* 🧹 chore: Update logger imports to use @librechat/data-schemas across multiple files and remove unused sleep function from queue.js (#9930)
* chore: Replace local isEnabled utility with @librechat/api import across multiple files, update test files
* chore: Replace local logger import with @librechat/data-schemas logger in countTokens.js and fork.js
* chore: Update logs volume path in docker-compose.yml to correct directory
* chore: import order of isEnabled in static.js
* ✨ v0.8.0
* 🔧 chore: Update config version to 1.3.0
* 🔧 chore: Bump @librechat/api version to 1.4.1
* 🔧 chore: Update @librechat/client version to 0.3.1
* 🔧 chore: Bump librechat-data-provider version to 0.8.020
* 🔧 chore: Bump @librechat/data-schemas version to 0.0.23
* initialize servers sequentially
* adjust for exported properties that are not nullable anymore
* use underscore separator
* mock with set
* customize init timeout via env var
* feat: Add new Claude models to sharedAnthropicModels list
* chore: use correct claude aliases for default list
* chore: update deepseek model rates for accuracy
* chore: update @librechat/agents dependency to version 2.4.82
* chore: move domain related functions to `packages/api`
* fix: isEmailDomainAllowed for case-insensitive domain matching
- Added tests to validate case-insensitive matching for email domains in various scenarios.
- Updated isEmailDomainAllowed function to convert email domains to lowercase for consistent comparison.
- Improved handling of null/undefined entries in allowedDomains.
* ci: Mock isEmailDomainAllowed in samlStrategy tests
- Added a mock implementation for isEmailDomainAllowed to return true in samlStrategy tests, ensuring consistent behavior during test execution.
* ci: Update import of isEmailDomainAllowed in ldapStrategy tests
- Changed the import of isEmailDomainAllowed from the domains service to the api package for consistency and to reflect recent refactoring.
* refactor: move `loadOCRConfig` from `packages/data-provider` to `packages/api` and return `undefined` if not explicitly configured
* fix: loadOCRConfig import from @librechat/api
* refactor: update defaultTextMimeTypes to support virtually all file types for text parsing
* fix: improve OCR capability check and error message for unsupported file types
* ci: remove unnecessary ocr expectation from AppService test
* 🌐 feat: OpenRouter Web Search
- Added tests for handling web_search parameter with OpenRouter in various scenarios.
- Implemented logic to manage web_search in modelOptions and addParams/dropParams.
- Ensured correct configuration of llmConfig and modelKwargs for OpenRouter, including handling of plugins.
- Improved overall integration of OpenRouter with OpenAI API, ensuring expected behavior across different configurations.
* chore: bump @librechat/agents to v2.4.81
- Fixed a bug in reinitMCPServer where a user connection was created for an app-level server whenever this server is reinitialized
- Made MCPManager.getUserConnection to return an error if the connection is app-level
- Add MCPManager.getConnection to return either an app connection or a user connection based on the serverName
- Made MCPManager.appConnections public to avoid unnecessary wrapper methods.
* 🕵️ feat: Enhance Index Sync and MeiliSearch filtering for User Field
- Implemented `ensureFilterableAttributes` function to configure MeiliSearch indexes for messages and conversations to filter by user.
- Updated sync logic to trigger a full re-sync if the user field is missing or index settings are modified.
- Adjusted search queries in Conversation and Message models to include user filtering.
- Ensured 'user' field is marked as filterable in MongoDB schema for both messages and conversations.
This update improves data integrity and search capabilities by ensuring user-related data is properly indexed and retrievable.
