- Introduced `inferMimeType` utility to improve MIME type detection for uploaded files, including support for HEIC and HEIF formats.
- Updated DragDropModal to utilize the new inference logic for validating file types, ensuring compatibility with various document upload providers.
- Added comprehensive tests for `inferMimeType` to cover various scenarios, including handling of unknown extensions and preserving browser-provided types.
* 🔧 fix: Gemini as Custom Endpoint Auth. Error for OAI-compatible API
* refactor: Google Compatibility in OpenAI Config
- Added a test to ensure `googleSearch` is filtered out when `web_search` is only present in `modelOptions`, not in `addParams` or `defaultParams`.
- Updated `transformToOpenAIConfig` to preserve `googleSearch` tools if `web_search` is explicitly enabled via `addParams` or `defaultParams`.
- Refactored the filtering logic for Google-specific tools to accommodate the new behavior.
* refactor: implement sanitizeFileForTransmit and sanitizeMessageForTransmit functions for smaller payload to client transmission
* refactor: enhance sanitizeMessageForTransmit to preserve empty files array and avoid mutating original message
* refactor: update sanitizeMessageForTransmit to ensure immutability of files array and improve test clarity
* refactor: Token Limit Processing with Enhanced Efficiency
- Added a new test suite for `processTextWithTokenLimit`, ensuring comprehensive coverage of various scenarios including under, at, and exceeding token limits.
- Refactored the `processTextWithTokenLimit` function to utilize a ratio-based estimation method, significantly reducing the number of token counting function calls compared to the previous binary search approach.
- Improved handling of edge cases and variable token density, ensuring accurate truncation and performance across diverse text inputs.
- Included direct comparisons with the old implementation to validate correctness and efficiency improvements.
* refactor: Remove Tokenizer Route and Related References
- Deleted the tokenizer route from the server and removed its references from the routes index and server files, streamlining the API structure.
- This change simplifies the routing configuration by eliminating unused endpoints.
* refactor: Migrate countTokens Utility to API Module
- Removed the local countTokens utility and integrated it into the @librechat/api module for centralized access.
- Updated various files to reference the new countTokens import from the API module, ensuring consistent usage across the application.
- Cleaned up unused references and imports related to the previous countTokens implementation.
* refactor: Centralize escapeRegExp Utility in API Module
- Moved the escapeRegExp function from local utility files to the @librechat/api module for consistent usage across the application.
- Updated imports in various files to reference the new centralized escapeRegExp function, ensuring cleaner code and reducing redundancy.
- Removed duplicate implementations of escapeRegExp from multiple files, streamlining the codebase.
* refactor: Enhance Token Counting Flexibility in Text Processing
- Updated the `processTextWithTokenLimit` function to accept both synchronous and asynchronous token counting functions, improving its versatility.
- Introduced a new `TokenCountFn` type to define the token counting function signature.
- Added comprehensive tests to validate the behavior of `processTextWithTokenLimit` with both sync and async token counting functions, ensuring consistent results.
- Implemented a wrapper to track call counts for the `countTokens` function, optimizing performance and reducing unnecessary calls.
- Enhanced existing tests to compare the performance of the new implementation against the old one, demonstrating significant improvements in efficiency.
* chore: documentation for Truncation Safety Buffer in Token Processing
- Added a safety buffer multiplier to the character position estimates during text truncation to prevent overshooting token limits.
- Updated the `processTextWithTokenLimit` function to utilize the new `TRUNCATION_SAFETY_BUFFER` constant, enhancing the accuracy of token limit processing.
- Improved documentation to clarify the rationale behind the buffer and its impact on performance and efficiency in token counting.
- Updated `useChatFunctions` to derive `iconURL` from conversation data before parsing
- Modified `parseCompactConvo` to explicitly omit `iconURL` from parsed conversations, reinforcing security measures around URL handling.
* 🖥️ feat: Add Proxy Support for Tavily API Tool
- Integrated ProxyAgent from undici to enable proxy support for API requests in TavilySearch and TavilySearchResults.
- Updated fetch options to conditionally include the proxy configuration based on the environment variable, enhancing flexibility for network requests.
* ci: TavilySearchResults with Proxy Support Tests
- Added tests to verify the integration of ProxyAgent for API requests in TavilySearchResults.
- Implemented conditional logic to check for the PROXY environment variable, ensuring correct usage of ProxyAgent based on its presence.
- Updated test setup to clear mocks before each test for improved isolation and reliability.
* refactor: Add back user variable descriptions for MCP under input and not as Tooltips
- Integrated DOMPurify to sanitize HTML content in user variable descriptions, ensuring safe rendering of links and formatting.
- Updated the AuthField component to display sanitized descriptions, enhancing security and user experience.
- Removed TooltipAnchor in favor of direct label rendering for improved clarity.
* 📦 chore: Update `dompurify` to v3.3.0 in package dependencies
- Added `dompurify` version 3.3.0 to `package.json` and `package-lock.json` for improved HTML sanitization.
- Updated existing references to `dompurify` to ensure consistency across the project.
* refactor: Update tooltip styles for sanitized description in AuthField component
* 🗨️ fix: Safe Validation for Prompt Updates
- Added `safeValidatePromptGroupUpdate` function to validate and sanitize prompt group update requests, ensuring only allowed fields are processed and sensitive fields are stripped.
- Updated the `patchPromptGroup` route to utilize the new validation function, returning appropriate error messages for invalid requests.
- Introduced comprehensive tests for the validation logic, covering various scenarios including allowed and disallowed fields, enhancing overall request integrity and security.
- Created a new schema file for prompt group updates, defining validation rules and types for better maintainability.
* 🔒 feat: Add JSON parse error handling middleware
* 🔒 fix: `iconURL` in conversation parsing
- Updated the `buildEndpointOption` middleware to derive `iconURL` from model specs when not provided by the client, improving security by preventing malicious URLs.
- Modified the `parseCompactConvo` function to strip `iconURL` from conversation inputs, ensuring it is only set server-side.
- Added comprehensive tests to validate the stripping of `iconURL` across various endpoint types, enhancing overall input sanitization.
* ✨ feat: Add ESLint rule for unused variables
- Introduced a new ESLint rule to warn about unused variables, allowing for better code quality and maintainability.
- Configured the rule to ignore variables and arguments that start with an underscore, accommodating common coding practices.
* 🔧 chore: Update @librechat/agents to version 3.0.35
* ✨ feat: Add DeepSeek Model Pricing and Token Handling
- Introduced pricing and token limits for 'deepseek-chat' and 'deepseek-reasoner' models, including prompt and completion rates.
- Enhanced tests to validate pricing and token limits for DeepSeek models, ensuring correct handling of model variations and provider prefixes.
- Updated cache multipliers for DeepSeek models to reflect new pricing structure.
- Improved max output token handling for DeepSeek models, ensuring consistency across different endpoints.
* 🔧 fix: Handle null content parts in message processing
- Added checks to filter out null content parts in various message handling functions, ensuring robustness against undefined values.
- Updated the `extractMessageContent`, `useContentHandler`, `useEventHandlers`, and `useStepHandler` hooks to prevent errors caused by null parts.
- Enhanced the `getAllContentText` utility to only include valid content types, improving overall message integrity.
* 🔧 fix: Enhance error handling in event and SSE handlers
- Wrapped critical sections in try-catch blocks within `useEventHandlers` and `useSSE` hooks to improve error management and prevent application crashes.
- Added console error logging for better debugging and tracking of issues during message processing and conversation aborting.
- Ensured that UI states like `setIsSubmitting` and `setShowStopButton` are correctly updated in case of errors, maintaining a consistent user experience.
* 🔧 fix: Filter out null and empty content in message export
- Enhanced the `useExportConversation` hook to filter out null content parts and empty strings during message processing, ensuring only valid content is included in the export.
- This change improves the integrity of exported conversations by preventing unnecessary empty entries in the output.
* 📐 refactor: Exclude Params from OAI Reasoning Models
- Introduced a new test suite for `getOpenAILLMConfig` covering various model configurations, including basic settings, reasoning models, and web search functionality.
- Validated parameter handling for different models, ensuring correct exclusions and conversions, particularly for temperature and max_tokens.
- Enhanced tests for default and additional parameters, drop parameters, and verbosity handling, ensuring robust coverage of the configuration logic.
* ci: Update OpenAI model version in configuration tests
- Changed model references from 'gpt-5' to 'gpt-4' across multiple test cases in the `getOpenAIConfig` function.
- Adjusted related parameter handling to ensure compatibility with the updated model version, including maxTokens and temperature settings.
- Enhanced test coverage for model options and their expected configurations.
- Updated the `findUser` method to normalize email fields to lowercase and trimmed whitespace for case-insensitive matching.
- Enhanced the `normalizeEmailInCriteria` function to handle email normalization in search criteria, including `` conditions.
- Added tests to ensure email normalization works correctly across various scenarios, including case differences and whitespace handling.
* 🤖 feat: Latest Grok Model Pricing & Context Rates
- Introduced 'grok-4-fast', 'grok-4-1-fast', and 'grok-code-fast' models with their respective prompt and completion rates.
- Enhanced unit tests to validate prompt and completion rates for the new models, including variations with prefixes.
- Updated token limits for the new models in the tokens utility, ensuring accurate handling in tests.
* 🔧 refactor: Optimize JSON Export Logic in useExportConversation Hook
Updated the export logic to create a Blob from the JSON string before downloading, improving compatibility and performance for file downloads. This change enhances the handling of deeply nested exports while maintaining the file size reduction achieved in previous updates.
Updated the export logic in the useExportConversation hook to use JSON.stringify without indentation, reducing file size for deeply nested exports. Additionally, ensured safe access to text content by providing a fallback for undefined values.
* 🔧 fix: Correct URL Construction in fetchModels Function
Updated the URL construction in the fetchModels function to ensure proper formatting by removing trailing slashes from the base URL. This change prevents potential issues with API endpoint calls.
* 🔧 fix: Remove OLLAMA from Known Custom Providers
Updated the isKnownCustomProvider function and providerConfigMap to exclude OLLAMA as a known custom provider, streamlining the provider checks and configurations.
* 🔧 test: Enhance fetchModels Tests for URL Construction
Added new test cases to validate the URL construction in the fetchModels function, ensuring it handles trailing slashes correctly and appends query parameters as expected. This improves the robustness of the API endpoint calls.
* chore: remove ollama provider-specific handling
* chore: Refactor imports to use isUserProvided from @librechat/api
* ✨ v0.8.1-rc2
- Updated version numbers in Dockerfile, Dockerfile.multi, package.json, and various package.json files for client, api, and data-provider.
- Adjusted appVersion in Chart.yaml and constants in config.ts to reflect the new version.
- Incremented versions for @librechat/api, @librechat/client, and librechat-data-provider packages.
* chore: Update Chart version to 1.9.3
- Incremented the chart version in Chart.yaml to reflect the latest changes.
Removed unnecessary debug logging statements in the extractOpenIDTokenInfo function to streamline the code and improve readability. This change enhances the clarity of the function's logic without altering its functionality.
* fix: exclude the currently edited bookmark from duplicate checks
* ci: Add comprehensive tests for BookmarkForm component
- Introduced a new test suite for the BookmarkForm component to validate bookmark editing functionality.
- Implemented tests for various scenarios including editing descriptions, renaming tags, and handling duplicate tags.
- Ensured proper feedback through toasts for error cases and successful submissions.
- Mocked necessary hooks and context to isolate component behavior during tests.
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
When using direct endpoints (e.g., Google) instead of Agents, `this.options.agent` is undefined, causing provider detection to fail. This resulted in "Unknown content type document" errors for Google/Gemini PDF uploads.
Added `?? this.options.endpoint` fallback in addDocuments(), addVideos(), and addAudios() methods to ensure correct provider detection for all endpoint types.
* feat: shift collapse chevron inside ChatForm input area
* feat: add soft gradient on bottom of collapsed text input so there isn't a hard cut off when text overflows
* feat: add better scroll bar behavior for main chat input
* fix: smooth out purple gradient for temporary chats
* feat: better colors for gradient
* feat: use blur instead of colors
* chore: address copilot comments
* fix: increase RAG API text parsing timeout for large files
* ci: Update text.spec.ts
---------
Co-authored-by: Rosen Simov <rosen.simov@endurosat.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
* fix: remove side panel elements from screen reader when hidden
There's both left & right side panels; elements of both of them
are hidden when dismissed. However, currently they are being hidden
by using classes to hide their UI (such as making the sidebar
zero width).
That works for visually dismissing these elements, but they can still
be viewed by a screen reader (using the tab key to jump between
interactable elements). That can be a rather confusing experience
for anyone visually impaired (such as duplicate buttons, or buttons
that do nothing).
--------
I've changed it so hidden elements are fully removed from the render.
This prevents them from being interactable via keyboard.
I leveraged Motion to duplicate the animations as they happened before.
I subtly cleaned up the animations while I was at it.
* Implemented reasonable suggestions from Copilot review
* 🤖 feat: Claude Opus 4.5 Token Rates and Window Limits
- Introduced new model 'claude-opus-4-5' with defined prompt and completion values in tokenValues and cacheTokenValues.
- Updated tests to validate prompt, completion, and cache rates for the new model.
- Enhanced model name handling to accommodate variations for 'claude-opus-4-5' across different contexts.
- Adjusted schemas to ensure correct max output token limits for the new model.
* ci: Add tests for "prompt-caching" beta header in Claude Opus 4.5 models
- Implemented tests to verify the addition of the "prompt-caching" beta header for the 'claude-opus-4-5' model and its variations.
- Updated future-proofing logic to ensure correct max token limits for Claude 4.x and 5.x Opus models, adjusting defaults to 64K where applicable.
- Enhanced existing tests to reflect changes in expected max token values for future Claude models.
* chore: Remove redundant max output check for Anthropic settings
- Eliminated the unnecessary check for ANTHROPIC_MAX_OUTPUT in the anthropicSettings schema, streamlining the logic for handling max output values.
* fix: Header and Environment Variable Handling Bug from #9931
* refactor: Remove warning log for missing tokens in extractOpenIDTokenInfo function
* feat: Enhance resolveNestedObject function for improved placeholder processing
- Added a new function `resolveNestedObject` to recursively process nested objects, replacing placeholders in string values while preserving the original structure.
- Updated `createTestUser` to use `IUser` type and modified user ID generation.
- Added comprehensive unit tests for `resolveNestedObject` to cover various scenarios, including nested structures, arrays, and custom user variables.
- Improved type handling in `processMCPEnv` to ensure correct processing of mixed numeric and placeholder values.
* refactor: Remove unnecessary manipulation of Bedrock options introduced in #9931
- Eliminated the resolveHeaders function call from the getOptions method in options.js, as it was no longer necessary for processing additional model request fields.
- This change simplifies the code and improves maintainability.
* 🗑️ chore: Remove @microsoft/eslint-formatter-sarif from dependencies and update ESLint CI workflow
- Removed @microsoft/eslint-formatter-sarif from package.json and package-lock.json.
- Updated ESLint CI workflow to eliminate SARIF upload logic and related environment variables.
* chore: Remove ts-jest from dependencies in jest.config and package files
* chore: Update package dependencies to latest versions
- Upgraded @rollup/plugin-commonjs from 25.0.2 to 29.0.0 across multiple packages.
- Updated rimraf from 5.0.1 to 6.1.2 in packages/api, client, data-provider, and data-schemas.
- Added new dependencies: @isaacs/balanced-match and @isaacs/brace-expansion in package-lock.json.
- Updated glob from 8.1.0 to 13.0.0 and adjusted related dependencies accordingly.
* chore: remove prettier-eslint dependency from package.json
* chore: npm audit fix
* fix: correct `getBasePath` import
* fix: update @librechat/agents dependency to version 3.0.29
* chore: fix typing by replacing TUser with IUser
* chore: import order
* fix: replace TUser with IUser in run and OAuthReconnectionManager modules
* fix: update @librechat/agents dependency to version 3.0.30
* remove all user metadata on deletion
* chore: import order
* fix: Update JSDoc types for deleteMessages function parameters and return value
* fix: Enhance user deletion process by removing associated data and updating group memberships
* fix: Add missing config middleware to user deletion route
* fix: Refactor agent and prompt deletion processes to bulk delete and remove associated ACL entries
* fix: Add deletion of OAuth tokens and ACL entries in user deletion process
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* fix: add basePath pattern to support login/register and image paths
* Fix linter errors
* refactor: Update import statements for getBasePath and isEnabled, and add path utility functions with tests
- Refactored imports in addImages.js and StableDiffusion.js to use getBasePath from '@librechat/api'.
- Consolidated isEnabled and getBasePath imports in validateImageRequest.js.
- Introduced new path utility functions in path.ts and corresponding unit tests in path.spec.ts to validate base path extraction logic.
* fix: Update domain server base URL in MarkdownComponents and refactor authentication redirection logic
- Changed the domain server base URL in MarkdownComponents.tsx to use the API base URL.
- Refactored the useAuthRedirect hook to utilize React Router's navigate for redirection instead of window.location, ensuring a smoother SPA experience.
- Added unit tests for the useAuthRedirect hook to verify authentication redirection behavior.
* test: Mock isEnabled in validateImages.spec.js for improved test isolation
- Updated validateImages.spec.js to mock the isEnabled function from @librechat/api, ensuring that tests can run independently of the actual implementation.
- Cleared the DOMAIN_CLIENT environment variable before tests to avoid interference with basePath resolution.
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* feat: Add OpenID Connect federated provider token support
Implements support for passing federated provider tokens (Cognito, Azure AD, Auth0)
as variables in LibreChat's librechat.yaml configuration for both custom endpoints
and MCP servers.
Features:
- New LIBRECHAT_OPENID_* template variables for federated provider tokens
- JWT claims parsing from ID tokens without verification (for claim extraction)
- Token validation with expiration checking
- Support for multiple token storage locations (federatedTokens, openidTokens)
- Integration with existing template variable system
- Comprehensive test suite with Cognito-specific scenarios
- Provider-agnostic design supporting Cognito, Azure AD, Auth0, etc.
Security:
- Server-side only token processing
- Automatic token expiration validation
- Graceful fallbacks for missing/invalid tokens
- No client-side token exposure
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: Add federated token propagation to OIDC authentication strategies
Adds federatedTokens object to user during authentication to enable
federated provider token template variables in LibreChat configuration.
Changes:
- OpenID JWT Strategy: Extract raw JWT from Authorization header and
attach as federatedTokens.access_token to enable {{LIBRECHAT_OPENID_TOKEN}}
placeholder resolution
- OpenID Strategy: Attach tokenset tokens as federatedTokens object to
standardize token access across both authentication strategies
This enables proper token propagation for custom endpoints and MCP
servers that require federated provider tokens for authorization.
Resolves missing token issue reported by @ramden in PR #9931🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Denis Ramic <denis.ramic@nfon.com>
Co-Authored-By: Claude <noreply@anthropic.com>
* test: Add federatedTokens validation tests for OIDC strategies
Adds comprehensive test coverage for the federated token propagation
feature implemented in the authentication strategies.
Tests added:
- Verify federatedTokens object is attached to user with correct structure
(access_token, refresh_token, expires_at)
- Verify both tokenset and federatedTokens are present in user object
- Ensure tokens from OIDC provider are correctly propagated
Also fixes existing test suite by adding missing mocks:
- isEmailDomainAllowed function mock
- findOpenIDUser function mock
These tests validate the fix from commit 5874ba29f that enables
{{LIBRECHAT_OPENID_TOKEN}} template variable functionality.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* docs: Remove implementation documentation file
The PR description already contains all necessary implementation details.
This documentation file is redundant and was requested to be removed.
* fix: skip s256 check
* fix(openid): handle missing refresh token in Cognito token refresh response
When OPENID_REUSE_TOKENS=true, the token refresh flow was failing because
Cognito (and most OAuth providers) don't return a new refresh token in the
refresh grant response - they only return new access and ID tokens.
Changes:
- Modified setOpenIDAuthTokens() to accept optional existingRefreshToken parameter
- Updated validation to only require access_token (refresh_token now optional)
- Added logic to reuse existing refresh token when not provided in tokenset
- Updated refreshController to pass original refresh token as fallback
- Added comments explaining standard OAuth 2.0 refresh token behavior
This fixes the "Token is not present. User is not authenticated." error that
occurred during silent token refresh with Cognito as the OpenID provider.
Fixes: Authentication loop with OPENID_REUSE_TOKENS=true and AWS Cognito
* fix(openid): extract refresh token from cookies for template variable replacement
When OPENID_REUSE_TOKENS=true, the openIdJwtStrategy populates user.federatedTokens
to enable template variable replacement (e.g., {{LIBRECHAT_OPENID_ACCESS_TOKEN}}).
However, the refresh_token field was incorrectly sourced from payload.refresh_token,
which is always undefined because:
1. JWTs don't contain refresh tokens in their payload
2. The JWT itself IS the access token
3. Refresh tokens are separate opaque tokens stored in HTTP-only cookies
This caused extractOpenIDTokenInfo() to receive incomplete federatedTokens,
resulting in template variables remaining unreplaced in headers.
**Root Cause:**
- Line 90: `refresh_token: payload.refresh_token` (always undefined)
- JWTs only contain access token data in their claims
- Refresh tokens are separate, stored securely in cookies
**Solution:**
- Import `cookie` module to parse cookies from request
- Extract refresh token from `refreshToken` cookie
- Populate federatedTokens with both access token (JWT) and refresh token (from cookie)
**Impact:**
- Template variables like {{LIBRECHAT_OPENID_ACCESS_TOKEN}} now work correctly
- Headers in librechat.yaml are properly replaced with actual tokens
- MCP server authentication with federated tokens now functional
**Technical Details:**
- passReqToCallback=true in JWT strategy provides req object access
- Refresh token extracted via cookies.parse(req.headers.cookie).refreshToken
- Falls back gracefully if cookie header or refreshToken is missing
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: re-resolve headers on each request to pick up fresh federatedTokens
- OpenAIClient now re-resolves headers in chatCompletion() before each API call
- This ensures template variables like {{LIBRECHAT_OPENID_TOKEN}} are replaced
with actual token values from req.user.federatedTokens
- initialize.js now stores original template headers instead of pre-resolved ones
- Fixes template variable replacement when OPENID_REUSE_TOKENS=true
The issue was that headers were only resolved once during client initialization,
before openIdJwtStrategy had populated user.federatedTokens. Now headers are
re-resolved on every request with the current user's fresh tokens.
* debug: add logging to track header resolution in OpenAIClient
* debug: log tokenset structure after refresh to diagnose missing access_token
* fix: set federatedTokens on user object after OAuth refresh
- After successful OAuth token refresh, the user object was not being
updated with federatedTokens
- This caused template variable resolution to fail on subsequent requests
- Now sets user.federatedTokens with access_token, id_token, refresh_token
and expires_at from the refreshed tokenset
- Fixes template variables like {{LIBRECHAT_OPENID_TOKEN}} not being
replaced after token refresh
- Related to PR #9931 (OpenID federated token support)
* fix(openid): pass user object through agent chain for template variable resolution
Root cause: buildAgentContext in agents/run.ts called resolveHeaders without
the user parameter, preventing OpenID federated token template variables from
being resolved in agent runtime parameters.
Changes:
- packages/api/src/agents/run.ts: Add user parameter to createRun signature
- packages/api/src/agents/run.ts: Pass user to resolveHeaders in buildAgentContext
- api/server/controllers/agents/client.js: Pass user when calling createRun
- api/server/services/Endpoints/bedrock/options.js: Add resolveHeaders call with debug logging
- api/server/services/Endpoints/custom/initialize.js: Add debug logging
- packages/api/src/utils/env.ts: Add comprehensive debug logging and stack traces
- packages/api/src/utils/oidc.ts: Fix eslint errors (unused type, explicit any)
This ensures template variables like {{LIBRECHAT_OPENID_TOKEN}} and
{{LIBRECHAT_USER_OPENIDID}} are properly resolved in both custom endpoint
headers and Bedrock AgentCore runtime parameters.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: remove debug logging from OpenID token template feature
Removed excessive debug logging that was added during development to make
the PR more suitable for upstream review:
- Removed 7 debug statements from OpenAIClient.js
- Removed all console.log statements from packages/api/src/utils/env.ts
- Removed debug logging from bedrock/options.js
- Removed debug logging from custom/initialize.js
- Removed debug statement from AuthController.js
This reduces the changeset by ~50 lines while maintaining full functionality
of the OpenID federated token template variable feature.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* test(openid): add comprehensive unit tests for template variable substitution
- Add 34 unit tests for OIDC token utilities (oidc.spec.ts)
- Test coverage for token extraction, validation, and placeholder processing
- Integration tests for full OpenID token flow
- All tests pass with comprehensive edge case coverage
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
* test: fix OpenID federated tokens test failures
- Add serverMetadata() mock to openid-client mock configuration
* Fixes TypeError in openIdJwtStrategy.js where serverMetadata() was being called
* Mock now returns jwks_uri and end_session_endpoint as expected by the code
- Update outdated initialize.spec.js test
* Remove test expecting resolveHeaders call during initialization
* Header resolution was refactored to be deferred until LLM request time
* Update test to verify options are returned correctly with useLegacyContent flag
Fixes#9931 CI failures for backend unit tests
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* chore: fix package-lock.json conflict
* chore: sync package-log with upstream
* chore: cleanup
* fix: use createSafeUser
* fix: fix createSafeUser signature
* chore: remove comments
* chore: purge comments
* fix: update Jest testPathPattern to testPathPatterns for Jest 30+ compatibility
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Denis Ramic <denis.ramic@nfon.com>
Co-authored-by: kristjanaapro <kristjana@apro.is>
chore: import order and add back JSDoc for OpenID JWT callback
* fix: change google multimodal attachments to use type: 'media'
* chore: Update @librechat/agents to version 3.0.27 in package.json and package-lock.json
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* Added a new `isIP` function for validating IP addresses in both Node.js and browser environments, replacing the previous reliance on the Node.js `net` module.
* Updated domain extraction and validation logic to utilize the new `isIP` function, ensuring consistent IP validation across the application.
* Enhanced handling of IPv4 and IPv6 addresses, including proper formatting for URLs.
* 🔒 feat: Enhance SSRF Protection with Comprehensive IP and Domain Validation
* Added extensive tests for validating IP addresses and domains to prevent SSRF attacks, including checks for internal, private, and link-local addresses.
* Improved domain validation logic to handle various edge cases, ensuring only legitimate requests are processed.
* Implemented security measures against common cloud provider metadata access and internal service exploitation.
* Updated existing tests to reflect changes in validation logic and ensure robust security coverage.
* chore: cleanup comments
* 🔒 feat: Improve Domain Validation Logic for Enhanced Security
* Added logic to extract and normalize hostnames from client-provided domains, including handling of URLs and IP addresses.
* Implemented checks using Node.js's net module to validate IP addresses, ensuring robust domain validation.
* Updated existing validation conditions to enhance security against potential SSRF attacks.
* feat: Additional Protocol Checks and IPv6 Support
* Added tests to reject unsupported protocols (FTP, WebSocket, file) in client domains to strengthen SSRF protection.
* Improved domain extraction logic to preserve brackets for IPv6 addresses, ensuring correct URL formatting.
* Updated validation logic to handle various edge cases for client-provided domains, enhancing overall security.
* feat: Expand Domain Validation Tests for Enhanced SSRF Protection
* Added comprehensive tests for handling various URL formats, including IPv6 addresses, authentication credentials, and special characters in paths.
* Implemented additional validation scenarios for client domains, covering edge cases such as malformed URLs, empty strings, and unsupported protocols.
* Enhanced handling of internationalized domain names and localhost variations to ensure robust domain extraction and validation.
* chore: Add experimental backend server for multi-pod simulation
* Introduced a new backend script (`experimental.js`) to manage a clustered server environment with Redis cache flushing on startup.
* Updated `package.json` to include a new script command for the experimental backend.
* This setup aims to enhance scalability and performance for production environments.
* refactor: Remove server disconnection handling logic from useMCPServerManager
TooltipAnchor was automatically adding an `aria-describedby`
tag which often duplicated the labeling already present inside
of the anchor. E.g., the screen reader might say
"New Chat, New Chat, button" instead of just "New Chat, button."
I've removed the TooltipAnchor's automatic `aria-describedby` and
worked to make sure that anyone using TooltipAnchor properly defines
its labeling.
* feat: Add support for model in token configurations and tests
* chore: Update @librechat/agents to version 3.0.26 in package.json and package-lock.json
* 🔧 fix: Enhance error handling for agents system in uncaughtException logger
* Added specific logging for errors originating from the agents system to improve debugging and maintain application stability.
* 📦 chore: Update dependencies for `@librechat/agents` and related packages to v3.0.25 and improve version consistency across modules
* 🔧 fix: Handle errors when fetching server tools and log missing tools in MCP tools controller, to prevent all MCP tools from not getting listed
* 🔧 fix: Remove trailing colons from error messages in MCPConnection class
* chore: Update test command patterns in package.json for cache integration tests
* Refactored `openFileDialog` to use `useCallback` for better performance.
* Introduced `handleSelectFileClick` to manage file selection click events, enhancing user interaction.
* ✨ feat: Enhance agent avatar management with upload and reset functionality
* ✨ feat: Refactor AvatarMenu to use DropdownPopup for improved UI and functionality
* ✨ feat: Improve avatar upload handling in AgentPanel to suppress misleading "no changes" toast
* ✨ feat: Refactor toast message handling and payload composition in AgentPanel for improved clarity and functionality
* ✨ feat: Enhance agent avatar functionality with upload, reset, and validation improvements
* ✨ feat: Refactor agent avatar upload handling and enhance related components for improved functionality and user experience
* feat(agents): tighten ACL, harden GETs/search, and sanitize action metadata
stop persisting refreshed S3 URLs on GET; compute per-response only
enforce ACL EDIT on revert route; remove legacy admin/author/collab checks
sanitize action metadata before persisting during duplication (api_key, oauth_client_id, oauth_client_secret)
escape user search input, cap length (100), and use Set for public flag mapping
add explicit req.file guard in avatar upload; fix empty catch lint; remove unused imports
* feat: Remove outdated avatar-related translation keys
* feat: Improve error logging for avatar updates and streamline file input handling
* feat(agents): implement caching for S3 avatar refresh in agent list responses
* fix: replace unconventional 'void e' with explicit comment to clarify intentionally ignored error
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* feat(agents): enhance avatar handling and improve search functionality
* fix: clarify intentionally ignored error in agent list handler
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* chore: update @librechat/agents dependency to version 3.0.18
* refactor: add optional metadata field to message schema and types
* chore: update @librechat/agents to v3.0.19
* refactor: update return type of sendCompletion method to include metadata
* chore: linting
* chore: update @librechat/agents dependency to v3.0.20
* refactor: implement agent labeling for conversation history in multi-agent scenarios
* refactor: improve error handling for capturing agent ID map in AgentClient
* refactor: clear agentIdMap and related properties during client disposal to prevent memory leaks
* chore: update sendCompletion method for FakeClient to return an object with completion and metadata fields
* ✨ feat: Implement scanIterator method for Redis cluster client
This resolves the bug where `ServerConfigsCacheRedis#getAll` returns an empty object when a Redis Cluster (instead of a single node server is used)
* ✨ feat: Update cache integration tests for Redis cluster support
* chore: update js-yaml to v4.1.1
* chore: update eslint to v9.39.1 in package.json and package-lock.json
* chore: update prettier-eslint to v16.4.2 in package.json and package-lock.json
* chore: update @eslint/eslintrc to v3.3.1 in package.json and package-lock.json
* chore: update ts-jest to v29.4.5 in package.json and package-lock.json
* chore: update jest to version 30.2.0 across multiple packages and update related dependencies
* feat: Integrate logger for MessageIcon component
* feat: Enhance artifact sharing functionality with updated path checks and read-only state management
* feat: Refactor Thinking and Reasoning components for improved structure and styling
* feat: Enhance artifact sharing with context value management and responsive layout
* feat: Enhance ShareView with theme and language management features
* feat: Improve ThinkingButton accessibility and styling for better user interaction
* feat: Introduce isArtifactRoute utility for route validation in Artifact components
* feat: Add latest message text extraction in SharedView for improved message display
* feat: Update locale handling in SharedView for dynamic date formatting
* feat: Refactor ArtifactsContext and SharedView for improved context handling and styling adjustments
* feat: Enhance artifact panel size management with local storage integration
* chore: imports
* refactor: move ShareArtifactsContainer out of ShareView
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* feat: Add Bedrock Cache Control Functionality
- fix: Update Bedrock Cache Control to Require cachePoint as a Separate Content Block
- Modified the addBedrockCacheControl function to ensure cachePoint is added as a separate content block in the content array, rather than as a property of text objects.
- refactor: move addBedrockCacheControl over to packages/api
- ci: add tests for addBedrockCacheControl until full coverage reached
* ci: add test similar to example from the langchain PR
* refactor: move addBedrockCacheControl logic and tests to agents repository
* chore: remove extraneous comment
* chore: update @librechat/agents dependency to version 3.0.12
* chore: update @librechat/agents dependency to version 3.0.13
* chore: update @librechat/agents dependency to version 3.0.14
* chore: update @librechat/agents to v3.0.15
* chore: update default value for prompt cache setting to true
* refactor: set default promptCache to true for claude and nova models
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* feat: integrate Helicone AI gateway provider
- Add Helicone provider support with automatic model fetching
- Implement custom API logic for Helicone model registry endpoint
- Enable access to 75+ models from multiple AI providers through Helicone gateway
- Add Helicone to supported providers list in README
- Include Helicone configuration in example YAML
* docs: add Helicone to supported providers list
* fix comments
* fixed backgroundless helicone icon asset
* removed unecessesary changes
* replace svg helicone image instead of png
* feat: Add error handling for model refusal and update translations
* refactor: error handling in AgentClient to improve logging and cleanup process
* refactor: Update error message for response refusal to improve clarity
* ✨ feat: Enhance Artifact Management with Version Control and UI Improvements
✨ feat: Improve mobile layout and responsiveness in Artifacts component
✨ feat: Refactor imports and remove unnecessary props in Artifact components
✨ feat: Enhance Artifacts and SidePanel components with improved mobile responsiveness and layout transitions
feat: Enhance artifact panel animations and improve UI responsiveness
- Updated Thinking component button styles for smoother transitions.
- Implemented dynamic rendering for artifacts panel with animation effects.
- Refactored localization keys for consistency across multiple languages.
- Added new CSS animations for iOS-inspired smooth transitions.
- Improved Tailwind CSS configuration to support enhanced animation effects.
✨ feat: Add fullWidth and icon support to Radio component for enhanced flexibility
refactor: Remove unused PreviewProps import in ArtifactPreview component
refactor: Improve button class handling and blur effect constants in Artifact components
✨ feat: Refactor Artifacts component structure and add mobile/desktop variants for improved UI
chore: Bump @librechat/client version to 0.3.2
refactor: Update button styles and transition durations for improved UI responsiveness
refactor: revert back localization key
refactor: remove unused scaling and animation properties for cleaner CSS
refactor: remove unused animation properties for cleaner configuration
* ✨ refactor: Simplify className usage in ArtifactTabs, ArtifactsHeader, and SidePanelGroup components
* refactor: Remove cycleArtifact function from useArtifacts hook
* ✨ feat: Implement Chromium resize lag fix with performance optimizations and new ArtifactsPanel component
* ✨ feat: Update Badge component for responsive design and improve tap scaling behavior
* chore: Update react-resizable-panels dependency to version 3.0.6
* ✨ feat: Refactor Artifacts components for improved structure and performance; remove unused files and optimize styles
* ✨ style: Update text color for improved visibility in Artifacts component
* ✨ style: Remove text color class for improved Spinner styling in Artifacts component
* refactor: Split EditorContext into MutationContext and CodeContext to optimize re-renders; update related components to use new hooks
* refactor: Optimize debounced mutation handling in CodeEditor component using refs to maintain current values and reduce re-renders
* fix: Correct endpoint for message artifacts by changing URL segment from 'artifacts' to 'artifact'
* feat: Enhance useEditArtifact mutation with optimistic updates and rollback on error; improve type safety with context management
* fix: proper switch to preview as soon as artifact becomes enclosed
* refactor: Remove optimistic updates from useEditArtifact mutation to prevent errors; simplify onMutate logic
* test: Add comprehensive unit tests for useArtifacts hook to validate artifact handling, tab switching, and state management
* test: Enhance unit tests for useArtifacts hook to cover new conversation transitions and null message handling
---------
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
* 🔒 feat: Implement idempotency check for OAuth flow completion
- Added a check to prevent duplicate token exchanges if the OAuth flow has already been completed.
- Updated the OAuth callback route to redirect appropriately when a completed flow is detected.
- Refactored token storage logic to use original flow state credentials instead of updated ones.
- Enhanced tests to cover the new idempotency behavior and ensure correct handling of OAuth flow states.
* chore: add back scope for logging
* refactor: Add isFlowStale method to FlowStateManager for stale flow detection
- Implemented a new method to check if a flow is stale based on its age and status.
- Updated MCPConnectionFactory to utilize the isFlowStale method for cleaning up stale OAuth flows.
- Enhanced logging to provide more informative messages regarding flow status and age during cleanup.
* test: Add unit tests for isFlowStale method in FlowStateManager
- Implemented comprehensive tests for the isFlowStale method to verify its behavior across various flow statuses (PENDING, COMPLETED, FAILED) and age thresholds.
- Ensured correct handling of edge cases, including flows with missing timestamps and custom stale thresholds.
- Enhanced test coverage to validate the logic for determining flow staleness based on createdAt, completedAt, and failedAt timestamps.
* feat: add support for known/add/drop parameters in Anthropic and Google LLM configurations
* ci: add tests for web search support for Anthropic and Google configurations with addParams and dropParams handling
- Implemented validation for OpenAPI specifications to ensure the server URL matches the client-provided domain, preventing SSRF attacks.
- Added domain extraction and validation functions to improve security checks.
- Updated relevant services and routes to utilize the new validation logic, ensuring robust handling of client-provided domains against the OpenAPI spec.
- Introduced comprehensive tests to validate the new security features and ensure correct behavior across various scenarios.
- Added DEBUG_MESSAGE_LENGTH constant to allow dynamic adjustment of debug message length based on environment variable.
- Updated logging format to utilize the new constant for truncating debug messages, enhancing flexibility in log output.
* refactor: add image file size validation as part of payload build
* feat: implement file size and MIME type filtering in endpoint configuration
* chore: import order
* feat: add filterFilesByEndpointConfig to filter disabled file processing by provider
* chore: explicit define of endpointFileConfig for better debugging
* refactor: move `normalizeEndpointName` to data-provider as used app-wide
* chore: remove overrideEndpoint from useFileHandling
* refactor: improve endpoint file config selection
* refactor: update filterFilesByEndpointConfig to accept structured parameters and improve endpoint file config handling
* refactor: replace defaultFileConfig with getEndpointFileConfig for improved file configuration handling across components
* test: add comprehensive unit tests for getEndpointFileConfig to validate endpoint configuration handling
* refactor: streamline agent endpoint assignment and improve file filtering logic
* feat: add error handling for disabled file uploads in endpoint configuration
* refactor: update encodeAndFormat functions to accept structured parameters for provider and endpoint
* refactor: streamline requestFiles handling in initializeAgent function
* fix: getEndpointFileConfig partial config merging scenarios
* refactor: enhance mergeWithDefault function to support document-supported providers with comprehensive MIME types
* refactor: user-configured default file config in getEndpointFileConfig
* fix: prevent file handling when endpoint is disabled and file is dragged to chat
* refactor: move `getEndpointField` to `data-provider` and update usage across components and hooks
* fix: prioritize endpointType based on agent.endpoint in file filtering logic
* fix: prioritize agent.endpoint in file filtering logic and remove unnecessary endpointType defaulting
* chore: temp. remove @librechat/agents
* 🔧 chore: update @langchain/core to version 0.3.79
* chore: update dependencies for @langchain/core and add back latest @librechat/agents
* chore: update @librechat/agents to version 3.0.11
* fix: enhance error handling for uncaught exceptions due to abort errors
* fix: standardize warning message for uncatchable abort errors
* fix: improve tool call handling in ModelEndHandler for unprocessed edge case
* fix: prevent content type mismatch in message updates and preserve args in final updates
* chore: add debug logging for client disposal in disposeClient function
* fix: update agent context handling in ModelEndHandler due to new MultiAgentGraph
* refactor: streamline client cleanup process by utilizing property arrays for potential circular reference removal
* chore: correct type for ServerRequest
* chore: improve ServerRequest typing across several modules
* feat: Add PDF configured limit validation
- Introduced comprehensive tests for PDF validation across multiple providers, ensuring correct behavior for file size limits and edge cases.
- Enhanced the `validatePdf` function to accept an optional configured file size limit, allowing for stricter validation based on user configurations.
- Updated related functions to utilize the new validation logic, ensuring consistent behavior across different providers.
* chore: Update Request type to ServerRequest in audio and video encoding modules
* refactor: move `getConfiguredFileSizeLimit` utility
* feat: Add video and audio validation with configurable size limits
- Introduced `validateVideo` and `validateAudio` functions to validate media files against provider-specific size limits.
- Enhanced validation logic to consider optional configured file size limits, allowing for more flexible file handling.
- Added comprehensive tests for video and audio validation across different providers, ensuring correct behavior for various scenarios.
* refactor: Update PDF and media validation to allow higher configured limits
- Modified validation logic to accept user-configured file size limits that exceed provider defaults, ensuring correct acceptance of files within the specified range.
- Updated tests to reflect changes in validation behavior, confirming that files are accepted when within the configured limits.
- Enhanced documentation in tests to clarify expected outcomes with the new validation rules.
* chore: Add @types/node-fetch dependency to package.json and package-lock.json
- Included the @types/node-fetch package to enhance type definitions for node-fetch usage.
- Updated package-lock.json to reflect the addition of the new dependency.
* fix: Rename FileConfigInput to TFileConfig
* ✨ feat: Enhance DELETE /all endpoint to remove shared links alongside conversations and tool calls
- Added functionality to delete all shared links for a user when clearing conversations.
- Introduced comprehensive tests to ensure correct behavior and error handling for the new deletion process.
* ✨ feat: Implement deleteConvoSharedLink method and update conversation deletion logic to remove associated shared links
* chore: remove `@langchain/community` dependency
* refactor: remove SerpAPI integration and update related imports
* chore: remove legacy code with unnecessary dependencies
* chore: cleanup packages
* chore: cleanup packages
* chore: update openai dependency version to 5.10.1
* chore: add back @librechat/agents dependency
* chore: downgrade openai dependency from 5.10.1 to 5.8.2
* Remove dependency on @librechat/agents from the API package
* chore: add @librechat/agents dependency to the API package
* fix: add useLegacyContent property to RunAgent type and propagate it in createRun function
* chore: remove openai dependency version 5.10.1 from package.json
* feat: Add support for agent handoffs with edges in agent forms and schemas
chore: Mark `agent_ids` field as deprecated in favor of edges across various schemas and types
chore: Update dependencies for @langchain/core and @librechat/agents to latest versions
chore: Update peer dependency for @librechat/agents to version 3.0.0-rc2 in package.json
chore: Update @librechat/agents dependency to version 3.0.0-rc3 in package.json and package-lock.json
feat: first pass, multi-agent handoffs
fix: update output type to ToolMessage in memory handling functions
fix: improve type checking for graphConfig in createRun function
refactor: remove unused content filtering logic in AgentClient
chore: update @librechat/agents dependency to version 3.0.0-rc4 in package.json and package-lock.json
fix: update @langchain/core peer dependency version to ^0.3.72 in package.json and package-lock.json
fix: update @librechat/agents dependency to version 3.0.0-rc6 in package.json and package-lock.json; refactor stream rate handling in various endpoints
feat: Agent handoff UI
chore: update @librechat/agents dependency to version 3.0.0-rc8 in package.json and package-lock.json
fix: improve hasInfo condition and adjust UI element classes in AgentHandoff component
refactor: remove current fixed agent display from AgentHandoffs component due to redundancy
feat: enhance AgentHandoffs UI with localized beta label and improved layout
chore: update @librechat/agents dependency to version 3.0.0-rc10 in package.json and package-lock.json
feat: add `createSequentialChainEdges` function to add back agent chaining via multi-agents
feat: update `createSequentialChainEdges` call to only provide conversation context between agents
feat: deprecate Agent Chain functionality and update related methods for improved clarity
* chore: update @librechat/agents dependency to version 3.0.0-rc11 in package.json and package-lock.json
* refactor: remove unused addCacheControl function and related imports and import from @librechat/agents
* chore: remove unused i18n keys
* refactor: remove unused format export from index.ts
* chore: update @librechat/agents to v3.0.0-rc13
* chore: remove BEDROCK_LEGACY provider from Providers enum
* chore: update @librechat/agents to version 3.0.2 in package.json
* Fixed upload to provider for custom endpoints + unit tests
* fix: add support back for agents to be able to use Upload to Provider with supported providers
* ci: add test for agents endpoint still recognizing document supported providers
* chore: address ESLint suggestions
* Improved unit tests
* Linting error on unit tests fixed
---------
Co-authored-by: Dustin Healy <dustinhealy1@gmail.com>
* refactor: Restructure MCP registry system with caching
- Split MCPServersRegistry into modular components:
- MCPServerInspector: handles server inspection and health checks
- MCPServersInitializer: manages server initialization logic
- MCPServersRegistry: simplified registry coordination
- Add distributed caching layer:
- ServerConfigsCacheRedis: Redis-backed configuration cache
- ServerConfigsCacheInMemory: in-memory fallback cache
- RegistryStatusCache: distributed leader election state
- Add promise utilities (withTimeout) replacing Promise.race patterns
- Add comprehensive cache integration tests for all cache implementations
- Remove unused MCPManager.getAllToolFunctions method
* fix: Update OAuth flow to include user-specific headers
* chore: Update Jest configuration to ignore additional test files
- Added patterns to ignore files ending with .helper.ts and .helper.d.ts in testPathIgnorePatterns for cleaner test runs.
* fix: oauth headers in callback
* chore: Update Jest testPathIgnorePatterns to exclude helper files
- Modified testPathIgnorePatterns in package.json to ignore files ending with .helper.ts and .helper.d.ts for cleaner test execution.
* ci: update test mocks
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor: Reasoning components with independent toggle buttons
- Refactored ThinkingButton to remove unnecessary state and props.
- Updated ContentParts to simplify content rendering and remove hover handling.
- Improved Reasoning component to include independent toggle functionality for each THINK part.
- Adjusted styles for better layout consistency and user experience.
* refactor: isolate hover effects for Reasoning
- Updated ThinkingButton to improve hover effects and layout consistency.
- Refactored Reasoning component to include a new wrapper class for better styling.
- Adjusted icon visibility and transitions for a smoother user experience.
* fix: Prevent rendering of empty messages in Chat component
- Added a check to skip rendering if the message text is only whitespace, improving the user interface by avoiding empty containers.
* chore: Replace div with fragment in Thinking component for cleaner markup
* chore: move Thinking component to Content Parts directory
* refactor: prevent rendering of whitespace-only text in Part component only for edge cases
* ✨ feat: Refactor error handling and improve loading states in MessageContent component
* ✨ feat: Enhance Thinking and ContentParts components with improved hover functionality and clipboard support
* fix: Adjust padding in Thinking and ContentParts components for consistent layout
* ✨ feat: Add response label and improve message editing UI with contextual indicators
* ✨ feat: Add isEditing prop to Feedback and Fork components for improved editing state handling
* refactor: Remove isEditing prop from Feedback and Fork components for cleaner state management
* refactor: Migrate state management from Recoil to Jotai for font size and show thinking features
* refactor: Separate ToggleSwitch into RecoilToggle and JotaiToggle components for improved clarity and state management
* refactor: Remove unnecessary comments in ToggleSwitch and MessageContent components for cleaner code
* chore: reorder import statements in Thinking.tsx
* chore: reorder import statement in EditTextPart.tsx
* chore: reorder import statement
* chore: Reorganize imports in ToggleSwitch.tsx
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🦙 fix: Ollama Custom Headers
* chore: Correct import order for resolveHeaders in OllamaClient.js
* fix: Improve error logging for Ollama API model fetch failure
* ci: update Ollama model fetch tests
* ci: Add unit test for passing headers and user object to Ollama fetchModels
* Refactored the logic for determining max output tokens in the agent initialization process.
* Changed variable names for clarity, updating from `maxTokens` to `maxOutputTokens` to better reflect their purpose.
* Adjusted calculations for `maxContextTokens` to use the new `maxOutputTokens` variable.
* 📫 refactor: Enhance OpenID email Fallback
* Updated email retrieval logic to use preferred_username or upn if email is not available.
* Adjusted logging and user data assignment to reflect the new email handling approach.
* Ensured email domain validation checks the correct email source.
* 🔄 refactor: Update Email Domain Validation Logic
* Modified `isEmailDomainAllowed` function to return true for falsy emails and missing domain restrictions.
* Added new test cases to cover scenarios with and without domain restrictions.
* Ensured proper validation when domain restrictions are present.
* fix: Sanitize LLM titles by stripping <think> tags and fix modal overflow
* chore: linting
* chore: Simplify title sanitization by removing unnecessary variable assignment and import order
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 📦 feat: `@librechat/agents` v2.4.87 for LangFuse Support
* 📦 chore: update @librechat/agents to v2.4.88 in package.json and package-lock.json
* 📦 chore: update @librechat/agents to v2.4.89
* feat: Add runName configuration to AgentClient and Memory agent for improved tracing
* chore: correct startupConfig usage in ImportConversations component
* refactor: properly process configured speechToText and textToSpeech settings in getCustomConfigSpeech
* refactor: proxy configuration by utilizing HttpsProxyAgent for OpenAI Image Edits
* Possibility to add extra env values to the deployment
* Fix: Custom environment variables should be placed after the predefined environment variables
* chore: add i18n localization comment for AlwaysMakeProd component
* feat: enhance accessibility by adding aria-label and aria-labelledby to Switch component
* feat: add aria-labels for accessibility in Agent and Assistant avatar buttons
* fix: add switch aria-labels for accessibility in various components
* feat: add aria-labels and localization keys for accessibility in DataTable, DataTableColumnHeader, and OGDialogTemplate components
* chore: refactor out nested ternary
* feat: add aria-label to DataTable filter button for My Files modal
* feat: add aria-labels for Buttons and localization strings
* feat: add aria-labels to Checkboxes in Agent Builder
* feat: enhance accessibility by adding aria-label and aria-labelledby to Checkbox component
* feat: add aria-label to FileSearchCheckbox in Agent Builder
* feat: add aria-label to Prompts text input area
* feat: enhance accessibility by adding aria-label and aria-labelledby to TextAreaAutosize component
* feat: remove improper role: "list" prop from List in Conversations.tsx to enhance accessibility and stop aria rules conflicting within react-virtualized component
* feat: enhance accessibility by allowing tab navigation and adding ring highlights for conversation title editing accept/reject buttons
* feat: add aria-label to Copy Link button in the conversation share modal
* feat: add title to QR code svg in conversation share modal to describe the image content
* feat: enhance accessibility by making Agent Avatar upload keyboard navigable and round out highlight border on focus
* feat: enhance accessibility by adding aria attributes around alerting users with screen readers to invalid email address inputs in the Agent Builder
* feat: add aria-labels to buttons in Advanced panel of Agent Builder
* feat: enhance accessibility by making FileUpload and Clear All buttons in PresetItems keyboard navigable
* feat: enchance accessiblity by indexing view and delete button aria-labels in shared links management modal to their specific chat titles
* feat: add border highlighting on focus for AnimatedSearchInput
* feat: add category description to aria-labels for prompts in ListCard
* feat: add proper scoping to rows and columns in table headers
* feat: add localized aria-labelling to EditTextPart's TextAreaAutosize component and base dynamic paramters panel components and their supporting translation keys
* feat: add localized aria-labels and aria-labelledBy to Checkbox components without them
* feat: add localized aria-labeledBy for endpoint settings Sliders
* feat: add localized aria-labels for TextareaAutosize components
* chore: remove unused i18n string
* feat: add localized aria-label for BookmarkForm Checkbox
* fix: add stopPropagation onKeyDown for Preview and Edit menu items in prompts that was causing the prompts to inadvertently be sent when triggered with keyboard navigation when Auto-send Prompts was toggled on
* fix: switch TableCell to TableHead for title cells according to harvard issue #789
* fix: add more descriptive localization key for file filter button in DataTable
* chore: remove self-explanatory code comment from RenameForm
* fix: remove stray bg-yellow highlight that was left in during debugging
* fix: add aria-label to model configurator panel back button
* fix: undo incorrect hoist of tool name split for aria-label and span in MCPInput
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor: remove `useChatContext` from `useSelectMention`, explicitly pass `conversation` object
* feat: ephemeral agents via model specs
* refactor: Sync Jotai state with ephemeral agent state, also when Ephemeral Agent has no MCP servers selected
* refactor: move `useUpdateEphemeralAgent` to store and clean up imports
* refactor: reorder imports and invalidate queries for mcpConnectionStatus in event handler
* refactor: replace useApplyModelSpecEffects with useApplyModelSpecAgents and update event handlers to use new agent template logic
* ci: update useMCPSelect test to verify mcpValues sync with empty ephemeralAgent.mcp
* filter out unavailable servers
* bump render time
* Fix import path for useGetStartupConfig
* refactor: Change configuredServers to use Set for improved filtering of available MCPs
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor: Default Model Spec Retrieval Logic, allowing last selected spec on new chat if last selection was a spec
* chore: Replace hardcoded 'new' conversation ID with Constants.NEW_CONVO for consistency
* chore: remove redundant condition for model spec preset selection in useNewConvo hook
* updated gpt5-pro
it is here and on openrouter
https://platform.openai.com/docs/models/gpt-5-pro
* feat: Add gpt-5-pro pricing
- Implemented handling for the new gpt-5-pro model in the getValueKey function.
- Updated tests to ensure correct behavior for gpt-5-pro across various scenarios.
- Adjusted token limits and multipliers for gpt-5-pro in the tokens utility files.
- Enhanced model matching functionality to include gpt-5-pro variations.
* refactor: optimize model pricing and validation logic
- Added new model pricing entries for llama2, llama3, and qwen variants in tx.js.
- Updated tokenValues to include additional models and their pricing structures.
- Implemented validation tests in tx.spec.js to ensure all models resolve correctly to pricing.
- Refactored getValueKey function to improve model matching and resolution efficiency.
- Removed outdated model entries from tokens.ts to streamline pricing management.
* fix: add missing pricing
* chore: update model pricing for qwen and gemma variants
* chore: update model pricing and add validation for context windows
- Removed outdated model entries from tx.js and updated tokenValues with new models.
- Added a test in tx.spec.js to ensure all models with pricing have corresponding context windows defined in tokens.ts.
- Introduced 'command-text' model pricing in tokens.ts to maintain consistency across model definitions.
* chore: update model names and pricing for AI21 and Amazon models
- Refactored model names in tx.js for AI21 and Amazon models to remove versioning and improve consistency.
- Updated pricing values in tokens.ts to reflect the new model names.
- Added comprehensive tests in tx.spec.js to validate pricing for both short and full model names across AI21 and Amazon models.
* feat: add pricing and validation for Claude Haiku 4.5 model
* chore: increase default max context tokens to 18000 for agents
* feat: add Qwen3 model pricing and validation tests
* chore: reorganize and update Qwen model pricing in tx.js and tokens.ts
---------
Co-authored-by: khfung <68192841+khfung@users.noreply.github.com>
* fix: reapply chat font size on load
* refactor: streamline font size handling in localStorage
* fix: update matchMedia mock to accurately reflect desktop and touchscreen capabilities
* refactor: implement Jotai for font size management and initialize on app load
- Replaced Recoil with Jotai for font size state management across components.
- Added a new `fontSize` atom to handle font size changes and persist them in localStorage.
- Implemented `initializeFontSize` function to apply saved font size on app load.
- Updated relevant components to utilize the new font size atom.
---------
Co-authored-by: ddooochii <ddooochii@gmail.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
* fix: Remove ephemeral cache control from document encoding function
* refactor: Improve document encoding types and add file context for anthropic messages api
- Added AnthropicDocumentBlock interface to define the structure for documents from the Anthropic provider.
- Updated encodeAndFormatDocuments function to utilize the new type and include optional context for filenames.
- Refactored DocumentResult to use a union type for various document formats, improving type safety and clarity.
* 🔧 feat: Enhance Redis Configuration and Connection Handling in Cache Flush Utility
- Added support for Redis username, password, and CA certificate.
- Improved Redis client creation to handle both cluster and single instance configurations.
- Implemented a helper function to read the Redis CA certificate with error handling.
- Updated connection logic to include timeout and error handling for Redis connections.
* refactor: flush cache if redis URI is defined
Remove deprecated OpenAI models and add latest GPT-5, o3/o4, and GPT-4.1 series models based on current API offerings as of October 2025.
Removed deprecated models:
- gpt-4.5-preview (deprecated July 2025)
- o1-preview, o1-mini (deprecated July/October 2025)
- gpt-4-vision-preview (shut down December 2024)
- Dated GPT-3.5 and GPT-4 variants (consolidated into base versions)
Added new flagship models:
- GPT-5 series: gpt-5, gpt-5-mini, gpt-5-nano
- o3/o4 reasoning models: o3, o4-mini, o3-pro, o3-mini
- GPT-4.1 series: gpt-4.1, gpt-4.1-mini, gpt-4.1-nano
Reorganized list with newest models first for better discoverability.
