n8n-io/n8n · warning · Error

File too large: ${stat.size} bytes (max ${MAX_FILE_SIZE} byt

Error message

File too large: ${stat.size} bytes (max ${MAX_FILE_SIZE} bytes). Use searchFiles for specific content.

What it means

Thrown by the read_file tool when the target file's size exceeds MAX_FILE_SIZE (1 MB). The guard runs after path resolution but before reading the file content into memory. The message suggests using search_files for specific content rather than loading the whole file.

Source

Thrown at packages/@n8n/computer-use/src/tools/filesystem/read-file.ts:42

});

export const readFileTool: ToolDefinition<typeof inputSchema> = {
	name: 'read_file',
	description:
		'Read a file. Text is returned line-by-line; supported binaries (PNG, JPEG, GIF, WebP, PDF) are returned as base64 content the model can consume directly.',
	inputSchema,
	annotations: { readOnlyHint: true },
	async getAffectedResources({ filePath }, { dir }) {
		return [
			await buildFilesystemResource(dir, filePath, 'filesystemRead', `Read file: ${filePath}`),
		];
	},
	async execute({ filePath, startLine, maxLines }, { dir }) {
		const resolvedPath = await resolveReadablePath(dir, filePath);

		const stat = await fs.stat(resolvedPath);
		if (stat.size > MAX_FILE_SIZE) {
			throw new Error(
				`File too large: ${stat.size} bytes (max ${MAX_FILE_SIZE} bytes). Use searchFiles for specific content.`,
			);
		}

		const fileContent = await fs.readFile(resolvedPath);
		const buffer = Buffer.isBuffer(fileContent) ? fileContent : Buffer.from(fileContent);

		const binaryType = detectSupportedBinaryFile(filePath);
		if (binaryType) {
			return buildBinaryResult(resolvedPath, buffer, binaryType);
		}

		if (isLikelyBinaryContent(buffer)) {
			throw new Error('Unsupported binary file — only PNG, JPEG, GIF, WebP and PDF are readable');
		}

		return buildTextResult(filePath, buffer.toString('utf-8'), startLine, maxLines);
	},

View on GitHub (pinned to 5ac6606e81)

Solutions

1. Use search_files to find specific content with a regex pattern instead of reading the whole file
2. Use list_files to understand the directory structure first, then read only the relevant smaller files
3. If line-specific content is needed, use shell tools (grep, sed) to extract the relevant lines

Example fix

// before (read_file fails on a large log):
await read_file({ filePath: 'logs/app.log' });

// after (search for specific content):
await search_files({ pattern: 'ERROR', glob: 'logs/app.log' });

import * as fs from 'node:fs/promises';
import { MAX_FILE_SIZE } from './constants';

async function canReadFile(filePath: string): Promise<boolean> {
  const stat = await fs.stat(filePath);
  return stat.size <= MAX_FILE_SIZE;
}

// Before calling read_file:
if (!(await canReadFile(resolvedPath))) {
  // Use search_files instead
  await search_files({ pattern: 'keyword', glob: filePath });
}

function isReadFileTooLarge(e: unknown): boolean {
  return e instanceof Error && e.message.startsWith('File too large:') && e.message.includes('Use searchFiles');
}

When it happens

Trigger: Calling read_file on a file larger than 1 MB — a large log file, data export (JSON/CSV), minified JavaScript bundle, or large generated source file.

Common situations: Agent tries to read a large log file for debugging, a large data file for analysis, or a minified production bundle.

Related errors

• File too large: ${stat.size} bytes (max ${MAX_FILE_SIZE} byt
• oldString not found in file: ${filePath}
• Access denied: "${excludedSegment}" is excluded from filesys
• Unsupported binary file — only PNG, JPEG, GIF, WebP and PDF
• Pattern "${pattern}" escapes the base directory

AI-assisted analysis of n8n-io/n8n@5ac6606e81 (2026-08-12). Data as JSON: /api/errors/dee13dee5d6647e7. Report an issue: GitHub.