mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-12-17 17:00:15 +01:00
4 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Danny Avila
|
ea1dd59ef4
|
refactor(api): Central Logging 📜 (#1348)
* WIP: initial logging changes add several transports in ~/config/winston omit messages in logs, truncate long strings add short blurb in dotenv for debug logging GoogleClient: using logger OpenAIClient: using logger, handleOpenAIErrors Adding typedef for payload message bumped winston and using winston-daily-rotate-file moved config for server paths to ~/config dir Added `DEBUG_LOGGING=true` to .env.example * WIP: Refactor logging statements in code * WIP: Refactor logging statements and import configurations * WIP: Refactor logging statements and import configurations * refactor: broadcast Redis initialization message with `info` not `debug` * refactor: complete Refactor logging statements and import configurations * chore: delete unused tools * fix: circular dependencies due to accessing logger * refactor(handleText): handle booleans and write tests * refactor: redact sensitive values, better formatting * chore: improve log formatting, avoid passing strings to 2nd arg * fix(ci): fix jest tests due to logger changes * refactor(getAvailablePluginsController): cache plugins as they are static and avoids async addOpenAPISpecs call every time * chore: update docs * chore: update docs * chore: create separate meiliSync logger, clean up logs to avoid being unnecessarily verbose * chore: spread objects where they are commonly logged to allow string truncation * chore: improve error log formatting |
||
|
Danny Avila
|
365c39c405
|
feat: Accurate Token Usage Tracking & Optional Balance (#1018)
* refactor(Chains/llms): allow passing callbacks * refactor(BaseClient): accurately count completion tokens as generation only * refactor(OpenAIClient): remove unused getTokenCountForResponse, pass streaming var and callbacks in initializeLLM * wip: summary prompt tokens * refactor(summarizeMessages): new cut-off strategy that generates a better summary by adding context from beginning, truncating the middle, and providing the end wip: draft out relevant providers and variables for token tracing * refactor(createLLM): make streaming prop false by default * chore: remove use of getTokenCountForResponse * refactor(agents): use BufferMemory as ConversationSummaryBufferMemory token usage not easy to trace * chore: remove passing of streaming prop, also console log useful vars for tracing * feat: formatFromLangChain helper function to count tokens for ChatModelStart * refactor(initializeLLM): add role for LLM tracing * chore(formatFromLangChain): update JSDoc * feat(formatMessages): formats langChain messages into OpenAI payload format * chore: install openai-chat-tokens * refactor(formatMessage): optimize conditional langChain logic fix(formatFromLangChain): fix destructuring * feat: accurate prompt tokens for ChatModelStart before generation * refactor(handleChatModelStart): move to callbacks dir, use factory function * refactor(initializeLLM): rename 'role' to 'context' * feat(Balance/Transaction): new schema/models for tracking token spend refactor(Key): factor out model export to separate file * refactor(initializeClient): add req,res objects to client options * feat: add-balance script to add to an existing users' token balance refactor(Transaction): use multiplier map/function, return balance update * refactor(Tx): update enum for tokenType, return 1 for multiplier if no map match * refactor(Tx): add fair fallback value multiplier incase the config result is undefined * refactor(Balance): rename 'tokens' to 'tokenCredits' * feat: balance check, add tx.js for new tx-related methods and tests * chore(summaryPrompts): update prompt token count * refactor(callbacks): pass req, res wip: check balance * refactor(Tx): make convoId a String type, fix(calculateTokenValue) * refactor(BaseClient): add conversationId as client prop when assigned * feat(RunManager): track LLM runs with manager, track token spend from LLM, refactor(OpenAIClient): use RunManager to create callbacks, pass user prop to langchain api calls * feat(spendTokens): helper to spend prompt/completion tokens * feat(checkBalance): add helper to check, log, deny request if balance doesn't have enough funds refactor(Balance): static check method to return object instead of boolean now wip(OpenAIClient): implement use of checkBalance * refactor(initializeLLM): add token buffer to assure summary isn't generated when subsequent payload is too large refactor(OpenAIClient): add checkBalance refactor(createStartHandler): add checkBalance * chore: remove prompt and completion token logging from route handler * chore(spendTokens): add