2025-07-15 16:24:31 -06:00
|
|
|
const { cacheConfig } = require('./cacheConfig');
|
2025-04-12 18:46:36 -04:00
|
|
|
const { Keyv } = require('keyv');
|
2024-07-17 10:47:17 -04:00
|
|
|
const { CacheKeys, ViolationTypes, Time } = require('librechat-data-provider');
|
2025-07-15 16:24:31 -06:00
|
|
|
const { logFile } = require('./keyvFiles');
|
💫 feat: Config File & Custom Endpoints (#1474)
* WIP(backend/api): custom endpoint
* WIP(frontend/client): custom endpoint
* chore: adjust typedefs for configs
* refactor: use data-provider for cache keys and rename enums and custom endpoint for better clarity and compatibility
* feat: loadYaml utility
* refactor: rename back to from and proof-of-concept for creating schemas from user-defined defaults
* refactor: remove custom endpoint from default endpointsConfig as it will be exclusively managed by yaml config
* refactor(EndpointController): rename variables for clarity
* feat: initial load custom config
* feat(server/utils): add simple `isUserProvided` helper
* chore(types): update TConfig type
* refactor: remove custom endpoint handling from model services as will be handled by config, modularize fetching of models
* feat: loadCustomConfig, loadConfigEndpoints, loadConfigModels
* chore: reorganize server init imports, invoke loadCustomConfig
* refactor(loadConfigEndpoints/Models): return each custom endpoint as standalone endpoint
* refactor(Endpoint/ModelController): spread config values after default (temporary)
* chore(client): fix type issues
* WIP: first pass for multiple custom endpoints
- add endpointType to Conversation schema
- add update zod schemas for both convo/presets to allow non-EModelEndpoint value as endpoint (also using type assertion)
- use `endpointType` value as `endpoint` where mapping to type is necessary using this field
- use custom defined `endpoint` value and not type for mapping to modelsConfig
- misc: add return type to `getDefaultEndpoint`
- in `useNewConvo`, add the endpointType if it wasn't already added to conversation
- EndpointsMenu: use user-defined endpoint name as Title in menu
- TODO: custom icon via custom config, change unknown to robot icon
* refactor(parseConvo): pass args as an object and change where used accordingly; chore: comment out 'create schema' code
* chore: remove unused availableModels field in TConfig type
* refactor(parseCompactConvo): pass args as an object and change where used accordingly
* feat: chat through custom endpoint
* chore(message/convoSchemas): avoid saving empty arrays
* fix(BaseClient/saveMessageToDatabase): save endpointType
* refactor(ChatRoute): show Spinner if endpointsQuery or modelsQuery are still loading, which is apparent with slow fetching of models/remote config on first serve
* fix(useConversation): assign endpointType if it's missing
* fix(SaveAsPreset): pass real endpoint and endpointType when saving Preset)
* chore: recorganize types order for TConfig, add `iconURL`
* feat: custom endpoint icon support:
- use UnknownIcon in all icon contexts
- add mistral and openrouter as known endpoints, and add their icons
- iconURL support
* fix(presetSchema): move endpointType to default schema definitions shared between convoSchema and defaults
* refactor(Settings/OpenAI): remove legacy `isOpenAI` flag
* fix(OpenAIClient): do not invoke abortCompletion on completion error
* feat: add responseSender/label support for custom endpoints:
- use defaultModelLabel field in endpointOption
- add model defaults for custom endpoints in `getResponseSender`
- add `useGetSender` hook which uses EndpointsQuery to determine `defaultModelLabel`
- include defaultModelLabel from endpointConfig in custom endpoint client options
- pass `endpointType` to `getResponseSender`
* feat(OpenAIClient): use custom options from config file
* refactor: rename `defaultModelLabel` to `modelDisplayLabel`
* refactor(data-provider): separate concerns from `schemas` into `parsers`, `config`, and fix imports elsewhere
* feat: `iconURL` and extract environment variables from custom endpoint config values
* feat: custom config validation via zod schema, rename and move to `./projectRoot/librechat.yaml`
* docs: custom config docs and examples
* fix(OpenAIClient/mistral): mistral does not allow singular system message, also add `useChatCompletion` flag to use openai-node for title completions
* fix(custom/initializeClient): extract env var and use `isUserProvided` function
* Update librechat.example.yaml
* feat(InputWithLabel): add className props, and forwardRef
* fix(streamResponse): handle error edge case where either messages or convos query throws an error
* fix(useSSE): handle errorHandler edge cases where error response is and is not properly formatted from API, especially when a conversationId is not yet provided, which ensures stream is properly closed on error
* feat: user_provided keys for custom endpoints
* fix(config/endpointSchema): do not allow default endpoint values in custom endpoint `name`
* feat(loadConfigModels): extract env variables and optimize fetching models
* feat: support custom endpoint iconURL for messages and Nav
* feat(OpenAIClient): add/dropParams support
* docs: update docs with default params, add/dropParams, and notes to use config file instead of `OPENAI_REVERSE_PROXY`
* docs: update docs with additional notes
* feat(maxTokensMap): add mistral models (32k context)
* docs: update openrouter notes
* Update ai_setup.md
* docs(custom_config): add table of contents and fix note about custom name
* docs(custom_config): reorder ToC
* Update custom_config.md
* Add note about `max_tokens` field in custom_config.md
2024-01-03 09:22:48 -05:00
|
|
|
const keyvMongo = require('./keyvMongo');
|
2025-07-15 16:24:31 -06:00
|
|
|
const { standardCache, sessionCache, violationCache } = require('./cacheFactory');
|
2025-05-22 14:19:24 +02:00
|
|
|
|
feat: Message Rate Limiters, Violation Logging, & Ban System 🔨 (#903)
* refactor: require Auth middleware in route index files
* feat: concurrent message limiter
* feat: complete concurrent message limiter with caching
* refactor: SSE response methods separated from handleText
* fix(abortMiddleware): fix req and res order to standard, use endpointOption in req.body
* chore: minor name changes
* refactor: add isUUID condition to saveMessage
* fix(concurrentLimiter): logic correctly handles the max number of concurrent messages and res closing/finalization
* chore: bump keyv and remove console.log from Message
* fix(concurrentLimiter): ensure messages are only saved in later message children
* refactor(concurrentLimiter): use KeyvFile instead, could make other stores configurable in the future
* feat: add denyRequest function for error responses
* feat(utils): add isStringTruthy function
Introduce the isStringTruthy function to the utilities module to check if a string value is a case-insensitive match for 'true'
* feat: add optional message rate limiters by IP and userId
* feat: add optional message rate limiters by IP and userId to edit route
* refactor: rename isStringTruthy to isTrue for brevity
* refactor(getError): use map to make code cleaner
* refactor: use memory for concurrent rate limiter to prevent clearing on startup/exit, add multiple log files, fix error message for concurrent violation
* feat: check if errorMessage is object, stringify if so
* chore: send object to denyRequest which will stringify it
* feat: log excessive requests
* fix(getError): correctly pluralize messages
* refactor(limiters): make type consistent between logs and errorMessage
* refactor(cache): move files out of lib/db into separate cache dir
