LibreChat/api/server/services/Files/Code/process.js
Danny Avila 9054ca9c15
Some checks are pending
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Waiting to run
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Waiting to run
Docker Dev Images Build / build (Dockerfile, librechat-dev, node) (push) Waiting to run
Docker Dev Images Build / build (Dockerfile.multi, librechat-dev-api, api-build) (push) Waiting to run
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Waiting to run
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Blocked by required conditions
🆔 fix: Atomic File Dedupe, Bedrock Tokens Fix, and Allowed MIME Types (#11675)
* feat: Add support for Apache Parquet MIME types

- Introduced 'application/x-parquet' to the full MIME types list and code interpreter MIME types list.
- Updated application MIME types regex to include 'x-parquet' and 'vnd.apache.parquet'.
- Added mapping for '.parquet' files to 'application/x-parquet' in code type mapping, enhancing file format support.

* feat: Implement atomic file claiming for code execution outputs

- Added a new `claimCodeFile` function to atomically claim a file_id for code execution outputs, preventing duplicates by using a compound key of filename and conversationId.
- Updated `processCodeOutput` to utilize the new claiming mechanism, ensuring that concurrent calls for the same filename converge on a single record.
- Refactored related tests to validate the new atomic claiming behavior and its impact on file usage tracking and versioning.

* fix: Update image file handling to use cache-busting filepath

- Modified the `processCodeOutput` function to generate a cache-busting filepath for updated image files, improving browser caching behavior.
- Adjusted related tests to reflect the change from versioned filenames to cache-busted filepaths, ensuring accurate validation of image updates.

* fix: Update step handler to prevent undefined content for non-tool call types

- Modified the condition in useStepHandler to ensure that undefined content is only assigned for specific content types, enhancing the robustness of content handling.

* fix: Update bedrockOutputParser to handle maxTokens for adaptive models

- Modified the bedrockOutputParser logic to ensure that maxTokens is not set for adaptive models when neither maxTokens nor maxOutputTokens are provided, improving the handling of adaptive thinking configurations.
- Updated related tests to reflect these changes, ensuring accurate validation of the output for adaptive models.

* chore: Update @librechat/agents to version 3.1.38 in package.json and package-lock.json

* fix: Enhance file claiming and error handling in code processing

- Updated the `processCodeOutput` function to use a consistent file ID for claiming files, preventing duplicates and improving concurrency handling.
- Refactored the `createFileMethods` to include error handling for failed file claims, ensuring robust behavior when claiming files for conversations.
- These changes enhance the reliability of file management in the application.

* fix: Update adaptive thinking test for Opus 4.6 model

- Modified the test for configuring adaptive thinking to reflect that no default maxTokens should be set for the Opus 4.6 model.
- Updated assertions to ensure that maxTokens is undefined, aligning with the expected behavior for adaptive models.
2026-02-07 13:26:18 -05:00