JSDoc * feat(logTokenCost): record transactions for basic api calls * chore(ask/edit): invoke getResponseSender only once per API call * refactor(ask/edit): pass promptTokens to getIds and include in abort data * refactor(getIds -> getReqData): rename function * refactor(Tx): increase value if incomplete message * feat: record tokenUsage when message is aborted * refactor: subtract tokens when payload includes function_call * refactor: add namespace for token_balance * fix(spendTokens): only execute if corresponding token type amounts are defined * refactor(checkBalance): throws Error if not enough token credits * refactor(runTitleChain): pass and use signal, spread object props in create helpers, and use 'call' instead of 'run' * fix(abortMiddleware): circular dependency, and default to empty string for completionTokens * fix: properly cancel title requests when there isn't enough tokens to generate * feat(predictNewSummary): custom chain for summaries to allow signal passing refactor(summaryBuffer): use new custom chain * feat(RunManager): add getRunByConversationId method, refactor: remove run and throw llm error on handleLLMError * refactor(createStartHandler): if summary, add error details to runs * fix(OpenAIClient): support aborting from summarization & showing error to user refactor(summarizeMessages): remove unnecessary operations counting summaryPromptTokens and note for alternative, pass signal to summaryBuffer * refactor(logTokenCost -> recordTokenUsage): rename * refactor(checkBalance): include promptTokens in errorMessage * refactor(checkBalance/spendTokens): move to models dir * fix(createLanguageChain): correctly pass config * refactor(initializeLLM/title): add tokenBuffer of 150 for balance check * refactor(openAPIPlugin): pass signal and memory, filter functions by the one being called * refactor(createStartHandler): add error to run if context is plugins as well * refactor(RunManager/handleLLMError): throw error immediately if plugins, don't remove run * refactor(PluginsClient): pass memory and signal to tools, cleanup error handling logic * chore: use absolute equality for addTitle condition * refactor(checkBalance): move checkBalance to execute after userMessage and tokenCounts are saved, also make conditional * style: icon changes to match official * fix(BaseClient): getTokenCountForResponse -> getTokenCount * fix(formatLangChainMessages): add kwargs as fallback prop from lc_kwargs, update JSDoc * refactor(Tx.create): does not update balance if CHECK_BALANCE is not enabled * fix(e2e/cleanUp): cleanup new collections, import all model methods from index * fix(config/add-balance): add uncaughtException listener * fix: circular dependency * refactor(initializeLLM/checkBalance): append new generations to errorMessage if cost exceeds balance * fix(handleResponseMessage): only record token usage in this method if not error and completion is not skipped * fix(createStartHandler): correct condition for generations * chore: bump postcss due to moderate severity vulnerability * chore: bump zod due to low severity vulnerability * chore: bump openai & data-provider version * feat(types): OpenAI Message types * chore: update bun lockfile * refactor(CodeBlock): add error block formatting * refactor(utils/Plugin): factor out formatJSON and cn to separate files (json.ts and cn.ts), add extractJSON * chore(logViolation): delete user_id after error is logged * refactor(getMessageError -> Error): change to React.FC, add token_balance handling, use extractJSON to determine JSON instead of regex * fix(DALL-E): use latest openai SDK * chore: reorganize imports, fix type issue * feat(server): add balance route * fix(api/models): add auth * feat(data-provider): /api/balance query * feat: show balance if checking is enabled, refetch on final message or error * chore: update docs, .env.example with token_usage info, add balance script command * fix(Balance): fallback to empty obj for balance query * style: slight adjustment of balance element * docs(token_usage): add PR notes |
||
|
Danny Avila
|
6358383001
|
feat(db & e2e): Enhance DB Schemas/Controllers and Improve E2E Tests (#966)
* feat: add global teardown to remove test data and add registration/log-out to auth flow * refactor(models/Conversation): index user field and add JSDoc to deleteConvos * refactor: add user index to message schema and ensure user is saved to each Message * refactor: add user to each saveMessage call * fix: handle case where title is null in zod schema * feat(e2e): ensure messages are deleted on cleanUp * fix: set last convo for all endpoints on conversation update * fix: enable registration for CI env |
||
|
Danny Avila
|
7b2cedf5ff
|
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 |