* fix: reorder vision model entries for cheaper models first
* fix: add endpoint property to bedrock client initialization
* fix: exclude unsupported parameters for OpenAI Web Search models
* fix: enhance options to exclude unsupported parameters for Web Search models
* refactor: move `loadAuthValues` to `~/services/Tools/credentials`
* feat: add createAxiosInstance function to configure axios with proxy support
* WIP: First pass mistral ocr
* refactor: replace getConvoFiles with getToolFiles for improved file retrieval logic
* refactor: improve document formatting in encodeAndFormat function
* refactor: remove unused resendFiles parameter from buildOptions function (this option comes from the agent config)
* fix: update getFiles call to include files with `text` property as well
* refactor: move file handling to `initializeAgentOptions`
* refactor: enhance addImageURLs method to handle OCR text and improve message formatting
* refactor: update message formatting to handle OCR text in various content types
* refactor: remove unused resendFiles property from compactAgentsSchema
* fix: add error handling for Mistral OCR document upload and logging
* refactor: integrate OCR capability into file upload options and configuration
* refactor: skip processing for text source files in delete request, as they are directly tied to database
* feat: add metadata field to ExtendedFile type and update PanelColumns and PanelTable components for localization and metadata handling
* fix: source icon styling
* wip: first pass, frontend file context agent resources
* refactor: add hover card with contextual information for File Context (OCR) in FileContext component
* feat: enhance file processing by integrating file retrieval for OCR resources in agent initialization
* feat: implement OCR config; fix: agent resource deletion for ocr files
* feat: enhance agent initialization by adding OCR capability check in resource priming
* ci: fix `~/config` module mock
* ci: add OCR property expectation in AppService tests
* refactor: simplify OCR config loading by removing environment variable extraction, to be done when OCR is actually performed
* ci: add unit test to ensure environment variable references are not parsed in OCR config
* refactor: disable base64 image inclusion in OCR request
* refactor: enhance OCR configuration handling by validating environment variables and providing defaults
* refactor: use file stream from disk for mistral ocr api
* chore: update @librechat/agents to version 2.1.9
* feat: xAI standalone provider for agents
* chore: bump librechat-data-provider version to 0.7.6997
* fix: reorder import statements and enhance user listing output
* fix: Update Docker Compose commands to support v2 syntax with fallback
* 🔧 fix: drop `reasoning_effort` for o1-preview/mini models
* chore: requireLocalAuth logging
* fix: edge case artifact message editing logic to handle `new` conversation IDs
* fix: remove `temperature` from model options in OpenAIClient if o1-mini/preview
* fix: update type annotation for fetchPromisesMap to use Promise<string[]> instead of string[]
* feat: anthropic model fetching
* fix: update model name to use EModelEndpoint.openAI in fetchModels and fetchOpenAIModels
* fix: add error handling to modelController for loadModels
* fix: add error handling and logging for model fetching in loadDefaultModels
* ci: update getAnthropicModels tests to be asynchronous
* feat: add user ID to model options in OpenAI and custom endpoint initialization
---------
Co-authored-by: Andrei Berceanu <andreicberceanu@gmail.com>
Co-authored-by: KiGamji <maloyh44@gmail.com>
* feat: Add thinking and thinkingBudget parameters for Bedrock Anthropic models
* chore: Update @librechat/agents to version 2.1.8
* refactor: change region order in params
* refactor: Add maxTokens parameter to conversation preset schema
* refactor: Update agent client to use bedrockInputSchema and improve error handling for model parameters
* refactor: streamline/optimize llmConfig initialization and saving for bedrock
* fix: ensure config titleModel is used for all endpoints
