Compare commits

..

141 Commits

Author SHA1 Message Date
Danny Avila
1e53ffa7ea v0.8.1-rc1 (#10316)
*  v0.8.1-rc1

* chore: Update CONFIG_VERSION to 1.3.1
2025-10-30 16:36:54 -04:00
github-actions[bot]
65281464fc 🌍 i18n: Update translation.json with latest translations (#10315)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-10-30 16:23:37 -04:00
Peter
658921af88 🔗 fix: Provided Azure Base URL Construction for Responses API (#10289)
* fix: response api works with azure base url configured

* add unit test

---------

Co-authored-by: Peter Rothlaender <peter.rothlaender@ginkgo.com>
2025-10-30 14:57:03 -04:00
Sean McGrath
ce6456c39f 🎨 fix: Update artifacts Tailwind to official CDN (#10301)
Co-authored-by: Sean McGrath <sean.mcgrath@holmesgroup.com>
2025-10-30 14:49:00 -04:00
Danny Avila
d904b281f1 🦙 fix: Ollama Custom Headers (#10314)
* 🦙 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
2025-10-30 14:48:10 -04:00
github-actions[bot]
5e35b7d09d 🌍 i18n: Update translation.json with latest translations (#10298)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-10-29 16:41:55 -04:00
Danny Avila
6adb425780 🔄 refactor: Max tokens handling in Agent Initialization (#10299)
* 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.
2025-10-29 16:41:27 -04:00
Danny Avila
e6aeec9f25 🎚️ feat: Reasoning Parameters for Custom Endpoints (#10297) 2025-10-29 13:41:35 -04:00
Danny Avila
861ef98d29 📫 refactor: OpenID Email Claim Fallback (#10296)
* 📫 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.
2025-10-29 12:57:43 -04:00
poornapragnyah
05c706137e ✂️ fix: Trim Reasoning Tags from Titles and Delete Button Visibility (#10285)
* 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>
2025-10-29 12:48:58 -04:00
github-actions[bot]
9fbc2afe40 🌍 i18n: Update translation.json with latest translations (#10282)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-10-29 12:38:43 -04:00
Danny Avila
8adef91cf5 🎚️ fix: Default Max Output Tokens for Claude 4+ Models (#10293) 2025-10-29 12:28:01 -04:00
Danny Avila
70ff6e94f2 🪢 feat: Add Langfuse Tracing Support (#10292)
* 📦 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
2025-10-29 12:23:09 -04:00
Danny Avila
0e05ff484f 🔄 refactor: OAI Image Edit Proxy, Speech Settings Handling, Import Query Data Usage (#10281)
* 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
2025-10-28 09:36:03 -04:00
github-actions[bot]
250209858a 🌍 i18n: Update translation.json with latest translations (#10274)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-10-28 09:00:19 -04:00
Daniel Paulus
9e77f835a6 🎛️ feat: Custom Environment Variable Support to RAG API Helm Chart (#10245)
* Possibility to add extra env values to the deployment

* Fix: Custom environment variables should be placed after the predefined environment variables
2025-10-28 08:37:04 -04:00
Danny Avila
7973cb42ef 🔃 refactor: Clear MCP only on Model Spec Selection without MCP Servers (#10273) 2025-10-27 20:33:51 -04:00
Dustin Healy
0446d0e190 fix: Address Accessibility Issues (#10260)
* 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>
2025-10-27 19:46:43 -04:00
Danny Avila
33d6b337bc 📛 feat: Chat Badges via Model Specs (#10272)
* 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
2025-10-27 19:46:30 -04:00
github-actions[bot]
64df54528d 🌍 i18n: Update translation.json with latest translations (#10259)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-10-27 19:45:37 -04:00
Max Sanna
d46dde4e01 👫 fix: Update Entra ID group retrieval to use getMemberGroups and add pagination support (#10199) 2025-10-26 21:58:29 -04:00
Federico Ruggi
13b784a3e6 🧼 fix: Sanitize MCP Server Selection Against Config (#10243)
* 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>
2025-10-26 21:48:23 -04:00
Danny Avila
90e610ceda 🎪 refactor: Allow Last Model Spec Selection without Prioritizing (#10258)
* 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
2025-10-26 21:37:55 -04:00
github-actions[bot]
cbbbde3681 🌍 i18n: Update translation.json with latest translations (#10229)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-10-26 21:32:38 -04:00
Sebastien Bruel
05c9195197 🛠️ fix: Agent Tools Modal on First-Time Agent Creation (#10234) 2025-10-26 21:30:05 -04:00
Danny Avila
9495520f6f 📦 chore: update vite to v6.4.1 and @playwright/test to v1.56.1 (#10227)
* 📦 chore: update vite to v6.4.1

* 📦 chore: update @playwright/test to v1.56.1
2025-10-22 22:22:57 +02:00
Sebastien Bruel
87d7ee4b0e 🌐 feat: Configurable Domain and Port for Vite Dev Server (#10180) 2025-10-22 22:04:49 +02:00
Danny Avila
d8d5d59d92 ♻️ refactor: Message Cache Clearing Logic into Reusable Helper (#10226) 2025-10-22 22:02:29 +02:00
Danny Avila
e3d33fed8d 📦 chore: update @librechat/agents to v2.4.86 (#10216) 2025-10-22 16:51:58 +02:00
github-actions[bot]
cbf52eabe3 🌍 i18n: Update translation.json with latest translations (#10175)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-10-22 09:53:21 +02:00
Danny Avila
36f0365fd4 🧮 feat: Enhance Model Pricing Coverage and Pattern Matching (#10173)
* 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>
2025-10-19 15:23:27 +02:00
Federico Ruggi
589f119310 🩹 fix: Wrap Attempt to Reconnect OAuth MCP Servers (#10172) 2025-10-18 05:54:05 -04:00
Marco Beretta
d41b07c0af ♻️ refactor: Replace fontSize Recoil atom with Jotai (#10171)
* 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>
2025-10-18 05:50:34 -04:00
Sean McGrath
114deecc4e 🛠️ chore: Add @radix-ui/react-tooltip to Artifact Dependencies (#10112) 2025-10-16 16:26:14 -04:00
Danny Avila
f59daaeecc 📄 feat: Context Field for Anthropic Documents (PDF) (#10148)
* 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.
2025-10-16 16:24:14 -04:00
Danny Avila
bc77bbd1ba 🪂 refactor: OCR Fallback for "Upload as Text" File Process (#10126) 2025-10-15 09:20:54 -04:00
Danny Avila
c602088178 📱 fix: Improve Mobile Chat Focus Detection and Navigation (#10125) 2025-10-15 08:12:32 -04:00
Danny Avila
3d1cedb85b 📡 refactor: Flush Redis Cache Script (#10087)
* 🔧 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
2025-10-12 04:15:18 -04:00
Marlon
bf2567bc8f 🏷️ chore: update OpenAI models list in .env.example (#10085)
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
2025-10-12 04:13:17 -04:00
Federico Ruggi
5ce67b5b71 📮 feat: Custom OAuth Headers Support for MCP Server Config (#10014)
* add oauth_headers field to mcp options

* wrap fetch to pass oauth headers

* fix order

* consolidate headers passing

* fix tests
2025-10-11 11:17:12 -04:00
WhammyLeaf
cbd217efae 🏷️ feat: Add Custom Deployment Labels and Annotations for Helm (#10076) 2025-10-11 11:15:35 -04:00
François Leblanc
d990fe1d5f 📖 feat: Word Wrapping for Text and Markdown Code Blocks (#10055)
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.
2025-10-11 10:39:33 -04:00
Sebastien Bruel
7c9a868d34 📝 feat: Add Markdown Rendering Support for Artifacts (#10049)
* 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>
2025-10-11 10:37:35 -04:00
Peter Nancarrow
e9a85d5c65 🗂️ feat: Add Optional Group Field to ModelSpecs Configuration (#9996)
* 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>
2025-10-11 07:55:06 -04:00
Karthikeyan N
f61afc1124 💸 chore: Update Gemini 2.5 Flash Lite Input Pricing (#10062)
* 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
2025-10-11 07:53:28 -04:00
Marco Beretta
5566cc499e 🔗 fix: Add branch-specific shared links (targetMessageId) (#10016)
* 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>
2025-10-10 08:42:05 -04:00
Dustin Healy
ded3f2e998 🕸️ fix: Upload to Provider Filetype Filtering for DragDropModal (#10064) 2025-10-10 07:48:31 -04:00
Dustin Healy
7792fcee17 👆🏼 fix: Agent Support for Upload to Provider in DragDropModal (#10063) 2025-10-10 07:43:56 -04:00
github-actions[bot]
f931731ef8 🌍 i18n: Update translation.json with latest translations (#10070)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-10-10 07:43:11 -04:00
Danny Avila
07d0abc9fd 🖼️ fix: Extract File Context & Persist Attachments (#10069)
- 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
2025-10-10 05:35:37 -04:00
Danny Avila
fbe341a171 refactor: Latest Message Tracking with Robust Text Key Generation (#10059)
* 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
2025-10-10 04:22:16 -04:00
Danny Avila
20282f32c8 📦 chore: Bump nodemailer to v7.0.9 (#10045)
* chore: add build script for client package to streamline builds

* chore: update nodemailer dependency to version 7.0.9
2025-10-09 03:45:10 -04:00
José Pedro Silva
6fa3db2969 👑 feat: Add OIDC Claim-Based Admin Role Assignment (#9170)
* 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>
2025-10-09 03:35:22 -04:00
Dustin Healy
ff027e8243 👨‍🔧 fix: Direct Provider Attachment Support for Agents (#10035)
* fix: show direct upload option on applicable agents

* fix: allow agent file upload handler to process direct upload files (no tool_resource)
2025-10-09 03:31:04 -04:00
MarcAmick
e9b678dd6a ⚖️ fix: Add Configurable File Size Cap for Conversation Imports (#10012)
* 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>
2025-10-07 14:47:21 -04:00
github-actions[bot]
bb7a0274fa 🌍 i18n: Update translation.json with latest translations (#9995)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-10-07 14:14:18 -04:00
Marco Beretta
a5189052ec ️ fix: Accessibility, UI consistency, dialog & avatar refactors (#9975)
* 🔧 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
2025-10-07 14:12:49 -04:00
Danny Avila
bcd97aad2f 📎 feat: Direct Provider Attachment Support for Multimodal Content (#9994)
* 📎 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>
2025-10-06 17:30:16 -04:00
Danny Avila
9c77f53454 🔀 refactor: Only Cleanup Meili Sync if actually Synced 2025-10-05 22:41:40 -04:00
Danny Avila
31a283a4fe 🔍 feat: Add Serper as Scraper Provider and Firecrawl Version Support (#9984)
* 🔧 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
2025-10-05 20:34:05 -04:00
Danny Avila
857c054a9a 🗑️ feat: Cleanup for Orphaned MeiliSearch Documents (#9980)
- 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.
2025-10-05 15:54:47 -04:00
Danny Avila
c9103a1708 🤖 feat: Add Z.AI GLM Context Window & Pricing (#9979)
* 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
2025-10-05 09:08:29 -04:00
Danny Avila
7288449011 🫴 refactor: Add Broader Support for GPT-OSS Naming (#9978) 2025-10-05 07:02:09 -04:00
alfo-dev
7897801fbc 🧱 fix: DALL-E Proxy Bypass (#9971) 2025-10-05 06:56:21 -04:00
Danny Avila
838fb53208 🔃 refactor: Decouple Effects from AppService, move to data-schemas (#9974)
* 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
2025-10-05 06:37:57 -04:00
Danny Avila
9ff608e6af 📦 chore: fix packages/api peer dependencies (#9973) 2025-10-04 16:43:22 -04:00
Danny Avila
1b8a0bfaee ⚙️ chore: Resolve Build Warning, Package Cleanup, Robust Temp Chat Time (#9962)
* ⚙️ 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
2025-10-04 01:53:37 -04:00
Federico Ruggi
c0ed738aed 🚉 feat: MCP Registry Individual Server Init (2) (#9940)
* 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
2025-10-03 16:01:34 -04:00
Theo N. Truong
0e5bb6f98c 🔄 refactor: Migrate Cache Logic to TypeScript (#9771)
* 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>
2025-10-02 09:33:58 -04:00
github-actions[bot]
341435fb25 🌍 i18n: Update translation.json with latest translations (#9932)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-10-01 23:31:23 -04:00
Danny Avila
dbe4dd96b4 🧹 chore: Cleanup Logger and Utility Imports (#9935)
* 🧹 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
2025-10-01 23:30:47 -04:00
Danny Avila
b7d13cec6f v0.8.0 (#9929)
*  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
2025-10-01 18:00:56 -04:00
Danny Avila
37321ea10d 👨‍🚀 chore: Add Newer OpenAI Models to Default List (#9926) 2025-10-01 10:06:35 -04:00
WhammyLeaf
17ab91f1fd 🔓 feat: Expose Env Field in Helm Deployment Template (#9890)
* 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
2025-10-01 09:32:19 -04:00
Danny Avila
4777bd22c5 Revert "🚉 feat: MCP Registry Individual Server Init (#9887)"
This reverts commit b8720a9b7a.
2025-09-30 09:39:19 -04:00
normunds-wipo
dfe236acb5 📂 fix: Allow text/xml mimetype (#9908) 2025-09-30 08:49:41 -04:00
Federico Ruggi
c5d1861acf 🔧 fix: Ensure getServerToolFunctions Handles Errors (#9895)
* ensure getServerToolFunctions handles errors

* remove reduntant test
2025-09-30 08:48:39 -04:00
Federico Ruggi
b8720a9b7a 🚉 feat: MCP Registry Individual Server Init (#9887)
* initialize servers sequentially

* adjust for exported properties that are not nullable anymore

* use underscore separator

* mock with set

* customize init timeout via env var
2025-09-29 21:24:41 -04:00
linnil1
0b2fde73e3 ❇️ feat: Add Gemini 2.5 Default Models & Pricing (#9892)
* feat: Add Gemini 2.5 models support

* feat: Remove deprecated Gemini models
2025-09-29 21:23:28 -04:00
Danny Avila
c19b8755a7 🤖 feat: Claude Sonnet 4.5, DeepSeek V3.2 Context & Pricing (#9894)
* 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
2025-09-29 21:09:26 -04:00
github-actions[bot]
f6e19d8034 🌍 i18n: Update translation.json with latest translations (#9869)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-09-29 09:12:50 -04:00
Danny Avila
c0eb19730a 🪙 refactor: Auth Token Retrieval with Sorting and Query Options (#9884) 2025-09-29 09:06:40 -04:00
Danny Avila
a1471c2f37 📧 fix: Case-Insensitive Domain Matching (#9868)
* 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.
2025-09-27 21:20:19 -04:00
Danny Avila
712f0b3ca2 📌 fix: Exclude Pinned Keys from Cleanup and Fix MCP Pin State (#9867)
* 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
2025-09-27 17:21:48 -04:00
MyGitHub
062d813b21 ☸️ feat: Helm hostAliases Support For Custom DNS Mappings (#9857)
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>
2025-09-27 10:49:36 -04:00
Danny Avila
4b5b46604c 🔍 refactor: OCR Fully Optional with Defaults for "Upload as Text" (#9856)
* 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
2025-09-26 11:56:11 -04:00
Danny Avila
3d7eaf0fcc 🌐 feat: OpenRouter Web Search (#9853)
* 🌐 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
2025-09-26 09:35:41 -04:00
Danny Avila
823015160c 🕸️ refactor: Drop/Add web_search Param Handling for Custom Endpoints (#9852)
- 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.
2025-09-26 08:56:39 -04:00
Theo N. Truong
3219734b9e 🔌 fix: Shared MCP Server Connection Management (#9822)
- 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.
2025-09-26 08:24:36 -04:00
Danny Avila
4f3683fd9a 👤 fix: Missing User Placeholder Fields for MCP Services (#9824) 2025-09-24 22:48:38 -04:00
Danny Avila
57f8b333bc 🕵️ refactor: Optimize Message Search Performance (#9818)
* 🕵️ 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
2025-09-24 16:27:34 -04:00
Danny Avila
f9aebeba92 🛡️ fix: Title Generation Skip Logic Based On Endpoint Config (#9811) 2025-09-24 10:21:19 -04:00
github-actions[bot]
b85950aa9a 🌍 i18n: Update translation.json with latest translations (#9789)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-09-24 07:13:08 -04:00
Danny Avila
bcec5bfceb 🆔 fix: Prioritize Immutable Sub Claim for OIDC User ID (#9788)
* 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>
2025-09-23 14:46:53 -04:00
MyGitHub
e4f323e71a 🌐 feat: Helm DNS Configuration Support for Traffic Redirection (#9785)
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>
2025-09-23 10:41:58 -04:00
Ihsan Soydemir
d83826b604 🔐 feat: Support Multiple Roles in OPENID_REQUIRED_ROLE (#9171)
* 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>
2025-09-23 10:39:34 -04:00
Jerum Hubbert
2153db2f5f 📊 feat: Helm Chart Port Flexibility and MongoDB Update (#9750)
- 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>
2025-09-23 09:48:07 -04:00
Clay Rosenthal
de02892396 📦 fix: Helm Chart HPA Configuration Issues (#9770) 2025-09-23 09:44:40 -04:00
Sean McGrath
f61e057f7f 🔐 fix: MCP OAuth Token Persistence Race Condition and Refresh Auth Method (#9773)
* set supported endpoint auth method when token_url exists

* persist tokens immediately

* add token storage validation tests
2025-09-23 09:35:56 -04:00
Danny Avila
91e49d82aa 🔼 feat: Vercel App Attribution for LibreChat (#9769) 2025-09-22 16:15:15 -04:00
github-actions[bot]
880c7b43a1 🌍 i18n: Update translation.json with latest translations (#9764)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-09-22 14:58:35 -04:00
Danny Avila
c99a29f8da 📦 chore: update @librechat/agents to v2.4.80 (#9766) 2025-09-22 14:58:20 -04:00
Danny Avila
8a60e8990f 🤖 refactor: Side Panel Agent UI To Account For Ephemeral Agents (#9763)
* 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
2025-09-22 09:48:05 -04:00
Danny Avila
a6bf2b6ce3 🔐 refactor: Improve MCP Auth UX for Agent Panel (#9762)
* 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
2025-09-22 08:53:19 -04:00
github-actions[bot]
ff8dac570f 🌍 i18n: Update translation.json with latest translations (#9759)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-09-22 08:44:07 -04:00
Danny Avila
96870e0da0 refactor: MCP OAuth Polling with Gradual Backoff and Timeout Handling (#9752)
* 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
2025-09-21 22:58:19 -04:00
Danny Avila
f0599ad36c 🧬 refactor: Optimize MCP Tool Queries with Server-Centric Architecture
🧬 refactor: Optimize MCP Tool Queries with Server-Centric Architecture

refactor: optimize mcp tool queries by removing redundancy, making server-centric structure, enabling query only when expected, minimize looping/transforming query data, eliminating unused/compute-heavy methods

ci: MCP Server Tools Mocking in Agent Tests
2025-09-21 20:40:14 -04:00
Danny Avila
5b1a31ef4d 🔄 refactor: Optimize MCP Tool Initialization
🔄 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
2025-09-21 20:31:28 -04:00
Danny Avila
386900fb4f 🧰 refactor: Decouple MCP Tools from System Tools (#9748) 2025-09-21 07:56:40 -04:00
Federico Ruggi
9d2aba5df5 🛡️ fix: Handle Null MCPManager In OAuthReconnectionManager (#9740) 2025-09-20 11:06:23 -04:00
Thomas Joußen
a5195a57a4 🔐 fix: Handle Multiple Email Addresses in LDAP Auth (#9729) 2025-09-20 11:01:45 -04:00
Danny Avila
2489670f54 📂 refactor: File Read Operations (#9747)
* 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
2025-09-20 10:17:24 -04:00
Danny Avila
0352067da2 🎨 refactor: Improve Mermaid Artifacts Styling (#9742)
* 🎨 refactor: Improve Mermaid Artifacts Styling

* refactor: Replace ArtifactMarkdown with MermaidMarkdown
2025-09-20 08:19:44 -04:00
Danny Avila
fcaf55143d 🏷️ fix: Increment Tag Counters When Forking/Duplicating Conversations (#9737)
* 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
2025-09-19 22:02:09 -04:00
Danny Avila
aae3694b11 🛠️ chore: Typing and Remove Comments (#9732)
* chore: Update documentation for formatToolContent function, remove JSDoc types and duplicate comments

* chore: fix type errors due to attachment.filename in Attachment component
2025-09-19 16:22:53 -04:00
github-actions[bot]
68c9f668c1 🌍 i18n: Update translation.json with latest translations (#9726)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-09-19 13:26:57 -04:00
Danny Avila
8b2e1c6088 📝 fix: Prevent Deletion of User Input During AI Generation (#9719)
* 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>
2025-09-19 13:19:38 -04:00
Danny Avila
99135a3dc1 🔍 fix: Race Condition in Search Bar Clear Text Handler (#9718) 2025-09-19 07:52:16 -04:00
Danny Avila
344e7c44b5 🔐 fix: Respect Server's Token Endpoint Auth Methods for MCP OAuth Refresh (#9717)
* 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
2025-09-19 06:50:02 -04:00
github-actions[bot]
e5d2a932bc 🌍 i18n: Update translation.json with latest translations (#9704)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-09-19 06:06:40 -04:00
Danny Avila
c40554c03b 🏪 fix: Template for Chats Starting from Agent Marketplace (#9702)
* fix: correctly build conversation template and preset for chats starting from marketplace

* test: enhance AgentDetail tests with additional localization and conversation mocks
2025-09-18 21:05:43 -04:00
Danny Avila
98af4564e8 🎯 refactor: MCP Registry To Handle serverInstructions As String "true" (#9703)
- 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.
2025-09-18 21:03:21 -04:00
Real Null
26a58fcabc 🚨 fix: Redis CA file handling (#9692)
* 🚨 fix: Critical Redis CA file handling bug that could crash app

🔧 Added safe error handling for Redis CA certificate file reading in cacheConfig.js

## 🐛 Problem
- fs.readFileSync() was called directly without error handling
- Missing or inaccessible REDIS_CA files would throw unhandled exceptions
- 💥 Application would crash during startup with cryptic filesystem errors
-  No validation of file existence before attempting to read

##  Solution
-  Added getRedisCA() helper function with comprehensive error handling
- 🔍 Implemented fs.existsSync() check before file reading attempts
- 🛡️ Added try-catch block to handle filesystem errors gracefully
- 📝 Added informative warning/error logging for troubleshooting
- 🔄 Function returns null safely on any error condition

## 🎯 Benefits
- 🚫 Prevents application crashes from misconfigured CA certificate paths
- 🔍 Provides clear error messages for debugging certificate issues
-  Maintains backward compatibility for valid certificate configurations
- 🚀 Improves production stability and deployment reliability

## 🧪 Testing Results
-  Verified handling of missing REDIS_CA environment variable
-  Tested with non-existent file paths (returns null with warning)
-  Confirmed valid certificate files are read correctly
-  Validated error handling for permission/access issues

🎉 This fix ensures LibreChat continues running regardless of Redis CA
certificate configuration problems, improving overall system reliability.

