🧠 feat: User Memories for Conversational Context (#7760)

* 🧠 feat: User Memories for Conversational Context

chore: mcp typing, use `t`

WIP: first pass, Memories UI

- Added MemoryViewer component for displaying, editing, and deleting user memories.
- Integrated data provider hooks for fetching, updating, and deleting memories.
- Implemented pagination and loading states for better user experience.
- Created unit tests for MemoryViewer to ensure functionality and interaction with data provider.
- Updated translation files to include new UI strings related to memories.

chore: move mcp-related files to own directory

chore: rename librechat-mcp to librechat-api

WIP: first pass, memory processing and data schemas

chore: linting in fileSearch.js query description

chore: rename librechat-api to @librechat/api across the project

WIP: first pass, functional memory agent

feat: add MemoryEditDialog and MemoryViewer components for managing user memories

- Introduced MemoryEditDialog for editing memory entries with validation and toast notifications.
- Updated MemoryViewer to support editing and deleting memories, including pagination and loading states.
- Enhanced data provider to handle memory updates with optional original key for better management.
- Added new localization strings for memory-related UI elements.

feat: add memory permissions management

- Implemented memory permissions in the backend, allowing roles to have specific permissions for using, creating, updating, and reading memories.
- Added new API endpoints for updating memory permissions associated with roles.
- Created a new AdminSettings component for managing memory permissions in the frontend.
- Integrated memory permissions into the existing roles and permissions schemas.
- Updated the interface to include memory settings and permissions.
- Enhanced the MemoryViewer component to conditionally render admin settings based on user roles.
- Added localization support for memory permissions in the translation files.

feat: move AdminSettings component to a new position in MemoryViewer for better visibility

refactor: clean up commented code in MemoryViewer component

feat: enhance MemoryViewer with search functionality and improve MemoryEditDialog integration

- Added a search input to filter memories in the MemoryViewer component.
- Refactored MemoryEditDialog to accept children for better customization.
- Updated MemoryViewer to utilize the new EditMemoryButton and DeleteMemoryButton components for editing and deleting memories.
- Improved localization support by adding new strings for memory filtering and deletion confirmation.

refactor: optimize memory filtering in MemoryViewer using match-sorter

- Replaced manual filtering logic with match-sorter for improved search functionality.
- Enhanced performance and readability of the filteredMemories computation.

feat: enhance MemoryEditDialog with triggerRef and improve updateMemory mutation handling

feat: implement access control for MemoryEditDialog and MemoryViewer components

refactor: remove commented out code and create runMemory method

refactor: rename role based files

feat: implement access control for memory usage in AgentClient

refactor: simplify checkVisionRequest method in AgentClient by removing commented-out code

refactor: make `agents` dir in api package

refactor: migrate Azure utilities to TypeScript and consolidate imports

refactor: move sanitizeFilename function to a new file and update imports, add related tests

refactor: update LLM configuration types and consolidate Azure options in the API package

chore: linting

chore: import order

refactor: replace getLLMConfig with getOpenAIConfig and remove unused LLM configuration file

chore: update winston-daily-rotate-file to version 5.0.0 and add object-hash dependency in package-lock.json

refactor: move primeResources and optionalChainWithEmptyCheck functions to resources.ts and update imports

refactor: move createRun function to a new run.ts file and update related imports

fix: ensure safeAttachments is correctly typed as an array of TFile

chore: add node-fetch dependency and refactor fetch-related functions into packages/api/utils, removing the old generators file

refactor: enhance TEndpointOption type by using Pick to streamline endpoint fields and add new properties for model parameters and client options

feat: implement initializeOpenAIOptions function and update OpenAI types for enhanced configuration handling

fix: update types due to new TEndpointOption typing

fix: ensure safe access to group parameters in initializeOpenAIOptions function

fix: remove redundant API key validation comment in initializeOpenAIOptions function

refactor: rename initializeOpenAIOptions to initializeOpenAI for consistency and update related documentation

refactor: decouple req.body fields and tool loading from initializeAgentOptions

chore: linting

refactor: adjust column widths in MemoryViewer for improved layout

refactor: simplify agent initialization by creating loadAgent function and removing unused code

feat: add memory configuration loading and validation functions

WIP: first pass, memory processing with config

feat: implement memory callback and artifact handling

feat: implement memory artifacts display and processing updates

feat: add memory configuration options and schema validation for validKeys

fix: update MemoryEditDialog and MemoryViewer to handle memory state and display improvements

refactor: remove padding from BookmarkTable and MemoryViewer headers for consistent styling

