LibreChat/api/server/services/ActionService.js
Danny Avila 29ef91b4dd
🧠 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
2025-06-07 18:52:22 -04:00

437 lines
16 KiB
JavaScript

const jwt = require('jsonwebtoken');
const { nanoid } = require('nanoid');
const { sendEvent } = require('@librechat/api');
const { tool } = require('@langchain/core/tools');
const { logger } = require('@librechat/data-schemas');
const { GraphEvents, sleep } = require('@librechat/agents');
const {
Time,
CacheKeys,
StepTypes,
Constants,
AuthTypeEnum,
actionDelimiter,
isImageVisionTool,
actionDomainSeparator,
} = require('librechat-data-provider');
const { refreshAccessToken } = require('~/server/services/TokenService');
const { encryptV2, decryptV2 } = require('~/server/utils/crypto');
const { getActions, deleteActions } = require('~/models/Action');
const { deleteAssistant } = require('~/models/Assistant');
const { getFlowStateManager } = require('~/config');
const { logAxiosError } = require('~/utils');
const { getLogStores } = require('~/cache');
const { findToken } = require('~/models');
const JWT_SECRET = process.env.JWT_SECRET;
const toolNameRegex = /^[a-zA-Z0-9_-]+$/;
const replaceSeparatorRegex = new RegExp(actionDomainSeparator, 'g');
/**
* Validates tool name against regex pattern and updates if necessary.
* @param {object} params - The parameters for the function.
* @param {object} params.req - Express Request.
* @param {FunctionTool} params.tool - The tool object.
* @param {string} params.assistant_id - The assistant ID
* @returns {object|null} - Updated tool object or null if invalid and not an action.
*/
const validateAndUpdateTool = async ({ req, tool, assistant_id }) => {
let actions;
if (isImageVisionTool(tool)) {
return null;
}
if (!toolNameRegex.test(tool.function.name)) {
const [functionName, domain] = tool.function.name.split(actionDelimiter);
actions = await getActions({ assistant_id, user: req.user.id }, true);
const matchingActions = actions.filter((action) => {
const metadata = action.metadata;
return metadata && metadata.domain === domain;
});
const action = matchingActions[0];
if (!action) {
return null;
}
const parsedDomain = await domainParser(domain, true);
if (!parsedDomain) {
return null;
}
tool.function.name = `${functionName}${actionDelimiter}${parsedDomain}`;
}
return tool;
};
/**
* Encodes or decodes a domain name to/from base64, or replacing periods with a custom separator.
*
* Necessary due to `[a-zA-Z0-9_-]*` Regex Validation, limited to a 64-character maximum.
*
* @param {string} domain - The domain name to encode/decode.
* @param {boolean} inverse - False to decode from base64, true to encode to base64.
* @returns {Promise<string>} Encoded or decoded domain string.
*/
async function domainParser(domain, inverse = false) {
if (!domain) {
return;
}
const domainsCache = getLogStores(CacheKeys.ENCODED_DOMAINS);
const cachedDomain = await domainsCache.get(domain);
if (inverse && cachedDomain) {
return domain;
}
if (inverse && domain.length <= Constants.ENCODED_DOMAIN_LENGTH) {
return domain.replace(/\./g, actionDomainSeparator);
}
if (inverse) {
const modifiedDomain = Buffer.from(domain).toString('base64');
const key = modifiedDomain.substring(0, Constants.ENCODED_DOMAIN_LENGTH);
await domainsCache.set(key, modifiedDomain);
return key;
}
if (!cachedDomain) {
return domain.replace(replaceSeparatorRegex, '.');
}
try {
return Buffer.from(cachedDomain, 'base64').toString('utf-8');
} catch (error) {
logger.error(`Failed to parse domain (possibly not base64): ${domain}`, error);
return domain;
}
}
/**
* Loads action sets based on the user and assistant ID.
*
* @param {Object} searchParams - The parameters for loading action sets.
* @param {string} searchParams.user - The user identifier.
* @param {string} [searchParams.agent_id]- The agent identifier.
* @param {string} [searchParams.assistant_id]- The assistant identifier.
* @returns {Promise<Action[] | null>} A promise that resolves to an array of actions or `null` if no match.
*/
async function loadActionSets(searchParams) {
return await getActions(searchParams, true);
}
/**
* Creates a general tool for an entire action set.
*
* @param {Object} params - The parameters for loading action sets.
* @param {string} params.userId
* @param {ServerResponse} params.res
* @param {Action} params.action - The action set. Necessary for decrypting authentication values.
* @param {ActionRequest} params.requestBuilder - The ActionRequest builder class to execute the API call.
* @param {string | undefined} [params.name] - The name of the tool.
* @param {string | undefined} [params.description] - The description for the tool.
* @param {import('zod').ZodTypeAny | undefined} [params.zodSchema] - The Zod schema for tool input validation/definition
* @param {{ oauth_client_id?: string; oauth_client_secret?: string; }} params.encrypted - The encrypted values for the action.