🏷️ Type: 🐛 Bug Fix
📊 Impact: 🔴 High (prevents application crashes)
🎯 Area: Cache Configuration, Redis Integration

* chore: Redis CA certificate handling with proper logging + JSDocs

* chore: Improve error logging for Redis CA certificate file read failure

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2025-09-18 20:33:40 -04:00
Danny Avila
3fec63e597 💽 fix: Memory Permissions Handling (#9701) 2025-09-18 20:26:02 -04:00
Danny Avila
81139046e5 🔄 refactor: Convert OCR Tool Resource to Context (#9699)
* 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
2025-09-18 20:06:59 -04:00
Danny Avila
89d12a8ccd 🔍 fix: Retrieve Multiple Agents In File Access Check (#9695)
- 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.
2025-09-18 15:42:05 -04:00
github-actions[bot]
f6d34d78ca 🌍 i18n: Update translation.json with latest translations (#9691)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-09-18 14:45:21 -04:00
Danny Avila
48ca1bfd88 🧩 refactor: File Upload Options based on Ephemeral Agent (#9693)
* 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`
2025-09-18 14:44:55 -04:00
Danny Avila
208be7c06c 🗨️ refactor: Only Allow Prompt Queries with Access (#9688) 2025-09-18 10:00:33 -04:00
Danny Avila
02bfe32905 🛠️ fix: Missing Tool Definitions on Redis Cache Clear (#9681) 2025-09-17 23:19:28 -04:00
github-actions[bot]
4499494aba 🌍 i18n: Update translation.json with latest translations (#9679)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-09-17 23:14:49 -04:00
Federico Ruggi
d04da60b3b 💫 feat: MCP OAuth Auto-Reconnect (#9646)
* add oauth reconnect tracker

* add connection tracker to mcp manager

* reconnect oauth mcp servers function

* call reconnection in auth controller

* make sure to check connection in panel

* wait for isConnected

* add const for poll interval

* add logging to tryReconnect

* check expiration

* check mcp manager is not null

* check mcp manager is not null

* add test for reconnecting mcp server

* unify logic inside OAuthReconnectionManager

* test reconnection manager, adjust

* chore: reorder import statements in index.js

* chore: imports

* chore: imports

* chore: imports

* chore: imports

* chore: imports

* chore: imports and use types explicitly

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2025-09-17 16:49:36 -04:00
keltschdt
0e94d97bfb fix: Disable TTL For Transient OIDC Users In Permission Service (#9643) 2025-09-17 14:21:36 -04:00
Danny Avila
45ab4d4503 🎋 refactor: Improve Message UI State Handling (#9678)
* refactor: `ExecuteCode` component with submission state handling and cancellation message

* fix: Remove unnecessary argument check for execute_code tool call

* refactor: streamlined messages context

* chore: remove unused Convo prop

* chore: remove unnecessary whitespace in Message component

* refactor: enhance message context with submission state and latest message tracking

* chore: import order
2025-09-17 13:07:56 -04:00
github-actions[bot]
0ceef12eea 🌍 i18n: Update translation.json with latest translations (#9648)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-09-15 18:41:34 -04:00
Danny Avila
6738360051 📋 refactor: Agent Tool Permissions for File Upload Options (#9647)
- 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.
2025-09-15 12:57:40 -04:00
Dustin Healy
52b65492d5 👻 fix: Phantom MCP Tool Calls (#9634)
* fix: mcp tool calls no longer happening when unselected (without breaking new convo behavior)

* refactor: Improve ephemeral agent synchronization logic in useMCPSelect

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2025-09-15 10:35:15 -04:00
Danny Avila
7a9a99d2a0 🔗 refactor: URL sanitization for MCP logging (#9632) 2025-09-14 18:55:32 -04:00
Danny Avila
5bfb06b417 💻 feat: Add Proxy Config for Mistral OCR API (#9629)
* 💻 feat: Add proxy configuration support for Mistral OCR API requests

* refactor: Implement proxy support for Mistral API requests using HttpsProxyAgent
2025-09-14 18:50:41 -04:00
github-actions[bot]
2ce8f1f686 🌍 i18n: Update translation.json with latest translations (#9626)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-09-14 18:48:17 -04:00
Danny Avila
1a47601533 🔃 fix: Refresh Token Edge Cases (#9625)
* 🔃 fix: Refresh Token Edge Cases

* chore: Update parameter type for setAuthTokens function
2025-09-13 21:36:45 -04:00
644 changed files with 24608 additions and 9178 deletions

View File

@@ -163,10 +163,10 @@ GOOGLE_KEY=user_provided
# GOOGLE_AUTH_HEADER=true
# Gemini API (AI Studio)
# GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite-preview-06-17,gemini-2.0-flash,gemini-2.0-flash-lite
# GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite,gemini-2.0-flash,gemini-2.0-flash-lite
# Vertex AI
# GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite-preview-06-17,gemini-2.0-flash-001,gemini-2.0-flash-lite-001
# GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite,gemini-2.0-flash-001,gemini-2.0-flash-lite-001
# GOOGLE_TITLE_MODEL=gemini-2.0-flash-lite-001
@@ -196,7 +196,7 @@ GOOGLE_KEY=user_provided
#============#
OPENAI_API_KEY=user_provided
# OPENAI_MODELS=o1,o1-mini,o1-preview,gpt-4o,gpt-4.5-preview,chatgpt-4o-latest,gpt-4o-mini,gpt-3.5-turbo-0125,gpt-3.5-turbo-0301,gpt-3.5-turbo,gpt-4,gpt-4-0613,gpt-4-vision-preview,gpt-3.5-turbo-0613,gpt-3.5-turbo-16k-0613,gpt-4-0125-preview,gpt-4-turbo-preview,gpt-4-1106-preview,gpt-3.5-turbo-1106,gpt-3.5-turbo-instruct,gpt-3.5-turbo-instruct-0914,gpt-3.5-turbo-16k
# OPENAI_MODELS=gpt-5,gpt-5-codex,gpt-5-mini,gpt-5-nano,o3-pro,o3,o4-mini,gpt-4.1,gpt-4.1-mini,gpt-4.1-nano,o3-mini,o1-pro,o1,gpt-4o,gpt-4o-mini
DEBUG_OPENAI=false
@@ -459,6 +459,9 @@ OPENID_CALLBACK_URL=/oauth/openid/callback
OPENID_REQUIRED_ROLE=
OPENID_REQUIRED_ROLE_TOKEN_KIND=
OPENID_REQUIRED_ROLE_PARAMETER_PATH=
OPENID_ADMIN_ROLE=
OPENID_ADMIN_ROLE_PARAMETER_PATH=
OPENID_ADMIN_ROLE_TOKEN_KIND=
# 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
@@ -650,6 +653,12 @@ HELP_AND_FAQ_URL=https://librechat.ai
# Google tag manager id
#ANALYTICS_GTM_ID=user provided google tag manager id
# limit conversation file imports to a certain number of bytes in size to avoid the container
# maxing out memory limitations by unremarking this line and supplying a file size in bytes
# such as the below example of 250 mib
# CONVERSATION_IMPORT_MAX_FILE_SIZE_BYTES=262144000
#===============#
# REDIS Options #
#===============#

View File

@@ -0,0 +1,78 @@
name: Cache Integration Tests
on:
pull_request:
branches:
- main
- dev
- release/*
paths:
- 'packages/api/src/cache/**'
- 'redis-config/**'
- '.github/workflows/cache-integration-tests.yml'
jobs:
cache_integration_tests:
name: Run Cache Integration Tests
timeout-minutes: 30
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v4
- name: Use Node.js 20.x
uses: actions/setup-node@v4
with:
node-version: 20
cache: 'npm'
- name: Install Redis tools
run: |
sudo apt-get update
sudo apt-get install -y redis-server redis-tools
- name: Start Single Redis Instance
run: |
redis-server --daemonize yes --port 6379
sleep 2
# Verify single Redis is running
redis-cli -p 6379 ping || exit 1
- name: Start Redis Cluster
working-directory: redis-config
run: |
chmod +x start-cluster.sh stop-cluster.sh
./start-cluster.sh
sleep 10
# Verify cluster is running
redis-cli -p 7001 cluster info || exit 1
redis-cli -p 7002 cluster info || exit 1
redis-cli -p 7003 cluster info || exit 1
- name: Install dependencies
run: npm ci
- name: Build packages
run: |
npm run build:data-provider
npm run build:data-schemas
npm run build:api
- name: Run cache integration tests
working-directory: packages/api
env:
NODE_ENV: test
USE_REDIS: true
REDIS_URI: redis://127.0.0.1:6379
REDIS_CLUSTER_URI: redis://127.0.0.1:7001,redis://127.0.0.1:7002,redis://127.0.0.1:7003
run: npm run test:cache:integration
- name: Stop Redis Cluster
if: always()
working-directory: redis-config
run: ./stop-cluster.sh || true
- name: Stop Single Redis Instance
if: always()
run: redis-cli -p 6379 shutdown || true

View File

@@ -1,5 +1,2 @@
#!/usr/bin/env sh
set -e
. "$(dirname -- "$0")/_/husky.sh"
[ -n "$CI" ] && exit 0
npx lint-staged --config ./.husky/lint-staged.config.js

View File

@@ -1,4 +1,4 @@
# v0.8.0-rc4
# v0.8.1-rc1
# Base node image
FROM node:20-alpine AS node

View File

@@ -1,5 +1,5 @@
# Dockerfile.multi
# v0.8.0-rc4
# v0.8.1-rc1
# Base for all builds
FROM node:20-alpine AS base-min

View File

@@ -1,4 +1,5 @@
const Anthropic = require('@anthropic-ai/sdk');
const { logger } = require('@librechat/data-schemas');
const { HttpsProxyAgent } = require('https-proxy-agent');
const {
Constants,
@@ -9,7 +10,7 @@ const {
getResponseSender,
validateVisionModel,
} = require('librechat-data-provider');
const { SplitStreamHandler: _Handler } = require('@librechat/agents');
const { sleep, SplitStreamHandler: _Handler } = require('@librechat/agents');
const {
Tokenizer,
createFetch,
@@ -31,9 +32,7 @@ const {
} = require('./prompts');
const { spendTokens, spendStructuredTokens } = require('~/models/spendTokens');
const { encodeAndFormat } = require('~/server/services/Files/images/encode');
const { sleep } = require('~/server/utils');
const BaseClient = require('./BaseClient');
const { logger } = require('~/config');
const HUMAN_PROMPT = '\n\nHuman:';
const AI_PROMPT = '\n\nAssistant:';

View File

@@ -1,20 +1,29 @@
const crypto = require('crypto');
const fetch = require('node-fetch');
const { logger } = require('@librechat/data-schemas');
const { getBalanceConfig } = require('@librechat/api');
const {
supportsBalanceCheck,
isAgentsEndpoint,
isParamEndpoint,
EModelEndpoint,
getBalanceConfig,
extractFileContext,
encodeAndFormatAudios,
encodeAndFormatVideos,
encodeAndFormatDocuments,
} = require('@librechat/api');
const {
Constants,
ErrorTypes,
FileSources,
ContentTypes,
excludedKeys,
ErrorTypes,
Constants,
EModelEndpoint,
isParamEndpoint,
isAgentsEndpoint,
supportsBalanceCheck,
} = require('librechat-data-provider');
const { getMessages, saveMessage, updateMessage, saveConvo, getConvo } = require('~/models');
const { getStrategyFunctions } = require('~/server/services/Files/strategies');
const { checkBalance } = require('~/models/balanceMethods');
const { truncateToolCallOutputs } = require('./prompts');
const countTokens = require('~/server/utils/countTokens');
const { getFiles } = require('~/models/File');
const TextStream = require('./TextStream');
@@ -233,7 +242,6 @@ class BaseClient {
sender: 'User',
text,
isCreatedByUser: true,
targetModel: this.modelOptions?.model ?? this.model,
};
}
@@ -1199,8 +1207,135 @@ class BaseClient {
return await this.sendCompletion(payload, opts);
}
async addDocuments(message, attachments) {
const documentResult = await encodeAndFormatDocuments(
this.options.req,
attachments,
{
provider: this.options.agent?.provider,
useResponsesApi: this.options.agent?.model_parameters?.useResponsesApi,
},
getStrategyFunctions,
);
message.documents =
documentResult.documents && documentResult.documents.length
? documentResult.documents
: undefined;
return documentResult.files;
}
async addVideos(message, attachments) {
const videoResult = await encodeAndFormatVideos(
this.options.req,
attachments,
this.options.agent.provider,
getStrategyFunctions,
);
message.videos =
videoResult.videos && videoResult.videos.length ? videoResult.videos : undefined;
return videoResult.files;
}
async addAudios(message, attachments) {
const audioResult = await encodeAndFormatAudios(
this.options.req,
attachments,
this.options.agent.provider,
getStrategyFunctions,
);
message.audios =
audioResult.audios && audioResult.audios.length ? audioResult.audios : undefined;
return audioResult.files;
}
/**
* Extracts text context from attachments and sets it on the message.
* This handles text that was already extracted from files (OCR, transcriptions, document text, etc.)
* @param {TMessage} message - The message to add context to
* @param {MongoFile[]} attachments - Array of file attachments
* @returns {Promise<void>}
*/
async addFileContextToMessage(message, attachments) {
const fileContext = await extractFileContext({
attachments,
req: this.options?.req,
tokenCountFn: (text) => countTokens(text),
});
if (fileContext) {
message.fileContext = fileContext;
}
}
async processAttachments(message, attachments) {
const categorizedAttachments = {
images: [],
videos: [],
audios: [],
documents: [],
};
const allFiles = [];
for (const file of attachments) {
/** @type {FileSources} */
const source = file.source ?? FileSources.local;
if (source === FileSources.text) {
allFiles.push(file);
continue;
}
if (file.embedded === true || file.metadata?.fileIdentifier != null) {
allFiles.push(file);
continue;
}
if (file.type.startsWith('image/')) {
categorizedAttachments.images.push(file);
} else if (file.type === 'application/pdf') {
categorizedAttachments.documents.push(file);
allFiles.push(file);
} else if (file.type.startsWith('video/')) {
categorizedAttachments.videos.push(file);
allFiles.push(file);
} else if (file.type.startsWith('audio/')) {
categorizedAttachments.audios.push(file);
allFiles.push(file);
}
}
const [imageFiles] = await Promise.all([
categorizedAttachments.images.length > 0
? this.addImageURLs(message, categorizedAttachments.images)
: Promise.resolve([]),
categorizedAttachments.documents.length > 0
? this.addDocuments(message, categorizedAttachments.documents)
: Promise.resolve([]),
categorizedAttachments.videos.length > 0
? this.addVideos(message, categorizedAttachments.videos)
: Promise.resolve([]),
categorizedAttachments.audios.length > 0
? this.addAudios(message, categorizedAttachments.audios)
: Promise.resolve([]),
]);
allFiles.push(...imageFiles);
const seenFileIds = new Set();
const uniqueFiles = [];
for (const file of allFiles) {
if (file.file_id && !seenFileIds.has(file.file_id)) {
seenFileIds.add(file.file_id);
uniqueFiles.push(file);
} else if (!file.file_id) {
uniqueFiles.push(file);
}
}
return uniqueFiles;
}
/**
*
* @param {TMessage[]} _messages
* @returns {Promise<TMessage[]>}
*/
@@ -1249,7 +1384,8 @@ class BaseClient {
{},
);
await this.addImageURLs(message, files, this.visionMode);
await this.addFileContextToMessage(message, files);
await this.processAttachments(message, files);
this.message_file_map[message.messageId] = files;
return message;

View File

@@ -1,4 +1,6 @@
const { google } = require('googleapis');
const { sleep } = require('@librechat/agents');
const { logger } = require('@librechat/data-schemas');
const { getModelMaxTokens } = require('@librechat/api');
const { concat } = require('@langchain/core/utils/stream');
const { ChatVertexAI } = require('@langchain/google-vertexai');
@@ -22,8 +24,6 @@ const {
} = require('librechat-data-provider');
const { encodeAndFormat } = require('~/server/services/Files/images');
const { spendTokens } = require('~/models/spendTokens');
const { sleep } = require('~/server/utils');
const { logger } = require('~/config');
const {
formatMessage,
createContextHandlers,

View File

@@ -2,7 +2,7 @@ const { z } = require('zod');
const axios = require('axios');
const { Ollama } = require('ollama');
const { sleep } = require('@librechat/agents');
const { logAxiosError } = require('@librechat/api');
const { resolveHeaders } = require('@librechat/api');
const { logger } = require('@librechat/data-schemas');
const { Constants } = require('librechat-data-provider');
const { deriveBaseURL } = require('~/utils');
@@ -44,6 +44,7 @@ class OllamaClient {
constructor(options = {}) {
const host = deriveBaseURL(options.baseURL ?? 'http://localhost:11434');
this.streamRate = options.streamRate ?? Constants.DEFAULT_STREAM_RATE;
this.headers = options.headers ?? {};
/** @type {Ollama} */
this.client = new Ollama({ host });
}
@@ -51,27 +52,32 @@ class OllamaClient {
/**
* Fetches Ollama models from the specified base API path.
* @param {string} baseURL
* @param {Object} [options] - Optional configuration
* @param {Partial<IUser>} [options.user] - User object for header resolution
* @param {Record<string, string>} [options.headers] - Headers to include in the request
* @returns {Promise<string[]>} The Ollama models.
* @throws {Error} Throws if the Ollama API request fails
*/
static async fetchModels(baseURL) {
let models = [];
static async fetchModels(baseURL, options = {}) {
if (!baseURL) {
return models;
}
try {
const ollamaEndpoint = deriveBaseURL(baseURL);
/** @type {Promise<AxiosResponse<OllamaListResponse>>} */
const response = await axios.get(`${ollamaEndpoint}/api/tags`, {
timeout: 5000,
});
models = response.data.models.map((tag) => tag.name);
return models;
} catch (error) {
const logMessage =
"Failed to fetch models from Ollama API. If you are not using Ollama directly, and instead, through some aggregator or reverse proxy that handles fetching via OpenAI spec, ensure the name of the endpoint doesn't start with `ollama` (case-insensitive).";
logAxiosError({ message: logMessage, error });
return [];
}
const ollamaEndpoint = deriveBaseURL(baseURL);
const resolvedHeaders = resolveHeaders({
headers: options.headers,
user: options.user,
});
/** @type {Promise<AxiosResponse<OllamaListResponse>>} */
const response = await axios.get(`${ollamaEndpoint}/api/tags`, {
headers: resolvedHeaders,
timeout: 5000,
});
const models = response.data.models.map((tag) => tag.name);
return models;
}
/**

View File

@@ -1,6 +1,6 @@
const { OllamaClient } = require('./OllamaClient');
const { logger } = require('@librechat/data-schemas');
const { HttpsProxyAgent } = require('https-proxy-agent');
const { SplitStreamHandler, CustomOpenAIClient: OpenAI } = require('@librechat/agents');
const { sleep, SplitStreamHandler, CustomOpenAIClient: OpenAI } = require('@librechat/agents');
const {
isEnabled,
Tokenizer,
@@ -34,16 +34,15 @@ const {
createContextHandlers,
} = require('./prompts');
const { encodeAndFormat } = require('~/server/services/Files/images/encode');
const { addSpaceIfNeeded, sleep } = require('~/server/utils');
const { spendTokens } = require('~/models/spendTokens');
const { addSpaceIfNeeded } = require('~/server/utils');
const { handleOpenAIErrors } = require('./tools/util');
const { OllamaClient } = require('./OllamaClient');
const { summaryBuffer } = require('./memory');
const { runTitleChain } = require('./chains');
const { extractBaseURL } = require('~/utils');
const { tokenSplit } = require('./document');
const BaseClient = require('./BaseClient');
const { createLLM } = require('./llm');
const { logger } = require('~/config');
class OpenAIClient extends BaseClient {
constructor(apiKey, options = {}) {
@@ -614,65 +613,8 @@ class OpenAIClient extends BaseClient {
return (reply ?? '').trim();
}
initializeLLM({
model = openAISettings.model.default,
modelName,
temperature = 0.2,
max_tokens,
streaming,
}) {
const modelOptions = {
modelName: modelName ?? model,
temperature,
user: this.user,
};
if (max_tokens) {
modelOptions.max_tokens = max_tokens;
}
const configOptions = {};
if (this.langchainProxy) {
configOptions.basePath = this.langchainProxy;
}
if (this.useOpenRouter) {
configOptions.basePath = 'https://openrouter.ai/api/v1';
configOptions.baseOptions = {
headers: {
'HTTP-Referer': 'https://librechat.ai',
'X-Title': 'LibreChat',
},
};
}
const { headers } = this.options;
if (headers && typeof headers === 'object' && !Array.isArray(headers)) {
configOptions.baseOptions = {
headers: resolveHeaders({
headers: {
...headers,
...configOptions?.baseOptions?.headers,
},
}),
};
}
if (this.options.proxy) {
configOptions.httpAgent = new HttpsProxyAgent(this.options.proxy);
configOptions.httpsAgent = new HttpsProxyAgent(this.options.proxy);
}
const llm = createLLM({
modelOptions,
configOptions,
openAIApiKey: this.apiKey,
azure: this.azure,
streaming,
});
return llm;
initializeLLM() {
throw new Error('Deprecated');
}
/**

View File

@@ -1,5 +1,5 @@
const { Readable } = require('stream');
const { logger } = require('~/config');
const { logger } = require('@librechat/data-schemas');
class TextStream extends Readable {
constructor(text, options = {}) {

View File

@@ -1,5 +1,5 @@
const { logger } = require('@librechat/data-schemas');
const { ZeroShotAgentOutputParser } = require('langchain/agents');
const { logger } = require('~/config');
class CustomOutputParser extends ZeroShotAgentOutputParser {
constructor(fields) {

View File

@@ -1,7 +1,7 @@
const { z } = require('zod');
const { logger } = require('@librechat/data-schemas');
const { langPrompt, createTitlePrompt, escapeBraces, getSnippet } = require('../prompts');
const { createStructuredOutputChainFromZod } = require('langchain/chains/openai_functions');
const { logger } = require('~/config');
const langSchema = z.object({
language: z.string().describe('The language of the input text (full noun, no abbreviations).'),

View File

@@ -1,81 +0,0 @@
const { ChatOpenAI } = require('@langchain/openai');
const { isEnabled, sanitizeModelName, constructAzureURL } = require('@librechat/api');
/**
* 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.
*
* @example
* const llm = createLLM({
* modelOptions: { modelName: 'gpt-4o-mini', temperature: 0.2 },
* configOptions: { basePath: 'https://example.api/path' },
* callbacks: { onMessage: handleMessage },
* openAIApiKey: 'your-api-key'
* });
*/
function createLLM({
modelOptions,
configOptions,
callbacks,
streaming = false,
openAIApiKey,
azure = {},
}) {
let credentials = { openAIApiKey };
let configuration = {
apiKey: openAIApiKey,
...(configOptions.basePath && { baseURL: configOptions.basePath }),
};
/** @type {AzureOptions} */
let azureOptions = {};
if (azure) {
const useModelName = isEnabled(process.env.AZURE_USE_MODEL_AS_DEPLOYMENT_NAME);
credentials = {};
configuration = {};
azureOptions = azure;
azureOptions.azureOpenAIApiDeploymentName = useModelName
? sanitizeModelName(modelOptions.modelName)
: azureOptions.azureOpenAIApiDeploymentName;
}
if (azure && process.env.AZURE_OPENAI_DEFAULT_MODEL) {
modelOptions.modelName = process.env.AZURE_OPENAI_DEFAULT_MODEL;
}
if (azure && configOptions.basePath) {
const azureURL = constructAzureURL({
baseURL: configOptions.basePath,
azureOptions,
});
azureOptions.azureOpenAIBasePath = azureURL.split(
`/${azureOptions.azureOpenAIApiDeploymentName}`,
)[0];
}
return new ChatOpenAI(
{
streaming,
credentials,
configuration,
...azureOptions,
...modelOptions,
...credentials,
callbacks,
},
configOptions,
);
}
module.exports = createLLM;

