* docs: add changelog for v0.8.2 release with major accessibility improvements, dynamic MCP server management, and new model support
* docs: add documentation for Resumable Streams feature, including benefits, deployment modes, and troubleshooting tips
* ⚙️ Config v1.3.3
* docs: enhance Redis configuration guide to include horizontal scaling and resumable streams details
* docs: enhance configuration documentation for various services including Anthropic via Vertex AI, AWS Bedrock, Gemini Image Generation, and CDN options for Amazon S3 and Azure Blob Storage
* docs: enhance configuration documentation for logging, file upload, and speech features, including rate limiting options and environment variable references
* docs: update changelog for v0.8.2 to reflect major accessibility improvements and new resumable LLM streams feature
* docs: update changelog for v1.3.3 to include link to promptCache model specs documentation
* docs: enhance SSRF protection documentation for allowedDomains configuration in actions and MCP settings
* docs: update release date for Config v1.3.3 in changelog
* docs: v0.8.2-rc2 changelog
* docs: add highlights section
* fix: combine internationlization and change to correct full changelog link
* fix: add back what's changed header
* chore: polish highlights
* chore: final tweaks
* Update changelog for v0.8.2-rc2
* Remove highlights from v0.8.2-rc2 changelog
Removed highlights section from the changelog for version 0.8.2-rc2.
* Update release date for v0.8.2-rc2
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* docs: v0.8.2-rc1 changelog
* fix: swap out old mistake title
* fix: semantic commits take sorting precedence over emojis
* Update changelog for version 0.8.2-rc1
Added new features, bug fixes, and dependency updates for version 0.8.2-rc1.
* Update changelog for v0.8.2-rc1
Updated changelog for version 0.8.2-rc1 with new features, bug fixes, and dependency updates.
* Fix changelog entry for @librechat/agents bump
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* docs: add v0.8.1 changelog
* chore: reorder model updates
* chore: bump date
* chore: bump date and latest commits
* chore: update release date to 2025/12/11 for v0.8.1
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
- Introduced `context` capability for agents endpoint, enabling file uploads in chat.
- Enhanced `fileConfig` with OCR, text parsing, STT separation, and `fileTokenLimit` parameter.
- Added `transactions` object structure for token usage tracking.
- Included `jinaApiUrl` in `webSearch` configuration for custom Jina instances.
- Updated documentation for `fileConfig` to reflect new fields and processing methods.
* 📚 docs: Add OCR, textParsing, and fileTokenLimit configuration documentation (#376)
- Added support for `ocr` and `textParsing` configurations in `fileConfig`, allowing users to specify file types for OCR processing and direct text extraction.
- Introduced `fileTokenLimit` parameter for all endpoints to manage maximum token limits for file processing.
* 📚 docs: Add STT configuration documentation (#380)
- Added `stt` configuration to `fileConfig` for Speech-to-Text audio file processing, including supported MIME types.
- Updated changelog to reflect the addition of STT alongside existing OCR and text parsing configurations.
* 📚 docs: finish fileTokenLimit documentation and update changelog (#382)
* refactor: change `textParsing` to `text`
* docs: Enhance dotenv.mdx with MongoDB connection pool and schema configuration options
- Added new sections for MongoDB connection pool configuration, detailing options like MONGO_MAX_POOL_SIZE and MONGO_MIN_POOL_SIZE.
- Introduced MongoDB schema configuration options, including MONGO_AUTO_INDEX and MONGO_AUTO_CREATE.
- Provided usage examples and explanations for each new option to improve clarity and usability.
* docs: Add Microsoft Graph API integration details for Azure Entra ID
- Introduced new sections in dotenv.mdx and azure.mdx for Microsoft Graph API integration, enhancing permissions and sharing capabilities with people and group search features.
- Added prerequisites and configuration steps for enabling Graph API permissions in Azure app registration.
- Updated token-reuse.mdx to include information on Microsoft Graph API integration when using Azure Entra ID with token reuse.
* docs: Add OPENID_GENERATE_NONCE environment variable to dotenv.mdx
- Introduced the OPENID_GENERATE_NONCE variable, which forces the OpenID client to generate a nonce parameter, addressing requirements from identity providers like AWS Cognito and Authentik.
