* 🔧 fix: Agent Deletion Logic to Update User Favorites
* Added functionality to remove agents from user favorites when an agent is deleted.
* Implemented updates in the deleteAgent and deleteUserAgents functions to ensure user favorites are correctly modified.
* Added comprehensive tests to verify that agents are removed from user favorites across multiple scenarios, ensuring data integrity and user experience.
* 🔧 test: Enhance deleteUserAgents Functionality Tests
* Added comprehensive tests for the deleteUserAgents function to ensure it correctly removes agents from user favorites across various scenarios.
* Verified that user favorites are updated appropriately when agents are deleted, including cases where agents are shared among multiple users and when users have no favorites.
* Ensured that existing agents remain unaffected when no agents are associated with the author being deleted.
* 🔧 refactor: Remove Deprecated getListAgents Functionality
* Removed the deprecated getListAgents function from the Agent model, encouraging the use of getListAgentsByAccess for ACL-aware agent listing.
* Updated related tests in Agent.spec.js to eliminate references to getListAgents, ensuring code cleanliness and maintainability.
* Adjusted imports and exports accordingly to reflect the removal of the deprecated function.
* fix: email verification handling in create-user command
* set emailVerified to true when the input is 'y'
* normalize email verification input and set emailVerified to true by default
Fixes ByteString conversion errors when user names contain Unicode
characters > 255 (e.g., ć, đ, ł, š, ž) in MCP server headers.
- Add encodeHeaderValue() function to Base64 encode extended Unicode
- Update processUserPlaceholders() to encode name/username/email in headers
- Update processSingleValue() with isHeader parameter
- Apply encoding in processMCPEnv() and resolveHeaders()
Tested locally with MCP server using user name 'Đorđe' (contains đ=272).
Headers are correctly encoded as base64, preventing ByteString errors.
Co-authored-by: kenzaelk98 <kenzaelk98@leoninestudios.com>
Co-authored-by: heptapod <164861708+leondape@users.noreply.github.com>
* 🔧 fix: Prevent race conditions in message saving during abort scenarios
* Added logic to save partial responses before returning from the abort endpoint to ensure parentMessageId exists in the database.
* Updated the ResumableAgentController to save response messages before emitting final events, preventing orphaned parentMessageIds.
* Enhanced handling of unfinished responses to improve stability and data integrity in agent interactions.
* 🔧 fix: logging and job replacement handling in ResumableAgentController
* Added detailed logging for job creation and final event emissions to improve traceability.
* Implemented logic to check for job replacement before emitting events, preventing stale requests from affecting newer jobs.
* Updated abort handling to log additional context about the abort result, enhancing debugging capabilities.
* refactor: abort handling and token spending logic in AgentStream
* Added authorization check for abort attempts to prevent unauthorized access.
* Improved response message saving logic to ensure valid message IDs are stored.
* Implemented token spending for aborted requests to prevent double-spending across parallel agents.
* Enhanced logging for better traceability of token spending operations during abort scenarios.
* refactor: remove TODO comments for token spending in abort handling
* Removed outdated TODO comments regarding token spending for aborted requests in the abort endpoint.
* This change streamlines the code and clarifies the current implementation status.
* ✅ test: Add comprehensive tests for job replacement and abort handling
* Introduced unit tests for job replacement detection in ResumableAgentController, covering job creation timestamp tracking, stale job detection, and response message saving order.
* Added tests for the agent abort endpoint, ensuring proper authorization checks, early abort handling, and partial response saving.
* Enhanced logging and error handling in tests to improve traceability and robustness of the abort functionality.
* fix: Token Spending Logic for Multi-Agents on Abort Scenarios
* Implemented logic to skip token spending if a conversation is aborted, preventing double-spending.
* Introduced `spendCollectedUsage` function to handle token spending for multiple models during aborts, ensuring accurate accounting for parallel agents.
* Updated `GenerationJobManager` to store and retrieve collected usage data for improved abort handling.
* Added comprehensive tests for the new functionality, covering various scenarios including cache token handling and parallel agent usage.
