project_key, start_date, end_date, branch_patterns, progress_callback
             )
@@ -138,25 +195,27 @@ class GitDataFetcher:
             progress.update(repo_progress_ctx)
 
             # Step 2: Extract and fetch all referenced tickets
-            progress.set_description(repo_progress_ctx, f"{project_key}: Processing tickets")
+            progress.set_description(repo_progress_ctx, f"🎫 {project_key}: Processing tickets")
             logger.info("🔍 DEBUG: About to extract ticket references")
-            logger.info("Extracting ticket references...")
+            logger.info(f"Extracting ticket references for {project_key}...")
             ticket_ids = self._extract_all_ticket_references(daily_commits)
             logger.info(f"🔍 DEBUG: Extracted {len(ticket_ids)} ticket IDs")
 
             if jira_integration and ticket_ids:
-                logger.info(f"Fetching {len(ticket_ids)} unique tickets from JIRA...")
+                logger.info(
+                    f"Fetching {len(ticket_ids)} unique tickets from JIRA for {project_key}..."
+                )
                 self._fetch_detailed_tickets(
                     ticket_ids, jira_integration, project_key, progress_callback
                 )
 
             # Build commit-ticket correlations
-            logger.info("Building commit-ticket correlations...")
+            logger.info(f"Building commit-ticket correlations for {project_key}...")
             correlations_created = self._build_commit_ticket_correlations(daily_commits, repo_path)
             progress.update(repo_progress_ctx)
 
             # Step 3: Store daily commit batches
-            progress.set_description(repo_progress_ctx, f"{project_key}: Storing data")
+            progress.set_description(repo_progress_ctx, f"💾 {project_key}: Storing data")
             logger.info(
                 f"🔍 DEBUG: About to store daily batches. Daily commits has {len(daily_commits)} days"
             )
@@ -183,6 +242,46 @@ class GitDataFetcher:
         # Return summary statistics with ACTUAL stored counts
         # expected_commits already calculated above
 
+        # Calculate exclusion impact summary if exclusions are configured
+        exclusion_stats = {
+            "patterns_applied": len(self.exclude_paths),
+            "enabled": bool(self.exclude_paths),
+        }
+
+        if self.exclude_paths and expected_commits > 0:
+            # Get aggregate stats from daily_commit_batches
+            session = self.database.get_session()
+            try:
+                batch_stats = (
+                    session.query(
+                        func.sum(DailyCommitBatch.total_lines_added).label("total_added"),
+                        func.sum(DailyCommitBatch.total_lines_deleted).label("total_deleted"),
+                    )
+                    .filter(
+                        DailyCommitBatch.project_key == project_key,
+                        DailyCommitBatch.repo_path == str(repo_path),
+                    )
+                    .first()
+                )
+
+                if batch_stats and batch_stats.total_added:
+                    total_lines = (batch_stats.total_added or 0) + (batch_stats.total_deleted or 0)
+                    exclusion_stats["total_lines_after_filtering"] = total_lines
+                    exclusion_stats["lines_added"] = batch_stats.total_added or 0
+                    exclusion_stats["lines_deleted"] = batch_stats.total_deleted or 0
+
+                    logger.info(
+                        f"📊 Exclusion Impact Summary for {project_key}:\n"
+                        f"  - Exclusion patterns applied: {len(self.exclude_paths)}\n"
+                        f"  - Total lines after filtering: {total_lines:,}\n"
+                        f"  - Lines added: {batch_stats.total_added:,}\n"
+                        f"  - Lines deleted: {batch_stats.total_deleted:,}"
+                    )
+            except Exception as e:
+                logger.debug(f"Could not calculate exclusion impact summary: {e}")
+            finally:
+                session.close()
+
         results = {
             "project_key": project_key,
             "repo_path": str(repo_path),
@@ -196,6 +295,7 @@ class GitDataFetcher:
                 "correlations_created": correlations_created,
                 "batches_created": batches_created,
             },
+            "exclusions": exclusion_stats,
             "daily_commits": daily_commits,  # For immediate use if needed
         }
 
@@ -204,10 +304,20 @@ class GitDataFetcher:
             logger.info(
                 f"✅ Data fetch completed successfully for {project_key}: {actual_stored_commits}/{expected_commits} commits stored, {len(ticket_ids)} tickets"
             )
+            # Finish repository in Rich display with success
+            if hasattr(progress, "_use_rich") and progress._use_rich:
+                progress.finish_repository(project_key, success=True)
         else:
             logger.error(
                 f"⚠️ Data fetch completed with storage issues for {project_key}: {actual_stored_commits}/{expected_commits} commits stored, {len(ticket_ids)} tickets"
             )
+            # Finish repository in Rich display with error
+            if hasattr(progress, "_use_rich") and progress._use_rich:
+                progress.finish_repository(
+                    project_key,
+                    success=False,
+                    error_message=f"Storage issue: {actual_stored_commits}/{expected_commits} commits",
+                )
 
         return results
 
@@ -225,24 +335,148 @@ class GitDataFetcher:
         Returns:
             Dictionary mapping date strings (YYYY-MM-DD) to lists of commit data
         """
-        from git import Repo
+
+        # THREAD SAFETY: Use the module-level thread-local storage to ensure each thread
+        # gets its own Repo instance. This prevents thread-safety issues when called from ThreadPoolExecutor
+
+        # Set environment variables to prevent ANY password prompts before opening repo
+        original_env = {}
+        env_vars = {
+            "GIT_TERMINAL_PROMPT": "0",
+            "GIT_ASKPASS": "/bin/echo",  # Use full path to echo
+            "SSH_ASKPASS": "/bin/echo",
+            "GCM_INTERACTIVE": "never",
+            "GIT_SSH_COMMAND": "ssh -o BatchMode=yes -o StrictHostKeyChecking=no -o PasswordAuthentication=no",
+            "DISPLAY": "",
+            "GIT_CREDENTIAL_HELPER": "",  # Disable credential helper
+            "GCM_PROVIDER": "none",  # Disable Git Credential Manager
+            "GIT_CREDENTIALS": "",  # Clear any cached credentials
+            "GIT_CONFIG_NOSYSTEM": "1",  # Don't use system config
+        }
+
+        # Save original environment and set our values
+        for key, value in env_vars.items():
+            original_env[key] = os.environ.get(key)
+            os.environ[key] = value
 