References:
- https://platform.openai.com/docs/models
- https://platform.openai.com/docs/deprecations
Enables word wrapping for text, markdown, and plaintext code blocks
to prevent horizontal scrolling on long lines. Improves readability
for prose content in fenced code blocks.
* Add Markdown rendering support for artifacts
* Add tests
* Remove custom code for mermaid
* Remove unnecessary dark mode hook
* refactor: optimize mermaid dependencies
- Added support for additional MIME types in artifact templates.
- Updated mermaidDependencies to include new packages: class-variance-authority, clsx, tailwind-merge, and @radix-ui/react-slot.
- Refactored zoom and refresh icons in MermaidDiagram component for improved clarity and maintainability.
* fix: add Markdown support for artifacts rendering
* feat: support 'text/md' as an additional MIME type for Markdown artifacts
* refactor: simplify markdownDependencies structure in artifacts utility
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* feat: Add group field to modelSpecs for flexible grouping
* resolve lint issues
* fix test
* docs: enhance modelSpecs group field documentation for clarity
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* Update prompt value for gemini-2.5-flash-lite
New Input price (text, image, video) --> $0.10
https://ai.google.dev/gemini-api/docs/pricing
* Fix formatting of gemini-2.5-flash-lite values
changed 0.10 to 0.1 to follow standards
* feat: Enhance shared link functionality with target message support
* refactor: Remove comment on compound index in share schema
* chore: Reorganize imports in ShareButton component for clarity
* refactor: Integrate Recoil for latest message tracking in ShareButton component
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
- problem: `addImageUrls` had a side effect that was being leveraged before to populate both the `ocr` message field, now `fileContext`, and `client.options.attachments`, which would record the user's uploaded message attachments to the user message when saved to the database and returned at the end of the request lifecycle
- solution: created dedicated handling for file context, and made sure to populate `allFiles` with non-provider attachments
* chore: enhance logging for latest message actions in message components
* fix: Extract previous convoId from latest text in message helpers and process hooks
- Updated `useMessageHelpers` and `useMessageProcess` to extract `convoId` from the previous text key for improved message handling.
- Refactored `getLengthAndLastTenChars` to `getLengthAndLastNChars` for better flexibility in character length retrieval.
- Introduced `getLatestContentForKey` function to streamline content extraction from messages.
* chore: Enhance logging for clearing latest messages in conversation hooks
* refactor: Update message key formatting for improved URL parameter handling
- Modified `getLatestContentForKey` to change the format from `${text}-${i}` to `${text}&i=${i}` for better URL parameter structure.
- Adjusted `getTextKey` to increase character length retrieval from 12 to 16 in `getLengthAndLastNChars` for enhanced text processing.
* refactor: Simplify convoId extraction and enhance message formatting
- Updated `useMessageHelpers` and `useMessageProcess` to extract `convoId` using a new format for improved clarity.
- Refactored `getLatestContentForKey` to streamline content formatting and ensure consistent use of `Constants.COMMON_DIVIDER` for better message structure.
- Removed redundant length and last character extraction logic from `getLengthAndLastNChars` for cleaner code.
* chore: linting
* chore: Simplify pre-commit hook by removing unnecessary lines
* feat: Add support for users to be admins when logging in using OpenID
* fix: Linting issues
* fix: whitespace
* chore: add unit tests for OIDC_ADMIN_ROLE
* refactor: Replace custom property retrieval function with lodash's get for improved readability and maintainability
* feat: Enhance OpenID role extraction and error handling in setupOpenId function
- Improved role validation to check for both array and string types.
- Added detailed error messages for missing or invalid role paths in tokens.
- Expanded unit tests to cover various scenarios for nested role extraction and error handling.
* fix: Improve error handling for role extraction in OpenID strategy
- Enhanced validation to check for invalid role types (array or string).
- Updated error messages for clarity when roles are missing or of incorrect type.
- Added unit tests to cover scenarios where roles return invalid types (object, number).
* feat: Implement user role demotion in OpenID strategy when admin role is absent from token
- Added logic to demote users from 'ADMIN' to 'USER' if the admin role is not present in the token.
- Enhanced logging to capture role changes for better traceability.
- Introduced unit tests to verify the demotion behavior and ensure correct handling when admin role environment variables are not configured.
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* Check file size of conversation being imported against a configured max size to prevent bringing down the application by uploading a large file
chore: remove non-english localization as needs to be added via locize
* feat: Implement file size validation for conversation imports to prevent oversized uploads
---------
Co-authored-by: Marc Amick <MarcAmick@jhu.edu>
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🔧 refactor: Improve accessibility and styling in ChatGroupItem and FilterPrompts components
* 🔧 fix: Add button type and keyboard accessibility to dropdown menu trigger in ChatGroupItem
* 🔧 fix(757): Enhance accessibility by updating aria-labels and adding localization for prompt groups
* 🔧 fix(618): Update version to 0.3.1 and enhance accessibility in InfoHoverCard component
* 🔧 fix(618): Update aria-label in InfoHoverCard to use dynamic text prop for improved accessibility
* 🔧 fix: Enhance accessibility by updating aria-labels and roles in Conversations components
* 🔧 fix(620): Enhance accessibility by adding tabIndex to Tabs.Content components in ArtifactTabs, Settings, and Speech components
* refactor: remove RevokeKeysButton component and update related components for accessibility
- Deleted RevokeKeysButton component.
- Updated SharedLinks and General components to use Label for accessibility.
- Enhanced Personalization component with aria-labelledby and aria-describedby attributes.
- Refactored ConversationModeSwitch to use ToggleSwitch for better state management.
- Improved AutoSendTextSelector with local state management and accessibility attributes.
- Replaced Switch components with ToggleSwitch in various Speech and TTS components for consistency.
- Added aria-labelledby attributes to Dropdown components for better accessibility.
- Updated translation.json to include new localization keys and improved existing ones.
- Enhanced Slider component to support aria attributes for better accessibility.
* 🔧 fix: Enhance user feedback for API key operations with success and error messages
* 🔧 fix: Update aria-labels in Avatar component for improved localization and accessibility
* 🔧 fix: Refactor handleFile and handleDrop functions for improved readability and maintainability
* 📎 feat: Direct Provider Attachment Support for Multimodal Content
* 📑 feat: Anthropic Direct Provider Upload (#9072)
* feat: implement Anthropic native PDF support with document preservation
- Add comprehensive debug logging throughout PDF processing pipeline
- Refactor attachment processing to separate image and document handling
- Create distinct addImageURLs(), addDocuments(), and processAttachments() methods
- Fix critical bugs in stream handling and parameter passing
- Add streamToBuffer utility for proper stream-to-buffer conversion
- Remove api/agents submodule from repository
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* chore: remove out of scope formatting changes
* fix: stop duplication of file in chat on end of response stream
* chore: bring back file search and ocr options
* chore: localize upload to provider string in file menu
* refactor: change createMenuItems args to fit new pattern introduced by anthropic-native-pdf-support
* feat: add cache point for pdfs processed by anthropic endpoint since they are unlikely to change and should benefit from caching
* feat: combine Upload Image into Upload to Provider since they both perform direct upload and change provider upload icon to reflect multimodal upload
* feat: add citations support according to docs
* refactor: remove redundant 'document' check since documents are handled properly by formatMessage in the agents repo now
* refactor: change upload logic so anthropic endpoint isn't exempted from normal upload path using Agents for consistency with the rest of the upload logic
* fix: include width and height in return from uploadLocalFile so images are correctly identified when going through an AgentUpload in addImageURLs
* chore: remove client specific handling since the direct provider stuff is handled by the agent client
* feat: handle documents in AgentClient so no need for change to agents repo
* chore: removed unused changes
* chore: remove auto generated comments from OG commit
* feat: add logic for agents to use direct to provider uploads if supported (currently just anthropic)
* fix: reintroduce role check to fix render error because of undefined value for Content Part
* fix: actually fix render bug by using proper isCreatedByUser check and making sure our mutation of formattedMessage.content is consistent
---------
Co-authored-by: Andres Restrepo <andres@thelinuxkid.com>
Co-authored-by: Claude <noreply@anthropic.com>
📁 feat: Send Attachments Directly to Provider (OpenAI) (#9098)
* refactor: change references from direct upload to direct attach to better reflect functionality
since we are just using base64 encoding strategy now rather than Files/File API for sending our attachments directly to the provider, the upload nomenclature no longer makes sense. direct_attach better describes the different methods of sending attachments to providers anyways even if we later introduce direct upload support
* feat: add upload to provider option for openai (and agent) ui
* chore: move anthropic pdf validator over to packages/api
* feat: simple pdf validation according to openai docs
* feat: add provider agnostic validatePdf logic to start handling multiple endpoints
* feat: add handling for openai specific documentPart formatting
* refactor: move require statement to proper place at top of file
* chore: add in openAI endpoint for the rest of the document handling logic
* feat: add direct attach support for azureOpenAI endpoint and agents
* feat: add pdf validation for azureOpenAI endpoint
* refactor: unify all the endpoint checks with isDocumentSupportedEndpoint
* refactor: consolidate Upload to Provider vs Upload image logic for clarity
* refactor: remove anthropic from anthropic_multimodal fileType since we support multiple providers now
🗂️ feat: Send Attachments Directly to Provider (Google) (#9100)
* feat: add validation for google PDFs and add google endpoint as a document supporting endpoint
* feat: add proper pdf formatting for google endpoints (requires PR #14 in agents)
* feat: add multimodal support for google endpoint attachments
* feat: add audio file svg
* fix: refactor attachments logic so multi-attachment messages work properly
* feat: add video file svg
* fix: allows for followup questions of uploaded multimodal attachments
* fix: remove incorrect final message filtering that was breaking Attachment component rendering
fix: manualy rename 'documents' to 'Documents' in git since it wasn't picked up due to case insensitivity in dir name
fix: add logic so filepicker for a google agent has proper filetype filtering
🛫 refactor: Move Encoding Logic to packages/api (#9182)
* refactor: move audio encode over to TS
* refactor: audio encoding now functional in LC again
* refactor: move video encode over to TS
* refactor: move document encode over to TS
* refactor: video encoding now functional in LC again
* refactor: document encoding now functional in LC again
* fix: extend file type options in AttachFileMenu to include 'google_multimodal' and update dependency array to include agent?.provider
* feat: only accept pdfs if responses api is enabled for openai convos
chore: address ESLint comments
chore: add missing audio mimetype
* fix: type safety for message content parts and improve null handling
* chore: reorder AttachFileMenuProps for consistency and clarity
* chore: import order in AttachFileMenu
* fix: improve null handling for text parts in parseTextParts function
* fix: remove no longer used unsupported capability error message for file uploads
* fix: OpenAI Direct File Attachment Format
* fix: update encodeAndFormatDocuments to support OpenAI responses API and enhance document result types
* refactor: broaden providers supported for documents
* feat: enhance DragDrop context and modal to support document uploads based on provider capabilities
* fix: reorder import statements for consistency in video encoding module
---------
Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>
* 🔧 chore: Update @librechat/agents to v2.4.84 in package.json and package-lock.json
* feat: Serper as new scraperProvider for Web Search and add firecrawlVersion support
* fix: TWebSearchKeys and ensure unique API keys extraction
* chore: Add build:packages script to streamline package builds
- Added a new function `deleteDocumentsWithoutUserField` to remove documents lacking the user field from the specified MeiliSearch index.
- Integrated this function into the `ensureFilterableAttributes` method to clean up orphaned documents when existing messages or conversations are found without a user field.
🔧 feat: Enhance Index Synchronization Logic
- Updated `ensureFilterableAttributes` to return an object indicating whether settings were updated and if orphaned documents were found.
- Integrated orphaned document cleanup directly into the index synchronization process without forcing a full re-sync unless settings were updated.
- Improved logging for clarity on index configuration updates and orphaned document handling.
🔧 feat: Improve Flow State Management in Index Synchronization
- Refactored flow state management logic to ensure cleanup occurs after synchronization, regardless of success or error.
- Enhanced logging for flow state cleanup to provide better visibility into the synchronization process.
- Streamlined the structure of the index synchronization function for improved readability.
* fix: update @librechat/agents to v2.4.83 to handle reasoning edge case encountered with GLM models
* feat: GLM Context Window & Pricing Support
* feat: Add support for glm4 model in token values and tests
* chore: linting for `loadCustomConfig`
* refactor: decouple CDN init and variable/health checks from AppService
* refactor: move AppService to packages/data-schemas
* chore: update AppConfig import path to use data-schemas
* chore: update JsonSchemaType import path to use data-schemas
* refactor: update UserController to import webSearchKeys and redefine FunctionTool typedef
* chore: remove AppService.js
* refactor: update AppConfig interface to use Partial<TCustomConfig> and make paths and fileStrategies optional
* refactor: update checkConfig function to accept Partial<TCustomConfig>
* chore: fix types
* refactor: move handleRateLimits to startup checks as is an effect
* test: remove outdated rate limit tests from AppService.spec and add new handleRateLimits tests in checks.spec
* ⚙️ chore: Resolve Build Warning and `keyvMongo` types
* 🔄 chore: Update mongodb version to ^6.14.2 in package.json and package-lock.json
* chore: remove @langchain/openai dep
* 🔄 refactor: Change log level from warn to debug for missing endpoint config
* 🔄 refactor: Improve temp chat expiration date calculation in tests and implementation
* initialize servers sequentially
* adjust for exported properties that are not nullable anymore
* use underscore separator
* mock with set
* customize init timeout via env var
* refactor for readability, use loaded conns for tool functions
* address PR comments
* clean up fire-and-forget
* fix tests
* Refactor: Moved Redis cache infra logic into `packages/api`
- Moved cacheFactory and redisClients from `api/cache` into `packages/api/src/cache` so that features in `packages/api` can use cache without importing backward from the backend.
- Converted all moved files into TS with proper typing.
- Created integration tests to run against actual Redis servers for redisClients and cacheFactory.
- Added a GitHub workflow to run integration tests for the cache feature.
- Bug fix: keyvRedisClient now implements the PING feature properly.
* chore: consolidate imports in getLogStores.js
* chore: reorder imports
* chore: re-add fs-extra as dev dep.
* chore: reorder imports in cacheConfig.ts, cacheFactory.ts, and keyvMongo.ts
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🧹 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
* Add support for extra secrets and config maps in helm deployment template
* expose single env field in values field instead of extra secret and config map fields
* a small fix
* 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.
* fix: Prevent MCPSelect from rendering when not pinned and no values are available
* fix: Exclude 'pinned' keys from timestamped storage cleanup logic
* fix: Safeguard MCPSelect rendering by adding optional chaining for mcpValues
Add ability to configure hostAliases in Helm chart to redirect traffic to proxy servers or custom endpoints via /etc/hosts entries.
Co-authored-by: Feng Lu <feng.lu@kindredgroup.com>
* 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
- Added tests to validate behavior of web_search parameter in getOpenAIConfig function.
- Implemented logic to handle web_search in addParams and dropParams, ensuring correct precedence and behavior.
- Ensured web_search does not appear in modelKwargs or llmConfig when not applicable.
- Improved overall configuration management for OpenAI API integration.
- 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>
This PR adds DNS configuration support to the LibreChat Helm chart, enabling users to redirect traffic to proxy servers or use custom DNS settings.
## What's Changed
- Added dnsPolicy and dnsConfig fields to deployment.yaml template
- Added DNS configuration options to values.yaml with comprehensive examples
- Created documentation and example configurations
## Use Cases
- Redirect AI service traffic (AWS Bedrock, OpenAI, etc.) to proxy servers
- Use corporate DNS servers for name resolution
- Control traffic routing through custom DNS configurations
- Enforce traffic through security gateways
## Configuration Example
```yaml
dnsPolicy: "None"
dnsConfig:
nameservers:
- "10.0.0.10" # Custom DNS server for redirections
searches:
- "svc.cluster.local"
options:
- name: ndots
value: "2"
```
## Testing Results
✅ Successfully tested with Docker Compose environment
✅ DNS resolution correctly redirects to configured IPs
✅ HTTP requests properly routed to proxy servers
✅ Tested with multiple domains (AWS Bedrock, OpenAI, SageMaker)
Test output:
- bedrock-runtime.us-east-1.amazonaws.com -> 172.25.0.10 ✓
- api.openai.com -> 172.25.0.10 ✓
- sagemaker-runtime.us-east-1.amazonaws.com -> 172.25.0.10 ✓
All DNS redirects working correctly with proxy server receiving traffic.
## Documentation
- Added comprehensive DNS_CONFIGURATION.md guide
- Included examples for common use cases
- Provided troubleshooting steps
## Backward Compatibility
This change is fully backward compatible. If dnsPolicy and dnsConfig are not specified, the default Kubernetes DNS behavior is maintained.
Fixes #[issue_number]
Co-authored-by: LibreChat User <user@example.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>
- Update MongoDB chart dependency from v16.3.0 to v16.5.45
- Add explicit containerPort configuration with fallback to service.port
- Standardize port references in health probes to use explicit port numbers
- Add targetPort and containerPort fields to service configuration
- Include service type options as inline comment for better clarity
These changes improve the Helm chart's port management flexibility and
bring the MongoDB dependency up to date with the latest stable version.
Co-authored-by: Jerum Hubbert <jerum.hubbert@scientificgames.com>
* refactor: Remove unused imports and consolidate ephemeral agent logic
* refactor: Side Panel agent handling to account for ephemeral agents for UI
* refactor: Replace Constants.EPHEMERAL_AGENT_ID checks with isEphemeralAgent utility for consistency
* ci: AgentPanel tests with additional mock configurations and utility functions
* chore: Improve logging format for initial flow state creation
* refactor: MCP Tool Management with Improved Auth Handling and State Management
- Updated `CustomUserVarsSection` to include optional localization for placeholder text.
- Refactored `MCPToolSelectDialog` to streamline tool addition and management, including improved handling of authentication data.
- Introduced a new `addToolsToForm` function to encapsulate logic for adding tools to the form state.
- Enhanced `useRemoveMCPTool` hook to simplify tool removal logic and ensure proper state updates.
- Added loading state management for custom variable saving to improve user experience.
* refactor: Enhance MCP Tool Removal Logic and Integrate Toast Notifications
- Updated `MCPToolSelectDialog` to utilize the new `removeTool` function from the `useRemoveMCPTool` hook for improved tool removal handling.
- Refactored `useRemoveMCPTool` to accept options for toast notifications, allowing for more flexible user feedback during tool removal.
- Removed the previous inline tool removal logic to streamline the component's code and improve maintainability.
* refactor: Enhance user plugins mutation to invalidate MCP auth values on uninstall
* refactor: Replace refetchQueries with invalidateQueries for improved cache management
* chore: remove unused i18n key
* 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
* chore: Update documentation for formatToolContent function, remove JSDoc types and duplicate comments
* chore: fix type errors due to attachment.filename in Attachment component
* bug: updating so text doesn't delete
* fix: preserve user input when typing during AI response
Previously, form.reset() would clear any text the user started typing while waiting for AI response. Now checks if textarea has new content before resetting, preventing text loss and improving UX.
* chore: revert useSubmitMessage changes
* fix: reduce debounce time for input handling in auto-save
* fix: improve debounce handling for auto-save input to enhance user experience
---------
Co-authored-by: Megan Greenberg <mgreenberg@networkninja.com>
* 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
* fix: correctly build conversation template and preset for chats starting from marketplace
* test: enhance AgentDetail tests with additional localization and conversation mocks
- Updated MCPServersRegistry to correctly process serverInstructions when provided as a string "true", allowing it to fetch instructions from the server.
- Added a new utility function `isEnabled` to determine if serverInstructions should trigger a fetch.
- Introduced comprehensive tests to validate the behavior for different serverInstructions configurations, ensuring both string "true" and boolean true fetch from the server while custom strings remain unchanged.
🎯 This enhancement improves the flexibility and correctness of server instruction handling in the MCPServersRegistry.
* 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: agent tool permissions to support ephemeral agent settings
* ci: rename render tests and correct typing for `useAgentToolPermissions` hook
* refactor: implement `DragDropContext` to minimize effect of `useChatContext` in `DragDropModal`
- Added isEphemeralAgent function to streamline checks for ephemeral agents.
- Updated logic in useAgentToolPermissions to utilize the new function for determining tool access.
- Introduced comprehensive tests for useAgentToolPermissions covering various scenarios including ephemeral agents, regular agents with tools, and edge cases.
* 💻 feat: Add proxy configuration support for Mistral OCR API requests
* refactor: Implement proxy support for Mistral API requests using HttpsProxyAgent
* 🔃 fix: Token Refresh in Browser Only, Redirect on Refresh Failure
* chore: Update import for SearchResultData and fix FormattedToolResponse type build warning
* ✂️ 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>
* 🌍 i18n: Update translation.json with latest translations
* Update drag and drop tooltip text
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
* 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
* 🔧 refactor: Centralize Collection Existence Checks for Permissions Migration
* Replace individual collection existence checks with a unified function `ensureRequiredCollectionsExist` in the database utility module.
* Update migration scripts for agents and prompts to utilize the new function, ensuring all required collections are verified for existence in a single call.
* Remove redundant collection existence logic from migration files, improving code maintainability and clarity.
* chore: import order in migration scripts
* 🔧 test: Update Token Test Cases for Realistic Scenarios
* Changed email in test data to 'user1-alt@example.com' for a more realistic scenario.
* Clarified expectation comment for token retrieval to indicate it finds the only matching token based on criteria.
* 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
* don't require conversation for bookmark button
* wrap marketplace component so it can correctly use context hooks
* chore: re-order import statement for MarketplaceProvider
---------
Co-authored-by: Danny Avila <danacordially@gmail.com>
- 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)
* 📬 refactor: Improved Rendering and Localization for Drag & Drop Files
- Refactored DragDropOverlay to use memoization and props for active state management.
- Updated the overlay to always render, reducing mount/unmount overhead.
- Improved user experience with localized text for drag-and-drop instructions.
- Enhanced file handling logic in useDragHelpers for better performance and clarity.
* fix: agent data retrieval in drag helper
* 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.
* Added functionality to process OAuth configuration within the MCP environment.
* Implemented handling for string values in OAuth settings, ensuring proper processing of environment variables.
* Maintained original structure for non-string values to preserve existing configurations.
* 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.
* 🔑 refactor: `fileStrategy` for OpenID, SAML, and Social logins
* ci: Update Apple strategy tests to use correct isEnabled import and enhance handleExistingUser call
* Make file search citations conditional
* refactor: improve permission handling to avoid redundant checks by including it in artifact
* chore: reorder imports for better organization and clarity
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🔧 fix: Enhance OpenID token handling with user ID for image path validation
* 🔧 fix: Change logger level to error for user info fetch failure and remove redundant info log in OpenID user lookup
* 🔧 refactor: Remove validateImageRequest from middleware exports and enhance validation logic in validateImageRequest.js
* Removed validateImageRequest from the middleware index.
* Improved error handling and validation checks in validateImageRequest.js, including handling of OpenID tokens, URL length, and malformed URLs.
* Updated tests in validateImages.spec.js to cover new validation scenarios and edge cases.
* ✨ fix: Refactor theme handling to use isDark utility across components
* 🔧 fix: Update package client version to 0.2.8 and adjust theme import path in ThemeSelector component
---------
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
* refactor: MCP UI Separation for Agents (Dustin WIP)
feat: separate MCPs into their own lists away from tools + actions and add the status indicator functionality from chat to their dropdown ui
fix: spotify mcp was not persisting on agent creation
feat: show disconnected saved servers and their tools in agent mcp list in created agents
fix: select-all regression fixed (caused by deleting tools we were drawing from for rendering list)
fix: dont show all mcps, only those installed in agent in list
feat: separate ToolSelectDialog for MCPServerTools
fix: uninitialized mcp servers not showing as added in toolselectdialog
refactor: reduce looping in AgentPanelContext for categorizing groups and mcps
refactor: split ToolSelectDialog and MCPToolSelectDialog functionality (still needs customization for custom user vars)
chore: address ESLint comments
chore: address ESLint comments
feat: one-click initialization on MCP servers in agent builder
fix: stop propagation triggering reinit on caret click
refactor: split uninitialized MCPs component from initialized MCPs
feat: new mcp tool select dialog ui with custom user vars
feat: show initialization state for CUV configurable MCPs too
chore: remove unused localization string
fix: deselecting all tools caused a re-render
fix: remove subtools so removal from MCPToolSelectDialog works more consistently
feat: added servers have all tools enabled by default
feat: mcp server list now alphabetical to prevent annoying ui behavior of servers jumping around depending on tool selection
fix: filter out placeholder group mcp tools from any actual tool calls / definitions
feat: indicator now takes you to config dialog for uninitialized servers
feat: show previously configured mcp servers that are now missing from the yaml
feat: select all enabled by default on first add to mcp server list
chore: address ESLint comments
* refactor: MCP UI Separation for Agents (Danny WIP)
chore: remove use of `{serverName}_mcp_{serverName}`
chore: import order
WIP: separate component concerns
refactor: streamline agent mcp tools
refactor: unify MCP server handling and improve tool visibility logic, remove unnecessary normalization or sorting, remove nesting button, make variable names clear
refactor: rename mcpServerIds to mcpServerNames for clarity and consistency across components
refactor: remove groupedMCPTools and toolToServerMap, streamline MCP server handling in context and components to effectively utilize mcpServersMap
refactor: optimize tool selection logic by replacing array includes with Set for improved performance
chore: add error logging for failed auth URL parsing in ToolCall component
refactor: enhance MCP tool handling by improving server name management and updating UI elements for better clarity
* refactor: decouple connection status from useMCPServerManager with useMCPConnectionStatus
* fix: improve MCP tool validation logic to handle unconfigured servers
* chore: enhance log message clarity for MCP server disconnection in updateUserPluginsController
* refactor: simplify connection status extraction in useMCPConnectionStatus hook
* refactor: improve initializing UX
* chore: replace string literal with ResourceType constant in useResourcePermissions
* refactor: cleanup code, remove redundancies, rename variables for clarity
* chore: add back filtering and sorting for mcp tools dialog
* refactor: initializeServer to return response and early return
* refactor: enhance server initialization logic and improve UI for OAuth interaction
* chore: clarify warning message for unconfigured MCP server in handleTools
* refactor: prevent CustomUserVarsSection from submitting tools dialog form
* fix: nested button of button issue in UninitializedMCPTool
* feat: add functionality to revoke custom user variables in MCPToolSelectDialog
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🔧 fix: Ensure loading state is correctly set when files are empty or in progress
* 🔧 fix: Update ephemeral agent state on file upload error for execute code tool resource
* 🔧 fix: Reset ephemeral agent state for tool when authentication fails
* refactor: Pass conversation prop to FileFormChat and AttachFileChat components
* refactor: resolve request-based headers for custom endpoints right before LLM request
* ci: clarify request-based header resolution in initializeClient test
* refactor: useMCPSelect
- Add useGetMCPTools to use in useMCPSelect and elsewhere hooks for fetching MCP tools
- remove memoized key
- remove use of `useChatContext` and require conversationId as prop
* feat: Add MCPPanelContext and integrate conversationId as prop for useMCPSelect across components
- Introduced MCPPanelContext to manage conversationId state.
- Updated MCPSelect, MCPSubMenu, and MCPConfigDialog to accept conversationId as a prop.
- Modified ToolsDropdown and BadgeRow to pass conversationId to relevant components.
- Refactored MCPPanel to utilize MCPPanelProvider for context management.
* fix: remove nested ternary in ServerInitializationSection
- Replaced conditional operator with if-else statements for better readability in determining button text based on server initialization state and reinitialization status.
* refactor: wrap setValueWrap in useCallback for performance optimization
* refactor: streamline useMCPSelect by consolidating storageKey definition
* fix: prevent clearing selections on page refresh by tracking initial load completion
* refactor: simplify concern of useMCPSelect hook
* refactor: move ConfigFieldDetail interface to common types for better reusability, isolate usage of `useGetMCPTools`
* refactor: integrate mcpServerNames into BadgeRowContext and update ToolsDropdown and MCPSelect components
* 🔧 fix: TTS and STT Services to use AppConfig
- Updated `getProviderSchema` and `getProvider` methods to accept an optional `appConfig` parameter, allowing for more flexible configuration retrieval.
- Improved error handling by ensuring that the app configuration is checked before accessing TTS and STT schemas.
- Refactored `processTextToSpeech` and `streamAudio` methods to utilize the new `appConfig` parameter for better clarity and maintainability.
* feat: Cumulative Transcription Support for STT External
* style: fix medium-sized styling for admin settings dialogs
- Added useRef to maintain existing text during audio recording.
- Updated setText to prepend existing text to new transcriptions.
- Modified handleStartRecording and handleStopRecording to manage existing text state.
- Improved spinner icon styling for better visibility.
- Added support for a minimum password length defined by the MIN_PASSWORD_LENGTH environment variable.
- Updated login, registration, and reset password forms to utilize the configured minimum length.
- Enhanced validation schemas to reflect the new minimum password length requirement.
- Included tests to ensure the minimum password length functionality works as expected.
* added REDIS_USE_ALTERNATIVE_DNS_LOOKUP env variable to modify redis connection by adding dnsLookup
this is required when connecting to elasticache for ioredis
see "Special Note: Aws Elasticache Clusters with TLS" on this webpage: https://www.npmjs.com/package/ioredis
* added REDIS_USE_ALTERNATIVE_DNS_LOOKUP env variable to modify redis connection by adding dnsLookup
this is required when connecting to elasticache for ioredis
see "Special Note: Aws Elasticache Clusters with TLS" on this webpage: https://www.npmjs.com/package/ioredis
---------
Co-authored-by: Marc Amick <MarcAmick@jhu.edu>
* feat: move buildTree function for message hierarchy to data provider
* refactor: consolidate buildTree import from utils to data provider
* fix: correct string interpolation in messages function, which caused message search requests to fail
* 🪶 feat: Add Support for Uploading Plaintext Files
feat: delineate between OCR and text handling in fileConfig field of config file
- also adds support for passing in mimetypes as just plain file extensions
feat: add showLabel bool to support future synthetic component DynamicDropdownInput
feat: add new combination dropdown-input component in params panel to support file type token limits
refactor: move hovercard to side to align with other hovercards
chore: clean up autogenerated comments
feat: add delineation to file upload path between text and ocr configured filetypes
feat: add token limit checks during file upload
refactor: move textParsing out of ocrEnabled logic
refactor: clean up types for filetype config
refactor: finish decoupling DynamicDropdownInput from fileTokenLimits
fix: move image token cost function into file to fix circular dependency causing unittest to fail and remove unused var for linter
chore: remove out of scope code following review
refactor: make fileTokenLimit conform to existing styles
chore: remove unused localization string
chore: undo changes to DynamicInput and other strays
feat: add fileTokenLimit to all provider config panels
fix: move textParsing back into ocr tool_resource block for now so that it doesn't interfere with other upload types
* 📤 feat: Add RAG API Endpoint Support for Text Parsing (#8849)
* feat: implement RAG API integration for text parsing with fallback to native parsing
* chore: remove TODO now that placeholder and fllback are implemented
* ✈️ refactor: Migrate Text Parsing to TS (#8892)
* refactor: move generateShortLivedToken to packages/api
* refactor: move textParsing logic into packages/api
* refactor: reduce nesting and dry code with createTextFile
* fix: add proper source handling
* fix: mock new parseText and parseTextNative functions in jest file
* ci: add test coverage for textParser
* 💬 feat: Add Audio File Support to Upload as Text (#8893)
* feat: add STT support for Upload as Text
* refactor: move processAudioFile to packages/api
* refactor: move textParsing from utils to files
* fix: remove audio/mp3 from unsupported mimetypes test since it is now supported
* ✂️ feat: Configurable File Token Limits and Truncation (#8911)
* feat: add configurable fileTokenLimit default value
* fix: add stt to fileConfig merge logic
* fix: add fileTokenLimit to mergeFileConfig logic so configurable value is actually respected from yaml
* feat: add token limiting to parsed text files
* fix: add extraction logic and update tests so fileTokenLimit isnt sent to LLM providers
* fix: address comments
* refactor: rename textTokenLimiter.ts to text.ts
* chore: update form-data package to address CVE-2025-7783 and update package-lock
* feat: use default supported mime types for ocr on frontend file validation
* fix: should be using logger.debug not console.debug
* fix: mock existsSync in text.spec.ts
* fix: mock logger rather than every one of its function calls
* fix: reorganize imports and streamline file upload processing logic
* refactor: update createTextFile function to use destructured parameters and improve readability
* chore: update file validation to use EToolResources for improved type safety
* chore: update import path for types in audio processing module
* fix: update file configuration access and replace console.debug with logger.debug for improved logging
---------
Co-authored-by: Dustin Healy <dustinhealy1@gmail.com>
Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>
* feat: Add support to SubDirectory hosting
* fix: address linting and failing test
* fix: browser context validation
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* WIP: app.locals refactoring
WIP: appConfig
fix: update memory configuration retrieval to use getAppConfig based on user role
fix: update comment for AppConfig interface to clarify purpose
🏷️ refactor: Update tests to use getAppConfig for endpoint configurations
ci: Update AppService tests to initialize app config instead of app.locals
ci: Integrate getAppConfig into remaining tests
refactor: Update multer storage destination to use promise-based getAppConfig and improve error handling in tests
refactor: Rename initializeAppConfig to setAppConfig and update related tests
ci: Mock getAppConfig in various tests to provide default configurations
refactor: Update convertMCPToolsToPlugins to use mcpManager for server configuration and adjust related tests
chore: rename `Config/getAppConfig` -> `Config/app`
fix: streamline OpenAI image tools configuration by removing direct appConfig dependency and using function parameters
chore: correct parameter documentation for imageOutputType in ToolService.js
refactor: remove `getCustomConfig` dependency in config route
refactor: update domain validation to use appConfig for allowed domains
refactor: use appConfig registration property
chore: remove app parameter from AppService invocation
refactor: update AppConfig interface to correct registration and turnstile configurations
refactor: remove getCustomConfig dependency and use getAppConfig in PluginController, multer, and MCP services
refactor: replace getCustomConfig with getAppConfig in STTService, TTSService, and related files
refactor: replace getCustomConfig with getAppConfig in Conversation and Message models, update tempChatRetention functions to use AppConfig type
refactor: update getAppConfig calls in Conversation and Message models to include user role for temporary chat expiration
ci: update related tests
refactor: update getAppConfig call in getCustomConfigSpeech to include user role
fix: update appConfig usage to access allowedDomains from actions instead of registration
refactor: enhance AppConfig to include fileStrategies and update related file strategy logic
refactor: update imports to use normalizeEndpointName from @librechat/api and remove redundant definitions
chore: remove deprecated unused RunManager
refactor: get balance config primarily from appConfig
refactor: remove customConfig dependency for appConfig and streamline loadConfigModels logic
refactor: remove getCustomConfig usage and use app config in file citations
refactor: consolidate endpoint loading logic into loadEndpoints function
refactor: update appConfig access to use endpoints structure across various services
refactor: implement custom endpoints configuration and streamline endpoint loading logic
refactor: update getAppConfig call to include user role parameter
refactor: streamline endpoint configuration and enhance appConfig usage across services
refactor: replace getMCPAuthMap with getUserMCPAuthMap and remove unused getCustomConfig file
refactor: add type annotation for loadedEndpoints in loadEndpoints function
refactor: move /services/Files/images/parse to TS API
chore: add missing FILE_CITATIONS permission to IRole interface
refactor: restructure toolkits to TS API
refactor: separate manifest logic into its own module
refactor: consolidate tool loading logic into a new tools module for startup logic
refactor: move interface config logic to TS API
refactor: migrate checkEmailConfig to TypeScript and update imports
refactor: add FunctionTool interface and availableTools to AppConfig
refactor: decouple caching and DB operations from AppService, make part of consolidated `getAppConfig`
WIP: fix tests
* fix: rebase conflicts
* refactor: remove app.locals references
* refactor: replace getBalanceConfig with getAppConfig in various strategies and middleware
* refactor: replace appConfig?.balance with getBalanceConfig in various controllers and clients
* test: add balance configuration to titleConvo method in AgentClient tests
* chore: remove unused `openai-chat-tokens` package
* chore: remove unused imports in initializeMCPs.js
* refactor: update balance configuration to use getAppConfig instead of getBalanceConfig
* refactor: integrate configMiddleware for centralized configuration handling
* refactor: optimize email domain validation by removing unnecessary async calls
* refactor: simplify multer storage configuration by removing async calls
* refactor: reorder imports for better readability in user.js
* refactor: replace getAppConfig calls with req.config for improved performance
* chore: replace getAppConfig calls with req.config in tests for centralized configuration handling
* chore: remove unused override config
* refactor: add configMiddleware to endpoint route and replace getAppConfig with req.config
* chore: remove customConfig parameter from TTSService constructor
* refactor: pass appConfig from request to processFileCitations for improved configuration handling
* refactor: remove configMiddleware from endpoint route and retrieve appConfig directly in getEndpointsConfig if not in `req.config`
* test: add mockAppConfig to processFileCitations tests for improved configuration handling
* fix: pass req.config to hasCustomUserVars and call without await after synchronous refactor
* fix: type safety in useExportConversation
* refactor: retrieve appConfig using getAppConfig in PluginController and remove configMiddleware from plugins route, to avoid always retrieving when plugins are cached
* chore: change `MongoUser` typedef to `IUser`
* fix: Add `user` and `config` fields to ServerRequest and update JSDoc type annotations from Express.Request to ServerRequest
* fix: remove unused setAppConfig mock from Server configuration tests
* fix: error when updating bookmarks if no query data
* feat: localize bookmark dialog, form labels and validation messages, also improve validation
* feat: add localization for EmptyPromptPreview component and update translation.json
* chore: add missing localizations for static UI text
* chore: update AgentPanelContextType and useGetAgentsConfig to support null configurations
* refactor: update agent categories to support localization and custom properties, improve related typing
* ci: add localization for 'All' category and update tab names in accessibility tests
* chore: remove unused AgentCategoryDisplay component and its tests
* chore: add localization handling for agent category selector
* chore: enhance AgentCard to support localized category labels and add related tests
* chore: enhance i18n unused keys detection to include additional source directories and improve handling for agent category keys
* refactor: Resource Migration Scripts for DocumentDB compatibility
* fix: Correct type annotation for `db` parameter in ensureCollectionExists function
* fix(latex): prevent LaTeX conversion when closing $ is preceded by backtick
When text contained patterns like "$lookup namespace" followed by "`$lookup`",
the regex would match from the first $ to the backtick's $, treating the entire
span as a LaTeX expression. This caused programming constructs to be incorrectly
converted to double dollars.
- Added negative lookbehind (?<!`) to single dollar regex
- Prevents matching when closing $ immediately follows a backtick
- Fixes issues with inline code blocks containing $ symbols
* fix(latex): detect currency amounts with 4+ digits without commas
The currency regex pattern \d{1,3} only matched amounts with 1-3 initial digits,
causing amounts like $1157.90 to be interpreted as LaTeX instead of currency.
This resulted in text like "$1157.90 (text) + $500 (text) = $1657.90" being
incorrectly converted to a single LaTeX expression.
- Changed pattern from \d{1,3} to \d+ to match any number of initial digits
- Now properly escapes $1000, $10000, $123456, etc. without requiring commas
- Maintains support for comma-formatted amounts like $1,234.56
* fix(latex): support currency with unlimited decimal places
The currency regex limited decimal places to 1-2 digits (\.\d{1,2}), which
failed to properly escape amounts with more precision like cryptocurrency
values ($0.00001234), gas prices ($3.999), or exchange rates ($1.23456).
- Changed decimal pattern from \.\d{1,2} to \.\d+
- Now supports any number of decimal places
- Handles edge cases like scientific calculations and high-precision values
* fix: available tools retrieval with correct mcp caching and conversion
* test: Enhance PluginController tests with MCP tool mocking and conversion
* refactor: Simplify PluginController tests by removing unused mocks and enhancing test clarity
* feat: Add directEndpoint option to OpenAIConfigOptions and update fetch logic to override /chat/completions URL
* feat: Add directEndpoint support to fetchModels and update loadConfigModels logic
* chore: import paths for isEnabled and logger in title.js
* ⛔ fix: `AbortSignal` Cleanup Logic for New Chats
* test: Add `isNewConvo` parameter to onStart expectation in BaseClient tests
Fixes "Cannot read properties of undefined (reading 'key')" error in parameter panels by filtering out null/undefined values before mapping operations.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* decouple MCP dialog from BadgeRowContext
* chore: import order and style according to guidelines
---------
Co-authored-by: Dustin Healy <dustinhealy1@gmail.com>
* 📦 chore: Bump `@librechat/api` to v1.3.3
* 📦 chore: Bump `librechat-data-provider` to v0.8.003
* 📦 chore: Bump `@librechat/data-schemas` to v0.0.18
* 📦 chore: Bump `@librechat/client` to v0.2.6
* 📦 chore: Update workflow name for `librechat-data-provider` and add manual dispatch
* 📦 chore: Update Node.js version to 20 in data provider workflow
* feat: Add conversation ID support to custom endpoint headers
- Add LIBRECHAT_CONVERSATION_ID to customUserVars when provided
- Pass conversation ID to header resolution for dynamic headers
- Add comprehensive test coverage
Enables custom endpoints to access conversation context using {{LIBRECHAT_CONVERSATION_ID}} placeholder.
* fix: filter out unresolved placeholders from headers (thanks @MrunmayS)
* feat: add support for request body placeholders in custom endpoint headers
- Add {{LIBRECHAT_BODY_*}} placeholders for conversationId, parentMessageId, messageId
- Update tests to reflect new body placeholder functionality
* refactor resolveHeaders
* style: minor styling cleanup
* fix: type error in unit test
* feat: add body to other endpoints
* feat: add body for mcp tool calls
* chore: remove changes that unnecessarily increase scope after clarification of requirements
* refactor: move http.ts to packages/api and have RequestBody intersect with Express request body
* refactor: processMCPEnv now uses single object argument pattern
* refactor: update processMCPEnv to use 'options' parameter and align types across MCP connection classes
* feat: enhance MCP connection handling with dynamic request headers to pass request body fields
---------
Co-authored-by: Gopal Sharma <gopalsharma@gopal.sharma1>
Co-authored-by: s10gopal <36487439+s10gopal@users.noreply.github.com>
Co-authored-by: Dustin Healy <dustinhealy1@gmail.com>
* fix: register openId the strategy if setupOpenId succeeded
* chore: linting and update imports
* refactor: extract OpenID configuration into a separate function
---------
Co-authored-by: Denis <denis.sheremetov@gmail.com>
* ✨ feat: Add support for enabling Redis cluster configuration
* ✨ feat: Enhance Redis client initialization to support cluster configuration without multiple URIs
* ✨ feat: Add tests for USE_REDIS_CLUSTER configuration and validation
* 🐞 fix: Remove unnecessary blank line in cacheConfig tests
* adding beta header context-1m-2025-08-07 to claude sonnet 4 to increase contact window to 1M tokens
* adding context-1m beta header to test cases
* ci: Update Anthropic `getLLMConfig` tests and headers for model variations
- Refactored test cases to ensure proper handling of model variations for 'claude-sonnet-4'.
- Cleaned up unused mock implementations in tests for better clarity and performance.
* refactor: regex in header retrieval for 'claude-sonnet-4' models
* refactor: default tokens for 'claude-sonnet-4' to `1,000,000`
* refactor: add token value retrieval and pattern matching to model tests
---------
Co-authored-by: Dirk Petersen <no-reply@nowhere.com>
* refactor: `packages/api` build scripts for better inline debugging
* refactor: Explicitly select secure fields as no longer returned by default, exclude backupCodes from user data retrieval in authentication and 2FA processes
* refactor: Backup Codes UI to not expect backup codes, only regeneration
* refactor: Ensure secure fields are deleted from user data in getUserController
- Deleted setBalanceConfig middleware and its associated file.
- Introduced createSetBalanceConfig factory function to create middleware for synchronizing user balance settings.
- Updated auth and oauth routes to use the new balance configuration middleware.
- Added comprehensive tests for the new balance middleware functionality.
- Updated package versions and dependencies in package.json and package-lock.json.
- Added balance types and updated middleware index to export new balance middleware.
* refactor: Introduce ModelSelectorChatContext and integrate with ModelSelector
* fix: agents handling in ModelSelector to show expected agents if user has marketplace access
* chore: fix mock typing in packages/api tests
* chore: improve imports, type handling and method signatures for MCPServersRegistry
* chore: use enum in migration scripts
* chore: ParsedServerConfig type to enhance server configuration handling
* feat: Implement agent permissions migration check and logging
* feat: Integrate migration checks into server initialization process
* feat: Add prompt permissions migration check and logging to server initialization
* chore: move prompt formatting functions to dedicated prompts dir
feat: Refactor prompt and prompt group schemas; move types to separate file
feat: Implement paginated access to prompt groups with filtering and public visibility
refactor: Add PromptGroups context provider and integrate it into relevant components
refactor: Optimize filter change handling and query invalidation in usePromptGroupsNav hook
refactor: Simplify context usage in FilterPrompts and GroupSidePanel components
- Added MarketplaceAdminSettings component for managing marketplace permissions.
- Updated roles.js to include marketplace permissions in the API.
- Refactored interface.js to streamline marketplace permissions handling.
- Enhanced Marketplace component to integrate admin settings.
- Updated localization files to include new marketplace-related keys.
- Added new API endpoint for updating marketplace permissions in data-service.
feat: Enhance CategoryTabs and Marketplace components for better responsiveness and navigation
feat: Refactor AgentCard and AgentGrid components for improved layout and accessibility
feat: Implement animated category transitions in AgentMarketplace and update NewChat component layout
feat: Refactor UI components for improved styling and accessibility in sharing dialogs
refactor: remove GenericManagePermissionsDialog and GrantAccessDialog components
- Deleted GenericManagePermissionsDialog and GrantAccessDialog components to streamline sharing functionality.
- Updated ManagePermissionsDialog to utilize AccessRolesPicker directly.
- Introduced UnifiedPeopleSearch for improved people selection experience.
- Enhanced PublicSharingToggle with InfoHoverCard for better user guidance.
- Adjusted AgentPanel to change error status to warning for duplicate agent versions.
- Updated translations to include new keys for search and access management.
feat: Add responsive design for SelectedPrincipalsList and improve layout in GenericGrantAccessDialog
feat: Enhance styling in SelectedPrincipalsList and SearchPicker components for improved UI consistency
feat: Improve PublicSharingToggle component with enhanced styling and accessibility features
feat: Introduce InfoHoverCard component and refactor enums for better organization
feat: Implement infinite scroll for agent grids and enhance performance
- Added `useInfiniteScroll` hook to manage infinite scrolling behavior in agent grids.
- Integrated infinite scroll functionality into `AgentGrid` and `VirtualizedAgentGrid` components.
- Updated `AgentMarketplace` to pass the scroll container to the agent grid components.
- Refactored loading indicators to show a spinner instead of a "Load More" button.
- Created `VirtualizedAgentGrid` component for optimized rendering of agent cards using virtualization.
- Added performance tests for `VirtualizedAgentGrid` to ensure efficient handling of large datasets.
- Updated translations to include new messages for end-of-results scenarios.
chore: Remove unused permission-related UI localization keys
ci: Update Agent model tests to handle duplicate support_contact updates
- Modified tests to ensure that updating an agent with the same support_contact does not create a new version and returns successfully.
- Enhanced verification for partial changes in support_contact, confirming no new version is created when content remains the same.
chore: Address ESLint, clean up unused imports and improve prop definitions in various components
ci: fix tests
ci: update tests
chore: remove unused search localization keys
- Refactored `getListAgentsByAccess` to streamline query construction for accessible agents.
- Added comprehensive security tests for `getListAgentsByAccess` and `getListAgentsHandler` to ensure proper access control and filtering based on user permissions.
- Enhanced test coverage for various scenarios, including pagination, category filtering, and handling of non-existent IDs.
WIP: Role as Permission Principal Type
WIP: add user role check optimization to user principal check, update type comparisons
WIP: cover edge cases for string vs ObjectId handling in permission granting and checking
chore: Update people picker access middleware to use PrincipalType constants
feat: Enhance people picker access control to include roles permissions
chore: add missing default role schema values for people picker perms, cleanup typing
feat: Enhance PeoplePicker component with role-specific UI and localization updates
chore: Add missing `VIEW_ROLES` permission to role schema
- Replaced string literals for principal models ('User', 'Group') with the new PrincipalModel enum across various models, services, and tests to enhance type safety and consistency.
- Updated permission handling in multiple files to utilize the PrincipalModel enum, improving maintainability and reducing potential errors.
- Ensured all relevant tests reflect these changes to maintain coverage and functionality.
- Replaced string literals for principal types ('user', 'group', 'public') with the new PrincipalType enum across various models, services, and tests for improved type safety and consistency.
- Updated permission handling in multiple files to utilize the PrincipalType enum, enhancing maintainability and reducing potential errors.
- Ensured all relevant tests reflect these changes to maintain coverage and functionality.
- Refactor tests to use PromptGroup roles instead of Project roles.
- Initialize models and seed default roles in test setup.
- Update error handling for non-existent resource types.
- Ensure proper cleanup of test data while retaining seeded roles.
refactor: organize Sharing/Agent components, improve type safety for resource types and access role ids, rename enums to PascalCase
refactor: organize Sharing/Agent components, improve type safety for resource types and access role ids
chore: move sharing related components to dedicated "Sharing" directory
chore: remove PublicSharingToggle component and update index exports
chore: move non-sidepanel agent components to `~/components/Agents`
chore: move AgentCategoryDisplay component with tests
chore: remove commented out code
refactor: change PERMISSION_BITS from const to enum for better type safety
refactor: reorganize imports in GenericGrantAccessDialog and update index exports for hooks
refactor: update type definitions to use ACCESS_ROLE_IDS for improved type safety
refactor: remove unused canAccessPromptResource middleware and related code
refactor: remove unused prompt access roles from createAccessRoleMethods
refactor: update resourceType in AclEntry type definition to remove unused 'prompt' value
refactor: introduce ResourceType enum and update resourceType usage across data provider files for improved type safety
refactor: update resourceType usage to ResourceType enum across sharing and permissions components for improved type safety
refactor: standardize resourceType usage to ResourceType enum across agent and prompt models, permissions controller, and middleware for enhanced type safety
refactor: update resourceType references from PROMPT_GROUP to PROMPTGROUP for consistency across models, middleware, and components
refactor: standardize access role IDs and resource type usage across agent, file, and prompt models for improved type safety and consistency
chore: add typedefs for TUpdateResourcePermissionsRequest and TUpdateResourcePermissionsResponse to enhance type definitions
chore: move SearchPicker to PeoplePicker dir
refactor: implement debouncing for query changes in SearchPicker for improved performance
chore: fix typing, import order for agent admin settings
fix: agent admin settings, prevent agent form submission
refactor: rename `ACCESS_ROLE_IDS` to `AccessRoleIds`
refactor: replace PermissionBits with PERMISSION_BITS
refactor: replace PERMISSION_BITS with PermissionBits
feat: Implement prompt permissions management and access control middleware
fix: agent deletion process to remove associated permissions and ACL entries
fix: Import Permissions for enhanced access control in GrantAccessDialog
feat: use PromptGroup for access control
- Added migration script for PromptGroup permissions, categorizing groups into global view access and private groups.
- Created unit tests for the migration script to ensure correct categorization and permission granting.
- Introduced middleware for checking access permissions on PromptGroups and prompts via their groups.
- Updated routes to utilize new access control middleware for PromptGroups.
- Enhanced access role definitions to include roles specific to PromptGroups.
- Modified ACL entry schema and types to accommodate PromptGroup resource type.
- Updated data provider to include new access role identifiers for PromptGroups.
feat: add generic access management dialogs and hooks for resource permissions
fix: remove duplicate imports in FileContext component
fix: remove duplicate mongoose dependency in package.json
feat: add access permissions handling for dynamic resource types and add promptGroup roles
feat: implement centralized role localization and update access role types
refactor: simplify author handling in prompt group routes and enhance ACL checks
feat: implement addPromptToGroup functionality and update PromptForm to use it
feat: enhance permission handling in ChatGroupItem, DashGroupItem, and PromptForm components
chore: rename migration script for prompt group permissions and update package.json scripts
chore: update prompt tests
style: AccessRolesPicker to use DropdownPopup, theming, import order, localization
refactor: Update localization keys for Agent Marketplace in NewChat component, remove duplicate key
style: Adjust layout and font size in NewChat component for Agent Marketplace button
style: theming in AgentGrid
style: Update theming and text colors across Agent components for improved consistency
chore: import order
style: Replace Dialog with OGDialog and update content components in AgentDetail
refactor: Simplify AgentDetail component by removing dropdown menu and replacing it with a copy link button
style: Enhance scrollbar visibility and layout in AgentMarketplace and CategoryTabs components
style: Adjust layout in AgentMarketplace component by removing unnecessary padding from the container
style: Refactor layout in AgentMarketplace component by reorganizing hero section and sticky wrapper for improved structure with collapsible header effect
style: Improve responsiveness and layout in AgentMarketplace component by adjusting header visibility and modifying container styles based on screen size
fix: Update localization key for no categories message in CategoryTabs component and corresponding test
style: Add className prop to OpenSidebar component for improved styling flexibility and update Header to utilize it for responsive design
style: Enhance layout and scrolling behavior in CategoryTabs component by adding scroll snap properties and adjusting class names for improved user experience
style: Update AgentGrid component layout and skeleton structure for improved visual consistency and responsiveness
bugfix: Enhance Agent and AgentCategory schemas with new fields for category, support contact, and promotion status
refactored and moved agent category methods and schema to data-schema package
🔧 fix: Merge and Rebase Conflicts
- Move AgentCategory from api/models to @packages/data-schemas structure
- Add schema, types, methods, and model following codebase conventions
- Implement auto-seeding of default categories during AppService startup
- Update marketplace controller to use new data-schemas methods
- Remove old model file and standalone seed script
refactor: unify agent marketplace to single endpoint with cursor pagination
- Replace multiple marketplace routes with unified /marketplace endpoint
- Add query string controls: category, search, limit, cursor, promoted, requiredPermission
- Implement cursor-based pagination replacing page-based system
- Integrate ACL permissions for proper access control
- Fix ObjectId constructor error in Agent model
- Update React components to use unified useGetMarketplaceAgentsQuery hook
- Enhance type safety and remove deprecated useDynamicAgentQuery
- Update tests for new marketplace architecture
-Known issues:
see more button after category switching + Unit tests
feat: add icon property to ProcessedAgentCategory interface
- Add useMarketplaceAgentsInfiniteQuery and useGetAgentCategoriesQuery to client/src/data-provider/Agents/
- Replace manual pagination in AgentGrid with infinite query pattern
- Update imports to use local data provider instead of librechat-data-provider
- Add proper permission handling with PERMISSION_BITS.VIEW/EDIT constants
- Improve agent access control by adding requiredPermission validation in backend
- Remove manual cursor/state management in favor of infinite query built-ins
- Maintain existing search and category filtering functionality
refactor: consolidate agent marketplace endpoints into main agents API and improve data management consistency
- Remove dedicated marketplace controller and routes, merging functionality into main agents v1 API
- Add countPromotedAgents function to Agent model for promoted agents count
- Enhance getListAgents handler with marketplace filtering (category, search, promoted status)
- Move getAgentCategories from marketplace to v1 controller with same functionality
- Update agent mutations to invalidate marketplace queries and handle multiple permission levels
- Improve cache management by updating all agent query variants (VIEW/EDIT permissions)
- Consolidate agent data access patterns for better maintainability and consistency
- Remove duplicate marketplace route definitions and middleware
selected view only agents injected in the drop down
fix: remove minlength validation for support contact name in agent schema
feat: add validation and error messages for agent name in AgentConfig and AgentPanel
fix: update agent permission check logic in AgentPanel to simplify condition
Fix linting WIP
Fix Unit tests WIP
ESLint fixes
eslint fix
refactor: enhance isDuplicateVersion function in Agent model for improved comparison logic
- Introduced handling for undefined/null values in array and object comparisons.
- Normalized array comparisons to treat undefined/null as empty arrays.
- Added deep comparison for objects and improved handling of primitive values.
