🔄 refactor: Convert OCR Tool Resource to Context (#9699)

* WIP: conversion of `ocr` to `context`

* refactor: make `primeResources` backwards-compatible for `ocr` tool_resources

* refactor: Convert legacy `ocr` tool resource to `context` in agent updates

- Implemented conversion logic to replace `ocr` with `context` in both incoming updates and existing agent data.
- Merged file IDs and files from `ocr` into `context` while ensuring deduplication.
- Updated tools array to reflect the change from `ocr` to `context`.

* refactor: Enhance context file handling in agent processing

- Updated the logic for managing context files by consolidating file IDs from both `ocr` and `context` resources.
- Improved backwards compatibility by ensuring that context files are correctly populated and handled.
- Simplified the iteration over context files for better readability and maintainability.

* refactor: Enhance tool_resources handling in primeResources

- Added tests to verify the deletion behavior of tool_resources fields, ensuring original objects remain unchanged.
- Implemented logic to delete `ocr` and `context` fields after fetching and re-categorizing files.
- Preserved context field when the context capability is disabled, ensuring correct behavior in various scenarios.

* refactor: Replace `ocrEnabled` with `contextEnabled` in AgentConfig

* refactor: Adjust legacy tool handling order for improved clarity

* refactor: Implement OCR to context conversion functions and remove original conversion logic in update agent handling

* refactor: Move contextEnabled declaration to maintain consistent order in capabilities

* refactor: Update localization keys for file context to improve clarity and accuracy

* chore: Update localization key for file context information to improve clarity

api/models/File.js

@@ -42,7 +42,7 @@ const getToolFilesByIds = async (fileIds, toolResourceSet) => {
       $or: [],
     };
 
-    if (toolResourceSet.has(EToolResources.ocr)) {
+    if (toolResourceSet.has(EToolResources.context)) {
       filter.$or.push({ text: { $exists: true, $ne: null }, context: FileContext.agents });
     }
     if (toolResourceSet.has(EToolResources.file_search)) {

api/server/controllers/agents/__tests__/v1.spec.js

@@ -158,7 +158,7 @@ describe('duplicateAgent', () => {
     });
   });
 
-  it('should handle tool_resources.ocr correctly', async () => {
+  it('should convert `tool_resources.ocr` to `tool_resources.context`', async () => {
     const mockAgent = {
       id: 'agent_123',
       name: 'Test Agent',
@@ -178,7 +178,7 @@ describe('duplicateAgent', () => {
     expect(createAgent).toHaveBeenCalledWith(
       expect.objectContaining({
         tool_resources: {
-          ocr: { enabled: true, config: 'test' },
+          context: { enabled: true, config: 'test' },
         },
       }),
     );

api/server/controllers/agents/v1.js

@@ -2,7 +2,12 @@ const { z } = require('zod');
 const fs = require('fs').promises;
 const { nanoid } = require('nanoid');
 const { logger } = require('@librechat/data-schemas');
-const { agentCreateSchema, agentUpdateSchema } = require('@librechat/api');
+const {
+  agentCreateSchema,
+  agentUpdateSchema,
+  mergeAgentOcrConversion,
+  convertOcrToContextInPlace,
+} = require('@librechat/api');
 const {
   Tools,
   Constants,
@@ -198,19 +203,32 @@ const getAgentHandler = async (req, res, expandProperties = false) => {
  * @param {object} req.params - Request params
  * @param {string} req.params.id - Agent identifier.
  * @param {AgentUpdateParams} req.body - The Agent update parameters.
- * @returns {Agent} 200 - success response - application/json
+ * @returns {Promise<Agent>} 200 - success response - application/json
  */
 const updateAgentHandler = async (req, res) => {
   try {
     const id = req.params.id;
     const validatedData = agentUpdateSchema.parse(req.body);
     const { _id, ...updateData } = removeNullishValues(validatedData);
+
+    // Convert OCR to context in incoming updateData
+    convertOcrToContextInPlace(updateData);
+
     const existingAgent = await getAgent({ id });
 
     if (!existingAgent) {
       return res.status(404).json({ error: 'Agent not found' });
     }
 
+    // Convert legacy OCR tool resource to context format in existing agent
+    const ocrConversion = mergeAgentOcrConversion(existingAgent, updateData);
+    if (ocrConversion.tool_resources) {
+      updateData.tool_resources = ocrConversion.tool_resources;
+    }
+    if (ocrConversion.tools) {
+      updateData.tools = ocrConversion.tools;
+    }
+
     let updatedAgent =
       Object.keys(updateData).length > 0
         ? await updateAgent({ id }, updateData, {
@@ -255,7 +273,7 @@ const updateAgentHandler = async (req, res) => {
  * @param {object} req - Express Request
  * @param {object} req.params - Request params
  * @param {string} req.params.id - Agent identifier.
- * @returns {Agent} 201 - success response - application/json
+ * @returns {Promise<Agent>} 201 - success response - application/json
  */
 const duplicateAgentHandler = async (req, res) => {
   const { id } = req.params;
@@ -288,9 +306,19 @@ const duplicateAgentHandler = async (req, res) => {
       hour12: false,
     })})`;
 