         try:
-            repo = Repo(repo_path)
+            # THREAD SAFETY: Create a fresh Repo instance for this thread
+            # Do NOT reuse Repo instances across threads
+            from git import Repo
+
+            # Check for security issues in repository configuration
+            self._check_repository_security(repo_path, project_key)
+
+            # When skip_remote_fetch is enabled, use a more restricted repository access
+            if self.skip_remote_fetch:
+                # Use a special git configuration that completely disables credential helpers
+                import tempfile
+
+                # Create a secure temporary directory for our config
+                temp_dir = tempfile.mkdtemp(prefix="gitflow_")
+
+                # Create a temporary git config that disables all authentication
+                tmp_config_path = os.path.join(temp_dir, ".gitconfig")
+                with open(tmp_config_path, "w") as tmp_config:
+                    tmp_config.write("[credential]\n")
+                    tmp_config.write("    helper = \n")
+                    tmp_config.write("[core]\n")
+                    tmp_config.write("    askpass = \n")
+
+                # Set GIT_CONFIG to use our temporary config
+                os.environ["GIT_CONFIG_GLOBAL"] = tmp_config_path
+                os.environ["GIT_CONFIG_SYSTEM"] = "/dev/null"
+
+                # Store temp_dir in thread-local storage for cleanup
+                _thread_local.temp_dir = temp_dir
+
+                try:
+                    # Open repository with our restricted configuration
+                    # THREAD SAFETY: Each thread gets its own Repo instance
+                    repo = Repo(repo_path)
+                finally:
+                    # Clean up temporary config directory
+                    try:
+                        import shutil
+
+                        if hasattr(_thread_local, "temp_dir"):
+                            shutil.rmtree(_thread_local.temp_dir, ignore_errors=True)
+                            delattr(_thread_local, "temp_dir")
+                    except:
+                        pass
+
+                try:
+                    # Configure git to never prompt for credentials
+                    with repo.config_writer() as git_config:
+                        git_config.set_value("core", "askpass", "")
+                        git_config.set_value("credential", "helper", "")
+                except Exception as e:
+                    logger.debug(f"Could not update git config: {e}")
+
+                # Note: We can't monkey-patch remotes as it's a property without setter
+                # The skip_remote_fetch flag will prevent remote operations elsewhere
+
+                logger.debug(
+                    f"Opened repository {project_key} in offline mode (skip_remote_fetch=true)"
+                )
+            else:
+                # THREAD SAFETY: Each thread gets its own Repo instance
+                repo = Repo(repo_path)
+            # Track repository status
+            self.repository_status[project_key] = {
+                "path": str(repo_path),
+                "remote_update": "skipped" if self.skip_remote_fetch else "pending",
+                "authentication_issues": False,
+                "error": None,
+            }
+
             # Update repository from remote before analysis
-            self._update_repository(repo)
+            if not self.skip_remote_fetch:
+                logger.info(f"📥 Updating repository {project_key} from remote...")
+
+            update_success = self._update_repository(repo)
+            if not self.skip_remote_fetch:
+                self.repository_status[project_key]["remote_update"] = (
+                    "success" if update_success else "failed"
+                )
+                if not update_success:
+                    logger.warning(
+                        f"⚠️ {project_key}: Continuing with local repository state (remote update failed)"
+                    )
+
         except Exception as e:
-            logger.error(f"Failed to open repository at {repo_path}: {e}")
+            logger.error(f"Failed to open repository {project_key} at {repo_path}: {e}")
+            self.repository_status[project_key] = {
+                "path": str(repo_path),
+                "remote_update": "error",
+                "authentication_issues": "authentication" in str(e).lower()
+                or "password" in str(e).lower(),
+                "error": str(e),
+            }
+            # Restore original environment variables before returning
+            for key, value in original_env.items():
+                if value is None:
+                    os.environ.pop(key, None)
+                else:
+                    os.environ[key] = value
             return {}
 
         # Get branches to analyze
         branches_to_analyze = self._get_branches_to_analyze(repo, branch_patterns)
 
         if not branches_to_analyze:
-            logger.warning(f"No accessible branches found in repository {repo_path}")
+            logger.warning(
+                f"No accessible branches found in repository {project_key} at {repo_path}"
+            )
+            # Restore original environment variables before returning
+            for key, value in original_env.items():
+                if value is None:
+                    os.environ.pop(key, None)
+                else:
+                    os.environ[key] = value
             return {}
 
-        logger.info(f"Analyzing branches: {branches_to_analyze}")
+        logger.info(f"🌿 {project_key}: Analyzing branches: {branches_to_analyze}")
 
         # Calculate days to process
         current_date = start_date.date()
@@ -263,18 +497,34 @@ class GitDataFetcher:
         daily_commits = {}
         all_commit_hashes = set()  # Track all hashes for deduplication
 
+        # Count total commits first for Rich display
+        try:
+            for branch_name in branches_to_analyze[:1]:  # Sample from first branch
+                sample_commits = list(
+                    repo.iter_commits(branch_name, since=start_date, until=end_date)
+                )
+                # Estimate based on first branch (multiply by number of branches for rough estimate)
+                len(sample_commits) * len(branches_to_analyze)
+                break
+        except:
+            len(days_to_process) * 50  # Default estimate
+
+        # Update repository in Rich display with estimated commit count
+        if hasattr(progress, "_use_rich") and progress._use_rich:
+            progress.update_repository(project_key, 0, 0.0)
+
         # Create nested progress for day-by-day processing
         with progress.progress(
             total=len(days_to_process),
-            description=f"Fetching commits for {project_key}",
+            description=f"📅 Fetching commits for repository: {project_key}",
             unit="days",
             nested=True,
         ) as day_progress_ctx:
 
             for day_date in days_to_process:
-                # Update description to show current day
+                # Update description to show current repository and day clearly
                 day_str = day_date.strftime("%Y-%m-%d")
-                progress.set_description(day_progress_ctx, f"{project_key}: Processing {day_str}")
+                progress.set_description(day_progress_ctx, f"🔍 {project_key}: Analyzing {day_str}")
 