440 lines
14 KiB
JavaScript

const path = require('path');
const { v4 } = require('uuid');
const axios = require('axios');
const { logger } = require('@librechat/data-schemas');
const { getCodeBaseURL } = require('@librechat/agents');
const { logAxiosError, getBasePath } = require('@librechat/api');
const {
Tools,
megabyte,
fileConfig,
FileContext,
FileSources,
imageExtRegex,
inferMimeType,
EToolResources,
EModelEndpoint,
mergeFileConfig,
getEndpointFileConfig,
} = require('librechat-data-provider');
const { filterFilesByAgentAccess } = require('~/server/services/Files/permissions');
const { createFile, getFiles, updateFile, claimCodeFile } = require('~/models');
const { getStrategyFunctions } = require('~/server/services/Files/strategies');
const { convertImage } = require('~/server/services/Files/images/convert');
const { determineFileType } = require('~/server/utils');
/**
* Creates a fallback download URL response when file cannot be processed locally.
* Used when: file exceeds size limit, storage strategy unavailable, or download error occurs.
* @param {Object} params - The parameters.
* @param {string} params.name - The filename.
* @param {string} params.session_id - The code execution session ID.
* @param {string} params.id - The file ID from the code environment.
* @param {string} params.conversationId - The current conversation ID.
* @param {string} params.toolCallId - The tool call ID that generated the file.
* @param {string} params.messageId - The current message ID.
* @param {number} params.expiresAt - Expiration timestamp (24 hours from creation).
* @returns {Object} Fallback response with download URL.
*/
const createDownloadFallback = ({
id,
name,
messageId,
expiresAt,
session_id,
toolCallId,
conversationId,
}) => {
const basePath = getBasePath();
return {
filename: name,
filepath: `${basePath}/api/files/code/download/${session_id}/${id}`,
expiresAt,
conversationId,
toolCallId,
messageId,
};
};
/**
* Process code execution output files - downloads and saves both images and non-image files.
* All files are saved to local storage with fileIdentifier metadata for code env re-upload.
* @param {ServerRequest} params.req - The Express request object.
* @param {string} params.id - The file ID from the code environment.
* @param {string} params.name - The filename.
* @param {string} params.apiKey - The code execution API key.
* @param {string} params.toolCallId - The tool call ID that generated the file.
* @param {string} params.session_id - The code execution session ID.
* @param {string} params.conversationId - The current conversation ID.
* @param {string} params.messageId - The current message ID.
* @returns {Promise<MongoFile & { messageId: string, toolCallId: string } | undefined>} The file metadata or undefined if an error occurs.
*/
const processCodeOutput = async ({
req,
id,
name,
apiKey,
toolCallId,
conversationId,
messageId,
session_id,
}) => {
const appConfig = req.config;
const currentDate = new Date();
const baseURL = getCodeBaseURL();
const fileExt = path.extname(name).toLowerCase();
const isImage = fileExt && imageExtRegex.test(name);
const mergedFileConfig = mergeFileConfig(appConfig.fileConfig);
const endpointFileConfig = getEndpointFileConfig({
fileConfig: mergedFileConfig,
endpoint: EModelEndpoint.agents,
});
const fileSizeLimit = endpointFileConfig.fileSizeLimit ?? mergedFileConfig.serverFileSizeLimit;
try {
const formattedDate = currentDate.toISOString();
const response = await axios({
method: 'get',
url: `${baseURL}/download/${session_id}/${id}`,
responseType: 'arraybuffer',
headers: {
'User-Agent': 'LibreChat/1.0',
'X-API-Key': apiKey,
},
timeout: 15000,
});
const buffer = Buffer.from(response.data, 'binary');
// Enforce file size limit
if (buffer.length > fileSizeLimit) {
logger.warn(
`[processCodeOutput] File "${name}" (${(buffer.length / megabyte).toFixed(2)} MB) exceeds size limit of ${(fileSizeLimit / megabyte).toFixed(2)} MB, falling back to download URL`,
);
return createDownloadFallback({