* refactor: enhance OpenAIClient and agent initialization to support endpoint checks for OpenRouter
* chore: bump @google/generative-ai
* 🔧 fix: Log warning for aborted operations in AgentClient
* ci: Remove unused saveMessageToDatabase mock in FakeClient initialization
* ci: test actual implementation of saveMessageToDatabase
* refactor: Change log level from warning to error for aborted operations in AgentClient
* refactor: Add className prop to Image component for customizable styling, use theme selectors
* feat: FLUX Image Generation tool
* refactor: use new image output format for agents using DALL-E tools
* refactor: Enhance image fetching with proxy support and adjust logging placement in DALL-E 3 integration
* refactor: Enhance StableDiffusionAPI to support agent-specific return values and display message for generated images
* refactor: Add unit test execution for librechat-mcp in backend review workflow
* refactor: Update environment variable extraction logic, export from serpate module to avoid circular refs, and remove deprecated tests
* refactor: Add unit tests for environment variable extraction and enhance StdioOptionsSchema to process env variables
* 🔧 refactor: Update settings to use 'as const' for improved type safety and make gpt-4o-mini default model (cheapest)
* 📖 docs: Update README to reflect support for GPT-4.5 in image analysis feature
* 🔧 refactor: Update model handling to use default settings and improve encoding logic
* 🔧 refactor: Enhance model version extraction logic for improved compatibility with future GPT and omni models
* feat: GPT-4.5 tx/token update, vision support
* fix: $ref resolution logic in OpenAPI handling
* feat: add new 'anthropic-beta' header for Claude 3.7 to include token-efficient tools; ref: https://docs.anthropic.com/en/docs/build-with-claude/tool-use/token-efficient-tool-use
* fix: handling of top_k and top_p parameters for Claude-3.7 models (allowed without reasoning)
* feat: bump @librechat/agents for Anthropic Reasoning support
* fix: update reasoning handling for OpenRouter integration
* fix: enhance agent token spending logic to include cache creation and read details
* fix: update logic for thinking status in ContentParts component
* refactor: improve agent title handling
* chore: bump @librechat/agents to version 2.1.7 for parallel tool calling for Google models
* chore: include all assets for service worker, remove unused tsconfig.node.json, eslint ignore vite config
* chore: exclude image files from service worker caching
* refactor: simplify googleSchema transformation and error handling
* fix: max output tokens cap for 3.7 models
* fix: skip index fixing in CI, development, and test environments
* ci: add maxOutputTokens handling tests for Claude models
* refactor: drop top_k and top_p parameters for claude-3.7 in AnthropicClient and add tests for new behavior
* refactor: conditionally include top_k and top_p parameters for non-claude-3.7 models
* ci: add unit tests for getLLMConfig function with various model options
* chore: remove all OPENROUTER_API_KEY legacy logic
* refactor: optimize stream chunk handling
* feat: reset model parameters button
* refactor: remove unused examples field from convoSchema and presetSchema
* chore: update librechat-data-provider version to 0.7.6993
* refactor: move excludedKeys set to data-provider for better reusability
* feat: enhance saveMessageToDatabase to handle unset fields and fetched conversation state
* feat: add 'iconURL' and 'greeting' to excludedKeys in data provider config
* fix: add optional chaining to user ID retrieval in getConvo call
* chore: remove auto-focus for now
* refactor: move react-hook-form Controller Logic to AgentSelect from AgentPanel
* fix: a11y focus issue with AgentSelect by never replacing it in its component tree
* fix: maintain ComboBox focus and force re-render on agent ID change in AgentPanel
* chore: `gemini-2.0-flash-lite-preview-02-05` (deprecated)
* refactor: extract cache control logic and headers configuration to helper functions in AnthropicClient
* feat: anthropic agents prompt caching
* chore: bump @librechat/agents and related dependencies
* fix: typo
* fix: missing console color methods for admin scripts