View File

@@ -1,7 +1,5 @@
const createLLM = require('./createLLM');
const createCoherePayload = require('./createCoherePayload');
module.exports = {
createLLM,
createCoherePayload,
};

View File

@@ -1,31 +0,0 @@
require('dotenv').config();
const { ChatOpenAI } = require('@langchain/openai');
const { getBufferString, ConversationSummaryBufferMemory } = require('langchain/memory');
const chatPromptMemory = new ConversationSummaryBufferMemory({
llm: new ChatOpenAI({ modelName: 'gpt-4o-mini', temperature: 0 }),
maxTokenLimit: 10,
returnMessages: true,
});
(async () => {
await chatPromptMemory.saveContext({ input: 'hi my name\'s Danny' }, { output: 'whats up' });
await chatPromptMemory.saveContext({ input: 'not much you' }, { output: 'not much' });
await chatPromptMemory.saveContext(
{ input: 'are you excited for the olympics?' },
{ output: 'not really' },
);
// We can also utilize the predict_new_summary method directly.
const messages = await chatPromptMemory.chatHistory.getMessages();
console.log('MESSAGES\n\n');
console.log(JSON.stringify(messages));
const previous_summary = '';
const predictSummary = await chatPromptMemory.predictNewSummary(messages, previous_summary);
console.log('SUMMARY\n\n');
console.log(JSON.stringify(getBufferString([{ role: 'system', content: predictSummary }])));
// const { history } = await chatPromptMemory.loadMemoryVariables({});
// console.log('HISTORY\n\n');
// console.log(JSON.stringify(history));
})();

View File

@@ -1,7 +1,7 @@
const { logger } = require('@librechat/data-schemas');
const { ConversationSummaryBufferMemory, ChatMessageHistory } = require('langchain/memory');
const { formatLangChainMessages, SUMMARY_PROMPT } = require('../prompts');
const { predictNewSummary } = require('../chains');
const { logger } = require('~/config');
const createSummaryBufferMemory = ({ llm, prompt, messages, ...rest }) => {
const chatHistory = new ChatMessageHistory(messages);

View File

@@ -1,4 +1,4 @@
const { logger } = require('~/config');
const { logger } = require('@librechat/data-schemas');
/**
* The `addImages` function corrects any erroneous image URLs in the `responseMessage.text`

View File

@@ -3,6 +3,7 @@ const { EModelEndpoint, ArtifactModes } = require('librechat-data-provider');
const { generateShadcnPrompt } = require('~/app/clients/prompts/shadcn-docs/generate');
const { components } = require('~/app/clients/prompts/shadcn-docs/components');
/** @deprecated */
// eslint-disable-next-line no-unused-vars
const artifactsPromptV1 = dedent`The assistant can create and reference artifacts during conversations.
@@ -115,6 +116,7 @@ Here are some examples of correct usage of artifacts:
</assistant_response>
</example>
</examples>`;
const artifactsPrompt = dedent`The assistant can create and reference artifacts during conversations.
Artifacts are for substantial, self-contained content that users might modify or reuse, displayed in a separate UI window for clarity.
@@ -165,6 +167,10 @@ Artifacts are for substantial, self-contained content that users might modify or
- SVG: "image/svg+xml"
- The user interface will render the Scalable Vector Graphics (SVG) image within the artifact tags.
- The assistant should specify the viewbox of the SVG rather than defining a width/height
- Markdown: "text/markdown" or "text/md"
- The user interface will render Markdown content placed within the artifact tags.
- Supports standard Markdown syntax including headers, lists, links, images, code blocks, tables, and more.
- Both "text/markdown" and "text/md" are accepted as valid MIME types for Markdown content.
- Mermaid Diagrams: "application/vnd.mermaid"
- The user interface will render Mermaid diagrams placed within the artifact tags.
- React Components: "application/vnd.react"
@@ -366,6 +372,10 @@ Artifacts are for substantial, self-contained content that users might modify or
- SVG: "image/svg+xml"
- The user interface will render the Scalable Vector Graphics (SVG) image within the artifact tags.
- The assistant should specify the viewbox of the SVG rather than defining a width/height
- Markdown: "text/markdown" or "text/md"
- The user interface will render Markdown content placed within the artifact tags.
- Supports standard Markdown syntax including headers, lists, links, images, code blocks, tables, and more.
- Both "text/markdown" and "text/md" are accepted as valid MIME types for Markdown content.
- Mermaid Diagrams: "application/vnd.mermaid"
- The user interface will render Mermaid diagrams placed within the artifact tags.
- React Components: "application/vnd.react"

View File

@@ -1,7 +1,7 @@
const { z } = require('zod');
const { Tool } = require('@langchain/core/tools');
const { logger } = require('@librechat/data-schemas');
const { SearchClient, AzureKeyCredential } = require('@azure/search-documents');
const { logger } = require('~/config');
class AzureAISearch extends Tool {
// Constants for default values
@@ -18,7 +18,7 @@ class AzureAISearch extends Tool {
super();
this.name = 'azure-ai-search';
this.description =
'Use the \'azure-ai-search\' tool to retrieve search results relevant to your input';
"Use the 'azure-ai-search' tool to retrieve search results relevant to your input";
/* Used to initialize the Tool without necessary variables. */
this.override = fields.override ?? false;

View File

@@ -1,9 +1,8 @@
const { z } = require('zod');
const path = require('path');
const OpenAI = require('openai');
const fetch = require('node-fetch');
const { v4: uuidv4 } = require('uuid');
const { ProxyAgent } = require('undici');
const { ProxyAgent, fetch } = require('undici');
const { Tool } = require('@langchain/core/tools');
const { logger } = require('@librechat/data-schemas');
const { getImageBasename } = require('@librechat/api');

View File

@@ -3,12 +3,12 @@ const axios = require('axios');
const fetch = require('node-fetch');
const { v4: uuidv4 } = require('uuid');
const { Tool } = require('@langchain/core/tools');
const { logger } = require('@librechat/data-schemas');
const { HttpsProxyAgent } = require('https-proxy-agent');
const { FileContext, ContentTypes } = require('librechat-data-provider');
const { logger } = require('~/config');
const displayMessage =
'Flux displayed an image. All generated images are already plainly visible, so don\'t repeat the descriptions in detail. Do not list download links as they are available in the UI already. The user may download the images by clicking on them, but do not mention anything about downloading to the user.';
"Flux displayed an image. All generated images are already plainly visible, so don't repeat the descriptions in detail. Do not list download links as they are available in the UI already. The user may download the images by clicking on them, but do not mention anything about downloading to the user.";
/**
* FluxAPI - A tool for generating high-quality images from text prompts using the Flux API.

View File

@@ -5,6 +5,7 @@ const FormData = require('form-data');
const { ProxyAgent } = require('undici');
const { tool } = require('@langchain/core/tools');
const { logger } = require('@librechat/data-schemas');
const { HttpsProxyAgent } = require('https-proxy-agent');
const { logAxiosError, oaiToolkit } = require('@librechat/api');
const { ContentTypes, EImageOutputType } = require('librechat-data-provider');
const { getStrategyFunctions } = require('~/server/services/Files/strategies');
@@ -348,16 +349,7 @@ Error Message: ${error.message}`);
};
if (process.env.PROXY) {
try {
const url = new URL(process.env.PROXY);
axiosConfig.proxy = {
host: url.hostname.replace(/^\[|\]$/g, ''),
port: url.port ? parseInt(url.port, 10) : undefined,
protocol: url.protocol.replace(':', ''),
};
} catch (error) {
logger.error('Error parsing proxy URL:', error);
}
axiosConfig.httpsAgent = new HttpsProxyAgent(process.env.PROXY);
}
if (process.env.IMAGE_GEN_OAI_AZURE_API_VERSION && process.env.IMAGE_GEN_OAI_BASEURL) {

View File

@@ -6,9 +6,9 @@ const axios = require('axios');
const sharp = require('sharp');
const { v4: uuidv4 } = require('uuid');
const { Tool } = require('@langchain/core/tools');
const { logger } = require('@librechat/data-schemas');
const { FileContext, ContentTypes } = require('librechat-data-provider');
const paths = require('~/config/paths');
const { logger } = require('~/config');
const displayMessage =
"Stable Diffusion displayed an image. All generated images are already plainly visible, so don't repeat the descriptions in detail. Do not list download links as they are available in the UI already. The user may download the images by clicking on them, but do not mention anything about downloading to the user.";

View File

@@ -1,7 +1,7 @@
const { z } = require('zod');
const { Tool } = require('@langchain/core/tools');
const { logger } = require('@librechat/data-schemas');
const { getEnvironmentVariable } = require('@langchain/core/utils/env');
const { logger } = require('~/config');
/**
* Tool for the Traversaal AI search API, Ares.
@@ -21,7 +21,7 @@ class TraversaalSearch extends Tool {
query: z
.string()
.describe(
'A properly written sentence to be interpreted by an AI to search the web according to the user\'s request.',
"A properly written sentence to be interpreted by an AI to search the web according to the user's request.",
),
});
@@ -38,7 +38,6 @@ class TraversaalSearch extends Tool {
return apiKey;
}
// eslint-disable-next-line no-unused-vars
async _call({ query }, _runManager) {
const body = {
query: [query],

View File

@@ -1,8 +1,8 @@
/* eslint-disable no-useless-escape */
const axios = require('axios');
const { z } = require('zod');
const axios = require('axios');
const { Tool } = require('@langchain/core/tools');
const { logger } = require('~/config');
const { logger } = require('@librechat/data-schemas');
class WolframAlphaAPI extends Tool {
constructor(fields) {

View File

@@ -68,19 +68,19 @@ const primeFiles = async (options) => {
/**
*
* @param {Object} options
* @param {ServerRequest} options.req
* @param {string} options.userId
* @param {Array<{ file_id: string; filename: string }>} options.files
* @param {string} [options.entity_id]
* @param {boolean} [options.fileCitations=false] - Whether to include citation instructions
* @returns
*/
const createFileSearchTool = async ({ req, files, entity_id, fileCitations = false }) => {
const createFileSearchTool = async ({ userId, files, entity_id, fileCitations = false }) => {
return tool(
async ({ query }) => {
if (files.length === 0) {
return 'No files to search. Instruct the user to add files for the search.';
}
const jwtToken = generateShortLivedToken(req.user.id);
const jwtToken = generateShortLivedToken(userId);
if (!jwtToken) {
return 'There was an error authenticating the file search request.';
}

View File

@@ -1,5 +1,5 @@
const OpenAI = require('openai');
const { logger } = require('~/config');
const { logger } = require('@librechat/data-schemas');
/**
* Handles errors that may occur when making requests to OpenAI's API.

View File

@@ -1,8 +1,13 @@
const { logger } = require('@librechat/data-schemas');
const { SerpAPI } = require('@langchain/community/tools/serpapi');
const { Calculator } = require('@langchain/community/tools/calculator');
const { mcpToolPattern, loadWebSearchAuth, checkAccess } = require('@librechat/api');
const { EnvVar, createCodeExecutionTool, createSearchTool } = require('@librechat/agents');
const {
checkAccess,
createSafeUser,
mcpToolPattern,
loadWebSearchAuth,
} = require('@librechat/api');
const {
Tools,
Constants,
@@ -33,7 +38,7 @@ const { createFileSearchTool, primeFiles: primeSearchFiles } = require('./fileSe
const { getUserPluginAuthValue } = require('~/server/services/PluginService');
const { createMCPTool, createMCPTools } = require('~/server/services/MCP');
const { loadAuthValues } = require('~/server/services/Tools/credentials');
const { getCachedTools } = require('~/server/services/Config');
const { getMCPServerTools } = require('~/server/services/Config');
const { getRoleByName } = require('~/models/Role');
/**
@@ -250,7 +255,6 @@ const loadTools = async ({
/** @type {Record<string, string>} */
const toolContextMap = {};
const cachedTools = (await getCachedTools({ userId: user, includeGlobal: true })) ?? {};
const requestedMCPTools = {};
for (const tool of tools) {
@@ -307,7 +311,7 @@ const loadTools = async ({
}
return createFileSearchTool({
req: options.req,
userId: user,
files,
entity_id: agent?.id,
fileCitations,
@@ -340,7 +344,7 @@ Current Date & Time: ${replaceSpecialVars({ text: '{{iso_datetime}}' })}
});
};
continue;
} else if (tool && cachedTools && mcpToolPattern.test(tool)) {
} else if (tool && mcpToolPattern.test(tool)) {
const [toolName, serverName] = tool.split(Constants.mcp_delimiter);
if (toolName === Constants.mcp_server) {
/** Placeholder used for UI purposes */
@@ -353,33 +357,21 @@ Current Date & Time: ${replaceSpecialVars({ text: '{{iso_datetime}}' })}
continue;
}
if (toolName === Constants.mcp_all) {
const currentMCPGenerator = async (index) =>
createMCPTools({
req: options.req,
res: options.res,
index,
requestedMCPTools[serverName] = [
{
type: 'all',
serverName,
userMCPAuthMap,
model: agent?.model ?? model,
provider: agent?.provider ?? endpoint,
signal,
});
requestedMCPTools[serverName] = [currentMCPGenerator];
},
];
continue;
}
const currentMCPGenerator = async (index) =>
createMCPTool({
index,
req: options.req,
res: options.res,
toolKey: tool,
userMCPAuthMap,
model: agent?.model ?? model,
provider: agent?.provider ?? endpoint,
signal,
});
requestedMCPTools[serverName] = requestedMCPTools[serverName] || [];
requestedMCPTools[serverName].push(currentMCPGenerator);
requestedMCPTools[serverName].push({
type: 'single',
toolKey: tool,
serverName,
});
continue;
}
@@ -422,24 +414,65 @@ Current Date & Time: ${replaceSpecialVars({ text: '{{iso_datetime}}' })}
const mcpToolPromises = [];
/** MCP server tools are initialized sequentially by server */
let index = -1;
for (const [serverName, generators] of Object.entries(requestedMCPTools)) {
const failedMCPServers = new Set();
const safeUser = createSafeUser(options.req?.user);
for (const [serverName, toolConfigs] of Object.entries(requestedMCPTools)) {
index++;
for (const generator of generators) {
/** @type {LCAvailableTools} */
let availableTools;
for (const config of toolConfigs) {
try {
if (generator && generators.length === 1) {
if (failedMCPServers.has(serverName)) {
continue;
}
const mcpParams = {
index,
signal,
user: safeUser,
userMCPAuthMap,
res: options.res,
model: agent?.model ?? model,
serverName: config.serverName,
provider: agent?.provider ?? endpoint,
};
if (config.type === 'all' && toolConfigs.length === 1) {
/** Handle async loading for single 'all' tool config */
mcpToolPromises.push(
generator(index).catch((error) => {
createMCPTools(mcpParams).catch((error) => {
logger.error(`Error loading ${serverName} tools:`, error);
return null;
}),
);
continue;
}
const mcpTool = await generator(index);
if (!availableTools) {
try {
availableTools = await getMCPServerTools(serverName);
} catch (error) {
logger.error(`Error fetching available tools for MCP server ${serverName}:`, error);
}
}
/** Handle synchronous loading */
const mcpTool =
config.type === 'all'
? await createMCPTools(mcpParams)
: await createMCPTool({
...mcpParams,
availableTools,
toolKey: config.toolKey,
});
if (Array.isArray(mcpTool)) {
loadedTools.push(...mcpTool);
} else if (mcpTool) {
loadedTools.push(mcpTool);
} else {
failedMCPServers.add(serverName);
logger.warn(
`MCP tool creation failed for "${config.toolKey}", server may be unavailable or unauthenticated.`,
);
}
} catch (error) {
logger.error(`Error loading MCP tool for server ${serverName}:`, error);

View File

@@ -30,7 +30,6 @@ jest.mock('~/server/services/Config', () => ({
}),
}));
const { BaseLLM } = require('@langchain/openai');
const { Calculator } = require('@langchain/community/tools/calculator');
const { User } = require('~/db/models');
@@ -172,7 +171,6 @@ describe('Tool Handlers', () => {
beforeAll(async () => {
const toolMap = await loadTools({
user: fakeUser._id,
model: BaseLLM,
tools: sampleTools,
returnMap: true,
useSpecs: true,
@@ -266,7 +264,6 @@ describe('Tool Handlers', () => {
it('returns an empty object when no tools are requested', async () => {
toolFunctions = await loadTools({
user: fakeUser._id,
model: BaseLLM,
returnMap: true,
useSpecs: true,
});
@@ -276,7 +273,6 @@ describe('Tool Handlers', () => {
process.env.SD_WEBUI_URL = mockCredential;
toolFunctions = await loadTools({
user: fakeUser._id,
model: BaseLLM,
tools: ['stable-diffusion'],
functions: true,
returnMap: true,

View File

@@ -1,108 +0,0 @@
const KeyvRedis = require('@keyv/redis').default;
const { Keyv } = require('keyv');
const { RedisStore } = require('rate-limit-redis');
const { Time } = require('librechat-data-provider');
const { logger } = require('@librechat/data-schemas');
const { RedisStore: ConnectRedis } = require('connect-redis');
const MemoryStore = require('memorystore')(require('express-session'));
const { keyvRedisClient, ioredisClient, GLOBAL_PREFIX_SEPARATOR } = require('./redisClients');
const { cacheConfig } = require('./cacheConfig');
const { violationFile } = require('./keyvFiles');
/**
* Creates a cache instance using Redis or a fallback store. Suitable for general caching needs.
* @param {string} namespace - The cache namespace.
* @param {number} [ttl] - Time to live for cache entries.
* @param {object} [fallbackStore] - Optional fallback store if Redis is not used.
* @returns {Keyv} Cache instance.
*/
const standardCache = (namespace, ttl = undefined, fallbackStore = undefined) => {
if (
cacheConfig.USE_REDIS &&
!cacheConfig.FORCED_IN_MEMORY_CACHE_NAMESPACES?.includes(namespace)
) {
try {
const keyvRedis = new KeyvRedis(keyvRedisClient);
const cache = new Keyv(keyvRedis, { namespace, ttl });
keyvRedis.namespace = cacheConfig.REDIS_KEY_PREFIX;
keyvRedis.keyPrefixSeparator = GLOBAL_PREFIX_SEPARATOR;
cache.on('error', (err) => {
logger.error(`Cache error in namespace ${namespace}:`, err);
});
return cache;
} catch (err) {
logger.error(`Failed to create Redis cache for namespace ${namespace}:`, err);
throw err;
}
}
if (fallbackStore) return new Keyv({ store: fallbackStore, namespace, ttl });
return new Keyv({ namespace, ttl });
};
/**
* Creates a cache instance for storing violation data.
* Uses a file-based fallback store if Redis is not enabled.
* @param {string} namespace - The cache namespace for violations.
* @param {number} [ttl] - Time to live for cache entries.
* @returns {Keyv} Cache instance for violations.
*/
const violationCache = (namespace, ttl = undefined) => {
return standardCache(`violations:${namespace}`, ttl, violationFile);
};
/**
* Creates a session cache instance using Redis or in-memory store.
* @param {string} namespace - The session namespace.
* @param {number} [ttl] - Time to live for session entries.
* @returns {MemoryStore | ConnectRedis} Session store instance.
*/
const sessionCache = (namespace, ttl = undefined) => {
namespace = namespace.endsWith(':') ? namespace : `${namespace}:`;
if (!cacheConfig.USE_REDIS) return new MemoryStore({ ttl, checkPeriod: Time.ONE_DAY });
const store = new ConnectRedis({ client: ioredisClient, ttl, prefix: namespace });
if (ioredisClient) {
ioredisClient.on('error', (err) => {
logger.error(`Session store Redis error for namespace ${namespace}:`, err);
});
}
return store;
};
/**
* Creates a rate limiter cache using Redis.
* @param {string} prefix - The key prefix for rate limiting.
* @returns {RedisStore|undefined} RedisStore instance or undefined if Redis is not used.
*/
const limiterCache = (prefix) => {
if (!prefix) throw new Error('prefix is required');
if (!cacheConfig.USE_REDIS) return undefined;
prefix = prefix.endsWith(':') ? prefix : `${prefix}:`;
try {
if (!ioredisClient) {
logger.warn(`Redis client not available for rate limiter with prefix ${prefix}`);
return undefined;
}
return new RedisStore({ sendCommand, prefix });
} catch (err) {
logger.error(`Failed to create Redis rate limiter for prefix ${prefix}:`, err);
return undefined;
}
};
const sendCommand = (...args) => {
if (!ioredisClient) {
logger.warn('Redis client not available for command execution');
return Promise.reject(new Error('Redis client not available'));
}
return ioredisClient.call(...args).catch((err) => {
logger.error('Redis command execution failed:', err);
throw err;
});
};
module.exports = { standardCache, sessionCache, violationCache, limiterCache };