* fix: Memory Context Handling for Multi-Agents
* Refactored `buildMessages` method to pass memory context to parallel agents, ensuring they share the same user context.
* Improved handling of memory context when no existing instructions are present for parallel agents.
* Added comprehensive tests to verify memory context propagation and behavior under various scenarios, including cases with no memory available and empty agent configurations.
* Enhanced logging for better traceability of memory context additions to agents.
* chore: Memory Context Documentation for Parallel Agents
* Updated documentation in the `AgentClient` class to clarify the in-place mutation of agentConfig objects when passing memory context to parallel agents.
* Added notes on the implications of mutating objects directly to ensure all parallel agents receive the correct memory context before execution.
* chore: UsageMetadata Interface docs for Token Spending
* Expanded the UsageMetadata interface to support both OpenAI and Anthropic cache token formats.
* Added detailed documentation for cache token properties, including mutually exclusive fields for different model types.
* Improved clarity on how to access cache token details for accurate token spending tracking.
* fix: Enhance Token Spending Logic in Abort Middleware
* Refactored `spendCollectedUsage` function to utilize Promise.all for concurrent token spending, improving performance and ensuring all operations complete before clearing the collectedUsage array.
* Added documentation to clarify the importance of clearing the collectedUsage array to prevent double-spending in abort scenarios.
* Updated tests to verify the correct behavior of the spending logic and the clearing of the array after spending operations.
* Improved detection of code blocks to support both language identifiers and plain code fences.
* Updated tests to cover various scenarios, including edge cases with different language identifiers and multiline content.
* Ensured proper handling of code blocks with trailing whitespace and complex syntax.
* 🔧 fix: meilisearch incorrect count of total documents & performance improvement
Temporary documents were counted & removed 2 redundant heavy calls to the database, use known information instead
🔧 fix: respect MEILI_SYNC_THRESHOLD value
Do not sync with meili if threshold was not reached
* refactor: reformat lint
* fix: forces update if meili index settingsUpdated
* fix: focus transfer on add tool in Add Tools dialog
* fix: focus transfer to inputs on add mcp server in Add MCP Server Tools dialog
* chore: add comments disabling ESLint autfocus and documenting the purpose of the override
* chore: remove stray newline
- Added session cookie options for OpenID and SAML configurations, including maxAge and secure attributes based on the environment.
- Introduced DEFAULT_SESSION_EXPIRY from data-schemas for better session handling.
* Updated the background color in mobile.css for improved visibility.
* Refactored class names in SidePanelGroup.tsx to utilize a utility function for better consistency and maintainability.
* 🔧 fix: Update @librechat/agents version to 3.0.771 in package.json and package-lock.json
* 🔧 fix: Update @librechat/agents version to 3.0.772 in package.json and package-lock.json
* 🔧 fix: Update @librechat/agents version to 3.0.774 in package.json and package-lock.json
* 🔧 fix: Update z-index values for navigation and mask layers in mobile view
- Increased z-index of the .nav-mask class from 63 to 105 for improved layering.
- Updated z-index of the nav component from 70 to 110 to ensure it appears above other elements.
* 🔧 fix: Adjust z-index for navigation component in mobile view
- Updated the z-index of the .nav class from 64 to 110 to ensure proper layering above other elements.
* 🔧 fix: Standardize z-index values across conversation and navigation components
- Updated z-index to 125 for various components including ConvoOptions, AccountSettings, BookmarkNav, and FavoriteItem to ensure consistent layering and visibility across the application.
* 🛠️ fix: unreliable retry logic during meili sync in case of interruption
🛠️ fix: exclude temporary documents from the count on startup for meili sync
🛠️ refactor: improved meili index cleanup before sync
* fix: don't swallow the exception to prevent indefinite loop
fix: update log messages for more clarity
fix: more test coverage for exception handling
* 🪵 refactor: Preserve job error state for late stream subscribers
* 🔧 fix: Enhance error handling for late subscribers in GenerationJobManager
- Implemented a cleanup strategy for error jobs to prevent immediate deletion, allowing late clients to receive error messages.
- Updated job status handling to prioritize error notifications over completion events.