* feat: Anthropic Claude 3.7 Sonnet Support
* feat: update eventsource to version 3.0.2 and upgrade @modelcontextprotocol/sdk to 1.4.1
* fix: update DynamicInput to handle number type and improve initial value logic
* feat: first pass Anthropic Reasoning (Claude 3.7)
* feat: implement streaming support in AnthropicClient with reasoning UI handling
* feat: add missing xAI (grok) models
* style: Enhance ControlCombobox with Carat Display, ClassName, and Disabled State
* refactor(ModelPanel): replace SelectDropdown with ControlCombobox for improved accessibility
* style: Adjust padding and positioning in ModelPanel for improved layout
* style(ControlCombobox): add containerClassName and iconSide props for enhanced customization
* style(ControlCombobox): add iconClassName prop for customizable icon styling
* refactor(AgentPanel): enhance layout with new button for creating agents and adjust structure for better alignment
* refactor(AgentSelect): replace SelectDropDown with ControlCombobox for improved accessibility and layout
* feat(translation): add new translation key for improved UI clarity
* style(AgentSwitcher, AssistantSwitcher): add iconClassName prop for customizable icon styling
* refactor(AgentPanelSkeleton): improve layout of skeleton components to match new visual structure
* style(AgentPanel, AgentPanelSkeleton): add margin to flex container for improved layout consistency
* a11y(AgentSelect, ControlCombobox): add selectId prop for preventing focus going to start to page after agent selection
* fix(AgentSelect): update SELECT_ID constant for improved clarity in component identification
* fix(GoogleClient): update type annotation, add abort handling for content generation requests, catch "uncaught" abort errors and GoogleGenerativeAI errors from `@google/generative-ai`
* 🔧 refactor: handle full path for code env. file re-upload
* fix: update react-resizable-panels to version 2.1.7 to resolve error thrown on unmount of artifacts; ref: https://github.com/bvaughn/react-resizable-panels/issues/372
* refactor: replace promptPrefix with systemMessage in GoogleClient for improved clarity, and to prevent saving LibreChat feature-specific instructions to the user's custom instructions
* refactor: Improve error logging for file upload and processing functions to prevent verbosity
* refactor: Add uploads directory to Docker Compose to persist file uploads
* refactor: `addAgentResourceFile` to handle edge case of non-existing `tool_resource` array
* refactor: Remove version specification from deploy-compose.yml
* refactor: Prefix filenames with file_id to ensure uniqueness in file uploads
* refactor: Enhance error handling in deleteVectors to log warnings for non-404 errors
* refactor: Limit file search results to top 5 based on relevance score
* 🌍 i18n: Update translation.json with latest translations
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* chore: bump https-proxy-agent and @librechat/agents
* refactor: Improve error logging in OllamaClient for API fetch failures
* feat: Add DeepSeek provider support and enhance provider name handling
* refactor: Use Providers.OLLAMA constant for model name check in fetchModels function
* feat: Enhance formatAgentMessages to handle reasoning content type
* feat: OpenRouter Agent Reasoning
* hard work and dedicationgit add .env.example :)
* fix: Handle Google social login with missing last name
Social login with Google was previously displaying 'undefined' when
a user's last name was empty or not provided.
Changes:
- Conditionally render last name only if it exists
- Prevent displaying 'undefined' when last name is missing
* fix: add missing file endings for developers yml,yaml and log
---------
Co-authored-by: Mohamed Al-Duraji <mbalduraji@college.harvard.edu>
Co-authored-by: Deepak Kendole <deepakdpk101@gmail.com>
Co-authored-by: Peter Rothlaender <peter.rothlaender@ginkgo.com>
* refactor: remove artifacts toggle
* refactor: allow hiding side panel while allowing artifacts view
* chore: rename SidePanelGroup to SidePanel for clarity
* Revert "refactor: remove artifacts toggle"
This reverts commit f884c2cfcd.