View File

@@ -1,432 +0,0 @@
const { Time } = require('librechat-data-provider');
// Mock dependencies first
const mockKeyvRedis = {
namespace: '',
keyPrefixSeparator: '',
};
const mockKeyv = jest.fn().mockReturnValue({
mock: 'keyv',
on: jest.fn(),
});
const mockConnectRedis = jest.fn().mockReturnValue({ mock: 'connectRedis' });
const mockMemoryStore = jest.fn().mockReturnValue({ mock: 'memoryStore' });
const mockRedisStore = jest.fn().mockReturnValue({ mock: 'redisStore' });
const mockIoredisClient = {
call: jest.fn(),
on: jest.fn(),
};
const mockKeyvRedisClient = {};
const mockViolationFile = {};
// Mock modules before requiring the main module
jest.mock('@keyv/redis', () => ({
default: jest.fn().mockImplementation(() => mockKeyvRedis),
}));
jest.mock('keyv', () => ({
Keyv: mockKeyv,
}));
jest.mock('./cacheConfig', () => ({
cacheConfig: {
USE_REDIS: false,
REDIS_KEY_PREFIX: 'test',
FORCED_IN_MEMORY_CACHE_NAMESPACES: [],
},
}));
jest.mock('./redisClients', () => ({
keyvRedisClient: mockKeyvRedisClient,
ioredisClient: mockIoredisClient,
GLOBAL_PREFIX_SEPARATOR: '::',
}));
jest.mock('./keyvFiles', () => ({
violationFile: mockViolationFile,
}));
jest.mock('connect-redis', () => ({ RedisStore: mockConnectRedis }));
jest.mock('memorystore', () => jest.fn(() => mockMemoryStore));
jest.mock('rate-limit-redis', () => ({
RedisStore: mockRedisStore,
}));
jest.mock('@librechat/data-schemas', () => ({
logger: {
error: jest.fn(),
warn: jest.fn(),
info: jest.fn(),
},
}));
// Import after mocking
const { standardCache, sessionCache, violationCache, limiterCache } = require('./cacheFactory');
const { cacheConfig } = require('./cacheConfig');
describe('cacheFactory', () => {
beforeEach(() => {
jest.clearAllMocks();
// Reset cache config mock
cacheConfig.USE_REDIS = false;
cacheConfig.REDIS_KEY_PREFIX = 'test';
cacheConfig.FORCED_IN_MEMORY_CACHE_NAMESPACES = [];
});
describe('redisCache', () => {
it('should create Redis cache when USE_REDIS is true', () => {
cacheConfig.USE_REDIS = true;
const namespace = 'test-namespace';
const ttl = 3600;
standardCache(namespace, ttl);
expect(require('@keyv/redis').default).toHaveBeenCalledWith(mockKeyvRedisClient);
expect(mockKeyv).toHaveBeenCalledWith(mockKeyvRedis, { namespace, ttl });
expect(mockKeyvRedis.namespace).toBe(cacheConfig.REDIS_KEY_PREFIX);
expect(mockKeyvRedis.keyPrefixSeparator).toBe('::');
});
it('should create Redis cache with undefined ttl when not provided', () => {
cacheConfig.USE_REDIS = true;
const namespace = 'test-namespace';
standardCache(namespace);
expect(mockKeyv).toHaveBeenCalledWith(mockKeyvRedis, { namespace, ttl: undefined });
});
it('should use fallback store when USE_REDIS is false and fallbackStore is provided', () => {
cacheConfig.USE_REDIS = false;
const namespace = 'test-namespace';
const ttl = 3600;
const fallbackStore = { some: 'store' };
standardCache(namespace, ttl, fallbackStore);
expect(mockKeyv).toHaveBeenCalledWith({ store: fallbackStore, namespace, ttl });
});
it('should create default Keyv instance when USE_REDIS is false and no fallbackStore', () => {
cacheConfig.USE_REDIS = false;
const namespace = 'test-namespace';
const ttl = 3600;
standardCache(namespace, ttl);
expect(mockKeyv).toHaveBeenCalledWith({ namespace, ttl });
});
it('should handle namespace and ttl as undefined', () => {
cacheConfig.USE_REDIS = false;
standardCache();
expect(mockKeyv).toHaveBeenCalledWith({ namespace: undefined, ttl: undefined });
});
it('should use fallback when namespace is in FORCED_IN_MEMORY_CACHE_NAMESPACES', () => {
cacheConfig.USE_REDIS = true;
cacheConfig.FORCED_IN_MEMORY_CACHE_NAMESPACES = ['forced-memory'];
const namespace = 'forced-memory';
const ttl = 3600;
standardCache(namespace, ttl);
expect(require('@keyv/redis').default).not.toHaveBeenCalled();
expect(mockKeyv).toHaveBeenCalledWith({ namespace, ttl });
});
it('should use Redis when namespace is not in FORCED_IN_MEMORY_CACHE_NAMESPACES', () => {
cacheConfig.USE_REDIS = true;
cacheConfig.FORCED_IN_MEMORY_CACHE_NAMESPACES = ['other-namespace'];
const namespace = 'test-namespace';
const ttl = 3600;
standardCache(namespace, ttl);
expect(require('@keyv/redis').default).toHaveBeenCalledWith(mockKeyvRedisClient);
expect(mockKeyv).toHaveBeenCalledWith(mockKeyvRedis, { namespace, ttl });
});
it('should throw error when Redis cache creation fails', () => {
cacheConfig.USE_REDIS = true;
const namespace = 'test-namespace';
const ttl = 3600;
const testError = new Error('Redis connection failed');
const KeyvRedis = require('@keyv/redis').default;
KeyvRedis.mockImplementationOnce(() => {
throw testError;
});
expect(() => standardCache(namespace, ttl)).toThrow('Redis connection failed');
const { logger } = require('@librechat/data-schemas');
expect(logger.error).toHaveBeenCalledWith(
`Failed to create Redis cache for namespace ${namespace}:`,
testError,
);
expect(mockKeyv).not.toHaveBeenCalled();
});
});
describe('violationCache', () => {
it('should create violation cache with prefixed namespace', () => {
const namespace = 'test-violations';
const ttl = 7200;
// We can't easily mock the internal redisCache call since it's in the same module
// But we can test that the function executes without throwing
expect(() => violationCache(namespace, ttl)).not.toThrow();
});
it('should create violation cache with undefined ttl', () => {
const namespace = 'test-violations';
violationCache(namespace);
// The function should call redisCache with violations: prefixed namespace
// Since we can't easily mock the internal redisCache call, we test the behavior
expect(() => violationCache(namespace)).not.toThrow();
});
it('should handle undefined namespace', () => {
expect(() => violationCache(undefined)).not.toThrow();
});
});
describe('sessionCache', () => {
it('should return MemoryStore when USE_REDIS is false', () => {
cacheConfig.USE_REDIS = false;
const namespace = 'sessions';
const ttl = 86400;
const result = sessionCache(namespace, ttl);
expect(mockMemoryStore).toHaveBeenCalledWith({ ttl, checkPeriod: Time.ONE_DAY });
expect(result).toBe(mockMemoryStore());
});
it('should return ConnectRedis when USE_REDIS is true', () => {
cacheConfig.USE_REDIS = true;
const namespace = 'sessions';
const ttl = 86400;
const result = sessionCache(namespace, ttl);
expect(mockConnectRedis).toHaveBeenCalledWith({
client: mockIoredisClient,
ttl,
prefix: `${namespace}:`,
});
expect(result).toBe(mockConnectRedis());
});
it('should add colon to namespace if not present', () => {
cacheConfig.USE_REDIS = true;
const namespace = 'sessions';
sessionCache(namespace);
expect(mockConnectRedis).toHaveBeenCalledWith({
client: mockIoredisClient,
ttl: undefined,
prefix: 'sessions:',
});
});
it('should not add colon to namespace if already present', () => {
cacheConfig.USE_REDIS = true;
const namespace = 'sessions:';
sessionCache(namespace);
expect(mockConnectRedis).toHaveBeenCalledWith({
client: mockIoredisClient,
ttl: undefined,
prefix: 'sessions:',
});
});
it('should handle undefined ttl', () => {
cacheConfig.USE_REDIS = false;
const namespace = 'sessions';
sessionCache(namespace);
expect(mockMemoryStore).toHaveBeenCalledWith({
ttl: undefined,
checkPeriod: Time.ONE_DAY,
});
});
it('should throw error when ConnectRedis constructor fails', () => {
cacheConfig.USE_REDIS = true;
const namespace = 'sessions';
const ttl = 86400;
// Mock ConnectRedis to throw an error during construction
const redisError = new Error('Redis connection failed');
mockConnectRedis.mockImplementationOnce(() => {
throw redisError;
});
// The error should propagate up, not be caught
expect(() => sessionCache(namespace, ttl)).toThrow('Redis connection failed');
// Verify that MemoryStore was NOT used as fallback
expect(mockMemoryStore).not.toHaveBeenCalled();
});
it('should register error handler but let errors propagate to Express', () => {
cacheConfig.USE_REDIS = true;
const namespace = 'sessions';
// Create a mock session store with middleware methods
const mockSessionStore = {
get: jest.fn(),
set: jest.fn(),
destroy: jest.fn(),
};
mockConnectRedis.mockReturnValue(mockSessionStore);
const store = sessionCache(namespace);
// Verify error handler was registered
expect(mockIoredisClient.on).toHaveBeenCalledWith('error', expect.any(Function));
// Get the error handler
const errorHandler = mockIoredisClient.on.mock.calls.find((call) => call[0] === 'error')[1];
// Simulate an error from Redis during a session operation
const redisError = new Error('Socket closed unexpectedly');
// The error handler should log but not swallow the error
const { logger } = require('@librechat/data-schemas');
errorHandler(redisError);
expect(logger.error).toHaveBeenCalledWith(
`Session store Redis error for namespace ${namespace}::`,
redisError,
);
// Now simulate what happens when session middleware tries to use the store
const callback = jest.fn();
mockSessionStore.get.mockImplementation((sid, cb) => {
cb(new Error('Redis connection lost'));
});
// Call the store's get method (as Express session would)
store.get('test-session-id', callback);
// The error should be passed to the callback, not swallowed
expect(callback).toHaveBeenCalledWith(new Error('Redis connection lost'));
});
it('should handle null ioredisClient gracefully', () => {
cacheConfig.USE_REDIS = true;
const namespace = 'sessions';
// Temporarily set ioredisClient to null (simulating connection not established)
const originalClient = require('./redisClients').ioredisClient;
require('./redisClients').ioredisClient = null;
// ConnectRedis might accept null client but would fail on first use
// The important thing is it doesn't throw uncaught exceptions during construction
const store = sessionCache(namespace);
expect(store).toBeDefined();
// Restore original client
require('./redisClients').ioredisClient = originalClient;
});
});
describe('limiterCache', () => {
it('should return undefined when USE_REDIS is false', () => {
cacheConfig.USE_REDIS = false;
const result = limiterCache('prefix');
expect(result).toBeUndefined();
});
it('should return RedisStore when USE_REDIS is true', () => {
cacheConfig.USE_REDIS = true;
const result = limiterCache('rate-limit');
expect(mockRedisStore).toHaveBeenCalledWith({
sendCommand: expect.any(Function),
prefix: `rate-limit:`,
});
expect(result).toBe(mockRedisStore());
});
it('should add colon to prefix if not present', () => {
cacheConfig.USE_REDIS = true;
limiterCache('rate-limit');
expect(mockRedisStore).toHaveBeenCalledWith({
sendCommand: expect.any(Function),
prefix: 'rate-limit:',
});
});
it('should not add colon to prefix if already present', () => {
cacheConfig.USE_REDIS = true;
limiterCache('rate-limit:');
expect(mockRedisStore).toHaveBeenCalledWith({
sendCommand: expect.any(Function),
prefix: 'rate-limit:',
});
});
it('should pass sendCommand function that calls ioredisClient.call', async () => {
cacheConfig.USE_REDIS = true;
mockIoredisClient.call.mockResolvedValue('test-value');
limiterCache('rate-limit');
const sendCommandCall = mockRedisStore.mock.calls[0][0];
const sendCommand = sendCommandCall.sendCommand;
// Test that sendCommand properly delegates to ioredisClient.call
const args = ['GET', 'test-key'];
const result = await sendCommand(...args);
expect(mockIoredisClient.call).toHaveBeenCalledWith(...args);
expect(result).toBe('test-value');
});
it('should handle sendCommand errors properly', async () => {
cacheConfig.USE_REDIS = true;
// Mock the call method to reject with an error
const testError = new Error('Redis error');
mockIoredisClient.call.mockRejectedValue(testError);
limiterCache('rate-limit');
const sendCommandCall = mockRedisStore.mock.calls[0][0];
const sendCommand = sendCommandCall.sendCommand;
// Test that sendCommand properly handles errors
const args = ['GET', 'test-key'];
await expect(sendCommand(...args)).rejects.toThrow('Redis error');
expect(mockIoredisClient.call).toHaveBeenCalledWith(...args);
});
it('should handle undefined prefix', () => {
cacheConfig.USE_REDIS = true;
expect(() => limiterCache()).toThrow('prefix is required');
});
});
});

View File

@@ -1,5 +1,5 @@
const { isEnabled } = require('@librechat/api');
const { Time, CacheKeys } = require('librechat-data-provider');
const { isEnabled } = require('~/server/utils');
const getLogStores = require('./getLogStores');
const { USE_REDIS, LIMIT_CONCURRENT_MESSAGES } = process.env ?? {};

View File

@@ -1,9 +1,13 @@
const { cacheConfig } = require('./cacheConfig');
const { Keyv } = require('keyv');
const { CacheKeys, ViolationTypes, Time } = require('librechat-data-provider');
const { logFile } = require('./keyvFiles');
const keyvMongo = require('./keyvMongo');
const { standardCache, sessionCache, violationCache } = require('./cacheFactory');
const { Time, CacheKeys, ViolationTypes } = require('librechat-data-provider');
const {
logFile,
keyvMongo,
cacheConfig,
sessionCache,
standardCache,
violationCache,
} = require('@librechat/api');
const namespaces = {
[ViolationTypes.GENERAL]: new Keyv({ store: logFile, namespace: 'violations' }),

3
api/cache/index.js vendored
View File

@@ -1,5 +1,4 @@
const keyvFiles = require('./keyvFiles');
const getLogStores = require('./getLogStores');
const logViolation = require('./logViolation');
module.exports = { ...keyvFiles, getLogStores, logViolation };
module.exports = { getLogStores, logViolation };

View File

@@ -1,9 +0,0 @@
const { KeyvFile } = require('keyv-file');
const logFile = new KeyvFile({ filename: './data/logs.json' }).setMaxListeners(20);
const violationFile = new KeyvFile({ filename: './data/violations.json' }).setMaxListeners(20);
module.exports = {
logFile,
violationFile,
};

View File

@@ -1,4 +1,4 @@
const { isEnabled } = require('~/server/utils');
const { isEnabled } = require('@librechat/api');
const { ViolationTypes } = require('librechat-data-provider');
const getLogStores = require('./getLogStores');
const banViolation = require('./banViolation');

View File

@@ -1,6 +1,6 @@
const { MCPManager, FlowStateManager } = require('@librechat/api');
const { EventSource } = require('eventsource');
const { Time } = require('librechat-data-provider');
const { MCPManager, FlowStateManager, OAuthReconnectionManager } = require('@librechat/api');
const logger = require('./winston');
global.EventSource = EventSource;
@@ -26,4 +26,6 @@ module.exports = {
createMCPManager: MCPManager.createInstance,
getMCPManager: MCPManager.getInstance,
getFlowStateManager,
createOAuthReconnectionManager: OAuthReconnectionManager.createInstance,
getOAuthReconnectionManager: OAuthReconnectionManager.getInstance,
};

View File

@@ -1,10 +1,8 @@
const mongoose = require('mongoose');
const { MeiliSearch } = require('meilisearch');
const { logger } = require('@librechat/data-schemas');
const { FlowStateManager } = require('@librechat/api');
const { CacheKeys } = require('librechat-data-provider');
const { isEnabled } = require('~/server/utils');
const { isEnabled, FlowStateManager } = require('@librechat/api');
const { getLogStores } = require('~/cache');
const Conversation = mongoose.models.Conversation;
@@ -32,78 +30,264 @@ class MeiliSearchClient {
}
/**
* Performs the actual sync operations for messages and conversations
* Deletes documents from MeiliSearch index that are missing the user field
* @param {import('meilisearch').Index} index - MeiliSearch index instance
* @param {string} indexName - Name of the index for logging
* @returns {Promise<number>} - Number of documents deleted
*/
async function performSync() {
const client = MeiliSearchClient.getInstance();
async function deleteDocumentsWithoutUserField(index, indexName) {
let deletedCount = 0;
let offset = 0;
const batchSize = 1000;
const { status } = await client.health();
if (status !== 'available') {
throw new Error('Meilisearch not available');
}
try {
while (true) {
const searchResult = await index.search('', {
limit: batchSize,
offset: offset,
});
if (indexingDisabled === true) {
logger.info('[indexSync] Indexing is disabled, skipping...');
return { messagesSync: false, convosSync: false };
}
if (searchResult.hits.length === 0) {
break;
}
let messagesSync = false;
let convosSync = false;
const idsToDelete = searchResult.hits.filter((hit) => !hit.user).map((hit) => hit.id);
// Check if we need to sync messages
const messageProgress = await Message.getSyncProgress();
if (!messageProgress.isComplete) {
logger.info(
`[indexSync] Messages need syncing: ${messageProgress.totalProcessed}/${messageProgress.totalDocuments} indexed`,
);
if (idsToDelete.length > 0) {
logger.info(
`[indexSync] Deleting ${idsToDelete.length} documents without user field from ${indexName} index`,
);
await index.deleteDocuments(idsToDelete);
deletedCount += idsToDelete.length;
}
// Check if we should do a full sync or incremental
const messageCount = await Message.countDocuments();
const messagesIndexed = messageProgress.totalProcessed;
const syncThreshold = parseInt(process.env.MEILI_SYNC_THRESHOLD || '1000', 10);
if (searchResult.hits.length < batchSize) {
break;
}
if (messageCount - messagesIndexed > syncThreshold) {
logger.info('[indexSync] Starting full message sync due to large difference');
await Message.syncWithMeili();
messagesSync = true;
} else if (messageCount !== messagesIndexed) {
logger.warn('[indexSync] Messages out of sync, performing incremental sync');
await Message.syncWithMeili();
messagesSync = true;
offset += batchSize;
}
} else {
logger.info(
`[indexSync] Messages are fully synced: ${messageProgress.totalProcessed}/${messageProgress.totalDocuments}`,
);
}
// Check if we need to sync conversations
const convoProgress = await Conversation.getSyncProgress();
if (!convoProgress.isComplete) {
logger.info(
`[indexSync] Conversations need syncing: ${convoProgress.totalProcessed}/${convoProgress.totalDocuments} indexed`,
);
const convoCount = await Conversation.countDocuments();
const convosIndexed = convoProgress.totalProcessed;
const syncThreshold = parseInt(process.env.MEILI_SYNC_THRESHOLD || '1000', 10);
if (convoCount - convosIndexed > syncThreshold) {
logger.info('[indexSync] Starting full conversation sync due to large difference');
await Conversation.syncWithMeili();
convosSync = true;
} else if (convoCount !== convosIndexed) {
logger.warn('[indexSync] Convos out of sync, performing incremental sync');
await Conversation.syncWithMeili();
convosSync = true;
if (deletedCount > 0) {
logger.info(`[indexSync] Deleted ${deletedCount} orphaned documents from ${indexName} index`);
}
} else {
logger.info(
`[indexSync] Conversations are fully synced: ${convoProgress.totalProcessed}/${convoProgress.totalDocuments}`,
);
} catch (error) {
logger.error(`[indexSync] Error deleting documents from ${indexName}:`, error);
}
return { messagesSync, convosSync };
return deletedCount;
}
/**
* Ensures indexes have proper filterable attributes configured and checks if documents have user field
* @param {MeiliSearch} client - MeiliSearch client instance
* @returns {Promise<{settingsUpdated: boolean, orphanedDocsFound: boolean}>} - Status of what was done
*/
async function ensureFilterableAttributes(client) {
let settingsUpdated = false;
let hasOrphanedDocs = false;
try {
// Check and update messages index
try {
const messagesIndex = client.index('messages');
const settings = await messagesIndex.getSettings();
if (!settings.filterableAttributes || !settings.filterableAttributes.includes('user')) {
logger.info('[indexSync] Configuring messages index to filter by user...');
await messagesIndex.updateSettings({
filterableAttributes: ['user'],
});
logger.info('[indexSync] Messages index configured for user filtering');
settingsUpdated = true;
}
// Check if existing documents have user field indexed
try {
const searchResult = await messagesIndex.search('', { limit: 1 });
if (searchResult.hits.length > 0 && !searchResult.hits[0].user) {
logger.info(
'[indexSync] Existing messages missing user field, will clean up orphaned documents...',
);
hasOrphanedDocs = true;
}
} catch (searchError) {
logger.debug('[indexSync] Could not check message documents:', searchError.message);
}
} catch (error) {
if (error.code !== 'index_not_found') {
logger.warn('[indexSync] Could not check/update messages index settings:', error.message);
}
}
// Check and update conversations index
try {
const convosIndex = client.index('convos');
const settings = await convosIndex.getSettings();
if (!settings.filterableAttributes || !settings.filterableAttributes.includes('user')) {
logger.info('[indexSync] Configuring convos index to filter by user...');
await convosIndex.updateSettings({
filterableAttributes: ['user'],
});
logger.info('[indexSync] Convos index configured for user filtering');
settingsUpdated = true;
}
// Check if existing documents have user field indexed
try {
const searchResult = await convosIndex.search('', { limit: 1 });
if (searchResult.hits.length > 0 && !searchResult.hits[0].user) {
logger.info(
'[indexSync] Existing conversations missing user field, will clean up orphaned documents...',
);
hasOrphanedDocs = true;
}
} catch (searchError) {
logger.debug('[indexSync] Could not check conversation documents:', searchError.message);
}
} catch (error) {
if (error.code !== 'index_not_found') {
logger.warn('[indexSync] Could not check/update convos index settings:', error.message);
}
}
// If either index has orphaned documents, clean them up (but don't force resync)
if (hasOrphanedDocs) {
try {
const messagesIndex = client.index('messages');
await deleteDocumentsWithoutUserField(messagesIndex, 'messages');
} catch (error) {
logger.debug('[indexSync] Could not clean up messages:', error.message);
}
try {
const convosIndex = client.index('convos');
await deleteDocumentsWithoutUserField(convosIndex, 'convos');
} catch (error) {
logger.debug('[indexSync] Could not clean up convos:', error.message);
}
logger.info('[indexSync] Orphaned documents cleaned up without forcing resync.');
}
if (settingsUpdated) {
logger.info('[indexSync] Index settings updated. Full re-sync will be triggered.');
}
} catch (error) {
logger.error('[indexSync] Error ensuring filterable attributes:', error);
}
return { settingsUpdated, orphanedDocsFound: hasOrphanedDocs };
}
/**
* Performs the actual sync operations for messages and conversations
* @param {FlowStateManager} flowManager - Flow state manager instance
* @param {string} flowId - Flow identifier
* @param {string} flowType - Flow type
*/
async function performSync(flowManager, flowId, flowType) {
try {
const client = MeiliSearchClient.getInstance();
const { status } = await client.health();
if (status !== 'available') {
throw new Error('Meilisearch not available');
}
if (indexingDisabled === true) {
logger.info('[indexSync] Indexing is disabled, skipping...');
return { messagesSync: false, convosSync: false };
}
/** Ensures indexes have proper filterable attributes configured */
const { settingsUpdated, orphanedDocsFound: _orphanedDocsFound } =
await ensureFilterableAttributes(client);
let messagesSync = false;
let convosSync = false;
// Only reset flags if settings were actually updated (not just for orphaned doc cleanup)
if (settingsUpdated) {
logger.info(
'[indexSync] Settings updated. Forcing full re-sync to reindex with new configuration...',
);
// Reset sync flags to force full re-sync
await Message.collection.updateMany({ _meiliIndex: true }, { $set: { _meiliIndex: false } });
await Conversation.collection.updateMany(
{ _meiliIndex: true },
{ $set: { _meiliIndex: false } },
);
}
// Check if we need to sync messages
const messageProgress = await Message.getSyncProgress();
if (!messageProgress.isComplete || settingsUpdated) {
logger.info(
`[indexSync] Messages need syncing: ${messageProgress.totalProcessed}/${messageProgress.totalDocuments} indexed`,
);
// Check if we should do a full sync or incremental
const messageCount = await Message.countDocuments();
const messagesIndexed = messageProgress.totalProcessed;
const syncThreshold = parseInt(process.env.MEILI_SYNC_THRESHOLD || '1000', 10);
if (messageCount - messagesIndexed > syncThreshold) {
logger.info('[indexSync] Starting full message sync due to large difference');
await Message.syncWithMeili();
messagesSync = true;
} else if (messageCount !== messagesIndexed) {
logger.warn('[indexSync] Messages out of sync, performing incremental sync');
await Message.syncWithMeili();
messagesSync = true;
}
} else {
logger.info(
`[indexSync] Messages are fully synced: ${messageProgress.totalProcessed}/${messageProgress.totalDocuments}`,
);
}
// Check if we need to sync conversations
const convoProgress = await Conversation.getSyncProgress();
if (!convoProgress.isComplete || settingsUpdated) {
logger.info(
`[indexSync] Conversations need syncing: ${convoProgress.totalProcessed}/${convoProgress.totalDocuments} indexed`,
);
const convoCount = await Conversation.countDocuments();
const convosIndexed = convoProgress.totalProcessed;
const syncThreshold = parseInt(process.env.MEILI_SYNC_THRESHOLD || '1000', 10);
if (convoCount - convosIndexed > syncThreshold) {
logger.info('[indexSync] Starting full conversation sync due to large difference');
await Conversation.syncWithMeili();
convosSync = true;
} else if (convoCount !== convosIndexed) {
logger.warn('[indexSync] Convos out of sync, performing incremental sync');
await Conversation.syncWithMeili();
convosSync = true;
}
} else {
logger.info(
`[indexSync] Conversations are fully synced: ${convoProgress.totalProcessed}/${convoProgress.totalDocuments}`,
);
}
return { messagesSync, convosSync };
} finally {
if (indexingDisabled === true) {
logger.info('[indexSync] Indexing is disabled, skipping cleanup...');
} else if (flowManager && flowId && flowType) {
try {
await flowManager.deleteFlow(flowId, flowType);
logger.debug('[indexSync] Flow state cleaned up');
} catch (cleanupErr) {
logger.debug('[indexSync] Could not clean up flow state:', cleanupErr.message);
}
}
}
}
/**
@@ -116,24 +300,26 @@ async function indexSync() {
logger.info('[indexSync] Starting index synchronization check...');
// Get or create FlowStateManager instance
const flowsCache = getLogStores(CacheKeys.FLOWS);
if (!flowsCache) {
logger.warn('[indexSync] Flows cache not available, falling back to direct sync');
return await performSync(null, null, null);
}
const flowManager = new FlowStateManager(flowsCache, {
ttl: 60000 * 10, // 10 minutes TTL for sync operations
});
// Use a unique flow ID for the sync operation
const flowId = 'meili-index-sync';
const flowType = 'MEILI_SYNC';
try {
// Get or create FlowStateManager instance
const flowsCache = getLogStores(CacheKeys.FLOWS);
if (!flowsCache) {
logger.warn('[indexSync] Flows cache not available, falling back to direct sync');
return await performSync();
}
const flowManager = new FlowStateManager(flowsCache, {
ttl: 60000 * 10, // 10 minutes TTL for sync operations
});
// Use a unique flow ID for the sync operation
const flowId = 'meili-index-sync';
const flowType = 'MEILI_SYNC';
// This will only execute the handler if no other instance is running the sync
const result = await flowManager.createFlowWithHandler(flowId, flowType, performSync);
const result = await flowManager.createFlowWithHandler(flowId, flowType, () =>
performSync(flowManager, flowId, flowType),
);
if (result.messagesSync || result.convosSync) {
logger.info('[indexSync] Sync completed successfully');

