Merge pull request #1107 from afjcjsbx/fix/deny-reading-binary-files

fix(tool) prevent read huge files in tool

pkg/agent/instance.go

@@ -70,7 +70,8 @@ func NewAgentInstance(
 	toolsRegistry := tools.NewToolRegistry()
 
 	if cfg.Tools.IsToolEnabled("read_file") {
-		toolsRegistry.Register(tools.NewReadFileTool(workspace, readRestrict, allowReadPaths))
+		maxReadFileSize := cfg.Tools.ReadFile.MaxReadFileSize
+		toolsRegistry.Register(tools.NewReadFileTool(workspace, readRestrict, maxReadFileSize, allowReadPaths))
 	}
 	if cfg.Tools.IsToolEnabled("write_file") {
 		toolsRegistry.Register(tools.NewWriteFileTool(workspace, restrict, allowWritePaths))

pkg/config/config.go

@@ -662,6 +662,11 @@ type MediaCleanupConfig struct {
 	Interval   int `                                    env:"PICOCLAW_MEDIA_CLEANUP_INTERVAL" json:"interval_minutes"`
 }
 
+type ReadFileToolConfig struct {
+	Enabled         bool `json:"enabled"`
+	MaxReadFileSize int  `json:"max_read_file_size"`
+}
+
 type ToolsConfig struct {
 	AllowReadPaths  []string           `json:"allow_read_paths"  env:"PICOCLAW_TOOLS_ALLOW_READ_PATHS"`
 	AllowWritePaths []string           `json:"allow_write_paths" env:"PICOCLAW_TOOLS_ALLOW_WRITE_PATHS"`
@@ -678,7 +683,7 @@ type ToolsConfig struct {
 	InstallSkill    ToolConfig         `json:"install_skill"                                            envPrefix:"PICOCLAW_TOOLS_INSTALL_SKILL_"`
 	ListDir         ToolConfig         `json:"list_dir"                                                 envPrefix:"PICOCLAW_TOOLS_LIST_DIR_"`
 	Message         ToolConfig         `json:"message"                                                  envPrefix:"PICOCLAW_TOOLS_MESSAGE_"`
-	ReadFile        ToolConfig         `json:"read_file"                                                envPrefix:"PICOCLAW_TOOLS_READ_FILE_"`
+	ReadFile        ReadFileToolConfig `json:"read_file"                                                envPrefix:"PICOCLAW_TOOLS_READ_FILE_"`
 	SendFile        ToolConfig         `json:"send_file"                                                envPrefix:"PICOCLAW_TOOLS_SEND_FILE_"`
 	Spawn           ToolConfig         `json:"spawn"                                                    envPrefix:"PICOCLAW_TOOLS_SPAWN_"`
 	SPI             ToolConfig         `json:"spi"                                                      envPrefix:"PICOCLAW_TOOLS_SPI_"`

pkg/config/defaults.go

@@ -466,8 +466,9 @@ func DefaultConfig() *Config {
 			Message: ToolConfig{
 				Enabled: true,
 			},
-			ReadFile: ToolConfig{
+			ReadFile: ReadFileToolConfig{
 				Enabled:         true,
+				MaxReadFileSize: 64 * 1024, // 64KB
 			},
 			Spawn: ToolConfig{
 				Enabled: true,

pkg/tools/filesystem.go

@@ -2,17 +2,24 @@ package tools
 
 import (
 	"context"
+	"errors"
 	"fmt"
+	"io"
 	"io/fs"
+	"math"
 	"os"
 	"path/filepath"
 	"regexp"
+	"strconv"
 	"strings"
 	"time"
 
 	"github.com/sipeed/picoclaw/pkg/fileutil"
+	"github.com/sipeed/picoclaw/pkg/logger"
 )
 