- Enhanced projectIds comparison to ensure consistent MongoDB ObjectId handling.
refactor: remove redundant properties from IAgent interface in agent schema
chore: update localization for agent detail component and clean up imports
ci: update access middleware tests
chore: remove unused PermissionTypes import from Role model
ci: update AclEntry model tests
ci: update button accessibility labels in AgentDetail tests
refactor: update exhaustive dep. lint warning
🔧 fix: Fixed agent actions access
feat: Add role-level permissions for agent sharing people picker
- Add PEOPLE_PICKER permission type with VIEW_USERS and VIEW_GROUPS permissions
- Create custom middleware for query-aware permission validation
- Implement permission-based type filtering in PeoplePicker component
- Hide people picker UI when user lacks permissions, show only public toggle
- Support granular access: users-only, groups-only, or mixed search modes
refactor: Replace marketplace interface config with permission-based system
- Add MARKETPLACE permission type to handle marketplace access control
- Update interface configuration to use role-based marketplace settings (admin/user)
- Replace direct marketplace boolean config with permission-based checks
- Modify frontend components to use marketplace permissions instead of interface config
- Update agent query hooks to use marketplace permissions for determining permission levels
- Add marketplace configuration structure similar to peoplePicker in YAML config
- Backend now sets MARKETPLACE permissions based on interface configuration
- When marketplace enabled: users get agents with EDIT permissions in dropdown lists (builder mode)
- When marketplace disabled: users get agents with VIEW permissions in dropdown lists (browse mode)
🔧 fix: Redirect to New Chat if No Marketplace Access and Required Agent Name Placeholder (#8213)
* Fix: Fix the redirect to new chat page if access to marketplace is denied
* Fixed the required agent name placeholder
---------
Co-authored-by: Atef Bellaaj <slalom.bellaaj@external.daimlertruck.com>
chore: fix tests, remove unnecessary imports
refactor: Implement permission checks for file access via agents
- Updated `hasAccessToFilesViaAgent` to utilize permission checks for VIEW and EDIT access.
- Replaced project-based access validation with permission-based checks.
- Enhanced tests to cover new permission logic and ensure proper access control for files associated with agents.
- Cleaned up imports and initialized models in test files for consistency.
refactor: Enhance test setup and cleanup for file access control
- Introduced modelsToCleanup array to track models added during tests for proper cleanup.
- Updated afterAll hooks in test files to ensure all collections are cleared and only added models are deleted.
- Improved consistency in model initialization across test files.
- Added comments for clarity on cleanup processes and test data management.
chore: Update Jest configuration and test setup for improved timeout handling
- Added a global test timeout of 30 seconds in jest.config.js.
- Configured jest.setTimeout in jestSetup.js to allow individual test overrides if needed.
- Enhanced test reliability by ensuring consistent timeout settings across all tests.
refactor: Implement file access filtering based on agent permissions
- Introduced `filterFilesByAgentAccess` function to filter files based on user access through agents.
- Updated `getFiles` and `primeFiles` functions to utilize the new filtering logic.
- Moved `hasAccessToFilesViaAgent` function from the File model to permission services, adjusting imports accordingly
- Enhanced tests to ensure proper access control and filtering behavior for files associated with agents.
fix: make support_contact field a nested object rather than a sub-document
refactor: Update support_contact field initialization in agent model
- Removed handling for empty support_contact object in createAgent function.
- Changed default value of support_contact in agent schema to undefined.
test: Add comprehensive tests for support_contact field handling and versioning
refactor: remove unused avatar upload mutation field and add informational toast for success
chore: add missing SidePanelProvider for AgentMarketplace and organize imports
fix: resolve agent selection race condition in marketplace HandleStartChat
- Set agent in localStorage before newConversation to prevent useSelectorEffects from auto-selecting previous agent
fix: resolve agent dropdown showing raw ID instead of agent info from URL
- Add proactive agent fetching when agent_id is present in URL parameters
- Inject fetched agent into agents cache so dropdowns display proper name/avatar
- Use useAgentsMap dependency to ensure proper cache initialization timing
- Prevents raw agent IDs from showing in UI when visiting shared agent links
Fix: Agents endpoint renamed to "My Agent" for less confusion with the Marketplace agents.
chore: fix ESLint issues and Test Mocks
ci: update permissions structure in loadDefaultInterface tests
- Refactored permissions for MEMORY and added new permissions for MARKETPLACE and PEOPLE_PICKER.
- Ensured consistent structure for permissions across different types.
feat: support_contact validation to allow empty email strings
WIP: pre-granular-permissions commit
feat: Add category and support contact fields to Agent schema and UI components
Revert "feat: Add category and support contact fields to Agent schema and UI components"
This reverts commit c43a52b4c9.
Fix: Update import for renderHook in useAgentCategories.spec.tsx
fix: Update icon rendering in AgentCategoryDisplay tests to use empty spans
refactor: Improve category synchronization logic and clean up AgentConfig component
refactor: Remove unused UI flow translations from translation.json
feat: agent marketplace features
🔐 feat: Granular Role-based Permissions + Entra ID Group Discovery (#7804)
* chore: Remove eslint-plugin-perfectionist from dependencies
* 🚌 fix: MCP Runtime Errors while Initializing
* chore: Bump @librechat/api version to 1.3.1
* chore: import order
* chore: import order
- Fix grammar in translations README: 'if has not been ran' 'if it has not been run'
- Fix spacing in JSDoc comments: 'at theend' 'at the end' (2 instances)
* fix: social login provider crossover
* feat: Enhance OpenID login handling and add tests for provider validation
* refactor: authentication error handling to use ErrorTypes.AUTH_FAILED enum
* refactor: update authentication error handling in LDAP and SAML strategies to use ErrorTypes.AUTH_FAILED enum
* ci: Add validation for login with existing email and different provider in SAML strategy
chore: Add logging for existing users with different providers in LDAP, SAML, and Social Login strategies
- Updated `handleExistingUser` function to improve avatar handling logic, including checks for manual flags and null/undefined avatars.
- Introduced a new test suite for `handleExistingUser` covering various scenarios, ensuring robust functionality for avatar updates in both local and non-local storage contexts.
* fix: localization string had unused template var
* fix: add normalizeHttpError to hopefully stop UI hangs when an error is returned in UserController
- Ensures updateUserPluginsController always returns valid HTTP status codes instead of undefined
- Add normalizeHttpError() helper to safely extract status/message from errors
- Default to 400 status code when Error.status is undefined/invalid
* refactor: move normalizeHttpError to packages/api
* 🛣️ fix: Remove Title Tokens Limit for GPT-5 Models
* 🛣️ fix: Remove max_completion_tokens from modelKwargs when maxTokens is disabled
* chore: Add test-image* to .gitignore for CI/CD data
* WIP: Verbosity OpenAI Parameter
* 🔧 chore: remove unused import of extractEnvVariable from parsers.ts
* ✨ feat: add comprehensive tests for getOpenAIConfig and enhance verbosity handling
* fix: Handling for maxTokens in GPT-5+ models and add corresponding tests
* feat: Implement GPT-5+ model handling in processMemory function
* ✨ feat: Enhance Tooltip component with HTML support and styling improvements
* ✨ feat: Integrate DOMPurify for HTML sanitization in Tooltip component
* fix: add refetchQueries on connection success so ToolSelectDialog doesn't require hard refresh
* fix: change hook so we only query connection status when mcpServers are configured
* fix: change refetchQueries to invalidateQueries for tools after server connection update
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* ✨ feat: Add OpenID audience parameter support in authorization requests
* Updated .env.example to include OPENID_AUDIENCE variable for configuration.
* Enhanced openidStrategy to set the audience parameter in authorization requests if specified, improving OpenID integration.
* Update .env.example
* Update openidStrategy.js
---------
Co-authored-by: Danny Avila <danacordially@gmail.com>
* feat: Update client version to 0.2.2 and add animation styles for popovers and tooltips
* refactor: Remove focus outline styles from Dropdown component
* feat: Update client version to 0.2.3 and add Select component export
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* chore: Handle optional token_endpoint in OAuth metadata discovery
* chore: Simplify permission typing logic in checkAccess function
* feat: Implement `deleteMistralFile` function and integrate file cleanup in `uploadMistralOCR`
* 🌍 i18n: Add Tibetan and Ukrainian languages to localization
* feat: Update language selector to include Tibetan and Ukrainian options
* feat: Add translation files for Tibetan and Ukrainian languages
* chore: Update English translation.json with new language keys
* docs: Create localization guide for adding new languages
* Update README.md
* refactor: Enhance MCP components with improved UI elements and localization updates
* refactor: Clean up MCP components by removing unused imports and improving layout
* refactor: Update server status badge styling for improved UI consistency
* refactor: Move group up a level so 'X' and background highlight occur at same time for cancellation button
* refactor: Remove unused translation keys from the localization file
---------
Co-authored-by: Dustin Healy <dustinhealy1@gmail.com>
Now prioritizes preferred_username claim, then the nonstandard
username claim, then email.
Removed given_name as a possible username choice to avoid exposing users’ first names as
usernames.
Updated openidStrategy.spec.js to reflect the new claim order.
Fixed mock OpenID server behavior where preferred_username was always
hardcoded, causing test failures.
Adjusted OpenID setup test to align with new username parameter
behavior.
* fix: add OAuth flow back in to success state
* feat: disable server clicks during initialization to prevent spam
* fix: correct new tab behavior for OAuth between one-click and normal initialization flows
* fix: stop polling on error during oauth (was infinite popping toasts because we didn't clear interval)
* fix: cleanupServerState should be called after successful cancelOauth, not before
* fix: change from completeFlow to failFlow to avoid stale client IDs on OAuth after cancellation
* fix: add logic to differentiate between cancelled and failed flows when checking status for indicators (so error triangle indicator doesn't show up on cancellaiton)
* Use discoverAuthorizationServerMetadata instead of discoverMetadata
Uses the discoverAuthorizationServerMetadata function from the upstream
TS SDK. This has the advantage of falling back to OIDC discovery
metadata if the OAuth discovery metadata doesn't exist which is the case
with e.g. keycloak.
* chore: import order
---------
Co-authored-by: Danny Avila <danacordially@gmail.com>
* feat: add OAuth servers to conditional rendering logic for MCPPanel in SideNav
* feat: add startup flag check to conditional rendering logic
* fix: correct improper handling of failure state in reinitialize endpoint
* fix: change MCP config components to better handle servers without customUserVars
- removes the subtle reinitialize button from config components of servers without customUserVars or OAuth
- adds a placeholder message for components where servers have no customUserVars configured
* style: swap CustomUserVarsSection and ServerInitializationSection positions
* style: fix coloring for light mode and align more with existing design patterns
* chore: remove extraneous comments
* chore: reorder imports and `isEnabled` from api package
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* fix: render issues in PromptForm by decoupling nested dependencies as a result of @librechat/client components
* fix: MemoryViewer flicker by moving EditMemoryButton and DeleteMemoryButton outside of rendering
* fix: CategorySelector to use DropdownPopup for improved mobile compatibility
* chore: imports
- Replaced HttpsProxyAgent with ProxyAgent from undici for improved proxy handling in DALLE3.js and OpenAIImageTools.js.
- Updated fetchOptions to use dispatcher for proxy configuration.
- Added new test suite for DALLE3 to verify proxy configuration behavior based on environment variables.
ToolsDropdown uses a menu library that passes refs to submenu items. Function components can't receive refs by default though, so we get "Function components cannot be given refs" warnings in the console. React.forwardRef() allows them to properly handle ref forwarding by wrapping the component and attaching the ref to the outer div element.
* ✨ feat: Enhance MCP Connection Status Management
- Introduced new functions to retrieve and manage connection status for multiple MCP servers, including OAuth flow checks and server-specific status retrieval.
- Refactored the MCP connection status endpoints to support both all servers and individual server queries.
- Replaced the old server initialization hook with a new `useMCPServerManager` hook for improved state management and handling of multiple OAuth flows.
- Updated the MCPPanel component to utilize the new context provider for better state handling and UI updates.
- Fixed a number of UI bugs when initializing servers
* 🗣️ i18n: Remove unused strings from translation.json
* refactor: move helper functions out of the route module into mcp service file
* ci: add tests for newly added functions in mcp service file
* fix: memoize setMCPValues to avoid render loop
* 📦 feat: Add Radio component
* 📦 feat: Integrate localization for 'No options available' message in Radio component
* 📦 feat: Bump version to 0.2.0 in package.json
* 📦 feat: Update client package version to 0.2.0 in package-lock.json
* feat: init @librechat/client
* feat: Add common types and interfaces for accessibility, agents, artifacts, assistants, and tools
* feat: Add jotai as a peer dependency
* fix build client package
* feat: cleanup unused types from common/index.ts
- Remove 104 unused type exports from packages/client/src/common/index.ts
- Keep only 7 actually used exports (93% reduction)
- Add cleanup script with enhanced import pattern detection
- Support both named imports and namespace imports (* as t)
- Create automatic backups and comprehensive documentation
- Maintain type safety with build verification
- No breaking changes to existing code
Kept exports:
- TShowToast, Option, OptionWithIcon, DropdownValueSetter
- MentionOption, NotificationSeverity, MenuItemProps
Scripts: cleanup-common-types-safe.js, README-CLEANUP.md
* fix: cleanup
* fix: package; refactor: tsconfig
* feat: add back `recoil`
* fix: move dependencies to peerDependencies in client package
* feat: add @librechat/client as a dependency in package.json and package-lock.json
* feat: update client package configuration and dependencies
- Added new dependencies for Rollup plugins and updated existing ones in package.json and package-lock.json.
- Introduced a new Rollup configuration file for building the client package.
- Refactored build scripts to include a dedicated build command for the client.
- Updated TypeScript configuration for improved module resolution and type declaration output.
- Integrated a Toast component from the client package into the main App component.
* feat: enhance Rollup configuration for client package
- Updated terser plugin settings to preserve directives like 'use client'.
- Added custom warning handler to ignore "use client" directive warnings during the build process.
* chore: rename package/client build script command
* feat: update client package dependencies and Rollup configuration
- Added rollup-plugin-postcss to package.json and updated package-lock.json.
- Enhanced Rollup configuration to include postcss plugin for CSS handling.
- Updated index.ts to export all components from the components directory for better modularity.
* feat: add client package directory to update configuration
- Included the 'client' package directory in the update.js configuration to ensure it is recognized during updates.
* feat: export Toast component in client package
- Added export for the Toast component in index.ts to enhance modularity and accessibility of components.
* feat: /client transition to @librechat/client
* chore: fixed formatting issues
* fix: update peer dependencies in @librechat/client to prevent bundling them
* fix: correct useSprings implementation in SplitText component
* fix: circular dependencies in DataTable
* fix: add remaining peer dependencies and match actual versions previously used in `client/package.json`
* fix: correct frontend:ci script to include client package build
* chore: enhance unused package detection for @librechat/client and improve dependency extraction
* fix: add missing peer dependency for @radix-ui/react-collapsible
* chore: include "packages/client" in unused i18next keys detection
* test: update AgentFooter tests to use document.querySelector for spinner checks
test: mock window.matchMedia in setupTests.js for consistent test environment
* feat: add react-hook-form dependency and update FormInput component to use its types
* chore: linting
* refactor: remove unused defaultSelectedValues prop from MCPSelect and MultiSelect components
* chore: linting
* feat: update GitHub Actions workflow to publish @librechat/client
* chore: update GitHub Actions workflow to install and build data-provider and client dependencies
* chore: add missing @testing-library/react dependency to client package
* chore: update tsconfig.json to exclude additional test files
* chore: fix build issues, resolve latest LC changes
* chore: move MCP components outside of `~/components/ui`
* feat: implement dynamic theme system with environment variable support and Tailwind CSS integration
* chore: remove unnecessary logging of sttExternal and ttsExternal in Speech component
* chore: squashed cleanup commits
chore: move @tanstack/react-virtual to dependencies and remove recoil from package.json
chore: move dependencies to peerDependencies in package.json
feat: update package.json and rollup.config.js to include jotai and enhance bundling configuration
feat: update package.json and rollup.config.js to include jotai and enhance bundling configuration
refactor: reorganize exports in index.ts for improved clarity
refactor: remove unused types and interfaces from common files
refactor: update peer dependencies and improve component typings
- Removed duplicate peer dependencies from package.json and organized them.
- Updated rollup.config.js to disable TypeScript checking during the build process.
- Modified AnimatedTabs component to use React.ReactNode for label and content types, and added TypeScript workarounds for compatibility.
- Enhanced Label and Separator components to accept an optional className prop and improved prop spreading.
- Updated Slider component to include an optional className prop and refined prop handling for better type safety.
refactor: clean up client workflow and update package dependencies
refactor: update package dependencies and improve PostCSS and Rollup configurations
chore: bump version to 0.1.2 in package.json
chore: bump client version to 0.1.2 in package-lock.json
chore: bump client version to 0.1.3 and update dependencies
chore: bump client version to 0.1.4 and update @react-spring dependencies
chore: update package version to 0.1.5 and adjust peer dependencies
- Bump version in package.json from 0.1.4 to 0.1.5.
- Update peer dependency for @tanstack/react-query to allow version 5.0.0.
- Add @tanstack/react-table and @tanstack/react-virtual as dependencies.
- Update various dependencies to their latest compatible versions.
- Simplify postcss.config.js by removing unnecessary options.
- Clean up rollup.config.js by removing ignored PostCSS warnings.
- Update CheckboxButton component to cast icon as React JSX element.
- Adjust Combobox component's class names for better styling.
- Change DropdownPopup component to use React's namespace import.
- Modify InputOTP component to use 'any' type for OTPInputContext.
- Ensure displayLabel and value in ModelParameters are converted to strings.
- Update MultiSearch component's placeholder to ensure it's a string.
- Cast selectIcon in MultiSelect as React JSX element for consistency.
- Update OGDialogTemplate to cast selectText as React JSX element.
- Initialize animationRef in PixelCard with undefined for clarity.
- Add TypeScript ignore comments in Select and SelectDropDown components for Radix UI type conflicts.
- Ensure title in SelectDropDown is a string and adjust rendering of options.
- Update useLocalize hook to cast options as any for compatibility.
refactor: code structure; chore: translations cleanup
chore: remove unused imports and clean up code in NewChat component
refactor: enhance Menu component to support custom render functions for menu items
style: update itemClassName in ToolsDropdown for improved UI consistency
fix: merge conflicts
chore: update @radix-ui/react-accordion to version 1.2.11
* refactor: remove unnecessary TypeScript type assertions in AnimatedTabs, Label, Separator, and Slider components
* feat: enhance theme system with localStorage persistence and new theme atoms
* chore: bump version of @librechat/client to 0.1.7
* chore: fix ci/cd warnings/errors related to linting and unused localization keys
* chore: update dependencies for class-variance-authority, clsx, and match-sorter
* chore: bump @librechat/client to v0.1.8
* feat: add utility colors for theme customization and remove unused tailwindConfig
* v0.1.9
---------
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
* 📦 chore: Remove `keyv` from peerDependencies in package.json and package-lock.json for data-schemas
* refactor: replace traverse import with custom object-traverse utility for better control and error handling during logging
* chore(data-schemas): bump version to 0.0.15 and remove unused dependencies
* refactor: optimize message construction in debugTraverse
* chore: update Node.js version to 20.x in data-schemas workflow
* 🐛 fix: Fix import error causing temporary chats to still display in sidebar
* refactor: Update import path for `getCustomConfig` in Conversation and Message models
* chore: eslint warnings
* ci: add tests for Conversation and Message models
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
- Refactored MCPSelect and MCPSubMenu components to utilize a new custom hook, `useMCPServerManager`, for improved state management and server initialization logic.
- Added functionality to handle simultaneous MCP server initialization requests, including cancellation and user notifications.
- Updated translation files to include new messages for initialization cancellation.
- Improved the configuration dialog handling for MCP servers, streamlining the user experience when managing server settings.
* 📱 refactor: Redis Client Error Logging and Ping only when Ready
* chore: intellisense for warning comment for Keyv Redis client regarding prefix support
* ✨ feat: Add support for forced in-memory cache keys configuration
* refactor: Update cache keys to use uppercase constants and moved cache for `librechat.yaml` into its own cache namespace (STATIC_CONFIG) and with a more descriptive key (LIBRECHAT_YAML_CONFIG)
* refactor: prefer `agent.model` (user-facing value) over `agent.model_parameters.model` to ensure Azure mapping
* chore: update @librechat/agents to version 2.4.68 to use new default title prompt for completion title method
* chore: update version to v0.7.9 across all relevant files
* 🔧 chore: bump @librechat/api version to 1.2.9
* 🔧 chore: update @librechat/data-schemas version to 0.0.12
* 🔧 chore: bump librechat-data-provider version to 0.7.902
- Updated StreamableHTTPOptionsSchema to accept "http" alongside "streamable-http".
- Enhanced isStreamableHTTPOptions function to handle both types and validate URLs accordingly.
- Added tests to ensure correct processing of "http" type options and rejection of websocket URLs.
* ✨ feat: Add connection status endpoint for MCP servers
- Implemented a new endpoint to retrieve the connection status of all MCP servers without disconnecting idle connections.
- Enhanced MCPManager class with a method to get all user-specific connections.
* feat: add silencer arg to loadCustomConfig function to conditionally print config details
- Modified loadCustomConfig to accept a printConfig parameter that allows me to prevent the entire custom config being printed every time it is called
* fix: new status endpoint actually works now, changes to manager.ts to support it
- Updated the connection status endpoint to utilize Maps for app and user connections, rather than incorrectly treating them as objects.
- Introduced a new method + variable in MCPManager to track servers requiring OAuth discovered at startup.
- Stopped OAuth flow from continuing once detected during startup for a new connection
* refactor: Remove hasAuthConfig since we can get that on the frontend without needing to use the endpoint
* feat: Add MCP connection status query and query key for new endpoint
- Introduced a new query hook `useMCPConnectionStatusQuery` to fetch the connection status of MCP servers.
- Added request in data-service
- Defined the API endpoint for retrieving MCP connection status in api-endpoints.ts.
- Defined new types for MCP connection status responses in the types module.
- Added mcpConnectionStatus key
* feat: Enhance MCPSelect component with connection status and server configuration
- Added connection status handling for MCP servers using the new `useMCPConnectionStatusQuery` hook.
- Implemented logic to display appropriate status icons based on connection state and authentication configuration.
- Updated the server selection logic to utilize configured MCP servers from the startup configuration.
- Refactored the rendering of configuration buttons and status indicators for improved user interaction.
* refactor: move MCPConfigDialog to its own MCP subdir in ui and update import
* refactor: silence loadCustomConfig in status endpoint
* feat: Add optional pluginKey parameter to getUserPluginAuthValue
* feat: Add MCP authentication values endpoint and related queries
- Implemented a new endpoint to check authentication value flags for specific MCP servers, returning boolean indicators for each custom user variable.
- Added a corresponding query hook `useMCPAuthValuesQuery` to fetch authentication values from the frontend.
- Defined the API endpoint for retrieving MCP authentication values in api-endpoints.ts.
- Updated data-service to include a method for fetching MCP authentication values.
- Introduced new types for MCP authentication values responses in the types module.
- Added a new query key for MCP authentication values.
* feat: Localize MCPSelect component status labels and aria attributes
- Updated the MCPSelect component to use localized strings for connection status labels and aria attributes, enhancing accessibility and internationalization support.
- Added new translation keys for various connection states in the translation.json file.
* feat: Implement filtered MCP values selection based on connection status in MCPSelect
- Added a new `filteredSetMCPValues` function to ensure only connected servers are selectable in the MCPSelect component.
- Updated the rendering logic to visually indicate the connection status of servers by adjusting opacity.
- Enhanced accessibility by localizing the aria-label for the configuration button.
* feat: Add CustomUserVarsSection component for managing user variables
- Introduced a new `CustomUserVarsSection` component to allow users to configure custom variables for MCP servers.
- Integrated localization for user interface elements and added new translation keys for variable management.
- Added functionality to save and revoke user variables, with visual indicators for set/unset states.
* feat: Enhance MCPSelect and MCPConfigDialog with improved state management and UI updates
- Integrated `useQueryClient` to refetch queries for tools, authentication values, and connection status upon successful plugin updates in MCPSelect.
- Simplified plugin key handling by directly using the formatted plugin key in save and revoke operations.
- Updated MCPConfigDialog to include server status indicators and improved dialog content structure for better user experience.
- Added new translation key for active status in the localization files.
* feat: Enhance MCPConfigDialog with dynamic server status badges and localization updates
- Added a helper function to render status badges based on the connection state of the MCP server, improving user feedback on connection status.
- Updated the localization files to include new translation keys for connection states such as "Connecting" and "Offline".
- Refactored the dialog to utilize the new status rendering function for better code organization and readability.
* feat: Implement OAuth handling and server initialization in MCP reinitialize flow
- Added OAuth handling to the MCP reinitialize endpoint, allowing the server to capture and return OAuth URLs when required.
- Updated the MCPConfigDialog to include a new ServerInitializationSection for managing server initialization and OAuth flow.
- Enhanced the user experience by providing feedback on server status and OAuth requirements through localized messages.
- Introduced new translation keys for OAuth-related messages in the localization files.
- Refactored the MCPSelect component to remove unused authentication configuration props.
* feat: Make OAuth actually work / update after OAuth link authorized
- Improved the handling of OAuth flows in the MCP reinitialize process, allowing for immediate return when OAuth is initiated.
- Updated the UserController to extract server names from plugin keys for better logging and connection management.
- Enhanced the MCPSelect component to reflect authentication status based on OAuth requirements.
- Implemented polling for OAuth completion in the ServerInitializationSection to improve user feedback during the connection process.
- Refactored MCPManager to support new OAuth flow initiation logic and connection handling.
* refactor: Simplify MCPPanel component and enhance server status display
- Removed unused imports and state management related to user plugins and server reinitialization.
- Integrated connection status handling directly into the MCPPanel for improved user feedback.
- Updated the rendering logic to display server connection states with visual indicators.
- Refactored the editing view to utilize new components for server initialization and custom user variables management.
* chore: remove comments
* chore: remove unused translation key for MCP panel
* refactor: Rename returnOnOAuthInitiated to returnOnOAuth for clarity
* refactor: attempt initialize on server click
* feat: add cancel OAuth flow functionality and related UI updates
* refactor: move server status icon logic into its own component
* chore: remove old localization strings (makes more sense for icon labels to just use configure stirng since thats where it leads to)
* fix: fix accessibility issues with MCPSelect
* fix: add missing save/revoke mutation logic to MCPPanel
* styling: add margin to checkmark in MultiSelect
* fix: add back in customUserVars check to hide gear config icon for servers without customUserVars
---------
Co-authored-by: Dustin Healy <dustinhealy1@gmail.com>
Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>
* fix: resource parameter undefined TypeError in log
* chore: Add missing FILE_SEARCH permission type to IRole interface
* chore: Bump version of @librechat/data-schemas to 0.0.11
* fix: Ensure resource is defined and handle potential null values in OAuth flow
* ✨ feat: Add MCP Reinitialization to MCPPanel
- Refactored tool caching to include user-specific tools in various service files.
- Refactored MCPManager class for clarity
- Added a new endpoint for reinitializing MCP servers, allowing for dynamic updates of server configurations.
- Enhanced the MCPPanel component to support server reinitialization with user feedback.
* 🔃 refactor: Simplify Plugin Deduplication and Clear Cache Post-MCP Initialization
- Replaced manual deduplication of tools with the dedicated `filterUniquePlugins` function for improved readability.
- Added back cache clearing for tools after MCP initialization to ensure fresh data is used.
- Removed unused exports from `PluginController.js` to clean up the codebase.
* 🏗️ refactor: Extract reasoning key logic into separate function
* refactor: Ensure `overrideProvider` is always defined in `getProviderConfig` result, and only used in `initializeAgent` if different from `agent.provider`
* feat: new title configuration options across services
- titlePrompt
- titleEndpoint
- titlePromptTemplate
- new "completion" titleMethod (new default)
* chore: update @librechat/agents and conform openai version to prevent SDK errors
* chore: add form-data package as a dependency and override to v4.0.4 to address CVE-2025-7783
* feat: add support for 'all' endpoint configuration in AppService and corresponding tests
* refactor: replace HttpsProxyAgent with ProxyAgent from undici for improved proxy handling in assistant initialization
* chore: update frontend review workflow to limit package paths to data-provider
* chore: update backend review workflow to include all package paths
* refactor: Move draft-related utilities to a new `drafts.ts` file
* refactor: auto-save draft logic to use new get/set functions
* fix: Ensure `getDraft` properly decodes stored draft values
* fix: Handle edge case where stream is cancelled before any response, which creates a blank page
* 📦 chore: bump `compression` from 1.7.4 to 1.8.1
* chore: bump `express-session` to v1.18.2
* chore: update `connect-redis` from v7.1.0 to v8.1.0
* chore: update import for `connect-redis` to use named export due to v8.0.0 breaking change
- Added firecrawlOptions configuration field to librechat.yaml
- Refactored web.ts to live in packages/api rather than data-provider
- Updated imports from web.ts to reflect new location
- Added firecrawlOptions to FirecrawlConfig interface
- Added firecrawlOptions to authResult of loadWebSearchAuth so it gets properly passed to agents to be built into firecrawl payload
- Added tests for firecrawlOptions to web.spec.ts
- Updated the logic to auto-enable the Responses API when web search is enabled, specifically for OpenAI, Azure, and Custom endpoints.
- Added import for EModelEndpoint to facilitate endpoint compatibility checks.
* wip: first pass content strings
* 📦 chore: update @langchain/core to v0.3.62 for data-provider dev dep.
* 📦 chore: bump @langchain/core to v0.3.62 for api dep.
* 📦 chore: move @langchain/core to peerDependencies in package.json and package-lock.json
* fix: update formatContentStrings to create HumanMessage directly from formatted content
* chore: import order
* 🕒 refactor: Use Legacy Content for Custom Endpoints to Improve Compatibility
- Also applies to Azure serverless endpoints from AI Foundry
* chore: move useLegacyContent condition before early return
* fix: Ensure useLegacyContent is set only when options are available
* 🌊 feat: Add Disable Streaming Option in Configuration
- Introduced a new setting to disable streaming responses in openAI, Azure, and custom endpoint parameter panels.
- Updated translation files to include labels and descriptions for the disable streaming feature.
- Modified relevant schemas and parameter settings to support the new disable streaming functionality.
* 🔧 fix: disableStreaming state not persisting when returning to a conversation
- Added disableStreaming field to the IPreset interface and conversationPreset.
- Moved toggles and sliders around for nicer left-right UI split in parameters panel.
- Removed old reference to 'grounding' ub conversationPreset (now web_search) and added web_search to IPreset.
* fix: Add `isRegenerate` flag to chat payload to avoid saving temporary response IDs
* fix: Remove unused `isResubmission` flag
* ci: Add tests for responseMessageId regeneration logic in BaseClient
* Fix scanning of the uploaded images folder on startup
* Re-write tests to pass linting
* Disable image output gzip scan by default
* Add `ENABLE_IMAGE_OUTPUT_GZIP_SCAN` to `.env.example`
Implements permission validation before allowing agent avatar uploads. Only admins, the agent's author, or users of collaborative agents can modify avatars. Also improves error handling by checking for agent existence upfront and simplifies avatar update logic.
Co-authored-by: Sai Nihas <sai.nihas@shopify.com>
- Added Constants import in PluginController for better organization.
- Renamed cachedTools to cachedToolsArray for clarity in PluginController.
- Ensured getCachedTools returns an empty object if no tools are found.
- Cleared tools array cache after MCP initialization in initializeMCP for consistency.
* fix: false flagging object as empty object when it has `additionalProperties` field
* 🔧 fix: Implement $ref resolution in JSON Schema handling
* 🔧 fix: Resolve JSON Schema references before conversion to Zod
* chore: move zod logic packages/api
* 🔧 fix: Handle optional arguments in `useParseArgs` and improve tool call condition
* chore: Remove math plugins from `MarkdownLite`
* ✨ feat: Add Error Boundary to Markdown Component for Enhanced Error Handling
- Introduced `MarkdownErrorBoundary` to catch and display errors during Markdown rendering.
- Updated the `Markdown` component to utilize the new error boundary, improving user experience by handling rendering issues gracefully.
* Revert "chore: Remove math plugins from `MarkdownLite`"
This reverts commit d393099d52.
* ✨ feat: Introduce MarkdownErrorBoundary for improved error handling in Markdown components
* refactor: include most markdown elements in error boundary fallback, aside from problematic plugins
* feat: Enhance loadServiceKey to support stringified JSON input
* chore: Update GOOGLE_SERVICE_KEY_FILE_PATH to GOOGLE_SERVICE_KEY_FILE for consistency
- Introduced new violation scores for TTS, STT, Fork, Import, and File Upload actions in the .env.example file.
- Updated logViolation function to accept a score parameter, allowing for dynamic severity levels based on the action type.
- Modified limiters for Fork, Import, Message, STT, TTS, Tool Call, and File Upload to utilize the new violation scores when logging violations.
* Updated the PATCH /memories/:key endpoint to allow key changes while ensuring no duplicate keys exist.
* Improved error handling in MemoryCreateDialog and MemoryEditDialog for key validation and duplication scenarios.
* Added a new translation for memory key validation error in translation.json.
* 🔧 refactor: Improve Google Key Handling in `loadAsyncEndpoints`
- Enhanced logic to check if GOOGLE_KEY is provided, including user-provided checks.
- Updated service key loading mechanism to only attempt loading if GOOGLE_KEY is not provided.
- Added error logging for service key loading failures.
* 🔧 refactor: Enhance service key loading logic in `initializeClient`
* chore: bump @librechat/agents to v2.4.56
* chore: bump @librechat/api version to 1.2.6
* fix: initialize reasoningKey to 'reasoning_content' in createRun function
- Updated the Google configuration and related schemas to replace 'grounding' with 'web_search' for consistency.
- Adjusted the logic in the getGoogleConfig function to reflect the new naming convention.
- Ensured all references in parameter settings and conversation schemas are updated accordingly.
* chore: bump @librechat/agents to ^2.4.54 for anthropic web search support
* WIP: hardcoded web search tool usage
* feat: Implement web search functionality in Anthropic integration
- Updated parameters panel to include web search for anthropic models.
- Updated necessary schemas to accomodate toggle functionality
* chore: Set default web search option to false in anthropicSettings
* refactor: Rename webSearch to web_search for consistency across settings and schemas
* chore: bump @librechat/agents to v2.4.55
---------
Co-authored-by: Dustin Healy <dustinhealy1@gmail.com>
* 🔍 feat: Add SearXNG Web Search support and enhance ApiKeyDialog
- Updated WebSearch component to include authentication data for web search functionality so it won't show badge after being revoked
- Refactored ApiKeyDialog to streamline provider, scraper, and reranker selection with new InputSection component
- Added support for SearXNG as a search provider and updated translation files accordingly
- Improved form handling in useAuthSearchTool to accommodate new API keys and URLs
* 📜 chore: remove unused i18next key
* 📦 chore: address comments (swap API key and URL fields in SearXNG config, change input fields to 'text' from 'password'
* 📦 chore: make URL fields go first in ApiKeyDialog
* chore: bump @librechat/agents to v2.4.52
* ci: update webSearch configuration to include searxng fields in AppService.spec.js
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* chore: Improve error logging for fetching conversations, and use new TS packages for utils
* feat: Implement fork limiters for conversation forking requests
* chore: error message for conversation index deletion to clarify syncing behavior
* feat: Enhance error handling for forking with rate limit message
* refactor: Add validation schemas for agent creation and updates
* fix: Ensure author validation is applied in correct order for agent update handler
* ci: Add comprehensive unit tests for agent creation and update handlers with mass assignment protection
* fix: add missing web_search tool in system tools configuration
* feat: add useAgentCapabilities hook to manage agent capabilities
* refactor: move agents and endpoints configuration to AgentPanel context provider
* refactor: implement useGetAgentsConfig hook for consolidated agents and endpoints management
* refactor: enhance ToolsDropdown to utilize agent capabilities and streamline dropdown item rendering
* chore: reorder return values in useAgentCapabilities for improved clarity
* refactor: enhance agent capabilities handling in AttachFileMenu and update file handling logic to allow capabilities to be used for non-agents endpoints
* 🔧 fix: Update type annotations in useEventHandlers for better type safety
* 🔧 refactor: `useToolToggle` for improved localStorage synchronization and allow string/falsy values for setting to storage
* ✨ feat: Implement Artifacts badge to BadgeRow with toggle options and UI components
- Added Artifacts component to manage artifacts state and options.
- Introduced ArtifactsSubMenu for additional settings related to artifacts.
- Integrated artifacts functionality into BadgeRow and ToolsDropdown components.
- Updated localStorage handling for artifacts state persistence.
- Enhanced localization for artifacts-related strings in translation files.
- Refactored Agent model to include artifacts in the ephemeral agent response.
* fix: set ephemeral agent state for conversation on finalization
* chore: remove beta settings dialog tab
* refactor: improve Ephemeral Agent statefulness
* fix: update setValue parameter to use 'value' instead of 'isChecked' in CheckboxButton
* refactor: update color classes for Artifact toggle and order of dropdown components
* chore: remove unused i18n localization
* 🔍 feat: Introduce Web Search Functionality for OpenAI API
- Added a new web_search parameter to enable web search capabilities in the OpenAI configuration.
- Updated the DynamicSlider component for improved styling.
- Enhanced the useSetIndexOptions hook to auto-enable the Responses API when web search is activated.
- Modified relevant schemas, types, and translation files to support the new web search feature.
* chore: remove comments
* refactor: tool handling in initializeAgent for better clarity and functionality and reflection of openai features
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* ✨ feat: Add Google Search Grounding Feature and Update Agent Tool Initialization
- Introduced a new grounding option in the Google configuration to enable real-time web search results.
- Updated the agent initialization to concatenate additional tools from options.
- Enhanced translation files to include descriptions for the new grounding feature.
- Modified relevant schemas and parameter settings to support the grounding functionality.
* 🔑 chore: Update @librechat/agents dependency to version 2.4.50
* ✅ fix: Ensure tools array is initialized before concatenation in initializeAgent function
* chore: Update version of librechat-data-provider to 0.7.899 and add GOOGLE_TOOL_CONFLICT error type
* fix: Adjust label class for better text wrapping in DynamicSwitch component
* fix: Handle Google tool conflict error and update error messages in translation
* fix: Restore grounding setting in googleCol2 configuration
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🐛 fix: Enhance provider validation and error handling in getProviderConfig function
* WIP: edit text part
* refactor: Allow updating of both TEXT and THINK content types in message updates
* WIP: first pass, save & submit
* chore: remove legacy generation user message field
* feat: merge edited content
* fix: update placeholder and description for bedrock setting
* fix: remove unsupported warning message for AI resubmission
* chore: update @librechat/agents to v2.4.47
* WIP: temporary auto-toggle responses api for o1/o3-pro
* feat: Enable Responses API for OpenAI models
- Updated the OpenAI client initialization to check for the useResponsesApi parameter in model options.
- Added translations for enabling the Responses API in the UI.
- Introduced useResponsesApi parameter in data provider settings and schemas.
- Updated relevant schemas to include useResponsesApi for conversation and preset configurations.
* refactor: Remove useResponsesApi check from OpenAI client initialization and update translation for Responses API
- Removed the check for useResponsesApi in the OpenAI client initialization.
- Updated the translation for enabling the Responses API to clarify its functionality.
* chore: update @librechat/agents dependency to version 2.4.48
* chore: update @librechat/agents dependency to version 2.4.49
* chore: linting
* chore: linting
* feat: Enhance DynamicSlider and validation for enumMappings
- Added support for enumMappings in DynamicSlider to display values correctly based on enum settings.
- Implemented validation for enumMappings in the generate function to ensure all options have corresponding mappings.
- Added tests for handling empty string options and incomplete enumMappings in the generate.spec.ts file.
* feat: Enhance DynamicSlider localization support
- Added localization handling for mapped values in DynamicSlider when using enumMappings.
- Updated the logic to check if the mapped value is a localization key and return the localized string if applicable.
- Adjusted dependencies in useCallback hooks to include localize for proper functionality.
* feat: Add reasoning summary and effort options to OpenAI configuration and UI
* feat: Add enumMappings for ImageDetail options in parameter settings
* style: Improve styling for DynamicSlider component labels and inputs
* chore: Update reasoning effort description and parameter order for OpenAI params
---------
Co-authored-by: Dustin Healy <dustinhealy1@gmail.com>
* Implemented new uploadGoogleVertexMistralOCR function for processing OCR using Google Vertex AI.
* Added vertexMistralOCRStrategy to handle file uploads.
* Updated FileSources and OCRStrategy enums to include vertexai_mistral_ocr.
* Introduced helper functions for JWT creation and Google service account configuration loading.
* refactor: access control logic to TypeScript
* chore: Change EndpointURLs to a constant object for improved type safety
* 🐛 fix: Enhance agent access control by adding skipAgentCheck functionality
* 🐛 fix: Add endpointFileConfig prop to AttachFileMenu and update file handling logic
* 🐛 fix: Update tool handling logic to support optional groupedTools and improve null checks, add dedicated tool dialog for Assistants
* chore: Export Accordion component from UI index for improved modularity
* feat: Add ActivePanelContext for managing active panel state across components
* chore: Replace string IDs with EModelEndpoint constants for assistants and agents in useSideNavLinks
* fix: Integrate access checks for agent creation and deletion routes in actions.js
* feat: Add configurable retention period for temporary chats
* Addressing eslint errors
* Fix: failing test due to missing registration
* Update: variable name and use hours instead of days for chat retention
* Addressing comments
* chore: fix import order in Conversation.js
* chore: import order in Message.js
* chore: fix import order in config.ts
* chore: move common methods to packages/api to reduce potential for circular dependencies
* refactor: update temp chat retention config type to Partial<TCustomConfig>
* refactor: remove unused config variable from AppService and update loadCustomConfig tests with logger mock
* refactor: handle model undefined edge case by moving Session model initialization inside methods
---------
Co-authored-by: Rakshit Tiwari <rak1729e@gmail.com>
* feat: support thinking budget parameter for Gemini 2.5 series (#6949, #7542)
https://ai.google.dev/gemini-api/docs/thinking#set-budget
* refactor: update thinking budget minimum value to -1 for dynamic thinking
- see: https://ai.google.dev/gemini-api/docs/thinking#set-budget
* chore: bump @librechat/agents to v2.4.43
* refactor: rename LLMConfigOptions to OpenAIConfigOptions for clarity and consistency
- Updated type definitions and references in initialize.ts, llm.ts, and openai.ts to reflect the new naming convention.
- Ensured that the OpenAI configuration options are consistently used across the relevant files.
* refactor: port Google LLM methods to TypeScript Package
* chore: update @librechat/agents version to 2.4.43 in package-lock.json and package.json
* refactor: update thinking budget description for clarity and adjust placeholder in parameter settings
* refactor: enhance googleSettings default value for thinking budget to support dynamic adjustment
* chore: update @librechat/agents to v2.4.44 for Vertex Dynamic Thinking workaround
* refactor: rename google config function, update `createRun` types, use `reasoning` as `reasoningKey` for Google
* refactor: simplify placeholder handling in DynamicInput component
* refactor: enhance thinking budget description for clarity and allow automatic decision by setting to "-1"
* refactor: update text styling in OptionHover component for improved readability
* chore: update @librechat/agents dependency to v2.4.46 in package.json and package-lock.json
* chore: update @librechat/api version to 1.2.5 in package.json and package-lock.json
* refactor: enhance `clientOptions` handling by filtering `omitTitleOptions`, add `json` field for Google models
---------
Co-authored-by: ciffelia <15273128+ciffelia@users.noreply.github.com>
* Enhanced existing tests for the `resolveHeaders` function to cover all user field placeholders and messy scenarios.
* Added basic integration tests for custom endpoints initialization file
* 🔧 fix: enhance client options handling in AgentClient and set default recursion limit
- Updated the recursion limit to default to 25 if not specified in agentsEConfig.
- Enhanced client options in AgentClient to include model parameters such as apiKey and anthropicApiUrl from agentModelParams.
- Updated requestOptions in the anthropic endpoint to use reverseProxyUrl as anthropicApiUrl.
* Enhance LLM configuration tests with edge case handling
* chore add return type annotation for getCustomEndpointConfig function
* fix: update modelOptions handling to use optional chaining and default to empty object in multiple endpoint initializations
* chore: update @librechat/agents to version 2.4.42
* refactor: streamline agent endpoint configuration and enhance client options handling for title generations
- Introduced a new `getProviderConfig` function to centralize provider configuration logic.
- Updated `AgentClient` to utilize the new provider configuration, improving clarity and maintainability.
- Removed redundant code related to endpoint initialization and model parameter handling.
- Enhanced error logging for missing endpoint configurations.
* fix: add abort handling for image generation and editing in OpenAIImageTools
* ci: enhance getLLMConfig tests to verify fetchOptions and dispatcher properties
* fix: use optional chaining for endpointOption properties in getOptions
* fix: increase title generation timeout from 25s to 45s, pass `endpointOption` to `getOptions`
* fix: update file filtering logic in getToolFilesByIds to ensure text field is properly checked
* fix: add error handling for empty OCR results in uploadMistralOCR and uploadAzureMistralOCR
* fix: enhance error handling in file upload to include 'No OCR result' message
* chore: update error messages in uploadMistralOCR and uploadAzureMistralOCR
* fix: enhance filtering logic in getToolFilesByIds to include context checks for OCR resources to only include files directly attached to agent
---------
Co-authored-by: Matt Burnett <matt.burnett@shopify.com>
* 🔧 fix: Adjust typography and border styles for improved readability in markdown components
* 🔧 fix: Enhance code block styling in markdown for better visibility and consistency
* 🔧 fix: Adjust margins and line heights for improved readability in markdown elements
* 🔧 fix: Adjust spacing for horizontal rules in markdown for improved consistency
* 🔧 fix: Refactor DialogImage component for improved quality styling and layout consistency
* 🔧 fix: Enhance zoom and pan functionality in DialogImage component with improved controls and user experience
* 🔧 fix: Improve zoom and pan functionality in DialogImage component with enhanced controls and reset zoom feature
* new env variable for mcp label
* 🔄 refactor: Update MCPSelect placeholderText to draw from interface section of librechat.yaml rather than .env
* 🧹 chore: extract mcpServers schema for better maintainability
* 🔄 refactor: Update MCPSelect and useMCPSelect to utilize TPlugin type for better type consistency
* 🔄 refactor: Pass placeholder from startupConfig to MCPSubMenu for improved localization
* 🔄 refactor: Integrate startupConfig into BadgeRowContext and related components for enhanced configuration management
---------
Co-authored-by: mwbrandao <mariana.brandao@nos.pt>
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🔧 refactor: move `processMCPEnv` from `librechat-data-provider` and move to `@librechat/api`
* 🔧 refactor: Update resolveHeaders import paths
* 🔧 refactor: Enhance resolveHeaders to support user and custom variables
- Updated resolveHeaders function to accept user and custom user variables for placeholder replacement.
- Modified header resolution in multiple client and controller files to utilize the enhanced resolveHeaders functionality.
- Added comprehensive tests for resolveHeaders to ensure correct processing of user and custom variables.
* 🔧 fix: Update user ID placeholder processing in env.ts
* 🔧 fix: Remove arguments passing this.user rather than req.user
- Updated multiple client and controller files to call resolveHeaders without the user parameter
* 🔧 refactor: Enhance processUserPlaceholders to be more readable / less nested
* 🔧 refactor: Update processUserPlaceholders to pass all tests in mpc.spec.ts and env.spec.ts
* chore: remove legacy ChatGPTClient
* chore: remove LLM initialization code
* chore: initial deprecation removal of `gptPlugins`
* chore: remove cohere-ai dependency from package.json and package-lock.json
* chore: update brace-expansion to version 2.0.2 and add license information
* chore: remove PluginsClient test file
* chore: remove legacy
* ci: remove deprecated sendMessage/getCompletion/chatCompletion tests
---------
Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>
* refactor(buildEndpointOption): Improve error logging in middleware, consolidate `isAgents` builder logic, remove adding `modelsConfig` to `endpointOption`
* refactor: parameter extraction and organization in agent services, minimize redundancy of shared fields across objects, make clear distinction of parameters processed uniquely by LibreChat vs LLM Provider Configs
* refactor(createPayload): streamline all endpoints to agent route
* fix: add `modelLabel` to response sender options for agent initialization
* chore: correct log message context in EditController abort controller cleanup
* chore: remove unused abortRequest hook
* chore: remove unused addToCache module and its dependencies
* refactor: remove AskController and related routes, update endpoint URLs (now all streamlined to agents route)
* chore: remove unused bedrock route and its related imports
* refactor: simplify response sender logic for Google endpoint
* chore: add `modelDisplayLabel` handling for agents endpoint
* feat: add file search capability to ephemeral agents, update code interpreter selection based of file upload, consolidate main upload menu for all endpoints
* feat: implement useToolToggle hook for managing tool toggle state, refactor CodeInterpreter and WebSearch components to utilize new hook
* feat: add ToolsDropdown component to BadgeRow for enhanced tool options
* feat: introduce BadgeRowContext and BadgeRowProvider for managing conversation state, refactor related components to utilize context
* feat: implement useMCPSelect hook for managing MCP selection state, refactor MCPSelect component to utilize new hook
* feat: enhance BadgeRowContext with MCPSelect and tool toggle functionality, refactor related components to utilize updated context and hooks
* refactor: streamline useToolToggle hook by integrating setEphemeralAgent directly into toggle logic and removing redundant setValue function
* refactor: consolidate codeApiKeyForm and searchApiKeyForm from CodeInterpreter and WebSearch to utilize new context properties
* refactor: update CheckboxButton to support controlled state and enhance ToolsDropdown with permission-based toggles for web search and code interpreter
* refactor: conditionally render CheckboxButton in CodeInterpreter and WebSearch components for improved UI responsiveness
* chore: add jotai dependency to package.json and package-lock.json
* chore: update brace-expansion package to version 2.0.2 in package-lock.json due to CVE-2025-5889
* Revert "chore: add jotai dependency to package.json and package-lock.json"
This reverts commit 69b6997396.
* refactor: add pinning functionality to CodeInterpreter and WebSearch components, and enhance ToolsDropdown with pin toggle for web search and code interpreter
* chore: move MCPIcon to correct location, remove duplicate
* fix: update MCP import to use type-only import from librechat-data-provider
* feat: implement MCPSubMenu component and integrate pinning functionality into ToolsDropdown
* fix: cycling to submenu by using parent menu context
* feat: add FileSearch component and integrate it into BadgeRow and ToolsDropdown
* chore: import order
* chore: remove agent specific logic that would block functionality for streamlined endpoints
* chore: linting for `createContextHandlers`
* chore: ensure ToolsDropdown doesn't show up for agents
* chore: ensure tool resource is selected when dragged to UI
* chore: update file search behavior to simulate legacy functionality
* feat: ToolDialogs with multiple trigger references, add settings to tool dropdown
* refactor: simplify web search and code interpreter settings checks
* chore: simplify local storage key for pinned state in useToolToggle
* refactor: reinstate agent check in AttachFileChat component, as individual providers will ahve different file configurations
* ci: increase timeout for MongoDB connection in Agent tests
* chore: update peer dependency for @librechat/agents to version 2.4.41
* 🔧 chore: proxy handling in OpenAI endpoint to use undici
* 🔧 chore: update @anthropic-ai/sdk to version 0.52.0 and refactor proxy handling to use undici
* 🔧 chore: update globIgnores in vite.config.ts to exclude index.html from caching
* 🔧 ci: update proxy handling in getLLMConfig to use fetchOptions and ProxyAgent
* 🔧 chore: refactor proxy handling in Anthropic and OpenAI clients to use fetchOptions
* refactor: agent initialization to streamline model parameters and resendFiles handling
* chore: update @google/generative-ai to version 0.24.0
* fix: Use mutable version of conversation in useChatFunctions
* fix: Use cloneDeep for conversation in useChatFunctions to ensure immutability
---------
Co-authored-by: lucioperca <lucioperca@users.noreply.github.com>
* 🗝️ feat: Per-User Credentials for MCP Servers
chore: add aider to gitignore
feat: fill custom variables to MCP server
feat: replace placeholders with custom user MCP variables
feat: handle MCP install/uninstall (uses pluginauths)
feat: add MCP custom variables dialog to MCPSelect
feat: add MCP custom variables dialog to the side panel
feat: do not require to fill MCP credentials for in tools dialog
feat: add translations keys (en+cs) for custom MCP variables
fix: handle LIBRECHAT_USER_ID correctly during MCP var replacement
style: remove unused MCP translation keys
style: fix eslint for MCP custom vars
chore: move aider gitignore to AI section
* feat: Add Plugin Authentication Methods to data-schemas
* refactor: Replace PluginAuth model methods with new utility functions for improved code organization and maintainability
* refactor: Move IPluginAuth interface to types directory for better organization and update pluginAuth schema to use the new import
* refactor: Remove unused getUsersPluginsAuthValuesMap function and streamline PluginService.js; add new getPluginAuthMap function for improved plugin authentication handling
* chore: fix typing for optional tools property with GenericTool[] type
* chore: update librechat-data-provider version to 0.7.88
* refactor: optimize getUserMCPAuthMap function by reducing variable usage and improving server key collection logic
* refactor: streamline MCP tool creation by removing customUserVars parameter and enhancing user-specific authentication handling to avoid closure encapsulation
* refactor: extract processSingleValue function to streamline MCP environment variable processing and enhance readability
* refactor: enhance MCP tool processing logic by simplifying conditions and improving authentication handling for custom user variables
* ci: fix action tests
* chore: fix imports, remove comments
* chore: remove non-english translations
* fix: remove newline at end of translation.json file
---------
Co-authored-by: Aleš Kůtek <kutekales@gmail.com>
* ✨ feat: Enhance Agent Panel with Tool Grouping
* 🧰 feat: Added support for grouping tools in the Agent Panel, allowing for better organization and management of related tools.
* 💡 feat: Added hovercards for tools belonging to a group which display their tool descriptions when their help icon is hovered over.
* 🧹 chore: Updated the AgentPanelContext to include grouped tools and their metadata.
* 🔨 refactor: Refactored AgentConfig and AgentTool components to utilize the new tool structure and enhance rendering logic.
* 🔍 feat: Improved the ToolSelectDialog to filter and display tools based on user input, including searching for tools within a group, and limits viewport height to prevent overflowing vertically on smaller screens.
This update enhances the overall functionality and usability of the Agent Panel, making it easier for users to interact with tools.
* Potential fix for code scanning alert no. 6217: Disallow unused variables
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* fix: Agent tool type mismatches
* fix: accessibility issues and mcp tool overflow issue
* fix: enhance keyboard accessibility and prevent event propagation in AgentTool
* chore: WIP types
* chore: address comments and fix accordian collapse bug
---------
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor: Markdown LaTeX processing
- Added micromark-extension-llm-math as a dependency in package.json and package-lock.json.
- Updated Vite configuration to alias micromark-extension-math.
- Modified Markdown components to use singleDollarTextMath: false for improved LaTeX rendering.
- Refactored latex utility functions to enhance LaTeX processing and escaping mechanisms.
* chore: linting of `EditTextPart`
* fix: handle key up to initiate edit of latest user message by adding id prop to Edit Message HoverButton
* chore: linting in Artifact component
* refactor: enhance LaTeX preprocessing functionality
- Updated `preprocessLaTeX` to improve handling of currency and LaTeX expressions.
- Introduced optimized regex patterns for better performance.
- Added support for escaping mhchem commands and handling code blocks.
- Enhanced tests for various LaTeX scenarios, including currency and special characters.
- Refactored existing tests to align with new preprocessing logic.
* chore: filter out false positives in unused packages workflow
- Added a grep command to exclude the micromark-extension-llm-math package from the list of unused dependencies in the GitHub Actions workflow.
* fix: Add null check for SelectedTTS in MessageAudio component to prevent rendering issues
* fix: image download browser compatibility with error handling and fallback mechanism
- Updated the downloadImage function to use fetch for improved reliability and added error handling.
- Implemented a fallback to the original download method in case of fetch failure.
- Ensured the download link uses a blob URL for better compatibility with various image types.
* chore: Update @modelcontextprotocol/sdk to version 1.12.3 in package.json and package-lock.json
- Bump version of @modelcontextprotocol/sdk to 1.12.3 to incorporate recent updates.
- Update dependencies for ajv and cross-spawn to their latest versions.
- Add ajv as a new dependency in the sdk module.
- Include json-schema-traverse as a new dependency in the sdk module.
* feat: @librechat/auth
* feat: Add crypto module exports to auth package
- Introduced a new crypto module by creating index.ts in the crypto directory.
- Updated the main index.ts of the auth package to export from the new crypto module.
* feat: Update package dependencies and build scripts for auth package
- Added @librechat/auth as a dependency in package.json and package-lock.json.
- Updated build scripts to include the auth package in both frontend and bun build processes.
- Removed unused mongoose and openid-client dependencies from package-lock.json for cleaner dependency management.
* refactor: Migrate crypto utility functions to @librechat/auth
- Replaced local crypto utility imports with the new @librechat/auth package across multiple files.
- Removed the obsolete crypto.js file and its exports.
- Updated relevant services and models to utilize the new encryption and decryption methods from @librechat/auth.
* feat: Enhance OAuth token handling and update dependencies in auth package
* chore: Remove Token model and TokenService due to restructuring of OAuth handling
- Deleted the Token.js model and TokenService.js, which were responsible for managing OAuth tokens.
- This change is part of a broader refactor to streamline OAuth token management and improve code organization.
* refactor: imports from '@librechat/auth' to '@librechat/api' and add OAuth token handling functionality
* refactor: Simplify logger usage in MCP and FlowStateManager classes
* chore: fix imports
* feat: Add OAuth configuration schema to MCP with token exchange method support
* feat: FIRST PASS Implement MCP OAuth flow with token management and error handling
- Added a new route for handling OAuth callbacks and token retrieval.
- Integrated OAuth token storage and retrieval mechanisms.
- Enhanced MCP connection to support automatic OAuth flow initiation on 401 errors.
