refactor(agent-smith): remove unused filesystem scanning configuration options

- Remove WorkspaceDepth: No longer needed with signature-driven scanning
- Remove MaxFilesPerScan: File count naturally limited by signature patterns
- Keep MaxFileSize: Still useful to avoid scanning overly large files
- Update example configuration to reflect simplified options
- Update all tests to remove references to removed fields
- Cleaner, more focused configuration for signature-driven approach

Co-authored-by: Ona <[email protected]>

Author: kylos101

components/ee/agent-smith/example-config.json

@@ -57,7 +57,6 @@
         "enabled": true,
         "scanInterval": "5m",
         "maxFileSize": 1024,
-        "workspaceDepth": 3,
-        "maxFilesPerScan": 200
+        "workingArea": "/var/gitpod/workspaces"
     }
 }

components/ee/agent-smith/pkg/agent/agent.go

@@ -143,12 +143,10 @@ func NewAgentSmith(cfg config.Config) (*Smith, error) {
 	if cfg.FilesystemScanning != nil && cfg.FilesystemScanning.Enabled {
 		// Create filesystem detector config
 		fsConfig := detector.FilesystemScanningConfig{
-			Enabled:         cfg.FilesystemScanning.Enabled,
-			ScanInterval:    cfg.FilesystemScanning.ScanInterval,
-			MaxFileSize:     cfg.FilesystemScanning.MaxFileSize,
-			WorkspaceDepth:  cfg.FilesystemScanning.WorkspaceDepth,
-			MaxFilesPerScan: cfg.FilesystemScanning.MaxFilesPerScan,
-			WorkingArea:     cfg.FilesystemScanning.WorkingArea,
+			Enabled:      cfg.FilesystemScanning.Enabled,
+			ScanInterval: cfg.FilesystemScanning.ScanInterval,
+			MaxFileSize:  cfg.FilesystemScanning.MaxFileSize,
+			WorkingArea:  cfg.FilesystemScanning.WorkingArea,
 		}
 
 		filesystemDetec, err = detector.NewFilesystemDetector(fsConfig)

components/ee/agent-smith/pkg/config/config.go

@@ -193,12 +193,10 @@ type WorkspaceManagerConfig struct {
 
 // FilesystemScanning configures filesystem signature scanning
 type FilesystemScanning struct {
-	Enabled         bool          `json:"enabled"`
-	ScanInterval    time.Duration `json:"scanInterval"`
-	MaxFileSize     int64         `json:"maxFileSize"`
-	WorkspaceDepth  int           `json:"workspaceDepth"`
-	MaxFilesPerScan int           `json:"maxFilesPerScan"`
-	WorkingArea     string        `json:"workingArea"`
+	Enabled      bool          `json:"enabled"`
+	ScanInterval time.Duration `json:"scanInterval"`
+	MaxFileSize  int64         `json:"maxFileSize"`
+	WorkingArea  string        `json:"workingArea"`
 }
 
 // Slackwebhooks holds slack notification configuration for different levels of penalty severity

components/ee/agent-smith/pkg/detector/filesystem.go

@@ -55,12 +55,10 @@ type FilesystemDetector struct {
 
 // FilesystemScanningConfig holds configuration for filesystem scanning
 type FilesystemScanningConfig struct {
-	Enabled         bool
-	ScanInterval    time.Duration
-	MaxFileSize     int64
-	WorkspaceDepth  int
-	MaxFilesPerScan int
-	WorkingArea     string
+	Enabled      bool
+	ScanInterval time.Duration
+	MaxFileSize  int64
+	WorkingArea  string
 }
 
 var _ FileDetector = &FilesystemDetector{}
@@ -78,12 +76,6 @@ func NewFilesystemDetector(config FilesystemScanningConfig) (*FilesystemDetector
 	if config.MaxFileSize == 0 {
 		config.MaxFileSize = 1024 // 1KB default
 	}
-	if config.WorkspaceDepth == 0 {
-		config.WorkspaceDepth = 3
-	}
-	if config.MaxFilesPerScan == 0 {
-		config.MaxFilesPerScan = 200
-	}
 	if config.WorkingArea == "" {
 		return nil, fmt.Errorf("workingArea must be specified")
 	}
@@ -260,8 +252,6 @@ type WorkspaceDirectory struct {
 }
 
 func (det *FilesystemDetector) scanWorkspaceDirectory(wsDir WorkspaceDirectory, signatures []FilesystemSignature, files chan<- File) {
-	fileCount := 0
-
 	// Create a minimal workspace object for this directory
 	workspace := &common.Workspace{
 		InstanceID: wsDir.InstanceID,
@@ -271,23 +261,11 @@ func (det *FilesystemDetector) scanWorkspaceDirectory(wsDir WorkspaceDirectory,
 