View File

@@ -11,7 +11,7 @@ const {
getProjectByName,
} = require('./Project');
const { removeAllPermissions } = require('~/server/services/PermissionService');
const { getCachedTools } = require('~/server/services/Config');
const { getMCPServerTools } = require('~/server/services/Config');
const { getActions } = require('./Action');
const { Agent } = require('~/db/models');
@@ -49,53 +49,67 @@ const createAgent = async (agentData) => {
*/
const getAgent = async (searchParameter) => await Agent.findOne(searchParameter).lean();
/**
* Get multiple agent documents based on the provided search parameters.
*
* @param {Object} searchParameter - The search parameters to find agents.
* @returns {Promise<Agent[]>} Array of agent documents as plain objects.
*/
const getAgents = async (searchParameter) => await Agent.find(searchParameter).lean();
/**
* Load an agent based on the provided ID
*
* @param {Object} params
* @param {ServerRequest} params.req
* @param {string} params.spec
* @param {string} params.agent_id
* @param {string} params.endpoint
* @param {import('@librechat/agents').ClientOptions} [params.model_parameters]
* @returns {Promise<Agent|null>} The agent document as a plain object, or null if not found.
*/
const loadEphemeralAgent = async ({ req, agent_id, endpoint, model_parameters: _m }) => {
const loadEphemeralAgent = async ({ req, spec, agent_id, endpoint, model_parameters: _m }) => {
const { model, ...model_parameters } = _m;
/** @type {Record<string, FunctionTool>} */
const availableTools = await getCachedTools({ userId: req.user.id, includeGlobal: true });
const modelSpecs = req.config?.modelSpecs?.list;
/** @type {TModelSpec | null} */
let modelSpec = null;
if (spec != null && spec !== '') {
modelSpec = modelSpecs?.find((s) => s.name === spec) || null;
}
/** @type {TEphemeralAgent | null} */
const ephemeralAgent = req.body.ephemeralAgent;
const mcpServers = new Set(ephemeralAgent?.mcp);
if (modelSpec?.mcpServers) {
for (const mcpServer of modelSpec.mcpServers) {
mcpServers.add(mcpServer);
}
}
/** @type {string[]} */
const tools = [];
if (ephemeralAgent?.execute_code === true) {
if (ephemeralAgent?.execute_code === true || modelSpec?.executeCode === true) {
tools.push(Tools.execute_code);
}
if (ephemeralAgent?.file_search === true) {
if (ephemeralAgent?.file_search === true || modelSpec?.fileSearch === true) {
tools.push(Tools.file_search);
}
if (ephemeralAgent?.web_search === true) {
if (ephemeralAgent?.web_search === true || modelSpec?.webSearch === true) {
tools.push(Tools.web_search);
}
const addedServers = new Set();
if (mcpServers.size > 0) {
for (const toolName of Object.keys(availableTools)) {
if (!toolName.includes(mcp_delimiter)) {
continue;
}
const mcpServer = toolName.split(mcp_delimiter)?.[1];
if (mcpServer && mcpServers.has(mcpServer)) {
addedServers.add(mcpServer);
tools.push(toolName);
}
}
for (const mcpServer of mcpServers) {
if (addedServers.has(mcpServer)) {
continue;
}
tools.push(`${mcp_all}${mcp_delimiter}${mcpServer}`);
const serverTools = await getMCPServerTools(mcpServer);
if (!serverTools) {
tools.push(`${mcp_all}${mcp_delimiter}${mcpServer}`);
addedServers.add(mcpServer);
continue;
}
tools.push(...Object.keys(serverTools));
addedServers.add(mcpServer);
}
}
@@ -120,17 +134,18 @@ const loadEphemeralAgent = async ({ req, agent_id, endpoint, model_parameters: _
*
* @param {Object} params
* @param {ServerRequest} params.req
* @param {string} params.spec
* @param {string} params.agent_id
* @param {string} params.endpoint
* @param {import('@librechat/agents').ClientOptions} [params.model_parameters]
* @returns {Promise<Agent|null>} The agent document as a plain object, or null if not found.
*/
const loadAgent = async ({ req, agent_id, endpoint, model_parameters }) => {
const loadAgent = async ({ req, spec, agent_id, endpoint, model_parameters }) => {
if (!agent_id) {
return null;
}
if (agent_id === EPHEMERAL_AGENT_ID) {
return await loadEphemeralAgent({ req, agent_id, endpoint, model_parameters });
return await loadEphemeralAgent({ req, spec, agent_id, endpoint, model_parameters });
}
const agent = await getAgent({
id: agent_id,
@@ -835,6 +850,7 @@ const countPromotedAgents = async () => {
module.exports = {
getAgent,
getAgents,
loadAgent,
createAgent,
updateAgent,

View File

@@ -8,6 +8,7 @@ process.env.CREDS_IV = '0123456789abcdef';
jest.mock('~/server/services/Config', () => ({
getCachedTools: jest.fn(),
getMCPServerTools: jest.fn(),
}));
const mongoose = require('mongoose');
@@ -30,7 +31,7 @@ const {
generateActionMetadataHash,
} = require('./Agent');
const permissionService = require('~/server/services/PermissionService');
const { getCachedTools } = require('~/server/services/Config');
const { getCachedTools, getMCPServerTools } = require('~/server/services/Config');
const { AclEntry } = require('~/db/models');
/**
@@ -1929,6 +1930,16 @@ describe('models/Agent', () => {
another_tool: {},
});
// Mock getMCPServerTools to return tools for each server
getMCPServerTools.mockImplementation(async (server) => {
if (server === 'server1') {
return { tool1_mcp_server1: {} };
} else if (server === 'server2') {
return { tool2_mcp_server2: {} };
}
return null;
});
const mockReq = {
user: { id: 'user123' },
body: {
@@ -2113,6 +2124,14 @@ describe('models/Agent', () => {
getCachedTools.mockResolvedValue(availableTools);
// Mock getMCPServerTools to return all tools for server1
getMCPServerTools.mockImplementation(async (server) => {
if (server === 'server1') {
return availableTools; // All 100 tools belong to server1
}
return null;
});
const mockReq = {
user: { id: 'user123' },
body: {
@@ -2654,6 +2673,17 @@ describe('models/Agent', () => {
tool_mcp_server2: {}, // Different server
});
// Mock getMCPServerTools to return only tools matching the server
getMCPServerTools.mockImplementation(async (server) => {
if (server === 'server1') {
// Only return tool that correctly matches server1 format
return { tool_mcp_server1: {} };
} else if (server === 'server2') {
return { tool_mcp_server2: {} };
}
return null;
});
const mockReq = {
user: { id: 'user123' },
body: {

View File

@@ -1,4 +1,4 @@
const { logger } = require('~/config');
const { logger } = require('@librechat/data-schemas');
const options = [
{

View File

@@ -112,17 +112,8 @@ module.exports = {
update.expiredAt = null;
}
/** @type {{ $set: Partial<TConversation>; $addToSet?: Record<string, any>; $unset?: Record<keyof TConversation, number> }} */
/** @type {{ $set: Partial<TConversation>; $unset?: Record<keyof TConversation, number> }} */
const updateOperation = { $set: update };
if (convo.model && convo.endpoint) {
updateOperation.$addToSet = {
modelHistory: {
model: convo.model,
endpoint: convo.endpoint,
},
};
}
if (metadata && metadata.unsetFields && Object.keys(metadata.unsetFields).length > 0) {
updateOperation.$unset = metadata.unsetFields;
}
@@ -183,7 +174,7 @@ module.exports = {
if (search) {
try {
const meiliResults = await Conversation.meiliSearch(search);
const meiliResults = await Conversation.meiliSearch(search, { filter: `user = "${user}"` });
const matchingIds = Array.isArray(meiliResults.hits)
? meiliResults.hits.map((result) => result.conversationId)
: [];

View File

@@ -239,10 +239,46 @@ const updateTagsForConversation = async (user, conversationId, tags) => {
}
};
/**
* Increments tag counts for existing tags only.
* @param {string} user - The user ID.
* @param {string[]} tags - Array of tag names to increment
* @returns {Promise<void>}
*/
const bulkIncrementTagCounts = async (user, tags) => {
if (!tags || tags.length === 0) {
return;
}
try {
const uniqueTags = [...new Set(tags.filter(Boolean))];
if (uniqueTags.length === 0) {
return;
}
const bulkOps = uniqueTags.map((tag) => ({
updateOne: {
filter: { user, tag },
update: { $inc: { count: 1 } },
},
}));
const result = await ConversationTag.bulkWrite(bulkOps);
if (result && result.modifiedCount > 0) {
logger.debug(
`user: ${user} | Incremented tag counts - modified ${result.modifiedCount} tags`,
);
}
} catch (error) {
logger.error('[bulkIncrementTagCounts] Error incrementing tag counts', error);
}
};
module.exports = {
getConversationTags,
createConversationTag,
updateConversationTag,
deleteConversationTag,
bulkIncrementTagCounts,
updateTagsForConversation,
};

View File

@@ -42,7 +42,7 @@ const getToolFilesByIds = async (fileIds, toolResourceSet) => {
$or: [],
};
if (toolResourceSet.has(EToolResources.ocr)) {
if (toolResourceSet.has(EToolResources.context)) {
filter.$or.push({ text: { $exists: true, $ne: null }, context: FileContext.agents });
}
if (toolResourceSet.has(EToolResources.file_search)) {

View File

@@ -1,4 +1,4 @@
const { logger } = require('~/config');
const { logger } = require('@librechat/data-schemas');
const { createTransaction, createStructuredTransaction } = require('./Transaction');
/**
* Creates up to two transactions to record the spending of tokens.

View File

@@ -1,4 +1,4 @@
const { matchModelName } = require('@librechat/api');
const { matchModelName, findMatchingPattern } = require('@librechat/api');
const defaultRate = 6;
/**
@@ -6,44 +6,58 @@ const defaultRate = 6;
* source: https://aws.amazon.com/bedrock/pricing/
* */
const bedrockValues = {
// Basic llama2 patterns
// Basic llama2 patterns (base defaults to smallest variant)
llama2: { prompt: 0.75, completion: 1.0 },
'llama-2': { prompt: 0.75, completion: 1.0 },
'llama2-13b': { prompt: 0.75, completion: 1.0 },
'llama2:13b': { prompt: 0.75, completion: 1.0 },
'llama2:70b': { prompt: 1.95, completion: 2.56 },
'llama2-70b': { prompt: 1.95, completion: 2.56 },
// Basic llama3 patterns
// Basic llama3 patterns (base defaults to smallest variant)
llama3: { prompt: 0.3, completion: 0.6 },
'llama-3': { prompt: 0.3, completion: 0.6 },
'llama3-8b': { prompt: 0.3, completion: 0.6 },
'llama3:8b': { prompt: 0.3, completion: 0.6 },
'llama3-70b': { prompt: 2.65, completion: 3.5 },
'llama3:70b': { prompt: 2.65, completion: 3.5 },
// llama3-x-Nb pattern
// llama3-x-Nb pattern (base defaults to smallest variant)
'llama3-1': { prompt: 0.22, completion: 0.22 },
'llama3-1-8b': { prompt: 0.22, completion: 0.22 },
'llama3-1-70b': { prompt: 0.72, completion: 0.72 },
'llama3-1-405b': { prompt: 2.4, completion: 2.4 },
'llama3-2': { prompt: 0.1, completion: 0.1 },
'llama3-2-1b': { prompt: 0.1, completion: 0.1 },
'llama3-2-3b': { prompt: 0.15, completion: 0.15 },
'llama3-2-11b': { prompt: 0.16, completion: 0.16 },
'llama3-2-90b': { prompt: 0.72, completion: 0.72 },
'llama3-3': { prompt: 2.65, completion: 3.5 },
'llama3-3-70b': { prompt: 2.65, completion: 3.5 },
// llama3.x:Nb pattern
// llama3.x:Nb pattern (base defaults to smallest variant)
'llama3.1': { prompt: 0.22, completion: 0.22 },
'llama3.1:8b': { prompt: 0.22, completion: 0.22 },
'llama3.1:70b': { prompt: 0.72, completion: 0.72 },
'llama3.1:405b': { prompt: 2.4, completion: 2.4 },
'llama3.2': { prompt: 0.1, completion: 0.1 },
'llama3.2:1b': { prompt: 0.1, completion: 0.1 },
'llama3.2:3b': { prompt: 0.15, completion: 0.15 },
'llama3.2:11b': { prompt: 0.16, completion: 0.16 },
'llama3.2:90b': { prompt: 0.72, completion: 0.72 },
'llama3.3': { prompt: 2.65, completion: 3.5 },
'llama3.3:70b': { prompt: 2.65, completion: 3.5 },
// llama-3.x-Nb pattern
// llama-3.x-Nb pattern (base defaults to smallest variant)
'llama-3.1': { prompt: 0.22, completion: 0.22 },
'llama-3.1-8b': { prompt: 0.22, completion: 0.22 },
'llama-3.1-70b': { prompt: 0.72, completion: 0.72 },
'llama-3.1-405b': { prompt: 2.4, completion: 2.4 },
'llama-3.2': { prompt: 0.1, completion: 0.1 },
'llama-3.2-1b': { prompt: 0.1, completion: 0.1 },
'llama-3.2-3b': { prompt: 0.15, completion: 0.15 },
'llama-3.2-11b': { prompt: 0.16, completion: 0.16 },
'llama-3.2-90b': { prompt: 0.72, completion: 0.72 },
'llama-3.3': { prompt: 2.65, completion: 3.5 },
'llama-3.3-70b': { prompt: 2.65, completion: 3.5 },
'mistral-7b': { prompt: 0.15, completion: 0.2 },
'mistral-small': { prompt: 0.15, completion: 0.2 },
@@ -52,15 +66,19 @@ const bedrockValues = {
'mistral-large-2407': { prompt: 3.0, completion: 9.0 },
'command-text': { prompt: 1.5, completion: 2.0 },
'command-light': { prompt: 0.3, completion: 0.6 },
'ai21.j2-mid-v1': { prompt: 12.5, completion: 12.5 },
'ai21.j2-ultra-v1': { prompt: 18.8, completion: 18.8 },
'ai21.jamba-instruct-v1:0': { prompt: 0.5, completion: 0.7 },
'amazon.titan-text-lite-v1': { prompt: 0.15, completion: 0.2 },
'amazon.titan-text-express-v1': { prompt: 0.2, completion: 0.6 },
'amazon.titan-text-premier-v1:0': { prompt: 0.5, completion: 1.5 },
'amazon.nova-micro-v1:0': { prompt: 0.035, completion: 0.14 },
'amazon.nova-lite-v1:0': { prompt: 0.06, completion: 0.24 },
'amazon.nova-pro-v1:0': { prompt: 0.8, completion: 3.2 },
// AI21 models
'j2-mid': { prompt: 12.5, completion: 12.5 },
'j2-ultra': { prompt: 18.8, completion: 18.8 },
'jamba-instruct': { prompt: 0.5, completion: 0.7 },
// Amazon Titan models
'titan-text-lite': { prompt: 0.15, completion: 0.2 },
'titan-text-express': { prompt: 0.2, completion: 0.6 },
'titan-text-premier': { prompt: 0.5, completion: 1.5 },
// Amazon Nova models
'nova-micro': { prompt: 0.035, completion: 0.14 },
'nova-lite': { prompt: 0.06, completion: 0.24 },
'nova-pro': { prompt: 0.8, completion: 3.2 },
'nova-premier': { prompt: 2.5, completion: 12.5 },
'deepseek.r1': { prompt: 1.35, completion: 5.4 },
};
@@ -71,88 +89,136 @@ const bedrockValues = {
*/
const tokenValues = Object.assign(
{
// Legacy token size mappings (generic patterns - check LAST)
'8k': { prompt: 30, completion: 60 },
'32k': { prompt: 60, completion: 120 },
'4k': { prompt: 1.5, completion: 2 },
'16k': { prompt: 3, completion: 4 },
// Generic fallback patterns (check LAST)
'claude-': { prompt: 0.8, completion: 2.4 },
deepseek: { prompt: 0.28, completion: 0.42 },
command: { prompt: 0.38, completion: 0.38 },
gemma: { prompt: 0.02, completion: 0.04 }, // Base pattern (using gemma-3n-e4b pricing)
gemini: { prompt: 0.5, completion: 1.5 },
'gpt-oss': { prompt: 0.05, completion: 0.2 },
// Specific model variants (check FIRST - more specific patterns at end)
'gpt-3.5-turbo-1106': { prompt: 1, completion: 2 },
'o4-mini': { prompt: 1.1, completion: 4.4 },
'o3-mini': { prompt: 1.1, completion: 4.4 },
o3: { prompt: 2, completion: 8 },
'o1-mini': { prompt: 1.1, completion: 4.4 },
'o1-preview': { prompt: 15, completion: 60 },
o1: { prompt: 15, completion: 60 },
'gpt-3.5-turbo-0125': { prompt: 0.5, completion: 1.5 },
'gpt-4-1106': { prompt: 10, completion: 30 },
'gpt-4.1': { prompt: 2, completion: 8 },
'gpt-4.1-nano': { prompt: 0.1, completion: 0.4 },
'gpt-4.1-mini': { prompt: 0.4, completion: 1.6 },
'gpt-4.1': { prompt: 2, completion: 8 },
'gpt-4.5': { prompt: 75, completion: 150 },
'gpt-4o-mini': { prompt: 0.15, completion: 0.6 },
'gpt-5': { prompt: 1.25, completion: 10 },
'gpt-5-mini': { prompt: 0.25, completion: 2 },
'gpt-5-nano': { prompt: 0.05, completion: 0.4 },
'gpt-4o': { prompt: 2.5, completion: 10 },
'gpt-4o-2024-05-13': { prompt: 5, completion: 15 },
'gpt-4-1106': { prompt: 10, completion: 30 },
'gpt-3.5-turbo-0125': { prompt: 0.5, completion: 1.5 },
'claude-3-opus': { prompt: 15, completion: 75 },
'gpt-4o-mini': { prompt: 0.15, completion: 0.6 },
'gpt-5': { prompt: 1.25, completion: 10 },
'gpt-5-nano': { prompt: 0.05, completion: 0.4 },
'gpt-5-mini': { prompt: 0.25, completion: 2 },
'gpt-5-pro': { prompt: 15, completion: 120 },
o1: { prompt: 15, completion: 60 },
'o1-mini': { prompt: 1.1, completion: 4.4 },
'o1-preview': { prompt: 15, completion: 60 },
o3: { prompt: 2, completion: 8 },
'o3-mini': { prompt: 1.1, completion: 4.4 },
'o4-mini': { prompt: 1.1, completion: 4.4 },
'claude-instant': { prompt: 0.8, completion: 2.4 },
'claude-2': { prompt: 8, completion: 24 },
'claude-2.1': { prompt: 8, completion: 24 },
'claude-3-haiku': { prompt: 0.25, completion: 1.25 },
'claude-3-sonnet': { prompt: 3, completion: 15 },
'claude-3-opus': { prompt: 15, completion: 75 },
'claude-3-5-haiku': { prompt: 0.8, completion: 4 },
'claude-3.5-haiku': { prompt: 0.8, completion: 4 },
'claude-3-5-sonnet': { prompt: 3, completion: 15 },
'claude-3.5-sonnet': { prompt: 3, completion: 15 },
'claude-3-7-sonnet': { prompt: 3, completion: 15 },
'claude-3.7-sonnet': { prompt: 3, completion: 15 },
'claude-3-5-haiku': { prompt: 0.8, completion: 4 },
'claude-3.5-haiku': { prompt: 0.8, completion: 4 },
'claude-3-haiku': { prompt: 0.25, completion: 1.25 },
'claude-sonnet-4': { prompt: 3, completion: 15 },
'claude-haiku-4-5': { prompt: 1, completion: 5 },
'claude-opus-4': { prompt: 15, completion: 75 },
'claude-2.1': { prompt: 8, completion: 24 },
'claude-2': { prompt: 8, completion: 24 },
'claude-instant': { prompt: 0.8, completion: 2.4 },
'claude-': { prompt: 0.8, completion: 2.4 },
'command-r-plus': { prompt: 3, completion: 15 },
'claude-sonnet-4': { prompt: 3, completion: 15 },
'command-r': { prompt: 0.5, completion: 1.5 },
'deepseek-reasoner': { prompt: 0.55, completion: 2.19 },
deepseek: { prompt: 0.14, completion: 0.28 },
/* cohere doesn't have rates for the older command models,
so this was from https://artificialanalysis.ai/models/command-light/providers */
command: { prompt: 0.38, completion: 0.38 },
gemma: { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
'gemma-2': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
'gemma-3': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
'gemma-3-27b': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
'gemini-2.0-flash-lite': { prompt: 0.075, completion: 0.3 },
'gemini-2.0-flash': { prompt: 0.1, completion: 0.4 },
'gemini-2.0': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
'gemini-2.5-pro': { prompt: 1.25, completion: 10 },
'gemini-2.5-flash': { prompt: 0.15, completion: 3.5 },
'gemini-2.5': { prompt: 0, completion: 0 }, // Free for a period of time
'gemini-1.5-flash-8b': { prompt: 0.075, completion: 0.3 },
'gemini-1.5-flash': { prompt: 0.15, completion: 0.6 },
'command-r-plus': { prompt: 3, completion: 15 },
'command-text': { prompt: 1.5, completion: 2.0 },
'deepseek-reasoner': { prompt: 0.28, completion: 0.42 },
'deepseek-r1': { prompt: 0.4, completion: 2.0 },
'deepseek-v3': { prompt: 0.2, completion: 0.8 },
'gemma-2': { prompt: 0.01, completion: 0.03 }, // Base pattern (using gemma-2-9b pricing)
'gemma-3': { prompt: 0.02, completion: 0.04 }, // Base pattern (using gemma-3n-e4b pricing)
'gemma-3-27b': { prompt: 0.09, completion: 0.16 },
'gemini-1.5': { prompt: 2.5, completion: 10 },
'gemini-1.5-flash': { prompt: 0.15, completion: 0.6 },
'gemini-1.5-flash-8b': { prompt: 0.075, completion: 0.3 },
'gemini-2.0': { prompt: 0.1, completion: 0.4 }, // Base pattern (using 2.0-flash pricing)
'gemini-2.0-flash': { prompt: 0.1, completion: 0.4 },
'gemini-2.0-flash-lite': { prompt: 0.075, completion: 0.3 },
'gemini-2.5': { prompt: 0.3, completion: 2.5 }, // Base pattern (using 2.5-flash pricing)
'gemini-2.5-flash': { prompt: 0.3, completion: 2.5 },
'gemini-2.5-flash-lite': { prompt: 0.1, completion: 0.4 },
'gemini-2.5-pro': { prompt: 1.25, completion: 10 },
'gemini-pro-vision': { prompt: 0.5, completion: 1.5 },
gemini: { prompt: 0.5, completion: 1.5 },
'grok-2-vision-1212': { prompt: 2.0, completion: 10.0 },
'grok-2-vision-latest': { prompt: 2.0, completion: 10.0 },
'grok-2-vision': { prompt: 2.0, completion: 10.0 },
grok: { prompt: 2.0, completion: 10.0 }, // Base pattern defaults to grok-2
'grok-beta': { prompt: 5.0, completion: 15.0 },
'grok-vision-beta': { prompt: 5.0, completion: 15.0 },
'grok-2': { prompt: 2.0, completion: 10.0 },
'grok-2-1212': { prompt: 2.0, completion: 10.0 },
'grok-2-latest': { prompt: 2.0, completion: 10.0 },
'grok-2': { prompt: 2.0, completion: 10.0 },
'grok-3-mini-fast': { prompt: 0.6, completion: 4 },
'grok-3-mini': { prompt: 0.3, completion: 0.5 },
'grok-3-fast': { prompt: 5.0, completion: 25.0 },
'grok-2-vision': { prompt: 2.0, completion: 10.0 },
'grok-2-vision-1212': { prompt: 2.0, completion: 10.0 },
'grok-2-vision-latest': { prompt: 2.0, completion: 10.0 },
'grok-3': { prompt: 3.0, completion: 15.0 },
'grok-3-fast': { prompt: 5.0, completion: 25.0 },
'grok-3-mini': { prompt: 0.3, completion: 0.5 },
'grok-3-mini-fast': { prompt: 0.6, completion: 4 },
'grok-4': { prompt: 3.0, completion: 15.0 },
'grok-beta': { prompt: 5.0, completion: 15.0 },
'mistral-large': { prompt: 2.0, completion: 6.0 },
'pixtral-large': { prompt: 2.0, completion: 6.0 },
'mistral-saba': { prompt: 0.2, completion: 0.6 },
codestral: { prompt: 0.3, completion: 0.9 },
'ministral-8b': { prompt: 0.1, completion: 0.1 },
'ministral-3b': { prompt: 0.04, completion: 0.04 },
// GPT-OSS models
'ministral-8b': { prompt: 0.1, completion: 0.1 },
'mistral-nemo': { prompt: 0.15, completion: 0.15 },
'mistral-saba': { prompt: 0.2, completion: 0.6 },
'pixtral-large': { prompt: 2.0, completion: 6.0 },
'mistral-large': { prompt: 2.0, completion: 6.0 },
'mixtral-8x22b': { prompt: 0.65, completion: 0.65 },
kimi: { prompt: 0.14, completion: 2.49 }, // Base pattern (using kimi-k2 pricing)
// GPT-OSS models (specific sizes)
'gpt-oss:20b': { prompt: 0.05, completion: 0.2 },
'gpt-oss-20b': { prompt: 0.05, completion: 0.2 },
'gpt-oss:120b': { prompt: 0.15, completion: 0.6 },
'gpt-oss-120b': { prompt: 0.15, completion: 0.6 },
// GLM models (Zhipu AI) - general to specific
glm4: { prompt: 0.1, completion: 0.1 },
'glm-4': { prompt: 0.1, completion: 0.1 },
'glm-4-32b': { prompt: 0.1, completion: 0.1 },
'glm-4.5': { prompt: 0.35, completion: 1.55 },
'glm-4.5-air': { prompt: 0.14, completion: 0.86 },
'glm-4.5v': { prompt: 0.6, completion: 1.8 },
'glm-4.6': { prompt: 0.5, completion: 1.75 },
// Qwen models
qwen: { prompt: 0.08, completion: 0.33 }, // Qwen base pattern (using qwen2.5-72b pricing)
'qwen2.5': { prompt: 0.08, completion: 0.33 }, // Qwen 2.5 base pattern
'qwen-turbo': { prompt: 0.05, completion: 0.2 },
'qwen-plus': { prompt: 0.4, completion: 1.2 },
'qwen-max': { prompt: 1.6, completion: 6.4 },
'qwq-32b': { prompt: 0.15, completion: 0.4 },
// Qwen3 models
qwen3: { prompt: 0.035, completion: 0.138 }, // Qwen3 base pattern (using qwen3-4b pricing)
'qwen3-8b': { prompt: 0.035, completion: 0.138 },
'qwen3-14b': { prompt: 0.05, completion: 0.22 },
'qwen3-30b-a3b': { prompt: 0.06, completion: 0.22 },
'qwen3-32b': { prompt: 0.05, completion: 0.2 },
'qwen3-235b-a22b': { prompt: 0.08, completion: 0.55 },
// Qwen3 VL (Vision-Language) models
'qwen3-vl-8b-thinking': { prompt: 0.18, completion: 2.1 },
'qwen3-vl-8b-instruct': { prompt: 0.18, completion: 0.69 },
'qwen3-vl-30b-a3b': { prompt: 0.29, completion: 1.0 },
'qwen3-vl-235b-a22b': { prompt: 0.3, completion: 1.2 },
// Qwen3 specialized models
'qwen3-max': { prompt: 1.2, completion: 6 },
'qwen3-coder': { prompt: 0.22, completion: 0.95 },
'qwen3-coder-30b-a3b': { prompt: 0.06, completion: 0.25 },
'qwen3-coder-plus': { prompt: 1, completion: 5 },
'qwen3-coder-flash': { prompt: 0.3, completion: 1.5 },
'qwen3-next-80b-a3b': { prompt: 0.1, completion: 0.8 },
},
bedrockValues,
);
@@ -183,67 +249,39 @@ const cacheTokenValues = {
* @returns {string|undefined} The key corresponding to the model name, or undefined if no match is found.
*/
const getValueKey = (model, endpoint) => {
if (!model || typeof model !== 'string') {
return undefined;
}
// Use findMatchingPattern directly against tokenValues for efficient lookup
if (!endpoint || (typeof endpoint === 'string' && !tokenValues[endpoint])) {
const matchedKey = findMatchingPattern(model, tokenValues);
if (matchedKey) {
return matchedKey;
}
}
// Fallback: use matchModelName for edge cases and legacy handling
const modelName = matchModelName(model, endpoint);
if (!modelName) {
return undefined;
}
// Legacy token size mappings and aliases for older models
if (modelName.includes('gpt-3.5-turbo-16k')) {
return '16k';
} else if (modelName.includes('gpt-3.5-turbo-0125')) {
return 'gpt-3.5-turbo-0125';
} else if (modelName.includes('gpt-3.5-turbo-1106')) {
return 'gpt-3.5-turbo-1106';
} else if (modelName.includes('gpt-3.5')) {
return '4k';
} else if (modelName.includes('o4-mini')) {
return 'o4-mini';
} else if (modelName.includes('o4')) {
return 'o4';
} else if (modelName.includes('o3-mini')) {
return 'o3-mini';
} else if (modelName.includes('o3')) {
return 'o3';
} else if (modelName.includes('o1-preview')) {
return 'o1-preview';
} else if (modelName.includes('o1-mini')) {
return 'o1-mini';
} else if (modelName.includes('o1')) {
return 'o1';
} else if (modelName.includes('gpt-4.5')) {
return 'gpt-4.5';
} else if (modelName.includes('gpt-4.1-nano')) {
return 'gpt-4.1-nano';
} else if (modelName.includes('gpt-4.1-mini')) {
return 'gpt-4.1-mini';
} else if (modelName.includes('gpt-4.1')) {
return 'gpt-4.1';
} else if (modelName.includes('gpt-4o-2024-05-13')) {
return 'gpt-4o-2024-05-13';
} else if (modelName.includes('gpt-5-nano')) {
return 'gpt-5-nano';
} else if (modelName.includes('gpt-5-mini')) {
return 'gpt-5-mini';
} else if (modelName.includes('gpt-5')) {
return 'gpt-5';
} else if (modelName.includes('gpt-4o-mini')) {
return 'gpt-4o-mini';
} else if (modelName.includes('gpt-4o')) {
return 'gpt-4o';
} else if (modelName.includes('gpt-4-vision')) {
return 'gpt-4-1106';
} else if (modelName.includes('gpt-4-1106')) {
return 'gpt-4-1106';
return 'gpt-4-1106'; // Alias for gpt-4-vision
} else if (modelName.includes('gpt-4-0125')) {
return 'gpt-4-1106';
return 'gpt-4-1106'; // Alias for gpt-4-0125
} else if (modelName.includes('gpt-4-turbo')) {
return 'gpt-4-1106';
return 'gpt-4-1106'; // Alias for gpt-4-turbo
} else if (modelName.includes('gpt-4-32k')) {
return '32k';
} else if (modelName.includes('gpt-4')) {
return '8k';
} else if (tokenValues[modelName]) {
return modelName;
}
return undefined;