* fix: message processing in Search component to use linear list and not tree
* feat: Implement user filtering in MeiliSearch for shared links
* refactor: Optimize message search retrieval by batching database calls
* chore: Update MeiliSearch parameters type to use SearchParams for improved type safety
* add use of immutable claims to identify user object
* fix semicolons
* update email attribute on change
* replace ternary expressions
* fix semicolon
* chore: add typing
* chore: reorder fields in `findOpenIDUser`
* refactor: optimize user lookup logic in `findOpenIDUser` function to minimize database roundtrips
* refactor: integrate findOpenIDUser for improved user retrieval in refreshController
* refactor: improve error logging for invalid refresh tokens in refreshController
* ci: mock findUser correctly in openidStrategy tests
* test: add unit tests for findOpenIDUser function to enhance user retrieval logic
---------
Co-authored-by: Joachim Keltsch <joachim.keltsch@daimlertruck.com>
* feat: support multiple roles in OPENID_REQUIRED_ROLE
- Allow comma-separated roles in OPENID_REQUIRED_ROLE environment variable
- User needs ANY of the specified roles to login (OR logic)
- Maintain backward compatibility with single role configuration
- Add comprehensive test coverage for multiple role scenarios
* Add tests
* Fix linter
* Add missing closing brace
* Add new line
* Simplify tests
* Refresh OpenID verify callback in tests
* Fix OpenID spec and resolve linting errors
* test: Add backward compatibility test for single required role in OpenID strategy
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor: Implement gradual backoff polling for oauth connection status with timeout handling
* refactor: Enhance OAuth polling with gradual backoff and timeout handling; update reconnection tracking
* refactor: reconnection timeout behavior in OAuthReconnectionManager and OAuthReconnectionTracker
- Implement tests to verify reconnection timeout handling, including tracking of reconnection states and cleanup of timed-out entries.
- Enhance existing methods in OAuthReconnectionManager and OAuthReconnectionTracker to support timeout checks and cleanup logic.
- Ensure proper handling of multiple servers with different timeout periods and edge cases for active states.
* chore: remove comment
* refactor: Enforce strict 3-minute OAuth timeout with updated polling intervals and improved timeout handling
* refactor: Remove unused polling logic and prevent duplicate polling for servers in MCP server manager
* refactor: Update localization key for no memories message in MemoryViewer
* refactor: Improve MCP tool initialization by handling server failures
- Introduced a mechanism to track failed MCP servers, preventing retries for unavailable servers.
- Added logging for failed tool creation attempts to enhance debugging and monitoring.
* refactor: Update reconnection timeout to enforce a strict 3-minute limit
* ci: Update reconnection timeout tests to reflect a strict 3-minute limit
* ci: Update reconnection timeout tests to enforce a strict 3-minute limit
* chore: Remove unused MCP connection timeout message
🔄 refactor: Optimize MCP Tool Initialization
fix: update tool caching to use separated mcp logic
refactor: Replace `req.user` with `userId` in MCP handling functions
refactor: Replace `req` parameter with `userId` in file search tool functions
fix: Update user connection parameter to use object format in reinitMCPServer
refactor: Simplify MCP tool creation logic and improve handling of tool configurations to avoid capturing too much in closures
refactor: ensure MCP available tools are fetched from cache only when needed
* fix: axios response logging for text parsing, remove console logging, remove jsdoc
* refactor: error logging in logAxiosError function to handle various error types with type guards
* refactor: enhance text parsing with improved error handling and async file reading
* refactor: replace synchronous file reading with asynchronous methods for improved performance and memory management
* ci: update tests
* fix: increment tag counters when forking/duplicating conversations
- Add bulkIncrementTagCounts to update existing tag counts in bulk
- Integrate tag count updates into importBatchBuilder.saveBatch() using Promise.all
- Update frontend mutations to directly update cache instead of invalidating queries
- Optimize bulkIncrementTagCounts to skip unnecessary database queries
Fixes issue where forked/duplicated conversations with bookmarks would not increment
tag counters, leading to negative counts when bookmarks were later removed.
* chore: reorder import statements for clarity in fork.spec.js
* fix: respect server's token endpoint auth methods for MCP OAuth refresh
Previously, LibreChat always used Basic Auth when refreshing OAuth tokens if a
client_secret was present. This caused issues with servers (like FastMCP) that
only support client_secret_post. Now properly checks and respects the server's
advertised token_endpoint_auth_methods_supported.