+const MaxReadFileSize = 64 * 1024 // 64KB limit to avoid context overflow
+
 // validatePath ensures the given path is within the workspace if restrict is true.
 func validatePath(path, workspace string, restrict bool) (string, error) {
 	if workspace == "" {
@@ -86,14 +93,29 @@ func isWithinWorkspace(candidate, workspace string) bool {
 
 type ReadFileTool struct {
 	fs      fileSystem
+	maxSize int64
 }
 
-func NewReadFileTool(workspace string, restrict bool, allowPaths ...[]*regexp.Regexp) *ReadFileTool {
+func NewReadFileTool(
+	workspace string,
+	restrict bool,
+	maxReadFileSize int,
+	allowPaths ...[]*regexp.Regexp,
+) *ReadFileTool {
 	var patterns []*regexp.Regexp
 	if len(allowPaths) > 0 {
 		patterns = allowPaths[0]
 	}
-	return &ReadFileTool{fs: buildFs(workspace, restrict, patterns)}
+
+	maxSize := int64(maxReadFileSize)
+	if maxSize <= 0 {
+		maxSize = MaxReadFileSize
+	}
+
+	return &ReadFileTool{
+		fs:      buildFs(workspace, restrict, patterns),
+		maxSize: maxSize,
+	}
 }
 
 func (t *ReadFileTool) Name() string {
@@ -101,7 +123,7 @@ func (t *ReadFileTool) Name() string {
 }
 
 func (t *ReadFileTool) Description() string {
-	return "Read the contents of a file"
+	return "Read the contents of a file. Supports pagination via `offset` and `length`."
 }
 
 func (t *ReadFileTool) Parameters() map[string]any {
@@ -110,7 +132,17 @@ func (t *ReadFileTool) Parameters() map[string]any {
 		"properties": map[string]any{
 			"path": map[string]any{
 				"type":        "string",
-				"description": "Path to the file to read",
+				"description": "Path to the file to read.",
+			},
+			"offset": map[string]any{
+				"type":        "integer",
+				"description": "Byte offset to start reading from.",
+				"default":     0,
+			},
+			"length": map[string]any{
+				"type":        "integer",
+				"description": "Maximum number of bytes to read.",
+				"default":     t.maxSize,
 			},
 		},
 		"required": []string{"path"},
@@ -123,11 +155,171 @@ func (t *ReadFileTool) Execute(ctx context.Context, args map[string]any) *ToolRe
 		return ErrorResult("path is required")
 	}
 