View File

@@ -1,3 +1,4 @@
const { maxTokensMap } = require('@librechat/api');
const { EModelEndpoint } = require('librechat-data-provider');
const {
defaultRate,
@@ -113,6 +114,14 @@ describe('getValueKey', () => {
expect(getValueKey('gpt-5-nano-2025-01-30-0130')).toBe('gpt-5-nano');
});
it('should return "gpt-5-pro" for model type of "gpt-5-pro"', () => {
expect(getValueKey('gpt-5-pro-2025-01-30')).toBe('gpt-5-pro');
expect(getValueKey('openai/gpt-5-pro')).toBe('gpt-5-pro');
expect(getValueKey('gpt-5-pro-0130')).toBe('gpt-5-pro');
expect(getValueKey('gpt-5-pro-2025-01-30-0130')).toBe('gpt-5-pro');
expect(getValueKey('gpt-5-pro-preview')).toBe('gpt-5-pro');
});
it('should return "gpt-4o" for model type of "gpt-4o"', () => {
expect(getValueKey('gpt-4o-2024-08-06')).toBe('gpt-4o');
expect(getValueKey('gpt-4o-2024-08-06-0718')).toBe('gpt-4o');
@@ -184,6 +193,16 @@ describe('getValueKey', () => {
expect(getValueKey('claude-3.5-haiku-turbo')).toBe('claude-3.5-haiku');
expect(getValueKey('claude-3.5-haiku-0125')).toBe('claude-3.5-haiku');
});
it('should return expected value keys for "gpt-oss" models', () => {
expect(getValueKey('openai/gpt-oss-120b')).toBe('gpt-oss-120b');
expect(getValueKey('openai/gpt-oss:120b')).toBe('gpt-oss:120b');
expect(getValueKey('openai/gpt-oss-570b')).toBe('gpt-oss');
expect(getValueKey('gpt-oss-570b')).toBe('gpt-oss');
expect(getValueKey('groq/gpt-oss-1080b')).toBe('gpt-oss');
expect(getValueKey('gpt-oss-20b')).toBe('gpt-oss-20b');
expect(getValueKey('oai/gpt-oss:20b')).toBe('gpt-oss:20b');
});
});
describe('getMultiplier', () => {
@@ -278,6 +297,20 @@ describe('getMultiplier', () => {
);
});
it('should return the correct multiplier for gpt-5-pro', () => {
const valueKey = getValueKey('gpt-5-pro-2025-01-30');
expect(getMultiplier({ valueKey, tokenType: 'prompt' })).toBe(tokenValues['gpt-5-pro'].prompt);
expect(getMultiplier({ valueKey, tokenType: 'completion' })).toBe(
tokenValues['gpt-5-pro'].completion,
);
expect(getMultiplier({ model: 'gpt-5-pro-preview', tokenType: 'prompt' })).toBe(
tokenValues['gpt-5-pro'].prompt,
);
expect(getMultiplier({ model: 'openai/gpt-5-pro', tokenType: 'completion' })).toBe(
tokenValues['gpt-5-pro'].completion,
);
});
it('should return the correct multiplier for gpt-4o', () => {
const valueKey = getValueKey('gpt-4o-2024-08-06');
expect(getMultiplier({ valueKey, tokenType: 'prompt' })).toBe(tokenValues['gpt-4o'].prompt);
@@ -394,6 +427,18 @@ describe('getMultiplier', () => {
expect(getMultiplier({ model: key, tokenType: 'completion' })).toBe(expectedCompletion);
});
});
it('should return correct multipliers for GLM models', () => {
const models = ['glm-4.6', 'glm-4.5v', 'glm-4.5-air', 'glm-4.5', 'glm-4-32b', 'glm-4', 'glm4'];
models.forEach((key) => {
const expectedPrompt = tokenValues[key].prompt;
const expectedCompletion = tokenValues[key].completion;
expect(getMultiplier({ valueKey: key, tokenType: 'prompt' })).toBe(expectedPrompt);
expect(getMultiplier({ valueKey: key, tokenType: 'completion' })).toBe(expectedCompletion);
expect(getMultiplier({ model: key, tokenType: 'prompt' })).toBe(expectedPrompt);
expect(getMultiplier({ model: key, tokenType: 'completion' })).toBe(expectedCompletion);
});
});
});
describe('AWS Bedrock Model Tests', () => {
@@ -449,6 +494,249 @@ describe('AWS Bedrock Model Tests', () => {
});
});
describe('Amazon Model Tests', () => {
describe('Amazon Nova Models', () => {
it('should return correct pricing for nova-premier', () => {
expect(getMultiplier({ model: 'nova-premier', tokenType: 'prompt' })).toBe(
tokenValues['nova-premier'].prompt,
);
expect(getMultiplier({ model: 'nova-premier', tokenType: 'completion' })).toBe(
tokenValues['nova-premier'].completion,
);
expect(getMultiplier({ model: 'amazon.nova-premier-v1:0', tokenType: 'prompt' })).toBe(
tokenValues['nova-premier'].prompt,
);
expect(getMultiplier({ model: 'amazon.nova-premier-v1:0', tokenType: 'completion' })).toBe(
tokenValues['nova-premier'].completion,
);
});
it('should return correct pricing for nova-pro', () => {
expect(getMultiplier({ model: 'nova-pro', tokenType: 'prompt' })).toBe(
tokenValues['nova-pro'].prompt,
);
expect(getMultiplier({ model: 'nova-pro', tokenType: 'completion' })).toBe(
tokenValues['nova-pro'].completion,
);
expect(getMultiplier({ model: 'amazon.nova-pro-v1:0', tokenType: 'prompt' })).toBe(
tokenValues['nova-pro'].prompt,
);
expect(getMultiplier({ model: 'amazon.nova-pro-v1:0', tokenType: 'completion' })).toBe(
tokenValues['nova-pro'].completion,
);
});
it('should return correct pricing for nova-lite', () => {
expect(getMultiplier({ model: 'nova-lite', tokenType: 'prompt' })).toBe(
tokenValues['nova-lite'].prompt,
);
expect(getMultiplier({ model: 'nova-lite', tokenType: 'completion' })).toBe(
tokenValues['nova-lite'].completion,
);
expect(getMultiplier({ model: 'amazon.nova-lite-v1:0', tokenType: 'prompt' })).toBe(
tokenValues['nova-lite'].prompt,
);
expect(getMultiplier({ model: 'amazon.nova-lite-v1:0', tokenType: 'completion' })).toBe(
tokenValues['nova-lite'].completion,
);
});
it('should return correct pricing for nova-micro', () => {
expect(getMultiplier({ model: 'nova-micro', tokenType: 'prompt' })).toBe(
tokenValues['nova-micro'].prompt,
);
expect(getMultiplier({ model: 'nova-micro', tokenType: 'completion' })).toBe(
tokenValues['nova-micro'].completion,
);
expect(getMultiplier({ model: 'amazon.nova-micro-v1:0', tokenType: 'prompt' })).toBe(
tokenValues['nova-micro'].prompt,
);
expect(getMultiplier({ model: 'amazon.nova-micro-v1:0', tokenType: 'completion' })).toBe(
tokenValues['nova-micro'].completion,
);
});
it('should match both short and full model names to the same pricing', () => {
const models = ['nova-micro', 'nova-lite', 'nova-pro', 'nova-premier'];
const fullModels = [
'amazon.nova-micro-v1:0',
'amazon.nova-lite-v1:0',
'amazon.nova-pro-v1:0',
'amazon.nova-premier-v1:0',
];
models.forEach((shortModel, i) => {
const fullModel = fullModels[i];
const shortPrompt = getMultiplier({ model: shortModel, tokenType: 'prompt' });
const fullPrompt = getMultiplier({ model: fullModel, tokenType: 'prompt' });
const shortCompletion = getMultiplier({ model: shortModel, tokenType: 'completion' });
const fullCompletion = getMultiplier({ model: fullModel, tokenType: 'completion' });
expect(shortPrompt).toBe(fullPrompt);
expect(shortCompletion).toBe(fullCompletion);
expect(shortPrompt).toBe(tokenValues[shortModel].prompt);
expect(shortCompletion).toBe(tokenValues[shortModel].completion);
});
});
});
describe('Amazon Titan Models', () => {
it('should return correct pricing for titan-text-premier', () => {
expect(getMultiplier({ model: 'titan-text-premier', tokenType: 'prompt' })).toBe(
tokenValues['titan-text-premier'].prompt,
);
expect(getMultiplier({ model: 'titan-text-premier', tokenType: 'completion' })).toBe(
tokenValues['titan-text-premier'].completion,
);
expect(getMultiplier({ model: 'amazon.titan-text-premier-v1:0', tokenType: 'prompt' })).toBe(
tokenValues['titan-text-premier'].prompt,
);
expect(
getMultiplier({ model: 'amazon.titan-text-premier-v1:0', tokenType: 'completion' }),
).toBe(tokenValues['titan-text-premier'].completion);
});
it('should return correct pricing for titan-text-express', () => {
expect(getMultiplier({ model: 'titan-text-express', tokenType: 'prompt' })).toBe(
tokenValues['titan-text-express'].prompt,
);
expect(getMultiplier({ model: 'titan-text-express', tokenType: 'completion' })).toBe(
tokenValues['titan-text-express'].completion,
);
expect(getMultiplier({ model: 'amazon.titan-text-express-v1', tokenType: 'prompt' })).toBe(
tokenValues['titan-text-express'].prompt,
);
expect(
getMultiplier({ model: 'amazon.titan-text-express-v1', tokenType: 'completion' }),
).toBe(tokenValues['titan-text-express'].completion);
});
it('should return correct pricing for titan-text-lite', () => {
expect(getMultiplier({ model: 'titan-text-lite', tokenType: 'prompt' })).toBe(
tokenValues['titan-text-lite'].prompt,
);
expect(getMultiplier({ model: 'titan-text-lite', tokenType: 'completion' })).toBe(
tokenValues['titan-text-lite'].completion,
);
expect(getMultiplier({ model: 'amazon.titan-text-lite-v1', tokenType: 'prompt' })).toBe(
tokenValues['titan-text-lite'].prompt,
);
expect(getMultiplier({ model: 'amazon.titan-text-lite-v1', tokenType: 'completion' })).toBe(
tokenValues['titan-text-lite'].completion,
);
});
it('should match both short and full model names to the same pricing', () => {
const models = ['titan-text-lite', 'titan-text-express', 'titan-text-premier'];
const fullModels = [
'amazon.titan-text-lite-v1',
'amazon.titan-text-express-v1',
'amazon.titan-text-premier-v1:0',
];
models.forEach((shortModel, i) => {
const fullModel = fullModels[i];
const shortPrompt = getMultiplier({ model: shortModel, tokenType: 'prompt' });
const fullPrompt = getMultiplier({ model: fullModel, tokenType: 'prompt' });
const shortCompletion = getMultiplier({ model: shortModel, tokenType: 'completion' });
const fullCompletion = getMultiplier({ model: fullModel, tokenType: 'completion' });
expect(shortPrompt).toBe(fullPrompt);
expect(shortCompletion).toBe(fullCompletion);
expect(shortPrompt).toBe(tokenValues[shortModel].prompt);
expect(shortCompletion).toBe(tokenValues[shortModel].completion);
});
});
});
});
describe('AI21 Model Tests', () => {
describe('AI21 J2 Models', () => {
it('should return correct pricing for j2-mid', () => {
expect(getMultiplier({ model: 'j2-mid', tokenType: 'prompt' })).toBe(
tokenValues['j2-mid'].prompt,
);
expect(getMultiplier({ model: 'j2-mid', tokenType: 'completion' })).toBe(
tokenValues['j2-mid'].completion,
);
expect(getMultiplier({ model: 'ai21.j2-mid-v1', tokenType: 'prompt' })).toBe(
tokenValues['j2-mid'].prompt,
);
expect(getMultiplier({ model: 'ai21.j2-mid-v1', tokenType: 'completion' })).toBe(
tokenValues['j2-mid'].completion,
);
});
it('should return correct pricing for j2-ultra', () => {
expect(getMultiplier({ model: 'j2-ultra', tokenType: 'prompt' })).toBe(
tokenValues['j2-ultra'].prompt,
);
expect(getMultiplier({ model: 'j2-ultra', tokenType: 'completion' })).toBe(
tokenValues['j2-ultra'].completion,
);
expect(getMultiplier({ model: 'ai21.j2-ultra-v1', tokenType: 'prompt' })).toBe(
tokenValues['j2-ultra'].prompt,
);
expect(getMultiplier({ model: 'ai21.j2-ultra-v1', tokenType: 'completion' })).toBe(
tokenValues['j2-ultra'].completion,
);
});
it('should match both short and full model names to the same pricing', () => {
const models = ['j2-mid', 'j2-ultra'];
const fullModels = ['ai21.j2-mid-v1', 'ai21.j2-ultra-v1'];
models.forEach((shortModel, i) => {
const fullModel = fullModels[i];
const shortPrompt = getMultiplier({ model: shortModel, tokenType: 'prompt' });
const fullPrompt = getMultiplier({ model: fullModel, tokenType: 'prompt' });
const shortCompletion = getMultiplier({ model: shortModel, tokenType: 'completion' });
const fullCompletion = getMultiplier({ model: fullModel, tokenType: 'completion' });
expect(shortPrompt).toBe(fullPrompt);
expect(shortCompletion).toBe(fullCompletion);
expect(shortPrompt).toBe(tokenValues[shortModel].prompt);
expect(shortCompletion).toBe(tokenValues[shortModel].completion);
});
});
});
describe('AI21 Jamba Models', () => {
it('should return correct pricing for jamba-instruct', () => {
expect(getMultiplier({ model: 'jamba-instruct', tokenType: 'prompt' })).toBe(
tokenValues['jamba-instruct'].prompt,
);
expect(getMultiplier({ model: 'jamba-instruct', tokenType: 'completion' })).toBe(
tokenValues['jamba-instruct'].completion,
);
expect(getMultiplier({ model: 'ai21.jamba-instruct-v1:0', tokenType: 'prompt' })).toBe(
tokenValues['jamba-instruct'].prompt,
);
expect(getMultiplier({ model: 'ai21.jamba-instruct-v1:0', tokenType: 'completion' })).toBe(
tokenValues['jamba-instruct'].completion,
);
});
it('should match both short and full model names to the same pricing', () => {
const shortPrompt = getMultiplier({ model: 'jamba-instruct', tokenType: 'prompt' });
const fullPrompt = getMultiplier({
model: 'ai21.jamba-instruct-v1:0',
tokenType: 'prompt',
});
const shortCompletion = getMultiplier({ model: 'jamba-instruct', tokenType: 'completion' });
const fullCompletion = getMultiplier({
model: 'ai21.jamba-instruct-v1:0',
tokenType: 'completion',
});
expect(shortPrompt).toBe(fullPrompt);
expect(shortCompletion).toBe(fullCompletion);
expect(shortPrompt).toBe(tokenValues['jamba-instruct'].prompt);
expect(shortCompletion).toBe(tokenValues['jamba-instruct'].completion);
});
});
});
describe('Deepseek Model Tests', () => {
const deepseekModels = ['deepseek-chat', 'deepseek-coder', 'deepseek-reasoner', 'deepseek.r1'];
@@ -480,6 +768,187 @@ describe('Deepseek Model Tests', () => {
});
});
describe('Qwen3 Model Tests', () => {
describe('Qwen3 Base Models', () => {
it('should return correct pricing for qwen3 base pattern', () => {
expect(getMultiplier({ model: 'qwen3', tokenType: 'prompt' })).toBe(
tokenValues['qwen3'].prompt,
);
expect(getMultiplier({ model: 'qwen3', tokenType: 'completion' })).toBe(
tokenValues['qwen3'].completion,
);
});
it('should return correct pricing for qwen3-4b (falls back to qwen3)', () => {
expect(getMultiplier({ model: 'qwen3-4b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3'].prompt,
);
expect(getMultiplier({ model: 'qwen3-4b', tokenType: 'completion' })).toBe(
tokenValues['qwen3'].completion,
);
});
it('should return correct pricing for qwen3-8b', () => {
expect(getMultiplier({ model: 'qwen3-8b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-8b'].prompt,
);
expect(getMultiplier({ model: 'qwen3-8b', tokenType: 'completion' })).toBe(
tokenValues['qwen3-8b'].completion,
);
});
it('should return correct pricing for qwen3-14b', () => {
expect(getMultiplier({ model: 'qwen3-14b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-14b'].prompt,
);
expect(getMultiplier({ model: 'qwen3-14b', tokenType: 'completion' })).toBe(
tokenValues['qwen3-14b'].completion,
);
});
it('should return correct pricing for qwen3-235b-a22b', () => {
expect(getMultiplier({ model: 'qwen3-235b-a22b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-235b-a22b'].prompt,
);
expect(getMultiplier({ model: 'qwen3-235b-a22b', tokenType: 'completion' })).toBe(
tokenValues['qwen3-235b-a22b'].completion,
);
});
it('should handle model name variations with provider prefixes', () => {
const models = [
{ input: 'qwen3', expected: 'qwen3' },
{ input: 'qwen3-4b', expected: 'qwen3' },
{ input: 'qwen3-8b', expected: 'qwen3-8b' },
{ input: 'qwen3-32b', expected: 'qwen3-32b' },
];
models.forEach(({ input, expected }) => {
const withPrefix = `alibaba/${input}`;
expect(getMultiplier({ model: withPrefix, tokenType: 'prompt' })).toBe(
tokenValues[expected].prompt,
);
expect(getMultiplier({ model: withPrefix, tokenType: 'completion' })).toBe(
tokenValues[expected].completion,
);
});
});
});
describe('Qwen3 VL (Vision-Language) Models', () => {
it('should return correct pricing for qwen3-vl-8b-thinking', () => {
expect(getMultiplier({ model: 'qwen3-vl-8b-thinking', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-vl-8b-thinking'].prompt,
);
expect(getMultiplier({ model: 'qwen3-vl-8b-thinking', tokenType: 'completion' })).toBe(
tokenValues['qwen3-vl-8b-thinking'].completion,
);
});
it('should return correct pricing for qwen3-vl-8b-instruct', () => {
expect(getMultiplier({ model: 'qwen3-vl-8b-instruct', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-vl-8b-instruct'].prompt,
);
expect(getMultiplier({ model: 'qwen3-vl-8b-instruct', tokenType: 'completion' })).toBe(
tokenValues['qwen3-vl-8b-instruct'].completion,
);
});
it('should return correct pricing for qwen3-vl-30b-a3b', () => {
expect(getMultiplier({ model: 'qwen3-vl-30b-a3b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-vl-30b-a3b'].prompt,
);
expect(getMultiplier({ model: 'qwen3-vl-30b-a3b', tokenType: 'completion' })).toBe(
tokenValues['qwen3-vl-30b-a3b'].completion,
);
});
it('should return correct pricing for qwen3-vl-235b-a22b', () => {
expect(getMultiplier({ model: 'qwen3-vl-235b-a22b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-vl-235b-a22b'].prompt,