- Updated documentation to enhance clarity on its usage and importance in OpenID configurations.
* docs: Add SharePoint integration details and configuration instructions
- Introduced a new section in dotenv.mdx for SharePoint integration, detailing environment variables required for enabling the SharePoint file picker.
- Added comprehensive documentation in sharepoint.mdx covering the integration process, prerequisites, and user experience for accessing SharePoint files within LibreChat.
- Updated azure.mdx with additional information on SharePoint permissions needed for Azure app registration.
- Enhanced existing documentation to clarify the setup and usage of SharePoint features, ensuring users can effectively utilize this enterprise capability.
* docs: Add file citation configuration for agents endpoint in v1.2.9
- Introduced new file citation settings (`maxCitations`, `maxCitationsPerFile`, `minRelevanceScore`) to enhance control over citation quality and quantity in agent responses.
- Updated interface configuration to include `fileCitations`, enabling display of file citations during file search functionality.
- Added detailed documentation for the new configuration options in the changelog and relevant sections of the documentation.
* docs: Update fileCitations configuration details in v1.2.9
- Revised the description of the `fileCitations` setting to clarify its role as a global toggle for the `FILE_CITATIONS` permission, affecting all users regardless of individual permissions.
- Enhanced documentation in both the changelog and interface configuration sections to reflect these changes and improve user understanding of citation display behavior during file searches.
* docs: Add USE_REDIS_CLUSTER environment variable to Redis configuration
- Introduced the USE_REDIS_CLUSTER variable in dotenv.mdx to enable Redis cluster mode when using a single URI.
- Updated redis.mdx to include usage instructions for the new variable, enhancing clarity on Redis cluster configurations.
* chore: remove non-existant image reference
* chore: add missing code block language
* docs: Add migration instructions for agent permissions in v0.8.0-rc3+
- Introduced a new section detailing the migration to an ACL-based permission system for agents, including permission levels (OWNER, EDITOR, VIEWER).
- Provided step-by-step commands for running the migration based on different deployment methods (docker-compose, deploy-compose, local development).
- Explained the implications of the migration on existing agents and included a note on prompt permissions migration.
- Introduced a new changelog file detailing significant changes, features, and bug fixes in the v0.8.0-rc3 release.
- Created a corresponding page to display the changelog with metadata including date and title.
- Highlights include a granular permissions system, agent marketplace enhancements, and various new features and refactoring efforts.
Full changelog available at: https://github.com/danny-avila/LibreChat/compare/v0.8.0-rc2...v0.8.0-rc3
* v0.8.0-rc2
* 📚 docs: Update Redis configuration details in dotenv.mdx
- Added a new section highlighting Redis performance benefits and horizontal scaling capabilities.
- Updated configuration options for Redis, including new parameters for authentication and connection management.
- Clarified usage notes regarding `USE_REDIS`, `REDIS_URI`, and mutual exclusivity of `REDIS_KEY_PREFIX_VAR` and `REDIS_KEY_PREFIX`.
* 📚 docs: Update memory functionality notes in memory.mdx
- Removed the note indicating that memory only works with agents, clarifying the configuration requirements for memory functionality in LibreChat.
* 📚 docs: Update custom endpoint and default parameters documentation
- Clarified the usage of the `addParams` field in custom endpoints, emphasizing its importance for API-specific options like `max_tokens`.
- Removed default values for `temperature`, `top_p`, `presence_penalty`, and `frequency_penalty` from the default parameters section to streamline the documentation.
* 📚 docs: Enhance memory agent execution notes in memory.mdx
- Added a new callout explaining the execution behavior of the memory agent when memory is enabled.
- Clarified the timing and order of memory updates to ensure a seamless user experience during chat interactions.
* 📚 docs: Add Cloudflare Workers AI configuration documentation
- Introduced a new section detailing the setup and configuration for Cloudflare Workers AI.
- Included required environment variables and example YAML configuration for integration with LibreChat.
- Highlighted compatibility notes and known issues with specific models.
* 📚 docs: Update reasoning effort and add verbosity parameter in model specs
- Changed accepted values for reasoning effort from "None", "Low", "Medium", "High" to "minimal", "low", "medium", "high".