                 # Calculate day boundaries
                 day_start = datetime.combine(day_date, datetime.min.time(), tzinfo=timezone.utc)
@@ -286,12 +536,26 @@ class GitDataFetcher:
                 # Process each branch for this specific day
                 for branch_name in branches_to_analyze:
                     try:
-                        # Fetch commits for this specific day and branch
-                        branch_commits = list(
-                            repo.iter_commits(
-                                branch_name, since=day_start, until=day_end, reverse=False
+                        # Fetch commits for this specific day and branch with timeout protection
+                        def fetch_branch_commits():
+                            return list(
+                                repo.iter_commits(
+                                    branch_name, since=day_start, until=day_end, reverse=False
+                                )
                             )
-                        )
+
+                        # Use timeout wrapper to prevent hanging on iter_commits
+                        try:
+                            branch_commits = self.git_wrapper.run_with_timeout(
+                                fetch_branch_commits,
+                                timeout=15,  # 15 seconds per branch/day combination
+                                operation_name=f"iter_commits_{branch_name}_{day_str}",
+                            )
+                        except GitOperationTimeout:
+                            logger.warning(
+                                f"⏱️ Timeout fetching commits for branch {branch_name} on {day_str}, skipping"
+                            )
+                            continue
 
                         for commit in branch_commits:
                             # Skip if we've already processed this commit
@@ -307,6 +571,11 @@ class GitDataFetcher:
                                 all_commit_hashes.add(commit.hexsha)
                                 commits_found_today += 1
 
+                    except GitOperationTimeout as e:
+                        logger.warning(
+                            f"⏱️ Timeout processing branch {branch_name} for day {day_str}: {e}"
+                        )
+                        continue
                     except Exception as e:
                         logger.warning(
                             f"Error processing branch {branch_name} for day {day_str}: {e}"
@@ -333,8 +602,28 @@ class GitDataFetcher:
                 # Update progress bar
                 progress.update(day_progress_ctx)
 
+                # Update Rich display with current commit count and speed
+                if hasattr(progress, "_use_rich") and progress._use_rich:
+                    total_processed = len(all_commit_hashes)
+                    # Calculate speed (commits per second) based on elapsed time
+                    import time
+
+                    if not hasattr(self, "_fetch_start_time"):
+                        self._fetch_start_time = time.time()
+                    elapsed = time.time() - self._fetch_start_time
+                    speed = total_processed / elapsed if elapsed > 0 else 0
+                    progress.update_repository(project_key, total_processed, speed)
+
         total_commits = sum(len(commits) for commits in daily_commits.values())
         logger.info(f"Collected {total_commits} unique commits across {len(daily_commits)} days")
+
+        # Restore original environment variables
+        for key, value in original_env.items():
+            if value is None:
+                os.environ.pop(key, None)
+            else:
+                os.environ[key] = value
+
         return daily_commits
 
     def _extract_commit_data(
@@ -376,13 +665,19 @@ class GitDataFetcher:
                 line_stats = self._calculate_commit_stats(commit)
                 total_insertions = line_stats["insertions"]
                 total_deletions = line_stats["deletions"]
+                raw_insertions = line_stats.get("raw_insertions", total_insertions)
+                raw_deletions = line_stats.get("raw_deletions", total_deletions)
 
                 commit_data.update(
                     {
                         "files_changed": files_changed,
                         "files_changed_count": len(files_changed),
-                        "lines_added": total_insertions,
+                        "lines_added": total_insertions,  # Filtered counts for backward compatibility
                         "lines_deleted": total_deletions,
+                        "filtered_insertions": total_insertions,  # Explicitly filtered counts
+                        "filtered_deletions": total_deletions,
+                        "raw_insertions": raw_insertions,  # Raw unfiltered counts
+                        "raw_deletions": raw_deletions,
                     }
                 )
 
@@ -394,6 +689,10 @@ class GitDataFetcher:
                         "files_changed_count": 0,
                         "lines_added": 0,
                         "lines_deleted": 0,
+                        "filtered_insertions": 0,
+                        "filtered_deletions": 0,
+                        "raw_insertions": 0,
+                        "raw_deletions": 0,
                     }
                 )
 
@@ -422,9 +721,166 @@ class GitDataFetcher:
 
     def _should_exclude_file(self, file_path: str) -> bool:
         """Check if a file should be excluded based on exclude patterns."""
+        return any(self._matches_glob_pattern(file_path, pattern) for pattern in self.exclude_paths)
+
+    def _matches_glob_pattern(self, filepath: str, pattern: str) -> bool:
+        """Check if a file path matches a glob pattern, handling ** recursion correctly.
+
+        This method properly handles different glob pattern types:
+        - **/vendor/** : matches files inside vendor directories at any level
+        - **/*.min.js : matches files with specific suffix anywhere in directory tree
+        - vendor/** : matches files inside vendor directory at root level only
+        - **pattern** : handles other complex patterns with pathlib.match()
+        - simple patterns : uses fnmatch for basic wildcards
+
+        Args:
+            filepath: The file path to check
+            pattern: The glob pattern to match against
+
+        Returns:
+            True if the file path matches the pattern, False otherwise
+        """
+        import fnmatch
+        import re
+        from pathlib import PurePath
+
+        # Handle empty or invalid inputs
+        if not filepath or not pattern:
+            return False
+
+        path = PurePath(filepath)
+
+        # Check for multiple ** patterns first (most complex)
+        if "**" in pattern and pattern.count("**") > 1:
+            # Multiple ** patterns - use custom recursive matching for complex patterns
+            return self._match_recursive_pattern(filepath, pattern)
+
+        # Then handle simple ** patterns
+        elif pattern.startswith("**/") and pattern.endswith("/**"):
+            # Pattern like **/vendor/** - matches files inside vendor directories at any level
+            dir_name = pattern[3:-3]  # Extract 'vendor' from '**/vendor/**'
+            if not dir_name:  # Handle edge case of '**/**'
+                return True
+            return dir_name in path.parts
+
+        elif pattern.startswith("**/"):
+            # Pattern like **/*.min.js - matches files with specific suffix anywhere
+            suffix_pattern = pattern[3:]
+            if not suffix_pattern:  # Handle edge case of '**/'
+                return True
+            # Check against filename for file patterns, or any path part for directory patterns
+            if suffix_pattern.endswith("/"):
+                # Directory pattern like **/build/
+                dir_name = suffix_pattern[:-1]
+                return dir_name in path.parts
+            else:
+                # File pattern like *.min.js
+                return fnmatch.fnmatch(path.name, suffix_pattern)
+
+        elif pattern.endswith("/**"):
+            # Pattern like vendor/** or docs/build/** - matches files inside directory at root level
+            dir_name = pattern[:-3]
+            if not dir_name:  # Handle edge case of '/**'
+                return True
+
+            # Handle both single directory names and nested paths
+            expected_parts = PurePath(dir_name).parts
+            return (
+                len(path.parts) >= len(expected_parts)
+                and path.parts[: len(expected_parts)] == expected_parts
+            )
+
+        elif "**" in pattern:
+            # Single ** pattern - use pathlib matching with fallback
+            try:
+                return path.match(pattern)
+            except (ValueError, TypeError):
+                # Fall back to fnmatch if pathlib fails (e.g., invalid pattern)
+                try:
+                    return fnmatch.fnmatch(filepath, pattern)
+                except re.error:
+                    # Invalid regex pattern - return False to be safe
+                    return False
+        else:
+            # Simple pattern - use fnmatch for basic wildcards
+            try:
+                # Try matching the full path first
+                if fnmatch.fnmatch(filepath, pattern):
+                    return True
+                # Also try matching just the filename for simple patterns
+                # This allows "package-lock.json" to match "src/package-lock.json"
+                return fnmatch.fnmatch(path.name, pattern)
+            except re.error:
+                # Invalid regex pattern - return False to be safe
+                return False
+
+    def _match_recursive_pattern(self, filepath: str, pattern: str) -> bool:
+        """Handle complex patterns with multiple ** wildcards.
+
+        Args:
+            filepath: The file path to check
+            pattern: The pattern with multiple ** wildcards
+
+        Returns:
+            True if the path matches the pattern, False otherwise
+        """
         import fnmatch
+        from pathlib import PurePath
+
+        # Split pattern by ** to handle each segment
+        parts = pattern.split("**")
+
+        # Validate that we have actual segments
+        if not parts:
+            return False
 