* feat: add artifacts capability to agent configuration
* refactor: conditionally set artifacts mode based on endpoint type
* feat: Artifacts Capability for Agents
* refactor: enhance getStreamText method to handle intermediate replies and add `stream_options` for openai/azure
* feat: localize progress text and improve UX in CodeAnalyze and ExecuteCode components for expanding analysis
* 🤖 refactor: streamline model selection logic for title model in GoogleClient
* refactor: add options for empty object schemas in convertJsonSchemaToZod
* refactor: add utility function to check for empty object schemas in convertJsonSchemaToZod
* fix: Google MCP Tool errors, and remove Object Unescaping as Google fixed this
* fix: google safetySettings
* feat: add safety settings exclusion via GOOGLE_EXCLUDE_SAFETY_SETTINGS environment variable
* fix: rename environment variable for console JSON string length
* fix: disable portal for dropdown in ExportModal component
* fix: screenshot functionality to use image placeholder for remote images
* feat: add visionMode property to BaseClient and initialize in GoogleClient to fix resendFiles issue
* fix: enhance formatMessages to include image URLs in message content for Vertex AI
* fix: safety settings for titleChatCompletion
* fix: remove deprecated model assignment in GoogleClient and streamline title model retrieval
* fix: remove unused image preloading logic in ScreenshotContext
* chore: update default google models to latest models shared by vertex ai and gen ai
* refactor: enhance Google error messaging
* fix: update token values and model limits for Gemini models
* ci: fix model matching
* chore: bump version of librechat-data-provider to 0.7.699
* 🔧 fix: Update regex to correctly match OpenAI model identifiers
* 🔧 fix: Enhance tool filtering logic in ToolService to handle inclusion and exclusion criteria for basic tools and toolkits
* feat: support o3-mini Azure streaming
* chore: Update model filtering logic to exclude audio and realtime models
* ci: linting error
* adding youtube tool
* refactor: use short `url` param instead of `videoUrl`
* refactor: move API key retrieval to a separate credentials module
* refactor: remove unnecessary `isEdited` message property
* refactor: remove unnecessary `isEdited` message property pt. 2
* refactor: YouTube Tool with new `tool()` generator, handle tools already created by new `tool` generator
* fix: only reset request data for multi-convo messages
* refactor: enhance YouTube tool by adding transcript parsing and returning structured JSON responses
* refactor: update transcript parsing to handle raw response and clean up text output
* feat: support toolkits and refactor YouTube tool as a toolkit for better LLM usage
* refactor: remove unused OpenAPI specs and streamline tools transformation in loadAsyncEndpoints
* refactor: implement manifestToolMap for better tool management and streamline authentication handling
* feat: support toolkits for assistants
* refactor: rename loadedTools to toolDefinitions for clarity in PluginController and assistant controllers
* feat: complete support of toolkits for assistants
---------
Co-authored-by: Danilo Pejakovic <danilo.pejakovic@leoninestudios.com>
* ✨ feat: Implement Show Thinking feature; refactor: testing thinking render optimizations
* ✨ feat: Refactor Thinking component styles and enhance Markdown rendering
* chore: add back removed code, revert type changes
* chore: Add back resetCounter effect to Markdown component for improved code block indexing
* chore: bump @librechat/agents and google langchain packages
* WIP: reasoning type updates
* WIP: first pass, reasoning content blocks
* chore: revert code
* chore: bump @librechat/agents
* refactor: optimize reasoning tag handling
* style: ul indent padding
* feat: add Reasoning component to handle reasoning display
* feat: first pass, content reasoning part styling
* refactor: add content placeholder for endpoints using new stream handler
* refactor: only cache messages when requesting stream audio
* fix: circular dep.
* fix: add default param
* refactor: tts, only request after message stream, fix chrome autoplay
* style: update label for submitting state and add localization for 'Thinking...'
* fix: improve global audio pause logic and reset active run ID
* fix: handle artifact edge cases
* fix: remove unnecessary console log from artifact update test
* feat: add support for continued message handling with new streaming method
---------
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
* feat: Google Model Parameters
* fix: dynamic input number value, previously coerced by zod schema
* refactor: support openrouter reasoning tokens and XML for thinking directive to conform to ollama
* fix: virtualize combobox to prevent performance drop on re-renders of long model/agent/assistant lists
* refactor: simplify Fork component by removing unnecessary chat context index
* fix: prevent rendering of Thinking component when children are null
* refactor: update Markdown component to replace <think> tags and simplify remarkPlugins configuration