Fixes token refresh failures with error: "refresh_token.client_id: Field required"
* chore: remove MCP OAuth URL Logging
* WIP: conversion of `ocr` to `context`
* refactor: make `primeResources` backwards-compatible for `ocr` tool_resources
* refactor: Convert legacy `ocr` tool resource to `context` in agent updates
- Implemented conversion logic to replace `ocr` with `context` in both incoming updates and existing agent data.
- Merged file IDs and files from `ocr` into `context` while ensuring deduplication.
- Updated tools array to reflect the change from `ocr` to `context`.
* refactor: Enhance context file handling in agent processing
- Updated the logic for managing context files by consolidating file IDs from both `ocr` and `context` resources.
- Improved backwards compatibility by ensuring that context files are correctly populated and handled.
- Simplified the iteration over context files for better readability and maintainability.
* refactor: Enhance tool_resources handling in primeResources
- Added tests to verify the deletion behavior of tool_resources fields, ensuring original objects remain unchanged.
- Implemented logic to delete `ocr` and `context` fields after fetching and re-categorizing files.
- Preserved context field when the context capability is disabled, ensuring correct behavior in various scenarios.
* refactor: Replace `ocrEnabled` with `contextEnabled` in AgentConfig
* refactor: Adjust legacy tool handling order for improved clarity
* refactor: Implement OCR to context conversion functions and remove original conversion logic in update agent handling
* refactor: Move contextEnabled declaration to maintain consistent order in capabilities
* refactor: Update localization keys for file context to improve clarity and accuracy
* chore: Update localization key for file context information to improve clarity
- Implemented `getAgents` function to retrieve multiple agent documents based on search parameters.
- Updated `fileAccess` middleware to utilize `getAgents` instead of `getAgent` for improved file access checks.
- Added comprehensive tests for file access middleware, covering various scenarios including user permissions and agent ownership.
* ✂️ refactor: use artifacts and callbacks to pass UI resources
* chore: imports
* refactor: Update UIResource type imports and definitions across components and tests
* refactor: Update ToolCallInfo test data structure and enhance TAttachment type definition
---------
Co-authored-by: Samuel Path <samuel.path@shopify.com>
* refactor: Optimize Email Domain Validation in OpenID, SAML, and Social Login Strategies
- Implemented email domain validation for user authentication in OpenID and SAML strategies, ensuring only allowed domains are processed.
- Adjusted error messages for clarity and consistency across authentication methods.
- Refactored social login to validate email domains before checking for existing users, improving registration flow.
* refactor: Email Domain Validation in LDAP and Social Login Strategies
* Remove unused STATIC_CONFIG and LIBRECHAT_YAML_CONFIG cache keys.
These cache keys were identified as dead code - they were being written to but never read from anywhere in the codebase after a recent refactor:
- STATIC_CONFIG was used as a cache namespace that stored configuration data
- LIBRECHAT_YAML_CONFIG was the key used within that namespace to store parsed YAML config
- The cache.set() operation in loadCustomConfig.js stored the config but no cache.get() operations retrieved it
- Configuration data is already handled through other mechanisms without caching
* # removed tests regarding cache
- This allows use APP_CONFIG in FORCED_IN_MEMORY_CACHE_NAMESPACES
- Remove the complexity of nested namespace (e.g. we no longer have to worry about the prefix of every role key)
* fix: ChatGPT import logic breaks message graph when it encounters a system message
- Implemented `findNonSystemParent` to maintain parent-child relationships by skipping system messages.
- Added a test case to ensure system messages do not disrupt the conversation flow during import.
* fix: ChatGPT import, correct sender for user messages with GPT-4 model
* fix: Enhance model name extraction for assistant messages in import process
- Updated sender assignment logic to dynamically extract model names from model slugs, improving accuracy for various GPT models.
- Added comprehensive tests to validate the extraction and formatting of model names from different model slugs, ensuring robustness in the import functionality.