-        return any(fnmatch.fnmatch(file_path, pattern) for pattern in self.exclude_paths)
+        # Convert filepath to parts for easier matching
+        path_parts = list(PurePath(filepath).parts)
+
+        # Start matching from the beginning
+        path_index = 0
+
+        for i, part in enumerate(parts):
+            if not part:
+                # Empty part (e.g., from leading or trailing **)
+                if i == 0 or i == len(parts) - 1:
+                    # Leading or trailing ** - continue
+                    continue
+                # Middle empty part (consecutive **) - match any number of path components
+                continue
+
+            # Clean the part (remove leading/trailing slashes)
+            part = part.strip("/")
+
+            if not part:
+                continue
+
+            # Find where this part matches in the remaining path
+            found = False
+            for j in range(path_index, len(path_parts)):
+                # Check if the current path part matches the pattern part
+                if "/" in part:
+                    # Part contains multiple path components
+                    sub_parts = part.split("/")
+                    if j + len(sub_parts) <= len(path_parts) and all(
+                        fnmatch.fnmatch(path_parts[j + k], sub_parts[k])
+                        for k in range(len(sub_parts))
+                    ):
+                        path_index = j + len(sub_parts)
+                        found = True
+                        break
+                else:
+                    # Single component part
+                    if fnmatch.fnmatch(path_parts[j], part):
+                        path_index = j + 1
+                        found = True
+                        break
+
+            if not found and part:
+                # Required part not found in path
+                return False
+
+        return True
 
     def _get_branches_to_analyze(
         self, repo: Any, branch_patterns: Optional[list[str]]
@@ -441,33 +897,45 @@ class GitDataFetcher:
         - Handle missing remotes gracefully
         - Skip remote tracking branches to avoid duplicates
         - Use actual branch existence checking rather than assuming branches exist
+
+        THREAD SAFETY: This method is thread-safe as it doesn't modify shared state
+        and works with a repo instance passed as a parameter.
         """
         # Collect all available branches (local branches preferred)
         available_branches = []
 
         # First, try local branches
         try:
-            local_branches = [branch.name for branch in repo.branches]
+            # THREAD SAFETY: Create a new list to avoid sharing references
+            local_branches = list([branch.name for branch in repo.branches])
             available_branches.extend(local_branches)
             logger.debug(f"Found local branches: {local_branches}")
         except Exception as e:
             logger.debug(f"Error getting local branches: {e}")
 
         # If we have remotes, also consider remote branches (but clean the names)
-        try:
-            if repo.remotes and hasattr(repo.remotes, "origin"):
-                remote_branches = [
-                    ref.name.replace("origin/", "")
-                    for ref in repo.remotes.origin.refs
-                    if not ref.name.endswith("HEAD")  # Skip HEAD ref
-                ]
-                # Only add remote branches that aren't already in local branches
-                for branch in remote_branches:
-                    if branch not in available_branches:
-                        available_branches.append(branch)
-                logger.debug(f"Found remote branches: {remote_branches}")
-        except Exception as e:
-            logger.debug(f"Error getting remote branches: {e}")
+        # Skip remote branch checking if skip_remote_fetch is enabled to avoid auth prompts
+        if not self.skip_remote_fetch:
+            try:
+                if repo.remotes and hasattr(repo.remotes, "origin"):
+                    # THREAD SAFETY: Create a new list to avoid sharing references
+                    remote_branches = list(
+                        [
+                            ref.name.replace("origin/", "")
+                            for ref in repo.remotes.origin.refs
+                            if not ref.name.endswith("HEAD")  # Skip HEAD ref
+                        ]
+                    )
+                    # Only add remote branches that aren't already in local branches
+                    for branch in remote_branches:
+                        if branch not in available_branches:
+                            available_branches.append(branch)
+                    logger.debug(f"Found remote branches: {remote_branches}")
+            except Exception as e:
+                logger.debug(f"Error getting remote branches (may require authentication): {e}")
+                # Continue with local branches only
+        else:
+            logger.debug("Skipping remote branch enumeration (skip_remote_fetch=true)")
 
         # If no branches found, fallback to trying common names directly
         if not available_branches:
@@ -497,6 +965,7 @@ class GitDataFetcher:
         accessible_branches = []
         for branch in branches_to_test:
             try:
+                # THREAD SAFETY: Use iterator without storing intermediate results
                 next(iter(repo.iter_commits(branch, max_count=1)), None)
                 accessible_branches.append(branch)
             except Exception as e:
@@ -550,82 +1019,62 @@ class GitDataFetcher:
         Returns:
             bool: True if update succeeded, False if failed (but analysis continues)
         """
-        try:
-            if repo.remotes:
-                logger.info("Fetching latest changes from remote")
+        # Skip remote operations if configured
+        if self.skip_remote_fetch:
+            logger.info("🚫 Skipping remote fetch (skip_remote_fetch=true)")
+            return True
 