id,
name,
messageId,
toolCallId,
session_id,
conversationId,
expiresAt: currentDate.getTime() + 86400000,
});
}
const fileIdentifier = `${session_id}/${id}`;
/**
* Atomically claim a file_id for this (filename, conversationId, context) tuple.
* Uses $setOnInsert so concurrent calls for the same filename converge on
* a single record instead of creating duplicates (TOCTOU race fix).
*/
const newFileId = v4();
const claimed = await claimCodeFile({
filename: name,
conversationId,
file_id: newFileId,
user: req.user.id,
});
const file_id = claimed.file_id;
const isUpdate = file_id !== newFileId;
if (isUpdate) {
logger.debug(
`[processCodeOutput] Updating existing file "${name}" (${file_id}) instead of creating duplicate`,
);
}
if (isImage) {
const usage = isUpdate ? (claimed.usage ?? 0) + 1 : 1;
const _file = await convertImage(req, buffer, 'high', `${file_id}${fileExt}`);
const filepath = usage > 1 ? `${_file.filepath}?v=${Date.now()}` : _file.filepath;
const file = {
..._file,
filepath,
file_id,
messageId,
usage,
filename: name,
conversationId,
user: req.user.id,
type: `image/${appConfig.imageOutputType}`,
createdAt: isUpdate ? claimed.createdAt : formattedDate,
updatedAt: formattedDate,
source: appConfig.fileStrategy,
context: FileContext.execute_code,
metadata: { fileIdentifier },
};
await createFile(file, true);
return Object.assign(file, { messageId, toolCallId });
}
const { saveBuffer } = getStrategyFunctions(appConfig.fileStrategy);
if (!saveBuffer) {
logger.warn(
`[processCodeOutput] saveBuffer not available for strategy ${appConfig.fileStrategy}, falling back to download URL`,
);
return createDownloadFallback({
id,
name,
messageId,
toolCallId,
session_id,
conversationId,
expiresAt: currentDate.getTime() + 86400000,
});
}
const detectedType = await determineFileType(buffer, true);
const mimeType = detectedType?.mime || inferMimeType(name, '') || 'application/octet-stream';
/** Check MIME type support - for code-generated files, we're lenient but log unsupported types */
const isSupportedMimeType = fileConfig.checkType(
mimeType,
endpointFileConfig.supportedMimeTypes,
);
if (!isSupportedMimeType) {
logger.warn(
`[processCodeOutput] File "${name}" has unsupported MIME type "${mimeType}", proceeding with storage but may not be usable as tool resource`,
);
}
const fileName = `${file_id}__${name}`;
const filepath = await saveBuffer({
userId: req.user.id,
buffer,
fileName,
basePath: 'uploads',
});
const file = {
file_id,
filepath,
messageId,
object: 'file',
filename: name,
type: mimeType,
conversationId,
user: req.user.id,
bytes: buffer.length,
updatedAt: formattedDate,
metadata: { fileIdentifier },
source: appConfig.fileStrategy,
context: FileContext.execute_code,
usage: isUpdate ? (claimed.usage ?? 0) + 1 : 1,
createdAt: isUpdate ? claimed.createdAt : formattedDate,
};
await createFile(file, true);
return Object.assign(file, { messageId, toolCallId });
} catch (error) {
logAxiosError({
message: 'Error downloading/processing code environment file',
error,
});
// Fallback for download errors - return download URL so user can still manually download
return createDownloadFallback({
id,
name,
messageId,
toolCallId,
session_id,
conversationId,
expiresAt: currentDate.getTime() + 86400000,
});
}
};
function checkIfActive(dateString) {
const givenDate = new Date(dateString);
const currentDate = new Date();
const timeDifference = currentDate - givenDate;
const hoursPassed = timeDifference / (1000 * 60 * 60);
return hoursPassed < 23;
}
/**
* Retrieves the `lastModified` time string for a specified file from Code Execution Server.
*
* @param {Object} params - The parameters object.
* @param {string} params.fileIdentifier - The identifier for the file (e.g., "session_id/fileId").
* @param {string} params.apiKey - The API key for authentication.
*
* @returns {Promise<string|null>}
* A promise that resolves to the `lastModified` time string of the file if successful, or null if there is an
* error in initialization or fetching the info.