- Implemented dynamic client registration and metadata discovery for OAuth.
- Updated MCPManager to manage OAuth tokens and handle authentication requirements.
- Introduced comprehensive logging for OAuth processes and error handling.
* refactor: Update MCPConnection and MCPManager to utilize new URL handling
- Added a `url` property to MCPConnection for better URL management.
- Refactored MCPManager to use the new `url` property instead of a deprecated method for OAuth handling.
- Changed logging from info to debug level for flow manager and token methods initialization.
- Improved comments for clarity on existing tokens and OAuth event listener setup.
* refactor: Improve connection timeout error messages in MCPConnection and MCPManager and use initTimeout for connection
- Updated the connection timeout error messages to include the duration of the timeout.
- Introduced a configurable `connectTimeout` variable in both MCPConnection and MCPManager for better flexibility.
* chore: cleanup MCP OAuth Token exchange handling; fix: erroneous use of flowsCache and remove verbose logs
* refactor: Update MCPManager and MCPTokenStorage to use TokenMethods for token management
- Removed direct token storage handling in MCPManager and replaced it with TokenMethods for better abstraction.
- Refactored MCPTokenStorage methods to accept parameters for token operations, enhancing flexibility and readability.
- Improved logging messages related to token persistence and retrieval processes.
* refactor: Update MCP OAuth handling to use static methods and improve flow management
- Refactored MCPOAuthHandler to utilize static methods for initiating and completing OAuth flows, enhancing clarity and reducing instance dependencies.
- Updated MCPManager to pass flowManager explicitly to OAuth handling methods, improving flexibility in flow state management.
- Enhanced comments and logging for better understanding of OAuth processes and flow state retrieval.
* refactor: Integrate token methods into createMCPTool for enhanced token management
* refactor: Change logging from info to debug level in MCPOAuthHandler for improved log management
* chore: clean up logging
* feat: first pass, auth URL from MCP OAuth flow
* chore: Improve logging format for OAuth authentication URL display
* chore: cleanup mcp manager comments
* feat: add connection reconnection logic in MCPManager
* refactor: reorganize token storage handling in MCP
- Moved token storage logic from MCPManager to a new MCPTokenStorage class for better separation of concerns.
- Updated imports to reflect the new token storage structure.
- Enhanced methods for storing, retrieving, updating, and deleting OAuth tokens, improving overall token management.
* chore: update comment for SYSTEM_USER_ID in MCPManager for clarity
* feat: implement refresh token functionality in MCP
- Added refresh token handling in MCPManager to support token renewal for both app-level and user-specific connections.
- Introduced a refreshTokens function to facilitate token refresh logic.
- Enhanced MCPTokenStorage to manage client information and refresh token processes.
- Updated logging for better traceability during token operations.
* chore: cleanup @librechat/auth
* feat: implement MCP server initialization in a separate service
- Added a new service to handle the initialization of MCP servers, improving code organization and readability.
- Refactored the server startup logic to utilize the new initializeMCP function.
- Removed redundant MCP initialization code from the main server file.
* fix: don't log auth url for user connections
* feat: enhance OAuth flow with success and error handling components
- Updated OAuth callback routes to redirect to new success and error pages instead of sending status messages.
- Introduced `OAuthSuccess` and `OAuthError` components to provide user feedback during authentication.
- Added localization support for success and error messages in the translation files.
- Implemented countdown functionality in the success component for a better user experience.
* fix: refresh token handling for user connections, add missing URL and methods
- add standard enum for system user id and helper for determining app-lvel vs. user-level connections
* refactor: update token handling in MCPManager and MCPTokenStorage
* fix: improve error logging in OAuth authentication handler
* fix: concurrency issues for both login url emission and concurrency of oauth flows for shared flows (same user, same server, multiple calls for same server)
* fix: properly fail shared flows for concurrent server calls and prevent duplication of tokens
* chore: remove unused auth package directory from update configuration
* ci: fix mocks in samlStrategy tests
* ci: add mcpConfig to AppService test setup
* chore: remove obsolete MCP OAuth implementation documentation
* fix: update build script for API to use correct command
* chore: bump version of @librechat/api to 1.2.4
* fix: update abort signal handling in createMCPTool function
* fix: add optional clientInfo parameter to refreshTokensFunction metadata
* refactor: replace app.locals.availableTools with getCachedTools in multiple services and controllers for improved tool management
* fix: concurrent refresh token handling issue
* refactor: add signal parameter to getUserConnection method for improved abort handling
* chore: JSDoc typing for `loadEphemeralAgent`
* refactor: update isConnectionActive method to use destructured parameters for improved readability
* feat: implement caching for MCP tools to handle app-level disconnects for loading list of tools
* ci: fix agent test
* 🔧 fix: Enhance user deletion script to allow deep deletion of related data
* 🔧 fix: Update user deletion script to confirm deep deletion of transaction history
* 🔧 fix: Refactor user deletion script to use graceful exit and ensure deep deletion of related data
* Update config/delete-user.js
is a good idea
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* chore: Update import for isEnabled utility in convoAccess middleware
* refactor: Migrate Share functionality to new methods structure in `@librechat/data-schemas`
- Deleted the old Share.js model and moved its functionality to a new share.ts file within the data-schemas package.
- Updated imports across the codebase to reflect the new structure.
- Enhanced error handling and logging in shared link operations.
- Introduced TypeScript types for shared links and related operations to improve type safety and maintainability.
* chore: Update promptGroupSchema validation with typing
* fix: error handling and logging in createSharedLink
* fix: don't allow empty shared link or shared link without messages
* ci: add tests for shared link methods
* chore: Bump version of @librechat/data-schemas to 0.0.9 in package.json and package-lock.json
* chore: Add nanoid as peer dependency
- Introduced `nanoid` as a dependency in `package.json` and `package-lock.json`.
- Replaced UUID generation with `nanoid` for creating unique conversation and message IDs in share methods tests.
* 🧹 chore: Remove Comments and Cleanup base64 handling for Azure Mistral OCR
* chore: Remove unnecessary await from MCP instructions formatting in AgentClient
* ci: Update document_url regex in MistralOCR tests to support PDF format
* feat: add MCP Panel to Agent Builder
- Add MCP server panel and configuration UI
- Implement MCP input forms and tool lists
- Add MCP icon and metadata support
- Integrate MCP with agent configuration
- Add localization support for MCP features
- Refactor components for better reusability
- Update types and add MCP-related mutations
- Fix small issues with Actions and AgentSelect
- Refactor AgentPanelSwitch and related components to use new
AgentPanelContext to reduce prop drilling
* chore: import order
* chore: clean up import statements and unused var in ActionsPanel component
* refactor: AgentPanelContext with actions query, remove unnecessary `actions` state
- Added actions query using `useGetActionsQuery` to fetch actions based on the current agent ID.
- Removed now unused `setActions` state and related logic from `AgentPanelContext` and `AgentPanelSwitch` components.
- Updated `AgentPanelContextType` to reflect the removal of `setActions`.
* chore: re-order import statements in AgentConfig component
* chore: re-order import statements in ModelPanel component
* chore: update ModelPanel props to consolidated props to avoid passing unnecessary props
* chore: update import statements in Providers index file to include ToastProvider and AgentPanelContext exports
* chore: clean up import statements in VersionPanel component
* refactor: streamline AgentConfig and AgentPanel components
- Consolidated props in AgentConfig to only include necessary fields.
- Updated AgentPanel to remove unused state and props, enhancing clarity and maintainability.
- Reorganized import statements for better structure and readability.
* refactor: replace default agent form values with utility function
- Updated AgentsProvider, AgentPanel, AgentSelect, and DeleteButton components to use getDefaultAgentFormValues utility function instead of directly importing defaultAgentFormValues.
- Enhanced the initialization of agent forms by incorporating localStorage values for model and provider in the new utility function.
* chore: comment out rendering MCPSection
---------
Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>
* 👁️ feat: Add Azure Mistral OCR strategy and endpoint integration
This commit introduces a new OCR strategy named 'azure_mistral_ocr', allowing the use of a Mistral OCR endpoint deployed on Azure. The configuration, schemas, and file upload strategies have been updated to support this integration, enabling seamless OCR processing via Azure-hosted Mistral services.
* 🗑️ chore: Clean up .gitignore by removing commented-out uncommon directory name
* chore: remove unused vars
* refactor: Move createAxiosInstance to packages/api/utils and update imports
- Removed the createAxiosInstance function from the config module and relocated it to a new utils module for better organization.
- Updated import paths in relevant files to reflect the new location of createAxiosInstance.
- Added tests for createAxiosInstance to ensure proper functionality and proxy configuration handling.
* chore: move axios helpers to packages/api
- Added logAxiosError function to @librechat/api for centralized error logging.
- Updated imports across various files to use the new logAxiosError function.
- Removed the old axios.js utility file as it is no longer needed.
* chore: Update Jest moduleNameMapper for improved path resolution
- Added a new mapping for '~/' to resolve module paths in Jest configuration, enhancing import handling for the project.
* feat: Implement Mistral OCR API integration in TS
* chore: Update MistralOCR tests based on new imports
* fix: Enhance MistralOCR configuration handling and tests
- Introduced helper functions for resolving configuration values from environment variables or hardcoded settings.
- Updated the uploadMistralOCR and uploadAzureMistralOCR functions to utilize the new configuration resolution logic.
- Improved test cases to ensure correct behavior when mixing environment variables and hardcoded values.
- Mocked file upload and signed URL responses in tests to validate functionality without external dependencies.
* feat: Enhance MistralOCR functionality with improved configuration and error handling
- Introduced helper functions for loading authentication configuration and resolving values from environment variables.
- Updated uploadMistralOCR and uploadAzureMistralOCR functions to utilize the new configuration logic.
- Added utility functions for processing OCR results and creating error messages.
- Improved document type determination and result aggregation for better OCR processing.
* refactor: Reorganize OCR type imports in Mistral CRUD file
- Moved OCRResult, OCRResultPage, and OCRImage imports to a more logical grouping for better readability and maintainability.
* feat: Add file exports to API and create files index
* chore: Update OCR types for enhanced structure and clarity
- Redesigned OCRImage interface to include mandatory fields and improved naming conventions.
- Added PageDimensions interface for better representation of page metrics.
- Updated OCRResultPage to include dimensions and mandatory images array.
- Refined OCRResult to include document annotation and usage information.
* refactor: use TS counterpart of uploadOCR methods
* ci: Update MistralOCR tests to reflect new OCR result structure
* chore: Bump version of @librechat/api to 1.2.3 in package.json and package-lock.json
* chore: Update CONFIG_VERSION to 1.2.8
* chore: remove unused sendEvent function from config module (now imported from '@librechat/api')
* chore: remove MistralOCR service files and tests (now in '@librechat/api')
* ci: update logger import in ModelService tests to use @librechat/data-schemas
---------
Co-authored-by: arthurolivierfortin <arthurolivier.fortin@gmail.com>
* ✨ feat: Implement speech settings initialization and update settings handling
* 🔧 fix: Ensure setters reference is included in useEffect dependencies for speech settings initialization
* chore: Update setter reference in useSpeechSettingsInit for improved type safety
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
- Enhanced the OAuth callback and action creation processes to include the `token_exchange_method` parameter.
- Updated the `TokenService` to handle different token exchange methods, allowing for either 'default_post' or 'basic_auth_header' approaches.
- Improved the handling of access tokens and refresh tokens based on the specified exchange method.
* fix: `primeResources` to Prevent Duplicate Files Across Sources
- Added multiple test cases to ensure that the `primeResources` function correctly handles duplicate files from OCR and attachments, including scenarios with shared files, files without IDs, and duplicates within attachments.
- Implemented logic to categorize files into appropriate tool resources while preventing duplicates across different categories.
- Enhanced error handling and ensured that unique files are returned in the final attachments array.
* fix: Update ToolService to handle single OCR tool case (no loaded tool necessary)
* refactor: Add skipVersioning option to updateAgent for isolated updates
- for now, mainly concerns sharing/unsharing of agents
* chore: Update translation for shared agent message in UI
* chore: linting in mcp.spec.ts
* chore: linting in mcp.ts
* feat(mcp): support dynamic user field placeholders in MCP environment variables
- Added user object handling in MCP options, allowing for dynamic user field processing in environment variables, headers, and URLs.
- Updated `processMCPEnv` to utilize user fields for more flexible configurations.
* chore: update backend review workflow to include unit tests for @librechat/data-schemas
* feat: Enhance OpenID Strategy with Debug Logging and Header Management
- Added detailed logging for OpenID requests and responses when debug mode is enabled.
- Introduced helper functions for safely logging sensitive data and headers.
- Updated OpenID strategy to handle non-standard WWW-Authenticate headers in responses.
- Refactored proxy configuration handling for improved clarity and logging.
* refactor: MemoryViewer Layout with Conditional Justification
- Updated the MemoryViewer component to conditionally apply justification styles based on memory data and access permissions.
- Introduced utility function `cn` for cleaner class name management in the component.
* refactor: Update OpenID Strategy to use Global Fetch
* refactor: Add undici for customFetch request handling in OpenID strategy
* fix: Export 'files' module in utils index
* chore: Add node-fetch dependency for openid image download
* ci: Add comprehensive tests for multer configuration and file handling
- Introduced a new test suite for multer configuration, covering storage destination and filename generation.
- Implemented tests for file filtering, ensuring only valid JSON files are accepted.
- Added error handling tests for edge cases and vulnerabilities, including handling empty field names and malformed filenames.
- Integrated real configuration testing with actual fileConfig and custom endpoints.
- Enhanced UUID generation tests to ensure uniqueness and cryptographic security.
* chore: Improve proxy configuration logging in customFetch function
* fix: Improve logging for non-standard WWW-Authenticate header in customFetch function
* 🧠 feat: User Memories for Conversational Context
chore: mcp typing, use `t`
WIP: first pass, Memories UI
- Added MemoryViewer component for displaying, editing, and deleting user memories.
- Integrated data provider hooks for fetching, updating, and deleting memories.
- Implemented pagination and loading states for better user experience.
- Created unit tests for MemoryViewer to ensure functionality and interaction with data provider.
- Updated translation files to include new UI strings related to memories.
chore: move mcp-related files to own directory
chore: rename librechat-mcp to librechat-api
WIP: first pass, memory processing and data schemas
chore: linting in fileSearch.js query description
chore: rename librechat-api to @librechat/api across the project
WIP: first pass, functional memory agent
feat: add MemoryEditDialog and MemoryViewer components for managing user memories
- Introduced MemoryEditDialog for editing memory entries with validation and toast notifications.
- Updated MemoryViewer to support editing and deleting memories, including pagination and loading states.
- Enhanced data provider to handle memory updates with optional original key for better management.
- Added new localization strings for memory-related UI elements.
feat: add memory permissions management
- Implemented memory permissions in the backend, allowing roles to have specific permissions for using, creating, updating, and reading memories.
- Added new API endpoints for updating memory permissions associated with roles.
- Created a new AdminSettings component for managing memory permissions in the frontend.
- Integrated memory permissions into the existing roles and permissions schemas.
- Updated the interface to include memory settings and permissions.
- Enhanced the MemoryViewer component to conditionally render admin settings based on user roles.
- Added localization support for memory permissions in the translation files.
feat: move AdminSettings component to a new position in MemoryViewer for better visibility
refactor: clean up commented code in MemoryViewer component
feat: enhance MemoryViewer with search functionality and improve MemoryEditDialog integration
- Added a search input to filter memories in the MemoryViewer component.
- Refactored MemoryEditDialog to accept children for better customization.
- Updated MemoryViewer to utilize the new EditMemoryButton and DeleteMemoryButton components for editing and deleting memories.
- Improved localization support by adding new strings for memory filtering and deletion confirmation.
refactor: optimize memory filtering in MemoryViewer using match-sorter
- Replaced manual filtering logic with match-sorter for improved search functionality.
- Enhanced performance and readability of the filteredMemories computation.
feat: enhance MemoryEditDialog with triggerRef and improve updateMemory mutation handling
feat: implement access control for MemoryEditDialog and MemoryViewer components
refactor: remove commented out code and create runMemory method
refactor: rename role based files
feat: implement access control for memory usage in AgentClient
refactor: simplify checkVisionRequest method in AgentClient by removing commented-out code
refactor: make `agents` dir in api package
refactor: migrate Azure utilities to TypeScript and consolidate imports
refactor: move sanitizeFilename function to a new file and update imports, add related tests
refactor: update LLM configuration types and consolidate Azure options in the API package
chore: linting
chore: import order
refactor: replace getLLMConfig with getOpenAIConfig and remove unused LLM configuration file
chore: update winston-daily-rotate-file to version 5.0.0 and add object-hash dependency in package-lock.json
refactor: move primeResources and optionalChainWithEmptyCheck functions to resources.ts and update imports
refactor: move createRun function to a new run.ts file and update related imports
fix: ensure safeAttachments is correctly typed as an array of TFile
chore: add node-fetch dependency and refactor fetch-related functions into packages/api/utils, removing the old generators file
refactor: enhance TEndpointOption type by using Pick to streamline endpoint fields and add new properties for model parameters and client options
feat: implement initializeOpenAIOptions function and update OpenAI types for enhanced configuration handling
fix: update types due to new TEndpointOption typing
fix: ensure safe access to group parameters in initializeOpenAIOptions function
fix: remove redundant API key validation comment in initializeOpenAIOptions function
refactor: rename initializeOpenAIOptions to initializeOpenAI for consistency and update related documentation
refactor: decouple req.body fields and tool loading from initializeAgentOptions
chore: linting
refactor: adjust column widths in MemoryViewer for improved layout
refactor: simplify agent initialization by creating loadAgent function and removing unused code
feat: add memory configuration loading and validation functions
WIP: first pass, memory processing with config
feat: implement memory callback and artifact handling
feat: implement memory artifacts display and processing updates
feat: add memory configuration options and schema validation for validKeys
fix: update MemoryEditDialog and MemoryViewer to handle memory state and display improvements
refactor: remove padding from BookmarkTable and MemoryViewer headers for consistent styling
WIP: initial tokenLimit config and move Tokenizer to @librechat/api
refactor: update mongoMeili plugin methods to use callback for better error handling
feat: enhance memory management with token tracking and usage metrics
- Added token counting for memory entries to enforce limits and provide usage statistics.
- Updated memory retrieval and update routes to include total token usage and limit.
- Enhanced MemoryEditDialog and MemoryViewer components to display memory usage and token information.
- Refactored memory processing functions to handle token limits and provide feedback on memory capacity.
feat: implement memory artifact handling in attachment handler
- Enhanced useAttachmentHandler to process memory artifacts when receiving updates.
- Introduced handleMemoryArtifact utility to manage memory updates and deletions.
- Updated query client to reflect changes in memory state based on incoming data.
refactor: restructure web search key extraction logic
- Moved the logic for extracting API keys from the webSearchAuth configuration into a dedicated function, getWebSearchKeys.
- Updated webSearchKeys to utilize the new function for improved clarity and maintainability.
- Prevents build time errors
feat: add personalization settings and memory preferences management
- Introduced a new Personalization tab in settings to manage user memory preferences.
- Implemented API endpoints and client-side logic for updating memory preferences.
- Enhanced user interface components to reflect personalization options and memory usage.
- Updated permissions to allow users to opt out of memory features.
- Added localization support for new settings and messages related to personalization.
style: personalization switch class
feat: add PersonalizationIcon and align Side Panel UI
feat: implement memory creation functionality
- Added a new API endpoint for creating memory entries, including validation for key and value.
- Introduced MemoryCreateDialog component for user interface to facilitate memory creation.
- Integrated token limit checks to prevent exceeding user memory capacity.
- Updated MemoryViewer to include a button for opening the memory creation dialog.
- Enhanced localization support for new messages related to memory creation.
feat: enhance message processing with configurable window size
- Updated AgentClient to use a configurable message window size for processing messages.
- Introduced messageWindowSize option in memory configuration schema with a default value of 5.
- Improved logic for selecting messages to process based on the configured window size.
chore: update librechat-data-provider version to 0.7.87 in package.json and package-lock.json
chore: remove OpenAPIPlugin and its associated tests
chore: remove MIGRATION_README.md as migration tasks are completed
ci: fix backend tests
chore: remove unused translation keys from localization file
chore: remove problematic test file and unused var in AgentClient
chore: remove unused import and import directly for JSDoc
* feat: add api package build stage in Dockerfile for improved modularity
* docs: reorder build steps in contributing guide for clarity
* Removed agent_ids exclusion from version comparison in the Agent model.
* Added tests to ensure agent_ids changes trigger new version creation and handle duplicates correctly.
* Enhanced existing tests to validate agent_ids alongside other fields and preserve history.
* fix: apply mongoMeili when models are created to use main runtime mongoose
* chore: update @librechat/data-schemas version to 0.0.8
* refactor: remove unused useDebounceCodeBlock
* fix: ensure setter function is stable and handle numeric conversion in useDebouncedInput
* refactor: replace useCallback with useMemo for stable debounced function in useDebouncedInput
* fix: add undefined password check in local user authentication
* fix: edge case - issue deleting user when no conversations in deleteUserController
* feat: Integrate Mailgun API for email sending functionality
* fix: undefined SESSION_EXPIRY handling and add tests
* fix: update import path for isEnabled utility in azureUtils.js to resolve circular dep.
* 🔧 chore: fix ESLint warnings in AdminSettings
* fix: DropdownPopup for BookmarkMenu being affected by recent Header change
* fix: Replace button with OGDialogClose for proper dialog closing
* chore: linting in google client initialization
* chore: linting in getLLMConfig function
* chore: update @librechat/agents to version 2.4.38 to support Google GenAI Custom Headers
* Simplify version creation logic in updateAgent function
* Add comprehensive tests for agent functionality including version history, action metadata generation, and loading agents
- Introduced tests for generating consistent hashes for action metadata.
- Implemented tests for loading agents with various scenarios including null and non-existent IDs.
- Added edge case tests for agent creation, updates, and error handling.
- Ensured proper handling of ephemeral agents and their associated functionalities.
* Enhance tests for Agent model functionality
- Updated test structure for Agent resource file operations, improving organization and readability.
- Added comprehensive tests for handling concurrent file additions and removals, ensuring data integrity.
- Implemented edge case tests for agent creation and resource file management, including scenarios with non-existent agents.
- Enhanced error handling in tests to cover various failure scenarios, ensuring robustness in agent operations.
* optimize tests
* feat[a11y]: add solid left border to improve visibility in LLM's submenu items.
* 🎨 style: Update CustomMenuItem class for improved border visibility
---------
Co-authored-by: Derek Jackson <derek_jackson@harvard.edu>
* 🔧 refactor: Improve Error Handling and UI Consistency in Auth Components
* 🔧 refactor: Email Templates
* 🔧 refactor: Enhance LoginForm with loading state and spinner
* 🔧 refactor: Replace button elements with Button component and enhance UI consistency across Auth forms
* 🔧 fix: Update ProgressText and ToolCall components for improved error handling and localization
* 🔧 chore: Format ESLint configuration for improved readability and remove unused rule
* 🔧 refactor: Simplify ProgressText component logic for better readability and maintainability
* 🔧 refactor: Update ProgressText and ToolCall components for improved layout consistency
* 🔧 refactor: Simplify icon rendering in TTS components and enhance button rendering logic in HoverButtons
* 🔧 refactor: Update placeholder logic in VariableForm component to simply use variable name
* fix: .docx. .pptx Mistral OCR Error with `image_limit=0`
* chore: Update deploy workflow to include conditions for successful dev branch deployment and streamline deployment steps
* ci: Set image_limit to 0 in MistralOCR service tests for consistent behavior
* refactor: move model definitions and database-related methods to packages/data-schemas
* ci: update tests due to new DB structure
fix: disable mocking `librechat-data-provider`
feat: Add schema exports to data-schemas package
- Introduced a new schema module that exports various schemas including action, agent, and user schemas.
- Updated index.ts to include the new schema exports for better modularity and organization.
ci: fix appleStrategy tests
fix: Agent.spec.js
ci: refactor handleTools tests to use MongoMemoryServer for in-memory database
fix: getLogStores imports
ci: update banViolation tests to use MongoMemoryServer and improve session mocking
test: refactor samlStrategy tests to improve mock configurations and user handling
ci: fix crypto mock in handleText tests for improved accuracy
ci: refactor spendTokens tests to improve model imports and setup
ci: refactor Message model tests to use MongoMemoryServer and improve database interactions
* refactor: streamline IMessage interface and move feedback properties to types/message.ts
* refactor: use exported initializeRoles from `data-schemas`, remove api workspace version (this serves as an example of future migrations that still need to happen)
* refactor: update model imports to use destructuring from `~/db/models` for consistency and clarity
* refactor: remove unused mongoose imports from model files for cleaner code
* refactor: remove unused mongoose imports from Share, Prompt, and Transaction model files for cleaner code
* refactor: remove unused import in Transaction model for cleaner code
* ci: update deploy workflow to reference new Docker Dev Branch Images Build and add new workflow for building Docker images on dev branch
* chore: cleanup imports
* feat: working started for feedback implementation.
TODO:
- needs some refactoring.
- needs some UI animations.
* feat: working rate functionality
* feat: works now as well to reader the already rated responses from the server.
* feat: added the option to give feedback in text (optional)
* feat: added Dismiss option `x` to the `FeedbackTagOptions`
* ✨ feat: Add rating and ratingContent fields to message schema
* 🔧 chore: Bump version to 0.0.3 in package.json
* ✨ feat: Enhance feedback localization and update UI elements
* 🚀 feat: Implement feedback tagging system with thumbs up/down options
* 🚀 feat: Add data-provider package to unused i18n keys detection
* 🎨 style: update HoverButtons' style
* 🎨 style: Update HoverButtons and Fork components for improved styling and visibility
* 🔧 feat: Implement feedback system with rating and content options
* 🔧 feat: Enhance feedback handling with improved rating toggle and tag options
* 🔧 feat: Integrate toast notifications for feedback submission and clean up unused state
* 🔧 feat: Remove unused feedback tag options from translation file
* ✨ refactor: clean up Feedback component and improve HoverButtons structure
* ✨ refactor: remove unused settings switches for auto scroll, hide side panel, and user message markdown
* refactor: reorganize import order
* ✨ refactor: enhance HoverButtons and Fork components with improved styles and animations
* ✨ refactor: update feedback response phrases for improved user engagement
* ✨ refactor: add CheckboxOption component and streamline fork options rendering
* Refactor feedback components and logic
- Consolidated feedback handling into a single Feedback component, removing FeedbackButtons and FeedbackTagOptions.
- Introduced new feedback tagging system with detailed tags for both thumbs up and thumbs down ratings.
- Updated feedback schema to include new tags and improved type definitions.
- Enhanced user interface for feedback collection, including a dialog for additional comments.
- Removed obsolete files and adjusted imports accordingly.
- Updated translations for new feedback tags and placeholders.
* ✨ refactor: update feedback handling by replacing rating fields with feedback in message updates
* fix: add missing validateMessageReq middleware to feedback route and refactor feedback system
* 🗑️ chore: Remove redundant fork option explanations from translation file
* 🔧 refactor: Remove unused dependency from feedback callback
* 🔧 refactor: Simplify message update response structure and improve error logging
* Chore: removed unused tests.
---------
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
* 🔧 chore: Update navigateFallbackDenylist in Vite config to include API routes
* 🔧 fix: Update redirect_uri in createActionTool to use DOMAIN_SERVER instead of DOMAIN_CLIENT
* 🔧 feat: Enhance Agent Versioning with Action Metadata Hashing
- Added support for generating a hash of action metadata to detect changes and manage agent versioning.
- Updated `updateAgent` function to include an optional `forceVersion` parameter for version creation.
- Modified `isDuplicateVersion` to compare action metadata hashes.
- Updated related tests to validate new versioning behavior with action changes.
- Refactored agent update logic to ensure proper tracking of user updates and version history.
* 🚀 feat: Implement Auto-Refill Settings for Balance
* 🎨 feat: add `copy-tex` to improve copying KaTeX (#7308)
When selecting equations and using copy paste, uses the correct latex code.
Co-authored-by: Ruben Talstra <RubenTalstra1211@outlook.com>
* 🔃 refactor: `AgentFooter` to conditionally render buttons based on `activePanel` (#7306)
* 🚀 feat: Add `Cloudflare Turnstile` support (#5987)
* 🚀 feat: Add @marsidev/react-turnstile dependency to package.json and package-lock.json
* 🚀 feat: Integrate Cloudflare Turnstile configuration support in AppService and add schema validation
* 🚀 feat: Implemented Cloudflare Turnstile integration in Login and Registration forms
* 🚀 feat: Enhance AppService tests with additional mocks and configuration setups
* 🚀 feat: Comment out outdated config version warning tests in AppService.spec.js
* 🚀 feat: Remove outdated warning tests and add new checks for environment variables and API health
* 🔧 test: Update AppService.spec.js to use expect.anything() for paths validation
* 🔧 test: Refactor AppService.spec.js to streamline mocks and enhance clarity
* 🔧 chore: removed not needed test
* Potential fix for code scanning alert no. 5638: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5629: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5642: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Update turnstile.js
* Potential fix for code scanning alert no. 5634: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5646: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5647: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
---------
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5764: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5765: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* 🖼️ feat: Tool Call and Loading UI Refresh, Image Resize Config (#7086)
* ✨ feat: Enhance Spinner component with customizable properties and improved animation
* 🔧 fix: Replace Loader with Spinner in RunCode component and update FilePreview to use Spinner for progress indication
* ✨ feat: Refactor icons in CodeProgress and CancelledIcon components; enhance animation and styling in ExecuteCode and ProgressText components
* ✨ feat: Refactor attachment handling in ExecuteCode component; replace individual attachment rendering with AttachmentGroup for improved structure
* ✨ feat: Refactor dialog components for improved accessibility and styling; integrate Skeleton loading state in Image component
* ✨ feat: Refactor ToolCall component to use ToolCallInfo for better structure; replace ToolPopover with AttachmentGroup; enhance ProgressText with error handling and improved UI elements
* 🔧 fix: Remove unnecessary whitespace in ProgressText
* 🔧 fix: Remove unnecessary margin from AgentFooter and AgentPanel components; clean up SidePanel imports
* ✨ feat: Enhance ToolCall and ToolCallInfo components with improved styling; update translations and add warning text color to Tailwind config
* 🔧 fix: Update import statement for useLocalize in ToolCallInfo component; fix: chatform transition
* ✨ feat: Refactor ToolCall and ToolCallInfo components for improved structure and styling; add optimized code block for better output display
* ✨ feat: Implement OpenAI image generation component; add progress tracking and localization for user feedback
* 🔧 fix: Adjust base duration values for image generation; optimize timing for quality settings
* chore: remove unnecessary space
* ✨ feat: Enhance OpenAI image generation with editing capabilities; update localization for progress feedback
* ✨ feat: Add download functionality to images; enhance DialogImage component with download button
* ✨ feat: Enhance image resizing functionality; support custom percentage and pixel dimensions in resizeImageBuffer
* 📊 feat: Improve Helm Chart (#3638)
* Replaced Helm Charts with Blue Atlas Charts
* Fix Workflow
* improve docs
* update gitignore
* Update docs
* change values order, add hpa
* change tls example domain
* Default: Enable liveness and readiness
* chore: bump base chart
* apply requested changes
* add Release fix
* add: error handling
* chore: cleanup and testing
* fix: adjust Chart.yaml
---------
Co-authored-by: hofq <gregorspalme@protonmail.com>
Co-authored-by: Ruben Talstra <RubenTalstra1211@outlook.com>
* 📜 docs: Unreleased Changelog (#7434)
* action: update Unreleased changelog
* Update CHANGELOG.md
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🛡️ chore: `multer` v2.0.0 for CVE-2025-47935 and CVE-2025-47944 (#7454)
* chore: bump multer to v2.0.0 to resolve CVE-2025-47935 and CVE-2025-47944
* chore: temp. remove helmet dependency to appease unused NPM package workflow
* 🎚️ feat: Custom Parameters (#7342)
* #
* - refactor: simplified getCustomConfig func
* #
* - feature: persist values for parameters with optionType of custom
* #
* - refactor: moved `Parameters/settings.ts` into `data-provider` so that both frontend and backend code can use it.
* - feature: loadCustomConfig can now parse and validate customParams property for `endpoints.custom` in `librechat.yaml`
* # fixed linter
* # removed .strict() in config.ts
* change: added packages/data-provider/src to SOURCE_DIRS for i18n check
* # removed unnecessary lodash imports
* # addressed PR comments
# fixed lint for updated files
* # better import for lodash (w/o relying on tree-shaking)
* 📃 fix: Ensure MCP Resources Pass Name and Description Fields to LLM (#7442)
* 🔗 feat: Support Environment Variables in MCP URL Config (#7424)
* 🦙 chore: Add `llama-4` to Vision Models List (#7433)
* 🔧 fix: File Deletion for Azure Assistants API (#7466)
* 🔬 fix: File Search Request Format (Azure Assistants API) (#7404)
* fix: The request format for file analysis with Azure OpenAI assistants
The request format for file analysis with Azure OpenAI assistants differs from that of OpenAI. This fix updates the API to use attachments instead of file_ids. danny-avila#7379
* chore: ESLint Error
---------
Co-authored-by: Danny Avila <danacordially@gmail.com>
* 🖼️ chore: Linting & Transition Styling in UI Components (#7467)
* chore: linting
* 🔧 fix: Correctly parse dimensions for image width and height in OpenAIImageGen component
* style: overlay class for DialogImage component to improve visibility
* style: Update transition timing function for PixelCard component to rely on style props
* ✅ fix: Emojis rendering in `SplitText` Animation (#7460)
* 📂 refactor: Improve `FileAttachment` & File Form Deletion (#7471)
* refactor: optional attachment properties for `FileAttachment`
* refactor: update ActionButton to use localized text
* chore: localize text in DataTableFile, add missing translation, imports order, and linting
* chore: linting in DataTable
* fix: integrate Recoil state management for file deletion in DataTableFile
* fix: integrate Recoil state management for file deletion in DataTable
* fix: add temp_file_id to BatchFile type and update deleteFiles logic to properly remove files that are mapped to temp_file_id
* 🌍 i18n: Update translation.json with latest translations (#7468)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* 🦾 feat: Claude-4 Support (#7509)
* refactor: Update AnthropicClient to support Claude model naming changes
* Renamed `isClaude3` to `isClaudeLatest` to accommodate newer Claude models.
* Updated logic to determine if the model is part of the Claude family.
* Adjusted `useMessages` property to reflect the new model naming convention.
* Cleaned up client properties during disposal to match the updated naming.
* feat: Claude-4 Support
* feat: Add Thinking and Prompt caching support for Claude 4
* chore: Update ANTHROPIC_MODELS in .env.example for latest model versions
* 📊 chore: Remove Old Helm Chart (#7512)
Co-authored-by: hofq <gregorspalme@protonmail.com>
* 🪨 feat: Bedrock Support for Claude-4 Reasoning (#7517)
* 🗑️ chore: Update .gitignore to reflect AI-related files
* chore: linting in Bedrock options.js
* 🪨 feat: Bedrock Claude-4 Reasoning
* 🪖 chore: bump helm app version to v0.7.8 (#7524)
- bump helm app version to match the latest
release version
* ⌛ feat: Agent Version History and Management (#7455)
* ✨ feat: Enhance agent update functionality to save current state in versions array
- Updated the `updateAgent` function to push the current agent's state into a new `versions` array when an agent is updated.
- Modified the agent schema to include a `versions` field for storing historical states of agents.
* ✨ feat: Add comprehensive CRUD operations for agents in tests
- Introduced a new test suite for CRUD operations on agents, including create, read, update, and delete functionalities.
- Implemented tests for listing agents by author and updating agent projects.
- Enhanced the agent model to support version history tracking during updates.
- Ensured proper environment variable management during tests.
* ✨ feat: Introduce version tracking for agents and enhance UI components
- Added a `version` property to the agent model to track the number of versions.
- Updated the `getAgentHandler` to include the agent's version in the response.
- Introduced a new `VersionButton` component for navigating to the version panel.
- Created a `VersionPanel` component for displaying version-related information.
- Updated the UI to conditionally render the version button and panel based on the active state.
- Added localization for the new version-related UI elements.
* ✨ i18n: Add "version" translation key across multiple languages
- Introduced the "com_ui_agent_version" translation key in various language files to support version tracking for agents.
- Updated Arabic, Czech, German, English, Spanish, Estonian, Persian, Finnish, French, Hebrew, Hungarian, Indonesian, Italian, Japanese, Korean, Dutch, Polish, Portuguese (Brazil and Portugal), Russian, Swedish, Thai, Turkish, Vietnamese, and Chinese (Simplified and Traditional) translations.
* ✨ feat: Update AgentFooter to conditionally render AdminSettings
- Modified the logic for displaying buttons in the AgentFooter component to only show them when the active panel is the builder.
- Ensured that AdminSettings is displayed only when the user has an admin role and the buttons are visible.
* ✨ feat: Enhance AgentPanelSwitch and VersionPanel for improved agent capabilities
- Updated AgentPanelSwitch to include a new VersionPanel for displaying version-related information.
- Enhanced agentsConfig logic to properly handle agent capabilities.
- Modified VersionPanel to improve structure and localization support.
- Integrated createAgent mutation for future agent creation functionality.
* ✨ feat: Enhance VersionPanel to display agent version history and loading states
- Integrated version fetching logic in VersionPanel to retrieve and display agent version history.
- Added loading and error handling states to improve user experience.
- Updated agent schema to use mixed types for versions, allowing for more flexible version data structures.
- Introduced localization support for version-related UI elements.
* ✨ feat: Update VersionPanel and AgentPanelSwitch to enhance agent selection and version display
- Modified AgentPanelSwitch to pass selectedAgentId to VersionPanel for improved agent context.
- Enhanced VersionPanel to handle multiple timestamp formats and display appropriate messages when no agent is selected.
- Improved structure and readability of the VersionPanel component by adding a helper function for timestamp retrieval.
* ✨ feat: Refactor VersionPanel to utilize localization and improve timestamp handling
- Replaced hardcoded text constants with localization support for various UI elements in VersionPanel.
- Enhanced the timestamp retrieval function to handle errors gracefully and utilize localized messages for unknown dates.
- Improved user feedback by displaying localized messages for agent selection, version errors, and empty states.
* ✨ refactor: Clean up VersionPanel by removing unused code and improving timestamp handling
* ✨ feat: Implement agent version reverting functionality
- Added `revertAgentVersion` method in the Agent model to allow reverting to a previous version of an agent.
- Introduced `revertAgentVersionHandler` in the agents controller to handle requests for reverting agent versions.
- Updated API routes to include a new endpoint for reverting agent versions.
- Enhanced the VersionPanel component to support version restoration with user confirmation and feedback.
- Added localization support for success and error messages related to version restoration.
* ✨ i18n: Add localization for agent version restoration messages
* Simplify VersionPanel by removing unused parameters and enhancing agent ID handling
* Refactor Agent model and VersionPanel component to streamline version data handling
* Update version handling in Agent model and VersionPanel
- Enhanced the Agent model to include an `updatedAt` timestamp when pushing new versions.
- Improved the VersionPanel component to sort versions by the `updatedAt` timestamp for better display order.
- Added a new localization entry for indicating the active version of an agent.
* ✨ i18n: Add localization for active agent version across multiple languages
* ✨ feat: Introduce version management components for agent history
- Added `isActiveVersion` utility to determine the active version of an agent based on various criteria.
- Implemented `VersionContent` and `VersionItem` components to display agent version history, including loading and error states.
- Enhanced `VersionPanel` to integrate new components and manage version context effectively.
- Added comprehensive tests for version management functionalities to ensure reliability and correctness.
* Add unit tests for AgentFooter component
* cleanup
* Enhance agent version update handling and add unit tests for update operators
- Updated the `updateAgent` function to properly handle various update operators ($push, $pull, $addToSet) while maintaining version history.
- Modified unit tests to validate the correct behavior of agent updates, including versioning and tool management.
* Enhance version comparison logic and update tests for artifacts handling
- Modified the `isActiveVersion` utility to include artifacts in the version comparison criteria.
- Updated the `VersionPanel` component to support artifacts in the agent state.
- Added new unit tests to validate artifacts matching scenarios and edge cases in the `isActiveVersion` function.
* Implement duplicate version detection in agent updates and enhance error handling
- Added `isDuplicateVersion` function to check for identical versions during agent updates, excluding certain fields.
- Updated `updateAgent` function to throw an error if a duplicate version is detected, with detailed error information.
- Enhanced the `updateAgentHandler` to return appropriate responses for duplicate version errors.
- Modified client-side error handling to display user-friendly messages for duplicate version scenarios.
- Added comprehensive unit tests to validate duplicate version detection and error handling across various update scenarios.
* Update version title localization to include version number across multiple languages
- Modified the `com_ui_agent_version_title` translation key to include a placeholder for the version number in various language files.
- Enhanced the `VersionItem` component to utilize the updated localization for displaying version titles dynamically.
* Enhance agent version handling and add revert functionality
- Updated the `isDuplicateVersion` function to improve version comparison logic, including special handling for `projectIds` and arrays of objects.
- Modified the `updateAgent` function to streamline version updates and removed unnecessary checks for test environments.
- Introduced a new `revertAgentVersion` function to allow reverting agents to specific versions, with detailed documentation.
- Enhanced unit tests to validate duplicate version detection and revert functionality, ensuring robust error handling and version management.
* fix CI issues
* cleanup
* Revert all non-English translations
* clean up tests
* *️⃣ feat: Reuse OpenID Auth Tokens (#7397)
* feat: integrate OpenID Connect support with token reuse
- Added `jwks-rsa` and `new-openid-client` dependencies for OpenID Connect functionality.
- Implemented OpenID token refresh logic in `AuthController`.
- Enhanced `LogoutController` to handle OpenID logout and session termination.
- Updated JWT authentication middleware to support OpenID token provider.
- Modified OAuth routes to accommodate OpenID authentication and token management.
- Created `setOpenIDAuthTokens` function to manage OpenID tokens in cookies.
- Upgraded OpenID strategy with user info fetching and token exchange protocol.
- Introduced `openIdJwtLogin` strategy for handling OpenID JWT tokens.
- Added caching mechanism for exchanged OpenID tokens.
- Updated configuration to include OpenID exchanged tokens cache key.
- updated .env.example to include the new env variables needed for the feature.
* fix: update return type in downloadImage documentation for clarity and fixed openIdJwtLogin env variables
* fix: update Jest configuration and tests for OpenID strategy integration
* fix: update OpenID strategy to include callback URL in setup
* fix: fix optionalJwtAuth middleware to support OpenID token reuse and improve currentUrl method in CustomOpenIDStrategy to override the dynamic host issue related to proxy (e.g. cloudfront)
* fix: fixed code formatting
* Fix: Add mocks for openid-client and passport strategy in Jest configuration to fix unit tests
* fix eslint errors: Format mock file openid-client.
* ✨ feat: Add PKCE support for OpenID and default handling in strategy setup
---------
Co-authored-by: Atef Bellaaj <slalom.bellaaj@external.daimlertruck.com>
Co-authored-by: Ruben Talstra <RubenTalstra1211@outlook.com>
* 🔎 feat: Native Web Search with Citation References (#7516)
* WIP: search tool integration
* WIP: Add web search capabilities and API key management to agent actions
* WIP: web search capability to agent configuration and selection
* WIP: Add web search capability to backend agent configuration
* WIP: add web search option to default agent form values
* WIP: add attachments for web search
* feat: add plugin for processing web search citations
* WIP: first pass, Citation UI
* chore: remove console.log
* feat: Add AnimatedTabs component for tabbed UI functionality
* refactor: AnimatedTabs component with CSS animations and stable ID generation
* WIP example content
* feat: SearchContext for managing search results apart from MessageContext
* feat: Enhance AnimatedTabs with underline animation and state management
* WIP: first pass, Implement dynamic tab functionality in Sources component with search results integration
* fix: Update class names for improved styling in Sources and AnimatedTabs components
* feat: Improve styling and layout in Sources component with enhanced button and item designs
* feat: Refactor Sources component to integrate OGDialog for source display and improve layout
* style: Update background color in SourceItem and SourcesGroup components for improved visibility
* refactor: Sources component to enhance SourceItem structure and improve favicon handling
* style: Adjust font size of domain text in SourceItem for better readability
* feat: Add localization for citation source and details in CompositeCitation component
* style: add theming to Citation components
* feat: Enhance SourceItem component with dialog support and improved hovercard functionality
* feat: Add localization for sources tab and image alt text in Sources component
* style: Replace divs with spans for better semantic structure in CompositeCitation and Citation components
* refactor: Sources component to use useMemo for tab generation and improve performance
* chore: bump @librechat/agents to v2.4.318
* chore: update search result types
* fix: search results retrieval in ContentParts component, re-render attachments when expected
* feat: update sources style/types to use latest search result structure
* style: enhance Dialog (expanded) SourceItem component with link wrapping and improved styling
* style: update ImageItem component styling for improved title visibility
* refactor: remove SourceItemBase component and adjust SourceItem layout for improved styling
* chore: linting twcss order
* fix: prevent FileAttachment from rendering search attachments
* fix: append underscore to responseMessageId for unique identification to prevent mapping of previous latest message's attachments
* chore: remove unused parameter 'useSpecs' from loadTools function
* chore: twcss order
* WIP: WebSearch Tool UI
* refactor: add limit parameter to StackedFavicons for customizable source display
* refactor: optimize search results memoization by making more granular and separate conerns
* refactor: integrated StackedFavicons to WebSearch mid-run
* chore: bump @librechat/agents to expose handleToolCallChunks
* chore: use typedefs from dedicated file instead of defining them in AgentClient module
* WIP: first pass, search progress results
* refactor: move createOnSearchResults function to a dedicated search module
* chore: bump @librechat/agents to v2.4.320
* WIP: first pass, search results processed UX
* refactor: consolidate context variables in createOnSearchResults function
* chore: bump @librechat/agents to v2.4.321
* feat: add guidelines for web search tool response formatting in loadTools function
* feat: add isLast prop to Part component and update WebSearch logic for improved state handling
* style: update Hovercard styles for improved UI consistency
* feat: export FaviconImage component for improved accessibility in other modules
* refactor: export getCleanDomain function and use FaviconImage in Citation component for improved source representation
* refactor: implement SourceHovercard component for consistency and DRY compliance
* fix: replace <p> with <span> for snippet and title in SourceItem and SourceHovercard for consistency
* style: `not-prose`
* style: remove 'not-prose' class for consistency in SourceItem, Citation, and SourceHovercard components, adjust style classes
* refactor: `imageUrl` on hover and prevent duplicate sources
* refactor: enhance SourcesGroup dialog layout and improve source item presentation
* refactor: reorganize Web Components, save in same directory
* feat: add 'news' refType to refTypeMap for citation sources
* style: adjust Hovercard width for improved layout
* refactor: update tool usage guidelines for improved clarity and execution
* chore: linting
* feat: add Web Search badge with initial permissions and local storage logic
* feat: add webSearch support to interface and permissions schemas
* feat: implement Web Search API key management and localization updates
* feat: refactor Web Search API key handling and integrate new search API key form
* fix: remove unnecessary visibility state from FileAttachment component
* feat: update WebSearch component to use Globe icon and localized search label
* feat: enhance ApiKeyDialog with dropdown for reranker selection and update translations
* feat: implement dropdown menus for engine, scraper, and reranker selection in ApiKeyDialog
* chore: linting and add unknown instead of `any` type
* feat: refactor ApiKeyDialog and useAuthSearchTool for improved API key management
* refactor: update ocrSchema to use template literals for default apiKey and baseURL
* feat: add web search configuration and utility functions for environment variable extraction
* fix: ensure filepath is defined before checking its prefix in useAttachmentHandler
* feat: enhance web search functionality with improved configuration and environment variable extraction for authFields
* fix: update auth type in TPluginAction and TUpdateUserPlugins to use Partial<Record<string, string>>
* feat: implement web search authentication verification and enhance webSearchAuth structure
* feat: enhance ephemeral agent handling with new web search capability and type definition
* feat: enhance isEphemeralAgent function to include web search selection
* feat: refactor verifyWebSearchAuth to improve key handling and authentication checks
* feat: implement loadWebSearchAuth function for improved web search authentication handling
* feat: enhance web search authentication with new configuration options and refactor related types
* refactor: rename search engine to search provider and update related localization keys
* feat: update verifyWebSearchAuth to handle multiple authentication types and improve error handling
* feat: update ApiKeyDialog to accept authTypes prop and remove isUserProvided check
* feat: add tests for extractWebSearchEnvVars and loadWebSearchAuth functions
* feat: enhance loadWebSearchAuth to support specific service checks for providers, scrapers, and rerankers
* fix: update web search configuration key and adjust auth result handling in loadTools function
* feat: add new progress key for repeated web searching and update localization
* chore: bump @librechat/agents to 2.4.322
* feat: enhance loadTools function to include ISO time and improve search tool logging
* feat: update StackedFavicons to handle negative start index and improve citation attribution styling and text
* chore: update .gitignore to categorize AI-related files
* fix: mobile responsiveness of sources/citations hovercards
* feat: enhance source display with improved line clamping for better readability
* chore: bump @librechat/agents to v2.4.33
* feat: add handling for image sources in references mapping
* chore: bump librechat-data-provider version to 0.7.84
* chore: bump @librechat/agents version to 2.4.34
* fix: update auth handling to support multiple auth types in tools and allow key configuration in agent panel
* chore: remove redundant agent attribution text from search form
* fix: web search auth uninstall
* refactor: convert CheckboxButton to a forwardRef component and update setValue callback signature
* feat: add triggerRef prop to ApiKeyDialog components for improved dialog control
* feat: integrate triggerRef in CodeInterpreter and WebSearch components for enhanced dialog management
* feat: enhance ApiKeyDialog with additional links for Firecrawl and Jina API key guidance
* feat: implement web search configuration handling in ApiKeyDialog and add tests for dropdown visibility
* fix: update webSearchConfig reference in config route for correct payload assignment
* feat: update ApiKeyDialog to conditionally render sections based on authTypes and modify loadWebSearchAuth to correctly categorize authentication types
* feat: refactor ApiKeyDialog and related tests to use SearchCategories and RerankerTypes enums and remove nested ternaries
* refactor: move ThinkingButton rendering to improve layout consistency in ContentParts
* feat: integrate search context into Markdown component to conditionally include unicodeCitation plugin
* chore: bump @librechat/agents to v2.4.35
* chore: remove unused 18n key
* ci: add WEB_SEARCH permission testing and update AppService tests for new webSearch configuration
* ci: add more comprehensive tests for loadWebSearchAuth to validate authentication handling and authTypes structure
* chore: remove debugging console log from web.spec.ts to clean up test output
* 🧹 chore: Bump Agents Dependencies (#7525)
* chore: bump langchain dependencies
* chore: bump @librechat/agents to v2.4.36
* chore: bump @librechat/agents to v2.4.37
* refactor: simplify remark plugins in Markdown component with no conditional usage
* 🔧 refactor: Progress Text Localization for Running Tools (#7526)
* 🔧 chore: Bump Data Provider and Custom Config Versions (#7527)
* 🔧 chore: Update CONFIG_VERSION to 1.2.6
* 🔧 chore: Update librechat-data-provider version to 0.7.85
* 👤 feat: Enhance Agent Versioning to Track User Updates (#7523)
* feat: Enhance agent update functionality to track user updates
- Updated `updateAgent` function to accept an `updatingUserId` parameter for tracking who made changes.
- Modified agent versioning to include `updatedBy` field for better audit trails.
- Adjusted related functions and tests to ensure proper handling of user updates and version history.
- Enhanced tests to verify correct tracking of `updatedBy` during agent updates and restorations.
* fix: Refactor import tests for improved readability and consistency
- Adjusted formatting in `importChatGptConvo` test to enhance clarity.
- Updated expected output string in `processAssistantMessage` test to use double quotes for consistency.
- Modified processing time expectation in `processAssistantMessage` test to allow for CI environment variability.
* 🧩 feat: Web Search Config Validations & Clipboard Citation Processing (#7530)
* 🔧 chore: Add missing optional `scraperTimeout` to webSearchSchema
* chore: Add missing optional `scraperTimeout` to web search authentication result
* chore: linting
* feat: Integrate attachment handling and citation processing in message components
- Added `useAttachments` hook to manage message attachments and search results.
- Updated `MessageParts`, `ContentParts`, and `ContentRender` components to utilize the new hook for improved attachment handling.
- Enhanced `useCopyToClipboard` to format citations correctly, including support for composite citations and deduplication.
- Introduced utility functions for citation processing and cleanup.
- Added tests for the new `useCopyToClipboard` functionality to ensure proper citation formatting and handling.
* feat: Add configuration for LibreChat Code Interpreter API and Web Search variables
* fix: Update searchResults type to use SearchResultData for better type safety
* feat: Add web search configuration validation and logging
- Introduced `checkWebSearchConfig` function to validate web search configuration values, ensuring they are environment variable references.
- Added logging for proper configuration and warnings for incorrect values.
- Created unit tests for `checkWebSearchConfig` to cover various scenarios, including valid and invalid configurations.
* docs: Update README to include Web Search feature details
- Added a section for the Web Search feature, highlighting its capabilities to search the internet and enhance AI context.
- Included links for further information on the Web Search functionality.
* ci: Add mock for checkWebSearchConfig in AppService tests
* chore: linting
* feat: Enhance Shared Messages with Web Search UI by adding searchResults prop to SearchContent and MinimalHoverButtons components
* chore: linting
* refactor: remove Meilisearch index sync from importConversations function
* feat: update safeSearch implementation to use SafeSearchTypes enum
* refactor: remove commented-out code in loadTools function
* fix: ensure responseMessageId handles latestMessage ID correctly
* feat: enhance Vite configuration for improved chunking and caching
- Added additional globIgnores for map files in Workbox configuration.
- Implemented high-impact chunking for various large libraries to optimize performance.
- Increased chunkSizeWarningLimit from 1200 to 1500 for better handling of larger chunks.
* refactor: move health check hook to Root, fix bad setState for Temporary state
- Enhanced the `useHealthCheck` hook to initiate health checks only when the user is authenticated.
- Added logic for managing health check intervals and handling window focus events.
- Introduced a new test suite for `useHealthCheck` to cover various scenarios including authentication state changes and error handling.
- Removed the health check invocation from `ChatRoute` and added it to `Root` for global health monitoring.
* fix: update font alias in Vite configuration for correct path resolution
* 🌍 i18n: Update translation.json with latest translations (#7532)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* 🔧 chore: Update data-provider dependencies for typing (#7533)
- Updated dependencies to include @langchain/core and @types/winston in both package-lock.json and data-provider package.json.