-                # Use subprocess for git fetch to prevent password prompts
-                env = os.environ.copy()
-                env["GIT_TERMINAL_PROMPT"] = "0"
-                env["GIT_ASKPASS"] = ""
-                env["GCM_INTERACTIVE"] = "never"
+        # Check for stale repository (last fetch > 1 hour ago)
+        self._check_repository_staleness(repo)
 
-                # Run git fetch with timeout
-                try:
-                    result = subprocess.run(
-                        ["git", "fetch", "--all"],
-                        cwd=repo.working_dir,
-                        env=env,
-                        capture_output=True,
-                        text=True,
-                        timeout=30,  # 30 second timeout
-                    )
+        try:
+            # Check if we have remotes without triggering authentication
+            has_remotes = False
+            try:
+                has_remotes = bool(repo.remotes)
+            except Exception as e:
+                logger.debug(f"Could not check for remotes (may require authentication): {e}")
+                return True  # Continue with local analysis
 
-                    if result.returncode != 0:
-                        error_str = result.stderr.lower()
-                        if any(
-                            x in error_str
-                            for x in ["authentication", "permission denied", "401", "403"]
-                        ):
-                            logger.error(
-                                "GitHub authentication failed. Please check your token is valid and has appropriate permissions. "
-                                "You can verify with: gh auth status"
-                            )
-                            # Skip fetch but continue with local analysis
-                            return False
-                        logger.warning(f"Git fetch failed: {result.stderr}")
-                        return False
+            if has_remotes:
+                logger.info("Fetching latest changes from remote")
 
-                except subprocess.TimeoutExpired:
-                    logger.error(
-                        "Git fetch timed out (likely authentication failure). Continuing with local repository state."
+                # Use our timeout wrapper for safe git operations
+                repo_path = Path(repo.working_dir)
+
+                # Try to fetch with timeout protection
+                fetch_success = self.git_wrapper.fetch_with_timeout(repo_path, timeout=30)
+
+                if not fetch_success:
+                    # Mark this repository as having authentication issues if applicable
+                    if hasattr(self, "repository_status"):
+                        for key in self.repository_status:
+                            if repo.working_dir.endswith(key) or key in repo.working_dir:
+                                self.repository_status[key]["remote_update"] = "failed"
+                                break
+
+                    # Explicit warning to user about stale data
+                    logger.warning(
+                        f"❌ Failed to fetch updates for {repo_path.name}. "
+                        f"Analysis will use potentially stale local data. "
+                        f"Check authentication or network connectivity."
                     )
                     return False
+                else:
+                    # Explicit success confirmation
+                    logger.info(f"✅ Successfully fetched updates for {repo_path.name}")
 
                 # Only try to pull if not in detached HEAD state
                 if not repo.head.is_detached:
                     current_branch = repo.active_branch
                     tracking = current_branch.tracking_branch()
                     if tracking:
-                        # Pull latest changes using subprocess
-                        try:
-                            result = subprocess.run(
-                                ["git", "pull"],
-                                cwd=repo.working_dir,
-                                env=env,
-                                capture_output=True,
-                                text=True,
-                                timeout=30,
-                            )
-
-                            if result.returncode != 0:
-                                error_str = result.stderr.lower()
-                                if any(
-                                    x in error_str
-                                    for x in ["authentication", "permission denied", "401", "403"]
-                                ):
-                                    logger.error(
-                                        "GitHub authentication failed during pull. Continuing with local repository state."
-                                    )
-                                    return False
-                                logger.warning(f"Git pull failed: {result.stderr}")
-                                return False
+                        # Pull latest changes using timeout wrapper
+                        pull_success = self.git_wrapper.pull_with_timeout(repo_path, timeout=30)
+                        if pull_success:
                             logger.debug(f"Pulled latest changes for {current_branch.name}")
-
-                        except subprocess.TimeoutExpired:
-                            logger.error(
-                                "Git pull timed out. Continuing with local repository state."
-                            )
+                        else:
+                            logger.warning("Git pull failed, continuing with fetched state")
                             return False
                     else:
                         logger.debug(
@@ -642,6 +1091,114 @@ class GitDataFetcher:
             # Continue with analysis using local state
             return False
 