);
expect(getMultiplier({ model: 'qwen3-vl-235b-a22b', tokenType: 'completion' })).toBe(
tokenValues['qwen3-vl-235b-a22b'].completion,
);
});
});
describe('Qwen3 Specialized Models', () => {
it('should return correct pricing for qwen3-max', () => {
expect(getMultiplier({ model: 'qwen3-max', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-max'].prompt,
);
expect(getMultiplier({ model: 'qwen3-max', tokenType: 'completion' })).toBe(
tokenValues['qwen3-max'].completion,
);
});
it('should return correct pricing for qwen3-coder', () => {
expect(getMultiplier({ model: 'qwen3-coder', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-coder'].prompt,
);
expect(getMultiplier({ model: 'qwen3-coder', tokenType: 'completion' })).toBe(
tokenValues['qwen3-coder'].completion,
);
});
it('should return correct pricing for qwen3-coder-plus', () => {
expect(getMultiplier({ model: 'qwen3-coder-plus', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-coder-plus'].prompt,
);
expect(getMultiplier({ model: 'qwen3-coder-plus', tokenType: 'completion' })).toBe(
tokenValues['qwen3-coder-plus'].completion,
);
});
it('should return correct pricing for qwen3-coder-flash', () => {
expect(getMultiplier({ model: 'qwen3-coder-flash', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-coder-flash'].prompt,
);
expect(getMultiplier({ model: 'qwen3-coder-flash', tokenType: 'completion' })).toBe(
tokenValues['qwen3-coder-flash'].completion,
);
});
it('should return correct pricing for qwen3-next-80b-a3b', () => {
expect(getMultiplier({ model: 'qwen3-next-80b-a3b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-next-80b-a3b'].prompt,
);
expect(getMultiplier({ model: 'qwen3-next-80b-a3b', tokenType: 'completion' })).toBe(
tokenValues['qwen3-next-80b-a3b'].completion,
);
});
});
describe('Qwen3 Model Variations', () => {
it('should handle all qwen3 models with provider prefixes', () => {
const models = ['qwen3', 'qwen3-8b', 'qwen3-max', 'qwen3-coder', 'qwen3-vl-8b-instruct'];
const prefixes = ['alibaba', 'qwen', 'openrouter'];
models.forEach((model) => {
prefixes.forEach((prefix) => {
const fullModel = `${prefix}/${model}`;
expect(getMultiplier({ model: fullModel, tokenType: 'prompt' })).toBe(
tokenValues[model].prompt,
);
expect(getMultiplier({ model: fullModel, tokenType: 'completion' })).toBe(
tokenValues[model].completion,
);
});
});
});
it('should handle qwen3-4b falling back to qwen3 base pattern', () => {
const testCases = ['qwen3-4b', 'alibaba/qwen3-4b', 'qwen/qwen3-4b-preview'];
testCases.forEach((model) => {
expect(getMultiplier({ model, tokenType: 'prompt' })).toBe(tokenValues['qwen3'].prompt);
expect(getMultiplier({ model, tokenType: 'completion' })).toBe(
tokenValues['qwen3'].completion,
);
});
});
});
});
describe('getCacheMultiplier', () => {
it('should return the correct cache multiplier for a given valueKey and cacheType', () => {
expect(getCacheMultiplier({ valueKey: 'claude-3-5-sonnet', cacheType: 'write' })).toBe(
@@ -571,6 +1040,9 @@ describe('getCacheMultiplier', () => {
describe('Google Model Tests', () => {
const googleModels = [
'gemini-2.5-pro',
'gemini-2.5-flash',
'gemini-2.5-flash-lite',
'gemini-2.5-pro-preview-05-06',
'gemini-2.5-flash-preview-04-17',
'gemini-2.5-exp',
@@ -611,6 +1083,9 @@ describe('Google Model Tests', () => {
it('should map to the correct model keys', () => {
const expected = {
'gemini-2.5-pro': 'gemini-2.5-pro',
'gemini-2.5-flash': 'gemini-2.5-flash',
'gemini-2.5-flash-lite': 'gemini-2.5-flash-lite',
'gemini-2.5-pro-preview-05-06': 'gemini-2.5-pro',
'gemini-2.5-flash-preview-04-17': 'gemini-2.5-flash',
'gemini-2.5-exp': 'gemini-2.5',
@@ -766,6 +1241,110 @@ describe('Grok Model Tests - Pricing', () => {
});
});
describe('GLM Model Tests', () => {
it('should return expected value keys for GLM models', () => {
expect(getValueKey('glm-4.6')).toBe('glm-4.6');
expect(getValueKey('glm-4.5')).toBe('glm-4.5');
expect(getValueKey('glm-4.5v')).toBe('glm-4.5v');
expect(getValueKey('glm-4.5-air')).toBe('glm-4.5-air');
expect(getValueKey('glm-4-32b')).toBe('glm-4-32b');
expect(getValueKey('glm-4')).toBe('glm-4');
expect(getValueKey('glm4')).toBe('glm4');
});
it('should match GLM model variations with provider prefixes', () => {
expect(getValueKey('z-ai/glm-4.6')).toBe('glm-4.6');
expect(getValueKey('z-ai/glm-4.5')).toBe('glm-4.5');
expect(getValueKey('z-ai/glm-4.5-air')).toBe('glm-4.5-air');
expect(getValueKey('z-ai/glm-4.5v')).toBe('glm-4.5v');
expect(getValueKey('z-ai/glm-4-32b')).toBe('glm-4-32b');
expect(getValueKey('zai/glm-4.6')).toBe('glm-4.6');
expect(getValueKey('zai/glm-4.5')).toBe('glm-4.5');
expect(getValueKey('zai/glm-4.5-air')).toBe('glm-4.5-air');
expect(getValueKey('zai/glm-4.5v')).toBe('glm-4.5v');
expect(getValueKey('zai-org/GLM-4.6')).toBe('glm-4.6');
expect(getValueKey('zai-org/GLM-4.5')).toBe('glm-4.5');
expect(getValueKey('zai-org/GLM-4.5-Air')).toBe('glm-4.5-air');
expect(getValueKey('zai-org/GLM-4.5V')).toBe('glm-4.5v');
expect(getValueKey('zai-org/GLM-4-32B-0414')).toBe('glm-4-32b');
});
it('should match GLM model variations with suffixes', () => {
expect(getValueKey('glm-4.6-fp8')).toBe('glm-4.6');
expect(getValueKey('zai-org/GLM-4.6-FP8')).toBe('glm-4.6');
expect(getValueKey('zai-org/GLM-4.5-Air-FP8')).toBe('glm-4.5-air');
});
it('should prioritize more specific GLM model patterns', () => {
expect(getValueKey('glm-4.5-air-something')).toBe('glm-4.5-air');
expect(getValueKey('glm-4.5-something')).toBe('glm-4.5');
expect(getValueKey('glm-4.5v-something')).toBe('glm-4.5v');
});
it('should return correct multipliers for all GLM models', () => {
expect(getMultiplier({ model: 'glm-4.6', tokenType: 'prompt' })).toBe(
tokenValues['glm-4.6'].prompt,
);
expect(getMultiplier({ model: 'glm-4.6', tokenType: 'completion' })).toBe(
tokenValues['glm-4.6'].completion,
);
expect(getMultiplier({ model: 'glm-4.5v', tokenType: 'prompt' })).toBe(
tokenValues['glm-4.5v'].prompt,
);
expect(getMultiplier({ model: 'glm-4.5v', tokenType: 'completion' })).toBe(
tokenValues['glm-4.5v'].completion,
);
expect(getMultiplier({ model: 'glm-4.5-air', tokenType: 'prompt' })).toBe(
tokenValues['glm-4.5-air'].prompt,
);
expect(getMultiplier({ model: 'glm-4.5-air', tokenType: 'completion' })).toBe(
tokenValues['glm-4.5-air'].completion,
);
expect(getMultiplier({ model: 'glm-4.5', tokenType: 'prompt' })).toBe(
tokenValues['glm-4.5'].prompt,
);
expect(getMultiplier({ model: 'glm-4.5', tokenType: 'completion' })).toBe(
tokenValues['glm-4.5'].completion,
);
expect(getMultiplier({ model: 'glm-4-32b', tokenType: 'prompt' })).toBe(
tokenValues['glm-4-32b'].prompt,
);
expect(getMultiplier({ model: 'glm-4-32b', tokenType: 'completion' })).toBe(
tokenValues['glm-4-32b'].completion,
);
expect(getMultiplier({ model: 'glm-4', tokenType: 'prompt' })).toBe(
tokenValues['glm-4'].prompt,
);
expect(getMultiplier({ model: 'glm-4', tokenType: 'completion' })).toBe(
tokenValues['glm-4'].completion,
);
expect(getMultiplier({ model: 'glm4', tokenType: 'prompt' })).toBe(tokenValues['glm4'].prompt);
expect(getMultiplier({ model: 'glm4', tokenType: 'completion' })).toBe(
tokenValues['glm4'].completion,
);
});
it('should return correct multipliers for GLM models with provider prefixes', () => {
expect(getMultiplier({ model: 'z-ai/glm-4.6', tokenType: 'prompt' })).toBe(
tokenValues['glm-4.6'].prompt,
);
expect(getMultiplier({ model: 'zai/glm-4.5-air', tokenType: 'completion' })).toBe(
tokenValues['glm-4.5-air'].completion,
);
expect(getMultiplier({ model: 'zai-org/GLM-4.5V', tokenType: 'prompt' })).toBe(
tokenValues['glm-4.5v'].prompt,
);
});
});
describe('Claude Model Tests', () => {
it('should return correct prompt and completion rates for Claude 4 models', () => {
expect(getMultiplier({ model: 'claude-sonnet-4', tokenType: 'prompt' })).toBe(
@@ -782,6 +1361,37 @@ describe('Claude Model Tests', () => {
);
});
it('should return correct prompt and completion rates for Claude Haiku 4.5', () => {
expect(getMultiplier({ model: 'claude-haiku-4-5', tokenType: 'prompt' })).toBe(
tokenValues['claude-haiku-4-5'].prompt,
);
expect(getMultiplier({ model: 'claude-haiku-4-5', tokenType: 'completion' })).toBe(
tokenValues['claude-haiku-4-5'].completion,
);
});
it('should handle Claude Haiku 4.5 model name variations', () => {
const modelVariations = [
'claude-haiku-4-5',
'claude-haiku-4-5-20250420',
'claude-haiku-4-5-latest',
'anthropic/claude-haiku-4-5',
'claude-haiku-4-5/anthropic',
'claude-haiku-4-5-preview',
];
modelVariations.forEach((model) => {
const valueKey = getValueKey(model);
expect(valueKey).toBe('claude-haiku-4-5');
expect(getMultiplier({ model, tokenType: 'prompt' })).toBe(
tokenValues['claude-haiku-4-5'].prompt,
);
expect(getMultiplier({ model, tokenType: 'completion' })).toBe(
tokenValues['claude-haiku-4-5'].completion,
);
});
});
it('should handle Claude 4 model name variations with different prefixes and suffixes', () => {
const modelVariations = [
'claude-sonnet-4',
@@ -859,3 +1469,119 @@ describe('Claude Model Tests', () => {
});
});
});
describe('tokens.ts and tx.js sync validation', () => {
it('should resolve all models in maxTokensMap to pricing via getValueKey', () => {
const tokensKeys = Object.keys(maxTokensMap[EModelEndpoint.openAI]);
const txKeys = Object.keys(tokenValues);
const unresolved = [];
tokensKeys.forEach((key) => {
// Skip legacy token size mappings (e.g., '4k', '8k', '16k', '32k')
if (/^\d+k$/.test(key)) return;
// Skip generic pattern keys (end with '-' or ':')
if (key.endsWith('-') || key.endsWith(':')) return;
// Try to resolve via getValueKey
const resolvedKey = getValueKey(key);
// If it resolves and the resolved key has pricing, success
if (resolvedKey && txKeys.includes(resolvedKey)) return;
// If it resolves to a legacy key (4k, 8k, etc), also OK
if (resolvedKey && /^\d+k$/.test(resolvedKey)) return;
// If we get here, this model can't get pricing - flag it
unresolved.push({
key,
resolvedKey: resolvedKey || 'undefined',
context: maxTokensMap[EModelEndpoint.openAI][key],
});
});
if (unresolved.length > 0) {
console.log('\nModels that cannot resolve to pricing via getValueKey:');
unresolved.forEach(({ key, resolvedKey, context }) => {
console.log(` - '${key}' → '${resolvedKey}' (context: ${context})`);
});
}
expect(unresolved).toEqual([]);
});
it('should not have redundant dated variants with same pricing and context as base model', () => {
const txKeys = Object.keys(tokenValues);
const redundant = [];
txKeys.forEach((key) => {
// Check if this is a dated variant (ends with -YYYY-MM-DD)
if (key.match(/.*-\d{4}-\d{2}-\d{2}$/)) {
const baseKey = key.replace(/-\d{4}-\d{2}-\d{2}$/, '');
if (txKeys.includes(baseKey)) {
const variantPricing = tokenValues[key];
const basePricing = tokenValues[baseKey];
const variantContext = maxTokensMap[EModelEndpoint.openAI][key];
const baseContext = maxTokensMap[EModelEndpoint.openAI][baseKey];
const samePricing =
variantPricing.prompt === basePricing.prompt &&
variantPricing.completion === basePricing.completion;
const sameContext = variantContext === baseContext;
if (samePricing && sameContext) {
redundant.push({
key,
baseKey,
pricing: `${variantPricing.prompt}/${variantPricing.completion}`,
context: variantContext,
});
}
}
}
});
if (redundant.length > 0) {
console.log('\nRedundant dated variants found (same pricing and context as base):');
redundant.forEach(({ key, baseKey, pricing, context }) => {
console.log(` - '${key}' → '${baseKey}' (pricing: ${pricing}, context: ${context})`);
console.log(` Can be removed - pattern matching will handle it`);
});
}
expect(redundant).toEqual([]);
});
it('should have context windows in tokens.ts for all models with pricing in tx.js (openAI catch-all)', () => {
const txKeys = Object.keys(tokenValues);
const missingContext = [];
txKeys.forEach((key) => {
// Skip legacy token size mappings (4k, 8k, 16k, 32k)
if (/^\d+k$/.test(key)) return;
// Check if this model has a context window defined
const context = maxTokensMap[EModelEndpoint.openAI][key];
if (!context) {
const pricing = tokenValues[key];
missingContext.push({
key,
pricing: `${pricing.prompt}/${pricing.completion}`,
});
}
});
if (missingContext.length > 0) {
console.log('\nModels with pricing but missing context in tokens.ts:');
missingContext.forEach(({ key, pricing }) => {
console.log(` - '${key}' (pricing: ${pricing})`);
console.log(` Add to tokens.ts openAIModels/bedrockModels/etc.`);
});
}
expect(missingContext).toEqual([]);
});
});

View File

@@ -1,6 +1,6 @@
{
"name": "@librechat/backend",
"version": "v0.8.0-rc4",
"version": "v0.8.1-rc1",
"description": "",
"scripts": {
"start": "echo 'please run this from the root directory'",
@@ -47,9 +47,8 @@
"@langchain/core": "^0.3.62",
"@langchain/google-genai": "^0.2.13",
"@langchain/google-vertexai": "^0.2.13",
"@langchain/openai": "^0.5.18",
"@langchain/textsplitters": "^0.1.0",
"@librechat/agents": "^2.4.79",
"@librechat/agents": "^2.4.90",
"@librechat/api": "*",
"@librechat/data-schemas": "*",
"@microsoft/microsoft-graph-client": "^3.0.7",
@@ -94,7 +93,7 @@
"multer": "^2.0.2",
"nanoid": "^3.3.7",
"node-fetch": "^2.7.0",
"nodemailer": "^6.9.15",
"nodemailer": "^7.0.9",
"ollama": "^0.5.0",
"openai": "^5.10.1",
"openid-client": "^6.5.0",

View File

@@ -1,8 +1,8 @@
const cookies = require('cookie');
const jwt = require('jsonwebtoken');
const openIdClient = require('openid-client');
const { isEnabled } = require('@librechat/api');
const { logger } = require('@librechat/data-schemas');
const { isEnabled, findOpenIDUser } = require('@librechat/api');
const {
requestPasswordReset,
setOpenIDAuthTokens,
@@ -11,8 +11,9 @@ const {
registerUser,
} = require('~/server/services/AuthService');
const { findUser, getUserById, deleteAllUserSessions, findSession } = require('~/models');
const { getOpenIdConfig } = require('~/strategies');
const { getGraphApiToken } = require('~/server/services/GraphTokenService');
const { getOAuthReconnectionManager } = require('~/config');
const { getOpenIdConfig } = require('~/strategies');
const registrationController = async (req, res) => {
try {
@@ -71,8 +72,14 @@ const refreshController = async (req, res) => {
const openIdConfig = getOpenIdConfig();
const tokenset = await openIdClient.refreshTokenGrant(openIdConfig, refreshToken);
const claims = tokenset.claims();
const user = await findUser({ email: claims.email });
if (!user) {
const { user, error } = await findOpenIDUser({
findUser,
email: claims.email,
openidId: claims.sub,
idOnTheSource: claims.oid,
strategyName: 'refreshController',
});
if (error || !user) {
return res.status(401).redirect('/login');
}
const token = setOpenIDAuthTokens(tokenset, res, user._id.toString());
@@ -96,14 +103,29 @@ const refreshController = async (req, res) => {
return res.status(200).send({ token, user });
}
// Find the session with the hashed refresh token
const session = await findSession({
userId: userId,
refreshToken: refreshToken,
});
/** Session with the hashed refresh token */
const session = await findSession(
{
userId: userId,
refreshToken: refreshToken,
},
{ lean: false },
);
if (session && session.expiration > new Date()) {
const token = await setAuthTokens(userId, res, session._id);
const token = await setAuthTokens(userId, res, session);
// trigger OAuth MCP server reconnection asynchronously (best effort)
try {
void getOAuthReconnectionManager()
.reconnectServers(userId)
.catch((err) => {
logger.error('[refreshController] Error reconnecting OAuth MCP servers:', err);
});
} catch (err) {
logger.warn(`[refreshController] Cannot attempt OAuth MCP servers reconnection:`, err);
}
res.status(200).send({ token, user });
} else if (req?.query?.retry) {
// Retrying from a refresh token request that failed (401)
@@ -114,7 +136,7 @@ const refreshController = async (req, res) => {
res.status(401).send('Refresh token expired or not found for this user');
}
} catch (err) {
logger.error(`[refreshController] Refresh token: ${refreshToken}`, err);
logger.error(`[refreshController] Invalid refresh token:`, err);
res.status(403).send('Invalid refresh token');
}
};