WIP: initial tokenLimit config and move Tokenizer to @librechat/api

refactor: update mongoMeili plugin methods to use callback for better error handling

feat: enhance memory management with token tracking and usage metrics

- Added token counting for memory entries to enforce limits and provide usage statistics.
- Updated memory retrieval and update routes to include total token usage and limit.
- Enhanced MemoryEditDialog and MemoryViewer components to display memory usage and token information.
- Refactored memory processing functions to handle token limits and provide feedback on memory capacity.

feat: implement memory artifact handling in attachment handler

- Enhanced useAttachmentHandler to process memory artifacts when receiving updates.
- Introduced handleMemoryArtifact utility to manage memory updates and deletions.
- Updated query client to reflect changes in memory state based on incoming data.

refactor: restructure web search key extraction logic

- Moved the logic for extracting API keys from the webSearchAuth configuration into a dedicated function, getWebSearchKeys.
- Updated webSearchKeys to utilize the new function for improved clarity and maintainability.
- Prevents build time errors

feat: add personalization settings and memory preferences management

- Introduced a new Personalization tab in settings to manage user memory preferences.
- Implemented API endpoints and client-side logic for updating memory preferences.
- Enhanced user interface components to reflect personalization options and memory usage.
- Updated permissions to allow users to opt out of memory features.
- Added localization support for new settings and messages related to personalization.

style: personalization switch class

feat: add PersonalizationIcon and align Side Panel UI

feat: implement memory creation functionality

- Added a new API endpoint for creating memory entries, including validation for key and value.
- Introduced MemoryCreateDialog component for user interface to facilitate memory creation.
- Integrated token limit checks to prevent exceeding user memory capacity.
- Updated MemoryViewer to include a button for opening the memory creation dialog.
- Enhanced localization support for new messages related to memory creation.

feat: enhance message processing with configurable window size

- Updated AgentClient to use a configurable message window size for processing messages.
- Introduced messageWindowSize option in memory configuration schema with a default value of 5.
- Improved logic for selecting messages to process based on the configured window size.

chore: update librechat-data-provider version to 0.7.87 in package.json and package-lock.json

chore: remove OpenAPIPlugin and its associated tests

chore: remove MIGRATION_README.md as migration tasks are completed

ci: fix backend tests

chore: remove unused translation keys from localization file

chore: remove problematic test file and unused var in AgentClient

chore: remove unused import and import directly for JSDoc

* feat: add api package build stage in Dockerfile for improved modularity

* docs: reorder build steps in contributing guide for clarity
This commit is contained in:
Danny Avila 2025-06-07 18:52:22 -04:00 committed by GitHub
parent cd7dd576c1
commit 29ef91b4dd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
170 changed files with 5700 additions and 3632 deletions