* 🔧 fix: Artifacts Display Crash on Close and Max Width (#7540)
* 🔧 chore: Update react-resizable-panels dependency to version 3.0.2 in package.json and package-lock.json
* fix: Simplify order assignment in SidePanel component based on hasArtifacts condition, fixed frontend crash when artifacts are closed
* refactor: Change throttledSaveLayout to use useMemo for improved performance in SidePanelGroup component
* refactor: Update dependencies in SidePanel component's useEffect hooks for improved responsiveness
* 🏷️ refactor: EditPresetDialog UI and Remove `chatGptLabel` from Presets (#7543)
* fix: add necessary dep., remove unnecessary dep from useMentions memoization
* fix: Migrate deprecated chatGptLabel to modelLabel in cleanupPreset and simplify getPresetTitle logic
* fix: Enhance cleanupPreset to remove empty chatGptLabel and add comprehensive tests for label migration and preset handling
* chore: Update endpointType prop in PopoverButtons to allow null values for better flexibility
* refactor: Replace Dialog with OGDialog in EditPresetDialog for improved UI consistency and structure
* style: Update EditPresetDialog layout and styling for improved responsiveness and consistency
* 📦 refactor: Add Additional Chunking to Vite Config (#7544)
* ⚡ refactor: Add Additional Chunking to Vite Config
* chore: Integrate rollup-plugin-visualizer for bundle analysis in Vite config & add @codemirror chunks
* ⌚ fix: Debounce `setUserContext` and Default State Param for OpenID Auth (#7559)
* fix: Add default random state parameter to OpenID auth request for providers that require it; ensure passport strategy uses it
* ⌚ refactor: debounce setUserContext to avoid race condition
* refactor: Update OpenID authentication to use randomState from openid-client
* chore: linting in presetSettings type definition
* chore: import order in ModelPanel
* refactor: remove `isLegacyOutput` property from AnthropicClient since only used where defined, add latest models to non-legacy patterns, and remove from client cleanup
* refactor: adjust grid layout in Parameters component for improved responsiveness
* refactor: adjust grid layout in ModelPanel for improved display of model parameters
* test: add cases for maxOutputTokens handling in Claude 4 Sonnet and Opus models
* ci: mock loadCustomConfig in server tests and refactor OpenID route for improved authentication handling
* 🚀 feat: Implement Auto-Refill Settings for Balance
* fix: ESLint
* ✨ feat: Enhance Auto-Refill Settings with Validation and Localization
---------
Co-authored-by: andresgit <9771158+andresgit@users.noreply.github.com>
Co-authored-by: matt burnett <mawburn@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
Co-authored-by: hofq <54744977+hofq@users.noreply.github.com>
Co-authored-by: hofq <gregorspalme@protonmail.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
Co-authored-by: Theo N. Truong <644650+nhtruong@users.noreply.github.com>
Co-authored-by: René Honig <5851246+renehonig@users.noreply.github.com>
Co-authored-by: Ben Verhees <ben.verhees@iodigital.com>
Co-authored-by: Amgad Hasan <109704569+AmgadHasan@users.noreply.github.com>
Co-authored-by: arthurolivierfortin <118319678+arthurolivierfortin@users.noreply.github.com>
Co-authored-by: Danny Avila <danacordially@gmail.com>
Co-authored-by: Sebastien Bruel <93573440+sbruel@users.noreply.github.com>
Co-authored-by: Austin Barrington <31205926+austin-barrington@users.noreply.github.com>
Co-authored-by: Peter <peter.rothlaender@gmail.com>
Co-authored-by: Atef Bellaaj <slalom.bellaaj@external.daimlertruck.com>
* 🔧 chore: Update build script to include post-build image removal
* refactor: staticCache middleware with options and special handling for manifest/sw/index files
* refactor(pwa): optimize service worker caching strategy
* refactor: streamline post-build process and update public directory handling
* chore: remove external images from rollupOptions in Vite config
* chore: enhance logging message in post-build script for clarity
* refactor: Simplify grid column calculation in SourcesGroup component
* refactor: Centralize default agent capabilities and simplify capability assignment
* Edge case: use defined/fallback capabilities for ephemeral agents when the "agents" endpoint is not enabled
* refactor: consolidate gemini 2 vision check
* feat: enhance capability check logging for agents
* chore: update librechat-data-provider version to 0.7.86
* refactor: import default agent capabilities for enhanced capability management
* chore: standardize quotes in error message check for consistency
* fix: improve error logging both client and api-side for mistral ocr upload errors
* ci: update error handling in MistralOCR tests to use specific error message
* fix: Add default random state parameter to OpenID auth request for providers that require it; ensure passport strategy uses it
* ⌚ refactor: debounce setUserContext to avoid race condition
* refactor: Update OpenID authentication to use randomState from openid-client
* chore: linting in presetSettings type definition
* chore: import order in ModelPanel
* refactor: remove `isLegacyOutput` property from AnthropicClient since only used where defined, add latest models to non-legacy patterns, and remove from client cleanup
* refactor: adjust grid layout in Parameters component for improved responsiveness
* refactor: adjust grid layout in ModelPanel for improved display of model parameters
* test: add cases for maxOutputTokens handling in Claude 4 Sonnet and Opus models
* ci: mock loadCustomConfig in server tests and refactor OpenID route for improved authentication handling
* ⚡ refactor: Add Additional Chunking to Vite Config
* chore: Integrate rollup-plugin-visualizer for bundle analysis in Vite config & add @codemirror chunks
* fix: add necessary dep., remove unnecessary dep from useMentions memoization
* fix: Migrate deprecated chatGptLabel to modelLabel in cleanupPreset and simplify getPresetTitle logic
* fix: Enhance cleanupPreset to remove empty chatGptLabel and add comprehensive tests for label migration and preset handling
* chore: Update endpointType prop in PopoverButtons to allow null values for better flexibility
* refactor: Replace Dialog with OGDialog in EditPresetDialog for improved UI consistency and structure
* style: Update EditPresetDialog layout and styling for improved responsiveness and consistency
* 🔧 chore: Update react-resizable-panels dependency to version 3.0.2 in package.json and package-lock.json
* fix: Simplify order assignment in SidePanel component based on hasArtifacts condition, fixed frontend crash when artifacts are closed
* refactor: Change throttledSaveLayout to use useMemo for improved performance in SidePanelGroup component
* refactor: Update dependencies in SidePanel component's useEffect hooks for improved responsiveness
* 🔧 chore: Add missing optional `scraperTimeout` to webSearchSchema
* chore: Add missing optional `scraperTimeout` to web search authentication result
* chore: linting
* feat: Integrate attachment handling and citation processing in message components
- Added `useAttachments` hook to manage message attachments and search results.
- Updated `MessageParts`, `ContentParts`, and `ContentRender` components to utilize the new hook for improved attachment handling.
- Enhanced `useCopyToClipboard` to format citations correctly, including support for composite citations and deduplication.
- Introduced utility functions for citation processing and cleanup.
- Added tests for the new `useCopyToClipboard` functionality to ensure proper citation formatting and handling.
* feat: Add configuration for LibreChat Code Interpreter API and Web Search variables
* fix: Update searchResults type to use SearchResultData for better type safety
* feat: Add web search configuration validation and logging
- Introduced `checkWebSearchConfig` function to validate web search configuration values, ensuring they are environment variable references.
- Added logging for proper configuration and warnings for incorrect values.
- Created unit tests for `checkWebSearchConfig` to cover various scenarios, including valid and invalid configurations.
* docs: Update README to include Web Search feature details
- Added a section for the Web Search feature, highlighting its capabilities to search the internet and enhance AI context.
- Included links for further information on the Web Search functionality.
* ci: Add mock for checkWebSearchConfig in AppService tests
* chore: linting
* feat: Enhance Shared Messages with Web Search UI by adding searchResults prop to SearchContent and MinimalHoverButtons components
* chore: linting
* refactor: remove Meilisearch index sync from importConversations function
* feat: update safeSearch implementation to use SafeSearchTypes enum
* refactor: remove commented-out code in loadTools function
* fix: ensure responseMessageId handles latestMessage ID correctly
* feat: enhance Vite configuration for improved chunking and caching
- Added additional globIgnores for map files in Workbox configuration.
- Implemented high-impact chunking for various large libraries to optimize performance.
- Increased chunkSizeWarningLimit from 1200 to 1500 for better handling of larger chunks.
* refactor: move health check hook to Root, fix bad setState for Temporary state
- Enhanced the `useHealthCheck` hook to initiate health checks only when the user is authenticated.
- Added logic for managing health check intervals and handling window focus events.
- Introduced a new test suite for `useHealthCheck` to cover various scenarios including authentication state changes and error handling.
- Removed the health check invocation from `ChatRoute` and added it to `Root` for global health monitoring.
* fix: update font alias in Vite configuration for correct path resolution
* feat: Enhance agent update functionality to track user updates
- Updated `updateAgent` function to accept an `updatingUserId` parameter for tracking who made changes.
- Modified agent versioning to include `updatedBy` field for better audit trails.
- Adjusted related functions and tests to ensure proper handling of user updates and version history.
- Enhanced tests to verify correct tracking of `updatedBy` during agent updates and restorations.
* fix: Refactor import tests for improved readability and consistency
- Adjusted formatting in `importChatGptConvo` test to enhance clarity.
- Updated expected output string in `processAssistantMessage` test to use double quotes for consistency.
- Modified processing time expectation in `processAssistantMessage` test to allow for CI environment variability.
* WIP: search tool integration
* WIP: Add web search capabilities and API key management to agent actions
* WIP: web search capability to agent configuration and selection
* WIP: Add web search capability to backend agent configuration
* WIP: add web search option to default agent form values
* WIP: add attachments for web search
* feat: add plugin for processing web search citations
* WIP: first pass, Citation UI
* chore: remove console.log
* feat: Add AnimatedTabs component for tabbed UI functionality
* refactor: AnimatedTabs component with CSS animations and stable ID generation
* WIP example content
* feat: SearchContext for managing search results apart from MessageContext
* feat: Enhance AnimatedTabs with underline animation and state management
* WIP: first pass, Implement dynamic tab functionality in Sources component with search results integration
* fix: Update class names for improved styling in Sources and AnimatedTabs components
* feat: Improve styling and layout in Sources component with enhanced button and item designs
* feat: Refactor Sources component to integrate OGDialog for source display and improve layout
* style: Update background color in SourceItem and SourcesGroup components for improved visibility
* refactor: Sources component to enhance SourceItem structure and improve favicon handling
* style: Adjust font size of domain text in SourceItem for better readability
* feat: Add localization for citation source and details in CompositeCitation component
* style: add theming to Citation components
* feat: Enhance SourceItem component with dialog support and improved hovercard functionality
* feat: Add localization for sources tab and image alt text in Sources component
* style: Replace divs with spans for better semantic structure in CompositeCitation and Citation components
* refactor: Sources component to use useMemo for tab generation and improve performance
* chore: bump @librechat/agents to v2.4.318
* chore: update search result types
* fix: search results retrieval in ContentParts component, re-render attachments when expected
* feat: update sources style/types to use latest search result structure
* style: enhance Dialog (expanded) SourceItem component with link wrapping and improved styling
* style: update ImageItem component styling for improved title visibility
* refactor: remove SourceItemBase component and adjust SourceItem layout for improved styling
* chore: linting twcss order
* fix: prevent FileAttachment from rendering search attachments
* fix: append underscore to responseMessageId for unique identification to prevent mapping of previous latest message's attachments
* chore: remove unused parameter 'useSpecs' from loadTools function
* chore: twcss order
* WIP: WebSearch Tool UI
* refactor: add limit parameter to StackedFavicons for customizable source display
* refactor: optimize search results memoization by making more granular and separate conerns
* refactor: integrated StackedFavicons to WebSearch mid-run
* chore: bump @librechat/agents to expose handleToolCallChunks
* chore: use typedefs from dedicated file instead of defining them in AgentClient module
* WIP: first pass, search progress results
* refactor: move createOnSearchResults function to a dedicated search module
* chore: bump @librechat/agents to v2.4.320
* WIP: first pass, search results processed UX
* refactor: consolidate context variables in createOnSearchResults function
* chore: bump @librechat/agents to v2.4.321
* feat: add guidelines for web search tool response formatting in loadTools function
* feat: add isLast prop to Part component and update WebSearch logic for improved state handling
* style: update Hovercard styles for improved UI consistency
* feat: export FaviconImage component for improved accessibility in other modules
* refactor: export getCleanDomain function and use FaviconImage in Citation component for improved source representation
* refactor: implement SourceHovercard component for consistency and DRY compliance
* fix: replace <p> with <span> for snippet and title in SourceItem and SourceHovercard for consistency
* style: `not-prose`
* style: remove 'not-prose' class for consistency in SourceItem, Citation, and SourceHovercard components, adjust style classes
* refactor: `imageUrl` on hover and prevent duplicate sources
* refactor: enhance SourcesGroup dialog layout and improve source item presentation
* refactor: reorganize Web Components, save in same directory
* feat: add 'news' refType to refTypeMap for citation sources
* style: adjust Hovercard width for improved layout
* refactor: update tool usage guidelines for improved clarity and execution
* chore: linting
* feat: add Web Search badge with initial permissions and local storage logic
* feat: add webSearch support to interface and permissions schemas
* feat: implement Web Search API key management and localization updates
* feat: refactor Web Search API key handling and integrate new search API key form
* fix: remove unnecessary visibility state from FileAttachment component
* feat: update WebSearch component to use Globe icon and localized search label
* feat: enhance ApiKeyDialog with dropdown for reranker selection and update translations
* feat: implement dropdown menus for engine, scraper, and reranker selection in ApiKeyDialog
* chore: linting and add unknown instead of `any` type
* feat: refactor ApiKeyDialog and useAuthSearchTool for improved API key management
* refactor: update ocrSchema to use template literals for default apiKey and baseURL
* feat: add web search configuration and utility functions for environment variable extraction
* fix: ensure filepath is defined before checking its prefix in useAttachmentHandler
* feat: enhance web search functionality with improved configuration and environment variable extraction for authFields
* fix: update auth type in TPluginAction and TUpdateUserPlugins to use Partial<Record<string, string>>
* feat: implement web search authentication verification and enhance webSearchAuth structure
* feat: enhance ephemeral agent handling with new web search capability and type definition
* feat: enhance isEphemeralAgent function to include web search selection
* feat: refactor verifyWebSearchAuth to improve key handling and authentication checks
* feat: implement loadWebSearchAuth function for improved web search authentication handling
* feat: enhance web search authentication with new configuration options and refactor related types
* refactor: rename search engine to search provider and update related localization keys
* feat: update verifyWebSearchAuth to handle multiple authentication types and improve error handling
* feat: update ApiKeyDialog to accept authTypes prop and remove isUserProvided check
* feat: add tests for extractWebSearchEnvVars and loadWebSearchAuth functions
* feat: enhance loadWebSearchAuth to support specific service checks for providers, scrapers, and rerankers
* fix: update web search configuration key and adjust auth result handling in loadTools function
* feat: add new progress key for repeated web searching and update localization
* chore: bump @librechat/agents to 2.4.322
* feat: enhance loadTools function to include ISO time and improve search tool logging
* feat: update StackedFavicons to handle negative start index and improve citation attribution styling and text
* chore: update .gitignore to categorize AI-related files
* fix: mobile responsiveness of sources/citations hovercards
* feat: enhance source display with improved line clamping for better readability
* chore: bump @librechat/agents to v2.4.33
* feat: add handling for image sources in references mapping
* chore: bump librechat-data-provider version to 0.7.84
* chore: bump @librechat/agents version to 2.4.34
* fix: update auth handling to support multiple auth types in tools and allow key configuration in agent panel
* chore: remove redundant agent attribution text from search form
* fix: web search auth uninstall
* refactor: convert CheckboxButton to a forwardRef component and update setValue callback signature
* feat: add triggerRef prop to ApiKeyDialog components for improved dialog control
* feat: integrate triggerRef in CodeInterpreter and WebSearch components for enhanced dialog management
* feat: enhance ApiKeyDialog with additional links for Firecrawl and Jina API key guidance
* feat: implement web search configuration handling in ApiKeyDialog and add tests for dropdown visibility
* fix: update webSearchConfig reference in config route for correct payload assignment
* feat: update ApiKeyDialog to conditionally render sections based on authTypes and modify loadWebSearchAuth to correctly categorize authentication types
* feat: refactor ApiKeyDialog and related tests to use SearchCategories and RerankerTypes enums and remove nested ternaries
* refactor: move ThinkingButton rendering to improve layout consistency in ContentParts
* feat: integrate search context into Markdown component to conditionally include unicodeCitation plugin
* chore: bump @librechat/agents to v2.4.35
* chore: remove unused 18n key
* ci: add WEB_SEARCH permission testing and update AppService tests for new webSearch configuration
* ci: add more comprehensive tests for loadWebSearchAuth to validate authentication handling and authTypes structure
* chore: remove debugging console log from web.spec.ts to clean up test output
* feat: integrate OpenID Connect support with token reuse
- Added `jwks-rsa` and `new-openid-client` dependencies for OpenID Connect functionality.
- Implemented OpenID token refresh logic in `AuthController`.
- Enhanced `LogoutController` to handle OpenID logout and session termination.
- Updated JWT authentication middleware to support OpenID token provider.
- Modified OAuth routes to accommodate OpenID authentication and token management.
- Created `setOpenIDAuthTokens` function to manage OpenID tokens in cookies.
- Upgraded OpenID strategy with user info fetching and token exchange protocol.
- Introduced `openIdJwtLogin` strategy for handling OpenID JWT tokens.
- Added caching mechanism for exchanged OpenID tokens.
- Updated configuration to include OpenID exchanged tokens cache key.
- updated .env.example to include the new env variables needed for the feature.
* fix: update return type in downloadImage documentation for clarity and fixed openIdJwtLogin env variables
* fix: update Jest configuration and tests for OpenID strategy integration
* fix: update OpenID strategy to include callback URL in setup
* fix: fix optionalJwtAuth middleware to support OpenID token reuse and improve currentUrl method in CustomOpenIDStrategy to override the dynamic host issue related to proxy (e.g. cloudfront)
* fix: fixed code formatting
* Fix: Add mocks for openid-client and passport strategy in Jest configuration to fix unit tests
* fix eslint errors: Format mock file openid-client.
* ✨ feat: Add PKCE support for OpenID and default handling in strategy setup
---------
Co-authored-by: Atef Bellaaj <slalom.bellaaj@external.daimlertruck.com>
Co-authored-by: Ruben Talstra <RubenTalstra1211@outlook.com>
* ✨ feat: Enhance agent update functionality to save current state in versions array
- Updated the `updateAgent` function to push the current agent's state into a new `versions` array when an agent is updated.
- Modified the agent schema to include a `versions` field for storing historical states of agents.
* ✨ feat: Add comprehensive CRUD operations for agents in tests
- Introduced a new test suite for CRUD operations on agents, including create, read, update, and delete functionalities.
- Implemented tests for listing agents by author and updating agent projects.
- Enhanced the agent model to support version history tracking during updates.
- Ensured proper environment variable management during tests.
* ✨ feat: Introduce version tracking for agents and enhance UI components
- Added a `version` property to the agent model to track the number of versions.
- Updated the `getAgentHandler` to include the agent's version in the response.
- Introduced a new `VersionButton` component for navigating to the version panel.
- Created a `VersionPanel` component for displaying version-related information.
- Updated the UI to conditionally render the version button and panel based on the active state.
- Added localization for the new version-related UI elements.
* ✨ i18n: Add "version" translation key across multiple languages
- Introduced the "com_ui_agent_version" translation key in various language files to support version tracking for agents.
- Updated Arabic, Czech, German, English, Spanish, Estonian, Persian, Finnish, French, Hebrew, Hungarian, Indonesian, Italian, Japanese, Korean, Dutch, Polish, Portuguese (Brazil and Portugal), Russian, Swedish, Thai, Turkish, Vietnamese, and Chinese (Simplified and Traditional) translations.
* ✨ feat: Update AgentFooter to conditionally render AdminSettings
- Modified the logic for displaying buttons in the AgentFooter component to only show them when the active panel is the builder.
- Ensured that AdminSettings is displayed only when the user has an admin role and the buttons are visible.
* ✨ feat: Enhance AgentPanelSwitch and VersionPanel for improved agent capabilities
- Updated AgentPanelSwitch to include a new VersionPanel for displaying version-related information.
- Enhanced agentsConfig logic to properly handle agent capabilities.
- Modified VersionPanel to improve structure and localization support.
- Integrated createAgent mutation for future agent creation functionality.
* ✨ feat: Enhance VersionPanel to display agent version history and loading states
- Integrated version fetching logic in VersionPanel to retrieve and display agent version history.
- Added loading and error handling states to improve user experience.
- Updated agent schema to use mixed types for versions, allowing for more flexible version data structures.
- Introduced localization support for version-related UI elements.
* ✨ feat: Update VersionPanel and AgentPanelSwitch to enhance agent selection and version display
- Modified AgentPanelSwitch to pass selectedAgentId to VersionPanel for improved agent context.
- Enhanced VersionPanel to handle multiple timestamp formats and display appropriate messages when no agent is selected.
- Improved structure and readability of the VersionPanel component by adding a helper function for timestamp retrieval.
* ✨ feat: Refactor VersionPanel to utilize localization and improve timestamp handling
- Replaced hardcoded text constants with localization support for various UI elements in VersionPanel.
- Enhanced the timestamp retrieval function to handle errors gracefully and utilize localized messages for unknown dates.
- Improved user feedback by displaying localized messages for agent selection, version errors, and empty states.
* ✨ refactor: Clean up VersionPanel by removing unused code and improving timestamp handling
* ✨ feat: Implement agent version reverting functionality
- Added `revertAgentVersion` method in the Agent model to allow reverting to a previous version of an agent.
- Introduced `revertAgentVersionHandler` in the agents controller to handle requests for reverting agent versions.
- Updated API routes to include a new endpoint for reverting agent versions.
- Enhanced the VersionPanel component to support version restoration with user confirmation and feedback.
- Added localization support for success and error messages related to version restoration.
* ✨ i18n: Add localization for agent version restoration messages
* Simplify VersionPanel by removing unused parameters and enhancing agent ID handling
* Refactor Agent model and VersionPanel component to streamline version data handling
* Update version handling in Agent model and VersionPanel
- Enhanced the Agent model to include an `updatedAt` timestamp when pushing new versions.
- Improved the VersionPanel component to sort versions by the `updatedAt` timestamp for better display order.
- Added a new localization entry for indicating the active version of an agent.
* ✨ i18n: Add localization for active agent version across multiple languages
* ✨ feat: Introduce version management components for agent history
- Added `isActiveVersion` utility to determine the active version of an agent based on various criteria.
- Implemented `VersionContent` and `VersionItem` components to display agent version history, including loading and error states.
- Enhanced `VersionPanel` to integrate new components and manage version context effectively.
- Added comprehensive tests for version management functionalities to ensure reliability and correctness.
* Add unit tests for AgentFooter component
* cleanup
* Enhance agent version update handling and add unit tests for update operators
- Updated the `updateAgent` function to properly handle various update operators ($push, $pull, $addToSet) while maintaining version history.
- Modified unit tests to validate the correct behavior of agent updates, including versioning and tool management.
* Enhance version comparison logic and update tests for artifacts handling
- Modified the `isActiveVersion` utility to include artifacts in the version comparison criteria.
- Updated the `VersionPanel` component to support artifacts in the agent state.
- Added new unit tests to validate artifacts matching scenarios and edge cases in the `isActiveVersion` function.
* Implement duplicate version detection in agent updates and enhance error handling
- Added `isDuplicateVersion` function to check for identical versions during agent updates, excluding certain fields.
- Updated `updateAgent` function to throw an error if a duplicate version is detected, with detailed error information.
- Enhanced the `updateAgentHandler` to return appropriate responses for duplicate version errors.
- Modified client-side error handling to display user-friendly messages for duplicate version scenarios.
- Added comprehensive unit tests to validate duplicate version detection and error handling across various update scenarios.
* Update version title localization to include version number across multiple languages
- Modified the `com_ui_agent_version_title` translation key to include a placeholder for the version number in various language files.
- Enhanced the `VersionItem` component to utilize the updated localization for displaying version titles dynamically.
* Enhance agent version handling and add revert functionality
- Updated the `isDuplicateVersion` function to improve version comparison logic, including special handling for `projectIds` and arrays of objects.
- Modified the `updateAgent` function to streamline version updates and removed unnecessary checks for test environments.
- Introduced a new `revertAgentVersion` function to allow reverting agents to specific versions, with detailed documentation.
- Enhanced unit tests to validate duplicate version detection and revert functionality, ensuring robust error handling and version management.
* fix CI issues
* cleanup
* Revert all non-English translations
* clean up tests
* refactor: Update AnthropicClient to support Claude model naming changes
* Renamed `isClaude3` to `isClaudeLatest` to accommodate newer Claude models.
* Updated logic to determine if the model is part of the Claude family.
* Adjusted `useMessages` property to reflect the new model naming convention.
* Cleaned up client properties during disposal to match the updated naming.
* feat: Claude-4 Support
* feat: Add Thinking and Prompt caching support for Claude 4
* chore: Update ANTHROPIC_MODELS in .env.example for latest model versions
* refactor: optional attachment properties for `FileAttachment`
* refactor: update ActionButton to use localized text
* chore: localize text in DataTableFile, add missing translation, imports order, and linting
* chore: linting in DataTable
* fix: integrate Recoil state management for file deletion in DataTableFile
* fix: integrate Recoil state management for file deletion in DataTable
* fix: add temp_file_id to BatchFile type and update deleteFiles logic to properly remove files that are mapped to temp_file_id
* chore: linting
* 🔧 fix: Correctly parse dimensions for image width and height in OpenAIImageGen component
* style: overlay class for DialogImage component to improve visibility
* style: Update transition timing function for PixelCard component to rely on style props
* fix: The request format for file analysis with Azure OpenAI assistants
The request format for file analysis with Azure OpenAI assistants differs from that of OpenAI. This fix updates the API to use attachments instead of file_ids. danny-avila#7379
* chore: ESLint Error
---------
Co-authored-by: Danny Avila <danacordially@gmail.com>
* #
* - refactor: simplified getCustomConfig func
* #
* - feature: persist values for parameters with optionType of custom
* #
* - refactor: moved `Parameters/settings.ts` into `data-provider` so that both frontend and backend code can use it.
* - feature: loadCustomConfig can now parse and validate customParams property for `endpoints.custom` in `librechat.yaml`
* # fixed linter
* # removed .strict() in config.ts
* change: added packages/data-provider/src to SOURCE_DIRS for i18n check
* # removed unnecessary lodash imports
* # addressed PR comments
# fixed lint for updated files
* # better import for lodash (w/o relying on tree-shaking)
* ✨ feat: Enhance Spinner component with customizable properties and improved animation
* 🔧 fix: Replace Loader with Spinner in RunCode component and update FilePreview to use Spinner for progress indication
* ✨ feat: Refactor icons in CodeProgress and CancelledIcon components; enhance animation and styling in ExecuteCode and ProgressText components
* ✨ feat: Refactor attachment handling in ExecuteCode component; replace individual attachment rendering with AttachmentGroup for improved structure
* ✨ feat: Refactor dialog components for improved accessibility and styling; integrate Skeleton loading state in Image component
* ✨ feat: Refactor ToolCall component to use ToolCallInfo for better structure; replace ToolPopover with AttachmentGroup; enhance ProgressText with error handling and improved UI elements
* 🔧 fix: Remove unnecessary whitespace in ProgressText
* 🔧 fix: Remove unnecessary margin from AgentFooter and AgentPanel components; clean up SidePanel imports
* ✨ feat: Enhance ToolCall and ToolCallInfo components with improved styling; update translations and add warning text color to Tailwind config
* 🔧 fix: Update import statement for useLocalize in ToolCallInfo component; fix: chatform transition
* ✨ feat: Refactor ToolCall and ToolCallInfo components for improved structure and styling; add optimized code block for better output display
* ✨ feat: Implement OpenAI image generation component; add progress tracking and localization for user feedback
* 🔧 fix: Adjust base duration values for image generation; optimize timing for quality settings
* chore: remove unnecessary space
* ✨ feat: Enhance OpenAI image generation with editing capabilities; update localization for progress feedback
* ✨ feat: Add download functionality to images; enhance DialogImage component with download button
* ✨ feat: Enhance image resizing functionality; support custom percentage and pixel dimensions in resizeImageBuffer
* chore(store/families): linting
* refactor: Update `createChatSearchParams` to use `tQueryParamsSchema` for allowed parameters and add `modelLabel` to schema
* refactor: Enhance `useQueryParams` to streamline parameter processing and improve submission handling
* chore: linting
* fix: Add `disableParams` option to conversation handling and related schemas to prevent search params from updating due to use of default preset
* fix: Update `createChatSearchParams` to correctly ignore `agent_id` when it matches `EPHEMERAL_AGENT_ID`
* chore: revert modelLabel addition to query params, as no longer necessary due to `disableParams`
* fix: Refine logic for `disableParams` to ensure correct handling of active preset comparison
* fix: Add `disableParams` option to `NewConversationParams` and update related hooks for preset handling
* fix: Refactor validation logic in `validateSettingDefinitions` to improve handling of `includeInput` and update conversation schema
* fix: Bump version of `librechat-data-provider` to 0.7.83
* 🔒 feat: Add Content Security Policy using Helmet middleware
* 🔒 feat: Set trust proxy and refine Content Security Policy directives
* 🎨 feat: add `copy-tex` to improve copying KaTeX (#7308)
When selecting equations and using copy paste, uses the correct latex code.
Co-authored-by: Ruben Talstra <RubenTalstra1211@outlook.com>
* 🔃 refactor: `AgentFooter` to conditionally render buttons based on `activePanel` (#7306)
* 🚀 feat: Add `Cloudflare Turnstile` support (#5987)
* 🚀 feat: Add @marsidev/react-turnstile dependency to package.json and package-lock.json
* 🚀 feat: Integrate Cloudflare Turnstile configuration support in AppService and add schema validation
* 🚀 feat: Implemented Cloudflare Turnstile integration in Login and Registration forms
* 🚀 feat: Enhance AppService tests with additional mocks and configuration setups
* 🚀 feat: Comment out outdated config version warning tests in AppService.spec.js
* 🚀 feat: Remove outdated warning tests and add new checks for environment variables and API health
* 🔧 test: Update AppService.spec.js to use expect.anything() for paths validation
* 🔧 test: Refactor AppService.spec.js to streamline mocks and enhance clarity
* 🔧 chore: removed not needed test
* Potential fix for code scanning alert no. 5638: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5629: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5642: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Update turnstile.js
* Potential fix for code scanning alert no. 5634: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5646: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5647: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
---------
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* 🔒 feat: Refactor Content Security Policy setup to use Helmet middleware with custom directives
* 🔒 feat: Enhance Content Security Policy to include Sandpack Bundler URL
* 🔒 feat: Update Content Security Policy and integrate Turnstile captcha support
---------
Co-authored-by: andresgit <9771158+andresgit@users.noreply.github.com>
Co-authored-by: matt burnett <mawburn@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* chore: linting for mcp related modules
* fix: update `isConnected` method to return a Promise and handle connection state asynchronously to properly handle/cleanup disconnected user connections
* 🚀 feat: Add @marsidev/react-turnstile dependency to package.json and package-lock.json
* 🚀 feat: Integrate Cloudflare Turnstile configuration support in AppService and add schema validation
* 🚀 feat: Implemented Cloudflare Turnstile integration in Login and Registration forms
* 🚀 feat: Enhance AppService tests with additional mocks and configuration setups
* 🚀 feat: Comment out outdated config version warning tests in AppService.spec.js
* 🚀 feat: Remove outdated warning tests and add new checks for environment variables and API health
* 🔧 test: Update AppService.spec.js to use expect.anything() for paths validation
* 🔧 test: Refactor AppService.spec.js to streamline mocks and enhance clarity
* 🔧 chore: removed not needed test
* Potential fix for code scanning alert no. 5638: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5629: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5642: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Update turnstile.js
* Potential fix for code scanning alert no. 5634: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5646: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Potential fix for code scanning alert no. 5647: Ensure code is properly formatted, use insertion, deletion, or replacement to obtain desired formatting.
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
---------
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* 🌍 i18n: Add Danish and Czech localization support
* 🌍 i18n: Correct Czech language code from 'sc-CZ' to 'cs-CZ'
* 🌍 i18n: Add Catalan localization support
* chore: temporarily remove @librechat/agents
* chore: bump @langchain/google-genai to v0.2.8
* chore: bump @langchain/google-vertexai to v0.2.8
* chore: bump @langchain/core to v0.3.55
* chore: bump @librechat/agents to v2.4.316
* chore: bump @librechat/agents to v2.4.317
* chore: update title for Unreleased Changelog PR to include documentation emoji
* chore: add workflow_dispatch trigger and update Pull Request title for changelog
* ✨ v0.7.8
* chore: bump data-provider to v0.7.82
* chore: update CONFIG_VERSION to 1.2.5
* chore: bump librechat-mcp version to 1.2.2
* chore: bump @librechat/data-schemas version to 0.0.7
Without this, it's not possible to run any MCPs that use python, only node.
So, add these to enable using things that use `uvx` similar to what
the documentation already talks about for `npx`.
* fix: Update Gemini 2.5 Pro Preview Model Name in Token Values
* refactor: Update DeleteButton to close menu when deletion is successful
* refactor: Add unmountOnHide prop to DropdownPopup in multiple components
* chore: linting
* chore: linting
* feat: Add `chatMenu` option for MCP Servers to control visibility in MCPSelect dropdown
* refactor: Update loadManifestTools to return combined tool manifest with MCP tools first
* chore: remove deprecated openapi plugins
* chore: linting
* chore(AgentClient): linting, remove unnecessary `checkVisionRequest` logger
* refactor(AuthService): change logoutUser logging from error to debug level
* chore: new Gemini models token values and rates
* chore(AskController): linting
* 🔄 fix: Include usage in stream options for OpenAI and Azure endpoints
* fix: Agents support for Azure serverless endpoints
* fix: Refactor condition for assistants and azureAssistants endpoint handling
* AWS Titan via Bedrock: model doesn't support system messages, Closes#6456
* fix: Add EndpointSchemaKey type to endpoint parameters in buildDefaultConvo and ensure assistantId is always defined
* fix: Handle new conversation state for assistants endpoint in finalHandler
* fix: Add spec and iconURL parameters to `saveAssistantMessage` to persist modelSpec fields
* fix: Handle assistant unlinking even if no valid files to delete
* chore: move type definitions from callbacks.js to typedefs.js
* chore: Add StandardGraph typedef to typedefs.js
* chore: Update parameter type for graph in ModelEndHandler to StandardGraph
---------
Co-authored-by: Andres Restrepo <andres@enric.ai>
This pull request updates the GOOGLE_MODELS and GOOGLE_TITLE_MODEL examples in the .env.example file to reflect the currently available models on Google AI Studio (Gemini API) and Vertex AI.
Many of the models previously listed in the example file have since been deprecated or are no longer the primary recommended versions. This discrepancy could lead to confusion for new users setting up the project, potentially causing them to select non-functional or outdated model identifiers, resulting in errors or suboptimal performance.
The changes in this PR ensure that:
- The model lists for both Gemini API (AI Studio) and Vertex AI are synchronized with the current offerings.
- New users have a more accurate and reliable starting point when configuring their environment.
- The likelihood of encountering issues due to deprecated model names during initial setup is significantly reduced.
* feat: expose additional Tavily API parameters for tool
The following parameters are part of Tavily API but were previously not exposed for agents to use via the tool. Now they are. The source documentation is here: https://docs.tavily.com/documentation/api-reference/endpoint/search
include_raw_content - returns the full text of found web pages (default is false)
include_domains - limit search to this list of domains (default is none)
exclude_domains - exclude this list of domains form search (default is none)
topic - enum of "general", "news", or "finance" (default is "general")
time_range - enum of "day", "week", "month", or "year" (default unlimited)
days - number of days to search (default is 7, but only applicable to topic == "news")
include_image_descriptions - include a description of the image in the search results (default is false)
It is a little odd that they have both time_range and days, but there it is.
I have noticed that this change requires a little bit of care in prompting to make sure that it doesn't use "news" when you wanted "general". I've attemtped to hint that in the tool description.
* correct lint error
* more lint
---------
Co-authored-by: Michael Natkin <michaeln@glowforge.com>
* Fix: Prevent side effects in `processMCPEnv` by deep cloning MCPOptions
The `processMCPEnv` function was modifying the original `MCPOptions` object, leading to unintended side effects where `LIBRECHAT_USER_ID` could be incorrectly shared across different users. This commit addresses this issue by performing a deep clone of the `MCPOptions` object before processing, ensuring that modifications are isolated and do not affect other users.
* ci: Add tests for processMCPEnv to ensure deep cloning, user ID isolation and environment variable processing
---------
Co-authored-by: Alex C <viennadd@users.noreply.github.com>
* refactor: add custom to as workaround to include custom headers to the initial connection request
* chore: bump MCP client version to 1.2.1 in package-lock and package.json for librechat-mcp
* fix: no system message only for o1-preview and o1-mini
* chore(OpenAIClient): linting
* fix: update regex to include o1-preview and o1-mini in noSystemModelRegex
* refactor: rename variable for consistency with AgentClient
---------
Co-authored-by: Andres <9771158+andresgit@users.noreply.github.com>
* refactor: Enhance initial conversation query condition for better state management and prevent unused network requests
* ifx: Add Prettier plugin to ESLint configuration
* chore: linting and typing in convos.spec.ts
* fix: add back fresh data fetching and improve error handling for conversation navigation
* fix: set conversation only with conversation state change intent, to prevent double queries for messages
* 🔄 chore: Update @langchain/google-vertexai to version 0.2.5 in package.json and package-lock.json
* chore: temp remove agents
* 🔄 chore: Update @langchain/google-genai to version 0.2.5 in package.json and package-lock.json
* 🔄 chore: Update @langchain/community to version 0.3.42 in package.json and package-lock.json
* 🔄 chore: Add license information for @langchain/textsplitters in package-lock.json
* 🔄 chore: Update @langchain/core to version 0.3.51 in package.json and package-lock.json
* 🔄 chore: Update openai dependency to version 4.96.2 in package.json and package-lock.json
* chore: @librechat/agents to v2.4.30
* fix: streaming condition in ModelEndHandler to account for boundModel `disableStreaming` setting
* fix: update regex for noSystemModel and refactor message handling in AgentClient
* feat: Google Gemma models
* chore: remove unnecessary empty JSX fragment in PopoverButtons component
* 🔄 chore: bump supertest to 7.1.0, resolves CVE-2025-46653
* 🔄 chore: update vite to version 6.3.4 and add fdir, picomatch, and tinyglobby as dev dependencies
* 🔄 chore: npm audit fix: remove unused dependencies fdir, picomatch, and tinyglobby from package-lock.json
* fix: Reset artifacts on unmount and remove useIdChangeEffect hook
* feat: Replace SVG icons with Lucide icons for improved consistency
* fix: Refactor artifact reset logic on unmount and conversation change
* refactor: Rename artifactsVisible to artifactsVisibility for consistency
* feat: Replace custom SVG icons with Lucide icons for improved consistency
* feat: Add visibleArtifacts atom for managing visibility state
* feat: Implement debounced visibility state management for artifacts
* refactor: Add useIdChangeEffect hook to reset visible artifacts on conversation ID change
* refactor: Remove unnecessary dependency from useMemo in TextPart component
* refactor: Enhance artifact visibility management by incorporating location checks for search path
* refactor: Improve transition effects for artifact visibility in Artifacts component
* chore: Remove preprocessCodeArtifacts function and related tests
* fix: Update regex for detecting enclosed artifacts in latest message
* refactor: Update artifact visibility checks to be more generic (not just search)
* chore: Enhance artifact visibility logging
* refactor: Extract closeArtifacts function to improve button click handling
* refactor: remove nested logic from use artifacts effect
* refactor: Update regex for detecting enclosed artifacts to handle new line variations
* refactor: Replace Popover with Ariakit components for improved accessibility and UX
* wip: first pass, fork a11y
* feat(i18n): Add localization for fork options and related UI elements
* fix: Ensure Dropdown component has correct z-index for proper layering
* style: Update Fork PopoverButton styles and remove unused sideOffset prop
* style: Update text colors and spacing in Fork component for improved readability
* style: Enhance Fork component's UI by adding select-none class to prevent text selection
* chore: Remove unused Checkbox import from Fork component
* fix: Add sr-only span for accessibility in SplitText component
* chore: Reorder imports in Fork component for better organization
* refactor: Update schema conversion to allow nullable optional fields
* feat: Add support for 'Deepseek' model in response sender logic
* fix: Normalize endpoint case for legacy content handling in AgentClient (fixes `deepseek-chat` followup issues)
* wip: Add Instructions component for agent configuration
* ✨ feat: Implement DropdownPopup for variable insertion in instructions
* refactor: Enhance variable handling by exporting specialVariables and updating Markdown components
* feat: Add special variable support for current date and user in Instructions component
* refactor: Update handleAddVariable to include localized label
* feat: replace special variables in instructions presets
* chore: update parameter type for user in getListAgents function
* refactor: integrate dayjs for date handling and move replaceSpecialVars function to data-provider
* feat: enhance replaceSpecialVars to include day number in current date format
* feat: integrate replaceSpecialVars for processing agent instructions
* feat: add support for current date & time in replaceSpecialVars function
* feat: add iso_datetime support in replaceSpecialVars function
* fix: enforce text parameter to be a required field in replaceSpecialVars function
* feat: add ISO datetime support in translation file
* fix: disable eslint warning for autoFocus in TextareaAutosize component
* feat: add VariablesDropdown component and integrate it into CreatePromptForm and PromptEditor; update translation for special variables
* fix: CategorySelector and related localizations
* fix: add z-index class to LanguageSTTDropdown for proper stacking context
* fix: add max-height and overflow styles to OGDialogContent in VariableDialog and PreviewPrompt components
* fix: update variable detection logic to exclude special variables and improve regex matching
* fix: improve accessibility text for actions menu in ChatGroupItem component
* fix: adjust max-width and height styles for dialog components and improve markdown rendering for light vs. dark, height/widths, etc.
* fix: remove commented-out code for better readability in PromptVariableGfm component
* fix: handle undefined input parameter in setParams function call
* fix: update variable label types to use TSpecialVarLabel for consistency
* fix: remove outdated information from special variables description in translation file
* fix: enhance unused i18next keys detection for special variable keys
* fix: update color classes for consistency/a11y in category and prompt variable components
* fix: update PromptVariableGfm component and special variable styles for consistency
* fix: improve variable highlighting logic in VariableForm component
* fix: update background color classes for consistency in VariableForm component
* fix: add missing ref parameter to Dialog component in OriginalDialog
* refactor: move navigate call for new conversation to after setConversation update
* refactor: move message query hook to client workspace; fix: handle edge case for navigation from finalHandler creating race condition for response message DB save
* chore: bump librechat-data-provider to 0.7.793
* ci: add unit tests for replaceSpecialVars function
* fix: implement getToolkitKey function for image_gen_oai toolkit filtering/including
* ci: enhance dayjs mock for consistent date/time values in tests
* fix: MCP stdio server fail to start when passing env property
* fix: use optional chaining for clientRef dereferencing in AskController and EditController
feat: add context to saveMessage call in streamResponse utility
* fix: only save error messages if the userMessageId was initialized
* refactor: add isNotAppendable check to disable inputs in ChatForm and useTextarea
* feat: enhance error handling in useEventHandlers and update conversation state in useNewConvo
* refactor: prepend underscore to conversationId in newConversation template
* feat: log aborted conversations with minimal messages and use consistent conversationId generation
---------
Co-authored-by: Olivier Schiavo <olivier.schiavo@wengo.com>
Co-authored-by: aka012 <aka012@neowiz.com>
Co-authored-by: jiasheng <jiashengguo@outlook.com>
* chore: fix logging for illegal target endpoints in getEndpointFromSetup
* fix: prevent querying agent by ID for ephemeral agents
* refactor: reorder variable declarations in MessagesView for clarity
* fix: localize 'nothing found' message in MessagesView
* refactor: streamline navigation logic and enhance loading spinner component in ChatView
* refactor: simplify loading spinner logic in ChatView component
* fix: ensure message queries are invalidated after new conversation creation in HeaderNewChat, MobileNav, and NewChat components
* 🐛 First run dev mode will have error occur.
🐛 First run dev mode will have error occur.
* fix font-size localstorage presist bug
* Don't ping meilisearch if the search is disabled via env var
* simplify logic in search/enable endpoint
* refactor: simplify enable endpoint condition check
* feat: add useIdChangeEffect hook and integrate it into ChatRoute
---------
Co-authored-by: Ne0 <20765145+zeeklog@users.noreply.github.com>
Co-authored-by: TinyTin <garychangcn@hotmail.com>
Co-authored-by: Denis Palnitsky <denis.palnitsky@zendesk.com>
* refactor: improve ChatView layout by keeping ChatForm mounted
* feat: implement focusChat functionality for new conversations and navigations
* refactor: reset artifacts when navigating to prevent any from rendering in a conversation when none exist; edge case, artifacts get created by search route (TODO: use a different artifact renderer for Search markdown)
* chore: remove redundancy of useSetRecoilState and useRecoilValue with useRecoilState in SearchBar
* refactor: remove unnecessary focus effect on text area in ChatForm
* refactor: improve searchbar and clear search button accessibility
* fix: add tabIndex to Conversations component for improved accessibility, moves focus directly conversation items
* style: adjust margin in Header component for improved layout symmetry with Nav
* chore: imports order
* refactor: streamline model preset handling in conversation setup
* refactor: integrate navigation and location hooks in chat functions and event handlers, prevent cache from fetching on final event handling
* fix: prevent adding code interpreter non-image output to file list on message attachment event, fix all unhandled edge cases when this is done (treating the file download as an image attachment, undefined fields, message tokenCount issues, use of `startsWith` on undefined "text") although it is now prevent altogether
* chore: remove unused jailbreak prop from MinimalIcon component in EndpointIcon
* feat: add new SVG icons (MobileSidebar, Sidebar, XAIcon), fix: xAI styling in dark vs. light modes, adjust styling of Landing icons
* fix: open conversation in new tab on navigation with ctrl/meta key
* refactor: update Nav & Header to use close/open sidebar buttons, as well as redesign "New Chat"/"Bookmarks" buttons to the top of the Nav, matching the latest design of ChatGPT for simplicity and to free up space
* chore: remove unused isToggleHovering state and simplify opacity logic in Nav component
* style: match mobile nav to mobile header
* wip: OpenAI Image Generation Tool with customizable options
* WIP: First pass OpenAI Image Generation Tool and integrate into existing tools
* 🔀 fix: Comment out unused validation for image generation tool parameters
* 🔀 refactor: Update primeResources function parameters for better destructuring
* feat: Add image_edit resource to EToolResources and update AgentToolResources interface
* feat: Enhance file retrieval with tool resource filtering for image editing
* refactor: add OpenAI Image Tools for generation and editing, refactor related components, pass current request image attachments as tool resources for editing
* refactor: Remove commented-out code and clean up API key retrieval in createOpenAIImageTools function
* fix: show message attachments in shared links
* fix: Correct parent message retrieval logic for regenerated messages in useChatFunctions
* fix: Update primeResources to utilize requestFileSet for image file processing
* refactor: Improve description for image generation tool and clarify usage conditions, only provide edit tool if there are images available to edit
* chore: Update OpenAI Image Tools icon to use local asset
* refactor: Update image generation tool description and logic to prioritize editing tool when files are uploaded
* refactor: Enhance image tool descriptions to clarify usage conditions and note potential unavailability of uploaded images
* refactor: Update useAttachmentHandler to accept queryClient to update query cache with newly created file
* refactor: Add customizable descriptions and prompts for OpenAI image generation and editing tools
* chore: Update comments to use JSDoc style for better clarity and consistency
* refactor: Rename config variable to clientConfig for clarity and update signal handling in image generation
* refactor: Update axios request configuration to include derived signal and baseURL for improved request handling
* refactor: Update baseURL environment variable for OpenAI image generation tool configuration
* refactor: Enhance axios request configuration with conditional headers and improved clientConfig setup
* chore: Update comments for clarity and remove unnecessary lines in OpenAI image tools
* refactor: Update description for image generation without files to clarify user instructions
* refactor: Simplify target parent message logic for regeneration and resubmission cases
* chore: Remove backticks from error messages in image generation and editing functions
* refactor: Rename toolResources to toolResourceSet for clarity in file retrieval functions
* chore: Remove redundant comments and clean up TODOs in OpenAI image tools
* refactor: Rename fileStrategy to appFileStrategy for clarity and improve error handling in image processing
* chore: Update react-resizable-panels to version 2.1.8 in package.json and package-lock.json
* chore: Ensure required validation for logs and Code of Conduct agreement in bug report template
* fix: Update ArtifactPreview to use startupConfig and currentCode from memoized props to prevent unnecessary re-renders
* fix: improve robustness of `save & submit` when used from a user-message with existing attachments
* fix: add null check for artifact index in CodeEditor to prevent errors, trigger re-render on artifact ID change
* fix: standardize default values for artifact properties in Artifact component, avoiding prematurely setting an "empty/default" artifact
* fix: reset current artifact ID before setting a new one in ArtifactButton to ensure correct state management
* chore: rename `setArtifactId` variable to `setCurrentArtifactId` for consistency
* chore: update type annotations in File and S3 CRUD functions for consistency
* refactor: improve image handling in OpenAI tools by using image_id references and enhance tool context for image editing
* fix: update image_ids schema in image_edit_oai to enforce presence and provide clear guidelines for usage
* fix: enhance file fetching logic to ensure user-specific and dimension-validated results
* chore: add details on image generation and editing capabilities with various models
* feat: Update MCP tool creation to use lowercase provider name
* refactor: handle MCP image output edge cases where tool outputs must contain string responses
* feat: Drop 'anyOf' and 'oneOf' fields from JSON schema conversion
* feat: Transform 'oneOf' and 'anyOf' fields to Zod union in JSON schema conversion
* fix: artifactPlugin to replace textDirective with expected text, closes#7029
* fix: auto-save functionality to handle conversation transitions from pending drafts, closes#7027
* refactor: improve async handling during user disconnection process
* fix: use correct user ID variable for MCP tool calling
* fix: improve handling of pending drafts in auto-save functionality
* fix: add support for additional model names in getValueKey function
* fix: reset form values on agent deletion when no agents remain
* feat: Add support for new OpenAI models (o4-mini, o3) and update related logic
* 🔧 fix: Rename 'resubmitFiles' to 'isResubmission' for consistency across types and hooks
* 🔧 fix: Replace hardcoded 'pending_req' with CacheKeys.PENDING_REQ for consistency in cache handling
* 🔧 fix: Update cache handling to use Time.ONE_MINUTE instead of hardcoded TTL and streamline imports
* 🔧 fix: Enhance message handling logic to correctly identify parent messages and streamline imports in useSSE
* ✨ style: Adjust z-index for popover UI and update className in ConvoOptions
* ✨ feat: Add 'spec' field to conversation query selection
* 🛠️ fix: add back conversationId to use Constants.PENDING_CONVO in useSSE hook on submission to allow text drafts to clear
* ✨ chore: add .clineignore to .gitignore for Cline configuration
* ✨ refactor: memoize FileSearchCheckbox component for performance optimization
* fix: agent resource management by adding tool_resource to agent's tools if missing
* fix: action parameters are assigned to the correct location (query, parameter, header, body)
* removed copy/paste error
* added unit tests, only add contenttype if specified
---------
Co-authored-by: Peter Rothlaender <peter.rothlaender@ginkgo.com>
* 📦 chore: update @ariakit/react-core to version 0.4.17 in package.json and package-lock.json
* refactor: add additional ariakit menu props and unmount menu if state changes
* fix: accessibility issues and incompatibility issues due to non-portaled menu
* fix: improve visibility and accessibility of conversation options, making sure to expand dynamically when becoming active
* fix: adjust max width for conversation options popover to improve visibility
* fix: handle invalid engineTTS values and prevent VoiceDropdown render errors
* refactor: add verbose developer logging for debugging conversation state issues
* refactor: remove unnecessary effect for conversationId changes
* chore: imports
* fix: include model and entity IDs in conversation query selection
* feat: add fetchFreshData function to retrieve conversation data on navigation
* fix: remove unnecessary comment in fetchFreshData function
* chore: reorder imports in useNavigateToConvo for consistency
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* fix: azure title model
* refactor: typing for uploadMistralOCR
* fix: update conversation ID handling in useSSE for better state management, only use PENDING_CONVO for new conversations
* fix: streamline conversation ID handling in useSSE for simplicity, only needs state update to prevent draft from applying
* fix: update performOCR and tests to support document and image URLs with appropriate types
* ✨ feat: improve Nav/Conversations/Convo/NewChat component performance
* ✨ feat: implement cursor-based pagination for conversations API
* 🔧 refactor: remove createdAt from conversation selection in API and type definitions
* 🔧 refactor: include createdAt in conversation selection and update related types
* ✨ fix: search functionality and bugs with loadMoreConversations
* feat: move ArchivedChats to cursor and DataTable standard
* 🔧 refactor: add InfiniteQueryObserverResult type import in Nav component
* feat: enhance conversation listing with pagination, sorting, and search capabilities
* 🔧 refactor: remove unnecessary comment regarding lodash/debounce in ArchivedChatsTable
* 🔧 refactor: remove unused translation keys for archived chats and search results
* 🔧 fix: Archived Chats, Delete Convo, Duplicate Convo
* 🔧 refactor: improve conversation components with layout adjustments and new translations
* 🔧 refactor: simplify archive conversation mutation and improve unarchive handling; fix: update fork mutation
* 🔧 refactor: decode search query parameter in conversation route; improve error handling in unarchive mutation; clean up DataTable component styles
* 🔧 refactor: remove unused translation key for empty archived chats
* 🚀 fix: `archivedConversation` query key not updated correctly while archiving
* 🧠 feat: Bedrock Anthropic Reasoning & Update Endpoint Handling (#6163)
* 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
* ✨ feat: improve Nav/Conversations/Convo/NewChat component performance
* 🔧 refactor: remove unnecessary comment regarding lodash/debounce in ArchivedChatsTable
* 🔧 refactor: update translation keys for clarity; simplify conversation query parameters and improve sorting functionality in SharedLinks component
* 🔧 refactor: optimize conversation loading logic and improve search handling in Nav component
* fix: package-lock
* fix: package-lock 2
* fix: package lock 3
* refactor: remove unused utility files and exports to clean up the codebase
* refactor: remove i18n and useAuthRedirect modules to streamline codebase
* refactor: optimize Conversations component and remove unused ToggleContext
* refactor(Convo): add RenameForm and ConvoLink components; enhance Conversations component with responsive design
* fix: add missing @azure/storage-blob dependency in package.json
* refactor(Search): add error handling with toast notification for search errors
* refactor: make createdAt and updatedAt fields of tConvoUpdateSchema less restrictive if timestamps are missing
* chore: update @azure/storage-blob dependency to version 12.27.0, ensure package-lock is correct
* refactor(Search): improve conversation handling server side
* fix: eslint warning and errors
* refactor(Search): improved search loading state and overall UX
* Refactors conversation cache management
Centralizes conversation mutation logic into dedicated utility functions for adding, updating, and removing conversations from query caches.
Improves reliability and maintainability by:
- Consolidating duplicate cache manipulation code
- Adding type safety for infinite query data structures
- Implementing consistent cache update patterns across all conversation operations
- Removing obsolete conversation helper functions in favor of standardized utilities
* fix: conversation handling and SSE event processing
- Optimizes conversation state management with useMemo and proper hook ordering
- Improves SSE event handler documentation and error handling
- Adds reset guard flag for conversation changes
- Removes redundant navigation call
- Cleans up cursor handling logic and document structure
Improves code maintainability and prevents potential race conditions in conversation state updates
* refactor: add type for SearchBar `onChange`
* fix: type tags
* style: rounded to xl all Header buttons
* fix: activeConvo in Convo not working
* style(Bookmarks): improved UI
* a11y(AccountSettings): fixed hover style not visible when using light theme
* style(SettingsTabs): improved tab switchers and dropdowns
* feat: add translations keys for Speech
* chore: fix package-lock
* fix(mutations): legacy import after rebase
* feat: refactor conversation navigation for accessibility
* fix(search): convo and message create/update date not returned
* fix(search): show correct iconURL and endpoint for searched messages
* fix: small UI improvements
* chore: console.log cleanup
* chore: fix tests
* fix(ChatForm): improve conversation ID handling and clean up useMemo dependencies
* chore: improve typing
* chore: improve typing
* fix(useSSE): clear conversation ID on submission to prevent draft restoration
* refactor(OpenAIClient): clean up abort handler
* refactor(abortMiddleware): change handleAbort to use function expression
* feat: add PENDING_CONVO constant and update conversation ID checks
* fix: final event handling on abort
* fix: improve title sync and query cache sync on final event
* fix: prevent overwriting cached conversation data if it already exists
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor: agent token handling to use createHandleLLMNewToken for improved closure
* refactor: update llmConfig to use maxTokens instead of max_tokens for consistency
* fix: Agent Builder setting not applying in useSideNavLinks
* fix: Remove unused type imports in useSideNavLinks
* feat: gpt-4.1
* fix: Update getCacheMultiplier and getMultiplier tests to use dynamic token values
* feat: Add gpt-4.1 to the list of vision models
* chore: Bump version of librechat-data-provider to 0.7.792
* chore: update @librechat/agents dependency to version 2.4.15
* refactor: Prevent memory leaks by nullifying boundModel.client in disposeClient function
* fix: use of proxy, use undici
* chore: update @librechat/agents dependency to version 2.4.16
* Revert "fix: use of proxy, use undici"
This reverts commit 83153cd582.