>> feat: add getLogStores function so Keyv instance is not redundantly created on every violation
feat: separate violation logging to own function with logViolation
* fix: cache/index.js export, properly record userViolations
* refactor(messageLimiters): use new logging method, add logging to registrations
* refactor(logViolation): make userLogs an array of logs per user
* feat: add logging to login limiter
* refactor: pass req as first param to logViolation and record offending IP
* refactor: rename isTrue helper fn to isEnabled
* feat: add simple non_browser check and log violation
* fix: open handles in unit tests, remove KeyvMongo as not used and properly mock global fetch
* chore: adjust nodemon ignore paths to properly ignore logs
* feat: add math helper function for safe use of eval
* refactor(api/convos): use middleware at top of file to avoid redundancy
* feat: add delete all static method for Sessions
* fix: redirect to login on refresh if user is not found, or the session is not found but hasn't expired (ban case)
* refactor(getLogStores): adjust return type
* feat: add ban violation and check ban logic
refactor(logViolation): pass both req and res objects
* feat: add removePorts helper function
* refactor: rename getError to getMessageError and add getLoginError for displaying different login errors
* fix(AuthContext): fix type issue and remove unused code
* refactor(bans): ban by ip and user id, send response based on origin
* chore: add frontend ban messages
* refactor(routes/oauth): add ban check to handler, also consolidate logic to avoid redundancy
* feat: add ban check to AI messaging routes
* feat: add ban check to login/registration
* fix(ci/api): mock KeyvMongo to avoid tests hanging
* docs: update .env.example
> refactor(banViolation): calculate interval rate crossover, early return if duration is invalid
ci(banViolation): add tests to ensure users are only banned when expected
* docs: improve wording for mod system
* feat: add configurable env variables for violation scores
* chore: add jsdoc for uaParser.js
* chore: improve ban text log
* chore: update bun test scripts
* refactor(math.js): add fallback values
* fix(KeyvMongo/banLogs): refactor keyv instances to top of files to avoid memory leaks, refactor ban logic to use getLogStores instead
refactor(getLogStores): get a single log store by type
* fix(ci): refactor tests due to banLogs changes, also make sure to clear and revoke sessions even if ban duration is 0
* fix(banViolation.js): getLogStores import
* feat: handle 500 code error at login
* fix(middleware): handle case where user.id is _id and not just id
* ci: add ban secrets for backend unit tests
* refactor: logout user upon ban
* chore: log session delete message only if deletedCount > 0
* refactor: change default ban duration (2h) and make logic more clear in JSDOC
* fix: login and registration limiters will now return rate limiting error
* fix: userId not parsable as non ObjectId string
* feat: add useTimeout hook to properly clear timeouts when invoking functions within them
refactor(AuthContext): cleanup code by using new hook and defining types in ~/common
* fix: login error message for rate limits
* docs: add info for automated mod system and rate limiters, update other docs accordingly
* chore: bump data-provider version
2023-09-13 10:57:07 -04:00
|
|
|
const namespaces = {
|
2025-07-15 16:24:31 -06:00
|
|
|
[ViolationTypes.GENERAL]: new Keyv({ store: logFile, namespace: 'violations' }),
|
|
|
|
[ViolationTypes.LOGINS]: violationCache(ViolationTypes.LOGINS),
|
|
|
|
[ViolationTypes.CONCURRENT]: violationCache(ViolationTypes.CONCURRENT),
|
|
|
|
[ViolationTypes.NON_BROWSER]: violationCache(ViolationTypes.NON_BROWSER),
|
|
|
|
[ViolationTypes.MESSAGE_LIMIT]: violationCache(ViolationTypes.MESSAGE_LIMIT),
|
|
|
|
[ViolationTypes.REGISTRATIONS]: violationCache(ViolationTypes.REGISTRATIONS),
|
|
|
|
[ViolationTypes.TOKEN_BALANCE]: violationCache(ViolationTypes.TOKEN_BALANCE),
|
|
|
|
[ViolationTypes.TTS_LIMIT]: violationCache(ViolationTypes.TTS_LIMIT),
|
|
|
|
[ViolationTypes.STT_LIMIT]: violationCache(ViolationTypes.STT_LIMIT),
|
|
|
|
[ViolationTypes.CONVO_ACCESS]: violationCache(ViolationTypes.CONVO_ACCESS),
|
|
|
|
[ViolationTypes.TOOL_CALL_LIMIT]: violationCache(ViolationTypes.TOOL_CALL_LIMIT),
|
|
|
|
[ViolationTypes.FILE_UPLOAD_LIMIT]: violationCache(ViolationTypes.FILE_UPLOAD_LIMIT),
|
|
|
|
[ViolationTypes.VERIFY_EMAIL_LIMIT]: violationCache(ViolationTypes.VERIFY_EMAIL_LIMIT),
|
|
|
|
[ViolationTypes.RESET_PASSWORD_LIMIT]: violationCache(ViolationTypes.RESET_PASSWORD_LIMIT),
|
|
|
|
[ViolationTypes.ILLEGAL_MODEL_REQUEST]: violationCache(ViolationTypes.ILLEGAL_MODEL_REQUEST),
|
|
|
|
[ViolationTypes.BAN]: new Keyv({
|
2024-04-20 15:02:56 -04:00
|
|
|
store: keyvMongo,
|
2025-07-15 16:24:31 -06:00
|
|
|
namespace: CacheKeys.BANS,
|
|
|
|
ttl: cacheConfig.BAN_DURATION,
|
2024-04-20 15:02:56 -04:00
|
|
|
}),
|
2025-07-15 16:24:31 -06:00
|
|
|
|
|
|
|
[CacheKeys.OPENID_SESSION]: sessionCache(CacheKeys.OPENID_SESSION),
|
|
|
|
[CacheKeys.SAML_SESSION]: sessionCache(CacheKeys.SAML_SESSION),
|
|
|
|
|
|
|
|
[CacheKeys.ROLES]: standardCache(CacheKeys.ROLES),
|
|
|
|
[CacheKeys.MCP_TOOLS]: standardCache(CacheKeys.MCP_TOOLS),
|
|
|
|
[CacheKeys.CONFIG_STORE]: standardCache(CacheKeys.CONFIG_STORE),
|
|
|
|
[CacheKeys.PENDING_REQ]: standardCache(CacheKeys.PENDING_REQ),
|
|
|
|
[CacheKeys.ENCODED_DOMAINS]: new Keyv({ store: keyvMongo, namespace: CacheKeys.ENCODED_DOMAINS }),
|
|
|
|
[CacheKeys.ABORT_KEYS]: standardCache(CacheKeys.ABORT_KEYS, Time.TEN_MINUTES),
|
|
|
|
[CacheKeys.TOKEN_CONFIG]: standardCache(CacheKeys.TOKEN_CONFIG, Time.THIRTY_MINUTES),
|
|
|
|
[CacheKeys.GEN_TITLE]: standardCache(CacheKeys.GEN_TITLE, Time.TWO_MINUTES),
|
|
|
|
[CacheKeys.S3_EXPIRY_INTERVAL]: standardCache(CacheKeys.S3_EXPIRY_INTERVAL, Time.THIRTY_MINUTES),
|
|
|
|
[CacheKeys.MODEL_QUERIES]: standardCache(CacheKeys.MODEL_QUERIES),
|
|
|
|
[CacheKeys.AUDIO_RUNS]: standardCache(CacheKeys.AUDIO_RUNS, Time.TEN_MINUTES),
|
|
|
|
[CacheKeys.MESSAGES]: standardCache(CacheKeys.MESSAGES, Time.ONE_MINUTE),
|
|
|
|
[CacheKeys.FLOWS]: standardCache(CacheKeys.FLOWS, Time.ONE_MINUTE * 3),
|
|
|
|
[CacheKeys.OPENID_EXCHANGED_TOKENS]: standardCache(
|
|
|
|
CacheKeys.OPENID_EXCHANGED_TOKENS,
|
|
|
|
Time.TEN_MINUTES,
|
2024-02-19 22:47:39 -05:00
|
|
|
),
|
feat: Message Rate Limiters, Violation Logging, & Ban System 🔨 (#903)
* refactor: require Auth middleware in route index files
* feat: concurrent message limiter
* feat: complete concurrent message limiter with caching
* refactor: SSE response methods separated from handleText
* fix(abortMiddleware): fix req and res order to standard, use endpointOption in req.body
* chore: minor name changes
* refactor: add isUUID condition to saveMessage
* fix(concurrentLimiter): logic correctly handles the max number of concurrent messages and res closing/finalization
* chore: bump keyv and remove console.log from Message
* fix(concurrentLimiter): ensure messages are only saved in later message children
* refactor(concurrentLimiter): use KeyvFile instead, could make other stores configurable in the future
* feat: add denyRequest function for error responses
* feat(utils): add isStringTruthy function
Introduce the isStringTruthy function to the utilities module to check if a string value is a case-insensitive match for 'true'
* feat: add optional message rate limiters by IP and userId
* feat: add optional message rate limiters by IP and userId to edit route
* refactor: rename isStringTruthy to isTrue for brevity
* refactor(getError): use map to make code cleaner