-	content, err := t.fs.ReadFile(path)
+	// offset (optional, default 0)
+	offset, err := getInt64Arg(args, "offset", 0)
 	if err != nil {
 		return ErrorResult(err.Error())
 	}
-	return NewToolResult(string(content))
+	if offset < 0 {
+		return ErrorResult("offset must be >= 0")
+	}
+
+	// length (optional, capped at MaxReadFileSize)
+	length, err := getInt64Arg(args, "length", t.maxSize)
+	if err != nil {
+		return ErrorResult(err.Error())
+	}
+	if length <= 0 {
+		return ErrorResult("length must be > 0")
+	}
+	if length > t.maxSize {
+		length = t.maxSize
+	}
+
+	file, err := t.fs.Open(path)
+	if err != nil {
+		return ErrorResult(err.Error())
+	}
+	defer file.Close()
+
+	// measure total size
+	totalSize := int64(-1) // -1 means unknown
+	if info, statErr := file.Stat(); statErr == nil {
+		totalSize = info.Size()
+	}
+
+	// sniff the first 512 bytes to detect binary content before loading
+	// it into the LLM context. Seeking back to 0 afterwards restores state.
+	sniff := make([]byte, 512)
+	sniffN, _ := file.Read(sniff)
+
+	// Reset read position to beginning before applying the caller's offset.
+	if seeker, ok := file.(io.Seeker); ok {
+		_, err = seeker.Seek(0, io.SeekStart)
+		if err != nil {
+			return ErrorResult(fmt.Sprintf("failed to reset file position after sniff: %v", err))
+		}
+	} else {
+		// Non-seekable: we consumed sniffN bytes above; account for them when
+		// discarding to reach the requested offset below.
+		// If offset < sniffN the data we already read covers it, which we
+		// cannot replay on a non-seekable stream — return a clear error.
+		if offset < int64(sniffN) && offset > 0 {
+			return ErrorResult(
+				"non-seekable file: cannot seek to an offset within the first 512 bytes after binary detection",
+			)
+		}
+	}
+
+	// Seek to the requested offset.
+	if seeker, ok := file.(io.Seeker); ok {
+		_, err = seeker.Seek(offset, io.SeekStart)
+		if err != nil {
+			return ErrorResult(fmt.Sprintf("failed to seek to offset %d: %v", offset, err))
+		}
+	} else if offset > 0 {
+		// Fallback for non-seekable streams: discard leading bytes.
+		// sniffN bytes were already consumed above, so subtract them.
+		remaining := offset - int64(sniffN)
+		if remaining > 0 {
+			_, err = io.CopyN(io.Discard, file, remaining)
+			if err != nil {
+				return ErrorResult(fmt.Sprintf("failed to advance to offset %d: %v", offset, err))
+			}
+		}
+	}
+
+	// read length+1 bytes to reliably detect whether more content exists
+	// without relying on totalSize (which may be -1 for non-seekable streams).
+	// This avoids the false-positive TRUNCATED message on the last page.
+	probe := make([]byte, length+1)
+	n, err := io.ReadFull(file, probe)
+	// FIX: io.ReadFull returns io.ErrUnexpectedEOF for partial reads (0 < n < len),
+	// and io.EOF only when n == 0. Both are normal terminal conditions — only
+	// other errors are genuine failures.
+	if err != nil && err != io.EOF && !errors.Is(err, io.ErrUnexpectedEOF) {
+		return ErrorResult(fmt.Sprintf("failed to read file content: %v", err))
+	}
+
+	// hasMore is true only when we actually got the extra probe byte.
+	hasMore := int64(n) > length
+	data := probe[:min(int64(n), length)]
+
+	if len(data) == 0 {
+		return NewToolResult("[END OF FILE - no content at this offset]")
+	}
+
+	// Build metadata header.
+	// use filepath.Base(path) instead of the raw path to avoid leaking
+	// internal filesystem structure into the LLM context.
+	readEnd := offset + int64(len(data))
+	// use ASCII hyphen-minus instead of en-dash (U+2013) to keep the
+	// header parseable by downstream tools and log processors.
+	readRange := fmt.Sprintf("bytes %d-%d", offset, readEnd-1)
+
+	displayPath := filepath.Base(path)
+	var header string
+	if totalSize >= 0 {
+		header = fmt.Sprintf(
+			"[file: %s | total: %d bytes | read: %s]",
+			displayPath, totalSize, readRange,
+		)
+	} else {
+		header = fmt.Sprintf(
+			"[file: %s | read: %s | total size unknown]",
+			displayPath, readRange,
+		)
+	}
+
+	if hasMore {
+		header += fmt.Sprintf(
+			"\n[TRUNCATED - file has more content. Call read_file again with offset=%d to continue.]",
+			readEnd,
+		)
+	} else {
+		header += "\n[END OF FILE - no further content.]"
+	}
+
+	logger.DebugCF("tool", "ReadFileTool execution completed successfully",
+		map[string]any{
+			"path":       path,
+			"bytes_read": len(data),
+			"has_more":   hasMore,
+		})
+
+	return NewToolResult(header + "\n\n" + string(data))
+}
+
+// getInt64Arg extracts an integer argument from the args map, returning the
+// provided default if the key is absent.
+func getInt64Arg(args map[string]any, key string, defaultVal int64) (int64, error) {
+	raw, exists := args[key]
+	if !exists {
+		return defaultVal, nil
+	}
+
+	switch v := raw.(type) {
+	case float64:
+		if v != math.Trunc(v) {
+			return 0, fmt.Errorf("%s must be an integer, got float %v", key, v)
+		}
+		if v > math.MaxInt64 || v < math.MinInt64 {
+			return 0, fmt.Errorf("%s value %v overflows int64", key, v)
+		}
+		return int64(v), nil
+	case int:
+		return int64(v), nil
+	case int64:
+		return v, nil
+	case string:
+		parsed, err := strconv.ParseInt(v, 10, 64)
+		if err != nil {
+			return 0, fmt.Errorf("invalid integer format for %s parameter: %w", key, err)
+		}
+		return parsed, nil
+	default:
+		return 0, fmt.Errorf("unsupported type %T for %s parameter", raw, key)
+	}
 }
 
