🔄 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
This commit is contained in:
Danny Avila 2025-09-18 20:06:59 -04:00 committed by GitHub
parent 89d12a8ccd
commit 81139046e5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
25 changed files with 1281 additions and 76 deletions

View file

@ -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' },
},
}),
);

View file

@ -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 {

View file

@ -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();
});