+    def _check_repository_staleness(self, repo) -> None:
+        """Check if repository hasn't been fetched recently and warn user.
+
+        Args:
+            repo: GitPython Repo object
+        """
+        try:
+            repo_path = Path(repo.working_dir)
+            fetch_head_path = repo_path / ".git" / "FETCH_HEAD"
+
+            if fetch_head_path.exists():
+                # Get last fetch time from FETCH_HEAD modification time
+                last_fetch_time = datetime.fromtimestamp(
+                    fetch_head_path.stat().st_mtime, tz=timezone.utc
+                )
+                now = datetime.now(timezone.utc)
+                hours_since_fetch = (now - last_fetch_time).total_seconds() / 3600
+
+                if hours_since_fetch > 1:
+                    logger.warning(
+                        f"⏰ Repository {repo_path.name} last fetched {hours_since_fetch:.1f} hours ago. "
+                        f"Data may be stale."
+                    )
+            else:
+                logger.warning(
+                    f"⚠️ Repository {repo_path.name} has never been fetched. "
+                    f"Will attempt to fetch now."
+                )
+        except Exception as e:
+            logger.debug(f"Could not check repository staleness: {e}")
+
+    def _check_repository_security(self, repo_path: Path, project_key: str) -> None:
+        """Check for security issues in repository configuration.
+
+        Warns about:
+        - Exposed tokens in remote URLs
+        - Insecure credential storage
+        """
+
+        try:
+            # Check for tokens in remote URLs
+            result = subprocess.run(
+                ["git", "remote", "-v"],
+                cwd=repo_path,
+                capture_output=True,
+                text=True,
+                timeout=2,
+                env={"GIT_TERMINAL_PROMPT": "0"},
+            )
+
+            if result.returncode == 0:
+                output = result.stdout
+                # Check for various token patterns in URLs
+                token_patterns = [
+                    r"https://[^@]*@",  # Any HTTPS URL with embedded credentials
+                    r"ghp_[a-zA-Z0-9]+",  # GitHub Personal Access Token
+                    r"ghs_[a-zA-Z0-9]+",  # GitHub Server Token
+                    r"github_pat_[a-zA-Z0-9]+",  # New GitHub PAT format
+                ]
+
+                for pattern in token_patterns:
+                    import re
+
+                    if re.search(pattern, output):
+                        logger.warning(
+                            f"⚠️  SECURITY WARNING for {project_key}: "
+                            f"Repository appears to have credentials in remote URL. "
+                            f"This is a security risk! Consider using: "
+                            f"1) GitHub CLI (gh auth login), "
+                            f"2) SSH keys, or "
+                            f"3) Git credential manager instead."
+                        )
+                        break
+        except:
+            # Don't fail analysis due to security check
+            pass
+
+    def get_repository_status_summary(self) -> dict[str, Any]:
+        """Get a summary of repository fetch status.
+
+        Returns:
+            Dictionary with status summary including any repositories with issues
+        """
+        summary = {
+            "total_repositories": len(self.repository_status),
+            "successful_updates": 0,
+            "failed_updates": 0,
+            "skipped_updates": 0,
+            "authentication_issues": [],
+            "errors": [],
+        }
+
+        for project_key, status in self.repository_status.items():
+            if status["remote_update"] == "success":
+                summary["successful_updates"] += 1
+            elif status["remote_update"] == "failed":
+                summary["failed_updates"] += 1
+                if status.get("authentication_issues"):
+                    summary["authentication_issues"].append(project_key)
+            elif status["remote_update"] == "skipped":
+                summary["skipped_updates"] += 1
+            elif status["remote_update"] == "error":
+                summary["errors"].append(
+                    {"repository": project_key, "error": status.get("error", "Unknown error")}
+                )
+
+        return summary
+
     def _extract_all_ticket_references(
         self, daily_commits: dict[str, list[dict[str, Any]]]
     ) -> set[str]:
@@ -919,8 +1476,20 @@ class GitDataFetcher:
                                 "branch": commit.get("branch", "main"),
                                 "is_merge": commit.get("is_merge", False),
                                 "files_changed_count": commit.get("files_changed_count", 0),
-                                "insertions": commit.get("lines_added", 0),
-                                "deletions": commit.get("lines_deleted", 0),
+                                # Store raw unfiltered values in insertions/deletions
+                                "insertions": commit.get(
+                                    "raw_insertions", commit.get("lines_added", 0)
+                                ),
+                                "deletions": commit.get(
+                                    "raw_deletions", commit.get("lines_deleted", 0)
+                                ),
+                                # Store filtered values separately
+                                "filtered_insertions": commit.get(
+                                    "filtered_insertions", commit.get("lines_added", 0)
+                                ),
+                                "filtered_deletions": commit.get(
+                                    "filtered_deletions", commit.get("lines_deleted", 0)
+                                ),
                                 "story_points": commit.get("story_points"),
                                 "ticket_references": commit.get("ticket_references", []),
                             }
@@ -1193,24 +1762,48 @@ class GitDataFetcher:
             session.close()
 
     def _calculate_commit_stats(self, commit: Any) -> dict[str, int]:
-        """Calculate commit statistics using reliable git diff --numstat.
+        """Calculate commit statistics using reliable git diff --numstat with exclude_paths filtering.
 
         Returns:
-            Dictionary with 'files', 'insertions', and 'deletions' counts
+            Dictionary with both raw and filtered statistics:
+            - 'files', 'insertions', 'deletions': filtered counts
+            - 'raw_insertions', 'raw_deletions': unfiltered counts
+
+        THREAD SAFETY: This method is thread-safe as it works with commit objects
+        that have their own repo references.
         """
         stats = {"files": 0, "insertions": 0, "deletions": 0}
 
+        # Track raw stats for storage
+        raw_stats = {"files": 0, "insertions": 0, "deletions": 0}
+        excluded_stats = {"files": 0, "insertions": 0, "deletions": 0}
+
         # For initial commits or commits without parents
         parent = commit.parents[0] if commit.parents else None
 
         try:
-            # Use git command directly for accurate line counts
+            # THREAD SAFETY: Use the repo reference from the commit object
+            # Each thread has its own commit object with its own repo reference
             repo = commit.repo
-            if parent:
-                diff_output = repo.git.diff(parent.hexsha, commit.hexsha, "--numstat")
-            else:
-                # Initial commit - use git show with --numstat
-                diff_output = repo.git.show(commit.hexsha, "--numstat", "--format=")
+            Path(repo.working_dir)
+
+            def get_diff_output():
+                if parent:
+                    return repo.git.diff(parent.hexsha, commit.hexsha, "--numstat")
+                else:
+                    # Initial commit - use git show with --numstat
+                    return repo.git.show(commit.hexsha, "--numstat", "--format=")
+
+            # Use timeout wrapper for git diff operations
+            try:
+                diff_output = self.git_wrapper.run_with_timeout(
+                    get_diff_output,
+                    timeout=10,  # 10 seconds for diff operations
+                    operation_name=f"diff_{commit.hexsha[:8]}",
+                )
+            except GitOperationTimeout:
+                logger.warning(f"⏱️ Timeout calculating stats for commit {commit.hexsha[:8]}")
+                return stats  # Return zeros
 
             # Parse the numstat output: insertions\tdeletions\tfilename
             for line in diff_output.strip().split("\n"):
@@ -1222,9 +1815,22 @@ class GitDataFetcher:
                     try:
                         insertions = int(parts[0]) if parts[0] != "-" else 0
                         deletions = int(parts[1]) if parts[1] != "-" else 0
-                        # filename = parts[2] - we don't filter here since files_changed list is handled separately
-
-                        # Count all changes (raw stats, no filtering)
+                        filename = parts[2]
+
+                        # Always count raw stats
+                        raw_stats["files"] += 1
+                        raw_stats["insertions"] += insertions
+                        raw_stats["deletions"] += deletions
+
+                        # Skip excluded files based on exclude_paths patterns
+                        if self._should_exclude_file(filename):
+                            logger.debug(f"Excluding file from line counts: {filename}")
+                            excluded_stats["files"] += 1
+                            excluded_stats["insertions"] += insertions
+                            excluded_stats["deletions"] += deletions
+                            continue
+
+                        # Count only non-excluded files and their changes
                         stats["files"] += 1
                         stats["insertions"] += insertions
                         stats["deletions"] += deletions
@@ -1233,10 +1839,36 @@ class GitDataFetcher:
                         # Skip binary files or malformed lines
                         continue
 