 type WriteFileTool struct {
@@ -249,6 +441,7 @@ type fileSystem interface {
 	ReadFile(path string) ([]byte, error)
 	WriteFile(path string, data []byte) error
 	ReadDir(path string) ([]os.DirEntry, error)
+	Open(path string) (fs.File, error)
 }
 
 // hostFs is an unrestricted fileReadWriter that operates directly on the host filesystem.
@@ -278,6 +471,20 @@ func (h *hostFs) WriteFile(path string, data []byte) error {
 	return fileutil.WriteFileAtomic(path, data, 0o600)
 }
 
+func (h *hostFs) Open(path string) (fs.File, error) {
+	f, err := os.Open(path)
+	if err != nil {
+		if os.IsNotExist(err) {
+			return nil, fmt.Errorf("failed to open file: file not found: %w", err)
+		}
+		if os.IsPermission(err) {
+			return nil, fmt.Errorf("failed to open file: access denied: %w", err)
+		}
+		return nil, fmt.Errorf("failed to open file: %w", err)
+	}
+	return f, nil
+}
+
 // sandboxFs is a sandboxed fileSystem that operates within a strictly defined workspace using os.Root.
 type sandboxFs struct {
 	workspace string
@@ -389,6 +596,26 @@ func (r *sandboxFs) ReadDir(path string) ([]os.DirEntry, error) {
 	return entries, err
 }
 
+func (r *sandboxFs) Open(path string) (fs.File, error) {
+	var f fs.File
+	err := r.execute(path, func(root *os.Root, relPath string) error {
+		file, err := root.Open(relPath)
+		if err != nil {
+			if os.IsNotExist(err) {
+				return fmt.Errorf("failed to open file: file not found: %w", err)
+			}
+			if os.IsPermission(err) || strings.Contains(err.Error(), "escapes from parent") ||
+				strings.Contains(err.Error(), "permission denied") {
+				return fmt.Errorf("failed to open file: access denied: %w", err)
+			}
+			return fmt.Errorf("failed to open file: %w", err)
+		}
+		f = file
+		return nil
+	})
+	return f, err
+}
+
 // whitelistFs wraps a sandboxFs and allows access to specific paths outside
 // the workspace when they match any of the provided patterns.
 type whitelistFs struct {
@@ -427,6 +654,13 @@ func (w *whitelistFs) ReadDir(path string) ([]os.DirEntry, error) {
 	return w.sandbox.ReadDir(path)
 }
 
+func (w *whitelistFs) Open(path string) (fs.File, error) {
+	if w.matches(path) {
+		return w.host.Open(path)
+	}
+	return w.sandbox.Open(path)
+}
+
 // buildFs returns the appropriate fileSystem implementation based on restriction
 // settings and optional path whitelist patterns.
 func buildFs(workspace string, restrict bool, patterns []*regexp.Regexp) fileSystem {

pkg/tools/filesystem_test.go

@@ -18,7 +18,7 @@ func TestFilesystemTool_ReadFile_Success(t *testing.T) {
 	testFile := filepath.Join(tmpDir, "test.txt")
 	os.WriteFile(testFile, []byte("test content"), 0o644)
 
-	tool := NewReadFileTool("", false)
+	tool := NewReadFileTool("", false, MaxReadFileSize)
 	ctx := context.Background()
 	args := map[string]any{
 		"path": testFile,
@@ -45,7 +45,7 @@ func TestFilesystemTool_ReadFile_Success(t *testing.T) {
 