* refactor: use memory for concurrent rate limiter to prevent clearing on startup/exit, add multiple log files, fix error message for concurrent violation
* feat: check if errorMessage is object, stringify if so
* chore: send object to denyRequest which will stringify it
* feat: log excessive requests
* fix(getError): correctly pluralize messages
* refactor(limiters): make type consistent between logs and errorMessage
* refactor(cache): move files out of lib/db into separate cache dir
>> feat: add getLogStores function so Keyv instance is not redundantly created on every violation
feat: separate violation logging to own function with logViolation
* fix: cache/index.js export, properly record userViolations
* refactor(messageLimiters): use new logging method, add logging to registrations
* refactor(logViolation): make userLogs an array of logs per user
* feat: add logging to login limiter
* refactor: pass req as first param to logViolation and record offending IP
* refactor: rename isTrue helper fn to isEnabled
* feat: add simple non_browser check and log violation
* fix: open handles in unit tests, remove KeyvMongo as not used and properly mock global fetch
* chore: adjust nodemon ignore paths to properly ignore logs
* feat: add math helper function for safe use of eval
* refactor(api/convos): use middleware at top of file to avoid redundancy
* feat: add delete all static method for Sessions
* fix: redirect to login on refresh if user is not found, or the session is not found but hasn't expired (ban case)
* refactor(getLogStores): adjust return type
* feat: add ban violation and check ban logic
refactor(logViolation): pass both req and res objects
* feat: add removePorts helper function
* refactor: rename getError to getMessageError and add getLoginError for displaying different login errors
* fix(AuthContext): fix type issue and remove unused code
* refactor(bans): ban by ip and user id, send response based on origin
* chore: add frontend ban messages
* refactor(routes/oauth): add ban check to handler, also consolidate logic to avoid redundancy
* feat: add ban check to AI messaging routes
* feat: add ban check to login/registration
* fix(ci/api): mock KeyvMongo to avoid tests hanging
* docs: update .env.example
> refactor(banViolation): calculate interval rate crossover, early return if duration is invalid
ci(banViolation): add tests to ensure users are only banned when expected
* docs: improve wording for mod system
* feat: add configurable env variables for violation scores
* chore: add jsdoc for uaParser.js
* chore: improve ban text log
* chore: update bun test scripts
* refactor(math.js): add fallback values
* fix(KeyvMongo/banLogs): refactor keyv instances to top of files to avoid memory leaks, refactor ban logic to use getLogStores instead
refactor(getLogStores): get a single log store by type
* fix(ci): refactor tests due to banLogs changes, also make sure to clear and revoke sessions even if ban duration is 0
* fix(banViolation.js): getLogStores import
* feat: handle 500 code error at login
* fix(middleware): handle case where user.id is _id and not just id
* ci: add ban secrets for backend unit tests
* refactor: logout user upon ban
* chore: log session delete message only if deletedCount > 0
* refactor: change default ban duration (2h) and make logic more clear in JSDOC
* fix: login and registration limiters will now return rate limiting error
* fix: userId not parsable as non ObjectId string
* feat: add useTimeout hook to properly clear timeouts when invoking functions within them
refactor(AuthContext): cleanup code by using new hook and defining types in ~/common
* fix: login error message for rate limits
* docs: add info for automated mod system and rate limiters, update other docs accordingly
* chore: bump data-provider version
2023-09-13 10:57:07 -04:00
|
|
|
};
|
|
|
|
|
2024-12-28 17:32:05 -05:00
|
|
|
/**
|
|
|
|
* Gets all cache stores that have TTL configured
|
|
|
|
* @returns {Keyv[]}
|
|
|
|
*/
|
|
|
|
function getTTLStores() {
|
2025-01-03 18:11:14 -05:00
|
|
|
return Object.values(namespaces).filter(
|
2025-07-15 16:24:31 -06:00
|
|
|
(store) =>
|
|
|
|
store instanceof Keyv &&
|
|
|
|
parseInt(store.opts?.ttl ?? '0') > 0 &&
|
|
|
|
!store.opts?.store?.constructor?.name?.includes('Redis'), // Only include non-Redis stores
|
2024-12-28 17:32:05 -05:00
|
|
|
);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Clears entries older than the cache's TTL
|
|
|
|
* @param {Keyv} cache
|
|
|
|
*/
|
|
|
|
async function clearExpiredFromCache(cache) {
|
|
|
|
if (!cache?.opts?.store?.entries) {
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
const ttl = cache.opts.ttl;
|
|
|
|
if (!ttl) {
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
const expiryTime = Date.now() - ttl;
|
|
|
|
let cleared = 0;
|
|
|
|
|
|
|
|
// Get all keys first to avoid modification during iteration
|
|
|
|
const keys = Array.from(cache.opts.store.keys());
|
|
|
|
|
|
|
|
for (const key of keys) {
|
|
|
|
try {
|
|
|
|
const raw = cache.opts.store.get(key);
|
2025-01-03 18:11:14 -05:00
|
|
|
if (!raw) {
|
|
|
|
continue;
|
|
|
|
}
|
2024-12-28 17:32:05 -05:00
|
|
|
|
|
|
|
const data = cache.opts.deserialize(raw);
|
|
|
|
// Check if the entry is older than TTL
|
|
|
|
if (data?.expires && data.expires <= expiryTime) {
|
|
|
|
const deleted = await cache.opts.store.delete(key);
|
|
|
|
if (!deleted) {
|
2025-07-15 16:24:31 -06:00
|
|
|
cacheConfig.DEBUG_MEMORY_CACHE &&
|
2025-01-03 18:11:14 -05:00
|
|
|
console.warn(`[Cache] Error deleting entry: ${key} from ${cache.opts.namespace}`);
|
2024-12-28 17:32:05 -05:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
cleared++;
|
|
|
|
}
|
|
|
|
} catch (error) {
|
2025-07-15 16:24:31 -06:00
|
|
|
cacheConfig.DEBUG_MEMORY_CACHE &&
|
2025-01-03 18:11:14 -05:00
|
|
|
console.log(`[Cache] Error processing entry from ${cache.opts.namespace}:`, error);
|
2024-12-28 17:32:05 -05:00
|
|
|
const deleted = await cache.opts.store.delete(key);
|
|
|
|
if (!deleted) {
|
2025-07-15 16:24:31 -06:00
|
|
|
cacheConfig.DEBUG_MEMORY_CACHE &&
|
2025-01-03 18:11:14 -05:00
|
|
|
console.warn(`[Cache] Error deleting entry: ${key} from ${cache.opts.namespace}`);
|
2024-12-28 17:32:05 -05:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
cleared++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (cleared > 0) {
|
2025-07-15 16:24:31 -06:00
|
|
|
cacheConfig.DEBUG_MEMORY_CACHE &&
|
2025-01-03 18:11:14 -05:00
|
|
|
console.log(
|
|
|
|
`[Cache] Cleared ${cleared} entries older than ${ttl}ms from ${cache.opts.namespace}`,
|
|
|
|
);
|
2024-12-28 17:32:05 -05:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
const auditCache = () => {
|
|
|
|
const ttlStores = getTTLStores();
|
|
|
|
console.log('[Cache] Starting audit');
|
|
|
|
|
2025-01-03 18:11:14 -05:00
|
|
|
ttlStores.forEach((store) => {
|
2024-12-28 17:32:05 -05:00
|
|
|
if (!store?.opts?.store?.entries) {
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
console.log(`[Cache] ${store.opts.namespace} entries:`, {
|
|
|
|
count: store.opts.store.size,
|
|
|
|
ttl: store.opts.ttl,
|
|
|
|
keys: Array.from(store.opts.store.keys()),
|
2025-01-03 18:11:14 -05:00
|
|
|
entriesWithTimestamps: Array.from(store.opts.store.entries()).map(([key, value]) => ({
|
|
|
|
key,
|
|
|
|
value,
|
|
|
|
})),
|
2024-12-28 17:32:05 -05:00
|
|
|
});
|
|
|
|
});
|
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
2025-01-03 18:11:14 -05:00
|
|
|
* Clears expired entries from all TTL-enabled stores
|
|
|
|
*/
|
2024-12-28 17:32:05 -05:00
|
|
|
async function clearAllExpiredFromCache() {
|
|
|
|
const ttlStores = getTTLStores();
|
2025-01-03 18:11:14 -05:00
|
|
|