- Updated default value for reasoning effort to reflect API default when not set.
- Introduced a new parameter, verbosity, with accepted values "low", "medium", "high" and provided default value information.
- Updated relevant sections in the URL query documentation to include the new verbosity parameter.
* 📚 docs: Add Auth0 configuration for OpenID Connect
- Introduced a new documentation file for configuring Auth0 as an OpenID Connect provider for LibreChat.
- Updated existing documentation to include Auth0 in the OpenID Connect section and token reuse guidelines.
- Added necessary environment variable details and configuration steps specific to Auth0, including the importance of the `OPENID_AUDIENCE` variable for token validation.
* chore: add bash syntaxing to code blocks
* chore: add alias for cloudflare
* chore: clarification in cloudflare ai docs
- Introduced `fileSearch` option to enable or disable the file search button in the chat interface, with a default value of `true`.
- Updated configuration documentation to include `fileSearch` alongside `webSearch`.
- Enhanced changelog to reflect these new features and their implications for the chat interface.
* docs: `temporaryChatRetention` to configure retention period for temporary chats to changelog
* docs: `clientImageResize` for automatic client-side image resizing before upload to changelog
* docs: Add rate limiting configurations for login, registration, import conversations, and forking
- Introduced detailed documentation for rate limiting features to prevent abuse, including limits on login attempts, registration, conversation imports, and conversation forking.
- Added configuration options for both IP and user-based limits across these features.
- Updated existing documentation to reflect new rate limiting capabilities and their implications for system security and resource management.
* docs: Fix typos in OpenID on-behalf flow configuration variables
* docs: Add GOOGLE_SERVICE_KEY_FILE environment variable for Vertex AI authentication
- Introduced the `GOOGLE_SERVICE_KEY_FILE` option in the dotenv documentation, allowing users to specify the path to their Google service account JSON key file.
- Updated the Google configuration documentation to include alternative methods for managing service account credentials, enhancing flexibility for users.
* chore: Update bun.lockb to reflect dependency changes
* docs: Update changelog for version 1.2.8 with enhancements to MCP server management and new features
- Enhanced MCP server management with new features including `serverInstructions`, user placeholder variables, `customUserVars`, and centralized `mcpServers` configuration.
- Improved connection status tracking and OAuth support for MCP servers.
- Added support for dynamic user field placeholders in custom endpoint headers.
- Updated `clientImageResize` and `temporaryChatRetention` configurations with detailed descriptions.
- Enhanced web search configuration with comprehensive Firecrawl scraper options.
- Improved Model Specs documentation with updates on parameter support.
* docs: Update OCR configuration documentation for Google Vertex AI support
- Added `vertexai_mistral_ocr` strategy option for OCR configuration, enabling the use of Mistral OCR models on Google Cloud Vertex AI.
- Updated documentation to include methods for providing Google Cloud service account credentials, including file path, URL, base64 encoded JSON, and raw JSON string.
- Enhanced existing sections to reflect the new strategy and its requirements, including automatic extraction of project ID and JWT authentication for secure access.
- Included example configurations for Google Vertex AI deployments in the documentation.
* docs: Enhance GOOGLE_SERVICE_KEY_FILE documentation for base64 encoding option
- Added support for providing the `GOOGLE_SERVICE_KEY_FILE` as a base64 encoded JSON string in the documentation.
- Updated existing sections to clarify the various methods for specifying Google Cloud service account credentials, improving user guidance for Vertex AI authentication.
* docs: Add `REDIS_KEY_PREFIX_VAR` to dotenv documentation for dynamic Redis key prefix
- Introduced `REDIS_KEY_PREFIX_VAR`, an environment variable for specifying a dynamic Redis key prefix, enhancing flexibility for cloud deployments.
- Updated documentation to reflect this new option and its use case, particularly in scenarios involving Kubernetes revision numbers.
* docs: Update changelog and configuration documentation for title generation enhancements
- Added detailed configuration options for title generation across all endpoints, including `titleMethod`, `titlePrompt`, `titlePromptTemplate`, and `titleEndpoint`.
- Updated existing documentation to reflect these new options and their usage, improving clarity on how to customize title generation.