View file

@ -1,294 +1,41 @@
const { createContentAggregator, Providers } = require('@librechat/agents');
const {
Constants,
ErrorTypes,
EModelEndpoint,
EToolResources,
getResponseSender,
AgentCapabilities,
replaceSpecialVars,
providerEndpointMap,
} = require('librechat-data-provider');
const { logger } = require('@librechat/data-schemas');
const { createContentAggregator } = require('@librechat/agents');
const { Constants, EModelEndpoint, getResponseSender } = require('librechat-data-provider');
const {
getDefaultHandlers,
createToolEndCallback,
} = require('~/server/controllers/agents/callbacks');
const initAnthropic = require('~/server/services/Endpoints/anthropic/initialize');
const getBedrockOptions = require('~/server/services/Endpoints/bedrock/options');
const initOpenAI = require('~/server/services/Endpoints/openAI/initialize');
const initCustom = require('~/server/services/Endpoints/custom/initialize');
const initGoogle = require('~/server/services/Endpoints/google/initialize');
const generateArtifactsPrompt = require('~/app/clients/prompts/artifacts');
const { getCustomEndpointConfig } = require('~/server/services/Config');
const { processFiles } = require('~/server/services/Files/process');
const { initializeAgent } = require('~/server/services/Endpoints/agents/agent');
const { loadAgentTools } = require('~/server/services/ToolService');
const AgentClient = require('~/server/controllers/agents/client');
const { getConvoFiles } = require('~/models/Conversation');
const { getToolFilesByIds } = require('~/models/File');
const { getModelMaxTokens } = require('~/utils');
const { getAgent } = require('~/models/Agent');
const { getFiles } = require('~/models/File');
const { logger } = require('~/config');
const providerConfigMap = {
[Providers.XAI]: initCustom,
[Providers.OLLAMA]: initCustom,
[Providers.DEEPSEEK]: initCustom,
[Providers.OPENROUTER]: initCustom,
[EModelEndpoint.openAI]: initOpenAI,
[EModelEndpoint.google]: initGoogle,
[EModelEndpoint.azureOpenAI]: initOpenAI,
[EModelEndpoint.anthropic]: initAnthropic,
[EModelEndpoint.bedrock]: getBedrockOptions,
};
/**
* @param {Object} params
* @param {ServerRequest} params.req
* @param {Promise<Array<MongoFile | null>> | undefined} [params.attachments]
* @param {Set<string>} params.requestFileSet
* @param {AgentToolResources | undefined} [params.tool_resources]
* @returns {Promise<{ attachments: Array<MongoFile | undefined> | undefined, tool_resources: AgentToolResources | undefined }>}
*/
const primeResources = async ({
req,
attachments: _attachments,
tool_resources: _tool_resources,
requestFileSet,
}) => {
try {
/** @type {Array<MongoFile | undefined> | undefined} */
let attachments;
const tool_resources = _tool_resources ?? {};
const isOCREnabled = (req.app.locals?.[EModelEndpoint.agents]?.capabilities ?? []).includes(
AgentCapabilities.ocr,
);
if (tool_resources[EToolResources.ocr]?.file_ids && isOCREnabled) {
const context = await getFiles(
{
file_id: { $in: tool_resources.ocr.file_ids },
},
{},
{},
);
attachments = (attachments ?? []).concat(context);
function createToolLoader() {
/**
* @param {object} params
* @param {ServerRequest} params.req
* @param {ServerResponse} params.res
* @param {string} params.agentId
* @param {string[]} params.tools
* @param {string} params.provider
* @param {string} params.model
* @param {AgentToolResources} params.tool_resources
* @returns {Promise<{ tools: StructuredTool[], toolContextMap: Record<string, unknown> } | undefined>}
*/
return async function loadTools({ req, res, agentId, tools, provider, model, tool_resources }) {
const agent = { id: agentId, tools, provider, model };
try {
return await loadAgentTools({
req,
res,
agent,
tool_resources,
});
} catch (error) {
logger.error('Error loading tools for agent ' + agentId, error);
}
if (!_attachments) {
return { attachments, tool_resources };
}
/** @type {Array<MongoFile | undefined> | undefined} */
const files = await _attachments;
if (!attachments) {
/** @type {Array<MongoFile | undefined>} */
attachments = [];
}
for (const file of files) {
if (!file) {
continue;
}
if (file.metadata?.fileIdentifier) {
const execute_code = tool_resources[EToolResources.execute_code] ?? {};
if (!execute_code.files) {
tool_resources[EToolResources.execute_code] = { ...execute_code, files: [] };
}
tool_resources[EToolResources.execute_code].files.push(file);
} else if (file.embedded === true) {
const file_search = tool_resources[EToolResources.file_search] ?? {};
if (!file_search.files) {
tool_resources[EToolResources.file_search] = { ...file_search, files: [] };
}
tool_resources[EToolResources.file_search].files.push(file);
} else if (
requestFileSet.has(file.file_id) &&
file.type.startsWith('image') &&
file.height &&
file.width
) {
const image_edit = tool_resources[EToolResources.image_edit] ?? {};
if (!image_edit.files) {
tool_resources[EToolResources.image_edit] = { ...image_edit, files: [] };
}
tool_resources[EToolResources.image_edit].files.push(file);
}
attachments.push(file);
}
return { attachments, tool_resources };
} catch (error) {
logger.error('Error priming resources', error);
return { attachments: _attachments, tool_resources: _tool_resources };
}
};
/**
* @param {...string | number} values
* @returns {string | number | undefined}
*/
function optionalChainWithEmptyCheck(...values) {
for (const value of values) {
if (value !== undefined && value !== null && value !== '') {
return value;
}