* refactor: reorder remarkPlugins to improve plugin configuration in Markdown component
* fix: google-thinking model safety settings fix
* chore: update pricing/context for deepseek models
* ci: update Deepseek model token limits to use dynamic mapping
* 🔧 refactor: Remove unused penalties and enhance reasoning token handling in OpenAIClient
* 🔧 refactor: `addInstructions` default to adding instructions at index 0, flag for legacy behavior
* chore: remove long placeholder
* chore: update localization strings across multiple languages
* ci: adjust tests for new `addInstructions` behavior
* ✨ feat: Add OpenWeather Tool for Weather Data Retrieval 🌤️
* chore: linting
* chore: move test files
* fix: tool icon, allow user-provided keys, conform to app key assignment pattern
* chore: linting not included in #5212
---------
Co-authored-by: Jonathan Addington <jonathan.addington@jmaddington.com>
* 🐛 fix: default modelSpecs not being set
* feat: Add imageDetail parameter for OpenAI endpoints in tQueryParamsSchema
* feat: Implement processModelSpecs function to enhance model specs processing from configuration
* feat: Refactor configuration schemas and types for improved structure and clarity
* feat: Add append_current_datetime parameter to tQueryParamsSchema for enhanced endpoint functionality
* fix: Add endpointType to getSaveOptions and enhance endpoint handling in Settings component
* fix: Change endpointType to be nullable and optional in tConversationSchema for improved flexibility
* fix: allow save & submit for google endpoint
* 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
* docs: Update README to include Model Context Protocol support and enhance access descriptions
* fix: Update civic integrity threshold to use 'BLOCK_NONE' as default
* fix: Update GOOGLE_MODELS in .env.example and adjust civic integrity threshold for new model compatibility
* ✨ v0.7.6
* feat: Add 'gemini-2.0-flash-thinking-exp' model to googleModels context windows
* 📝 chore: Add comment to clarify purpose of check_updates.sh script
* feat: mcp package
* feat: add librechat-mcp package and update dependencies
* feat: refactor MCPConnectionSingleton to handle transport initialization and connection management
* feat: change private methods to public in MCPConnectionSingleton for improved accessibility
* feat: filesystem demo
* chore: everything demo and move everything under mcp workspace
* chore: move ts-node to mcp workspace
* feat: mcp examples
* feat: working sse MCP example
* refactor: rename MCPConnectionSingleton to MCPConnection for clarity
* refactor: replace MCPConnectionSingleton with MCPConnection for consistency
* refactor: manager/connections
* refactor: update MCPConnection to use type definitions from mcp types
* refactor: update MCPManager to use winston logger and enhance server initialization
* refactor: share logger between connections and manager
* refactor: add schema definitions and update MCPManager to accept logger parameter
* feat: map available MCP tools
* feat: load manifest tools
* feat: add MCP tools delimiter constant and update plugin key generation
* feat: call MCP tools
* feat: update librechat-data-provider version to 0.7.63 and enhance StdioOptionsSchema with additional properties
* refactor: simplify typing
* chore: update types/packages
* feat: MCP Tool Content parsing
* chore: update dependencies and improve package configurations
* feat: add 'mcp' directory to package and update configurations
* refactor: return CONTENT_AND_ARTIFACT format for MCP callTool
* chore: bump @librechat/agents
* WIP: MCP artifacts
* chore: bump @librechat/agents to v1.8.7
* fix: ensure filename has extension when saving base64 image
* fix: move base64 buffer conversion before filename extension check
* chore: update backend review workflow to install MCP package
* fix: use correct `mime` method
* fix: enhance file metadata with message and tool call IDs in image saving process
* fix: refactor ToolCall component to handle MCP tool calls and improve domain extraction
* fix: update ToolItem component for default isInstalled value and improve localization in ToolSelectDialog
* fix: update ToolItem component to use consistent text color for tool description
* style: add theming to ToolSelectDialog
* fix: improve domain extraction logic in ToolCall component
* refactor: conversation item theming, fix rename UI bug, optimize props, add missing types
* feat: enhance MCP options schema with base options (iconPath to start) and make transport type optional, infer based on other option fields
* fix: improve reconnection logic with parallel init and exponential backoff and enhance transport debug logging
* refactor: improve logging format
* refactor: improve logging of available tools by displaying tool names
* refactor: improve reconnection/connection logic
* feat: add MCP package build process to Dockerfile
* feat: add fallback icon for tools without an image in ToolItem component
* feat: Assistants Support for MCP Tools
* fix(build): configure rollup to use output.dir for dynamic imports
* chore: update @librechat/agents to version 1.8.8 and add @langchain/anthropic dependency
* fix: update CONFIG_VERSION to 1.2.0