await Promise.all(ttlStores.map((store) => clearExpiredFromCache(store)));
|
2024-12-28 17:32:05 -05:00
|
|
|
|
|
|
|
// Force garbage collection if available (Node.js with --expose-gc flag)
|
|
|
|
if (global.gc) {
|
|
|
|
global.gc();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2025-07-15 16:24:31 -06:00
|
|
|
if (!cacheConfig.USE_REDIS && !cacheConfig.CI) {
|
2024-12-28 17:32:05 -05:00
|
|
|
/** @type {Set<NodeJS.Timeout>} */
|
|
|
|
const cleanupIntervals = new Set();
|
|
|
|
|
|
|
|
// Clear expired entries every 30 seconds
|
|
|
|
const cleanup = setInterval(() => {
|
|
|
|
clearAllExpiredFromCache();
|
|
|
|
}, Time.THIRTY_SECONDS);
|
|
|
|
|
|
|
|
cleanupIntervals.add(cleanup);
|
|
|
|
|
2025-07-15 16:24:31 -06:00
|
|
|
if (cacheConfig.DEBUG_MEMORY_CACHE) {
|
2024-12-28 17:32:05 -05:00
|
|
|
const monitor = setInterval(() => {
|
|
|
|
const ttlStores = getTTLStores();
|
|
|
|
const memory = process.memoryUsage();
|
|
|
|
const totalSize = ttlStores.reduce((sum, store) => sum + (store.opts?.store?.size ?? 0), 0);
|
|
|
|
|
|
|
|
console.log('[Cache] Memory usage:', {
|
|
|
|
heapUsed: `${(memory.heapUsed / 1024 / 1024).toFixed(2)} MB`,
|
|
|
|
heapTotal: `${(memory.heapTotal / 1024 / 1024).toFixed(2)} MB`,
|
|
|
|
rss: `${(memory.rss / 1024 / 1024).toFixed(2)} MB`,
|
|
|
|
external: `${(memory.external / 1024 / 1024).toFixed(2)} MB`,
|
|
|
|
totalCacheEntries: totalSize,
|
|
|
|
});
|
|
|
|
|
|
|
|
auditCache();
|
|
|
|
}, Time.ONE_MINUTE);
|
|
|
|
|
|
|
|
cleanupIntervals.add(monitor);
|
|
|
|
}
|
|
|
|
|
|
|
|
const dispose = () => {
|
2025-07-15 16:24:31 -06:00
|
|
|
cacheConfig.DEBUG_MEMORY_CACHE && console.log('[Cache] Cleaning up and shutting down...');
|
2025-01-03 18:11:14 -05:00
|
|
|
cleanupIntervals.forEach((interval) => clearInterval(interval));
|
2024-12-28 17:32:05 -05:00
|
|
|
cleanupIntervals.clear();
|
|
|
|
|
|
|
|
// One final cleanup before exit
|
|
|
|
clearAllExpiredFromCache().then(() => {
|
2025-07-15 16:24:31 -06:00
|
|
|
cacheConfig.DEBUG_MEMORY_CACHE && console.log('[Cache] Final cleanup completed');
|
2024-12-28 17:32:05 -05:00
|
|
|
process.exit(0);
|
|
|
|
});
|
|
|
|
};
|
|
|
|
|
|
|
|
// Handle various termination signals
|
|
|
|
process.on('SIGTERM', dispose);
|
|
|
|
process.on('SIGINT', dispose);
|
|
|
|
process.on('SIGQUIT', dispose);
|
|
|
|
process.on('SIGHUP', dispose);
|
|
|
|
}
|
|
|
|
|
feat: Message Rate Limiters, Violation Logging, & Ban System 🔨 (#903)
* refactor: require Auth middleware in route index files
* feat: concurrent message limiter
* feat: complete concurrent message limiter with caching
* refactor: SSE response methods separated from handleText
* fix(abortMiddleware): fix req and res order to standard, use endpointOption in req.body
* chore: minor name changes
* refactor: add isUUID condition to saveMessage
* fix(concurrentLimiter): logic correctly handles the max number of concurrent messages and res closing/finalization
* chore: bump keyv and remove console.log from Message
* fix(concurrentLimiter): ensure messages are only saved in later message children
* refactor(concurrentLimiter): use KeyvFile instead, could make other stores configurable in the future
* feat: add denyRequest function for error responses
* feat(utils): add isStringTruthy function
Introduce the isStringTruthy function to the utilities module to check if a string value is a case-insensitive match for 'true'
* feat: add optional message rate limiters by IP and userId
* feat: add optional message rate limiters by IP and userId to edit route
* refactor: rename isStringTruthy to isTrue for brevity
* refactor(getError): use map to make code cleaner
* refactor: use memory for concurrent rate limiter to prevent clearing on startup/exit, add multiple log files, fix error message for concurrent violation
* feat: check if errorMessage is object, stringify if so
* chore: send object to denyRequest which will stringify it
* feat: log excessive requests
* fix(getError): correctly pluralize messages
* refactor(limiters): make type consistent between logs and errorMessage
* refactor(cache): move files out of lib/db into separate cache dir
>> feat: add getLogStores function so Keyv instance is not redundantly created on every violation
feat: separate violation logging to own function with logViolation
* fix: cache/index.js export, properly record userViolations
* refactor(messageLimiters): use new logging method, add logging to registrations
* refactor(logViolation): make userLogs an array of logs per user
* feat: add logging to login limiter
* refactor: pass req as first param to logViolation and record offending IP
* refactor: rename isTrue helper fn to isEnabled
* feat: add simple non_browser check and log violation
* fix: open handles in unit tests, remove KeyvMongo as not used and properly mock global fetch
* chore: adjust nodemon ignore paths to properly ignore logs
* feat: add math helper function for safe use of eval
* refactor(api/convos): use middleware at top of file to avoid redundancy
* feat: add delete all static method for Sessions
* fix: redirect to login on refresh if user is not found, or the session is not found but hasn't expired (ban case)
* refactor(getLogStores): adjust return type
* feat: add ban violation and check ban logic
refactor(logViolation): pass both req and res objects
* feat: add removePorts helper function
* refactor: rename getError to getMessageError and add getLoginError for displaying different login errors
* fix(AuthContext): fix type issue and remove unused code
* refactor(bans): ban by ip and user id, send response based on origin
* chore: add frontend ban messages
* refactor(routes/oauth): add ban check to handler, also consolidate logic to avoid redundancy
* feat: add ban check to AI messaging routes
* feat: add ban check to login/registration
* fix(ci/api): mock KeyvMongo to avoid tests hanging
* docs: update .env.example
> refactor(banViolation): calculate interval rate crossover, early return if duration is invalid
ci(banViolation): add tests to ensure users are only banned when expected
* docs: improve wording for mod system
* feat: add configurable env variables for violation scores
* chore: add jsdoc for uaParser.js
* chore: improve ban text log
* chore: update bun test scripts
* refactor(math.js): add fallback values
* fix(KeyvMongo/banLogs): refactor keyv instances to top of files to avoid memory leaks, refactor ban logic to use getLogStores instead
refactor(getLogStores): get a single log store by type
* fix(ci): refactor tests due to banLogs changes, also make sure to clear and revoke sessions even if ban duration is 0
* fix(banViolation.js): getLogStores import
* feat: handle 500 code error at login
* fix(middleware): handle case where user.id is _id and not just id
* ci: add ban secrets for backend unit tests
* refactor: logout user upon ban
* chore: log session delete message only if deletedCount > 0
* refactor: change default ban duration (2h) and make logic more clear in JSDOC
* fix: login and registration limiters will now return rate limiting error
* fix: userId not parsable as non ObjectId string
* feat: add useTimeout hook to properly clear timeouts when invoking functions within them
refactor(AuthContext): cleanup code by using new hook and defining types in ~/common
* fix: login error message for rate limits
* docs: add info for automated mod system and rate limiters, update other docs accordingly
* chore: bump data-provider version
2023-09-13 10:57:07 -04:00
|
|
|
/**
|
2023-10-11 17:05:47 -04:00
|
|
|
* Returns the keyv cache specified by type.
|
|
|
|
* If an invalid type is passed, an error will be thrown.