* @returns { Promise<typeof tool | { _call: (toolInput: Object | string) => unknown}> } An object with `_call` method to execute the tool input.
*/
async function createActionTool({
userId,
res,
action,
requestBuilder,
zodSchema,
name,
description,
encrypted,
}) {
/** @type {(toolInput: Object | string, config: GraphRunnableConfig) => Promise<unknown>} */
const _call = async (toolInput, config) => {
try {
/** @type {import('librechat-data-provider').ActionMetadataRuntime} */
const metadata = action.metadata;
const executor = requestBuilder.createExecutor();
const preparedExecutor = executor.setParams(toolInput ?? {});
if (metadata.auth && metadata.auth.type !== AuthTypeEnum.None) {
try {
if (metadata.auth.type === AuthTypeEnum.OAuth && metadata.auth.authorization_url) {
const action_id = action.action_id;
const identifier = `${userId}:${action.action_id}`;
const requestLogin = async () => {
const { args: _args, stepId, ...toolCall } = config.toolCall ?? {};
if (!stepId) {
throw new Error('Tool call is missing stepId');
}
const statePayload = {
nonce: nanoid(),
user: userId,
action_id,
};
const stateToken = jwt.sign(statePayload, JWT_SECRET, { expiresIn: '10m' });
try {
const redirectUri = `${process.env.DOMAIN_CLIENT}/api/actions/${action_id}/oauth/callback`;
const params = new URLSearchParams({
client_id: metadata.oauth_client_id,
scope: metadata.auth.scope,
redirect_uri: redirectUri,
access_type: 'offline',
response_type: 'code',
state: stateToken,
});
const authURL = `${metadata.auth.authorization_url}?${params.toString()}`;
/** @type {{ id: string; delta: AgentToolCallDelta }} */
const data = {
id: stepId,
delta: {
type: StepTypes.TOOL_CALLS,
tool_calls: [{ ...toolCall, args: '' }],
auth: authURL,
expires_at: Date.now() + Time.TWO_MINUTES,
},
};
const flowsCache = getLogStores(CacheKeys.FLOWS);
const flowManager = getFlowStateManager(flowsCache);
await flowManager.createFlowWithHandler(
`${identifier}:oauth_login:${config.metadata.thread_id}:${config.metadata.run_id}`,
'oauth_login',
async () => {
sendEvent(res, { event: GraphEvents.ON_RUN_STEP_DELTA, data });
logger.debug('Sent OAuth login request to client', { action_id, identifier });
return true;
},
config?.signal,
);
logger.debug('Waiting for OAuth Authorization response', { action_id, identifier });
const result = await flowManager.createFlow(
identifier,
'oauth',
{
state: stateToken,
userId: userId,
client_url: metadata.auth.client_url,
redirect_uri: `${process.env.DOMAIN_SERVER}/api/actions/${action_id}/oauth/callback`,
/** Encrypted values */
encrypted_oauth_client_id: encrypted.oauth_client_id,
encrypted_oauth_client_secret: encrypted.oauth_client_secret,
},
config?.signal,
);
logger.debug('Received OAuth Authorization response', { action_id, identifier });
data.delta.auth = undefined;
data.delta.expires_at = undefined;
sendEvent(res, { event: GraphEvents.ON_RUN_STEP_DELTA, data });
await sleep(3000);
metadata.oauth_access_token = result.access_token;
metadata.oauth_refresh_token = result.refresh_token;
const expiresAt = new Date(Date.now() + result.expires_in * 1000);
metadata.oauth_token_expires_at = expiresAt.toISOString();
} catch (error) {
const errorMessage = 'Failed to authenticate OAuth tool';
logger.error(errorMessage, error);
throw new Error(errorMessage);
}
};
const tokenPromises = [];
tokenPromises.push(findToken({ userId, type: 'oauth', identifier }));
tokenPromises.push(
findToken({
userId,
type: 'oauth_refresh',
identifier: `${identifier}:refresh`,
}),
);
const [tokenData, refreshTokenData] = await Promise.all(tokenPromises);
if (tokenData) {
// Valid token exists, add it to metadata for setAuth
metadata.oauth_access_token = await decryptV2(tokenData.token);
if (refreshTokenData) {
metadata.oauth_refresh_token = await decryptV2(refreshTokenData.token);
}
metadata.oauth_token_expires_at = tokenData.expiresAt.toISOString();
} else if (!refreshTokenData) {
// No tokens exist, need to authenticate
await requestLogin();
} else if (refreshTokenData) {
// Refresh token is still valid, use it to get new access token
try {
const refresh_token = await decryptV2(refreshTokenData.token);
const refreshTokens = async () =>
await refreshAccessToken({
userId,
identifier,
refresh_token,
client_url: metadata.auth.client_url,
encrypted_oauth_client_id: encrypted.oauth_client_id,
encrypted_oauth_client_secret: encrypted.oauth_client_secret,