 	// For each signature, check if any of its target files exist
 	for _, sig := range signatures {
-		if fileCount >= det.config.MaxFilesPerScan {
-			break
-		}
-
 		for _, pattern := range sig.Filenames {
-			if fileCount >= det.config.MaxFilesPerScan {
-				break
-			}
-
 			// Find files matching the pattern
 			matchingFiles := det.findMatchingFiles(wsDir.Path, pattern)
 
 			for _, filePath := range matchingFiles {
-				if fileCount >= det.config.MaxFilesPerScan {
-					break
-				}
-
 				// Check if file exists and get its info
 				info, err := os.Stat(filePath)
 				if err != nil {
@@ -307,7 +285,6 @@ func (det *FilesystemDetector) scanWorkspaceDirectory(wsDir WorkspaceDirectory,
 
 				det.filesScannedTotal.Inc()
 				det.filesFoundTotal.Inc()
-				fileCount++
 
 				file := File{
 					Path:      filePath,

components/ee/agent-smith/pkg/detector/filesystem_test.go

@@ -26,12 +26,10 @@ func TestFilesystemDetector_Config_Defaults(t *testing.T) {
 				WorkingArea: "/tmp/test-workspaces",
 			},
 			expectedConfig: FilesystemScanningConfig{
-				Enabled:         true,
-				ScanInterval:    5 * time.Minute,
-				MaxFileSize:     1024,
-				WorkspaceDepth:  3,
-				MaxFilesPerScan: 200,
-				WorkingArea:     "/tmp/test-workspaces",
+				Enabled:      true,
+				ScanInterval: 5 * time.Minute,
+				MaxFileSize:  1024,
+				WorkingArea:  "/tmp/test-workspaces",
 			},
 		},
 		{
@@ -43,31 +41,25 @@ func TestFilesystemDetector_Config_Defaults(t *testing.T) {
 				WorkingArea:  "/tmp/test-workspaces",
 			},
 			expectedConfig: FilesystemScanningConfig{
-				Enabled:         true,
-				ScanInterval:    10 * time.Minute,
-				MaxFileSize:     2048,
-				WorkspaceDepth:  3,
-				MaxFilesPerScan: 200,
-				WorkingArea:     "/tmp/test-workspaces",
+				Enabled:      true,
+				ScanInterval: 10 * time.Minute,
+				MaxFileSize:  2048,
+				WorkingArea:  "/tmp/test-workspaces",
 			},
 		},
 		{
 			name: "all custom values",
 			inputConfig: FilesystemScanningConfig{
-				Enabled:         true,
-				ScanInterval:    2 * time.Minute,
-				MaxFileSize:     512,
-				WorkspaceDepth:  2,
-				MaxFilesPerScan: 100,
-				WorkingArea:     "/tmp/test-workspaces",
+				Enabled:      true,
+				ScanInterval: 2 * time.Minute,
+				MaxFileSize:  512,
+				WorkingArea:  "/tmp/test-workspaces",
 			},
 			expectedConfig: FilesystemScanningConfig{
-				Enabled:         true,
-				ScanInterval:    2 * time.Minute,
-				MaxFileSize:     512,
-				WorkspaceDepth:  2,
-				MaxFilesPerScan: 100,
-				WorkingArea:     "/tmp/test-workspaces",
+				Enabled:      true,
+				ScanInterval: 2 * time.Minute,
+				MaxFileSize:  512,
+				WorkingArea:  "/tmp/test-workspaces",
 			},
 		},
 	}
@@ -85,11 +77,8 @@ func TestFilesystemDetector_Config_Defaults(t *testing.T) {
 			if detector.config.MaxFileSize != tt.expectedConfig.MaxFileSize {
 				t.Errorf("MaxFileSize = %v, expected %v", detector.config.MaxFileSize, tt.expectedConfig.MaxFileSize)
 			}
-			if detector.config.WorkspaceDepth != tt.expectedConfig.WorkspaceDepth {
-				t.Errorf("WorkspaceDepth = %v, expected %v", detector.config.WorkspaceDepth, tt.expectedConfig.WorkspaceDepth)
-			}
-			if detector.config.MaxFilesPerScan != tt.expectedConfig.MaxFilesPerScan {
-				t.Errorf("MaxFilesPerScan = %v, expected %v", detector.config.MaxFilesPerScan, tt.expectedConfig.MaxFilesPerScan)
+			if detector.config.WorkingArea != tt.expectedConfig.WorkingArea {
+				t.Errorf("WorkingArea = %v, expected %v", detector.config.WorkingArea, tt.expectedConfig.WorkingArea)
 			}
 		})
 	}