|
feat: Message Rate Limiters, Violation Logging, & Ban System 🔨 (#903)
* refactor: require Auth middleware in route index files
* feat: concurrent message limiter
* feat: complete concurrent message limiter with caching
* refactor: SSE response methods separated from handleText
* fix(abortMiddleware): fix req and res order to standard, use endpointOption in req.body
* chore: minor name changes
* refactor: add isUUID condition to saveMessage
* fix(concurrentLimiter): logic correctly handles the max number of concurrent messages and res closing/finalization
* chore: bump keyv and remove console.log from Message
* fix(concurrentLimiter): ensure messages are only saved in later message children
* refactor(concurrentLimiter): use KeyvFile instead, could make other stores configurable in the future
* feat: add denyRequest function for error responses
* feat(utils): add isStringTruthy function
Introduce the isStringTruthy function to the utilities module to check if a string value is a case-insensitive match for 'true'
* feat: add optional message rate limiters by IP and userId
* feat: add optional message rate limiters by IP and userId to edit route
* refactor: rename isStringTruthy to isTrue for brevity
* refactor(getError): use map to make code cleaner
* refactor: use memory for concurrent rate limiter to prevent clearing on startup/exit, add multiple log files, fix error message for concurrent violation
* feat: check if errorMessage is object, stringify if so
* chore: send object to denyRequest which will stringify it
* feat: log excessive requests
* fix(getError): correctly pluralize messages
* refactor(limiters): make type consistent between logs and errorMessage
* refactor(cache): move files out of lib/db into separate cache dir
>> feat: add getLogStores function so Keyv instance is not redundantly created on every violation
feat: separate violation logging to own function with logViolation
* fix: cache/index.js export, properly record userViolations
* refactor(messageLimiters): use new logging method, add logging to registrations
* refactor(logViolation): make userLogs an array of logs per user
* feat: add logging to login limiter
* refactor: pass req as first param to logViolation and record offending IP
* refactor: rename isTrue helper fn to isEnabled
* feat: add simple non_browser check and log violation
* fix: open handles in unit tests, remove KeyvMongo as not used and properly mock global fetch
* chore: adjust nodemon ignore paths to properly ignore logs
* feat: add math helper function for safe use of eval
* refactor(api/convos): use middleware at top of file to avoid redundancy
* feat: add delete all static method for Sessions
* fix: redirect to login on refresh if user is not found, or the session is not found but hasn't expired (ban case)
* refactor(getLogStores): adjust return type
* feat: add ban violation and check ban logic
refactor(logViolation): pass both req and res objects
* feat: add removePorts helper function
* refactor: rename getError to getMessageError and add getLoginError for displaying different login errors
* fix(AuthContext): fix type issue and remove unused code
* refactor(bans): ban by ip and user id, send response based on origin
* chore: add frontend ban messages
* refactor(routes/oauth): add ban check to handler, also consolidate logic to avoid redundancy
* feat: add ban check to AI messaging routes
* feat: add ban check to login/registration
* fix(ci/api): mock KeyvMongo to avoid tests hanging
* docs: update .env.example
> refactor(banViolation): calculate interval rate crossover, early return if duration is invalid
ci(banViolation): add tests to ensure users are only banned when expected
* docs: improve wording for mod system
* feat: add configurable env variables for violation scores
* chore: add jsdoc for uaParser.js
* chore: improve ban text log
* chore: update bun test scripts
* refactor(math.js): add fallback values
* fix(KeyvMongo/banLogs): refactor keyv instances to top of files to avoid memory leaks, refactor ban logic to use getLogStores instead
refactor(getLogStores): get a single log store by type
* fix(ci): refactor tests due to banLogs changes, also make sure to clear and revoke sessions even if ban duration is 0
* fix(banViolation.js): getLogStores import
* feat: handle 500 code error at login
* fix(middleware): handle case where user.id is _id and not just id
* ci: add ban secrets for backend unit tests
* refactor: logout user upon ban
* chore: log session delete message only if deletedCount > 0
* refactor: change default ban duration (2h) and make logic more clear in JSDOC
* fix: login and registration limiters will now return rate limiting error
* fix: userId not parsable as non ObjectId string
* feat: add useTimeout hook to properly clear timeouts when invoking functions within them
refactor(AuthContext): cleanup code by using new hook and defining types in ~/common
* fix: login error message for rate limits
* docs: add info for automated mod system and rate limiters, update other docs accordingly
* chore: bump data-provider version
2023-09-13 10:57:07 -04:00
|
|
|
*
|
💫 feat: Config File & Custom Endpoints (#1474)
* WIP(backend/api): custom endpoint
* WIP(frontend/client): custom endpoint
* chore: adjust typedefs for configs
* refactor: use data-provider for cache keys and rename enums and custom endpoint for better clarity and compatibility
* feat: loadYaml utility
* refactor: rename back to from and proof-of-concept for creating schemas from user-defined defaults
* refactor: remove custom endpoint from default endpointsConfig as it will be exclusively managed by yaml config
* refactor(EndpointController): rename variables for clarity
* feat: initial load custom config
* feat(server/utils): add simple `isUserProvided` helper
* chore(types): update TConfig type
* refactor: remove custom endpoint handling from model services as will be handled by config, modularize fetching of models
* feat: loadCustomConfig, loadConfigEndpoints, loadConfigModels
* chore: reorganize server init imports, invoke loadCustomConfig
* refactor(loadConfigEndpoints/Models): return each custom endpoint as standalone endpoint
* refactor(Endpoint/ModelController): spread config values after default (temporary)
* chore(client): fix type issues
* WIP: first pass for multiple custom endpoints
- add endpointType to Conversation schema
- add update zod schemas for both convo/presets to allow non-EModelEndpoint value as endpoint (also using type assertion)
- use `endpointType` value as `endpoint` where mapping to type is necessary using this field
- use custom defined `endpoint` value and not type for mapping to modelsConfig
- misc: add return type to `getDefaultEndpoint`
- in `useNewConvo`, add the endpointType if it wasn't already added to conversation
- EndpointsMenu: use user-defined endpoint name as Title in menu
- TODO: custom icon via custom config, change unknown to robot icon
* refactor(parseConvo): pass args as an object and change where used accordingly; chore: comment out 'create schema' code
* chore: remove unused availableModels field in TConfig type
* refactor(parseCompactConvo): pass args as an object and change where used accordingly
* feat: chat through custom endpoint
* chore(message/convoSchemas): avoid saving empty arrays
* fix(BaseClient/saveMessageToDatabase): save endpointType
* refactor(ChatRoute): show Spinner if endpointsQuery or modelsQuery are still loading, which is apparent with slow fetching of models/remote config on first serve
* fix(useConversation): assign endpointType if it's missing
* fix(SaveAsPreset): pass real endpoint and endpointType when saving Preset)
* chore: recorganize types order for TConfig, add `iconURL`
* feat: custom endpoint icon support:
- use UnknownIcon in all icon contexts
- add mistral and openrouter as known endpoints, and add their icons
- iconURL support
* fix(presetSchema): move endpointType to default schema definitions shared between convoSchema and defaults
* refactor(Settings/OpenAI): remove legacy `isOpenAI` flag
* fix(OpenAIClient): do not invoke abortCompletion on completion error
* feat: add responseSender/label support for custom endpoints:
- use defaultModelLabel field in endpointOption
- add model defaults for custom endpoints in `getResponseSender`
- add `useGetSender` hook which uses EndpointsQuery to determine `defaultModelLabel`
- include defaultModelLabel from endpointConfig in custom endpoint client options
- pass `endpointType` to `getResponseSender`
* feat(OpenAIClient): use custom options from config file
* refactor: rename `defaultModelLabel` to `modelDisplayLabel`
* refactor(data-provider): separate concerns from `schemas` into `parsers`, `config`, and fix imports elsewhere
* feat: `iconURL` and extract environment variables from custom endpoint config values
* feat: custom config validation via zod schema, rename and move to `./projectRoot/librechat.yaml`
* docs: custom config docs and examples
* fix(OpenAIClient/mistral): mistral does not allow singular system message, also add `useChatCompletion` flag to use openai-node for title completions
* fix(custom/initializeClient): extract env var and use `isUserProvided` function
* Update librechat.example.yaml
* feat(InputWithLabel): add className props, and forwardRef
* fix(streamResponse): handle error edge case where either messages or convos query throws an error
* fix(useSSE): handle errorHandler edge cases where error response is and is not properly formatted from API, especially when a conversationId is not yet provided, which ensures stream is properly closed on error
* feat: user_provided keys for custom endpoints
* fix(config/endpointSchema): do not allow default endpoint values in custom endpoint `name`
* feat(loadConfigModels): extract env variables and optimize fetching models
* feat: support custom endpoint iconURL for messages and Nav
* feat(OpenAIClient): add/dropParams support
* docs: update docs with default params, add/dropParams, and notes to use config file instead of `OPENAI_REVERSE_PROXY`
* docs: update docs with additional notes
* feat(maxTokensMap): add mistral models (32k context)
* docs: update openrouter notes
* Update ai_setup.md
* docs(custom_config): add table of contents and fix note about custom name
* docs(custom_config): reorder ToC
* Update custom_config.md
* Add note about `max_tokens` field in custom_config.md
2024-01-03 09:22:48 -05:00
|
|
|
* @param {string} key - The key for the namespace to access
|
|
|
|
* @returns {Keyv} - If a valid key is passed, returns an object containing the cache store of the specified key.