+            # Log exclusion statistics if significant
+            if excluded_stats["files"] > 0 or (
+                raw_stats["insertions"] > 0 and stats["insertions"] < raw_stats["insertions"]
+            ):
+                reduction_pct = (
+                    100 * (1 - stats["insertions"] / raw_stats["insertions"])
+                    if raw_stats["insertions"] > 0
+                    else 0
+                )
+                logger.info(
+                    f"Commit {commit.hexsha[:8]}: Excluded {excluded_stats['files']} files, "
+                    f"{excluded_stats['insertions']} insertions, {excluded_stats['deletions']} deletions "
+                    f"({reduction_pct:.1f}% reduction)"
+                )
+
+            # Log if exclusions are configured
+            if self.exclude_paths and raw_stats["files"] > 0:
+                logger.debug(
+                    f"Commit {commit.hexsha[:8]}: Applied {len(self.exclude_paths)} exclusion patterns. "
+                    f"Raw: {raw_stats['files']} files, +{raw_stats['insertions']} -{raw_stats['deletions']}. "
+                    f"Filtered: {stats['files']} files, +{stats['insertions']} -{stats['deletions']}"
+                )
+
         except Exception as e:
             # Log the error for debugging but don't crash
             logger.warning(f"Error calculating commit stats for {commit.hexsha[:8]}: {e}")
 
+        # Return both raw and filtered stats
+        stats["raw_insertions"] = raw_stats["insertions"]
+        stats["raw_deletions"] = raw_stats["deletions"]
         return stats
 