- Included notes on shared endpoint settings applicable to various AI models, enhancing user guidance for configuration.
* fix: broken links
* chore: formatting
* chore: reorganize librechat.yaml sub sections
- Updated changelog for version 1.2.8 to include enhancements in MCP server management, such as connection status tracking and OAuth support.
- Added detailed documentation on connection status indicators, server initialization processes, and user interface improvements for managing MCP servers.
- Introduced new images and videos to illustrate the updated features and functionalities.
* 📘 docs: Enhance Model Specs documentation with new parameters and default values
- Updated Model Specs documentation to include new parameters: `reasoning_effort`, `reasoning_summary`, `useResponsesApi`, `web_search`, `disableStreaming`, `thinking`, and `thinkingBudget`.
- Added some default values for existing parameters
- Documented changes in changelog
* docs: change note on model params from 'numbers' to 'values' to account for new params that don't have numeric values
* 📚 docs: Add MCP Servers configuration to interface documentation
- Introduced `mcpServers` field in the interface configuration with a placeholder for the MCP server selection dropdown.
- Updated example configurations and added detailed descriptions for the `mcpServers` key and its sub-key `placeholder` in the documentation.
* 📚 docs: Add docs update summary to config_v1.2.8 changelog
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 📚 docs: Update OCR documentation for clarity and structure
* 📚 docs: Add Model Context Protocol (MCP) documentation and update features
* 📚 docs: Add Model Context Protocol (MCP) section to features documentation
* 📚 docs: Enhance MCP documentation with OAuth authentication details and configuration examples
* 📚 docs: Update MCP documentation with improved configuration examples and OAuth authentication details
* 📚 docs: Update dotenv documentation to reflect new index header constants
* 📚 docs: Revise MCP integration documentation for Agents with clearer instructions and new images
- Updated the steps for adding MCP tools to agents for better clarity and organization.
- Introduced new images to illustrate the MCP tools interface.
- Removed outdated image and improved the overall structure of the documentation.
* 📚 docs: Enhance MCP documentation with custom user variables support
---------
Co-authored-by: Aleš Kůtek <kutekales@gmail.com>
* 📚 docs: Update Config Version to v1.2.8 and add Azure Mistral OCR support
- Updated version numbers in multiple configuration files to reflect the new version 1.2.8.
- Introduced a new `azure_mistral_ocr` strategy option for OCR configuration, enabling the use of Mistral OCR models deployed on Azure AI Foundry.
- Enhanced documentation for OCR configuration to include details on Azure deployment and its requirements.
- Added changelog entries for version 1.2.8, summarizing the new features and updates.
* 📚 docs: Enhance changelog for v1.2.8 with MCP Servers updates
- Added `serverInstructions` to MCP Servers object structure, detailing its role in agent context.
- Introduced new dynamic user field placeholders for enhanced multi-user support, including `{{LIBRECHAT_USER_ID}}` and `{{LIBRECHAT_USER_*}}`.
- Updated documentation links for better navigation and clarity on MCP Servers object structure.
* 📚 docs: Update changelog and OCR documentation for v1.2.8
- Enhanced the changelog for v1.2.8 with additional details on user field placeholders in the MCP Servers object structure.
- Improved OCR documentation by linking strategies to their respective sections for better clarity and navigation.
- Noted the future implementation status of the custom OCR service in the documentation.
* feat: memories update
* docs: Add LibreChat documentation rules and configuration update guidelines
* docs: Update Node.js version requirements across documentation
- Revised Node.js prerequisites to specify v20.19.0+ (or ^22.12.0 or >= 23.0.0) in README.md, get_started.mdx, npm.mdx, docker_linux.mdx, and nginx.mdx for clarity and compatibility with openid-client v6.
* docs: Add DEBUG_OPENID_REQUESTS environment variable for enhanced OpenID debugging
- Introduced a new environment variable, DEBUG_OPENID_REQUESTS, to enable detailed logging of OpenID request headers for better troubleshooting.
- Updated documentation to include troubleshooting steps for OpenID Connect, emphasizing the use of the new logging feature.