|
|
|
|
* @throws Will throw an error if an invalid key is passed.
|
feat: Message Rate Limiters, Violation Logging, & Ban System 🔨 (#903)
* refactor: require Auth middleware in route index files
* feat: concurrent message limiter
* feat: complete concurrent message limiter with caching
* refactor: SSE response methods separated from handleText
* fix(abortMiddleware): fix req and res order to standard, use endpointOption in req.body
* chore: minor name changes
* refactor: add isUUID condition to saveMessage
* fix(concurrentLimiter): logic correctly handles the max number of concurrent messages and res closing/finalization
* chore: bump keyv and remove console.log from Message
* fix(concurrentLimiter): ensure messages are only saved in later message children
* refactor(concurrentLimiter): use KeyvFile instead, could make other stores configurable in the future
* feat: add denyRequest function for error responses
* feat(utils): add isStringTruthy function
Introduce the isStringTruthy function to the utilities module to check if a string value is a case-insensitive match for 'true'
* feat: add optional message rate limiters by IP and userId
* feat: add optional message rate limiters by IP and userId to edit route
* refactor: rename isStringTruthy to isTrue for brevity
* refactor(getError): use map to make code cleaner
* refactor: use memory for concurrent rate limiter to prevent clearing on startup/exit, add multiple log files, fix error message for concurrent violation
* feat: check if errorMessage is object, stringify if so
* chore: send object to denyRequest which will stringify it
* feat: log excessive requests
* fix(getError): correctly pluralize messages
* refactor(limiters): make type consistent between logs and errorMessage
* refactor(cache): move files out of lib/db into separate cache dir
>> feat: add getLogStores function so Keyv instance is not redundantly created on every violation
feat: separate violation logging to own function with logViolation
* fix: cache/index.js export, properly record userViolations
* refactor(messageLimiters): use new logging method, add logging to registrations
* refactor(logViolation): make userLogs an array of logs per user
* feat: add logging to login limiter
* refactor: pass req as first param to logViolation and record offending IP
* refactor: rename isTrue helper fn to isEnabled
* feat: add simple non_browser check and log violation
* fix: open handles in unit tests, remove KeyvMongo as not used and properly mock global fetch
* chore: adjust nodemon ignore paths to properly ignore logs
* feat: add math helper function for safe use of eval
* refactor(api/convos): use middleware at top of file to avoid redundancy
* feat: add delete all static method for Sessions
* fix: redirect to login on refresh if user is not found, or the session is not found but hasn't expired (ban case)
* refactor(getLogStores): adjust return type
* feat: add ban violation and check ban logic
refactor(logViolation): pass both req and res objects
* feat: add removePorts helper function
* refactor: rename getError to getMessageError and add getLoginError for displaying different login errors
* fix(AuthContext): fix type issue and remove unused code
* refactor(bans): ban by ip and user id, send response based on origin
* chore: add frontend ban messages
* refactor(routes/oauth): add ban check to handler, also consolidate logic to avoid redundancy
* feat: add ban check to AI messaging routes
* feat: add ban check to login/registration
* fix(ci/api): mock KeyvMongo to avoid tests hanging
* docs: update .env.example
> refactor(banViolation): calculate interval rate crossover, early return if duration is invalid
ci(banViolation): add tests to ensure users are only banned when expected
* docs: improve wording for mod system
* feat: add configurable env variables for violation scores
* chore: add jsdoc for uaParser.js
* chore: improve ban text log
* chore: update bun test scripts
* refactor(math.js): add fallback values
* fix(KeyvMongo/banLogs): refactor keyv instances to top of files to avoid memory leaks, refactor ban logic to use getLogStores instead
refactor(getLogStores): get a single log store by type
* fix(ci): refactor tests due to banLogs changes, also make sure to clear and revoke sessions even if ban duration is 0
* fix(banViolation.js): getLogStores import
* feat: handle 500 code error at login
* fix(middleware): handle case where user.id is _id and not just id
* ci: add ban secrets for backend unit tests
* refactor: logout user upon ban
* chore: log session delete message only if deletedCount > 0
* refactor: change default ban duration (2h) and make logic more clear in JSDOC
* fix: login and registration limiters will now return rate limiting error
* fix: userId not parsable as non ObjectId string
* feat: add useTimeout hook to properly clear timeouts when invoking functions within them
refactor(AuthContext): cleanup code by using new hook and defining types in ~/common
* fix: login error message for rate limits
* docs: add info for automated mod system and rate limiters, update other docs accordingly
* chore: bump data-provider version
2023-09-13 10:57:07 -04:00
|
|
|
*/
|
💫 feat: Config File & Custom Endpoints (#1474)
* WIP(backend/api): custom endpoint
* WIP(frontend/client): custom endpoint
* chore: adjust typedefs for configs
* refactor: use data-provider for cache keys and rename enums and custom endpoint for better clarity and compatibility
* feat: loadYaml utility
* refactor: rename back to from and proof-of-concept for creating schemas from user-defined defaults
* refactor: remove custom endpoint from default endpointsConfig as it will be exclusively managed by yaml config
* refactor(EndpointController): rename variables for clarity
* feat: initial load custom config
* feat(server/utils): add simple `isUserProvided` helper
* chore(types): update TConfig type
* refactor: remove custom endpoint handling from model services as will be handled by config, modularize fetching of models
* feat: loadCustomConfig, loadConfigEndpoints, loadConfigModels
* chore: reorganize server init imports, invoke loadCustomConfig
* refactor(loadConfigEndpoints/Models): return each custom endpoint as standalone endpoint
* refactor(Endpoint/ModelController): spread config values after default (temporary)
* chore(client): fix type issues
* WIP: first pass for multiple custom endpoints
- add endpointType to Conversation schema
- add update zod schemas for both convo/presets to allow non-EModelEndpoint value as endpoint (also using type assertion)
- use `endpointType` value as `endpoint` where mapping to type is necessary using this field
- use custom defined `endpoint` value and not type for mapping to modelsConfig
- misc: add return type to `getDefaultEndpoint`
- in `useNewConvo`, add the endpointType if it wasn't already added to conversation
- EndpointsMenu: use user-defined endpoint name as Title in menu
- TODO: custom icon via custom config, change unknown to robot icon
* refactor(parseConvo): pass args as an object and change where used accordingly; chore: comment out 'create schema' code
* chore: remove unused availableModels field in TConfig type
* refactor(parseCompactConvo): pass args as an object and change where used accordingly
* feat: chat through custom endpoint
* chore(message/convoSchemas): avoid saving empty arrays
* fix(BaseClient/saveMessageToDatabase): save endpointType
* refactor(ChatRoute): show Spinner if endpointsQuery or modelsQuery are still loading, which is apparent with slow fetching of models/remote config on first serve
* fix(useConversation): assign endpointType if it's missing
* fix(SaveAsPreset): pass real endpoint and endpointType when saving Preset)
* chore: recorganize types order for TConfig, add `iconURL`
* feat: custom endpoint icon support:
- use UnknownIcon in all icon contexts
- add mistral and openrouter as known endpoints, and add their icons
- iconURL support
* fix(presetSchema): move endpointType to default schema definitions shared between convoSchema and defaults
* refactor(Settings/OpenAI): remove legacy `isOpenAI` flag
* fix(OpenAIClient): do not invoke abortCompletion on completion error
* feat: add responseSender/label support for custom endpoints:
- use defaultModelLabel field in endpointOption
- add model defaults for custom endpoints in `getResponseSender`
- add `useGetSender` hook which uses EndpointsQuery to determine `defaultModelLabel`
- include defaultModelLabel from endpointConfig in custom endpoint client options
- pass `endpointType` to `getResponseSender`
* feat(OpenAIClient): use custom options from config file
* refactor: rename `defaultModelLabel` to `modelDisplayLabel`