- Added integration tests to verify error preservation and proper notification to late subscribers, including scenarios with Redis support.
* 🪨 feat: Anthropic Beta Support for Bedrock
- Updated the Bedrock input parser to dynamically generate `anthropic_beta` headers based on the model identifier.
- Added a new utility function `getBedrockAnthropicBetaHeaders` to determine applicable headers for various Anthropic models.
- Modified existing tests to reflect changes in expected `anthropic_beta` values, including new test cases for full model IDs.
* test: Update Bedrock Input Parser Tests for Beta Headers
- Modified the test case for explicit thinking configuration to reflect the addition of `anthropic_beta` headers.
- Ensured that the test now verifies the presence of specific beta header values in the additional model request fields.
* feat: Bedrock provider support in memory processing
- Introduced support for the Bedrock provider in the memory processing logic.
- Updated the handling of instructions to ensure they are included in user messages for Bedrock, while maintaining the standard approach for other providers.
- Added tests to verify the correct behavior for both Bedrock and non-Bedrock providers regarding instruction handling.
* refactor: Bedrock memory processing logic
- Improved handling of the first message in Bedrock memory processing to ensure proper content is used.
- Added logging for cases where the first message content is not a string.
- Adjusted the processed messages to include the original content or fallback to a new HumanMessage if no messages are present.
* feat: Enhance Bedrock configuration handling in memory processing
- Added logic to set the temperature to 1 when using the Bedrock provider with thinking enabled.
- Ensured compatibility with additional model request fields for improved memory processing.
- Changed the endpoint check from `isAgentsEndpoint` to `isAssistantsEndpoint` to adjust the logic for processing file uploads.
- Reordered the import statements for better organization.
- Upgraded several dependencies including browserify-sign (4.2.3 to 4.2.5), hono (4.11.3 to 4.11.4), parse-asn1 (5.1.7 to 5.1.9), pbkdf2 (3.1.3 to 3.1.5), and ripemd160 (2.0.2 to 2.0.3).
- Adjusted engine requirements for compatibility with older Node.js versions.
- Cleaned up unnecessary nested module entries for pbkdf2.
* Refresh all S3 avatars for this user's accessible agent set, not the first page
* Cleaner debug messages
* Log errors as errors
* refactor: avatar refresh logic to process agents in batches and improve error handling. Introduced new utility functions for refreshing S3 avatars and updating agent records. Updated tests to cover various scenarios including cache hits, user ownership checks, and error handling. Added constants for maximum refresh limits.
* refactor: update avatar refresh logic to allow users with VIEW access to refresh avatars for all accessible agents. Removed checks for agent ownership and author presence, and updated related tests to reflect new behavior.
* chore: Remove YouTube toolkit due to #11331
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🔧 refactor: use approximate number of documents to improve performance
* 🔧 refactor: unittests for approximate document count in meilisearch sync
* refactor: limits persentage based on approximate total count & one more test case
* 🗑️ refactor: Remove YouTube API integration and related configurations as it's broken and should be integrated via MCP instead. Currently there seems not to be a single MCP out there with working get_transcript methods for months. API seems to have changed and there are no maintainers on these projects. We will work out something soon an MCP solution
- Deleted YouTube API key and related configurations from .env.example.
- Removed YouTube tools and their references from the API client, including the manifest and structured files.
- Updated package.json to remove YouTube-related dependencies.
- Cleaned up toolkit exports by removing YouTube toolkit references.
* chore: revert package removal to properly remove packages
* 🗑️ refactor: Remove YouTube API and related dependencies due to integration issues
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🔧 refactor: Improve token calculation in AgentClient.recordCollectedUsage
- Updated the token calculation logic to sum output tokens directly from all entries, addressing issues with negative values in parallel execution scenarios.
- Added comments for clarity on the usage of input tokens and output tokens.
- Introduced a new test file for comprehensive testing of the recordCollectedUsage function, covering various execution scenarios including sequential and parallel processing, cache token handling, and model fallback logic.