 // TestFilesystemTool_ReadFile_NotFound verifies error handling for missing file
 func TestFilesystemTool_ReadFile_NotFound(t *testing.T) {
-	tool := NewReadFileTool("", false)
+	tool := NewReadFileTool("", false, MaxReadFileSize)
 	ctx := context.Background()
 	args := map[string]any{
 		"path": "/nonexistent_file_12345.txt",
@@ -59,7 +59,7 @@ func TestFilesystemTool_ReadFile_NotFound(t *testing.T) {
 	}
 
 	// Should contain error message
-	if !strings.Contains(result.ForLLM, "failed to read") && !strings.Contains(result.ForUser, "failed to read") {
+	if !strings.Contains(result.ForLLM, "failed to open file") && !strings.Contains(result.ForUser, "failed to read") {
 		t.Errorf("Expected error message, got ForLLM: %s, ForUser: %s", result.ForLLM, result.ForUser)
 	}
 }
@@ -271,7 +271,7 @@ func TestFilesystemTool_ReadFile_RejectsSymlinkEscape(t *testing.T) {
 		t.Skipf("symlink not supported in this environment: %v", err)
 	}
 
-	tool := NewReadFileTool(workspace, true)
+	tool := NewReadFileTool(workspace, true, MaxReadFileSize)
 	result := tool.Execute(context.Background(), map[string]any{
 		"path": link,
 	})
@@ -289,7 +289,7 @@ func TestFilesystemTool_ReadFile_RejectsSymlinkEscape(t *testing.T) {
 }
 
 func TestFilesystemTool_EmptyWorkspace_AccessDenied(t *testing.T) {
-	tool := NewReadFileTool("", true) // restrict=true but workspace=""
+	tool := NewReadFileTool("", true, MaxReadFileSize) // restrict=true but workspace=""
 
 	// Try to read a sensitive file (simulated by a temp file outside workspace)
 	tmpDir := t.TempDir()
@@ -499,7 +499,7 @@ func TestWhitelistFs_AllowsMatchingPaths(t *testing.T) {
 	// Pattern allows access to the outsideDir.
 	patterns := []*regexp.Regexp{regexp.MustCompile(`^` + regexp.QuoteMeta(outsideDir))}
 
-	tool := NewReadFileTool(workspace, true, patterns)
+	tool := NewReadFileTool(workspace, true, MaxReadFileSize, patterns)
 
