🗂️ feat: Better Persistence for Code Execution Files Between Sessions (#11362)

* refactor: process code output files for re-use (WIP)

* feat: file attachment handling with additional metadata for downloads

* refactor: Update directory path logic for local file saving based on basePath

* refactor: file attachment handling to support TFile type and improve data merging logic

* feat: thread filtering of code-generated files

- Introduced parentMessageId parameter in addedConvo and initialize functions to enhance thread management.
- Updated related methods to utilize parentMessageId for retrieving messages and filtering code-generated files by conversation threads.
- Enhanced type definitions to include parentMessageId in relevant interfaces for better clarity and usage.

* chore: imports/params ordering

* feat: update file model to use messageId for filtering and processing

- Changed references from 'message' to 'messageId' in file-related methods for consistency.
- Added messageId field to the file schema and updated related types.
- Enhanced file processing logic to accommodate the new messageId structure.

* feat: enhance file retrieval methods to support user-uploaded execute_code files

- Added a new method `getUserCodeFiles` to retrieve user-uploaded execute_code files, excluding code-generated files.
- Updated existing file retrieval methods to improve filtering logic and handle edge cases.
- Enhanced thread data extraction to collect both message IDs and file IDs efficiently.
- Integrated `getUserCodeFiles` into relevant endpoints for better file management in conversations.

* chore: update @librechat/agents package version to 3.0.78 in package-lock.json and related package.json files

* refactor: file processing and retrieval logic

- Added a fallback mechanism for download URLs when files exceed size limits or cannot be processed locally.
- Implemented a deduplication strategy for code-generated files based on conversationId and filename to optimize storage.
- Updated file retrieval methods to ensure proper filtering by messageIds, preventing orphaned files from being included.
- Introduced comprehensive tests for new thread data extraction functionality, covering edge cases and performance considerations.

* fix: improve file retrieval tests and handling of optional properties

- Updated tests to safely access optional properties using non-null assertions.
- Modified test descriptions for clarity regarding the exclusion of execute_code files.
- Ensured that the retrieval logic correctly reflects the expected outcomes for file queries.

* test: add comprehensive unit tests for processCodeOutput functionality

- Introduced a new test suite for the processCodeOutput function, covering various scenarios including file retrieval, creation, and processing for both image and non-image files.
- Implemented mocks for dependencies such as axios, logger, and file models to isolate tests and ensure reliable outcomes.
- Validated behavior for existing files, new file creation, and error handling, including size limits and fallback mechanisms.
- Enhanced test coverage for metadata handling and usage increment logic, ensuring robust verification of file processing outcomes.

* test: enhance file size limit enforcement in processCodeOutput tests

- Introduced a configurable file size limit for tests to improve flexibility and coverage.
- Mocked the `librechat-data-provider` to allow dynamic adjustment of file size limits during tests.
- Updated the file size limit enforcement test to validate behavior when files exceed specified limits, ensuring proper fallback to download URLs.
- Reset file size limit after tests to maintain isolation for subsequent test cases.

api/server/services/Endpoints/agents/addedConvo.js

@@ -31,6 +31,7 @@ setGetAgent(getAgent);
  * @param {Function} params.loadTools - Function to load agent tools
  * @param {Array} params.requestFiles - Request files
  * @param {string} params.conversationId - The conversation ID
+ * @param {string} [params.parentMessageId] - The parent message ID for thread filtering
  * @param {Set} params.allowedProviders - Set of allowed providers
  * @param {Map} params.agentConfigs - Map of agent configs to add to
  * @param {string} params.primaryAgentId - The primary agent ID
@@ -46,6 +47,7 @@ const processAddedConvo = async ({
   loadTools,
   requestFiles,
   conversationId,
+  parentMessageId,
   allowedProviders,
   agentConfigs,
   primaryAgentId,
@@ -91,6 +93,7 @@ const processAddedConvo = async ({
         loadTools,
         requestFiles,
         conversationId,
+        parentMessageId,
         agent: addedAgent,
         endpointOption,
         allowedProviders,
@@ -99,9 +102,12 @@ const processAddedConvo = async ({
         getConvoFiles,
         getFiles: db.getFiles,
         getUserKey: db.getUserKey,
+        getMessages: db.getMessages,
         updateFilesUsage: db.updateFilesUsage,
+        getUserCodeFiles: db.getUserCodeFiles,
         getUserKeyValues: db.getUserKeyValues,
         getToolFilesByIds: db.getToolFilesByIds,
+        getCodeGeneratedFiles: db.getCodeGeneratedFiles,
       },
     );
 