     def _store_day_commits_incremental(
@@ -1266,8 +1898,16 @@ class GitDataFetcher:
                     "branch": commit.get("branch", "main"),
                     "is_merge": commit.get("is_merge", False),
                     "files_changed_count": commit.get("files_changed_count", 0),
-                    "insertions": commit.get("lines_added", 0),
-                    "deletions": commit.get("lines_deleted", 0),
+                    # Store raw unfiltered values
+                    "insertions": commit.get("raw_insertions", commit.get("lines_added", 0)),
+                    "deletions": commit.get("raw_deletions", commit.get("lines_deleted", 0)),
+                    # Store filtered values
+                    "filtered_insertions": commit.get(
+                        "filtered_insertions", commit.get("lines_added", 0)
+                    ),
+                    "filtered_deletions": commit.get(
+                        "filtered_deletions", commit.get("lines_deleted", 0)
+                    ),
                     "story_points": commit.get("story_points"),
                     "ticket_references": commit.get("ticket_references", []),
                 }
@@ -1283,3 +1923,297 @@ class GitDataFetcher:
         except Exception as e:
             # Log error but don't fail - commits will be stored again in batch at the end
             logger.warning(f"Failed to incrementally store commits for {date_str}: {e}")
+
+    def process_repositories_parallel(
+        self,
+        repositories: list[dict],
+        weeks_back: int = 4,
+        jira_integration: Optional[JIRAIntegration] = None,
+        start_date: Optional[datetime] = None,
+        end_date: Optional[datetime] = None,
+        max_workers: int = 3,
+    ) -> dict[str, Any]:
+        """Process multiple repositories in parallel with proper timeout protection.
+
+        Args:
+            repositories: List of repository configurations
+            weeks_back: Number of weeks to analyze
+            jira_integration: Optional JIRA integration for ticket data
+            start_date: Optional explicit start date
+            end_date: Optional explicit end date
+            max_workers: Maximum number of parallel workers
+
+        Returns:
+            Dictionary containing processing results and statistics
+        """
+        logger.info(
+            f"🚀 Starting parallel processing of {len(repositories)} repositories with {max_workers} workers"
+        )
+
+        # Initialize statistics
+        self.processing_stats = {
+            "total": len(repositories),
+            "processed": 0,
+            "success": 0,
+            "failed": 0,
+            "timeout": 0,
+            "repositories": {},
+        }
+
+        # Get progress service for updates
+        progress = get_progress_service()
+
+        # Start heartbeat logger for monitoring
+        with HeartbeatLogger(interval=5):
+            results = {}
+
+            # Use ThreadPoolExecutor for parallel processing
+            with ThreadPoolExecutor(max_workers=max_workers) as executor:
+                # Submit all repository processing tasks
+                future_to_repo = {}
+
+                for repo_config in repositories:
+                    repo_path = Path(repo_config.get("path", ""))
+                    project_key = repo_config.get("project_key", repo_path.name)
+                    branch_patterns = repo_config.get("branch_patterns")
+
+                    # Submit task with timeout wrapper
+                    future = executor.submit(
+                        self._process_repository_with_timeout,
+                        repo_path,
+                        project_key,
+                        weeks_back,
+                        branch_patterns,
+                        jira_integration,
+                        start_date,
+                        end_date,
+                    )
+                    future_to_repo[future] = {
+                        "path": repo_path,
+                        "project_key": project_key,
+                        "start_time": time.time(),
+                    }
+
+                    logger.info(f"📋 Submitted {project_key} for processing")
+
+                # Process results as they complete
+                for future in as_completed(future_to_repo):
+                    repo_info = future_to_repo[future]
+                    project_key = repo_info["project_key"]
+                    elapsed_time = time.time() - repo_info["start_time"]
+
+                    try:
+                        result = future.result(timeout=5)  # Short timeout to get result
+
+                        if result:
+                            self.processing_stats["success"] += 1
+                            self.processing_stats["repositories"][project_key] = {
+                                "status": "success",
+                                "elapsed_time": elapsed_time,
+                                "commits": result.get("stats", {}).get("total_commits", 0),
+                                "tickets": result.get("stats", {}).get("unique_tickets", 0),
+                            }
+                            results[project_key] = result
+
+                            logger.info(
+                                f"✅ {project_key}: Successfully processed "
+                                f"{result['stats']['total_commits']} commits in {elapsed_time:.1f}s"
+                            )
+
+                            # Update progress
+                            if hasattr(progress, "finish_repository"):
+                                # Check if progress adapter supports stats parameter
+                                if hasattr(progress, "update_stats"):
+                                    progress.update_stats(
+                                        processed=self.processing_stats["processed"],
+                                        success=self.processing_stats["success"],
+                                        failed=self.processing_stats["failed"],
+                                        timeout=self.processing_stats["timeout"],
+                                        total=self.processing_stats["total"],
+                                    )
+                                    progress.finish_repository(project_key, success=True)
+                                else:
+                                    progress.finish_repository(project_key, success=True)
+                        else:
+                            self.processing_stats["failed"] += 1
+                            self.processing_stats["repositories"][project_key] = {
+                                "status": "failed",
+                                "elapsed_time": elapsed_time,
+                                "error": "Processing returned no result",
+                            }
+
+                            logger.error(
+                                f"❌ {project_key}: Processing failed after {elapsed_time:.1f}s"
+                            )
+
+                            # Update progress
+                            if hasattr(progress, "finish_repository"):
+                                # Check if progress adapter supports stats parameter
+                                if hasattr(progress, "update_stats"):
+                                    progress.update_stats(
+                                        processed=self.processing_stats["processed"],
+                                        success=self.processing_stats["success"],
+                                        failed=self.processing_stats["failed"],
+                                        timeout=self.processing_stats["timeout"],
+                                        total=self.processing_stats["total"],
+                                    )
+                                    progress.finish_repository(
+                                        project_key,
+                                        success=False,
+                                        error_message="Processing failed",
+                                    )
+                                else:
+                                    progress.finish_repository(
+                                        project_key,
+                                        success=False,
+                                        error_message="Processing failed",
+                                    )
+
+                    except GitOperationTimeout:
+                        self.processing_stats["timeout"] += 1
+                        self.processing_stats["repositories"][project_key] = {
+                            "status": "timeout",
+                            "elapsed_time": elapsed_time,
+                            "error": "Operation timed out",
+                        }
+
+                        logger.error(f"⏱️ {project_key}: Timed out after {elapsed_time:.1f}s")
+
+                        # Update progress
+                        if hasattr(progress, "finish_repository"):
+                            # Check if progress adapter supports stats parameter
+                            if hasattr(progress, "update_stats"):
+                                progress.update_stats(
+                                    processed=self.processing_stats["processed"],
+                                    success=self.processing_stats["success"],
+                                    failed=self.processing_stats["failed"],
+                                    timeout=self.processing_stats["timeout"],
+                                    total=self.processing_stats["total"],
+                                )
+                                progress.finish_repository(
+                                    project_key, success=False, error_message="Timeout"
+                                )
+                            else:
+                                progress.finish_repository(
+                                    project_key, success=False, error_message="Timeout"
+                                )
+
+                    except Exception as e:
+                        self.processing_stats["failed"] += 1
+                        self.processing_stats["repositories"][project_key] = {
+                            "status": "failed",
+                            "elapsed_time": elapsed_time,
+                            "error": str(e),
+                        }
+
+                        logger.error(f"❌ {project_key}: Error after {elapsed_time:.1f}s - {e}")
+
+                        # Update progress
+                        if hasattr(progress, "finish_repository"):
+                            # Check if progress adapter supports stats parameter
+                            if hasattr(progress, "update_stats"):
+                                progress.update_stats(
+                                    processed=self.processing_stats["processed"],
+                                    success=self.processing_stats["success"],
+                                    failed=self.processing_stats["failed"],
+                                    timeout=self.processing_stats["timeout"],
+                                    total=self.processing_stats["total"],
+                                )
+                                progress.finish_repository(
+                                    project_key, success=False, error_message=str(e)
+                                )
+                            else:
+                                progress.finish_repository(
+                                    project_key, success=False, error_message=str(e)
+                                )
+
+                    finally:
+                        # Update processed counter BEFORE logging and progress updates
+                        self.processing_stats["processed"] += 1
+
+                        # Update progress service with actual processing stats
+                        if hasattr(progress, "update_stats"):
+                            progress.update_stats(
+                                processed=self.processing_stats["processed"],
+                                success=self.processing_stats["success"],
+                                failed=self.processing_stats["failed"],
+                                timeout=self.processing_stats["timeout"],
+                                total=self.processing_stats["total"],
+                            )
+
+                        # Log progress
+                        logger.info(
+                            f"📊 Progress: {self.processing_stats['processed']}/{self.processing_stats['total']} repositories "
+                            f"(✅ {self.processing_stats['success']} | ❌ {self.processing_stats['failed']} | ⏱️ {self.processing_stats['timeout']})"
+                        )
+
+        # Final summary
+        logger.info("=" * 60)
+        logger.info("📈 PARALLEL PROCESSING SUMMARY")
+        logger.info(f"   Total repositories: {self.processing_stats['total']}")
+        logger.info(f"   Successfully processed: {self.processing_stats['success']}")
+        logger.info(f"   Failed: {self.processing_stats['failed']}")
+        logger.info(f"   Timed out: {self.processing_stats['timeout']}")
+        logger.info("=" * 60)
+
+        return {"results": results, "statistics": self.processing_stats}
+
+    def _process_repository_with_timeout(
+        self,
+        repo_path: Path,
+        project_key: str,
+        weeks_back: int = 4,
+        branch_patterns: Optional[list[str]] = None,
+        jira_integration: Optional[JIRAIntegration] = None,
+        start_date: Optional[datetime] = None,
+        end_date: Optional[datetime] = None,
+        timeout_per_operation: int = 30,
+    ) -> Optional[dict[str, Any]]:
+        """Process a single repository with comprehensive timeout protection.
+
+        Args:
+            repo_path: Path to the repository
+            project_key: Project identifier
+            weeks_back: Number of weeks to analyze
+            branch_patterns: Branch patterns to include
+            jira_integration: JIRA integration for ticket data
+            start_date: Optional explicit start date
+            end_date: Optional explicit end date
+            timeout_per_operation: Timeout for individual git operations
+
+        Returns:
+            Repository processing results or None if failed
+        """
+        try:
+            # Track this repository in progress
+            progress = get_progress_service()
+            if hasattr(progress, "start_repository"):
+                progress.start_repository(project_key, 0)
+
+            logger.info(f"🔍 Processing repository: {project_key} at {repo_path}")
+
+            # Use the regular fetch method but with timeout wrapper active
+            with self.git_wrapper.operation_tracker("fetch_repository_data", repo_path):
+                result = self.fetch_repository_data(
+                    repo_path=repo_path,
+                    project_key=project_key,
+                    weeks_back=weeks_back,
+                    branch_patterns=branch_patterns,
+                    jira_integration=jira_integration,
+                    progress_callback=None,  # We handle progress at a higher level
+                    start_date=start_date,
+                    end_date=end_date,
+                )
+
+                return result
+
+        except GitOperationTimeout as e:
+            logger.error(f"⏱️ Repository {project_key} processing timed out: {e}")
+            raise
+
+        except Exception as e:
+            logger.error(f"❌ Error processing repository {project_key}: {e}")
+            import traceback
+
+            logger.debug(f"Full traceback: {traceback.format_exc()}")
+            return None