* 🔧 refactor: Anthropic `promptCache` handling in LLM configuration
* 🔧 test: Add comprehensive test for cache token handling in recordCollectedUsage
- Introduced a new test case to validate the handling of cache tokens across multiple tool calls in the recordCollectedUsage function.
- Ensured correct calculations for input and output tokens, including scenarios with cache creation and reading.
- Verified the expected interactions with token spending methods to enhance the robustness of the token management logic.
* 🔧 fix: MCP server ID resolver in access permissions (#11315)
- Replaced `findMCPServerById` with `findMCPServerByObjectId` in access permissions route and corresponding tests for improved clarity and consistency in resource identification.
* 🔧 refactor: Update MCP server resource access methods to use server name
- Replaced instances of `findMCPServerById` with `findMCPServerByServerName` across middleware, database, and test files for improved clarity and consistency in resource identification.
- Updated related comments and test cases to reflect the change in method usage.
* chore: Increase timeout for Redis update in GenerationJobManager integration tests
- Updated the timeout duration from 50ms to 200ms in the GenerationJobManager integration tests to ensure reliable verification of final event data in Redis after emitting the done event.
- Updated MessagesView to include min-height and overflow-hidden for better layout management.
- Adjusted ShareView to ensure proper height and overflow handling, enhancing the overall user experience.
* fix: Revoke OAuth and Vars. Config Regressions in MCP Panel
- Introduced a new Trash2 icon button in MCPCardActions for revoking OAuth access on connected OAuth servers.
- Updated MCPServerCard to handle the revoke action, allowing users to revoke OAuth for specific servers.
- Enhanced user experience by ensuring the revoke option is available regardless of the server's connection state.
* refactor: Reorganize Revoke Button Logic in MCPCardActions and Update Toast Messages
- Moved the Revoke button for OAuth servers to a new position in MCPCardActions for improved visibility.
- Updated the success message logic in useMCPServerManager to differentiate between uninstall and variable update actions, enhancing user feedback.
* i18n: Add new translation for MCP server access revocation message
* refactor: Centralize Deselection Logic in updateUserPluginsMutation
- Updated the success handler in useUpdateUserPluginsMutation to manage deselection of MCP server values when revoking access, improving code clarity and reducing redundancy.
- Simplified message assignment logic for user feedback during plugin updates.
* ✨ feat: Add proxy support for Google APIs in GeminiImageGen
- Implemented a proxy wrapper for globalThis.fetch to route requests to googleapis.com through a specified proxy.
- Added tests to verify the proxy configuration behavior, ensuring correct dispatcher application for Google API calls and preserving existing options.
Co-authored-by: [Your Name] <your.email@example.com>
* chore: remove comment
---------
Co-authored-by: [Your Name] <your.email@example.com>
Co-authored-by: Danny Avila <danacordially@gmail.com>
* 🔧 fix: Handle undefined tool definitions in agent and assistant creation (#11295)
* Updated the tool fetching logic in createAgentHandler, createAssistant, and patchAssistant functions to use nullish coalescing, ensuring that an empty object is returned if no tools are available. This change improves robustness against undefined values in tool definitions across multiple controller files.
* Adjusted the ToolService to maintain consistency in tool definition handling.
* 🔧 fix: Update filename generation in createToolEndCallback function
* Modified the filename generation logic to remove the tool_call_id from the filename, simplifying the naming convention for saved images. This change enhances clarity and consistency in the generated filenames.
* feat(bedrock): add Moonshot Kimi K2 Thinking model support
- Add Moonshot provider to BedrockProviders enum
- Add Moonshot-specific parameter settings with 16384 default max tokens
- Add conditional for anthropic_beta to only apply to Anthropic models
- Kimi K2 Thinking model: moonshot.kimi-k2-thinking (256K context)
* Delete add-kimi-bedrock.md
* Remove comment on anthropic_beta condition
Remove comment about adding anthropic_beta for Anthropic models.
* chore: enum order
* feat(bedrock): add tests to ensure anthropic_beta is not added to Moonshot Kimi K2 and DeepSeek models
---------
Co-authored-by: Danny Avila <danacordially@gmail.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