+    if (_tool_resources?.[EToolResources.context]) {
+      cloneData.tool_resources = {
+        [EToolResources.context]: _tool_resources[EToolResources.context],
+      };
+    }
+
     if (_tool_resources?.[EToolResources.ocr]) {
       cloneData.tool_resources = {
-        [EToolResources.ocr]: _tool_resources[EToolResources.ocr],
+        /** Legacy conversion from `ocr` to `context` */
+        [EToolResources.context]: {
+          ...(_tool_resources[EToolResources.context] ?? {}),
+          ..._tool_resources[EToolResources.ocr],
+        },
       };
     }
 
@@ -382,7 +410,7 @@ const duplicateAgentHandler = async (req, res) => {
  * @param {object} req - Express Request
  * @param {object} req.params - Request params
  * @param {string} req.params.id - Agent identifier.
- * @returns {Agent} 200 - success response - application/json
+ * @returns {Promise<Agent>} 200 - success response - application/json
  */
 const deleteAgentHandler = async (req, res) => {
   try {
@@ -484,7 +512,7 @@ const getListAgentsHandler = async (req, res) => {
  * @param {Express.Multer.File} req.file - The avatar image file.
  * @param {object} req.body - Request body
  * @param {string} [req.body.avatar] - Optional avatar for the agent's avatar.
- * @returns {Object} 200 - success response - application/json
+ * @returns {Promise<void>} 200 - success response - application/json
  */
 const uploadAgentAvatarHandler = async (req, res) => {
   try {

api/server/controllers/agents/v1.spec.js

@@ -512,6 +512,7 @@ describe('Agent Controllers - Mass Assignment Protection', () => {
       mockReq.params.id = existingAgentId;
       mockReq.body = {
         tool_resources: {
+          /** Legacy conversion from `ocr` to `context` */
           ocr: {
             file_ids: ['ocr1', 'ocr2'],
           },
@@ -531,7 +532,8 @@ describe('Agent Controllers - Mass Assignment Protection', () => {
 
       const updatedAgent = mockRes.json.mock.calls[0][0];
       expect(updatedAgent.tool_resources).toBeDefined();
-      expect(updatedAgent.tool_resources.ocr).toBeDefined();
+      expect(updatedAgent.tool_resources.ocr).toBeUndefined();
+      expect(updatedAgent.tool_resources.context).toBeDefined();
       expect(updatedAgent.tool_resources.execute_code).toBeDefined();
       expect(updatedAgent.tool_resources.invalid_tool).toBeUndefined();
     });

api/server/middleware/accessResources/fileAccess.js

@@ -10,11 +10,12 @@ const { getFiles } = require('~/models/File');
  */
 const checkAgentBasedFileAccess = async ({ userId, role, fileId }) => {
   try {
-    // Find agents that have this file in their tool_resources
+    /** Agents that have this file in their tool_resources */
     const agentsWithFile = await getAgents({
       $or: [
-        { 'tool_resources.file_search.file_ids': fileId },
         { 'tool_resources.execute_code.file_ids': fileId },
+        { 'tool_resources.file_search.file_ids': fileId },
+        { 'tool_resources.context.file_ids': fileId },
         { 'tool_resources.ocr.file_ids': fileId },
       ],
     });
@@ -83,7 +84,6 @@ const fileAccess = async (req, res, next) => {
       });
     }
 
-    // Get the file
     const [file] = await getFiles({ file_id: fileId });
     if (!file) {
       return res.status(404).json({
@@ -92,20 +92,18 @@ const fileAccess = async (req, res, next) => {
       });
     }
 
-    // Check if user owns the file
     if (file.user && file.user.toString() === userId) {
       req.fileAccess = { file };
       return next();
     }
 
-    // Check agent-based access (file inherits agent permissions)
+    /** Agent-based access (file inherits agent permissions) */
     const hasAgentAccess = await checkAgentBasedFileAccess({ userId, role: userRole, fileId });
     if (hasAgentAccess) {
       req.fileAccess = { file };
       return next();
     }
 
-    // No access
     logger.warn(`[fileAccess] User ${userId} denied access to file ${fileId}`);
     return res.status(403).json({
       error: 'Forbidden',

api/server/services/Files/process.js

@@ -552,7 +552,7 @@ const processAgentFileUpload = async ({ req, res, metadata }) => {
       throw new Error('File search is not enabled for Agents');
     }
     // Note: File search processing continues to dual storage logic below
-  } else if (tool_resource === EToolResources.ocr) {
+  } else if (tool_resource === EToolResources.context) {
     const { file_id, temp_file_id = null } = metadata;
 
     /**

api/server/services/ToolService.js

@@ -353,7 +353,12 @@ async function processRequiredActions(client, requiredActions) {
 async function loadAgentTools({ req, res, agent, signal, tool_resources, openAIApiKey }) {
   if (!agent.tools || agent.tools.length === 0) {
     return {};
-  } else if (agent.tools && agent.tools.length === 1 && agent.tools[0] === AgentCapabilities.ocr) {
+  } else if (
+    agent.tools &&
+    agent.tools.length === 1 &&
+    /** Legacy handling for `ocr` as may still exist in existing Agents */
+    (agent.tools[0] === AgentCapabilities.context || agent.tools[0] === AgentCapabilities.ocr)
+  ) {
     return {};
   }