* refactor(data-provider): separate concerns from `schemas` into `parsers`, `config`, and fix imports elsewhere
* feat: `iconURL` and extract environment variables from custom endpoint config values
* feat: custom config validation via zod schema, rename and move to `./projectRoot/librechat.yaml`
* docs: custom config docs and examples
* fix(OpenAIClient/mistral): mistral does not allow singular system message, also add `useChatCompletion` flag to use openai-node for title completions
* fix(custom/initializeClient): extract env var and use `isUserProvided` function
* Update librechat.example.yaml
* feat(InputWithLabel): add className props, and forwardRef
* fix(streamResponse): handle error edge case where either messages or convos query throws an error
* fix(useSSE): handle errorHandler edge cases where error response is and is not properly formatted from API, especially when a conversationId is not yet provided, which ensures stream is properly closed on error
* feat: user_provided keys for custom endpoints
* fix(config/endpointSchema): do not allow default endpoint values in custom endpoint `name`
* feat(loadConfigModels): extract env variables and optimize fetching models
* feat: support custom endpoint iconURL for messages and Nav
* feat(OpenAIClient): add/dropParams support
* docs: update docs with default params, add/dropParams, and notes to use config file instead of `OPENAI_REVERSE_PROXY`
* docs: update docs with additional notes
* feat(maxTokensMap): add mistral models (32k context)
* docs: update openrouter notes
* Update ai_setup.md
* docs(custom_config): add table of contents and fix note about custom name
* docs(custom_config): reorder ToC
* Update custom_config.md
* Add note about `max_tokens` field in custom_config.md
2024-01-03 09:22:48 -05:00
|
|
|
const getLogStores = (key) => {
|
|
|
|
if (!key || !namespaces[key]) {
|
|
|
|
throw new Error(`Invalid store key: ${key}`);
|
feat: Message Rate Limiters, Violation Logging, & Ban System 🔨 (#903)
* refactor: require Auth middleware in route index files
* feat: concurrent message limiter
* feat: complete concurrent message limiter with caching
* refactor: SSE response methods separated from handleText
* fix(abortMiddleware): fix req and res order to standard, use endpointOption in req.body
* chore: minor name changes
* refactor: add isUUID condition to saveMessage
* fix(concurrentLimiter): logic correctly handles the max number of concurrent messages and res closing/finalization
* chore: bump keyv and remove console.log from Message
* fix(concurrentLimiter): ensure messages are only saved in later message children
* refactor(concurrentLimiter): use KeyvFile instead, could make other stores configurable in the future
* feat: add denyRequest function for error responses
* feat(utils): add isStringTruthy function
Introduce the isStringTruthy function to the utilities module to check if a string value is a case-insensitive match for 'true'
* feat: add optional message rate limiters by IP and userId
* feat: add optional message rate limiters by IP and userId to edit route
* refactor: rename isStringTruthy to isTrue for brevity
* refactor(getError): use map to make code cleaner
* refactor: use memory for concurrent rate limiter to prevent clearing on startup/exit, add multiple log files, fix error message for concurrent violation
* feat: check if errorMessage is object, stringify if so
* chore: send object to denyRequest which will stringify it
* feat: log excessive requests
* fix(getError): correctly pluralize messages
* refactor(limiters): make type consistent between logs and errorMessage
* refactor(cache): move files out of lib/db into separate cache dir
>> feat: add getLogStores function so Keyv instance is not redundantly created on every violation
feat: separate violation logging to own function with logViolation
* fix: cache/index.js export, properly record userViolations
* refactor(messageLimiters): use new logging method, add logging to registrations
* refactor(logViolation): make userLogs an array of logs per user
* feat: add logging to login limiter
* refactor: pass req as first param to logViolation and record offending IP
* refactor: rename isTrue helper fn to isEnabled
* feat: add simple non_browser check and log violation
* fix: open handles in unit tests, remove KeyvMongo as not used and properly mock global fetch
* chore: adjust nodemon ignore paths to properly ignore logs
* feat: add math helper function for safe use of eval
* refactor(api/convos): use middleware at top of file to avoid redundancy
* feat: add delete all static method for Sessions
* fix: redirect to login on refresh if user is not found, or the session is not found but hasn't expired (ban case)
* refactor(getLogStores): adjust return type
* feat: add ban violation and check ban logic
refactor(logViolation): pass both req and res objects
* feat: add removePorts helper function
* refactor: rename getError to getMessageError and add getLoginError for displaying different login errors
* fix(AuthContext): fix type issue and remove unused code
* refactor(bans): ban by ip and user id, send response based on origin
* chore: add frontend ban messages
* refactor(routes/oauth): add ban check to handler, also consolidate logic to avoid redundancy
* feat: add ban check to AI messaging routes
* feat: add ban check to login/registration
* fix(ci/api): mock KeyvMongo to avoid tests hanging
* docs: update .env.example
> refactor(banViolation): calculate interval rate crossover, early return if duration is invalid
ci(banViolation): add tests to ensure users are only banned when expected
* docs: improve wording for mod system
* feat: add configurable env variables for violation scores
* chore: add jsdoc for uaParser.js
* chore: improve ban text log
* chore: update bun test scripts
* refactor(math.js): add fallback values
* fix(KeyvMongo/banLogs): refactor keyv instances to top of files to avoid memory leaks, refactor ban logic to use getLogStores instead
refactor(getLogStores): get a single log store by type
* fix(ci): refactor tests due to banLogs changes, also make sure to clear and revoke sessions even if ban duration is 0
* fix(banViolation.js): getLogStores import
* feat: handle 500 code error at login
* fix(middleware): handle case where user.id is _id and not just id
* ci: add ban secrets for backend unit tests
* refactor: logout user upon ban
* chore: log session delete message only if deletedCount > 0
* refactor: change default ban duration (2h) and make logic more clear in JSDOC
* fix: login and registration limiters will now return rate limiting error
* fix: userId not parsable as non ObjectId string
* feat: add useTimeout hook to properly clear timeouts when invoking functions within them
refactor(AuthContext): cleanup code by using new hook and defining types in ~/common
* fix: login error message for rate limits
* docs: add info for automated mod system and rate limiters, update other docs accordingly
* chore: bump data-provider version
2023-09-13 10:57:07 -04:00
|
|
|
}
|
💫 feat: Config File & Custom Endpoints (#1474)
* WIP(backend/api): custom endpoint
* WIP(frontend/client): custom endpoint
* chore: adjust typedefs for configs
* refactor: use data-provider for cache keys and rename enums and custom endpoint for better clarity and compatibility
* feat: loadYaml utility
* refactor: rename back to from and proof-of-concept for creating schemas from user-defined defaults
* refactor: remove custom endpoint from default endpointsConfig as it will be exclusively managed by yaml config
* refactor(EndpointController): rename variables for clarity
* feat: initial load custom config
* feat(server/utils): add simple `isUserProvided` helper
* chore(types): update TConfig type
* refactor: remove custom endpoint handling from model services as will be handled by config, modularize fetching of models
* feat: loadCustomConfig, loadConfigEndpoints, loadConfigModels
* chore: reorganize server init imports, invoke loadCustomConfig
* refactor(loadConfigEndpoints/Models): return each custom endpoint as standalone endpoint
* refactor(Endpoint/ModelController): spread config values after default (temporary)
* chore(client): fix type issues
* WIP: first pass for multiple custom endpoints
- add endpointType to Conversation schema
- add update zod schemas for both convo/presets to allow non-EModelEndpoint value as endpoint (also using type assertion)
- use `endpointType` value as `endpoint` where mapping to type is necessary using this field
- use custom defined `endpoint` value and not type for mapping to modelsConfig
- misc: add return type to `getDefaultEndpoint`
- in `useNewConvo`, add the endpointType if it wasn't already added to conversation
- EndpointsMenu: use user-defined endpoint name as Title in menu