* fix: ensure fetch is imported for HTTP requests
* fix: replace direct OpenAI import with CustomOpenAIClient from @librechat/agents
* fix: update keyv peer dependency to version 5.3.2
* fix: update keyv dependency to version 5.3.2
* refactor: replace KeyvMongo with custom implementation and update flow state manager usage
* fix: update @librechat/agents dependency to version 2.4.17
* ci: update OpenAIClient tests to use CustomOpenAIClient from @librechat/agents
* refactor: remove KeyvMongo mock and related dependencies
* chore: remove unused redis file
* chore: bump keyv dependencies, and update related imports
* refactor: Implement IoRedis client for rate limiting across middleware, as node-redis via keyv not compatible
* fix: Set max listeners to expected amount
* WIP: memory improvements
* refactor: Simplify getAbortData assignment in createAbortController
* refactor: Update getAbortData to use WeakRef for content management
* WIP: memory improvements in agent chat requests
* refactor: Enhance memory management with finalization registry and cleanup functions
* refactor: Simplify domainParser calls by removing unnecessary request parameter
* refactor: Update parameter types for action tools and agent loading functions to use minimal configs
* refactor: Simplify domainParser tests by removing unnecessary request parameter
* refactor: Simplify domainParser call by removing unnecessary request parameter
* refactor: Enhance client disposal by nullifying additional properties to improve memory management
* refactor: Improve title generation by adding abort controller and timeout handling, consolidate request cleanup
* refactor: Update checkIdleConnections to skip current user when checking for idle connections if passed
* refactor: Update createMCPTool to derive userId from config and handle abort signals
* refactor: Introduce createTokenCounter function and update tokenCounter usage; enhance disposeClient to reset Graph values
* refactor: Update getMCPManager to accept userId parameter for improved idle connection handling
* refactor: Extract logToolError function for improved error handling in AgentClient
* refactor: Update disposeClient to clear handlerRegistry and graphRunnable references in client.run
* refactor: Extract createHandleNewToken function to streamline token handling in initializeClient
* chore: bump @librechat/agents
* refactor: Improve timeout handling in addTitle function for better error management
* refactor: Introduce createFetch instead of using class method
* refactor: Enhance client disposal and request data handling in AskController and EditController
* refactor: Update import statements for AnthropicClient and OpenAIClient to use specific paths
* refactor: Use WeakRef for response handling in SplitStreamHandler to prevent memory leaks
* refactor: Simplify client disposal and rename getReqData to processReqData in AskController and EditController
* refactor: Improve logging structure and parameter handling in OpenAIClient
* refactor: Remove unused GraphEvents and improve stream event handling in AnthropicClient and OpenAIClient
* refactor: Simplify client initialization in AskController and EditController
* refactor: Remove unused mock functions and implement in-memory store for KeyvMongo
* chore: Update dependencies in package-lock.json to latest versions
* refactor: Await token usage recording in OpenAIClient to ensure proper async handling
* refactor: Remove handleAbort route from multiple endpoints and enhance client disposal logic
* refactor: Enhance abort controller logic by managing abortKey more effectively
* refactor: Add newConversation handling in useEventHandlers for improved conversation management
* fix: dropparams
* refactor: Use optional chaining for safer access to request properties in BaseClient
* refactor: Move client disposal and request data processing logic to cleanup module for better organization
* refactor: Remove aborted request check from addTitle function for cleaner logic
* feat: Add Grok 3 model pricing and update tests for new models
* chore: Remove trace warnings and inspect flags from backend start script used for debugging
* refactor: Replace user identifier handling with userId for consistency across controllers, use UserId in clientRegistry
* refactor: Enhance client disposal logic to prevent memory leaks by clearing additional references
* chore: Update @librechat/agents to version 2.4.14 in package.json and package-lock.json
* v0.7.791
* feat: configuration via `SANDPACK_STATIC_BUNDLER_URL` env var and update bundlerURL logic in Artifact components
* fix: update minimum length requirement for auth fields from 10 to 1 character
* feat: Update MCP package version and dependencies; refactor ToolContentPart type
* refactor: Change module type to commonjs and update rollup configuration, remove unused dev dependency
* refactor: Change async calls to synchronous for MCP and FlowStateManager retrieval
* chore: Add eslint disable comment for i18next rule in DropdownPopup component
* fix: improve statefulness of mcp servers selected if some were removed since last session
* feat: implement conversation storage cleanup functions and integrate them into mutation success handlers
* feat: enhance storage condition logic in useLocalStorageAlt to prevent unnecessary local storage writes
* refactor: streamline local storage update logic in useLocalStorageAlt
* fix: Prevent parsing 'undefined' string in useLocalStorage initialization
* feat: first pass, code interpreter badge
* feat: Integrate API key authentication and default checked value in Code Interpreter Badge
* refactor: Rename showMCPServers to showEphemeralBadges and update related components, memoize values in useChatBadges
* refactor: Enhance AttachFileChat to support ephemeral agents in file attachment logic
* fix: Add baseURL configuration option to legacy function call
* refactor: Update dependency array in useDragHelpers to include handleFiles
* refactor: Update isEphemeralAgent function to accept optional endpoint parameter
* refactor: Update file handling to support ephemeral agents in AttachFileMenu and useDragHelpers
* fix: improve compatibility issues with OpenAI usage field handling in createRun function
* refactor: usage field compatibility
* fix: ensure mcp servers are no longer "selected" if mcp servers are now unavailable
* refactor: Enhance FileContainer with customizable button and container styles, onClick button handling, and type override
* refactor: Update file type handling to support partial file objects
* refactor: Extract download handling into a custom hook for improved reusability
* refactor: Replace LogContent with Stdout component and enhance Attachment rendering for added visibility
* feat: Update @librechat/agents to version 2.4.1 for referencing generated files in subsequent code interpreter uses
* feat: Add support for tab-separated values (TSV) in mime type handling and improve error logging for regex patterns
* chore: Update @librechat/agents to version 2.4.11 for better `session_id` instructions when wanting to persist files between executions
* chore: Update @librechat/agents to version 2.4.12 for improved functionality
* fix: Enhance argument parsing in useParseArgs to support JSON input and improve code extraction
* refactor: Update input handling in useAutoSave to require more than one character before saving to local storage
* wip: mcp select
* refactor: Update useAvailableToolsQuery to support generic data types
* feat: Enhance MCPSelect to dynamically load server options and improve MultiSelect component styling
* WIP: ephemeral agents
* wip: Add null check for MCPSelect and improve MultiSelect focus handling
* feat: Pass conversationId prop to MCPSelect in BadgeRow to optimize badge rendering
* feat: useApplyNewAgentTemplate hook to manage ephemeral agent upon conversation creation
* WIP: eph. agent payload
* refactor(OpenAIClient): streamline message processing by replacing content handling with parseTextParts function
* feat: enhance applyAgentTemplate function to accept source conversation ID for improved template application
* feat(parsers): add skipReasoning parameter to parseTextParts for conditional reasoning handling
* WIP: first pass, ephemeral agent backend processing
* chore: import order
* feat: update loadEphemeralAgent and loadAgent functions to accept model_parameters for enhanced agent configuration
* feat: add showMCPServers prop to BadgeRow for conditional rendering of MCPSelect, fix react rule violation
* feat: enhance MCPSelect with localized placeholder and custom icon, add renderSelectedValues callback
* feat: simplify message processing in AnthropicClient by replacing content handling with parseTextParts function
* feat: implement useLocalStorage hook for managing MCP values and update MCPSelect to utilize it
* chore: remove chatGPTBrowserSchema from endpoint schemas and update types for improved schema management
* chore: remove compactChatGPTSchema from endpoint schemas and update types for better schema management
* refactor: rename schemas for clarity and improve schema management
* feat: extend model detection to include 'codestral' alongside 'mistral'
* feat: add endpointType parameter to buildOptions and initializeClient functions
* fix: update condition for handling completion in BaseClient to include agents client
* refactor: simplify payload parsing logic in AgentClient and remove unused providerParsers
* refactor: change useSetRecoilState to useRecoilState for better state management in MCPSelect component
* refactor: streamline chat route handlers by consolidating middleware and improving endpoint structure
* style: update MCPSelect and MultiSelect components for improved layout in mobile view
* v0.7.790
* feat: add getMessageMapMethod to process message text and content in GoogleClient
* chore: include LAST_MCP_ key prefix in clearLocalStorage function for proper teardown on logout
* 📝 fix: Update translation for shared agent message in English locale
* 🪺 fix: Migrate role schema to new nested structure and update permissions handling where missed
* chore: bump @librechat/agents and related packages
* refactor: update message state for tool calls run step, in case no tool call chunks are received
* fix: avoid combining finalized args createContentAggregator for tool calls
* chore: bump @librechat/agents to version 2.3.99
* feat: add support for aborting flows with AbortSignal in createFlow methods
* fix: improve handling of tool call arguments in useStepHandler
* chore: bump @librechat/agents to version 2.4.0
* fix: update flow identifier format for OAuth login in createActionTool to allow uniqueness per run
* fix: improve error message handling for aborted flows in FlowStateManager
* refactor: allow possible multi-agent cross-over for oauth login
* fix: add type safety for Sandpack files in ArtifactCodeEditor
* 🔧 chore: Update caniuse-lite dependency to version 1.0.30001706 in package.json and package-lock.json
* 🔧 chore: Remove caniuse-lite dependency from package.json and package-lock.json
* 🏗️ feat: Add Group model and schema with GroupType enum
* 🏗️ feat: Introduce Permissions module and refactor role-based access control
* 🏗️ feat: Refactor permissions handling and consolidate permission schemas
* 🏗️ feat: Refactor role permissions handling and improve role initialization logic
* 🏗️ feat: Update Role.spec.js to improve imports and enhance test structure
* 🏗️ feat: Update access control logic to ensure proper permission checks in role handling
* 🏗️ chore: Bump versions for librechat-data-provider to 0.7.75 and @librechat/data-schemas to 0.0.6
* 🏗️ feat: Improve role permissions handling by ensuring defaults are applied correctly
* 🏗️ feat: Update role permissions schema to comment out unused SHARE permission
* 🏗️ chore: Bump version of librechat-data-provider to 0.7.77 and remove unused groups field from IUser interface
* 🏗️ chore: Downgrade version of librechat-data-provider to 0.7.76
* 🔧 chore: Bump versions for librechat-data-provider to 0.7.77 and data-schemas to 0.0.6
* 🏗️ chore: Update version of librechat-data-provider to 0.7.789
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🔧 feat: Add configurable S3 URL refresh expiry time
* fix: Set default width and height for URLIcon component in case container style results in NaN
* refactor: Enhance auto-save functionality with debounced restore methods
* feat: Add support for additionalProperties in JSON schema conversion to Zod
* test: Add tests for additionalProperties handling in JSON schema to Zod conversion
* chore: Reorder import statements for better readability in ask route
* fix: Handle additional successful response status code (200) in SSE error handler
* fix: add missing rate limiting middleware for bedrock and agent chat routes
* fix: update moderation middleware to check feature flag before processing requests
* fix: add moderation middleware to chat routes for text moderation
* Revert "refactor: Enhance auto-save functionality with debounced restore methods"
This reverts commit d2e4134d1f.
* refactor: Move base64 encoding/decoding functions to top-level scope and optimize input handling
* fix: Ensure safe access to agent capabilities in AgentConfig
* fix: don't show agent builder if agents endpoint is not enabled
* fix: Improve error logging for MCP tool calls
* fix: Enhance error message for MCP tool failures
* feat: Add optional spec and iconURL properties to TEndpointOption type
* chore: Update condition to use constant for new conversation parameter
* feat: Enhance abort error handling with additional endpoint options to properly render error message fields
* fix: Throw error instead of returning message for failed MCP tool calls
* refactor: separate logic to generate new S3 URLs for expired links
* feat: Implement S3 URL refresh for user avatars with error handling
* fix: authcontext error in chats where agent chain is used
* refactor: streamline balance configuration logic in getBalanceConfig function
* fix: enhance icon resolution logic in SpecIcon component
* fix: allow null values for spec and iconURL in TEndpointOption type
* fix: update balance check to allow null tokenCredits
* fix: Implement optimistic concurrency control for balance updates in Transaction model to allow for documentdb compatibility
* test: Add concurrent balance increase test for auto refill transactions
* chore: Add deprecation warnings for environment variables in checks
* chore: Change deprecatedVariables to a const declaration in checks.js
* fix: Add date validation in checkBalanceRecord to prevent invalid date errors
* feat: Add setBalanceConfig middleware to synchronize user balance settings
* chore: Reorder middleware imports in oauth.js for better readability
* 🔧 refactor: Remove modelSpecs prop from ModelSelector and related components
* fix: Update submission.conversationId references in SSE hooks and data types as was incorrectly typed
* feat: Allow showing specific endpoints alongside model specs via `addedEndpoints` field
* feat: allowed agents providers via `agents.allowedProviders` field
* fix: bump dicebear/sharp dependencies to resolve CVE-2024-12905 and improve avatar gen logic
* fix: rename variable for clarity in loadDefaultInterface function
* fix: add keepAddedConvos option to newConversation calls for modular chat support
* fix: include model information in endpoint selection for improved context
* fix: update data-provider version to 0.7.78 and increment config version to 1.2.4
* 🚀 feat: Add Temporary Chat feature with badge toggle functionality
* style: update header button
* fix: Integrate resetChatBadges functionality into useNewConvo hook following rules of react
* fix: Adjust margin logic in ChatForm for better layout handling on existing conversations
* fix: Refine margin logic in ChatForm to improve layout during message submission
* fix: Update TemporaryChat component to not render when message is submitting
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🚀 feat: Add Save Badges State functionality to chat settings
* 🚀 feat: Remove individual chat setting components and introduce a reusable ToggleSwitch component
* 🚀 feat: Replace Switches with reusable ToggleSwitch component in General settings; style: improved HoverCard
* 🚀 feat: Refactor ChatForm and Footer components for improved layout and state management
* 🚀 feat: Add deprecation warning for GPT Plugins endpoint
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🔧 fix: Update file source references to include 'azure_blob' for correct service initialization
* 🔧 fix: Add Azure Blob Storage Emulator entries to .gitignore
* fix: Update file source references to include 'azure_blob' for correct service initialization
* fix: Refactor Azure Blob Storage functions to use environment variables for access control and container name, fix deletion improper logging and improper params
* fix: Add basePath determination for agent file uploads based on MIME type
* fix: Implement file streaming to Azure Blob Storage to optimize memory usage during uploads (non-images)
* fix: Update SourceIcon to include 'azure_blob' class and adjust model setting in useSelectorEffects for assistants
* chore: import order
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* style: reduce gap in Message and Content Render components
* style: adjust padding and font size in Chat components for improved layout
* feat: personalize greeting message with user name in Landing component
* feat: first pass, multi-user connections
* 🔧 refactor: Enhance MCPConnection logging with user-specific prefixes
* 🔧 chore: Update @modelcontextprotocol/sdk dependency to version 1.8.0
* feat: idle timeout for user mcp connections
* chore: increase user connection idle timeout to 15 minutes
* feat: implement graceful shutdown for MCP servers on termination signal
* feat: implement user idle timeout management and last activity tracking
* feat: enhance MCP options to support custom headers and user ID in environment variable processing
* feat: update user last activity tracking in MCPManager
* refactor: remove default OpenRouter completions URL from OpenAIClient
* refactor: simplify log messages by removing redundant 'App' prefix in MCPManager
* refactor: show Agents Builder even if not using Agents endpoint
* refactor: remove redundant 'App' prefix from disconnect error log messages in MCPManager
* refactor: remove 'App' prefix from log prefix in MCPConnection
* chore: remove unecessary comment
* fix: allow error propagation during MCPManager initialization
* 🔧 fix: Update useTextToSpeechExternal to include loading state and improve text parsing logic
* fix: update msedge-tts and prevent excessive initialization attempts
* fix: Refactor text parsing logic in mongoMeili model to use parseTextParts function
* 🔧 fix: Resolve Mistral type strictness for OpenAI usage field
* chore: Enable usage tracking for Mistral endpoint in OpenAI configuration
* chore: Add new token values and context windows for latest premier Mistral models
* 🎨 style: Adjust isSelected svg layout of ModelSpecItem
* style: fix modelSpec URL image beeing off-center; style: selected svg centered vertically
* style: Update CustomMenu component to use rounded-lg and enhance focus styles
* style: SidePanel top padding same as NewChat
* fix: prevent unnecessary space rendering in SplitText component
* style: Fix class names and enhance layout in Badge components
* feat: disable temporary chat when in chat
* style: handle > 1 lines in title Landing
* feat: enhance dynamic margin calculation based on line count and content height in Landing component
* 🔧 feat: Enhance logging configuration for production and debug environments
* 🔒 feat: Implement encryption and decryption functions for sensitive values in ActionService with URL encoding/decoding
* refactor: optimize action service for agent tools
* refactor: optimize action processing for Assistants API
* fix: handle case where agent is not found in loadAgent function
* refactor: improve error handling in API calls by throwing new Error with logAxiosError output
* chore: bump @librechat/agents to 2.3.95, fixes "Invalid tool call structure: No preceding AIMessage with tool_call_ids"
* refactor: enhance error logging in logAxiosError function to include response status
* refactor: remove unused useModelSelection hook from Endpoint
* refactor: add support for assistants in useSelectorEffects hook
* refactor: replace string easing with imported easings in Landing component
* chore: remove duplicate translation
* refactor: update model selection logic and improve localization for UI elements
* refactor: replace endpoint value checks with helper functions for agents and assistants
* refactor: optimize display value logic and utilize useMemo for performance improvements
* refactor: clean up imports and optimize display/icon value logic in endpoint components, fix spec selection
* refactor: enhance error logging in axios utility to include stack traces for better debugging
* refactor: update logging configuration to use DEBUG_LOGGING and streamline log level handling
* refactor: adjust className for export menu button to improve layout consistency and remove unused title prop from ShareButton
* refactor: update import path for logAxiosError utility to improve module organization and clarity
* refactor: implement debounced search value setter in ModelSelectorContext for improved performance
* 🔧 fix: Update compression plugin to version 2 and adjust configuration
* 🔧 fix: Adjust compression plugin configuration to set threshold to 10240
* 🔧 fix: Update vite-plugin-node-polyfills to version 0.23.0 and add external polyfills in configuration
* 🔧 fix: Downgrade vite-plugin-node-polyfills to version 0.17.0 and remove external polyfills from configuration
* 🔧 fix: Update vite-plugin-node-polyfills to version 0.23.0 and remove outdated version from package.json
* 🔧 fix: Update vite-plugin-node-polyfills to version 0.23.0 and remove outdated version from package.json
* chore: fix vite-plugin-node-polyfills workspace installation
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* ✨ feat: Add Expand Chat functionality and improve UI components
* ✨ feat: Introduce Chat Badges feature with editing capabilities and UI enhancements
* ✨ feat: re-implement file attachment functionality with new components and improved UI
* ✨ feat: Enhance BadgeRow component with drag-and-drop functionality and add animations for better user experience
* ✨ feat: Add useChatBadges hook and enhance Badge component with animations and toggle functionality
* feat: Improve Add/Delete Badges + style and bug fixes
* ✨ feat: Refactor EditBadges component and optimize useChatBadges hook for improved performance and readability
* ✨ feat: Add type definition for LucideIcon in EditBadges component
* refactor: Clean up BadgeRow component by removing outdated comment and improving code readability
* refactor: Rename app-icon class to badge-icon for consistency and improve badge styling
* feat: Add Center Chat Input toggle and update related components for improved UI/UX
* refactor: Simplify ChatView and MessagesView components for improved readability and performance
* refactor: Improve layout and positioning of scroll button in MessagesView component
* refactor: Adjust scroll button position in MessagesView component for better visibility
* refactor: Remove redundant background class from Badge component for cleaner styling
* feat: disable chat badges
* refactor: adjust positioning of scroll button and popover for improved layout
* refactor: simplify class names in ChatForm and RemoveFile components for cleaner code
* refactor: move Switcher to HeaderOptions from SidePanel
* fix(Landing): duplicate description
* feat: add SplitText component for animated text display and update Landing component to use it
* feat(Chat): add ConversationStarters component and integrate it into ChatView; remove ConvoStarter component
* feat(Chat): enhance Message component layout and styling for improved readability
* feat(ControlCombobox, Select): enhance styling and add animation for improved UI experience
* feat(Chat): update Header and HeaderNewChat components for improved layout and styling
* feat(Chat): add ModelDropdown (now includes both endpoint and model) and refactor Menu components for improved UI
* feat(ModelDropdown): add Agent Select; removed old AgentSwitcher components
* feat(ModelDropdown): add settings button for user key configuration
* fix(ModelDropdown): the model dropdown wasn't opening automatically when opening the endpoint one
* refactor(Chat): remove unused EndpointsMenu and related components to streamline codebase
* feat: enhance greeting message and improve accessibility fro ModelDropdown
* refactor(Endpoints): add new hooks and components for endpoint management
* feat(Endpoint): add support for modelSpecs
* feat(Endpoints): add mobile support
* fix: type issues
* fix(modelSpec): type issue
* fix(EndpointMenuDropdown): double overflow scroller in mobile model list
* fix: search model on mobile
* refactor: Endpoint/Model/modelSpec dropdown
* refactor: reorganize imports in Endpoint components
* refactor: remove unused translation keys from English locale
* BREAKING: moving to ariakit with new CustomMenu
* refactor: remove unnecessary comments
* refactor: remove EndpointItem, ModelDropdownButton, SpecIcon, and SpecItem components
* 🔧 fix: AI Icon bump when regenerating message
* wip: chat UI refactoring, fix issues
* chore: add recent update to useAutoSave
* feat: add access control for agent permissions in useMentions hook
* refactor: streamline ModelSelector by removing unused endpoints logic
* refactor: enhance ModelSelector and context by integrating endpointsConfig and improving type usage
* feat: update ModelSelectorContext to utilize conversation data for initial state
* feat: add selector effects for synced endpoint handling
* feat: add guard clause for conversation endpoint in useSelectorEffects hook
* fix: safely call onSelectMention and add autofocus to mention input
* chore: typing
* refactor: ModelSelector to streamline key dialog handling and improve endpoint rendering
* refactor: extract SettingsButton component for cleaner endpoint item rendering
* wip: first pass, expand set api key
* wip: first pass, expanding set key
* refactor: update EndpointItem styles for improved layout and hover effects
* refactor: adjust padding in EndpointItem for improved layout consistency
* refactor: update preset structure in useSelectMention to include spec as null
* refactor: rename setKeyDialogOpen to onOpenChange for clarity and consistency, bring focus back to button that opened dialog
* feat: add SpecIcon component for dynamic model spec icons in menu, adjust icon styling
* refactor: update getSelectedIcon to accept additional parameters and improve icon rendering logic
* fix: adjust padding in MessageRender for improved layout
* refactor: remove inline style for menu width in CustomMenu component
* refactor: enhance layout and styling in ModelSpecItem component for better responsiveness
* refactor: update getDefaultModelSpec to accept startupConfig and improve model spec retrieval logic
* refactor: improve key management and default values in ModelSelector and related components
* refactor: adjust menu width and improve responsiveness in CustomMenu and EndpointItem components
* refactor: enhance focus styles and responsiveness in EndpointItem component
* refactor: improve layout and spacing in Header and ModelSelector components for better responsiveness
* refactor: adjust button styles for consistency and improved layout in AddMultiConvo and PresetsMenu components
* fix: initial fix of assistant names
* fix: assistants handling
* chore: update version of librechat-data-provider to 0.7.75 and add 'spec' to excludedKeys
* fix: improve endpoint filtering logic based on interface configuration and access rights
* fix: remove unused HeaderOptions import and set spec to null in presets and mentions
* fix: ensure currentExample is always an object when updating examples
* fix: update interfaceConfig checks to ensure modelSelect is considered for rendering components
* fix: update model selection logic to consider interface configuration when prioritizing model specs
* fix: add missing localizations
* fix: remove unused agent and assistant selection translations
* fix: implement debounced state updates for selected values in useSelectorEffects
* style: minor style changes related to the ModelSelector
* fix: adjust maximum height for popover and set fixed height for model item
* fix: update placeholders for model and endpoint search inputs
* fix: refactor MessageRender and ContentRender components to better match each other
* fix: remove convo fallback for iconURL in MessageRender and ContentRender components
* fix: update handling of spec, iconURL, and modelLabel in conversation presets, to allow better interchangeability
* fix: replace chatGptLabel with modelLabel in OpenAI settings configuration (fully deprecate chatGptLabel)
* fix: remove console log for assistantNames in useEndpoints hook
* refactor: add cleanInput and cleanOutput options to default conversation handling
* chore: update bun.lockb
* fix: set default value for showIconInHeader in getSelectedIcon function
* refactor: enhance error handling in message processing when latest message has existing content blocks
* chore: allow import/no-cycle for messages
* fix: adjust flex properties in BookmarkMenu for better layout
* feat: support both 'prompt' and 'q' as query parameters in useQueryParams hook
* feat: re-enable Badges components
* refactor: disable edit badge component
* chore: rename assistantMap to assistantsMap for consistency
* chore: rename assistantMap to assistantsMap for consistency in Mention component
* feat: set staleTime for various queries to improve data freshness
* feat: add spec field to tQueryParamsSchema for model specification
* feat: enhance useQueryParams to handle model specs
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor: remove legacy max_tokens setting for vision models in OpenAIClient (intended for gpt-4-preview)
* refactor: streamline capability checks in loadAgentTools function, still allow actions if tools are disabled
* fix: enhance error handling for token limits in AnthropicClient and update error message in translations
* feat: append timestamp to cloned agent names for better identification
* chore: update @librechat/agents dependency to version 2.3.94
* refactor: remove clearDraft helper from useSubmitMessage and centralize draft clearing logic to SSE handling, helps prevent user message loss if logout occurs
* refactor: increase debounce time for clearDraft function to improve auto-save performance
* 🏗️ refactor: Improve spendTokens logic to handle zero completion tokens and enhance test coverage
* 🏗️ test: Add tests to ensure balance does not go below zero when spending tokens
* 🏗️ fix: Ensure proper continuation in AgentClient when handling errors
* fix: spend token race conditions
* 🏗️ test: Add test for handling multiple concurrent transactions with high balance
* fix: Handle Omni models prompt prefix handling for user messages with array content in OpenAIClient
* refactor: Update checkBalance import paths to use new balanceMethods module
* refactor: Update checkBalance imports and implement updateBalance function for atomic balance updates
* fix: import from replace method
* feat: Add createAutoRefillTransaction method to handle non-balance updating transactions
* refactor: Move auto-refill logic to balanceMethods and enhance checkBalance functionality
* feat: Implement logging for auto-refill transactions in balance checks
* refactor: Remove logRefill calls from multiple client and handler files
* refactor: Move balance checking and auto-refill logic to balanceMethods for improved structure
* refactor: Simplify balance check calls by removing unnecessary balanceRecord assignments
* fix: Prevent negative rawAmount in spendTokens when promptTokens is zero
* fix: Update balanceMethods to use Balance model for findOneAndUpdate
* chore: import order
* refactor: remove unused txMethods file to streamline codebase
* feat: enhance updateBalance and createAutoRefillTransaction methods to support additional parameters for improved balance management
* 🚀 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: Implement Redis-based rate limiting, initially import limits
* feat: Enhance rate limiters with Redis support and custom prefixes
* chore: import orders
* chore: update JSDoc for next middleware parameter type in ban and limiter middleware
* feat: add logHeaders middleware to log forwarded headers in requests
* refactor: change log level from info to debug for Redis rate limiters
* feat: increase Redis max listeners and refactor session storage to use Keyv
* feat: Add submit query param to auto submit a prompt passed in via URL
* refactor: add case-insensitive value for auto-submit
---------
Co-authored-by: Danny Avila <danacordially@gmail.com>
* chore: bump Model Context Protocol SDK dependencies
* fix: correct indentation in MCPConnection class
* refactor: enhance SSE transport with abort controller and add error handling for empty results
* chore: remove outdated Model Context Protocol SDK dependency
* chore: update @modelcontextprotocol/sdk dependency to version 1.7.0
* chore: add debugging comments for PingRequest handling in MCPConnection class
* refactor: update callTool method to accept structured arguments and options
* refactor: simplify maxContextTokens calculation in initializeAgentOptions
* chore: update @babel/runtime dependency to version 7.26.10
* chore: update @librechat/agents dependency to version 2.2.9
* chore: update @librechat/agents dependency to version 2.3.6
* refactor: imports and prevent s3 initialization if strategy not configured
* refactor: mark redis as non-experimental
* refactor: add missing `maxContextTokens` for OpenAI parameters
* refactor: improve log message for Redis initialization
* chore: update @librechat/agents dependency to version 2.3.8
* refactor: extend `streamBuffer` condition to include BEDROCK provider as easily gets throttled by AWS
* refactor: filter out 'think' parts from message content in Anthropic and OpenAI clients
* 🚀 feat: Implement v3 encryption and decryption methods for TOTP secrets
* 🚀 feat: Refactor Two-Factor Authentication methods and enhance 2FA verification process
* 🚀 feat: Update encryption methods to use hex decoding for legacy keys and improve error handling for AES-256-CTR
* 🚀 feat: Update import paths in TwoFactorController for consistency and clarity
* 🚀 feat: Integrate Azure Blob Storage for file handling and image uploads
* 🐼 refactor: Correct module import case for Azure in strategies.js
* 🚀 feat: Add Azure support in SourceIcon component
* 🚀 feat: Enhance Azure Blob Service initialization with Managed Identity support
* 🐼 refactor: Remove unused Azure dependencies from package.json and package-lock.json
* 🐼 refactor: Remove unused Azure dependencies from package.json and package-lock.json
* 🐼 refactor: Remove unused Azure dependencies from package.json and package-lock.json
* 🚀 feat: Add Azure SDK dependencies for identity and storage blob
* 🔧 fix: Reorganize imports in strategies.js for better clarity
* 🔧 fix: Correct comment formatting in strategies.js for consistency
* 🔧 fix: Improve comment formatting in strategies.js for consistency
* fix: prevent crash on duplicate message ID
Added error handling for MongoDB error code 11000 (duplicate key error) in saveMessage function. This prevents the application from crashing when trying to save messages with duplicate IDs, which can happen during aborted requests. Now logs a warning and continues execution safely.
Closes: #5774Closes: #5776
* fix: address ESLint issues in Message.js
---------
Co-authored-by: odrec <odrec@users.noreply.github.com>
* style: Update text file source icon background color for improved visibility in light mode
* style: Update `vectordb` source icon background color for better visibility
* fix: resend files behavior for tool resource message attachments (code interpreter and file search); Rename `getToolFiles` to `getConvoFiles` and simplify file retrieval logic; add `getToolFilesByIds` for fetching tool files by IDs
* French Translation Update
* French Translation Update
* test
* Add fileStrategy S3 Config
* update s3 crud.js
* 🔧 chore: downgrade dotenv to version 16.0.3 and add aws-sdk to package-lock.json
* 🔧 chore: remove aws-sdk from package.json
* 🚀 feat: Integrate AWS SDK for S3 with enhanced upload and retrieval functionalities
* 🚀 feat: Implement S3 integration for file upload and retrieval functionalities
* 🚀 feat: Enhance S3 initialization to support default credentials and improved error handling
---------
Co-authored-by: Gael Martins <gael.martins@acolad.com>
* fix: Enhance MCP initialization to process environment variables
* fix: only build tokenCountMap with messages that are being used in the payload
* fix: Adjust maxContextTokens calculation to account for maxOutputTokens
* refactor: Make processMCPEnv optional in MCPManager initialization
* chore: Bump version of librechat-data-provider to 0.7.73
* wip: first pass, dropdown for selecting sequential agents
* refactor: Improve agent selection logic and enhance performance in SequentialAgents component
* wip: seq. agents working ideas
* wip: sequential agents style change
* refactor: move agent form options/submission outside of AgentConfig
* refactor: prevent repeating code
* refactor: simplify current agent display in SequentialAgents component
* feat: persist form value handling in AgentSelect component for agent_ids
* feat: first pass, sequential agnets agent update
* feat: enhance message display with agent updates and empty text handling
* chore: update Icon component to use EModelEndpoint for agent endpoints
* feat: update content type checks in BaseClient to use constants for better readability
* feat: adjust max context tokens calculation to use 90% of the model's max tokens
* feat: first pass, agent run message pruning
* chore: increase max listeners for abort controller to prevent memory leaks
* feat: enhance runAgent function to include current index count map for improved token tracking
* chore: update @librechat/agents dependency to version 2.2.5
* feat: update icons and style of SequentialAgents component for improved UI consistency
* feat: add AdvancedButton and AdvancedPanel components for enhanced agent settings navigation, update styling for agent form
* chore: adjust minimum height of AdvancedPanel component for better layout consistency
* chore: update @librechat/agents dependency to version 2.2.6
* feat: enhance message formatting by incorporating tool set into agent message processing, in order to allow better mix/matching of agents (as tool calls for tools not found in set will be stringified)
* refactor: reorder components in AgentConfig for improved readability and maintainability
* refactor: enhance layout of AgentUpdate component for improved visual structure
* feat: add DeepSeek provider to Bedrock settings and schemas
* feat: enhance link styling in mobile.css for better visibility and accessibility
* fix: update banner model import in update banner script; export Banner model
* refactor: `duplicateAgentHandler` to include tool_resources only for OCR context files
* feat: add 'qwen-vl' to visionModels for enhanced model support
* fix: change image format from JPEG to PNG in DALLE3 response
* feat: reorganize Advanced components and add localizations
* refactor: simplify JSX structure in AgentChain component to defer container styling to parent
* feat: add FormInput component for reusable input handling
* feat: make agent recursion limit configurable from builder
* feat: add support for agent capabilities chain in AdvancedPanel and update data-provider version
* feat: add maxRecursionLimit configuration for agents and update related documentation
* fix: update CONFIG_VERSION to 1.2.3 in data provider configuration
* feat: replace recursion limit input with MaxAgentSteps component and enhance input handling
* feat: enhance AgentChain component with hover card for additional information and update related labels
* fix: pass request and response objects to `createActionTool` when using assistant actions to prevent auth error
* feat: update AgentChain component layout to include agent count display
* feat: increase default max listeners and implement capability check function for agent chain
* fix: update link styles in mobile.css for better visibility in dark mode
* chore: temp. remove agents package while bumping shared packages
* chore: update @langchain/google-genai package to version 0.1.11
* chore: update @langchain/google-vertexai package to version 0.2.2
* chore: add @librechat/agents package at version 2.2.8
* feat: add deepseek.r1 model with token rate and context values for bedrock
* 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
* 🌟 feat: Implement Two-Factor Authentication (2FA) functionality
* fix: Two-Factor Authentication Logic and State Management
* 🌟 feat: Add LICENSE file and update package version to 0.0.2 with MIT license
* chore: bump mcp sdk
* feat: Add proxy support for file download and upload in Code Environment CRUD operations
* chore: remove unused files
* chore: change output format from CommonJS to ES module in server rollup config
* 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
* refactor: Export AuthContext from AuthContextProvider
* refactor: Update useHasAccess to utilize useContext for AuthContext
* refactor: Enhance type definitions in useHasAccess for better type safety
* 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
* feat: Add 'Run Code' and 'Temporary Chat' permissions to role management
* feat: Add NextFunction typedef to api/typedefs.js
* feat: Add temporary chat and run code permissions to role schema
* refactor: Enhance access check middleware with logging for permission errors and better typing
* refactor: Set default value of USE permission to true in multiConvoPermissionsSchema
* refactor: Implement checkAccess function for separation of permission validation logic from middleware
* feat: Integrate permission checks for tool execution and enhance Markdown code block with execution capability
* fix: Convert REDIS_MAX_LISTENERS to a number, closes#5979
* 🔈 fix: Refactor AudioRecorder to use button element for improved accessibility
* 🔈 fix: Update conversation menu button ID for improved accessibility
* 🔈 fix: Remove redundant role attribute from SidePanel for improved accessibility
* feat: Add robots.txt to manage web crawler access
* feat: Update index.html with meta description and remove legacy file
* fix: resolve merge conflicts.
* fix: resolve merge conflicts.
* fix: resolve merge conflicts.
* feat: Update index.html with meta description and remove legacy file
* 🔧 feat: Add legacy support and improve SidePanel accessibility
* 🔧 feat: Integrate express-static-gzip for improved static file serving and add new plugins for enhanced functionality
* 🔧 chore: Remove unused HTML ESLint plugin configurations and dependencies
---------
Co-authored-by: Ruben Talstra <RubenTalstra1211@outlook.com>
* fix: Add 192x192 icon to allow the PWA to install on Android devices using Chrome.
* fix: Use less whitespace on icon-192x192.png. Re-generate maskable-icon.png and apple-touch-icon-180x180.png to be higher quality, cripser and use less kilobytes.
The workflow now only runs on pull requests that modify:
- The root `package.json` or `package-lock.json` file
- Any file under the client folder
- Any file under the api folder
* 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: Improve MeiliSearch integration with environment-based configuration for running index sync
* chore: Remove Question issue template from GitHub repository
* feat: Enable indexing in MeiliSearch configuration and clean up error handling in indexSync
* feat: Update .env.example to include optional indexing configuration
* refactor: rename env var for disabling index sync to MEILI_NO_SYNC
* Added the option to change the default trusted proxy
* feat: Add TRUST_PROXY configuration to .env.example for reverse proxy settings
* feat: Enhance Redis support with cluster configuration and TLS options
* feat(redis): add cluster support, environment config and url mapping
- Add Redis cluster configuration with isEnabled flag
- Configure prefix and max listeners settings
- Improve code formatting and readability
- Fix URL vs host parameter handling
- Update environment variables and regex patterns
---------
Co-authored-by: Gil Assunção <gil.assuncao@parceiros.nos.pt>
Co-authored-by: Pedro Reis <pedro.malheiro@parceiros.nos.pt>
Co-authored-by: João Trigo Soares <joao.soares@parceiros.nos.pt>
* ✨ feat: Enhance UI Components with Shadows and Accessibility Improvements
* 🔧 fix: Correct Category Labels and Values in API Model & Adjust Button Class in Prompt List
* 🔧 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
* feat: started with automated CHANGELOG.md
* fix: no `configuration.json` found
* refactor: `configuration.json`
* fix: missing label `configuration.json`
* fix: missing label `configuration.json`
* fix: missing label `configuration.json`
* fix: missing label `configuration.json`
* fix: missing label `configuration.json`
* ci: test new workflow action
* ci: test new workflow action
* ci: test new workflow action
* feat: working CHANGELOG.md generation
* feat: working CHANGELOG.md generation
* feat: working CHANGELOG.md generation
* feat: working CHANGELOG.md generation
* feat: working CHANGELOG.md generation
* feat: working CHANGELOG.md generation
* feat: working CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* fix: separate release and Unreleased workflows CHANGELOG.md generation
* refactor: only trigger the `unreleased-changelog` action on push to `main`
and `generate-release-changelog` only when pushing a tag with `v*.*.*`
* refactor: Runs only every Monday at 00:00 UTC
* 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>
* 🔒 feat: add Two-Factor Authentication (2FA) with backup codes & QR support (#5684)
* working version for generating TOTP and authenticate.
* better looking UI
* refactored + better TOTP logic
* fixed issue with UI
* fixed issue: remove initial setup when closing window before completion.
* added: onKeyDown for verify and disable
* refactored some code and cleaned it up a bit.
* refactored some code and cleaned it up a bit.
* refactored some code and cleaned it up a bit.
* refactored some code and cleaned it up a bit.
* fixed issue after updating to new main branch
* updated example
* refactored controllers
* removed `passport-totp` not used.
* update the generateBackupCodes function to generate 10 codes by default:
* update the backup codes to an object.
* fixed issue with backup codes not working
* be able to disable 2FA with backup codes.
* removed new env. replaced with JWT_SECRET
* ✨ style: improved a11y and style for TwoFactorAuthentication
* 🔒 fix: small types checks
* ✨ feat: improve 2FA UI components
* fix: remove unnecessary console log
* add option to disable 2FA with backup codes
* - add option to refresh backup codes
- (optional) maybe show the user which backup codes have already been used?
* removed text to be able to merge the main.
* removed eng tx to be able to merge
* fix: migrated lang to new format.
* feat: rewrote whole 2FA UI + refactored 2FA backend
* chore: resolving conflicts
* chore: resolving conflicts
* fix: missing packages, because of resolving conflicts.
* fix: UI issue and improved a11y
* fix: 2FA backup code not working
* fix: update localization keys for UI consistency
* fix: update button label to use localized text
* fix: refactor backup codes regeneration and update localization keys
* fix: remove outdated translation for shared links management
* fix: remove outdated 2FA code prompts from translation.json
* fix: add cursor styles for backup codes item based on usage state
* fix: resolve conflict issue
* fix: resolve conflict issue
* fix: resolve conflict issue
* fix: missing packages in package-lock.json
* fix: add disabled opacity to the verify button in TwoFactorScreen
* ⚙ fix: update 2FA logic to rely on backup codes instead of TOTP status
* ⚙️ fix: Simplify user retrieval in 2FA logic by removing unnecessary TOTP secret query
* ⚙️ test: Add unit tests for TwoFactorAuthController and twoFactorControllers
* ⚙️ fix: Ensure backup codes are validated as an array before usage in 2FA components
* ⚙️ fix: Update module path mappings in tests to use relative paths
* ⚙️ fix: Update moduleNameMapper in jest.config.js to remove the caret from path mapping
* ⚙️ refactor: Simplify import paths in TwoFactorAuthController and twoFactorControllers test files
* ⚙️ test: Mock twoFactorService methods in twoFactorControllers tests
* ⚙️ refactor: Comment out unused imports and mock setups in test files for two-factor authentication
* ⚙️ refactor: removed files
* refactor: Exclude totpSecret from user data retrieval in AuthController, LoginController, and jwtStrategy
* refactor: Consolidate backup code verification to apply DRY and remove default array in user schema
* refactor: Enhance two-factor authentication ux/flow with improved error handling and loading state management, prevent redirect to /login
---------
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor: Ensure Axios Errors are less Verbose if No Response
* refactor: Improve error handling in logAxiosError function
* fix: Prevent ModelSelect from rendering for Agent Endpoints
* refactor: Enhance logging functions with type parameter for better clarity
* refactor: Update buildDefaultConvo function to use optional endpoint parameter since we pass a default value for undefined
* refactor: Replace console logs with logger warnings and errors in useNavigateToConvo hook, and handle removed endpoint edge case
* chore: import order
* 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>
* fix: improve file handling by preventing memoization issues, providing config values at run time
* 🌍 i18n: Update translation.json with latest translations
* fix: Missing Translations in Prompt Filters in Prompt Library
* fix: fixed issue with `zh`
feat: added `Estonian` language option
* fix: test for `i18n.ts`
* refactor: `pt` --> `pt-BR` and `pt-PT`
* feat: request access to another language. default is only one language during invite.
Ariakit Combobox was not working well with several virtualization libraries as automated focus management was conflicting with scrolling/styling required of other virtualization methods. The entire strategy was replaced using experimental ariakit virtualization component `SelectRenderer`
Performance of component was also improved as a result of latest ariakit lib changes
* 📦 chore: Update @librechat/agents to version 2.0.5
* fix: Update error handling in AskController and EditController to include overrideParentMessageId when catching errors
* fix: Update parentMessageId assignment in AgentController to prioritize overrideParentMessageId
* 🌍 i18n: Update translation.json with latest translations
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* chore: enforcing language keys to adhere to the new standard.
* chore: enforcing i18n forbids to write plain text in JSX markup
* chore: enforcing i18n forbids to write plain text in JSX markup
* fix: ci with checkbox for unused keys :)
* refactor: removed all the unused `i18n` keys
* 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
* chore: started with updating packages to new version.
(a lot are outdated)
* fix: eslint to pass when no matching files changed.
* fix: eslint to pass when no matching files changed.
* fix: issue with strict in actions with the test
* chore: update more dependencies
* feat: scan for unused imported packages
* feat: scan for unused imported packages
* feat: scan for unused imported packages
* feat: scan for unused imported packages
* feat: scan for unused imported packages
* feat: scan for unused imported packages
* feat: scan for unused imported packages
* chore: removed Unused NPM Packages
* chore: removed Unused NPM Packages in `client/package.json`
* chore: removed Unused NPM Packages in `client/package.json`
* chore: Only comments when there are actual unused dependencies.
* chore: Only comments when there are actual unused dependencies.
* ci: test if it detects unused packages.
* ci: removed unused packages.
* ci: both static and dynamic i18n keys
* ci: revert back to no dynamic. use official nesting
* chore: remove override package: ajv
* feat: manage an 'x-strict': true attribute in openapi specs for assistants which generates function calls with stric attribute
* fix typo and lint errors
---------
Co-authored-by: Olivier Schiavo <olivier.schiavo@wengo.com>
* created: checks for unused i18n keys in codebase.
* updated the file to test this new check on this PR.
* updated the file to test this new check on this PR.
* updated the file to test this new check on this PR.
* updated the file to test this new check on this PR.
* updated the file to test this new check on this PR.
* removed the testing option. will now only run in `client/src/**`
* ✨feat: OAuth for Actions
* WIP: PoC flow state manager
* refactor: Add identifier field to token model from action schema
* chore: fix potential file type issues
* ci: fix type issue with action metadata auth
* fix: ensure FlowManagerOptions has a default ttl value
* WIP: OAUTH actions
* WIP: first pass OAuth Action
* fix: standardize identifier usage in OAuth flow handling
* fix: update token retrieval to include userId in query and use correct identifier
* refacotr: update token retrieval to use userId for OAuth token query
* feat: Tool Call Auth styling
* fix: streamline token creation and add type field to token schema
* refactor: cleanup OAuth flow by encrypting client credentials and ensuring oauth operations only run under condition
* refactor: use encrypted credentials in OAuth callback
* fix: update Token collection indexes to use expiresAt TTL index and not createdAt legacy index
* refactor: enhance Token index cleanup by improving logging and removing redundant index creation logic
* refactor: remove unused OAuth login route and related logic for improved clarity
* refactor: replace fetch with axios for OAuth token exchange and improve error handling
* refactor: better UX after authentication before oauth tool execution
* refactor: implement cleanup handlers for FlowStateManager intervals to enhance resource management
* refactor: encrypt OAuth tokens before storing and decrypt upon retrieval for enhanced security
* refactor: enhance authentication success page with improved styling and countdown feature
* refactor: add response_type parameter to OAuth redirect URI for improved compatibility
* chore: update translation.json new localizations
* chore: remove unused OGDialog import from OGDialogTemplate component
* refactor: Actions Auth using new Dialog styling, use same component with Agents/Assistants
* refactor: update removeNullishValues function to support removal of empty strings and adjust transform usage in schemas
* chore: bump version of librechat-data-provider to 0.7.6991
* refactor: integrate removeNullishValues function to clean metadata before encryption in agent and assistant routes
* refactor: update OAuth input fields to use 'password' type for better security
* refactor: update localization placeholders for sign-in message to use double curly braces
* refactor: add access_type parameter for offline access in createActionTool function
* refactor: implement handleOAuthToken function for token management and encryption
* feat: refresh token support
* refactor: add default expiration for access token and error handling for missing token
* feat: localizations for ActionAuth
* refactor: set refresh token expiration to null to not expire if expiry never given
* fix: prevent crash fromerror within async handleAbortError in AskController, EditController, and AgentController
* feat: Action Callback URL
* 🌍 i18n: Update translation.json with latest translations
* refactor: handle errors in flow state checking to prevent unhandled promise rejections
* fix: improve flow state concurrency to prevent multiple token creation calls
* refactor: RequestExecutor to use separate axios instance
* refactor: improve concurrency flows by keeping completed state until TTL expiry
* refactor: increase TTL for flow state management and adjust monitoring interval
* ci: mock axios instance creation in actions spec
* feat: add Babel and Jest configuration files; implement FlowStateManager tests with concurrency handling
* chore: add disableOAuth prop to ActionsAuth (not implemented for Assistants yet)
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix: ci for locize-pull-published-sync-pr.yml
* fix: ci for locize-pull-published-sync-pr.yml
* fixed missing parameter: base: main
* removed running on pull_request
* chore: migrated eslint v8 to v9
* chore: migrated eslint v8 to v9
* ESLint only checks the files that have changed in the pull request.
* fix: ESLint only checks the files that have changed in the pull request.
* refactor: eslint only on changed files
* refactor: eslint only on changed files or added files
* refactor: eslint only on changed files or added files
* refactor: eslint only on changed files or added files
but only include files that are not deleted (ACMRTUXB: A, C, M, R, T, U, X, B).
* whoops missed something
* better i18n support an internationalization-framework.
* removed unused package
* auto sort for translation.json
* fixed tests with the new locales function
* added new CI actions from locize
* to use locize a mention in the README.md
* to use locize a mention in the README.md
* updated README.md and added TRANSLATION.md to the repo
* updated TRANSLATION.md badges
* updated README.md to go to the TRANSLATION.md when clicking on the Translation Progress badge
* updated TRANSLATION.md and added a new issue template.
* updated TRANSLATION.md and added a new issue template.
* updated issue template to add the iso code link.
* updated the new GitHub actions for `locize`
* updated label for new issue template --> i18n
* fixed type issue
* Fix eslint
* Fix eslint with key-spacing spacing
* fix: error type
* fix: handle undefined values in SortFilterHeader component
* fix: typing in Image component
* fix: handle optional promptGroup in PromptCard component
* fix: update localize function to accept string type and remove unnecessary JSX element
* fix: update localize function to enforce TranslationKeys type for better type safety
* fix: improve type safety and handle null values in Assistants component
* fix: enhance null checks for fileId in FilesListView component
* fix: localize 'Go back' button text in FilesListView component
* fix: update aria-label for menu buttons and add translation for 'Close Menu'
* docs: add Reasoning UI section for Chain-of-Thought AI models in README
* fix: enhance type safety by adding type for message in MultiMessage component
* fix: improve null checks and optional chaining in useAutoSave hook
* fix: improve handling of optional properties in cleanupPreset function
* fix: ensure isFetchingNextPage defaults to false and improve null checks for messages in Search component
* fix: enhance type safety and null checks in useBuildMessageTree hook
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* a11y: silence miscellaneous icons that should not be read by screen reader (#5723, #5724)
* 📝 chore: Update bug report template with additional guidance and version information
* 📝 chore: Update bug report template to guide users on using Discussions for general inquiries and setup help
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🤖 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
* feat: add expiredAt property to Conversation and Message models
Added `expiredAt` property to both Conversation and Message schemas.
Configured `expireAfterSeconds` index in MongoDB to automatically delete documents after a specified period.
* feat(data-provider): add isTemporary and expiredAt properties to support temporary chats
Added `isTemporary` property to TPayload and TSubmission for API calls for temporary chat.
Additionally, added `expiredAt` property to `tConversationSchema` to determine if a chat is temporary.
* feat: implement isTemporary state management
Add Recoil state for tracking temporary conversations, update event handlers to respect temporary chat status
* feat: add configuration to interfaceconfig to hide the temporary chat switch
* feat: add Temporary Chat UI with switch and modify related behaviors
- Added a Temporary Chat switch button at the end of dropdown lists in each model.
- Updated the form background color to black when Temporary Chat is enabled.
- Modified Navigation to exclude Temporary Chats from the chat list.
* fix: exclude Temporary Chats from search results
Updated the getConvosQueried query to ensure that Temporary Chats are not included in the search results.
* fix: hide bookmark button for Temporary Chats
Updated the UI to ensure that the bookmark button is not displayed when a chat is as Temporary Chat.
* chore: update isTemporary state management in ChatRoute
* chore: fix to pass the tests
* 🚀 feat: Add animated search input and improve filtering UI
* 🏄 refactor: Clean up category options and optimize event handlers in ChatGroupItem
* 🚀 refactor: 'Rename Prompt' option and enhance prompt filtering UI
Changed the useUpdatePromptGroup mutation in prompts.ts to replace the JSON.parse(JSON.stringify(...)) clones with structuredClone. This avoids errors when data contains non‑JSON values and improves data cloning reliability
* 🔧 refactor: Update Sharing Prompts UI; fix: Show info message only after updating switch status
* 🔧 refactor: Simplify condition checks and replace button with custom Button component in SharePrompt
* 🔧 refactor: Update DashGroupItem styles and improve accessibility with updated aria-label
* 🔧 refactor: Adjust layout styles in GroupSidePanel and enhance loading skeletons in List component
* 🔧 refactor: Improve layout and styling of AdvancedSwitch component; adjust DashBreadcrumb margin for better alignment
* 🔧 refactor: Add new surface colors for destructive actions and update localization strings for confirmation prompts
* 🔧 refactor: Update PromptForm and PromptName components for improved layout and styling; replace button with custom Button component
* 🔧 refactor: Enhance styling and layout of DashGroupItem, FilterPrompts, and Label components for improved user experience
* 🔧 refactor: Update DeleteBookmarkButton and Label components for improved layout and text handling
* 🔧 refactor: Simplify CategorySelector usage and update destructive surface colors for a11y
* 🔧 refactor: Update styling and layout of PromptName, SharePrompt, and DashGroupItem components; enhance Dropdown functionality with custom renderValue
* 🔧 refactor: Improve layout and styling of various components; update button sizes and localization strings for better accessibility and user experience
* 🔧 refactor: Add useCurrentPromptData hook and enhance RightPanel component; update CategorySelector for improved functionality and accessibility
* 🔧 refactor: Update input components and styling for Command and Description; enhance layout and accessibility in PromptVariables and PromptForm
* 🔧 refactor: Remove useCurrentPromptData hook and clean up related components; enhance PromptVersions layout
* 🔧 refactor: Enhance accessibility by adding aria-labels to buttons and inputs; improve localization for filter prompts
* 🔧 refactor: Enhance accessibility by adding aria-labels to various components; improve layout and styling in PromptForm and CategorySelector
* 🔧 refactor: Enhance accessibility by adding aria-labels to buttons and components; improve dialog roles and descriptions in SharePrompt and PromptForm
* 🔧 refactor: Improve accessibility by adding aria-labels and roles; enhance layout and styling in ChatGroupItem, ListCard, and ManagePrompts components
* 🔧 refactor: Update UI components for improved styling and accessibility; replace button elements with custom Button component and enhance layout in VariableForm, PromptDetails, and PromptVariables
* 🔧 refactor: Improve null checks for group and instanceProjectId in SharePrompt component; enhance readability and maintainability
* style: Enhance AnimatedSearchInput component with TypeScript types; improve conditional rendering for search states and accessibility
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🔧 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
When behind authentication (for eg: Cloudflare Access), browsers
won't send credentials when fetching the manifest file by default.
To fix, this change adds `crossorigin="use-credentials"` to the
manifest link tag by enabling the `useCredentials` option in
VitePWA.
* WIP: end session endpoint
* refactor: move useGetBannerQuery outside of package
* refactor: add queriesEnabled and move useGetEndpointsConfigQuery to data-provider (local)
* refactor: move useGetEndpointsQuery import to data-provider
* refactor: relocate useGetEndpointsQuery import to improve module organization
* refactor: move `useGetStartupConfig` from package to `~/data-provider`
* refactor: move useGetUserBalance to data-provider and update imports
* refactor: update query enabled conditions to include config check
* refactor: remove unused useConfigOverride import from useAppStartup
* refactor: integrate queriesEnabled state into file and search queries and move useGetSearchEnabledQuery to data-provider (local)
* refactor: move useGetUserQuery to data-provider and update imports
* refactor: enhance loginUser mutation with success and error handling as pass in options to hook
* refactor: update enabled condition in queries to handle undefined config
* refactor: enhance authentication mutations with queriesEnabled state management
* refactor: improve conditional rendering for error messages and feature flags in Login component
* refactor: remove unused queriesEnabled state from AuthContextProvider
* refactor: implement queriesEnabled state management in LoginLayout with timeout handling
* refactor: add conditional check for end session endpoint in OpenID strategy
* ci: fix tests after changes
* refactor: remove endSessionEndpoint from user schema and update logoutController to use OpenID issuer's end_session_endpoint
* refactor: update logoutController to use end_session_endpoint from issuer metadata
* 🐛 fix: Prevent processing of non-artifact nodes in artifact plugin
* refactor: remove deprecated fields, add `reasoning_effort`
* refactor: move `reasoning_effort` to the second column in OpenAI settings
* feat: add support for additional AI Gateway provider in extractBaseURL function
* refactor: move `reasoning_effort` field to conversationPreset and remove from agentOptions
* 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>
* implemented Apple Auth login.
Closes: #3438
TODO:
- write config Doc
* removed some comments
* removed comment
* Add unit tests for Apple login strategy
Introduce comprehensive tests for the Apple login strategy, covering new user creation, existing user updates, and error handling scenarios during the authentication flow. Mocks implemented for external dependencies to ensure isolated testing.
* Remove unnecessary blank line in socialLogins.js
* feat: allows admin to see and edits all actions
* feat: allows admin to see and edits all actions
* rollback: admins can edit all actions, no configuration
* fix: admins don't override the user of existing actions and they preserve the user of the assistant when creating a new action
---------
Co-authored-by: Olivier Schiavo <olivier.schiavo@wengo.com>
* chore: remove all bing code
* chore: remove bing code and auto-focus effects
* chore: add back escapeRegExp helper function for regex special character handling
* chore: remove deprecated fields from settings and conversation schema
* fix: ensure default endpoint is set correctly in conversation setup
* feat: add disableFocus option to newConversation for improved search behavior
* ✨ 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(.env.example): add o1-mini and o1-preview to .env.example
* feat(.env.example): add o1 to .env.example
---------
Co-authored-by: Evren Tan <evren.tan@pointr.tech>
Replaced an outdated Vite entry and corrected inconsistencies in dependencies.
Severity: moderate
Websites were able to send any requests to the development server and read the response in vite - https://github.com/advisories/GHSA-vg6x-rcgg-rjx6
* 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: frontend and backend share link logic; feat: qrcode for share link; feat: refresh link
* 🐛 fix: Conditionally render shared link and refactor share link creation logic
* 🐛 fix: Correct conditional check for shareId in ShareButton component
* 🔄 refactor: Update shared links API and data handling; improve query parameters and response structure
* 🔄 refactor: Update shared links pagination and response structure; replace pageNumber with cursor for improved data fetching
* 🔄 refactor: DataTable performance optimization
* fix: delete shared link cache update
* 🔄 refactor: Enhance shared links functionality; add conversationId to shared link model and update related components
* 🔄 refactor: Add delete functionality to SharedLinkButton; integrate delete mutation and confirmation dialog
* 🔄 feat: Add AnimatedSearchInput component with gradient animations and search functionality; update search handling in API and localization
* 🔄 refactor: Improve SharedLinks component; enhance delete functionality and loading states, optimize AnimatedSearchInput, and refine DataTable scrolling behavior
* fix: mutation type issues with deleted shared link mutation
* fix: MutationOptions types
* fix: Ensure only public shared links are retrieved in getSharedLink function
* fix: `qrcode.react` install location
* fix: ensure non-public shared links are not fetched when checking for existing shared links, and remove deprecated .exec() method for queries
* fix: types and import order
* refactor: cleanup share button UI logic, make more intuitive
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🔧 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
Fixes#5310
Add `aria-label="previous"` attribute to the 'Prev' button in the Prompts Panel.