* refactor: modularize openai llm config logic into new getOpenAILLMConfig function (#9412)
* ✈️ refactor: Migrate Anthropic's getLLMConfig to TypeScript (#9413)
* refactor: move tokens.js over to packages/api and update imports
* refactor: port tokens.js to typescript
* refactor: move helpers.js over to packages/api and update imports
* refactor: port helpers.js to typescript
* refactor: move anthropic/llm.js over to packages/api and update imports
* refactor: port anthropic/llm.js to typescript with supporting types in types/anthropic.ts and updated tests in llm.spec.js
* refactor: move llm.spec.js over to packages/api and update import
* refactor: port llm.spec.js over to typescript
* 📝 Add Prompt Parameter Support for Anthropic Custom Endpoints (#9414)
feat: add anthropic llm config support for openai-like (custom) endpoints
* fix: missed compiler / type issues from addition of getAnthropicLLMConfig
* refactor: update tokens.ts to export constants and functions, enhance type definitions, and adjust default values
* WIP: first pass, decouple `llmConfig` from `configOptions`
* chore: update import path for OpenAI configuration from 'llm' to 'config'
* refactor: enhance type definitions for ThinkingConfig and update modelOptions in AnthropicConfigOptions
* refactor: cleanup type, introduce openai transform from alt provider
* chore: integrate removeNullishValues in Google llmConfig and update OpenAI exports
* chore: bump version of @librechat/api to 1.3.5 in package.json and package-lock.json
* refactor: update customParams type in OpenAIConfigOptions to use TConfig['customParams']
* refactor: enhance transformToOpenAIConfig to include fromEndpoint and improve config extraction
* refactor: conform userId field for anthropic/openai, cleanup anthropic typing
* ci: add backward compatibility tests for getOpenAIConfig with various endpoints and configurations
* ci: replace userId with user in clientOptions for getLLMConfig
* test: add Azure OpenAI endpoint tests for various configurations in getOpenAIConfig
* refactor: defaultHeaders retrieval for prompt caching for anthropic-based custom endpoint (litellm)
* test: add unit tests for getOpenAIConfig with various Anthropic model configurations
* test: enhance Anthropic compatibility tests with addParams and dropParams handling
* chore: update @librechat/agents dependency to version 2.4.78 in package.json and package-lock.json
* chore: update @librechat/agents dependency to version 2.4.79 in package.json and package-lock.json
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* fix: freq. and pres. penalty use camelcase
* ci: OpenAI Configuration Tests
* ci: Enhance OpenAI Configuration Tests with Azure and Custom Endpoint Scenarios
* Added integration tests for OpenAI and Azure configurations simulating various initialization scenarios.
* Updated OpenAIConfigOptions to allow null values for reverseProxyUrl and proxy.
* Improved handling of reasoning parameters in tests for both OpenAI and Azure setups.
* Ensured robust error handling for missing API keys and malformed configurations.
* Optimized performance for large parameter sets in configuration.
* test: Add comprehensive integration tests for Anthropic LLM configuration
* Introduced real usage integration tests for various Anthropic endpoint configurations, including handling of proxy and reverse proxy setups.
* Implemented model-specific scenarios for Claude-3.7 and web search functionality.
* Enhanced error handling for missing user IDs and large parameter sets.
* Validated parameter logic, including default values, boundary conditions, and type handling for numeric and array parameters.
* Ensured proper exclusion of system options from model options and maintained expected behavior across different model variations.
* feat: added support for custom JINA_API_URL
* fixed tests
* chore: Update @librechat/agents dependency to version 2.4.77 in package-lock.json and package.json files
* fix: Update Jina API URL to use environment variable in configuration files
* Refactor AppService, web.ts, and config.ts to replace hardcoded Jina API URL with an environment variable placeholder.
* Ensure consistency across tests and configuration for Jina API URL.
* chore: alphabetical order translation.json
* fix: alphabetical order
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* Refactor deleteTokens to use an array of conditions for querying, ensuring only specified fields are considered for deletion.
* Add error handling to prevent accidental deletion when no query parameters are provided.
* Update AuthService to match the new deleteTokens signature by passing an object instead of a string for email.