- TODO: custom icon via custom config, change unknown to robot icon
* refactor(parseConvo): pass args as an object and change where used accordingly; chore: comment out 'create schema' code
* chore: remove unused availableModels field in TConfig type
* refactor(parseCompactConvo): pass args as an object and change where used accordingly
* feat: chat through custom endpoint
* chore(message/convoSchemas): avoid saving empty arrays
* fix(BaseClient/saveMessageToDatabase): save endpointType
* refactor(ChatRoute): show Spinner if endpointsQuery or modelsQuery are still loading, which is apparent with slow fetching of models/remote config on first serve
* fix(useConversation): assign endpointType if it's missing
* fix(SaveAsPreset): pass real endpoint and endpointType when saving Preset)
* chore: recorganize types order for TConfig, add `iconURL`
* feat: custom endpoint icon support:
- use UnknownIcon in all icon contexts
- add mistral and openrouter as known endpoints, and add their icons
- iconURL support
* fix(presetSchema): move endpointType to default schema definitions shared between convoSchema and defaults
* refactor(Settings/OpenAI): remove legacy `isOpenAI` flag
* fix(OpenAIClient): do not invoke abortCompletion on completion error
* feat: add responseSender/label support for custom endpoints:
- use defaultModelLabel field in endpointOption
- add model defaults for custom endpoints in `getResponseSender`
- add `useGetSender` hook which uses EndpointsQuery to determine `defaultModelLabel`
- include defaultModelLabel from endpointConfig in custom endpoint client options
- pass `endpointType` to `getResponseSender`
* feat(OpenAIClient): use custom options from config file
* refactor: rename `defaultModelLabel` to `modelDisplayLabel`
* refactor(data-provider): separate concerns from `schemas` into `parsers`, `config`, and fix imports elsewhere
* feat: `iconURL` and extract environment variables from custom endpoint config values
* feat: custom config validation via zod schema, rename and move to `./projectRoot/librechat.yaml`
* docs: custom config docs and examples
* fix(OpenAIClient/mistral): mistral does not allow singular system message, also add `useChatCompletion` flag to use openai-node for title completions
* fix(custom/initializeClient): extract env var and use `isUserProvided` function
* Update librechat.example.yaml
* feat(InputWithLabel): add className props, and forwardRef
* fix(streamResponse): handle error edge case where either messages or convos query throws an error
* fix(useSSE): handle errorHandler edge cases where error response is and is not properly formatted from API, especially when a conversationId is not yet provided, which ensures stream is properly closed on error
* feat: user_provided keys for custom endpoints
* fix(config/endpointSchema): do not allow default endpoint values in custom endpoint `name`
* feat(loadConfigModels): extract env variables and optimize fetching models
* feat: support custom endpoint iconURL for messages and Nav
* feat(OpenAIClient): add/dropParams support
* docs: update docs with default params, add/dropParams, and notes to use config file instead of `OPENAI_REVERSE_PROXY`
* docs: update docs with additional notes
* feat(maxTokensMap): add mistral models (32k context)
* docs: update openrouter notes
* Update ai_setup.md
* docs(custom_config): add table of contents and fix note about custom name
* docs(custom_config): reorder ToC
* Update custom_config.md
* Add note about `max_tokens` field in custom_config.md
2024-01-03 09:22:48 -05:00
|
|
|
return namespaces[key];
|
feat: Message Rate Limiters, Violation Logging, & Ban System 🔨 (#903)
* refactor: require Auth middleware in route index files
* feat: concurrent message limiter
* feat: complete concurrent message limiter with caching
* refactor: SSE response methods separated from handleText
* fix(abortMiddleware): fix req and res order to standard, use endpointOption in req.body
* chore: minor name changes
* refactor: add isUUID condition to saveMessage
* fix(concurrentLimiter): logic correctly handles the max number of concurrent messages and res closing/finalization
* chore: bump keyv and remove console.log from Message
* fix(concurrentLimiter): ensure messages are only saved in later message children
* refactor(concurrentLimiter): use KeyvFile instead, could make other stores configurable in the future
* feat: add denyRequest function for error responses
* feat(utils): add isStringTruthy function
Introduce the isStringTruthy function to the utilities module to check if a string value is a case-insensitive match for 'true'
* feat: add optional message rate limiters by IP and userId
* feat: add optional message rate limiters by IP and userId to edit route
* refactor: rename isStringTruthy to isTrue for brevity
* refactor(getError): use map to make code cleaner
* refactor: use memory for concurrent rate limiter to prevent clearing on startup/exit, add multiple log files, fix error message for concurrent violation
* feat: check if errorMessage is object, stringify if so
* chore: send object to denyRequest which will stringify it
* feat: log excessive requests
* fix(getError): correctly pluralize messages
* refactor(limiters): make type consistent between logs and errorMessage
* refactor(cache): move files out of lib/db into separate cache dir
>> feat: add getLogStores function so Keyv instance is not redundantly created on every violation
feat: separate violation logging to own function with logViolation
* fix: cache/index.js export, properly record userViolations
* refactor(messageLimiters): use new logging method, add logging to registrations
* refactor(logViolation): make userLogs an array of logs per user
* feat: add logging to login limiter
* refactor: pass req as first param to logViolation and record offending IP
* refactor: rename isTrue helper fn to isEnabled
* feat: add simple non_browser check and log violation
* fix: open handles in unit tests, remove KeyvMongo as not used and properly mock global fetch
* chore: adjust nodemon ignore paths to properly ignore logs
* feat: add math helper function for safe use of eval
* refactor(api/convos): use middleware at top of file to avoid redundancy
* feat: add delete all static method for Sessions
* fix: redirect to login on refresh if user is not found, or the session is not found but hasn't expired (ban case)
* refactor(getLogStores): adjust return type
* feat: add ban violation and check ban logic
refactor(logViolation): pass both req and res objects
* feat: add removePorts helper function
* refactor: rename getError to getMessageError and add getLoginError for displaying different login errors
* fix(AuthContext): fix type issue and remove unused code
* refactor(bans): ban by ip and user id, send response based on origin
* chore: add frontend ban messages
* refactor(routes/oauth): add ban check to handler, also consolidate logic to avoid redundancy
* feat: add ban check to AI messaging routes
* feat: add ban check to login/registration
* fix(ci/api): mock KeyvMongo to avoid tests hanging
* docs: update .env.example
> refactor(banViolation): calculate interval rate crossover, early return if duration is invalid
ci(banViolation): add tests to ensure users are only banned when expected
* docs: improve wording for mod system
* feat: add configurable env variables for violation scores
* chore: add jsdoc for uaParser.js
* chore: improve ban text log
* chore: update bun test scripts
* refactor(math.js): add fallback values
* fix(KeyvMongo/banLogs): refactor keyv instances to top of files to avoid memory leaks, refactor ban logic to use getLogStores instead
refactor(getLogStores): get a single log store by type
* fix(ci): refactor tests due to banLogs changes, also make sure to clear and revoke sessions even if ban duration is 0
* fix(banViolation.js): getLogStores import
* feat: handle 500 code error at login
* fix(middleware): handle case where user.id is _id and not just id
* ci: add ban secrets for backend unit tests
* refactor: logout user upon ban
* chore: log session delete message only if deletedCount > 0
* refactor: change default ban duration (2h) and make logic more clear in JSDOC
* fix: login and registration limiters will now return rate limiting error
* fix: userId not parsable as non ObjectId string
* feat: add useTimeout hook to properly clear timeouts when invoking functions within them
refactor(AuthContext): cleanup code by using new hook and defining types in ~/common
* fix: login error message for rate limits
* docs: add info for automated mod system and rate limiters, update other docs accordingly
* chore: bump data-provider version
2023-09-13 10:57:07 -04:00
|
|
|
};
|
|
|
|
|
|
|
|
module.exports = getLogStores;
|