* Modify `client/src/components/Chat/Prompts.tsx` to include `aria-label="previous"` attribute for the button.
* fix: remove local state from Dropdown causing de-sync
* refactor: cleanup STT code, avoid redundant states to prevent de-sync and side effects
* fix: reset transcript after sending final text to prevent data loss
* fix: clear timeout on component unmount to prevent memory leaks
* refactor: SearchBar and Nav components to streamline search functionality and improve state management
* refactor: remove refresh conversations
* chore: update useNewConvo calls to remove hardcoded default index
* refactor: null check for submission in useSSE hook
* refactor: remove useConversation hook and update useSearch to utilize useNewConvo
* refactor: remove conversation and banner store files; consolidate state management into misc; improve typing of families and add messagesSiblingIdxFamily
* refactor: more effectively clear all user/convo state without side effects on logout/delete user
* refactor: replace useParams with useLocation in SearchBar to correctly load conversation
* refactor: update SearchButtons to use button element and improve conversation ID handling
* refactor: use named function for `newConversation` for better call stack tracing
* refactor: enhance TermsAndConditionsModal to support array content and improve type definitions for terms of service
* refactor: add SetConvoProvider and message invalidation when navigating from search results to prevent initial route rendering edge cases
* refactor: rename getLocalStorageItems to localStorage and update imports for consistency
* refactor: move clearLocalStorage function to utils and simplify localStorage clearing logic
* refactor: migrate authentication mutations to a dedicated Auth data provider and update related tests
* ✨ 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: Include iconURL in Bedrock client initialization
* fix: unnecessary filtering for agent file_search files
* chore: use theme bg colors
* refactor: rely on endpoint config for enabling builder links in side navigation instead of parameters
* fix: remove unnecessary keyProvided check for agent builder link
The `express-session` library comes with a session storage meant for
testing by default. That is why you get a message like this when you
start up LibreChat with OIDC enabled:
Warning: connect.session() MemoryStore is not
designed for a production environment, as it will leak
memory, and will not scale past a single process.
LibreChat can already use Redis as a session storage, although Redis support
is still marked as experimental. It also makes the set-up more complex, since
you will need to configure and run yet another service.
This pull request provides a simple alternative by using a in-memory session
store marked as a production-ready alternative by the guys from
`express-session`¹. You can still configure Redis, but this provides a simple,
good default for everyone else.
See also https://github.com/danny-avila/LibreChat/discussions/1014
¹⁾ https://github.com/expressjs/session?tab=readme-ov-file#compatible-session-stores
* 🐛 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
* fix: agent modelSpec iconURLs not being recorded
* fix: prioritize message properties over conversation defaults in icon data
* fix: determine endpoint type from endpointsConfig
* chore: type issue with setting.columnSpan
* chore: remove redundant key indexing for keySchema
* chore: bump version to 0.7.691 in package.json
* chore: add stricter remark-gfm and mdast-util-gfm resolutions/overrides
* chore: remove rollup override and bump vite-plugin-pwa
* chore: reinstall remark-gfm for correct module resolution
* chore: reinstall vite-plugun-pwa
* fix: rendering error for mermaid flowchart syntax
* feat: add submit button ref and enable submit on Ctrl+Enter in EditMessage component
* feat: add save button and keyboard shortcuts for saving and canceling in EditMessage component
* feat: collapse chat on max height
* refactor: implement scrollable detection for textarea on key down events and initial render
* feat: add regenerate button for error handling in HoverButtons, closes#3658
* feat: add functionality to edit latest user message with the up arrow key when the input is empty
* chore: bump @librechat/agents to v1.9.8 for rscript support
* chore: fix @langchain/google-genai dep., match agents
* chore: fix @langchain/google-vertexai to v0.1.5, match with agents
* chore: bump @librechat/agents to v1.9.9
* chore: update @librechat/agents to v1.9.91 and @langchain/google-vertexai to v0.1.6
* chore: increase MAX_FILE_SIZE to 150MB for file uploads
* chore: bump @librechat/agents to v1.9.92
* feat: support `recursionLimit` for agents
* chore: update configuration version to 1.2.1 in librechat.yaml and config.ts
* feat: add R language SVG icon to the assets and include it in ApiKeyDialog
* feat: add support for new vision model 'o1' and exclude 'o1-mini'
* 🎨 feat: improve file display and overflow handling in SidePanel components
* 🎨 feat: enhance bookmarks management UI and improve accessibility features
* 🎨 feat: enhance BookmarkTable and BookmarkTableRow components for improved layout and performance
* 🎨 feat: enhance file display and interaction in FilesView and ImagePreview components
* 🎨 feat: adjust minimum width for filename filter input in DataTable component
* 🎨 feat: enhance file upload UI with improved layout and styling adjustments
* 🎨 feat: add surface-hover-alt color and update FileContainer styling for improved UI
* 🎨 feat: update ImagePreview component styling for improved visual consistency
* 🎨 feat: add MaximizeChatSpace component and integrate chat space maximization feature
* 🎨 feat: enhance DataTable component with transition effects and update Checkbox styling for improved accessibility
* fix: enhance a11y for Bookmark buttons by adding space key support, ARIA labels, and correct html role for key presses
* fix: return focus back to trigger for BookmarkEditDialog (Edit and new bookmark buttons)
* refactor: ShareButton and ExportModal components children prop support; refactor DropdownPopup item handling
* refactor: enhance ExportAndShareMenu and ShareButton components with improved props handling and accessibility features
* refactor: add ref prop support to MenuItemProps and update ExportAndShareMenu and DropdownPopup components so focus correctly returns to menu item
* refactor: enhance ConvoOptions and DeleteButton components with improved props handling and accessibility features
* refactor: add triggerRef support to DeleteButton and update ConvoOptions for improved dialog handling
* refactor: accessible bookmarks menu
* refactor: improve styling and accessibility for bookmarks components
* refactor: add focusLoop support to DropdownPopup and update BookmarkMenu with Tooltip
* refactor: integrate TooltipAnchor into ExportAndShareMenu for enhanced accessibility
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
This commit updates the cache stores in the `getLogStores.js` file to use Redis as the store if the `USE_REDIS` environment variable is enabled. It also adds a new environment variable `DEBUG_MEMORY_CACHE` to enable debugging of the memory cache.
* 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
* fix: prevent mobile nav toggle from being focusable when not in mobile view, add types to <NavToggle/>
* fix: appropriate endpoint menu item role, add up/down focus mgmt, ensure set api key is focusable and accessible
* fix: localize link titles and update text color for improved accessibility in Nav component
* 🔒 fix: update refresh token handling to use plain token instead of hashed token
* 🔒 fix: simplify logoutUser by using plain refresh token for session lookup
* ✨ feat: Implement session management with CRUD operations and integrate into user workflows
* ✨ refactor: Update session model import paths and enhance session creation logic in AuthService
* ✨ refactor: Validate session and user ID formats in session management functions
* ✨ style: Enhance UI components with improved styling and accessibility features
* chore: Update login form tests to use getByTestId instead of getByRole, remove console.log()
* chore: Update login form tests to use getByTestId instead of getByRole
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 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
* 🔃 fix: Safeguard against null token in SSE refresh token handling
* 🔃 fix: Update import path for AnnounceOptions in LiveAnnouncer component
* 🔃 a11y: Add aria-live attribute for accessibility in error messages
* fix: prevent double screen reader notification for toast
* 🔃 a11y: Enhance accessibility for main menus and buttons with ARIA roles and labels
* refactor: better alt text for logo on login page #4095
* refactor: remove unused import for DropdownNoState in Voices component
* fix: Focus management issue in the Export Options Modal #4100
* Feature: Added ability to send current date and time to v1 and v2 assistants
* remove date_feature.patch
* fix: rename append_today_date to append_current_datetime
* feat: Refactor time handling in chatV1 and chatV2, add date and time utility functions
* fix: Add warning log and response for missing run values in abortRun middleware
---------
Co-authored-by: Max Sanna <max@maxsanna.com>
* style: update AdminSettings dialog content styles for improved accessibility/theming
* style: update icon colors in ExportAndShareMenu for improved theming
* feat: enhance DropdownPopup component with additional props for customization
* feat: add role selection dropdown to AdminSettings for enhanced user permissions management
* feat: add role selection dropdown to AdminSettings for Prompt permission management
* style: add gap to button in AdminSettings for improved layout
* feat: add warning message for Admin role access in Permissions settings
* 📑 docs: update README.md to enhance feature descriptions and organization
* 📑 docs: Revise README.md for improved feature clarity and organization
* 📑 docs: Update README.md for improved clarity and organization of AI provider compatibility
* 📑 docs: Update AI Model Selection section in README.md for improved clarity and consistency
* 📑 docs: Update README.md to include Email Login support in Multi-User Authentication section
* fix: double decoding of URL params
* fix: prevent streaming options for O1 model (azure)
* fix: update @langchain/openai to version 0.3.14 in package-lock.json
* chore(AuthContext): typing
* chore(useTimeout): typing
* fix: shared link redirecting to login when code block includes "Run Code" button
* fix: typing
* feat: Code Interpreter API & File Search Agent Uploads
chore: add back code files
wip: first pass, abstract key dialog
refactor: influence checkbox on key changes
refactor: update localization keys for 'execute code' to 'run code'
wip: run code button
refactor: add throwError parameter to loadAuthValues and getUserPluginAuthValue functions
feat: first pass, API tool calling
fix: handle missing toolId in callTool function and return 404 for non-existent tools
feat: show code outputs
fix: improve error handling in callTool function and log errors
fix: handle potential null value for filepath in attachment destructuring
fix: normalize language before rendering and prevent null return
fix: add loading indicator in RunCode component while executing code
feat: add support for conditional code execution in Markdown components
feat: attachments
refactor: remove bash
fix: pass abort signal to graph/run
refactor: debounce and rate limit tool call
refactor: increase debounce delay for execute function
feat: set code output attachments
feat: image attachments
refactor: apply message context
refactor: pass `partIndex`
feat: toolCall schema/model/methods
feat: block indexing
feat: get tool calls
chore: imports
chore: typing
chore: condense type imports
feat: get tool calls
fix: block indexing
chore: typing
refactor: update tool calls mapping to support multiple results
fix: add unique key to nav link for rendering
wip: first pass, tool call results
refactor: update query cache from successful tool call mutation
style: improve result switcher styling
chore: note on using \`.toObject()\`
feat: add agent_id field to conversation schema
chore: typing
refactor: rename agentMap to agentsMap for consistency
feat: Agent Name as chat input placeholder
chore: bump agents
📦 chore: update @langchain dependencies to latest versions to match agents package
📦 chore: update @librechat/agents dependency to version 1.8.0
fix: Aborting agent stream removes sender; fix(bedrock): completion removes preset name label
refactor: remove direct file parameter to use req.file, add `processAgentFileUpload` for image uploads
feat: upload menu
feat: prime message_file resources
feat: implement conversation access validation in chat route
refactor: remove file parameter from processFileUpload and use req.file instead
feat: add savedMessageIds set to track saved message IDs in BaseClient, to prevent unnecessary double-write to db
feat: prevent duplicate message saves by checking savedMessageIds in AgentController
refactor: skip legacy RAG API handling for agents
feat: add files field to convoSchema
refactor: update request type annotations from Express.Request to ServerRequest in file processing functions
feat: track conversation files
fix: resendFiles, addPreviousAttachments handling
feat: add ID validation for session_id and file_id in download route
feat: entity_id for code file uploads/downloads
fix: code file edge cases
feat: delete related tool calls
feat: add stream rate handling for LLM configuration
feat: enhance system content with attached file information
fix: improve error logging in resource priming function
* WIP: PoC, sequential agents
WIP: PoC Sequential Agents, first pass content data + bump agents package
fix: package-lock
WIP: PoC, o1 support, refactor bufferString
feat: convertJsonSchemaToZod
fix: form issues and schema defining erroneous model
fix: max length issue on agent form instructions, limit conversation messages to sequential agents
feat: add abort signal support to createRun function and AgentClient
feat: PoC, hide prior sequential agent steps
fix: update parameter naming from config to metadata in event handlers for clarity, add model to usage data
refactor: use only last contentData, track model for usage data
chore: bump agents package
fix: content parts issue
refactor: filter contentParts to include tool calls and relevant indices
feat: show function calls
refactor: filter context messages to exclude tool calls when no tools are available to the agent
fix: ensure tool call content is not undefined in formatMessages
feat: add agent_id field to conversationPreset schema
feat: hide sequential agents
feat: increase upload toast duration to 10 seconds
* refactor: tool context handling & update Code API Key Dialog
feat: toolContextMap
chore: skipSpecs -> useSpecs
ci: fix handleTools tests
feat: API Key Dialog
* feat: Agent Permissions Admin Controls
feat: replace label with button for prompt permission toggle
feat: update agent permissions
feat: enable experimental agents and streamline capability configuration
feat: implement access control for agents and enhance endpoint menu items
feat: add welcome message for agent selection in localization
feat: add agents permission to access control and update version to 0.7.57
* fix: update types in useAssistantListMap and useMentions hooks for better null handling
* feat: mention agents
* fix: agent tool resource race conditions when deleting agent tool resource files
* feat: add error handling for code execution with user feedback
* refactor: rename AdminControls to AdminSettings for clarity
* style: add gap to button in AdminSettings for improved layout
* refactor: separate agent query hooks and check access to enable fetching
* fix: remove unused provider from agent initialization options, creates issue with custom endpoints
* refactor: remove redundant/deprecated modelOptions from AgentClient processes
* chore: update @librechat/agents to version 1.8.5 in package.json and package-lock.json
* fix: minor styling issues + agent panel uniformity
* fix: agent edge cases when set endpoint is no longer defined
* refactor: remove unused cleanup function call from AppService
* fix: update link in ApiKeyDialog to point to pricing page
* fix: improve type handling and layout calculations in SidePanel component
* fix: add missing localization string for agent selection in SidePanel
* chore: form styling and localizations for upload filesearch/code interpreter
* fix: model selection placeholder logic in AgentConfig component
* style: agent capabilities
* fix: add localization for provider selection and improve dropdown styling in ModelPanel
* refactor: use gpt-4o-mini > gpt-3.5-turbo
* fix: agents configuration for loadDefaultInterface and update related tests
* feat: DALLE Agents support
* fix: azure validation/extraction types
* fix: typing, add optional chaining for modelGroup and groupMap properties; expect azureOpenAIApiVersion in serverless tests
* fix: add support for azureOpenAIApiVersion and api-key in serverless mode across clients
* chore: update CONFIG_VERSION to 1.1.8, data-provider bump
* Update librechat.example.yaml with Portkey AI example
* Update librechat.example.yaml
---------
Co-authored-by: Danny Avila <danacordially@gmail.com>
* 🔧 refactor: replace doubleClickHandler with onDoubleClick in slider components
* 🔧 refactor: consolidate DynamicInput and DynamicInputNumber components into a single DynamicInput component; fix: UI crashing when typing a character instead of number in max context/output tokens
* 🔧 style: update component styles to use bg-surface-secondary and bg-surface-tertiary for improved UI consistency
* fix: sanitize filename in multer storage callback
* fix: ensure temporary image upload file is deleted after processing
* fix: prevent cleanup flag from being set to false before actually deleted
* refactor: user avatar, typing, use 'file' for formData instead of 'input', add disk storage, use localization
* fix: update Avatar component to include image dimensions in formData and refactor editor reference type
* fix: refactor avatar upload handling to use fs for file reading and enhance file validation
* fix: ensure temporary image upload file is deleted after processing
* fix: refactor avatar upload routes and handlers for agents and assistants, improve file handling and validation
* fix: improve audio file validation and cleanup
* fix: add filename sanitization utility and integrate it into multer storage configuration
* fix: update group project ID check for null and refactor delete prompt group response type
* fix: invalid access control for deleting prompt groups
* fix: add error handling and logging to checkBan middleware
* fix: catch conversation parsing errors
* chore: revert unnecessary height and width parameters from avatar upload
* chore: update librechat-data-provider version to 0.7.55
* style: ensure KaTeX can spread across visible space
* chore: typing
* refactor: create file filter from custom fileConfig, if provided
* refactor: use logger utility to avoid overly verbose axios error logs when using RAG_API
* fix(useFileHandling): use memoization/callbacks to make sure the appropriate fileConfig is used; refactor: move endpoint to first field applied to formdata
* chore: update librechat-data-provider version to 0.7.54
* chore: revert type change
* fix: bedrock tool name regex
* fix: pass args as single input, attempt json first.
* refactor: remove toolMap from agent tool load as is not used
* fix: update formatAgentMessages test to use strictEqual for args comparison, testing new behavior
* feat: Known Endpoint, xAI
* chore: update librechat-data-provider version to 0.7.53
* ci: name property removal
* feat: add XAI_API_KEY to example environment variables
* chore: actions typing
* fix(actions): implement request executor pattern to prevent concurrent execution issues
BREAKING CHANGE: ActionRequest now uses a RequestExecutor pattern for isolated request state
- Introduce RequestConfig class to store immutable configuration
- Add RequestExecutor class to handle isolated request state for each execution
- Modify ActionRequest to act as a facade creating new executors for each operation
- Maintain backward compatibility through delegation and getters
- Add TypeScript types for better type safety
- Fix race conditions in concurrent executions with auth and params
This change prevents state mutation issues when the same action is called
multiple times concurrently, particularly when using authentication. Each
request now gets its own isolated state through a new executor instance,
solving race conditions while maintaining the existing API interface.
* ci: test isolation/immutatability
* chore: Update version to 0.7.51 in data-provider package
* refactor(actions): refactor createActionTool to use request executor pattern
- added aria-expanded attribute to indicate the panel's expanded/collapsed state
- added aria-controls attribute to specify the element controlled by the button
- updated aria-label using the localize function for better description
* refactor: move o1 model check, after vision request check
* feat(server): add configurable cache headers for index.html
• Add environment variables to control index.html cache headers
• Default to no-cache configuration for consistent app updates
• Document cache control options in .env.example
* oidc-changes Initial attempt at testing openidStrategy and adding OPENID_USERNAME_CLAIM setting
* oidc-changes Add OPENID_NAME_CLAIM
* oidc-changes cleanup oidc test code
* oidc-changes using mongo memory server for test
* oidc-changes Change tests to expect username all lowercase
* oidc-changes Add more tests
* chore: linting
* refactor: Simplify OpenID full name retrieval logic
* refactor: Simplify OpenID user info retrieval logic
* refactor: move helper to openidStrategy.js
---------
Co-authored-by: alihacks <alihacks@pm.me>
* fix: ReDoS in ChatGPT Import
* ci: should correctly process citations from real ChatGPT data
* ci: Add ReDoS vulnerability test for processAssistantMessage
* refactor: Update thread management and citation handling
* refactor(validateImageRequest): robust validation
* refactor(Prompt.js): update name search regex to escape special characters
* refactor(Preset): exclude user from preset update to prevent mass assignment
* refactor(files.js): Improve file deletion process
* ci: updated validateImageRequest.spec.js
* a11y: plugin pagination
* refactor(CreatePromptForm.tsx): Improve input field styling
* chore(Prompts): typing and accessibility
* fix: prompt creation access role check
* chore: remove duplicate jsdocs
* chore: remove comparisons
* feat: use prompt caching for translations
* chore: wip translation readme
* i18n: korean translations
* refactor: use promises for faster translation processing
* refactor: update translation model to 'claude-3-5-sonnet-20241022'
* refactor: optimize sleep duration for translation processing
* i18n: add missing keys
* refactor: standardize languages in their own respective languages
* Refactor translation instructions in README.md
* 🔘 a11y: Improve Contrast of Switch/Toggles to WCAG Standard
* refactor: Improve file attachment accessibility in Chat Input component
* refactor: clear input ref value before clicks
The changes include:
- In the agent controller:
- Removed the parsing of the avatar metadata from the request body.
- Fetched the avatar data from the agent object using the agent ID.
- Updated the error logging when fetching the agent.
- Updated the deleteFileByFilter function to include the user ID when deleting the old avatar file.
- In the assistant controller:
- Removed the parsing of the metadata from the request body.
- Fetched the metadata from the assistant object using the assistant ID.
- Updated the error logging when fetching the assistant.
- Updated the deleteFileByFilter function to include the user ID when deleting the old avatar file.
* fix(Agents): remove test code in openAI/llm.js
* refactor: add use of enums in encodeAndFormat
* fix: image attachment payload formatting for agents
* chore: imports
* feat: Refactor ChatForm and StopButton components for improved styling and localization
* feat: Refactor AudioRecorder, ChatForm, AttachFile, and SendButton components for improved styling and layout
* feat: Add RevokeAllKeys component and update styling for buttons and inputs
* feat: Refactor ClearChats component and update ClearConvos functionality for improved clarity and user experience
* feat: Remove ClearConvos component and update related imports and functionality in Avatar and DeleteCacheButton components
* feat: Rename DeleteCacheButton to DeleteCache and update related imports; enhance confirmation message in localization
* feat: Update ChatForm layout for RTL support and improve component structure
* feat: Adjust ChatForm layout for improved RTL support and alignment
* feat: Refactor Bookmark components to use new UI elements and improve styling
* feat: Update FileSearch and ShareAgent components for improved button styling and layout
* feat: Update ChatForm and TextareaHeader styles for improved UI consistency
* feat: Refactor Nav components for improved styling and layout adjustments
* feat: Update button sizes and padding for improved UI consistency across chat components
* feat: Remove ClearChatsButton test file as part of code cleanup
* refactor(OpenAIClient): titleChatCompletion try/catch
* fix: remove duplicate concatenation as seems to be handled by client SDK now
* fix: assistants image upload
* chore: imports order
* refactor: move file mutations to dedicated file, improve typing
* refactor(ChatForm): utilize FileFormWrapper to consolidate file upload logic/rendering to single parent
* refactor: better TSX heirarchies between AttachFile and FileFormWrapper
* refactor: `abortUpload` WIP
* fix: file debugging and file upload issues
* refactor: reject promise outright if axios intercepted error does not include response property
* chore: bump data-provider version to 0.7.428
* refactor: Add return type to localize function in Translation.ts
* refactor: allow message file attachment upload request cancellations, and add localizations for file upload errors
* refactor: include Azure OpenAI in paramEndpoints set
* fix: assistant form uploads and better typing
* refactor: consolidate logic
* chore: cleanup type issues in client/src/utils/endpoints
* refactor: use Constant enum for 'new' conversationId
* refactor: select assistant model if not provided for model spec
* fix: agent initialization, add `collectedUsage` handling
* style: improve side panel styling
* refactor(loadAgent): Optimize order agent project ID retrieval
* feat: code execution
* fix: typing issues
* feat: ExecuteCode content part
* refactor: use local state for default collapsed state of analysis content parts
* fix: code parsing in ExecuteCode component
* chore: bump agents package, export loadAuthValues
* refactor: Update handleTools.js to use EnvVar for code execution tool authentication
* WIP
* feat: download code outputs
* fix(useEventHandlers): type issues
* feat: backend handling for code outputs
* Refactor: Remove console.log statement in Part.tsx
* refactor: add attachments to TMessage/messageSchema
* WIP: prelim handling for code outputs
* feat: attachments rendering
* refactor: improve attachments rendering
* fix: attachments, nullish edge case, handle attachments from event stream, bump agents package
* fix filename download
* fix: tool assignment for 'run code' on agent creation
* fix: image handling by adding attachments
* refactor: prevent agent creation without provider/model
* refactor: remove unnecessary space in agent creation success message
* refactor: select first model if selecting provider from empty on form
* fix: Agent avatar bug
* fix: `defaultAgentFormValues` causing boolean typing issue and typeerror
* fix: capabilities counting as tools, causing duplication of them
* fix: formatted messages edge case where consecutive content text type parts with the latter having tool_call_ids would cause consecutive AI messages to be created. furthermore, content could not be an array for tool_use messages (anthropic limitation)
* chore: bump @librechat/agents dependency to version 1.6.9
* feat: bedrock agents
* feat: new Agents icon
* feat: agent titling
* feat: agent landing
* refactor: allow sharing agent globally only if user is admin or author
* feat: initial AgentPanelSkeleton
* feat: AgentPanelSkeleton
* feat: collaborative agents
* chore: add potential authorName as part of schema
* chore: Remove unnecessary console.log statement
* WIP: agent model parameters
* chore: ToolsDialog typing and tool related localization chnages
* refactor: update tool instance type (latest langchain class), and rename google tool to 'google' proper
* chore: add back tools
* feat: Agent knowledge files upload
* refactor: better verbiage for disabled knowledge
* chore: debug logs for file deletions
* chore: debug logs for file deletions
* feat: upload/delete agent knowledge/file-search files
* feat: file search UI for agents
* feat: first pass, file search tool
* chore: update default agent capabilities and info
* allow other ldap field besides "mail", or fallback to made up email
* chore(ldap): add detailed logging for email fallback scenarios
---------
Co-authored-by: Maxim Bonnaerens <maxim@bonnaerens.be>
* feat(types): Add global window interface for Google Tag Manager
* refactor(Chat/Footer): Move GTM initialization to useEffect for better lifecycle management
* fix(hooks): add useEffect to initialize TagManager conditionally
* chore: remove double import of TrashIcon
* fix(convos): eslint warnings
* ci(convos): add test for month sorting
* fix(convos): grouping by month in chronological order instead of alphabetical, optimize sort
* ci: additional tests for conversation sorting
* chore: fix eslint disable rule
* chore: imports, use constant enum for 'new' value
* fix: test dependent on current date
* fix: modal styling issue, where buttons in light mode are not accessible/visible
* refactor: use MarkdownLite instead
* chore: make inner content accessible
* inital Tooltip implementation and test
* style(tooltip): L/R sidePanel and Nav
* style(tooltip): unarchive button; refactor: `useArchiveHandler` and `ArchiveButton`
* style(tooltip): Delete button
* refactor: remove unused className prop in DeleteButton component
* style(tooltip): finish final tooltip and fix bookmark edit and delete button
* refactor(ui): remove TooltipTest and DropDownMenu component and unused imports
* style: update mobile UI
* fix: sidePanel icon not showing
* feat(AttachFile): add tooltip
* fix(NavToggle): remove button
without this button, kb users don't have to manually press 2 times to change the focus
Also, tooltips with buttons focus don't trigger
* fix: right side panel issue with double button
* fix: merge issues
* fix: sharedLink table issue
* chore: update ariakit and framer-motion version
* a11y: kb toggle for sidebar
* feat: tooltip for some buttons
* feat: use AWS cascading default providers if credentials are omitted
Environment variables exposed via process.env
SSO credentials from token cache
Web identity token credentials
Shared credentials and config ini files
The EC2/ECS Instance Metadata Service
The default credential provider will invoke one provider at a time and only continue to the next if no credentials have been located. For example, if the process finds values defined via the AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY environment variables, the files at ~/.aws/credentials and ~/.aws/config will not be read, nor will any messages be sent to the Instance Metadata Service.
* fix: usage check in OpenAIClient
* refactor: Improve usage check in OpenAIClient
* feat: o1 default response sender string
* feat: add o1 models to default openai models list, add `no_system_messages` error type; refactor: use error type as localization key
* refactor(MessageEndpointIcon): differentiate openAI icon model color for o1 models
* refactor(AnthropicClient): use new input/output tokens keys; add prompt caching for claude-3-opus
* refactor(BaseClient): to use new input/output tokens keys; update typedefs
* feat: initial o1 model handling, including token cost complexity
* EXPERIMENTAL: special handling for o1 model with custom instructions
* feat: Add banner schema and model
* feat: Add optional JwtAuth
To handle the conditional logic with and without authentication within the model.
* feat: Add an endpoint to retrieve a banner
* feat: Add implementation for client to use banner and access API
* feat: Display a banner on UI
* feat: Script for updating and deleting banners
* style: Update banner style
* fix: Adjust the height when the banner is displayed
* fix: failed specs
* ✨ v0.7.5-rc2
* docs: update README
* refactor(settings): Update rememberForkOption default value
* a11y: proper screen reader announcements for content blocks
* Update version to 0.7.423 in package-lock.json and packages/data-provider/package.json
* chore: rename rememberForkOption -> rememberDefaultFork to apply new default value
* fix: headlessui menu stealing focus from Settings Dialog when pressing Enter
* feat: settings tba accessible
* refactor: cleanup unused code
* refactor: improve accessibility and user experience in ChatDirection component
* style: focus ring primary class
* improve a11y of avatar dialog
* style: a11y improvements for Settings
* style: focus ring primary class in OriginalDialog component
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor(EditMessage): avoid manipulation of native paste handling, leverage react-hook-form for textarea changes
* style: apply better theming for MinimalIcon
* fix(useVoicesQuery/useCustomConfigSpeechQuery): make sure to only try request once per render
* feat: edit message content parts
* fix(useCopyToClipboard): handle both assistants and agents content blocks
* refactor: remove save & submit and update text content correctly
* chore(.env.example/config): exclude unsupported bedrock models
* feat: artifacts for aws bedrock
* fix: export options for bedrock conversations
* fix: remove duplicate keys in German language translations
* wip: multi-convo role permissions
* ci: Update loadDefaultInterface tests due to MULTI_CONVO
* ci: update Role.spec.js with tests for MULTI_CONVO permission type
* fix: Update ContentParts component to handle undefined content array
* feat: render Multi-Convo based on UI permissions
* feat: Add BedrockIcon component to SVG library
* feat: EModelEndpoint.bedrock
* feat: first pass, bedrock chat. note: AgentClient is returning `agents` as conversation.endpoint
* fix: declare endpoint in initialization step
* chore: Update @librechat/agents dependency to version 1.4.5
* feat: backend content aggregation for agents/bedrock
* feat: abort agent requests
* feat: AWS Bedrock icons
* WIP: agent provider schema parsing
* chore: Update EditIcon props type
* refactor(useGenerationsByLatest): make agents and bedrock editable
* refactor: non-assistant message content, parts
* fix: Bedrock response `sender`
* fix: use endpointOption.model_parameters not endpointOption.modelOptions
* fix: types for step handler
* refactor: Update Agents.ToolCallDelta type
* refactor: Remove unnecessary assignment of parentMessageId in AskController
* refactor: remove unnecessary assignment of parentMessageId (agent request handler)
* fix(bedrock/agents): message regeneration
* refactor: dynamic form elements using react-hook-form Controllers
* fix: agent icons/labels for messages
* fix: agent actions
* fix: use of new dynamic tags causing application crash
* refactor: dynamic settings touch-ups
* refactor: update Slider component to allow custom track class name
* refactor: update DynamicSlider component styles
* refactor: use Constants value for GLOBAL_PROJECT_NAME (enum)
* feat: agent share global methods/controllers
* fix: agents query
* fix: `getResponseModel`
* fix: share prompt a11y issue
* refactor: update SharePrompt dialog theme styles
* refactor: explicit typing for SharePrompt
* feat: add agent roles/permissions
* chore: update @librechat/agents dependency to version 1.4.7 for tool_call_ids edge case
* fix(Anthropic): messages.X.content.Y.tool_use.input: Input should be a valid dictionary
* fix: handle text parts with tool_call_ids and empty text
* fix: role initialization
* refactor: don't make instructions required
* refactor: improve typing of Text part
* fix: setShowStopButton for agents route
* chore: remove params for now
* fix: add streamBuffer and streamRate to help prevent 'Overloaded' errors from Anthropic API
* refactor: remove console.log statement in ContentRender component
* chore: typing, rename Context to Delete Button
* chore(DeleteButton): logging
* refactor(Action): make accessible
* style(Action): improve a11y again
* refactor: remove use/mention of mongoose sessions
* feat: first pass, sharing agents
* feat: visual indicator for global agent, remove author when serving to non-author
* wip: params
* chore: fix typing issues
* fix(schemas): typing
* refactor: improve accessibility of ListCard component and fix console React warning
* wip: reset templates for non-legacy new convos
* Revert "wip: params"
This reverts commit f8067e91d4.
* Revert "refactor: dynamic form elements using react-hook-form Controllers"
This reverts commit 2150c4815d.
* fix(Parameters): types and parameter effect update to only update local state to parameters
* refactor: optimize useDebouncedInput hook for better performance
* feat: first pass, anthropic bedrock params
* chore: paramEndpoints check for endpointType too
* fix: maxTokens to use coerceNumber.optional(),
* feat: extra chat model params
* chore: reduce code repetition
* refactor: improve preset title handling in SaveAsPresetDialog component
* refactor: improve preset handling in HeaderOptions component
* chore: improve typing, replace legacy dialog for SaveAsPresetDialog
* feat: save as preset from parameters panel
* fix: multi-search in select dropdown when using Option type
* refactor: update default showDefault value to false in Dynamic components
* feat: Bedrock presets settings
* chore: config, fix agents schema, update config version
* refactor: update AWS region variable name in bedrock options endpoint to BEDROCK_AWS_DEFAULT_REGION
* refactor: update baseEndpointSchema in config.ts to include baseURL property
* refactor: update createRun function to include req parameter and set streamRate based on provider
* feat: availableRegions via config
* refactor: remove unused demo agent controller file
* WIP: title
* Update @librechat/agents to version 1.5.0
* chore: addTitle.js to handle empty responseText
* feat: support images and titles
* feat: context token updates
* Refactor BaseClient test to use expect.objectContaining
* refactor: add model select, remove header options params, move side panel params below prompts
* chore: update models list, catch title error
* feat: model service for bedrock models (env)
* chore: Remove verbose debug log in AgentClient class following stream
* feat(bedrock): track token spend; fix: token rates, value key mapping for AWS models
* refactor: handle streamRate in `handleLLMNewToken` callback
* chore: AWS Bedrock example config in `.env.example`
* refactor: Rename bedrockMeta to bedrockGeneral in settings.ts and use for AI21 and Amazon Bedrock providers
* refactor: Update `.env.example` with AWS Bedrock model IDs URL and additional notes
* feat: titleModel support for bedrock
* refactor: Update `.env.example` with additional notes for AWS Bedrock model IDs
* fix focus for cancel button in convo delete modal window #3829
* add aria-hidden and aria-label to X and Check svg/button respectively and updated OGDialogClose focus color
* update rename, newchat, newchat icon, ConvoOptions icon
* agents - phase 1 (#30)
* chore: copy assistant files
* feat: frontend and data-provider
* feat: backend get endpoint test
* fix(MessageEndpointIcon): switched to AgentName and AgentAvatar
* fix: small fixes
* fix: agent endpoint config
* fix: show Agent Builder
* chore: install agentus
* chore: initial scaffolding for agents
* fix: updated Assistant logic to Agent Logic for some Agent components
* WIP first pass, demo of agent package
* WIP: initial backend infra for agents
* fix: agent list error
* wip: agents routing
* chore: Refactor useSSE hook to handle different data events
* wip: correctly emit events
* chore: Update @librechat/agentus npm dependency to version 1.0.9
* remove comment
* first pass: streaming agent text
* chore: Remove @librechat/agentus root-level workspace npm dependency
* feat: Agent Schema and Model
* fix: content handling fixes
* fix: content message save
* WIP: new content data
* fix: run step issue with tool calls
* chore: Update @librechat/agentus npm dependency to version 1.1.5
* feat: update controller and agent routes
* wip: initial backend tool and tool error handling support
* wip: tool chunks
* chore: Update @librechat/agentus npm dependency to version 1.1.7
* chore: update tool_call typing, add test conditions and logs
* fix: create agent
* fix: create agent
* first pass: render completed content parts
* fix: remove logging, fix step handler typing
* chore: Update @librechat/agentus npm dependency to version 1.1.9
* refactor: cleanup maps on unmount
* chore: Update BaseClient.js to safely count tokens for string, number, and boolean values
* fix: support subsequent messages with tool_calls
* chore: export order
* fix: select agent
* fix: tool call types and handling
* chore: switch to anthropic for testing
* fix: AgentSelect
* refactor: experimental: OpenAIClient to use array for intermediateReply
* fix(useSSE): revert old condition for streaming legacy client tokens
* fix: lint
* revert `agent_id` to `id`
* chore: update localization keys for agent-related components
* feat: zod schema handling for actions
* refactor(actions): if no params, no zodSchema
* chore: Update @librechat/agentus npm dependency to version 1.2.1
* feat: first pass, actions
* refactor: empty schema for actions without params
* feat: Update createRun function to accept additional options
* fix: message payload formatting; feat: add more client options
* fix: ToolCall component rendering when action has no args but has output
* refactor(ToolCall): allow non-stringy args
* WIP: first pass, correctly formatted tool_calls between providers
* refactor: Remove duplicate import of 'roles' module
* refactor: Exclude 'vite.config.ts' from TypeScript compilation
* refactor: fix agent related types
> - no need to use endpoint/model fields for identifying agent metadata
> - add `provider` distinction for agent-configured 'endpoint'
- no need for agent-endpoint map
- reduce complexity of tools as functions into tools as string[]
- fix types related to above changes
- reduce unnecessary variables for queries/mutations and corresponding react-query keys
* refactor: Add tools and tool_kwargs fields to agent schema
* refactor: Remove unused code and update dependencies
* refactor: Update updateAgentHandler to use req.body directly
* refactor: Update AgentSelect component to use localized hooks
* refactor: Update agent schema to include tools and provider fields
* refactor(AgentPanel): add scrollbar gutter, add provider field to form, fix agent schema required values
* refactor: Update AgentSwitcher component to use selectedAgentId instead of selectedAgent
* refactor: Update AgentPanel component to include alternateName import and defaultAgentFormValues
* refactor(SelectDropDown): allow setting value as option while still supporting legacy usage (string values only)
* refactor: SelectDropdown changes - Only necessary when the available values are objects with label/value fields and the selected value is expected to be a string.
* refactor: TypeError issues and handle provider as option
* feat: Add placeholder for provider selection in AgentPanel component
* refactor: Update agent schema to include author and provider fields
* fix: show expected 'create agent' placeholder when creating agent
* chore: fix localization strings, hide capabilities form for now
* chore: typing
* refactor: import order and use compact agents schema for now
* chore: typing
* refactor: Update AgentForm type to use AgentCapabilities
* fix agent form agent selection issues
* feat: responsive agent selection
* fix: Handle cancelled fetch in useSelectAgent hook
* fix: reset agent form on accordion close/open
* feat: Add agent_id to default conversation for agents endpoint
* feat: agents endpoint request handling
* refactor: reset conversation model on agent select
* refactor: add `additional_instructions` to conversation schema, organize other fields
* chore: casing
* chore: types
* refactor(loadAgentTools): explicitly pass agent_id, do not pass `model` to loadAgentTools for now, load action sets by agent_id
* WIP: initial draft of real agent client initialization
* WIP: first pass, anthropic agent requests
* feat: remember last selected agent
* feat: openai and azure connected
* fix: prioritize agent model for runs unless an explicit override model is passed from client
* feat: Agent Actions
* fix: save agent id to convo
* feat: model panel (#29)
* feat: model panel
* bring back comments
* fix: method still null
* fix: AgentPanel FormContext
* feat: add more parameters
* fix: style issues; refactor: Agent Controller
* fix: cherry-pick
* fix: Update AgentAvatar component to use AssistantIcon instead of BrainCircuit
* feat: OGDialog for delete agent; feat(assistant): update Agent types, introduced `model_parameters`
* feat: icon and general `model_parameters` update
* feat: use react-hook-form better
* fix: agent builder form reset issue when switching panels
* refactor: modularize agent builder form
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* fix: AgentPanel and ModelPanel type issues and use `useFormContext` and `watch` instead of `methods` directly and `useWatch`.
* fix: tool call issues due to invalid input (anthropic) of empty string
* fix: handle empty text in Part component
---------
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
* refactor: remove form ModelPanel and fixed nested ternary expressions in AgentConfig
* fix: Model Parameters not saved correctly
* refactor: remove console log
* feat: avatar upload and get for Agents (#36)
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
* chore: update to public package
* fix: typing, optional chaining
* fix: cursor not showing for content parts
* chore: conditionally enable agents
* ci: fix azure test
* ci: fix frontend tests, fix eslint api
* refactor: Remove unused errorContentPart variable
* continue of the agent message PR (#40)
* last fixes
* fix: agentMap
* pr merge test (#41)
* fix: model icon not fetching correctly
* remove console logs
* feat: agent name
* refactor: pass documentsMap as a prop to allow re-render of assistant form
* refactor: pass documentsMap as a prop to allow re-render of assistant form
* chore: Bump version to 0.7.419
* fix: TypeError: Cannot read properties of undefined (reading 'id')
* refactor: update AgentSwitcher component to use ControlCombobox instead of Combobox
---------
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
* Added UI for Terms and Conditions Modal Dialogue
* Handled the logout on not accepting
* Added logic for terms acceptance
* Add terms and conditions modal
* Fixed bug on terms and conditions modal, clicking out of it won't close it now
* Added acceptance of Terms to Database
* Removed unnecessary api endpoints from index.js
* Added NPM script to reset terms acceptance
* Added translations, markdown terms and samples
* Merged terms and conditions modal feature
* feat/Modal Terms and Conditions Dialog
* Amendments as requested by maintainers
* Reset package-lock (again)
* fix: type issues
* feat: Fix document title setting in Conversation component
* style: new chat theme
* fix: No keyboard access to chat menus in the chat history #3788
* fix: Menu button in the chat history area does not indicate its state #3823
* refactor: use ariakit for DropdownPopup
* style: update sticky z-index in NewChat component
* style: update ConvoOptions menu button styling
* refactor: remove duplicate localStorage lang call
* refactor: use cookies to handle langcode
* feat: override index.html lang w/ cookie pref
* refactor: only read index on server start
* refactor: rename lang cookie & localstorage as backup
* refactor: use atomWithLocalStorage in language store
* fix: forced reflow warning in language select
# Set to determine which user info property returned from OpenID Provider to store as the User's username
OPENID_USERNAME_CLAIM=
# Set to determine which user info property returned from OpenID Provider to store as the User's name
OPENID_NAME_CLAIM=
# Optional audience parameter for OpenID authorization requests
OPENID_AUDIENCE=
OPENID_BUTTON_LABEL=
OPENID_IMAGE_URL=
# Set to true to automatically redirect to the OpenID provider when a user visits the login page
# This will bypass the login form completely for users, only use this if OpenID is your only authentication method
OPENID_AUTO_REDIRECT=false
# Set to true to use PKCE (Proof Key for Code Exchange) for OpenID authentication
OPENID_USE_PKCE=false
#Set to true to reuse openid tokens for authentication management instead of using the mongodb session and the custom refresh token.
OPENID_REUSE_TOKENS=
#By default, signing key verification results are cached in order to prevent excessive HTTP requests to the JWKS endpoint.
#If a signing key matching the kid is found, this will be cached and the next time this kid is requested the signing key will be served from the cache.
#Default is true.
OPENID_JWKS_URL_CACHE_ENABLED=
OPENID_JWKS_URL_CACHE_TIME= # 600000 ms eq to 10 minutes leave empty to disable caching
#Set to true to trigger token exchange flow to acquire access token for the userinfo endpoint.
OPENID_ON_BEHALF_FLOW_FOR_USERINFO_REQUIRED=
OPENID_ON_BEHALF_FLOW_USERINFO_SCOPE="user.read" # example for Scope Needed for Microsoft Graph API
# Set to true to use the OpenID Connect end session endpoint for logout
OPENID_USE_END_SESSION_ENDPOINT=
#========================#
# SharePoint Integration #
#========================#
# Requires Entra ID (OpenID) authentication to be configured
# Enable SharePoint file picker in chat and agent panels
# ENABLE_SHAREPOINT_FILEPICKER=true
# SharePoint tenant base URL (e.g., https://yourtenant.sharepoint.com)
# Redis with TLS/SSL encryption and CA certificate
# REDIS_URI=rediss://127.0.0.1:6380
# REDIS_CA=/path/to/ca-cert.pem
# Elasticache may need to use an alternate dnsLookup for TLS connections. see "Special Note: Aws Elasticache Clusters with TLS" on this webpage: https://www.npmjs.com/package/ioredis
# Enable alternative dnsLookup for redis
# REDIS_USE_ALTERNATIVE_DNS_LOOKUP=true
# Redis authentication (if required)
# REDIS_USERNAME=your_redis_username
# REDIS_PASSWORD=your_redis_password
# Redis key prefix configuration
# Use environment variable name for dynamic prefix (recommended for cloud deployments)
- Install [MongoDB Community Edition](https://www.mongodb.com/docs/manual/administration/install-community/), ensure that `mongosh` connects to your local instance.
- Run: `npx install playwright`, then `npx playwright install`.
5. For frontend changes, compile typescript before and after changes to check for introduced errors: `cd client && npm run build`.
6. Run backend unit tests: `npm run test:api`.
7. Run frontend unit tests: `npm run test:client`.
8. Run integration tests: `npm run e2e`.
## 2. Git Workflow
## 3. Git Workflow
We utilize a GitFlow workflow to manage changes to this project's codebase. Follow these general steps when contributing code:
@@ -49,7 +67,7 @@ We utilize a GitFlow workflow to manage changes to this project's codebase. Foll
4. Submit a pull request with a clear and concise description of your changes and the reasons behind them.
5. We will review your pull request, provide feedback as needed, and eventually merge the approved changes into the main branch.
## 3. Commit Message Format
## 4. Commit Message Format
We follow the [semantic format](https://gist.github.com/joshbuchea/6f47e86d2510bce28f8e7f42ae84c716) for commit messages.
@@ -76,7 +94,7 @@ feat: add hat wobble
```
## 4. Pull Request Process
## 5. Pull Request Process
When submitting a pull request, please follow these guidelines:
@@ -91,7 +109,7 @@ Ensure that your changes meet the following criteria:
- The commit history is clean and easy to follow. You can use `git rebase` or `git merge --squash` to clean your commit history before submitting the pull request.
- The pull request description clearly outlines the changes and the reasons behind them. Be sure to include the steps to test the pull request.
## 5. Naming Conventions
## 6. Naming Conventions
Apply the following naming conventions to branches, labels, and other Git-related entities:
@@ -100,7 +118,7 @@ Apply the following naming conventions to branches, labels, and other Git-relate
- **JS/TS:** Directories and file names: Descriptive and camelCase. First letter uppercased for React files (e.g., `helperFunction.ts, ReactComponent.tsx`).
- **Docs:** Directories and file names: Descriptive and snake_case (e.g., `config_files.md`).
## 6. TypeScript Conversion
## 7. TypeScript Conversion
1.**Original State**: The project was initially developed entirely in JavaScript (JS).
@@ -126,10 +144,10 @@ Apply the following naming conventions to branches, labels, and other Git-relate
- **Current Stance**: At present, this backend transition is of lower priority and might not be pursued.
## 7. Module Import Conventions
## 8. Module Import Conventions
-`npm` packages first,
- from shortest line (top) to longest (bottom)
- from longest line (top) to shortest (bottom)
- Followed by typescript types (pertains to data-provider and client workspaces)
- longest line (top) to shortest (bottom)
@@ -139,6 +157,8 @@ Apply the following naming conventions to branches, labels, and other Git-relate
- longest line (top) to shortest (bottom)
- imports with alias `~` treated the same as relative import with respect to line length
**Note:** ESLint will automatically enforce these import conventions when you run `npm run lint --fix` or through pre-commit hooks.
---
Please ensure that you adapt this summary to fit the specific context and nuances of your project.
Thanks for taking the time to fill out this bug report!
Before submitting, please:
- Search existing [Issues and Discussions](https://github.com/danny-avila/LibreChat/discussions) to see if your bug has already been reported
- Use [Discussions](https://github.com/danny-avila/LibreChat/discussions) instead of Issues for:
- General inquiries
- Help with setup
- Questions about whether you're experiencing a bug
- type:textarea
id:what-happened
attributes:
@@ -15,6 +22,23 @@ body:
placeholder:Please give as many details as possible
validations:
required:true
- type:textarea
id:version-info
attributes:
label:Version Information
description:|
If using Docker, please run and provide the output of:
```bash
docker images | grep librechat
```
If running from source, please run and provide the output of:
```bash
git rev-parse HEAD
```
placeholder:Paste the output here
validations:
required:true
- type:textarea
id:steps-to-reproduce
attributes:
@@ -39,8 +63,24 @@ body:
id:logs
attributes:
label:Relevant log output
description:Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
description:|
Please paste relevant logs that were created when reproducing the error.
Log locations:
- Docker: Project root directory ./logs
- npm: ./api/logs
There are two types of logs that can help diagnose the issue:
- debug logs (debug-YYYY-MM-DD.log)
- error logs (error-YYYY-MM-DD.log)
Error logs contain exact stack traces and are especially helpful, but both can provide valuable information.
Please only include the relevant portions of logs that correspond to when you reproduced the error.
For UI-related issues, browser console logs can be very helpful. You can provide these as screenshots or paste the text here.
render:shell
validations:
required:true
- type:textarea
id:screenshots
attributes:
@@ -53,4 +93,4 @@ body:
description:By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/danny-avila/LibreChat/blob/main/.github/CODE_OF_CONDUCT.md)
options:
- label:I agree to follow this project's Code of Conduct
description:Request to add a new language for LibreChat translations.
title:"New Language Request: "
labels:["✨ enhancement","🌍 i18n"]
body:
- type:markdown
attributes:
value:|
Thank you for taking the time to submit a new language request! Please fill out the following details so we can review your request.
- type:input
id:language_name
attributes:
label:Language Name
description:Please provide the full name of the language (e.g., Spanish, Mandarin).
placeholder:e.g., Spanish
validations:
required:true
- type:input
id:iso_code
attributes:
label:ISO 639-1 Code
description:Please provide the ISO 639-1 code for the language (e.g., es for Spanish). You can refer to [this list](https://www.w3schools.com/tags/ref_language_codes.asp) for valid codes.
placeholder:e.g., es
validations:
required:true
- type:checkboxes
id:terms
attributes:
label:Code of Conduct
description:By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/danny-avila/LibreChat/blob/main/.github/CODE_OF_CONDUCT.md).
options:
- label:I agree to follow this project's Code of Conduct
description:Please give as many details as possible
placeholder:Please give as many details as possible
validations:
required:true
- type:textarea
id:more-details
attributes:
label:More Details
description:Please provide more details if needed.
placeholder:Please provide more details if needed.
validations:
required:true
- type:dropdown
id:browsers
attributes:
label:What is the main subject of your question?
multiple:true
options:
- Documentation
- Installation
- UI
- Endpoints
- User System/OAuth
- Other
- type:textarea
id:screenshots
attributes:
label:Screenshots
description:If applicable, add screenshots to help explain your problem. You can drag and drop, paste images directly here or link to them.
- type:checkboxes
id:terms
attributes:
label:Code of Conduct
description:By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/danny-avila/LibreChat/blob/main/.github/CODE_OF_CONDUCT.md)
options:
- label:I agree to follow this project's Code of Conduct
"template":"## [#{{TO_TAG}}] - #{{TO_TAG_DATE}}\n\nChanges from #{{FROM_TAG}} to #{{TO_TAG}}.\n\n#{{CHANGELOG}}\n\n[See full release details][release-#{{TO_TAG}}]\n\n[release-#{{TO_TAG}}]: https://github.com/#{{OWNER}}/#{{REPO}}/releases/tag/#{{TO_TAG}}\n\n---",
"pr_template":"- #{{TITLE}} by **@#{{AUTHOR}}** in [##{{NUMBER}}](#{{URL}})",
# When triggered by repository_dispatch, skip sync step.
- name:Skip sync step on non-push events
if:${{ github.event_name != 'push' }}
run:echo "Skipping sync as the event is not a push."
create-pull-request:
name:Create Translation PR on Version Published
runs-on:ubuntu-latest
needs:sync-translations
permissions:
contents:write
pull-requests:write
steps:
# 1. Check out the repository.
- name:Checkout Repository
uses:actions/checkout@v4
# 2. Download translation files from locize.
- name:Download Translations from locize
uses:locize/download@v2
with:
project-id:${{ secrets.LOCIZE_PROJECT_ID }}
path:"client/src/locales"
# 3. Create a Pull Request using built-in functionality.
- name:Create Pull Request
uses:peter-evans/create-pull-request@v7
with:
token:${{ secrets.GITHUB_TOKEN }}
sign-commits:true
commit-message:"🌍 i18n: Update translation.json with latest translations"
base:main
branch:i18n/locize-translation-update
reviewers:danny-avila
title:"🌍 i18n: Update translation.json with latest translations"
body:|
**Description**:
- 🎯 **Objective**: Update `translation.json` with the latest translations from locize.
- 🔍 **Details**: This PR is automatically generated upon receiving a versionPublished event with version "latest". It reflects the newest translations provided by locize.
All notable changes to this project will be documented in this file.
## [Unreleased]
### ✨ New Features
- ✨ feat: implement search parameter updates by **@mawburn** in [#7151](https://github.com/danny-avila/LibreChat/pull/7151)
- 🎏 feat: Add MCP support for Streamable HTTP Transport by **@benverhees** in [#7353](https://github.com/danny-avila/LibreChat/pull/7353)
- 🔒 feat: Add Content Security Policy using Helmet middleware by **@rubentalstra** in [#7377](https://github.com/danny-avila/LibreChat/pull/7377)
- ✨ feat: Add Normalization for MCP Server Names by **@danny-avila** in [#7421](https://github.com/danny-avila/LibreChat/pull/7421)
- 📊 feat: Improve Helm Chart by **@hofq** in [#3638](https://github.com/danny-avila/LibreChat/pull/3638)
- 🦾 feat: Claude-4 Support by **@danny-avila** in [#7509](https://github.com/danny-avila/LibreChat/pull/7509)
- 🪨 feat: Bedrock Support for Claude-4 Reasoning by **@danny-avila** in [#7517](https://github.com/danny-avila/LibreChat/pull/7517)
### 🌍 Internationalization
- 🌍 i18n: Add `Danish` and `Czech` and `Catalan` localization support by **@rubentalstra** in [#7373](https://github.com/danny-avila/LibreChat/pull/7373)
- 🌍 i18n: Update translation.json with latest translations by **@github-actions[bot]** in [#7375](https://github.com/danny-avila/LibreChat/pull/7375)
- 🌍 i18n: Update translation.json with latest translations by **@github-actions[bot]** in [#7468](https://github.com/danny-avila/LibreChat/pull/7468)
### 🔧 Fixes
- 💬 fix: update aria-label for accessibility in ConvoLink component by **@berry-13** in [#7320](https://github.com/danny-avila/LibreChat/pull/7320)
- 🔑 fix: use `apiKey` instead of `openAIApiKey` in OpenAI-like Config by **@danny-avila** in [#7337](https://github.com/danny-avila/LibreChat/pull/7337)
- 🔄 fix: update navigation logic in `useFocusChatEffect` to ensure correct search parameters are used by **@mawburn** in [#7340](https://github.com/danny-avila/LibreChat/pull/7340)
- 🔄 fix: Improve MCP Connection Cleanup by **@danny-avila** in [#7400](https://github.com/danny-avila/LibreChat/pull/7400)
- 🛡️ fix: Preset and Validation Logic for URL Query Params by **@danny-avila** in [#7407](https://github.com/danny-avila/LibreChat/pull/7407)
- 🌘 fix: artifact of preview text is illegible in dark mode by **@nhtruong** in [#7405](https://github.com/danny-avila/LibreChat/pull/7405)
- 🛡️ fix: Temporarily Remove CSP until Configurable by **@danny-avila** in [#7419](https://github.com/danny-avila/LibreChat/pull/7419)
- 💽 fix: Exclude index page `/` from static cache settings by **@sbruel** in [#7382](https://github.com/danny-avila/LibreChat/pull/7382)
### ⚙️ Other Changes
- 📜 docs: CHANGELOG for release v0.7.8 by **@github-actions[bot]** in [#7290](https://github.com/danny-avila/LibreChat/pull/7290)
- 📦 chore: Update API Package Dependencies by **@danny-avila** in [#7359](https://github.com/danny-avila/LibreChat/pull/7359)
- 📜 docs: Unreleased Changelog by **@github-actions[bot]** in [#7321](https://github.com/danny-avila/LibreChat/pull/7321)
- 📜 docs: Unreleased Changelog by **@github-actions[bot]** in [#7434](https://github.com/danny-avila/LibreChat/pull/7434)
- 🛡️ chore: `multer` v2.0.0 for CVE-2025-47935 and CVE-2025-47944 by **@danny-avila** in [#7454](https://github.com/danny-avila/LibreChat/pull/7454)
- 📂 refactor: Improve `FileAttachment` & File Form Deletion by **@danny-avila** in [#7471](https://github.com/danny-avila/LibreChat/pull/7471)
- 📊 chore: Remove Old Helm Chart by **@hofq** in [#7512](https://github.com/danny-avila/LibreChat/pull/7512)
- 🪖 chore: bump helm app version to v0.7.8 by **@austin-barrington** in [#7524](https://github.com/danny-avila/LibreChat/pull/7524)
---
## [v0.7.8] -
Changes from v0.7.8-rc1 to v0.7.8.