*/
async function getSessionInfo(fileIdentifier, apiKey) {
try {
const baseURL = getCodeBaseURL();
const [path, queryString] = fileIdentifier.split('?');
const session_id = path.split('/')[0];
let queryParams = {};
if (queryString) {
queryParams = Object.fromEntries(new URLSearchParams(queryString).entries());
}
const response = await axios({
method: 'get',
url: `${baseURL}/files/${session_id}`,
params: {
detail: 'summary',
...queryParams,
},
headers: {
'User-Agent': 'LibreChat/1.0',
'X-API-Key': apiKey,
},
timeout: 5000,
});
return response.data.find((file) => file.name.startsWith(path))?.lastModified;
} catch (error) {
logAxiosError({
message: `Error fetching session info: ${error.message}`,
error,
});
return null;
}
}
/**
*
* @param {Object} options
* @param {ServerRequest} options.req
* @param {Agent['tool_resources']} options.tool_resources
* @param {string} [options.agentId] - The agent ID for file access control
* @param {string} apiKey
* @returns {Promise<{
* files: Array<{ id: string; session_id: string; name: string }>,
* toolContext: string,
* }>}
*/
const primeFiles = async (options, apiKey) => {
const { tool_resources, req, agentId } = options;
const file_ids = tool_resources?.[EToolResources.execute_code]?.file_ids ?? [];
const agentResourceIds = new Set(file_ids);
const resourceFiles = tool_resources?.[EToolResources.execute_code]?.files ?? [];
// Get all files first
const allFiles = (await getFiles({ file_id: { $in: file_ids } }, null, { text: 0 })) ?? [];
// Filter by access if user and agent are provided
let dbFiles;
if (req?.user?.id && agentId) {
dbFiles = await filterFilesByAgentAccess({
files: allFiles,
userId: req.user.id,
role: req.user.role,
agentId,
});
} else {
dbFiles = allFiles;
}
dbFiles = dbFiles.concat(resourceFiles);
const files = [];
const sessions = new Map();
let toolContext = '';
for (let i = 0; i < dbFiles.length; i++) {
const file = dbFiles[i];
if (!file) {
continue;
}
if (file.metadata.fileIdentifier) {
const [path, queryString] = file.metadata.fileIdentifier.split('?');
const [session_id, id] = path.split('/');
const pushFile = () => {
if (!toolContext) {
toolContext = `- Note: The following files are available in the "${Tools.execute_code}" tool environment:`;
}
let fileSuffix = '';
if (!agentResourceIds.has(file.file_id)) {
fileSuffix =
file.context === FileContext.execute_code
? ' (from previous code execution)'
: ' (attached by user)';
}
toolContext += `\n\t- /mnt/data/${file.filename}${fileSuffix}`;
files.push({
id,
session_id,
name: file.filename,
});
};
if (sessions.has(session_id)) {
pushFile();
continue;
}
let queryParams = {};
if (queryString) {
queryParams = Object.fromEntries(new URLSearchParams(queryString).entries());
}
const reuploadFile = async () => {
try {
const { getDownloadStream } = getStrategyFunctions(file.source);
const { handleFileUpload: uploadCodeEnvFile } = getStrategyFunctions(
FileSources.execute_code,
);
const stream = await getDownloadStream(options.req, file.filepath);
const fileIdentifier = await uploadCodeEnvFile({
req: options.req,
stream,
filename: file.filename,
entity_id: queryParams.entity_id,
apiKey,
});
// Preserve existing metadata when adding fileIdentifier
const updatedMetadata = {
...file.metadata, // Preserve existing metadata (like S3 storage info)
fileIdentifier, // Add fileIdentifier
};
await updateFile({
file_id: file.file_id,
metadata: updatedMetadata,
});
sessions.set(session_id, true);
pushFile();
} catch (error) {
logger.error(
`Error re-uploading file ${id} in session ${session_id}: ${error.message}`,
error,
);
}
};
const uploadTime = await getSessionInfo(file.metadata.fileIdentifier, apiKey);
if (!uploadTime) {
logger.warn(`Failed to get upload time for file ${id} in session ${session_id}`);
await reuploadFile();
continue;
}
if (!checkIfActive(uploadTime)) {
await reuploadFile();
continue;
}
sessions.set(session_id, true);
pushFile();
}
}
return { files, toolContext };
};
module.exports = {
primeFiles,
processCodeOutput,
};