}
return values[values.length - 1];
}
/**
* @param {object} params
* @param {ServerRequest} params.req
* @param {ServerResponse} params.res
* @param {Agent} params.agent
* @param {Set<string>} [params.allowedProviders]
* @param {object} [params.endpointOption]
* @param {boolean} [params.isInitialAgent]
* @returns {Promise<Agent>}
*/
const initializeAgentOptions = async ({
req,
res,
agent,
endpointOption,
allowedProviders,
isInitialAgent = false,
}) => {
if (allowedProviders.size > 0 && !allowedProviders.has(agent.provider)) {
throw new Error(
`{ "type": "${ErrorTypes.INVALID_AGENT_PROVIDER}", "info": "${agent.provider}" }`,
);
}
let currentFiles;
/** @type {Array<MongoFile>} */
const requestFiles = req.body.files ?? [];
if (
isInitialAgent &&
req.body.conversationId != null &&
(agent.model_parameters?.resendFiles ?? true) === true
) {
const fileIds = (await getConvoFiles(req.body.conversationId)) ?? [];
/** @type {Set<EToolResources>} */
const toolResourceSet = new Set();
for (const tool of agent.tools) {
if (EToolResources[tool]) {
toolResourceSet.add(EToolResources[tool]);
}
}
const toolFiles = await getToolFilesByIds(fileIds, toolResourceSet);
if (requestFiles.length || toolFiles.length) {
currentFiles = await processFiles(requestFiles.concat(toolFiles));
}
} else if (isInitialAgent && requestFiles.length) {
currentFiles = await processFiles(requestFiles);
}
const { attachments, tool_resources } = await primeResources({
req,
attachments: currentFiles,
tool_resources: agent.tool_resources,
requestFileSet: new Set(requestFiles.map((file) => file.file_id)),
});
const provider = agent.provider;
const { tools, toolContextMap } = await loadAgentTools({
req,
res,
agent: {
id: agent.id,
tools: agent.tools,
provider,
model: agent.model,
},
tool_resources,
});
agent.endpoint = provider;
let getOptions = providerConfigMap[provider];
if (!getOptions && providerConfigMap[provider.toLowerCase()] != null) {
agent.provider = provider.toLowerCase();
getOptions = providerConfigMap[agent.provider];
} else if (!getOptions) {
const customEndpointConfig = await getCustomEndpointConfig(provider);
if (!customEndpointConfig) {
throw new Error(`Provider ${provider} not supported`);
}
getOptions = initCustom;
agent.provider = Providers.OPENAI;
}
const model_parameters = Object.assign(
{},
agent.model_parameters ?? { model: agent.model },
isInitialAgent === true ? endpointOption?.model_parameters : {},
);
const _endpointOption =
isInitialAgent === true
? Object.assign({}, endpointOption, { model_parameters })
: { model_parameters };
const options = await getOptions({
req,
res,
optionsOnly: true,
overrideEndpoint: provider,
overrideModel: agent.model,
endpointOption: _endpointOption,
});
if (
agent.endpoint === EModelEndpoint.azureOpenAI &&
options.llmConfig?.azureOpenAIApiInstanceName == null
) {
agent.provider = Providers.OPENAI;
}
if (options.provider != null) {
agent.provider = options.provider;
}
/** @type {import('@librechat/agents').ClientOptions} */
agent.model_parameters = Object.assign(model_parameters, options.llmConfig);
if (options.configOptions) {
agent.model_parameters.configuration = options.configOptions;
}
if (!agent.model_parameters.model) {
agent.model_parameters.model = agent.model;
}
if (agent.instructions && agent.instructions !== '') {
agent.instructions = replaceSpecialVars({
text: agent.instructions,
user: req.user,
});
}
if (typeof agent.artifacts === 'string' && agent.artifacts !== '') {
agent.additional_instructions = generateArtifactsPrompt({
endpoint: agent.provider,
artifacts: agent.artifacts,
});
}
const tokensModel =
agent.provider === EModelEndpoint.azureOpenAI ? agent.model : agent.model_parameters.model;
const maxTokens = optionalChainWithEmptyCheck(
agent.model_parameters.maxOutputTokens,
agent.model_parameters.maxTokens,
0,
);
const maxContextTokens = optionalChainWithEmptyCheck(
agent.model_parameters.maxContextTokens,
agent.max_context_tokens,
getModelMaxTokens(tokensModel, providerEndpointMap[provider]),
4096,
);
return {
...agent,
tools,
attachments,
toolContextMap,
maxContextTokens: (maxContextTokens - maxTokens) * 0.9,
};
};
}
const initializeClient = async ({ req, res, endpointOption }) => {
if (!endpointOption) {
@ -313,7 +60,6 @@ const initializeClient = async ({ req, res, endpointOption }) => {
throw new Error('No agent promise provided');
}
// Initialize primary agent
const primaryAgent = await endpointOption.agent;
if (!primaryAgent) {
throw new Error('Agent not found');
@ -323,10 +69,18 @@ const initializeClient = async ({ req, res, endpointOption }) => {
/** @type {Set<string>} */
const allowedProviders = new Set(req?.app?.locals?.[EModelEndpoint.agents]?.allowedProviders);
// Handle primary agent
const primaryConfig = await initializeAgentOptions({
const loadTools = createToolLoader();
/** @type {Array<MongoFile>} */
const requestFiles = req.body.files ?? [];
/** @type {string} */
const conversationId = req.body.conversationId;
const primaryConfig = await initializeAgent({
req,
res,
loadTools,
requestFiles,
conversationId,
agent: primaryAgent,
endpointOption,
allowedProviders,
@ -340,10 +94,13 @@ const initializeClient = async ({ req, res, endpointOption }) => {
if (!agent) {
throw new Error(`Agent ${agentId} not found`);
}
const config = await initializeAgentOptions({
const config = await initializeAgent({
req,
res,
agent,
loadTools,
requestFiles,
conversationId,
endpointOption,
allowedProviders,
});