});
const flowsCache = getLogStores(CacheKeys.FLOWS);
const flowManager = getFlowStateManager(flowsCache);
const refreshData = await flowManager.createFlowWithHandler(
`${identifier}:refresh`,
'oauth_refresh',
refreshTokens,
config?.signal,
);
metadata.oauth_access_token = refreshData.access_token;
if (refreshData.refresh_token) {
metadata.oauth_refresh_token = refreshData.refresh_token;
}
const expiresAt = new Date(Date.now() + refreshData.expires_in * 1000);
metadata.oauth_token_expires_at = expiresAt.toISOString();
} catch (error) {
logger.error('Failed to refresh token, requesting new login:', error);
await requestLogin();
}
} else {
await requestLogin();
}
}
await preparedExecutor.setAuth(metadata);
} catch (error) {
if (
error.message.includes('No access token found') ||
error.message.includes('Access token is expired')
) {
throw error;
}
throw new Error(`Authentication failed: ${error.message}`);
}
}
const response = await preparedExecutor.execute();
if (typeof response.data === 'object') {
return JSON.stringify(response.data);
}
return response.data;
} catch (error) {
const message = `API call to ${action.metadata.domain} failed:`;
return logAxiosError({ message, error });
}
};
if (name) {
return tool(_call, {
name: name.replace(replaceSeparatorRegex, '_'),
description: description || '',
schema: zodSchema,
});
}
return {
_call,
};
}
/**
* Encrypts a sensitive value.
* @param {string} value
* @returns {Promise<string>}
*/
async function encryptSensitiveValue(value) {
// Encode API key to handle special characters like ":"
const encodedValue = encodeURIComponent(value);
return await encryptV2(encodedValue);
}
/**
* Decrypts a sensitive value.
* @param {string} value
* @returns {Promise<string>}
*/
async function decryptSensitiveValue(value) {
const decryptedValue = await decryptV2(value);
return decodeURIComponent(decryptedValue);
}
/**
* Encrypts sensitive metadata values for an action.
*
* @param {ActionMetadata} metadata - The action metadata to encrypt.
* @returns {Promise<ActionMetadata>} The updated action metadata with encrypted values.
*/
async function encryptMetadata(metadata) {
const encryptedMetadata = { ...metadata };
// ServiceHttp
if (metadata.auth && metadata.auth.type === AuthTypeEnum.ServiceHttp) {
if (metadata.api_key) {
encryptedMetadata.api_key = await encryptSensitiveValue(metadata.api_key);
}
}
// OAuth
else if (metadata.auth && metadata.auth.type === AuthTypeEnum.OAuth) {
if (metadata.oauth_client_id) {
encryptedMetadata.oauth_client_id = await encryptSensitiveValue(metadata.oauth_client_id);
}
if (metadata.oauth_client_secret) {
encryptedMetadata.oauth_client_secret = await encryptSensitiveValue(
metadata.oauth_client_secret,
);
}
}
return encryptedMetadata;
}
/**
* Decrypts sensitive metadata values for an action.
*
* @param {ActionMetadata} metadata - The action metadata to decrypt.
* @returns {Promise<ActionMetadata>} The updated action metadata with decrypted values.
*/
async function decryptMetadata(metadata) {
const decryptedMetadata = { ...metadata };
// ServiceHttp
if (metadata.auth && metadata.auth.type === AuthTypeEnum.ServiceHttp) {
if (metadata.api_key) {
decryptedMetadata.api_key = await decryptSensitiveValue(metadata.api_key);
}
}
// OAuth
else if (metadata.auth && metadata.auth.type === AuthTypeEnum.OAuth) {
if (metadata.oauth_client_id) {
decryptedMetadata.oauth_client_id = await decryptSensitiveValue(metadata.oauth_client_id);
}
if (metadata.oauth_client_secret) {
decryptedMetadata.oauth_client_secret = await decryptSensitiveValue(
metadata.oauth_client_secret,
);
}
}
return decryptedMetadata;
}
/**
* Deletes an action and its corresponding assistant.
* @param {Object} params - The parameters for the function.
* @param {OpenAIClient} params.req - The Express Request object.
* @param {string} params.assistant_id - The ID of the assistant.
*/
const deleteAssistantActions = async ({ req, assistant_id }) => {
try {
await deleteActions({ assistant_id, user: req.user.id });
await deleteAssistant({ assistant_id, user: req.user.id });
} catch (error) {
const message = 'Trouble deleting Assistant Actions for Assistant ID: ' + assistant_id;
logger.error(message, error);
throw new Error(message);
}
};
module.exports = {
deleteAssistantActions,
validateAndUpdateTool,
createActionTool,
encryptMetadata,
decryptMetadata,
loadActionSets,
domainParser,
};