* 🚀 feat: Add automatic refill settings to balance schema
* 🚀 feat: Refactor balance feature to use global interface configuration
* 🚀 feat: Implement auto-refill functionality for balance management
* 🚀 feat: Enhance auto-refill logic and configuration for balance management
* 🚀 chore: Bump version to 0.7.74 in package.json and package-lock.json
* 🚀 chore: Bump version to 0.0.5 in package.json and package-lock.json
* 🚀 docs: Update comment for balance settings in librechat.example.yaml
* chore: space in `.env.example`
* 🚀 feat: Implement balance configuration loading and refactor related components
* 🚀 test: Refactor tests to use custom config for balance feature
* 🚀 fix: Update balance response handling in Transaction.js to use Balance model
* 🚀 test: Update AppService tests to include balance configuration in mock setup
* 🚀 test: Enhance AppService tests with complete balance configuration scenarios
* 🚀 refactor: Rename balanceConfig to balance and update related tests for clarity
* 🚀 refactor: Remove loadDefaultBalance and update balance handling in AppService
* 🚀 test: Update AppService tests to reflect new balance structure and defaults
* 🚀 test: Mock getCustomConfig in BaseClient tests to control balance configuration
* 🚀 test: Add get method to mockCache in OpenAIClient tests for improved cache handling
* 🚀 test: Mock getCustomConfig in OpenAIClient tests to control balance configuration
* 🚀 test: Remove mock for getCustomConfig in OpenAIClient tests to streamline configuration handling
* 🚀 fix: Update balance configuration reference in config.js for consistency
* refactor: Add getBalanceConfig function to retrieve balance configuration
* chore: Comment out example balance settings in librechat.example.yaml
* refactor: Replace getCustomConfig with getBalanceConfig for balance handling
* fix: tests
* refactor: Replace getBalanceConfig call with balance from request locals
* refactor: Update balance handling to use environment variables for configuration
* refactor: Replace getBalanceConfig calls with balance from request locals
* refactor: Simplify balance configuration logic in getBalanceConfig
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* feat: Refactor ModelEndHandler to collect usage metadata only if it exists
* feat: google tool end handling, custom anthropic class for better token ux
* refactor: differentiate between client <> request options
* feat: initial support for google agents
* feat: only cache messages with non-empty text
* feat: Cache non-empty messages in chatV2 controller
* fix: anthropic llm client options llmConfig
* refactor: streamline client options handling in LLM configuration
* fix: VertexAI Agent Auth & Tool Handling
* fix: additional fields for llmConfig, however customHeaders are not supported by langchain, requires PR
* feat: set default location for vertexai LLM configuration
* fix: outdated OpenAI Client options for getLLMConfig
* chore: agent provider options typing
* chore: add note about currently unsupported customHeaders in langchain GenAI client
* fix: skip transaction creation when rawAmount is NaN
* wip: initial cache control implementation, add typing for transactions handling
* feat: first pass of Anthropic Prompt Caching
* feat: standardize stream usage as pass in when calculating token counts
* feat: Add getCacheMultiplier function to calculate cache multiplier for different valueKeys and cacheTypes
* chore: imports order
* refactor: token usage recording in AnthropicClient, no need to "correct" as we have the correct amount
* feat: more accurate token counting using stream usage data
* feat: Improve token counting accuracy with stream usage data
* refactor: ensure more accurate than not token estimations if custom instructions or files are not being resent with every request
* refactor: cleanup updateUserMessageTokenCount to allow transactions to be as accurate as possible even if we shouldn't update user message token counts
* ci: fix tests
* fix(processModelData): handle `openrouter/auto` edge case
* fix(Tx.create): prevent negative multiplier edge case and prevent balance from becoming negative
* fix(NavLinks): render 0 balance properly
* refactor(NavLinks): show only up to 2 decimal places for balance
* fix(OpenAIClient/titleConvo): fix cohere condition and record token usage for `this.options.titleMethod === 'completion'`
* WIP: basic route for file downloads and file strategy for generating readablestream to pipe as res
* chore(DALLE3): add typing for OpenAI client
* chore: add `CONSOLE_JSON` notes to dotenv.md
* WIP: first pass OpenAI Assistants File Output handling
* feat: first pass assistants output file download from openai
* chore: yml vs. yaml variation to .gitignore for `librechat.yml`
* refactor(retrieveAndProcessFile): remove redundancies
* fix(syncMessages): explicit sort of apiMessages to fix message order on abort
* chore: add logs for warnings and errors, show toast on frontend
* chore: add logger where console was still being used
* chore: add assistants to supportsBalanceCheck
* feat(Transaction): getTransactions and refactor export of model
* refactor: use enum: ViolationTypes.TOKEN_BALANCE
* feat(assistants): check balance
* refactor(assistants): only add promptBuffer if new convo (for title), and remove endpoint definition
* refactor(assistants): Count tokens up to the current context window
* fix(Switcher): make Select list explicitly controlled
* feat(assistants): use assistant's default model when no model is specified instead of the last selected assistant, prevent assistant_id from being recorded in non-assistant endpoints
* chore(assistants/chat): import order
* chore: bump librechat-data-provider due to changes
* chore: bump anthropic SDK
* chore: update anthropic config settings (fileSupport, default models)
* feat: anthropic multi modal formatting
* refactor: update vision models and use endpoint specific max long side resizing
* feat(anthropic): multimodal messages, retry logic, and messages payload
* chore: add more safety to trimming content due to whitespace error for assistant messages
* feat(anthropic): token accounting and resending multiple images in progress
* chore: bump data-provider
* feat(anthropic): resendImages feature
* chore: optimize Edit/Ask controllers, switch model back to req model
* fix: false positive of invalid model
* refactor(validateVisionModel): use object as arg, pass in additional/available models
* refactor(validateModel): use helper function, `getModelsConfig`
* feat: add modelsConfig to endpointOption so it gets passed to all clients, use for properly validating vision models
* refactor: initialize default vision model and make sure it's available before assigning it
* refactor(useSSE): avoid resetting model if user selected a new model between request and response
* feat: show rate in transaction logging
* fix: return tokenCountMap regardless of payload shape
* feat: add GOOGLE_MODELS env var
* feat: add gemini vision support
* refactor(GoogleClient): adjust clientOptions handling depending on model
* fix(logger): fix redact logic and redact errors only
* fix(GoogleClient): do not allow non-multiModal messages when gemini-pro-vision is selected
* refactor(OpenAIClient): use `isVisionModel` client property to avoid calling validateVisionModel multiple times
* refactor: better debug logging by correctly traversing, redacting sensitive info, and logging condensed versions of long values
* refactor(GoogleClient): allow response errors to be thrown/caught above client handling so user receives meaningful error message
debug orderedMessages, parentMessageId, and buildMessages result
* refactor(AskController): use model from client.modelOptions.model when saving intermediate messages, which requires for the progress callback to be initialized after the client is initialized
* feat(useSSE): revert to previous model if the model was auto-switched by backend due to message attachments
* docs: update with google updates, notes about Gemini Pro Vision
* fix: redis should not be initialized without USE_REDIS and increase max listeners to 20
* 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