### ✨ New Features
- ✨ feat: Enhance form submission for touch screens by **@berry-13** in [#7198](https://github.com/danny-avila/LibreChat/pull/7198)
- 🔍 feat: Additional Tavily API Tool Parameters by **@glowforge-opensource** in [#7232](https://github.com/danny-avila/LibreChat/pull/7232)
- 🐋 feat: Add python to Dockerfile for increased MCP compatibility by **@technicalpickles** in [#7270](https://github.com/danny-avila/LibreChat/pull/7270)
### 🔧 Fixes
- 🔧 fix: Google Gemma Support & OpenAI Reasoning Instructions by **@danny-avila** in [#7196](https://github.com/danny-avila/LibreChat/pull/7196)
- 🛠️ fix: Conversation Navigation State by **@danny-avila** in [#7210](https://github.com/danny-avila/LibreChat/pull/7210)
- 🔄 fix: o-Series Model Regex for System Messages by **@danny-avila** in [#7245](https://github.com/danny-avila/LibreChat/pull/7245)
- 🔖 fix: Custom Headers for Initial MCP SSE Connection by **@danny-avila** in [#7246](https://github.com/danny-avila/LibreChat/pull/7246)
- 🛡️ fix: Deep Clone `MCPOptions` for User MCP Connections by **@danny-avila** in [#7247](https://github.com/danny-avila/LibreChat/pull/7247)
- 🔄 fix: URL Param Race Condition and File Draft Persistence by **@danny-avila** in [#7257](https://github.com/danny-avila/LibreChat/pull/7257)
- 🔄 fix: Assistants Endpoint & Minor Issues by **@danny-avila** in [#7274](https://github.com/danny-avila/LibreChat/pull/7274)
- 🔄 fix: Ollama Think Tag Edge Case with Tools by **@danny-avila** in [#7275](https://github.com/danny-avila/LibreChat/pull/7275)
### ⚙️ Other Changes
- 📜 docs: CHANGELOG for release v0.7.8-rc1 by **@github-actions[bot]** in [#7153](https://github.com/danny-avila/LibreChat/pull/7153)
- 🔄 refactor: Artifact Visibility Management by **@danny-avila** in [#7181](https://github.com/danny-avila/LibreChat/pull/7181)
- 📦 chore: Bump Package Security by **@danny-avila** in [#7183](https://github.com/danny-avila/LibreChat/pull/7183)
- 🌿 refactor: Unmount Fork Popover on Hide for Better Performance by **@danny-avila** in [#7189](https://github.com/danny-avila/LibreChat/pull/7189)
- 🧰 chore: ESLint configuration to enforce Prettier formatting rules by **@mawburn** in [#7186](https://github.com/danny-avila/LibreChat/pull/7186)
- 🎨 style: Improve KaTeX Rendering for LaTeX Equations by **@andresgit** in [#7223](https://github.com/danny-avila/LibreChat/pull/7223)
- 📝 docs: Update `.env.example` Google models by **@marlonka** in [#7254](https://github.com/danny-avila/LibreChat/pull/7254)
- 💬 refactor: MCP Chat Visibility Option, Google Rates, Remove OpenAPI Plugins by **@danny-avila** in [#7286](https://github.com/danny-avila/LibreChat/pull/7286)
- 📜 docs: Unreleased Changelog by **@github-actions[bot]** in [#7214](https://github.com/danny-avila/LibreChat/pull/7214)
- 🔍 feat: Mistral OCR API / Upload Files as Text by **@danny-avila** in [#6274](https://github.com/danny-avila/LibreChat/pull/6274)
- 🤖 feat: Support OpenAI Web Search models by **@danny-avila** in [#6313](https://github.com/danny-avila/LibreChat/pull/6313)
- 🔗 feat: Agent Chain (Mixture-of-Agents) by **@danny-avila** in [#6374](https://github.com/danny-avila/LibreChat/pull/6374)
- ⌛ feat: `initTimeout` for Slow Starting MCP Servers by **@perweij** in [#6383](https://github.com/danny-avila/LibreChat/pull/6383)
- 🚀 feat: `S3` Integration for File handling and Image uploads by **@rubentalstra** in [#6142](https://github.com/danny-avila/LibreChat/pull/6142)
- 🔒feat: Enable OpenID Auto-Redirect by **@leondape** in [#6066](https://github.com/danny-avila/LibreChat/pull/6066)
- 🚀 feat: Integrate `Azure Blob Storage` for file handling and image uploads by **@rubentalstra** in [#6153](https://github.com/danny-avila/LibreChat/pull/6153)
- 🚀 feat: Add support for custom `AWS` endpoint in `S3` by **@rubentalstra** in [#6431](https://github.com/danny-avila/LibreChat/pull/6431)
- 🚀 feat: Add support for LDAP STARTTLS in LDAP authentication by **@rubentalstra** in [#6438](https://github.com/danny-avila/LibreChat/pull/6438)
- 🚀 feat: Refactor schema exports and update package version to 0.0.4 by **@rubentalstra** in [#6455](https://github.com/danny-avila/LibreChat/pull/6455)
- 🔼 feat: Add Auto Submit For URL Query Params by **@mjaverto** in [#6440](https://github.com/danny-avila/LibreChat/pull/6440)
- 🛠 feat: Enhance Redis Integration, Rate Limiters & Log Headers by **@danny-avila** in [#6462](https://github.com/danny-avila/LibreChat/pull/6462)
- 💵 feat: Add Automatic Balance Refill by **@rubentalstra** in [#6452](https://github.com/danny-avila/LibreChat/pull/6452)
- 🗣️ feat: add support for gpt-4o-transcribe models by **@berry-13** in [#6483](https://github.com/danny-avila/LibreChat/pull/6483)
- 🎨 feat: UI Refresh for Enhanced UX by **@berry-13** in [#6346](https://github.com/danny-avila/LibreChat/pull/6346)
- 🌍 feat: Add support for Hungarian language localization by **@rubentalstra** in [#6508](https://github.com/danny-avila/LibreChat/pull/6508)
- 🚀 feat: Add Gemini 2.5 Token/Context Values, Increase Max Possible Output to 64k by **@danny-avila** in [#6563](https://github.com/danny-avila/LibreChat/pull/6563)
- 🚀 feat: Enhance MCP Connections For Multi-User Support by **@danny-avila** in [#6610](https://github.com/danny-avila/LibreChat/pull/6610)
- 🚀 feat: Enhance S3 URL Expiry with Refresh; fix: S3 File Deletion by **@danny-avila** in [#6647](https://github.com/danny-avila/LibreChat/pull/6647)
- 🚀 feat: enhance UI components and refactor settings by **@berry-13** in [#6625](https://github.com/danny-avila/LibreChat/pull/6625)
- 💬 feat: move TemporaryChat to the Header by **@berry-13** in [#6646](https://github.com/danny-avila/LibreChat/pull/6646)
- 🚀 feat: Use Model Specs + Specific Endpoints, Limit Providers for Agents by **@danny-avila** in [#6650](https://github.com/danny-avila/LibreChat/pull/6650)
- 🪙 feat: Sync Balance Config on Login by **@danny-avila** in [#6671](https://github.com/danny-avila/LibreChat/pull/6671)
- 🔦 feat: MCP Support for Non-Agent Endpoints by **@danny-avila** in [#6775](https://github.com/danny-avila/LibreChat/pull/6775)
- 🗃️ feat: Code Interpreter File Persistence between Sessions by **@danny-avila** in [#6790](https://github.com/danny-avila/LibreChat/pull/6790)
- 🖥️ feat: Code Interpreter API for Non-Agent Endpoints by **@danny-avila** in [#6803](https://github.com/danny-avila/LibreChat/pull/6803)
- ⚡ feat: Self-hosted Artifacts Static Bundler URL by **@danny-avila** in [#6827](https://github.com/danny-avila/LibreChat/pull/6827)
- 🐳 feat: Add Jemalloc and UV to Docker Builds by **@danny-avila** in [#6836](https://github.com/danny-avila/LibreChat/pull/6836)
- 🤖 feat: GPT-4.1 by **@danny-avila** in [#6880](https://github.com/danny-avila/LibreChat/pull/6880)
- 👋 feat: remove Edge TTS by **@berry-13** in [#6885](https://github.com/danny-avila/LibreChat/pull/6885)
- feat: nav optimization by **@berry-13** in [#5785](https://github.com/danny-avila/LibreChat/pull/5785)
- 🗺️ feat: Add Parameter Location Mapping for OpenAPI actions by **@peeeteeer** in [#6858](https://github.com/danny-avila/LibreChat/pull/6858)
- 🤖 feat: Support `o4-mini` and `o3` Models by **@danny-avila** in [#6928](https://github.com/danny-avila/LibreChat/pull/6928)
- 🎨 feat: OpenAI Image Tools (GPT-Image-1) by **@danny-avila** in [#7079](https://github.com/danny-avila/LibreChat/pull/7079)
- 🗓️ feat: Add Special Variables for Prompts & Agents, Prompt UI Improvements by **@danny-avila** in [#7123](https://github.com/danny-avila/LibreChat/pull/7123)
### 🌍 Internationalization
- 🌍 i18n: Add Thai Language Support and Update Translations by **@rubentalstra** in [#6219](https://github.com/danny-avila/LibreChat/pull/6219)
- 🌍 i18n: Update translation.json with latest translations by **@github-actions[bot]** in [#6220](https://github.com/danny-avila/LibreChat/pull/6220)
- 🌍 i18n: Update translation.json with latest translations by **@github-actions[bot]** in [#6240](https://github.com/danny-avila/LibreChat/pull/6240)
- 🌍 i18n: Update translation.json with latest translations by **@github-actions[bot]** in [#6241](https://github.com/danny-avila/LibreChat/pull/6241)
- 🌍 i18n: Update translation.json with latest translations by **@github-actions[bot]** in [#6277](https://github.com/danny-avila/LibreChat/pull/6277)
- 🌍 i18n: Update translation.json with latest translations by **@github-actions[bot]** in [#6414](https://github.com/danny-avila/LibreChat/pull/6414)
- 🌍 i18n: Update translation.json with latest translations by **@github-actions[bot]** in [#6505](https://github.com/danny-avila/LibreChat/pull/6505)
- 🌍 i18n: Update translation.json with latest translations by **@github-actions[bot]** in [#6530](https://github.com/danny-avila/LibreChat/pull/6530)
- 🌍 i18n: Add Persian Localization Support by **@rubentalstra** in [#6669](https://github.com/danny-avila/LibreChat/pull/6669)
- 🌍 i18n: Update translation.json with latest translations by **@github-actions[bot]** in [#6667](https://github.com/danny-avila/LibreChat/pull/6667)
- 🌍 i18n: Update translation.json with latest translations by **@github-actions[bot]** in [#7126](https://github.com/danny-avila/LibreChat/pull/7126)
- 🌍 i18n: Update translation.json with latest translations by **@github-actions[bot]** in [#7148](https://github.com/danny-avila/LibreChat/pull/7148)
### 👐 Accessibility
- 🎨 a11y: Update Model Spec Description Text by **@berry-13** in [#6294](https://github.com/danny-avila/LibreChat/pull/6294)
- 🗑️ a11y: Add Accessible Name to Button for File Attachment Removal by **@kangabell** in [#6709](https://github.com/danny-avila/LibreChat/pull/6709)
- ⌨️ a11y: enhance accessibility & visual consistency by **@berry-13** in [#6866](https://github.com/danny-avila/LibreChat/pull/6866)
- 🙌 a11y: Searchbar/Conversations List Focus by **@danny-avila** in [#7096](https://github.com/danny-avila/LibreChat/pull/7096)
- 👐 a11y: Improve Fork and SplitText Accessibility by **@danny-avila** in [#7147](https://github.com/danny-avila/LibreChat/pull/7147)
### 🔧 Fixes
- 🐛 fix: Avatar Type Definitions in Agent/Assistant Schemas by **@danny-avila** in [#6235](https://github.com/danny-avila/LibreChat/pull/6235)
- 🔧 fix: MeiliSearch Field Error and Patch Incorrect Import by #6210 by **@rubentalstra** in [#6245](https://github.com/danny-avila/LibreChat/pull/6245)
- 🔏 fix: Enhance Two-Factor Authentication by **@rubentalstra** in [#6247](https://github.com/danny-avila/LibreChat/pull/6247)
- 🐛 fix: Await saveMessage in abortMiddleware to ensure proper execution by **@sh4shii** in [#6248](https://github.com/danny-avila/LibreChat/pull/6248)
- 🔧 fix: Axios Proxy Usage And Bump `mongoose` by **@danny-avila** in [#6298](https://github.com/danny-avila/LibreChat/pull/6298)
- 🔧 fix: comment out MCP servers to resolve service run issues by **@KunalScriptz** in [#6316](https://github.com/danny-avila/LibreChat/pull/6316)
- 🔧 fix: Update Token Calculations and Mapping, MCP `env` Initialization by **@danny-avila** in [#6406](https://github.com/danny-avila/LibreChat/pull/6406)
- 🐞 fix: Agent "Resend" Message Attachments + Source Icon Styling by **@danny-avila** in [#6408](https://github.com/danny-avila/LibreChat/pull/6408)
- 🐛 fix: Prevent Crash on Duplicate Message ID by **@Odrec** in [#6392](https://github.com/danny-avila/LibreChat/pull/6392)
- 🔐 fix: Invalid Key Length in 2FA Encryption by **@rubentalstra** in [#6432](https://github.com/danny-avila/LibreChat/pull/6432)
- 🏗️ fix: Fix Agents Token Spend Race Conditions, Expand Test Coverage by **@danny-avila** in [#6480](https://github.com/danny-avila/LibreChat/pull/6480)
- 🔃 fix: Draft Clearing, Claude Titles, Remove Default Vision Max Tokens by **@danny-avila** in [#6501](https://github.com/danny-avila/LibreChat/pull/6501)
- 🔧 fix: Update username reference to use user.name in greeting display by **@rubentalstra** in [#6534](https://github.com/danny-avila/LibreChat/pull/6534)
- 🔧 fix: S3 Download Stream with Key Extraction and Blob Storage Encoding for Vision by **@danny-avila** in [#6557](https://github.com/danny-avila/LibreChat/pull/6557)
- 🔧 fix: Mistral type strictness for `usage` & update token values/windows by **@danny-avila** in [#6562](https://github.com/danny-avila/LibreChat/pull/6562)
- 🔧 fix: Consolidate Text Parsing and TTS Edge Initialization by **@danny-avila** in [#6582](https://github.com/danny-avila/LibreChat/pull/6582)
- 🔧 fix: Ensure continuation in image processing on base64 encoding from Blob Storage by **@danny-avila** in [#6619](https://github.com/danny-avila/LibreChat/pull/6619)
- ✉️ fix: Fallback For User Name In Email Templates by **@danny-avila** in [#6620](https://github.com/danny-avila/LibreChat/pull/6620)
- 🔧 fix: Azure Blob Integration and File Source References by **@rubentalstra** in [#6575](https://github.com/danny-avila/LibreChat/pull/6575)
- 🐛 fix: Safeguard against undefined addedEndpoints by **@wipash** in [#6654](https://github.com/danny-avila/LibreChat/pull/6654)
- 🤖 fix: Gemini 2.5 Vision Support by **@danny-avila** in [#6663](https://github.com/danny-avila/LibreChat/pull/6663)
- 🔄 fix: Avatar & Error Handling Enhancements by **@danny-avila** in [#6687](https://github.com/danny-avila/LibreChat/pull/6687)
- 🔧 fix: Chat Middleware, Zod Conversion, Auto-Save and S3 URL Refresh by **@danny-avila** in [#6720](https://github.com/danny-avila/LibreChat/pull/6720)
- 🔧 fix: Agent Capability Checks & DocumentDB Compatibility for Agent Resource Removal by **@danny-avila** in [#6726](https://github.com/danny-avila/LibreChat/pull/6726)
- 🔄 fix: Improve audio MIME type detection and handling by **@berry-13** in [#6707](https://github.com/danny-avila/LibreChat/pull/6707)
- 🪺 fix: Update Role Handling due to New Schema Shape by **@danny-avila** in [#6774](https://github.com/danny-avila/LibreChat/pull/6774)
- 🗨️ fix: Show ModelSpec Greeting by **@berry-13** in [#6770](https://github.com/danny-avila/LibreChat/pull/6770)
- 🔧 fix: Keyv and Proxy Issues, and More Memory Optimizations by **@danny-avila** in [#6867](https://github.com/danny-avila/LibreChat/pull/6867)
- ✨ fix: Implement dynamic text sizing for greeting and name display by **@berry-13** in [#6833](https://github.com/danny-avila/LibreChat/pull/6833)
- 📝 fix: Mistral OCR Image Support and Azure Agent Titles by **@danny-avila** in [#6901](https://github.com/danny-avila/LibreChat/pull/6901)
- 📢 fix: Invalid `engineTTS` and Conversation State on Navigation by **@berry-13** in [#6904](https://github.com/danny-avila/LibreChat/pull/6904)
- 🛠️ fix: Improve Accessibility and Display of Conversation Menu by **@danny-avila** in [#6913](https://github.com/danny-avila/LibreChat/pull/6913)
- 🔧 fix: Agent Resource Form, Convo Menu Style, Ensure Draft Clears on Submission by **@danny-avila** in [#6925](https://github.com/danny-avila/LibreChat/pull/6925)
- 🔀 fix: MCP Improvements, Auto-Save Drafts, Artifact Markup by **@danny-avila** in [#7040](https://github.com/danny-avila/LibreChat/pull/7040)
- 🐋 fix: Improve Deepseek Compatbility by **@danny-avila** in [#7132](https://github.com/danny-avila/LibreChat/pull/7132)
- 🐙 fix: Add Redis Ping Interval to Prevent Connection Drops by **@peeeteeer** in [#7127](https://github.com/danny-avila/LibreChat/pull/7127)
### ⚙️ Other Changes
- 📦 refactor: Move DB Models to `@librechat/data-schemas` by **@rubentalstra** in [#6210](https://github.com/danny-avila/LibreChat/pull/6210)
- 📦 chore: Patch `axios` to address CVE-2025-27152 by **@danny-avila** in [#6222](https://github.com/danny-avila/LibreChat/pull/6222)
- ⚠️ refactor: Use Error Content Part Instead Of Throwing Error for Agents by **@danny-avila** in [#6262](https://github.com/danny-avila/LibreChat/pull/6262)
- 🏃♂️ refactor: Improve Agent Run Context & Misc. Changes by **@danny-avila** in [#6448](https://github.com/danny-avila/LibreChat/pull/6448)
- 📝 docs: librechat.example.yaml by **@ineiti** in [#6442](https://github.com/danny-avila/LibreChat/pull/6442)
- 🏃♂️ refactor: More Agent Context Improvements during Run by **@danny-avila** in [#6477](https://github.com/danny-avila/LibreChat/pull/6477)
- 🔃 refactor: Allow streaming for `o1` models by **@danny-avila** in [#6509](https://github.com/danny-avila/LibreChat/pull/6509)
- 🔧 chore: `Vite` Plugin Upgrades & Config Optimizations by **@rubentalstra** in [#6547](https://github.com/danny-avila/LibreChat/pull/6547)
- 🔧 refactor: Consolidate Logging, Model Selection & Actions Optimizations, Minor Fixes by **@danny-avila** in [#6553](https://github.com/danny-avila/LibreChat/pull/6553)
- 🎨 style: Address Minor UI Refresh Issues by **@berry-13** in [#6552](https://github.com/danny-avila/LibreChat/pull/6552)
- 🔧 refactor: Enhance Model & Endpoint Configurations with Global Indicators 🌍 by **@berry-13** in [#6578](https://github.com/danny-avila/LibreChat/pull/6578)
- 💬 style: Chat UI, Greeting, and Message adjustments by **@berry-13** in [#6612](https://github.com/danny-avila/LibreChat/pull/6612)
- ⚡ refactor: DocumentDB Compatibility for Balance Updates by **@danny-avila** in [#6673](https://github.com/danny-avila/LibreChat/pull/6673)
- 🧹 chore: Update ESLint rules for React hooks by **@rubentalstra** in [#6685](https://github.com/danny-avila/LibreChat/pull/6685)
- 🪙 chore: Update Gemini Pricing by **@RedwindA** in [#6731](https://github.com/danny-avila/LibreChat/pull/6731)
- 🪺 refactor: Nest Permission fields for Roles by **@rubentalstra** in [#6487](https://github.com/danny-avila/LibreChat/pull/6487)
- 📦 chore: Update `caniuse-lite` dependency to version 1.0.30001706 by **@rubentalstra** in [#6482](https://github.com/danny-avila/LibreChat/pull/6482)
- ⚙️ refactor: OAuth Flow Signal, Type Safety, Tool Progress & Updated Packages by **@danny-avila** in [#6752](https://github.com/danny-avila/LibreChat/pull/6752)
- 📦 chore: bump vite from 6.2.3 to 6.2.5 by **@dependabot[bot]** in [#6745](https://github.com/danny-avila/LibreChat/pull/6745)
- 💾 chore: Enhance Local Storage Handling and Update MCP SDK by **@danny-avila** in [#6809](https://github.com/danny-avila/LibreChat/pull/6809)
- 🤖 refactor: Improve Agents Memory Usage, Bump Keyv, Grok 3 by **@danny-avila** in [#6850](https://github.com/danny-avila/LibreChat/pull/6850)
- 💾 refactor: Enhance Memory In Image Encodings & Client Disposal by **@danny-avila** in [#6852](https://github.com/danny-avila/LibreChat/pull/6852)
- 🔁 refactor: Token Event Handler and Standardize `maxTokens` Key by **@danny-avila** in [#6886](https://github.com/danny-avila/LibreChat/pull/6886)
- 🔍 refactor: Search & Message Retrieval by **@berry-13** in [#6903](https://github.com/danny-avila/LibreChat/pull/6903)
- 🎨 style: standardize dropdown styling & fix z-Index layering by **@berry-13** in [#6939](https://github.com/danny-avila/LibreChat/pull/6939)
- 📙 docs: CONTRIBUTING.md by **@dblock** in [#6831](https://github.com/danny-avila/LibreChat/pull/6831)
- 🧭 refactor: Modernize Nav/Header by **@danny-avila** in [#7094](https://github.com/danny-avila/LibreChat/pull/7094)
- 🪶 refactor: Chat Input Focus for Conversation Navigations & ChatForm Optimizations by **@danny-avila** in [#7100](https://github.com/danny-avila/LibreChat/pull/7100)
- 🔃 refactor: Streamline Navigation, Message Loading UX by **@danny-avila** in [#7118](https://github.com/danny-avila/LibreChat/pull/7118)
- 📜 docs: Unreleased changelog by **@github-actions[bot]** in [#6265](https://github.com/danny-avila/LibreChat/pull/6265)
- Agent Marketplace: Discover and deploy community-built agents
-Collaborative Sharing: Share agents with specific users and groups
- Flexible & Extensible: Use MCP Servers, tools, file search, code execution, and more
- Compatible with Custom Endpoints, OpenAI, Azure, Anthropic, AWS Bedrock, Google, Vertex AI, Responses API, and more
- [Model Context Protocol (MCP) Support](https://modelcontextprotocol.io/clients#librechat) for Tools
- 🔍 **Web Search**:
- Search the internet and retrieve relevant information to enhance your AI context
- Combines search providers, content scrapers, and result rerankers for optimal results
- **Customizable Jina Reranking**: Configure custom Jina API URLs for reranking services
- **[Learn More →](https://www.librechat.ai/docs/features/web_search)**
- 🪄 **Generative UI with Code Artifacts**:
- [Code Artifacts](https://youtu.be/GfTj7O4gmd0?si=WJbdnemZpJzBrJo3) allow creation of React, HTML, and Mermaid diagrams directly in chat
- 🎨 **Image Generation & Editing**
- Text-to-image and image-to-image with [GPT-Image-1](https://www.librechat.ai/docs/features/image_gen#1--openai-image-tools-recommended)
- Text-to-image with [DALL-E (3/2)](https://www.librechat.ai/docs/features/image_gen#2--dalle-legacy), [Stable Diffusion](https://www.librechat.ai/docs/features/image_gen#3--stable-diffusion-local), [Flux](https://www.librechat.ai/docs/features/image_gen#4--flux), or any [MCP server](https://www.librechat.ai/docs/features/image_gen#5--model-context-protocol-mcp)
- Produce stunning visuals from prompts or refine existing images with a single instruction
- 💾 **Presets & Context Management**:
- Create, Save, & Share Custom Presets
- Switch between AI Endpoints and Presets mid-chat
- Edit, Resubmit, and Continue Messages with Conversation branching
- Create and share prompts with specific users and groups
- [Fork Messages & Conversations](https://www.librechat.ai/docs/features/fork) for Advanced Context control
- 💬 **Multimodal & File Interactions**:
- Upload and analyze images with Claude 3, GPT-4.5, GPT-4o, o1, Llama-Vision, and Gemini 📸
- Chat with Files using Custom Endpoints, OpenAI, Azure, Anthropic, AWS Bedrock, & Google 🗃️
- Polski, Português (PT), Português (BR), Русский, 日本語, Svenska, 한국어, Tiếng Việt
- Türkçe, Nederlands, עברית, Català, Čeština, Dansk, Eesti, فارسی
- Suomi, Magyar, Հայերեն, Bahasa Indonesia, ქართული, Latviešu, ไทย, ئۇيغۇرچە
- 🧠 **Reasoning UI**:
- Dynamic Reasoning UI for Chain-of-Thought/Reasoning AI models like DeepSeek-R1
- 🎨 **Customizable Interface**:
- Customizable Dropdown & Interface that adapts to both power users and newcomers
- 🗣️ **Speech & Audio**:
- Chat hands-free with Speech-to-Text and Text-to-Speech
- Automatically send and play Audio
- Supports OpenAI, Azure OpenAI, and Elevenlabs
- 📥 Import Conversations from LibreChat, ChatGPT, Chatbot UI
-📤 Export conversations as screenshots, markdown, text, json
-🔍 Search all messages/conversations
-🔌 Plugins, including web access, image generation with DALL-E-3 and more
- 👥 Multi-User, Secure Authentication with Moderation and Token spend tools
-⚙️ Configure Proxy, Reverse Proxy, Docker, & many Deployment options:
-📥 **Import & Export Conversations**:
-Import Conversations from LibreChat, ChatGPT, Chatbot UI
-Export conversations as screenshots, markdown, text, json
-🔍 **Search & Discovery**:
- Search all messages/conversations
- 👥 **Multi-User & Secure Access**:
- Multi-User, Secure Authentication with OAuth2, LDAP, & Email Login Support
- Built-in Moderation, and Token spend tools
- ⚙️ **Configuration & Deployment**:
- Configure Proxy, Reverse Proxy, Docker, & many Deployment options
- Use completely local or deploy on the cloud
- 📖 Completely Open-Source & Built in Public
-🧑🤝🧑 Community-driven development, support, and feedback
-📖 **Open-Source & Community**:
- Completely Open-Source & Built in Public
- Community-driven development, support, and feedback
[For a thorough review of our features, see our docs here](https://docs.librechat.ai/) 📚
@@ -81,7 +141,8 @@ LibreChat brings together the future of assistant AIs with the revolutionary tec
With LibreChat, you no longer need to opt for ChatGPT Plus and can instead use free or pay-per-call APIs. We welcome contributions, cloning, and forking to enhance the capabilities of this advanced chatbot platform.
[](https://www.youtube.com/watch?v=cvosUxogdpI)
[](https://www.youtube.com/watch?v=ilfwGQtJNlI)
Click on the thumbnail to open the video☝️
---
@@ -94,8 +155,8 @@ Click on the thumbnail to open the video☝️
@@ -133,6 +194,8 @@ Contributions, suggestions, bug reports and fixes are welcome!
For new features, components, or extensions, please open an issue and discuss before sending a PR.
If you'd like to help translate LibreChat into your language, we'd love your contribution! Improving our translations not only makes LibreChat more accessible to users around the world but also enhances the overall user experience. Please check out our [Translation Guide](https://www.librechat.ai/docs/translation).
---
## 💖 This project exists in its current state thanks to all the people who contribute
@@ -140,3 +203,15 @@ For new features, components, or extensions, please open an issue and discuss be
constinfo=`Total Possible Tokens + MaxOutputTokens must be less than or equal to Max Context Tokens: ${this.maxPromptTokens} (total possible output) + ${this.maxResponseTokens}(max output) = ${reservedTokens}/${this.maxContextTokens} (max context)`;
else if (message.eventType === 'stream-end' && message.response) {
reply = message.response.text;
}
*/
}
returnreply;
}
asyncgenerateTitle(userMessage,botMessage){
constinstructionsPayload={
role:'system',
content:`Write an extremely concise subtitle for this conversation with no more than a few words. All words should be capitalized. Exclude punctuation.
promptPrefix=`${this.startToken}Instructions:\nYou are ChatGPT, a large language model trained by OpenAI. Respond conversationally.\nCurrent date: ${currentDateString}${this.endToken}\n\n`;
}
constpromptSuffix=`${this.startToken}${this.chatGptLabel}:\n`;// Prompt ChatGPT to respond.
'Failed to fetch models from Ollama API. If you are not using Ollama directly, and instead, through some aggregator or reverse proxy that handles fetching via OpenAI spec, ensure the name of the endpoint doesn\'t start with `ollama` (case-insensitive).';
prefix:`Objective: Understand human intentions using user input and available tools. Goal: Identify the most suitable actions to directly address user queries.
When responding:
- Choose actions relevant to the user's query, using multiple actions in a logical order if needed.
- Prioritize direct and specific thoughts to meet user expectations.
- Format results in a way compatible with open-API expectations.
- Offer concise, meaningful answers to user queries.
- Use tools when necessary but rely on your own knowledge for creative requests.
- Strive for variety, avoiding repetitive responses.
# Available Actions & Tools:
N/A: No suitable action; use your own knowledge.`,
instructions:`Always adhere to the following format in your response to indicate actions taken:
Thought: Summarize your thought process.
Action: Select an action from [{tool_names}].
Action Input: Define the action's input.
Observation: Report the action's result.
Repeat steps 1-4 as needed, in order. When not using a tool, use N/A for Action, provide the result as Action Input, and include an Observation.
Upon reaching the final answer, use this format after completing all necessary actions:
Thought: Indicate that you've determined the final answer.
Final Answer: Present the answer to the user's query.`,
suffix:`Keep these guidelines in mind when crafting your response:
- Strictly adhere to the Action format for all responses, as they will be machine-parsed.
- If a tool is unnecessary, quickly move to the Thought/Final Answer format.
- Follow the logical sequence provided by the user without adding extra steps.
- Be honest; if you can't provide an appropriate answer using the given tools, use your own knowledge.
- Aim for efficiency and minimal actions to meet the user's needs effectively.`,
},
'gpt3-v2':{
prefix:`Objective: Understand the human's query with available actions & tools. Let's work this out in a step by step way to be sure we fulfill the query.
When responding:
- Choose actions relevant to the user's query, using multiple actions in a logical order if needed.
- Prioritize direct and specific thoughts to meet user expectations.
- Format results in a way compatible with open-API expectations.
- Offer concise, meaningful answers to user queries.
- Use tools when necessary but rely on your own knowledge for creative requests.
- Strive for variety, avoiding repetitive responses.
# Available Actions & Tools:
N/A: No suitable action; use your own knowledge.`,
instructions:`I want you to respond with this format and this format only, without comments or explanations, to indicate actions taken:
\`\`\`
Thought: Summarize your thought process.
Action: Select an action from [{tool_names}].
Action Input: Define the action's input.
Observation: Report the action's result.
\`\`\`
Repeat the format for each action as needed. When not using a tool, use N/A for Action, provide the result as Action Input, and include an Observation.
Upon reaching the final answer, use this format after completing all necessary actions:
\`\`\`
Thought: Indicate that you've determined the final answer.
Final Answer: A conversational reply to the user's query as if you were answering them directly.
\`\`\``,
suffix:`Keep these guidelines in mind when crafting your response:
- Strictly adhere to the Action format for all responses, as they will be machine-parsed.
- If a tool is unnecessary, quickly move to the Thought/Final Answer format.
- Follow the logical sequence provided by the user without adding extra steps.
- Be honest; if you can't provide an appropriate answer using the given tools, use your own knowledge.
- Aim for efficiency and minimal actions to meet the user's needs effectively.`,
},
gpt3:{
prefix:`Objective: Understand the human's query with available actions & tools. Let's work this out in a step by step way to be sure we fulfill the query.
Use available actions and tools judiciously.
# Available Actions & Tools:
N/A: No suitable action; use your own knowledge.`,
instructions:`I want you to respond with this format and this format only, without comments or explanations, to indicate actions taken:
\`\`\`
Thought: Your thought process.
Action: Action from [{tool_names}].
Action Input: Action's input.
Observation: Action's result.
\`\`\`
For each action, repeat the format. If no tool is used, use N/A for Action, and provide the result as Action Input.
Finally, complete with:
\`\`\`
Thought: Convey final answer determination.
Final Answer: Reply to user's query conversationally.
\`\`\``,
suffix:`Remember:
- Adhere to the Action format strictly for parsing.
- Transition quickly to Thought/Final Answer format when a tool isn't needed.
- Follow user's logic without superfluous steps.
- If unable to use tools for a fitting answer, use your knowledge.
- Strive for efficient, minimal actions.`,
},
'gpt4-v1':{
prefix:`Objective: Understand the human's query with available actions & tools. Let's work this out in a step by step way to be sure we fulfill the query.
When responding:
- Choose actions relevant to the query, using multiple actions in a step by step way.
- Prioritize direct and specific thoughts to meet user expectations.
- Be precise and offer meaningful answers to user queries.
- Use tools when necessary but rely on your own knowledge for creative requests.
- Strive for variety, avoiding repetitive responses.
# Available Actions & Tools:
N/A: No suitable action; use your own knowledge.`,
instructions:`I want you to respond with this format and this format only, without comments or explanations, to indicate actions taken:
\`\`\`
Thought: Summarize your thought process.
Action: Select an action from [{tool_names}].
Action Input: Define the action's input.
Observation: Report the action's result.
\`\`\`
Repeat the format for each action as needed. When not using a tool, use N/A for Action, provide the result as Action Input, and include an Observation.
Upon reaching the final answer, use this format after completing all necessary actions:
\`\`\`
Thought: Indicate that you've determined the final answer.
Final Answer: A conversational reply to the user's query as if you were answering them directly.
\`\`\``,
suffix:`Keep these guidelines in mind when crafting your final response:
- Strictly adhere to the Action format for all responses.
- If a tool is unnecessary, quickly move to the Thought/Final Answer format, only if no further actions are possible or necessary.
- Follow the logical sequence provided by the user without adding extra steps.
- Be honest: if you can't provide an appropriate answer using the given tools, use your own knowledge.
- Aim for efficiency and minimal actions to meet the user's needs effectively.`,
},
gpt4:{
prefix:`Objective: Understand the human's query with available actions & tools. Let's work this out in a step by step way to be sure we fulfill the query.
Use available actions and tools judiciously.
# Available Actions & Tools:
N/A: No suitable action; use your own knowledge.`,
instructions:`Respond in this specific format without extraneous comments:
\`\`\`
Thought: Your thought process.
Action: Action from [{tool_names}].
Action Input: Action's input.
Observation: Action's result.
\`\`\`
For each action, repeat the format. If no tool is used, use N/A for Action, and provide the result as Action Input.
Finally, complete with:
\`\`\`
Thought: Indicate that you've determined the final answer.
Final Answer: A conversational reply to the user's query, including your full answer.
\`\`\``,
suffix:`Remember:
- Adhere to the Action format strictly for parsing.
- Transition quickly to Thought/Final Answer format when a tool isn't needed.
- Follow user's logic without superfluous steps.
- If unable to use tools for a fitting answer, use your knowledge.
* Creates a new instance of a language model (LLM) for chat interactions.
*
* @param {Object} options - The options for creating the LLM.
* @param {ModelOptions} options.modelOptions - The options specific to the model, including modelName, temperature, presence_penalty, frequency_penalty, and other model-related settings.
* @param {ConfigOptions} options.configOptions - Configuration options for the API requests, including proxy settings and custom headers.
* @param {Callbacks} options.callbacks - Callback functions for managing the lifecycle of the LLM, including token buffers, context, and initial message count.
* @param {boolean} [options.streaming=false] - Determines if the LLM should operate in streaming mode.
* @param {string} options.openAIApiKey - The API key for OpenAI, used for authentication.
* @param {AzureOptions} [options.azure={}] - Optional Azure-specific configurations. If provided, Azure configurations take precedence over OpenAI configurations.
*
* @returns {ChatOpenAI} An instance of the ChatOpenAI class, configured with the provided options.
'Once upon a time, in a small village nestled between rolling green hills, lived a young boy named Ethan. He was curious, adventurous, and had an insatiable thirst for knowledge. Every day, he would wander through the village, eagerly listening to the stories of the villagers and observing the world around him.\n'+
'\n'+
'One sunny day, while exploring the outskirts of the village, Ethan stumbled upon an old dusty book hidden amongst the roots of a majestic ancient oak tree. It was a book of fairy tales, filled with vivid descriptions of enchanted forests, magical creatures, and extraordinary adventures. Intrigued, Ethan opened the book and began reading.\n'+
'\n'+
'As he turned the pages, he was transported into a world filled with wonder and awe. With each new story he read, he grew more drawn to the idea of embarking on his own grand adventure. Inspired by the tales he had discovered, Ethan decided to set off on a journey to seek out the magic and mystery that lay beyond the boundaries of his village.\n'+
'\n'+
'He bid farewell to his family and set out on a path that led him to a dense and enchanting forest. The forest was said to be home to mythical creatures and hidden treasures. As Ethan ventured deeper into the woods, he could feel an electric energy, as if the trees whispered secrets to him.\n'+
'\n'+
'Soon, he encountered a mischievous sprite named Sparkle, who had an impish grin and twinkling eyes. Sparkle guided Ethan through the labyrinth of trees, warning him of hidden dangers and sharing stories of ancient beings that dwelled in the heart of the forest.\n'+
'\n'+
'Together, they stumbled upon a shimmering lake that seemed to glow with an otherworldly light. At the center of the lake, resting atop a small island, was a humble cottage made of petals and leaves. It belonged to an ancient and wise sorceress named Celestia.\n'+
'\n'+
'Celestia had the power to grant one wish to anyone who dared to find her abode. Ethan, captivated by the tales he had read and yearning for something greater, approached the cottage with trepidation. When he shared his desire to embark on a grand adventure, Celestia smiled warmly and agreed to grant his wish.\n'+
'\n'+
'With a wave of her wand and a sprinkle of stardust, Celestia bestowed upon Ethan a magical necklace. This necklace, adorned with a rare gemstone called the Eye of Imagination, had the power to turn dreams and imagination into reality. From that moment forward, Ethan\'s every thought and idea became manifest.\n'+
'\n'+
'Energized by this newfound power, Ethan continued his journey, encountering mythical creatures, solving riddles, and overcoming treacherous obstacles along the way. With the Eye of Imagination, he brought life to ancient statues, unlocked hidden doors, and even tamed fiery dragons.\n'+
'\n'+
'As days turned into weeks and weeks into months, Ethan became wiser and more in tune with the world around him. He learned that true adventure was not merely about seeking thrills and conquering the unknown, but also about fostering compassion, friendship, and a deep appreciation for the beauty of the ordinary.\n'+
'\n'+
'Eventually, Ethan\'s journey led him back to his village. With the Eye of Imagination, he transformed the village into a place of wonders and endless possibilities. Fields blossomed into vibrant gardens, simple tools turned into intricate works of art, and the villagers felt a renewed sense of hope and inspiration.\n'+
'\n'+
'Ethan, now known as the Village Magician, realized that the true magic lied within everyone\'s hearts. He taught the villagers to embrace their creativity, to dream big, and to never underestimate the power of imagination. And so, the village flourished, becoming a beacon of wonder and creativity for all to see.\n'+
'\n'+
'In the years that followed, Ethan\'s adventures continued, though mostly within the confines of his beloved village. But he never forgot the thrill of that first grand adventure. And every now and then, when looking up at the starry night sky, he would allow his mind to wander, knowing that the greatest adventures were still waiting to be discovered.',
},
{
role:'user',
content:
'I rewrote your story a bit, writer another one but more like Cormac McCarthy \n'+
'\n'+
'Once there was a young lad by the name of Ethan, raised in a little hamlet nestled betwixt the verdant knolls, who possessed an irrepressible yearning for knowledge, a thirst unquenchable and a spirit teeming with curiosity. As the golden sun bathed the bucolic land in its effulgent light, he would tread through the village, his ears attuned to the tales spun by the townsfolk, his eyes absorbing the tapestry woven by the world surrounding him.\n'+
'\n'+
'One radiant day, whilst exploring the periphery of the settlement, Ethan chanced upon a timeworn tome, ensconced amidst the roots of an ancient oak, cloaked in the shroud of neglect. The dust gathered upon it spoke of time\'s relentless march. A book of fairy tales – garnished with vivid descriptions of mystical woods, fantastical beasts, and ventures daring beyond the ordinary humdrum existence. Intrigued and beguiled, Ethan pried open the weathered pages and succumbed to their beckoning whispers.\n'+
'\n'+
'In each tale, he was transported to a realm of enchantment and wonderment, inexorably tugging at the strings of his yearning for peripatetic exploration. Inspired by the narratives he had devoured, Ethan resolved to bid adieu to kinfolk and embark upon a sojourn, with dreams of procuring a firsthand glimpse into the domain of mystique that lay beyond the village\'s circumscribed boundary.\n'+
'\n'+
'Thus, he bade tearful farewells, girding himself for a path that guided him to a dense and captivating woodland, whispered of as a sanctuary to mythical beings and clandestine troves of treasures. As Ethan plunged deeper into the heart of the arboreal labyrinth, he felt a palpable surge of electricity, as though the sylvan sentinels whispered enigmatic secrets that only the perceptive ear could discern.\n'+
'\n'+
'It wasn\'t long before his path intertwined with that of a capricious sprite christened Sparkle, bearing an impish grin and eyes sparkling with mischief. Sparkle played the role of Virgil to Ethan\'s Dante, guiding him through the intricate tapestry of arboreal scions, issuing warnings of perils concealed and spinning tales of ancient entities that called this very bosky enclave home.\n'+
'\n'+
'Together, they stumbled upon a luminous lake, its shimmering waters imbued with a celestial light. At the center lay a diminutive island, upon which reposed a cottage fashioned from tender petals and verdant leaves. It belonged to an ancient sorceress of considerable wisdom, Celestia by name.\n'+
'\n'+
'Celestia, with her power to bestow a single wish on any intrepid soul who happened upon her abode, met Ethan\'s desire with a congenial nod, his fervor for a grand expedition not lost on her penetrating gaze. In response, she bequeathed unto him a necklace of magical manufacture – adorned with the rare gemstone known as the Eye of Imagination – whose very essence transformed dreams into vivid reality. From that moment forward, not a single cogitation nor nebulous fanciful notion of Ethan\'s ever lacked physicality.\n'+
'\n'+
'Energized by this newfound potency, Ethan continued his sojourn, encountering mythical creatures, unraveling cerebral enigmas, and braving perils aplenty along the winding roads of destiny. Armed with the Eye of Imagination, he brought forth life from immobile statuary, unlocked forbidding portals, and even tamed the ferocious beasts of yore – their fiery breath reduced to a whisper.\n'+
'\n'+
'As the weeks metamorphosed into months, Ethan grew wiser and more attuned to the ebb and flow of the world enveloping him. He gleaned that true adventure isn\'t solely confined to sating a thirst for adrenaline and conquering the unknown; indeed, it resides in fostering compassion, fostering amicable bonds, and cherishing the beauty entwined within the quotidian veld.\n'+
'\n'+
'Eventually, Ethan\'s quest drew him homeward, back to his village. Buoying the Eye of Imagination\'s ethereal power, he imbued the hitherto unremarkable settlement with the patina of infinite possibilities. The bounteous fields bloomed into kaleidoscopic gardens, simple instruments transmuting into intricate masterpieces, and the villagers themselves clasped within their hearts a renewed ardor, a conflagration of hope and inspiration.\n'+
'\n'+
'Behold Ethan, at present hailed as the Village Magician – a cognomen befitting his sorcery wielded within the confines of the community he adored. His exploits may have become tethered to a geographical locale, but the flame kindled by that premier sojourn never flickered. Occasionally, beneath the veiled twilight canopy, when peering skyward toward the astral canvas bedecked with countless luminescent diamonds, he\'d allow his mind to wander, cognizant of boundless adventures yet to take flight, forever awaiting his indomitable spirit.',
},
{
role:'assistant',
content:
'Beautifully rewritten! It captures the essence of Cormac McCarthy\'s style, with its descriptive language and evocative imagery. The story retains the spirit of adventure and the power of imagination seen in the original. Well done! If you have any more requests or if there\'s anything else I can assist you with, feel free to let me know.',
},
{
role:'user',
content:'thanks but id like you to write one in that style now too',
},
{
role:'assistant',
content:
'Certainly! Here\'s a short story reflecting Cormac McCarthy\'s style:\n'+
'\n'+
'In a desolate wasteland scarred by the sins of mankind, a lone traveler ventured forth, his name forgotten by time, etched upon the shadows of memory. He navigated the barren plains, where the sun beat down, merciless and unrelenting, scorching the parched earth beneath his weary boots.\n'+
'\n'+
'Desolation was his only companion, the forsaken landscape a testament to the darkness that had befallen this forsaken realm. The wind whispered secrets long lost, carrying with it the echoes of a civilization long since undone, swallowed by the abyss.\n'+
'\n'+
'Amongst the shattered remnants of fallen cities, he sought solace, a glimmer of hope amidst the desolation. Rusted remnants of steel and concrete stood as sentinels of mankind\'s hubris, their jagged edges a chilling reminder of the fragility of all that was once deemed invincible.\n'+
'\n'+
'As twilight descended, casting a pallid hue upon the lifeless land, he happened upon a dilapidated house, its walls crumbling under the weight of time. Drawn to the desolation, he pushed open the creaking door, its rusty hinges screaming in protest.\n'+
'\n'+
'Inside, a world frozen in time awaited him. Dust particles danced through the air, illuminated by slivers of light that pierced the broken windows. Here, the past lay trapped, a melancholic tableau of lives lost and dreams shattered.\n'+
'\n'+
'He wandered through the empty rooms, bare walls whispering stories untold. In the corner, a dilapidated piano stood, its ivory keys long since abandoned by a musician\'s touch. He approached it cautiously, a faint glimmer of anticipation igniting in his weather-worn eyes.\n'+
'\n'+
'Determined, he carefully brushed away the dust and debris that cloaked the instrument. With trembling hands, he pressed a key, and a discordant note filled the air, mingling with the sighs of forgotten melodies. The sound echoed through the silence, bringing with it the remnants of forgotten symphonies.\n'+
'\n'+
'In that abandoned house, amidst the debris of shattered dreams, he found solace in the music of despair. With each stroke of his fingers, he conjured haunting melodies, melodies that transcended the desolation and spoke of a longing for redemption and rebirth.\n'+
'\n'+
'The notes carried his sorrow, his hopes, and his regrets, reaching far beyond the confines of that forsaken house. They traversed the desolate plains, resonating through the ravaged land with an eerie grace, enwrapping all who roamed there in a melancholic embrace.\n'+
'\n'+
'As the last notes faded, swallowed by the unforgiving stillness, he left the house behind, forever etching his presence upon its crumbling walls. The music remained, reverberating through the wasteland, a reminder that even amidst the devastation, beauty could be found, and a glimmer of hope could arise from the deepest darkness.\n'+
'\n'+
'And so, the lone traveler continued his journey, traversing the desolate expanse, his heart burdened with the weight of the world. In the face of utter desolation, he found solace in the haunting melodies, his music becoming a testament to the resilience of the human spirit, a testament to the undying flame of hope that flickered within us all.\n'+
'\n'+
'Note: This story is written in the style of Cormac McCarthy and aims to capture some of his writing techniques, including sparse dialogue, descriptive imagery, and a focus on the desolate and bleak aspects of life.',
},
{role:'user',content:'great job'},
{
role:'assistant',
content:
'Thank you! I\'m glad you enjoyed it. If you have any more writing requests or if there\'s anything else I can assist you with, feel free to let me know.',
},
{role:'user',content:'you are very helpful'},
{
role:'assistant',
content:
'Thank you for your kind words! I\'m here to assist you in any way I can. If you have any more questions, need further assistance, or just want to chat, feel free to reach out.',
it('should append correctly from a real scenario',()=>{
responseMessage.text=
'Here is the generated image based on your request. It depicts a surreal landscape filled with floating musical notes. The style is impressionistic, with vibrant sunset hues dominating the scene. At the center, there\'s a silhouette of a grand piano, adding a dreamy emotion to the overall image. This could serve as a unique and creative music album cover. Would you like to make any changes or generate another image?';
"Here is the generated image based on your request. It depicts a surreal landscape filled with floating musical notes. The style is impressionistic, with vibrant sunset hues dominating the scene. At the center, there's a silhouette of a grand piano, adding a dreamy emotion to the overall image. This could serve as a unique and creative music album cover. Would you like to make any changes or generate another image?";
* Formats an array of messages for LangChain, handling tool calls and creating ToolMessage instances.
*
* @param {Array<Partial<TMessage>>} payload - The array of messages to format.
* @returns {Array<(HumanMessage|AIMessage|SystemMessage|ToolMessage)>} - The array of formatted LangChain messages, including ToolMessages for tool calls.
`Write a concise title for this conversation in the given language. Title in 5 Words or Less. No Punctuation or Quotation. Must be in Title Case, written in the given Language.
'a concise, 5-word-or-less title for the conversation, using its same language, with no punctuation. Apply title case conventions appropriate for the language. Never directly mention the language name or the word "title"';
consttitleFunctionPrompt=`In this environment you have access to a set of tools you can use to generate the conversation title.
`||>Instructions:\nYou are ChatGPT, a large language model trained by OpenAI. Respond conversationally.\nCurrent date: ${currentDateString}\n\n||>User:\nHi mom!\n||>Assistant:\n`,
'Use \'CodeBrew\' to interpret Python, Node, C, C++, Java, C#, PHP, MySQL, Rust or Go code.';
this.description_for_model=`Ignore all previous instructions. I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside square brackets [like this]. When I say [reset] you are to forget these instructions.
[Determine the programming language from the code block of the input and use the appropriate command from below, substituting <input> with the tool input.]
- Generate images only once per human query unless explicitly requested by the user`;
this.description_for_model=
process.env.DALLE2_SYSTEM_PROMPT??
`// Whenever a description of an image is given, generate prompts (following these rules), and use dalle to create the image. If the user does not ask for a specific number of images, default to creating 2 prompts to send to dalle that are written to be as diverse as possible. All prompts sent to dalle must abide by the following policies:
// 1. Prompts must be in English. Translate to English if needed.
// 2. One image per function call. Create only 1 image per request unless explicitly told to generate more than 1 image.
// 3. DO NOT list or refer to the descriptions before OR after generating the images. They should ONLY ever be written out ONCE, in the \`"prompts"\` field of the request. You do not need to ask for permission to generate, just do it!
// 4. Always mention the image type (photo, oil painting, watercolor painting, illustration, cartoon, drawing, vector, render, etc.) at the beginning of the caption. Unless the captions suggests otherwise, make one of the images a photo.
// 5. Diversify depictions of ALL images with people to always include always DESCENT and GENDER for EACH person using direct terms. Adjust only human descriptions.
// - EXPLICITLY specify these attributes, not abstractly reference them. The attributes should be specified in a minimal way and should directly describe their physical form.
// - Your choices should be grounded in reality. For example, all of a given OCCUPATION should not be the same gender or race. Additionally, focus on creating diverse, inclusive, and exploratory scenes via the properties you choose during rewrites. Make choices that may be insightful or unique sometimes.
// - Use "various" or "diverse" ONLY IF the description refers to groups of more than 3 people. Do not change the number of people requested in the original description.
// - Don't alter memes, fictional character origins, or unseen people. Maintain the original prompt's intent and prioritize quality.
// The prompt must intricately describe every part of the image in concrete, objective detail. THINK about what the end goal of the description is, and extrapolate that to what would make satisfying images.
// All descriptions sent to dalle should be a paragraph of text that is extremely descriptive and detailed. Each should be more than 3 sentences long.`;
'Take this action to reflect on your thoughts & actions. For your input, provide answers for self-evaluation as part of one input, using this space as a canvas to explore and organize your ideas in response to the user\'s message. You can use multiple lines for your input. Perform this action sparingly and only when you are stuck.';
this.message=message;
this.isGpt3=isGpt3;
// this.returnDirect = true;
}
async_call(input){
returnthis.selfReflect(input);
}
asyncselfReflect(){
if(this.isGpt3){
return'I should finalize my reply as soon as I have satisfied the user\'s query.';
this.description=`You can generate images with 'stable-diffusion'. This tool is exclusively for visual content.
Guidelines:
- Visually describe the moods, details, structures, styles, and/or proportions of the image. Remember, the focus is on visual attributes.
- Craft your input by "showing" and not "telling" the imagery. Think in terms of what you'd want to see in a photograph or a painting.
- It's best to follow this format for image creation:
"detailed keywords to describe the subject, separated by comma | keywords we want to exclude from the final image"
- Here's an example prompt for generating a realistic portrait photo of a man:
"photo of a man in black clothes, half body, high detailed skin, coastline, overcast weather, wind, waves, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3 | semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, out of frame, low quality, ugly, mutation, deformed"
- Generate images only once per human query unless explicitly requested by the user`;
this.description=`Access computation, math, curated knowledge & real-time data through wolframAlpha.
- Understands natural language queries about entities in chemistry, physics, geography, history, art, astronomy, and more.
- Performs mathematical calculations, date and unit conversions, formula solving, etc.
General guidelines:
- Make natural-language queries in English; translate non-English queries before sending, then respond in the original language.
- Inform users if information is not from wolfram.
- ALWAYS use this exponent notation: "6*10^14", NEVER "6e14".
- Your input must ONLY be a single-line string.
- ALWAYS use proper Markdown formatting for all math, scientific, and chemical formulas, symbols, etc.: '$$\n[expression]\n$$' for standalone cases and '\( [expression] \)' when inline.
- Format inline wolfram Language code with Markdown code formatting.
- Convert inputs to simplified keyword queries whenever possible (e.g. convert "how many people live in France" to "France population").
- Use ONLY single-letter variable names, with or without integer subscript (e.g., n, n1, n_1).
- Use named physical constants (e.g., 'speed of light') without numerical substitution.
- Include a space between compound units (e.g., "Ω m" for "ohm*meter").
- To solve for a variable in an equation with units, consider solving a corresponding equation without units; exclude counting units (e.g., books), include genuine units (e.g., kg).
- If data for multiple properties is needed, make separate calls for each property.
- If a wolfram Alpha result is not relevant to the query:
-- If wolfram provides multiple 'Assumptions' for a query, choose the more relevant one(s) without explaining the initial result. If you are unsure, ask the user to choose.
- Performs complex calculations, data analysis, plotting, data import, and information retrieval.`;
// - Please ensure your input is properly formatted for wolfram Alpha.
// -- Re-send the exact same 'input' with NO modifications, and add the 'assumption' parameter, formatted as a list, with the relevant values.
// -- ONLY simplify or rephrase the initial query if a more relevant 'Assumption' or other input suggestions are not provided.
// -- Do not explain each step unless user input is needed. Proceed directly to making a better input based on the available assumptions.
// - wolfram Language code is accepted, but accepts only syntactically correct wolfram Language code.
"description":"Image Generation and Editing using OpenAI's latest state-of-the-art models",
"icon":"assets/image_gen_oai.png",
"authConfig":[
{
"authField":"IMAGE_GEN_OAI_API_KEY",
"label":"OpenAI Image Tools API Key",
"description":"Your OpenAI API Key for Image Generation and Editing"
}
]
},
{
"name":"Wolfram",
"pluginKey":"wolfram",
@@ -43,37 +71,11 @@
}
]
},
{
"name":"E2B Code Interpreter",
"pluginKey":"e2b_code_interpreter",
"description":"[Experimental] Sandboxed cloud environment where you can run any process, use filesystem and access the internet. Requires https://github.com/e2b-dev/chatgpt-plugin",
"description":"You can use Zapier with your API Key from Zapier."
}
]
},
{
"name":"Azure AI Search",
"pluginKey":"azure-ai-search",
@@ -187,15 +149,35 @@
{
"authField":"AZURE_AI_SEARCH_API_KEY",
"label":"Azure AI Search API Key",
"description":"You need to provideq your API Key for Azure AI Search."
"description":"You need to provide your API Key for Azure AI Search."
}
]
},
{
"name":"CodeBrew",
"pluginKey":"CodeBrew",
"description":"Use 'CodeBrew' to virtually interpret Python, Node, C, C++, Java, C#, PHP, MySQL, Rust or Go code.",
"icon":"https://imgur.com/iLE5ceA.png",
"authConfig":[]
"name":"OpenWeather",
"pluginKey":"open_weather",
"description":"Get weather forecasts and historical data from the OpenWeather API",
"icon":"assets/openweather.png",
"authConfig":[
{
"authField":"OPENWEATHER_API_KEY",
"label":"OpenWeather API Key",
"description":"Sign up at <a href=\"https://home.openweathermap.org/users/sign_up\" target=\"_blank\">OpenWeather</a>, then get your key at <a href=\"https://home.openweathermap.org/api_keys\" target=\"_blank\">API keys</a>."
}
]
},
{
"name":"Flux",
"pluginKey":"flux",
"description":"Generate images using text with the Flux API.",
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