 	// Read from whitelisted path should succeed.
 	result := tool.Execute(context.Background(), map[string]any{"path": outsideFile})
@@ -520,3 +520,127 @@ func TestWhitelistFs_AllowsMatchingPaths(t *testing.T) {
 		t.Errorf("expected non-whitelisted path to be blocked, got: %s", result.ForLLM)
 	}
 }
+
+// TestReadFileTool_ChunkedReading verifies the pagination logic of the tool
+// by reading a file in multiple chunks using 'offset' and 'length'.
+func TestReadFileTool_ChunkedReading(t *testing.T) {
+	tmpDir := t.TempDir()
+	testFile := filepath.Join(tmpDir, "pagination_test.txt")
+
+	// Create a test file with exactly 26 bytes of content
+	fullContent := "abcdefghijklmnopqrstuvwxyz"
+	err := os.WriteFile(testFile, []byte(fullContent), 0o644)
+	if err != nil {
+		t.Fatalf("Failed to write test file: %v", err)
+	}
+
+	tool := NewReadFileTool(tmpDir, false, MaxReadFileSize)
+	ctx := context.Background()
+
+	// --- Step 1: Read the first chunk (10 bytes) ---
+	args1 := map[string]any{
+		"path":   testFile,
+		"offset": 0,
+		"length": 10,
+	}
+	result1 := tool.Execute(ctx, args1)
+
+	if result1.IsError {
+		t.Fatalf("Chunk 1 failed: %s", result1.ForLLM)
+	}
+
+	// Expect the first 10 characters
+	if !strings.Contains(result1.ForLLM, "abcdefghij") {
+		t.Errorf("Chunk 1 should contain 'abcdefghij', got: %s", result1.ForLLM)
+	}
+	// Expect the header to indicate the file is truncated
+	if !strings.Contains(result1.ForLLM, "[TRUNCATED") {
+		t.Errorf("Chunk 1 header should indicate truncation, got: %s", result1.ForLLM)
+	}
+	// Expect the header to suggest the next offset (10)
+	if !strings.Contains(result1.ForLLM, "offset=10") {
+		t.Errorf("Chunk 1 header should suggest next offset=10, got: %s", result1.ForLLM)
+	}
+
+	// Step 2: Read the second chunk (10 bytes) ---
+	args2 := map[string]any{
+		"path":   testFile,
+		"offset": 10,
+		"length": 10,
+	}
+	result2 := tool.Execute(ctx, args2)
+
+	if result2.IsError {
+		t.Fatalf("Chunk 2 failed: %s", result2.ForLLM)
+	}
+
+	// Expect the next 10 characters
+	if !strings.Contains(result2.ForLLM, "klmnopqrst") {
+		t.Errorf("Chunk 2 should contain 'klmnopqrst', got: %s", result2.ForLLM)
+	}
+	// Expect the header to suggest the next offset (20)
+	if !strings.Contains(result2.ForLLM, "offset=20") {
+		t.Errorf("Chunk 2 header should suggest next offset=20, got: %s", result2.ForLLM)
+	}
+
+	// Step 3: Read the final chunk (remaining 6 bytes) ---
+	// We ask for 10 bytes, but only 6 are left in the file
+	args3 := map[string]any{
+		"path":   testFile,
+		"offset": 20,
+		"length": 10,
+	}
+	result3 := tool.Execute(ctx, args3)
+
+	if result3.IsError {
+		t.Fatalf("Chunk 3 failed: %s", result3.ForLLM)
+	}
+
+	// Expect the last 6 characters
+	if !strings.Contains(result3.ForLLM, "uvwxyz") {
+		t.Errorf("Chunk 3 should contain 'uvwxyz', got: %s", result3.ForLLM)
+	}
+	// Expect the header to indicate the end of the file
+	if !strings.Contains(result3.ForLLM, "[END OF FILE") {
+		t.Errorf("Chunk 3 header should indicate end of file, got: %s", result3.ForLLM)
+	}
+
+	// Ensure no TRUNCATED message is present in the final chunk
+	if strings.Contains(result3.ForLLM, "[TRUNCATED") {
+		t.Errorf("Chunk 3 header should NOT indicate truncation, got: %s", result3.ForLLM)
+	}
+}
+
+// TestReadFileTool_OffsetBeyondEOF checks the behavior when requesting
+// An offset that exceeds the total file size.
+func TestReadFileTool_OffsetBeyondEOF(t *testing.T) {
+	tmpDir := t.TempDir()
+	testFile := filepath.Join(tmpDir, "short.txt")
+
+	// create a file of only 5 bytes
+	err := os.WriteFile(testFile, []byte("12345"), 0o644)
+	if err != nil {
+		t.Fatalf("Failed to write test file: %v", err)
+	}
+
+	tool := NewReadFileTool(tmpDir, false, MaxReadFileSize)
+	ctx := context.Background()
+
+	args := map[string]any{
+		"path":   testFile,
+		"offset": int64(100), // Offset beyond the end of the file
+	}
+
+	result := tool.Execute(ctx, args)
+
+	// It should not be classified as a tool execution error
+	if result.IsError {
+		t.Errorf("A mistake was not expected, obtained IsError=true: %s", result.ForLLM)
+	}
+
+	// Must return EXACTLY the string provided in the code
+	expectedMsg := "[END OF FILE - no content at this offset]"
+	if result.ForLLM != expectedMsg {
+		t.Errorf("The message %q was expected, obtained: %q", expectedMsg, result.ForLLM)
+	}
+}