api/server/services/Endpoints/agents/initialize.js

@@ -3,10 +3,10 @@ const { createContentAggregator } = require('@librechat/agents');
 const {
   initializeAgent,
   validateAgentModel,
-  getCustomEndpointConfig,
-  createSequentialChainEdges,
   createEdgeCollector,
   filterOrphanedEdges,
+  getCustomEndpointConfig,
+  createSequentialChainEdges,
 } = require('@librechat/api');
 const {
   EModelEndpoint,
@@ -129,6 +129,8 @@ const initializeClient = async ({ req, res, signal, endpointOption }) => {
   const requestFiles = req.body.files ?? [];
   /** @type {string} */
   const conversationId = req.body.conversationId;
+  /** @type {string | undefined} */
+  const parentMessageId = req.body.parentMessageId;
 
   const primaryConfig = await initializeAgent(
     {
@@ -137,6 +139,7 @@ const initializeClient = async ({ req, res, signal, endpointOption }) => {
       loadTools,
       requestFiles,
       conversationId,
+      parentMessageId,
       agent: primaryAgent,
       endpointOption,
       allowedProviders,
@@ -146,9 +149,12 @@ const initializeClient = async ({ req, res, signal, endpointOption }) => {
       getConvoFiles,
       getFiles: db.getFiles,
       getUserKey: db.getUserKey,
+      getMessages: db.getMessages,
       updateFilesUsage: db.updateFilesUsage,
       getUserKeyValues: db.getUserKeyValues,
+      getUserCodeFiles: db.getUserCodeFiles,
       getToolFilesByIds: db.getToolFilesByIds,
+      getCodeGeneratedFiles: db.getCodeGeneratedFiles,
     },
   );
 
@@ -188,6 +194,7 @@ const initializeClient = async ({ req, res, signal, endpointOption }) => {
         loadTools,
         requestFiles,
         conversationId,
+        parentMessageId,
         endpointOption,
         allowedProviders,
       },
@@ -195,9 +202,12 @@ const initializeClient = async ({ req, res, signal, endpointOption }) => {
         getConvoFiles,
         getFiles: db.getFiles,
         getUserKey: db.getUserKey,
+        getMessages: db.getMessages,
         updateFilesUsage: db.updateFilesUsage,
         getUserKeyValues: db.getUserKeyValues,
+        getUserCodeFiles: db.getUserCodeFiles,
         getToolFilesByIds: db.getToolFilesByIds,
+        getCodeGeneratedFiles: db.getCodeGeneratedFiles,
       },
     );
     if (userMCPAuthMap != null) {
@@ -252,17 +262,18 @@ const initializeClient = async ({ req, res, signal, endpointOption }) => {
   const { userMCPAuthMap: updatedMCPAuthMap } = await processAddedConvo({
     req,
     res,
-    endpointOption,
-    modelsConfig,
-    logViolation,
     loadTools,
+    logViolation,
+    modelsConfig,
     requestFiles,
-    conversationId,
-    allowedProviders,
     agentConfigs,
-    primaryAgentId: primaryConfig.id,
     primaryAgent,
+    endpointOption,
     userMCPAuthMap,
+    conversationId,
+    parentMessageId,
+    allowedProviders,
+    primaryAgentId: primaryConfig.id,
   });
 
   if (updatedMCPAuthMap) {