* docs: Update changelog dates for versions v1.2.6 and v1.2.7
* docs: Enhance memory configuration documentation
- Updated the memory configuration section to clarify the default value for the personalize option.
- Changed the provider name from "openai" to "openAI" for consistency.
- Added notes regarding the provider field and valid model parameters.
- Improved examples for memory agent configuration.
* feat: Introduce web search functionality in configuration v1.2.6
- Added `webSearch` configuration to manage web search features, including search providers, scrapers, and rerankers.
- Implemented a toggle for `webSearch` in the interface configuration to control visibility in the chat interface.
- Updated agents configuration to include `web_search` capability, enabling web search for agents by default.
- Created detailed documentation for web search configuration and usage, including API key setup and component descriptions.
* feat: Add web search feature documentation and update configuration
- Introduced a new section for the web search feature in the documentation, detailing its capabilities and configuration options.
- Updated the `_meta.ts` file to include the web search entry.
- Enhanced the web search configuration instructions to emphasize the importance of using environment variable names instead of actual API keys in the YAML file.
* fix: Correct clip-path attribute to clipPath in RossIndex component
* docs: Expand web search feature documentation
- Added detailed information about the web search feature, including environment variable customization options.
- Included a table of required API keys for various search providers and services.
- Emphasized the ability to customize variable names in the `librechat.yaml` configuration file.
* docs: Update web search configuration settings
- Changed default `scraperTimeout` from 30000ms to 7500ms in the documentation.
- Updated `safeSearch` option to reflect new values: 0 (OFF), 1 (MODERATE - default), and 2 (STRICT).
- Enhanced descriptions for both settings to clarify their functionality and defaults.
* chore: officially deprecate `endpointsMenu`
* feat: add `chatMenu` option to MCP server configuration for dropdown visibility control
* chore: add missing `timeout` and `initTimeout` options to MCP server configuration
* chore: add Authorization header example to MCP server configuration
* Config v1.2.5
* chore: remove plugins configuration from Azure OpenAI documentation
* feat: add vLLM configuration documentation
* feat: add changelog for LibreChat v0.7.8 and update config date to 2025/5/7
* docs: Enhance MCP server documentation with multi-user support details and example configuration
* ✨ v0.7.8-rc1
* feat: Add changelog for v0.7.7-rc1 and update v0.7.8-rc1 to remove ogImage
* docs: Update new contributors section in changelog for v0.7.8-rc1
* docs: Remove idleTimeout from MCP server configuration examples for clarity
* chore: Remove template pricing page and related metadata for simplification
* feat: Add allowedProviders and addedEndpoints features for enhanced agent configuration
* wip: changelog 1.2.4
* feat: Enhance token balance management with auto-refill settings and detailed configuration options
* feat: Enhance balance management with new configuration options for auto-refill and user balances
* docs: Mark endpointsMenu setting as deprecated and provide migration guidance
* fix: Update Agent Chain Image to External Source and Remove Local File
* 📝 feat: Add timeout and initTimeout configuration options for MCP server requests
* WIP: Add `timeout` and `initTimeout` options for MCP server configuration
* 📝 feat: Update agent capabilities to include 'artifacts' and 'chain'
* 📝 feat: Add Agent Chain capability and Advanced Settings documentation
* 📝 feat: Add maxRecursionLimit option to agents configuration and update documentation
* 📝 feat: Update agents configuration with maxRecursionLimit and enhance capabilities documentation
* feat: Update Agent Chain documentation to include beta status and maximum agent limit
* 🌍 docs: Add OCR configuration documentation and object structure
* 🌍 docs: Enhance OCR capabilities documentation and add new feature details
* 🌍 docs: Add OCR configuration details and update links in documentation
* 🌍 docs: Update OCR configuration details and enhance documentation for new features
* 🌍 docs: Add OCR capability details and update changelog for new text extraction features
* 🌍 docs: Clarify OCR processing details in agent context and update documentation for text extraction
* 🌍 docs: Update OCR documentation title and enhance configuration details for Mistral model
* fix: example OCR `mistralModel` and clarifying comment on configuration
* 📘 docs: update Code Interpreter API limitations and add Rscript support
* 🚀 feat: Add recursionLimit to Agents Config for controlling maximum recursion depth