View File

@@ -1,7 +1,7 @@
const { logger } = require('@librechat/data-schemas');
const { CacheKeys } = require('librechat-data-provider');
const { loadDefaultModels, loadConfigModels } = require('~/server/services/Config');
const { getLogStores } = require('~/cache');
const { logger } = require('~/config');
/**
* @param {ServerRequest} req

View File

@@ -1,16 +1,9 @@
const { logger } = require('@librechat/data-schemas');
const { CacheKeys, Constants } = require('librechat-data-provider');
const {
getToolkitKey,
checkPluginAuth,
filterUniquePlugins,
convertMCPToolToPlugin,
convertMCPToolsToPlugins,
} = require('@librechat/api');
const { getCachedTools, setCachedTools, mergeUserTools } = require('~/server/services/Config');
const { CacheKeys } = require('librechat-data-provider');
const { getToolkitKey, checkPluginAuth, filterUniquePlugins } = require('@librechat/api');
const { getCachedTools, setCachedTools } = require('~/server/services/Config');
const { availableTools, toolkits } = require('~/app/clients/tools');
const { getAppConfig } = require('~/server/services/Config');
const { getMCPManager } = require('~/config');
const { getLogStores } = require('~/cache');
const getAvailablePluginsController = async (req, res) => {
@@ -72,63 +65,27 @@ const getAvailableTools = async (req, res) => {
}
const cache = getLogStores(CacheKeys.CONFIG_STORE);
const cachedToolsArray = await cache.get(CacheKeys.TOOLS);
const cachedUserTools = await getCachedTools({ userId });
const appConfig = req.config ?? (await getAppConfig({ role: req.user?.role }));
/** @type {TPlugin[]} */
let mcpPlugins;
if (appConfig?.mcpConfig) {
const mcpManager = getMCPManager();
mcpPlugins =
cachedUserTools != null
? convertMCPToolsToPlugins({ functionTools: cachedUserTools, mcpManager })
: undefined;
}
if (
cachedToolsArray != null &&
(appConfig?.mcpConfig != null ? mcpPlugins != null && mcpPlugins.length > 0 : true)
) {
const dedupedTools = filterUniquePlugins([...(mcpPlugins ?? []), ...cachedToolsArray]);
res.status(200).json(dedupedTools);
// Return early if we have cached tools
if (cachedToolsArray != null) {
res.status(200).json(cachedToolsArray);
return;
}
/** @type {Record<string, FunctionTool> | null} Get tool definitions to filter which tools are actually available */
let toolDefinitions = await getCachedTools({ includeGlobal: true });
let prelimCachedTools;
let toolDefinitions = await getCachedTools();
if (toolDefinitions == null && appConfig?.availableTools != null) {
logger.warn('[getAvailableTools] Tool cache was empty, re-initializing from app config');
await setCachedTools(appConfig.availableTools);
toolDefinitions = appConfig.availableTools;
}
/** @type {import('@librechat/api').LCManifestTool[]} */
let pluginManifest = availableTools;
if (appConfig?.mcpConfig != null) {
try {
const mcpManager = getMCPManager();
const mcpTools = await mcpManager.getAllToolFunctions(userId);
prelimCachedTools = prelimCachedTools ?? {};
for (const [toolKey, toolData] of Object.entries(mcpTools)) {
const plugin = convertMCPToolToPlugin({
toolKey,
toolData,
mcpManager,
});
if (plugin) {
pluginManifest.push(plugin);
}
prelimCachedTools[toolKey] = toolData;
}
await mergeUserTools({ userId, cachedUserTools, userTools: prelimCachedTools });
} catch (error) {
logger.error(
'[getAvailableTools] Error loading MCP Tools, servers may still be initializing:',
error,
);
}
} else if (prelimCachedTools != null) {
await setCachedTools(prelimCachedTools, { isGlobal: true });
}
/** @type {TPlugin[]} Deduplicate and authenticate plugins */
const uniquePlugins = filterUniquePlugins(pluginManifest);
const authenticatedPlugins = uniquePlugins.map((plugin) => {
@@ -139,13 +96,13 @@ const getAvailableTools = async (req, res) => {
}
});
/** Filter plugins based on availability and add MCP-specific auth config */
/** Filter plugins based on availability */
const toolsOutput = [];
for (const plugin of authenticatedPlugins) {
const isToolDefined = toolDefinitions[plugin.pluginKey] !== undefined;
const isToolDefined = toolDefinitions?.[plugin.pluginKey] !== undefined;
const isToolkit =
plugin.toolkit === true &&
Object.keys(toolDefinitions).some(
Object.keys(toolDefinitions ?? {}).some(
(key) => getToolkitKey({ toolkits, toolName: key }) === plugin.pluginKey,
);
@@ -153,39 +110,13 @@ const getAvailableTools = async (req, res) => {
continue;
}
const toolToAdd = { ...plugin };
if (plugin.pluginKey.includes(Constants.mcp_delimiter)) {
const parts = plugin.pluginKey.split(Constants.mcp_delimiter);
const serverName = parts[parts.length - 1];
const serverConfig = appConfig?.mcpConfig?.[serverName];
if (serverConfig?.customUserVars) {
const customVarKeys = Object.keys(serverConfig.customUserVars);
if (customVarKeys.length === 0) {
toolToAdd.authConfig = [];
toolToAdd.authenticated = true;
} else {
toolToAdd.authConfig = Object.entries(serverConfig.customUserVars).map(
([key, value]) => ({
authField: key,
label: value.title || key,
description: value.description || '',
}),
);
toolToAdd.authenticated = false;
}
}
}
toolsOutput.push(toolToAdd);
toolsOutput.push(plugin);
}
const finalTools = filterUniquePlugins(toolsOutput);
await cache.set(CacheKeys.TOOLS, finalTools);
const dedupedTools = filterUniquePlugins([...(mcpPlugins ?? []), ...finalTools]);
res.status(200).json(dedupedTools);
res.status(200).json(finalTools);
} catch (error) {
logger.error('[getAvailableTools]', error);
res.status(500).json({ message: error.message });

View File

@@ -1,4 +1,3 @@
const { Constants } = require('librechat-data-provider');
const { getCachedTools, getAppConfig } = require('~/server/services/Config');
const { getLogStores } = require('~/cache');
@@ -17,18 +16,10 @@ jest.mock('~/server/services/Config', () => ({
includedTools: [],
}),
setCachedTools: jest.fn(),
mergeUserTools: jest.fn(),
}));
// loadAndFormatTools mock removed - no longer used in PluginController
jest.mock('~/config', () => ({
getMCPManager: jest.fn(() => ({
getAllToolFunctions: jest.fn().mockResolvedValue({}),
getRawConfig: jest.fn().mockReturnValue({}),
})),
getFlowStateManager: jest.fn(),
}));
// getMCPManager mock removed - no longer used in PluginController
jest.mock('~/app/clients/tools', () => ({
availableTools: [],
@@ -159,52 +150,6 @@ describe('PluginController', () => {
});
describe('getAvailableTools', () => {
it('should use convertMCPToolsToPlugins for user-specific MCP tools', async () => {
const mockUserTools = {
[`tool1${Constants.mcp_delimiter}server1`]: {
type: 'function',
function: {
name: `tool1${Constants.mcp_delimiter}server1`,
description: 'Tool 1',
parameters: { type: 'object', properties: {} },
},
},
};
mockCache.get.mockResolvedValue(null);
getCachedTools.mockResolvedValueOnce(mockUserTools);
mockReq.config = {
mcpConfig: {
server1: {},
},
paths: { structuredTools: '/mock/path' },
};
// Mock MCP manager to return empty tools initially (since getAllToolFunctions is called)
const mockMCPManager = {
getAllToolFunctions: jest.fn().mockResolvedValue({}),
getRawConfig: jest.fn().mockReturnValue({}),
};
require('~/config').getMCPManager.mockReturnValue(mockMCPManager);
// Mock second call to return tool definitions (includeGlobal: true)
getCachedTools.mockResolvedValueOnce(mockUserTools);
await getAvailableTools(mockReq, mockRes);
expect(mockRes.status).toHaveBeenCalledWith(200);
const responseData = mockRes.json.mock.calls[0][0];
expect(responseData).toBeDefined();
expect(Array.isArray(responseData)).toBe(true);
expect(responseData.length).toBeGreaterThan(0);
const convertedTool = responseData.find(
(tool) => tool.pluginKey === `tool1${Constants.mcp_delimiter}server1`,
);
expect(convertedTool).toBeDefined();
// The real convertMCPToolsToPlugins extracts the name from the delimiter
expect(convertedTool.name).toBe('tool1');
});
it('should use filterUniquePlugins to deduplicate combined tools', async () => {
const mockUserTools = {
'user-tool': {
@@ -229,9 +174,6 @@ describe('PluginController', () => {
paths: { structuredTools: '/mock/path' },
};
// Mock second call to return tool definitions
getCachedTools.mockResolvedValueOnce(mockUserTools);
await getAvailableTools(mockReq, mockRes);
expect(mockRes.status).toHaveBeenCalledWith(200);
@@ -254,14 +196,7 @@ describe('PluginController', () => {
require('~/app/clients/tools').availableTools.push(mockPlugin);
mockCache.get.mockResolvedValue(null);
// First call returns null for user tools
getCachedTools.mockResolvedValueOnce(null);
mockReq.config = {
mcpConfig: null,
paths: { structuredTools: '/mock/path' },
};
// Second call (with includeGlobal: true) returns the tool definitions
// getCachedTools returns the tool definitions
getCachedTools.mockResolvedValueOnce({
tool1: {
type: 'function',
@@ -272,6 +207,10 @@ describe('PluginController', () => {
},
},
});
mockReq.config = {
mcpConfig: null,
paths: { structuredTools: '/mock/path' },
};
await getAvailableTools(mockReq, mockRes);
@@ -302,14 +241,7 @@ describe('PluginController', () => {
});
mockCache.get.mockResolvedValue(null);
// First call returns null for user tools
getCachedTools.mockResolvedValueOnce(null);
mockReq.config = {
mcpConfig: null,
paths: { structuredTools: '/mock/path' },
};
// Second call (with includeGlobal: true) returns the tool definitions
// getCachedTools returns the tool definitions
getCachedTools.mockResolvedValueOnce({
toolkit1_function: {
type: 'function',
@@ -320,6 +252,10 @@ describe('PluginController', () => {
},
},
});
mockReq.config = {
mcpConfig: null,
paths: { structuredTools: '/mock/path' },
};
await getAvailableTools(mockReq, mockRes);
@@ -331,126 +267,7 @@ describe('PluginController', () => {
});
});
describe('plugin.icon behavior', () => {
const callGetAvailableToolsWithMCPServer = async (serverConfig) => {
mockCache.get.mockResolvedValue(null);
const functionTools = {
[`test-tool${Constants.mcp_delimiter}test-server`]: {
type: 'function',
function: {
name: `test-tool${Constants.mcp_delimiter}test-server`,
description: 'A test tool',
parameters: { type: 'object', properties: {} },
},
},
};
// Mock the MCP manager to return tools and server config
const mockMCPManager = {
getAllToolFunctions: jest.fn().mockResolvedValue(functionTools),
getRawConfig: jest.fn().mockReturnValue(serverConfig),
};
require('~/config').getMCPManager.mockReturnValue(mockMCPManager);
// First call returns empty user tools
getCachedTools.mockResolvedValueOnce({});
// Mock getAppConfig to return the mcpConfig
mockReq.config = {
mcpConfig: {
'test-server': serverConfig,
},
};
// Second call (with includeGlobal: true) returns the tool definitions
getCachedTools.mockResolvedValueOnce(functionTools);
await getAvailableTools(mockReq, mockRes);
const responseData = mockRes.json.mock.calls[0][0];
return responseData.find(
(tool) => tool.pluginKey === `test-tool${Constants.mcp_delimiter}test-server`,
);
};
it('should set plugin.icon when iconPath is defined', async () => {
const serverConfig = {
iconPath: '/path/to/icon.png',
};
const testTool = await callGetAvailableToolsWithMCPServer(serverConfig);
expect(testTool.icon).toBe('/path/to/icon.png');
});
it('should set plugin.icon to undefined when iconPath is not defined', async () => {
const serverConfig = {};
const testTool = await callGetAvailableToolsWithMCPServer(serverConfig);
expect(testTool.icon).toBeUndefined();
});
});
describe('helper function integration', () => {
it('should properly handle MCP tools with custom user variables', async () => {
const appConfig = {
mcpConfig: {
'test-server': {
customUserVars: {
API_KEY: { title: 'API Key', description: 'Your API key' },
},
},
},
};
// Mock MCP tools returned by getAllToolFunctions
const mcpToolFunctions = {
[`tool1${Constants.mcp_delimiter}test-server`]: {
type: 'function',
function: {
name: `tool1${Constants.mcp_delimiter}test-server`,
description: 'Tool 1',
parameters: {},
},
},
};
// Mock the MCP manager to return tools
const mockMCPManager = {
getAllToolFunctions: jest.fn().mockResolvedValue(mcpToolFunctions),
getRawConfig: jest.fn().mockReturnValue({
customUserVars: {
API_KEY: { title: 'API Key', description: 'Your API key' },
},
}),
};
require('~/config').getMCPManager.mockReturnValue(mockMCPManager);
mockCache.get.mockResolvedValue(null);
mockReq.config = appConfig;
// First call returns user tools (empty in this case)
getCachedTools.mockResolvedValueOnce({});
// Second call (with includeGlobal: true) returns tool definitions including our MCP tool
getCachedTools.mockResolvedValueOnce(mcpToolFunctions);
await getAvailableTools(mockReq, mockRes);
expect(mockRes.status).toHaveBeenCalledWith(200);
const responseData = mockRes.json.mock.calls[0][0];
expect(Array.isArray(responseData)).toBe(true);
// Find the MCP tool in the response
const mcpTool = responseData.find(
(tool) => tool.pluginKey === `tool1${Constants.mcp_delimiter}test-server`,
);
// The actual implementation adds authConfig and sets authenticated to false when customUserVars exist
expect(mcpTool).toBeDefined();
expect(mcpTool.authConfig).toEqual([
{ authField: 'API_KEY', label: 'API Key', description: 'Your API key' },
]);
expect(mcpTool.authenticated).toBe(false);
});
it('should handle error cases gracefully', async () => {
mockCache.get.mockRejectedValue(new Error('Cache error'));
@@ -472,23 +289,13 @@ describe('PluginController', () => {
it('should handle null cachedTools and cachedUserTools', async () => {
mockCache.get.mockResolvedValue(null);
// First call returns null for user tools
getCachedTools.mockResolvedValueOnce(null);
// getCachedTools returns empty object instead of null
getCachedTools.mockResolvedValueOnce({});
mockReq.config = {
mcpConfig: null,
paths: { structuredTools: '/mock/path' },
};
// Mock MCP manager to return no tools
const mockMCPManager = {
getAllToolFunctions: jest.fn().mockResolvedValue({}),
getRawConfig: jest.fn().mockReturnValue({}),
};
require('~/config').getMCPManager.mockReturnValue(mockMCPManager);
// Second call (with includeGlobal: true) returns empty object instead of null
getCachedTools.mockResolvedValueOnce({});
await getAvailableTools(mockReq, mockRes);
// Should handle null values gracefully
@@ -503,9 +310,9 @@ describe('PluginController', () => {
paths: { structuredTools: '/mock/path' },
};
// Mock getCachedTools to return undefined for both calls
// Mock getCachedTools to return undefined
getCachedTools.mockReset();
getCachedTools.mockResolvedValueOnce(undefined).mockResolvedValueOnce(undefined);
getCachedTools.mockResolvedValueOnce(undefined);
await getAvailableTools(mockReq, mockRes);
@@ -514,51 +321,6 @@ describe('PluginController', () => {
expect(mockRes.json).toHaveBeenCalledWith([]);
});
it('should handle `cachedToolsArray` and `mcpPlugins` both being defined', async () => {
const cachedTools = [{ name: 'CachedTool', pluginKey: 'cached-tool', description: 'Cached' }];
// Use MCP delimiter for the user tool so convertMCPToolsToPlugins works
const userTools = {
[`user-tool${Constants.mcp_delimiter}server1`]: {
type: 'function',
function: {
name: `user-tool${Constants.mcp_delimiter}server1`,
description: 'User tool',
parameters: {},
},
},
};
mockCache.get.mockResolvedValue(cachedTools);
getCachedTools.mockResolvedValueOnce(userTools);
mockReq.config = {
mcpConfig: {
server1: {},
},
paths: { structuredTools: '/mock/path' },
};
// Mock MCP manager to return empty tools initially
const mockMCPManager = {
getAllToolFunctions: jest.fn().mockResolvedValue({}),
getRawConfig: jest.fn().mockReturnValue({}),
};
require('~/config').getMCPManager.mockReturnValue(mockMCPManager);
// The controller expects a second call to getCachedTools
getCachedTools.mockResolvedValueOnce({
'cached-tool': { type: 'function', function: { name: 'cached-tool' } },
[`user-tool${Constants.mcp_delimiter}server1`]:
userTools[`user-tool${Constants.mcp_delimiter}server1`],
});
await getAvailableTools(mockReq, mockRes);
expect(mockRes.status).toHaveBeenCalledWith(200);
const responseData = mockRes.json.mock.calls[0][0];
// Should have both cached and user tools
expect(responseData.length).toBeGreaterThanOrEqual(2);
});
it('should handle empty toolDefinitions object', async () => {
mockCache.get.mockResolvedValue(null);
// Reset getCachedTools to ensure clean state
@@ -569,76 +331,12 @@ describe('PluginController', () => {
// Ensure no plugins are available
require('~/app/clients/tools').availableTools.length = 0;
// Reset MCP manager to default state
const mockMCPManager = {
getAllToolFunctions: jest.fn().mockResolvedValue({}),
getRawConfig: jest.fn().mockReturnValue({}),
};
require('~/config').getMCPManager.mockReturnValue(mockMCPManager);
await getAvailableTools(mockReq, mockRes);
// With empty tool definitions, no tools should be in the final output
expect(mockRes.json).toHaveBeenCalledWith([]);
});
it('should handle MCP tools without customUserVars', async () => {
const appConfig = {
mcpConfig: {
'test-server': {
// No customUserVars defined
},
},
};
const mockUserTools = {
[`tool1${Constants.mcp_delimiter}test-server`]: {
type: 'function',
function: {
name: `tool1${Constants.mcp_delimiter}test-server`,
description: 'Tool 1',
parameters: { type: 'object', properties: {} },
},
},
};
// Mock the MCP manager to return the tools
const mockMCPManager = {
getAllToolFunctions: jest.fn().mockResolvedValue(mockUserTools),
getRawConfig: jest.fn().mockReturnValue({
// No customUserVars defined
}),
};
require('~/config').getMCPManager.mockReturnValue(mockMCPManager);
mockCache.get.mockResolvedValue(null);
mockReq.config = appConfig;
// First call returns empty user tools
getCachedTools.mockResolvedValueOnce({});
// Second call (with includeGlobal: true) returns the tool definitions
getCachedTools.mockResolvedValueOnce(mockUserTools);
// Ensure no plugins in availableTools for clean test
require('~/app/clients/tools').availableTools.length = 0;
await getAvailableTools(mockReq, mockRes);
expect(mockRes.status).toHaveBeenCalledWith(200);
const responseData = mockRes.json.mock.calls[0][0];
expect(Array.isArray(responseData)).toBe(true);
expect(responseData.length).toBeGreaterThan(0);
const mcpTool = responseData.find(
(tool) => tool.pluginKey === `tool1${Constants.mcp_delimiter}test-server`,
);
expect(mcpTool).toBeDefined();
expect(mcpTool.authenticated).toBe(true);
// The actual implementation sets authConfig to empty array when no customUserVars
expect(mcpTool.authConfig).toEqual([]);
});
it('should handle undefined filteredTools and includedTools', async () => {
mockReq.config = {};
mockCache.get.mockResolvedValue(null);
@@ -667,20 +365,129 @@ describe('PluginController', () => {
require('~/app/clients/tools').availableTools.push(mockToolkit);
mockCache.get.mockResolvedValue(null);
// First call returns empty object
// getCachedTools returns empty object to avoid null reference error
getCachedTools.mockResolvedValueOnce({});
mockReq.config = {
mcpConfig: null,
paths: { structuredTools: '/mock/path' },
};
// Second call (with includeGlobal: true) returns empty object to avoid null reference error
getCachedTools.mockResolvedValueOnce({});
await getAvailableTools(mockReq, mockRes);
// Should handle null toolDefinitions gracefully
expect(mockRes.status).toHaveBeenCalledWith(200);
});
it('should handle undefined toolDefinitions when checking isToolDefined (traversaal_search bug)', async () => {
// This test reproduces the bug where toolDefinitions is undefined
// and accessing toolDefinitions[plugin.pluginKey] causes a TypeError
const mockPlugin = {
name: 'Traversaal Search',
pluginKey: 'traversaal_search',
description: 'Search plugin',
};
// Add the plugin to availableTools
require('~/app/clients/tools').availableTools.push(mockPlugin);
mockCache.get.mockResolvedValue(null);
mockReq.config = {
mcpConfig: null,
paths: { structuredTools: '/mock/path' },
};
// CRITICAL: getCachedTools returns undefined
// This is what causes the bug when trying to access toolDefinitions[plugin.pluginKey]
getCachedTools.mockResolvedValueOnce(undefined);
// This should not throw an error with the optional chaining fix
await getAvailableTools(mockReq, mockRes);
// Should handle undefined toolDefinitions gracefully and return empty array
expect(mockRes.status).toHaveBeenCalledWith(200);
expect(mockRes.json).toHaveBeenCalledWith([]);
});
it('should re-initialize tools from appConfig when cache returns null', async () => {
// Setup: Initial state with tools in appConfig
const mockAppTools = {
tool1: {
type: 'function',
function: {
name: 'tool1',
description: 'Tool 1',
parameters: {},
},
},
tool2: {
type: 'function',
function: {
name: 'tool2',
description: 'Tool 2',
parameters: {},
},
},
};
// Add matching plugins to availableTools
require('~/app/clients/tools').availableTools.push(
{ name: 'Tool 1', pluginKey: 'tool1', description: 'Tool 1' },
{ name: 'Tool 2', pluginKey: 'tool2', description: 'Tool 2' },
);
// Simulate cache cleared state (returns null)
mockCache.get.mockResolvedValue(null);
getCachedTools.mockResolvedValueOnce(null); // Global tools (cache cleared)
mockReq.config = {
filteredTools: [],
includedTools: [],
availableTools: mockAppTools,
};
// Mock setCachedTools to verify it's called to re-initialize
const { setCachedTools } = require('~/server/services/Config');
await getAvailableTools(mockReq, mockRes);
// Should have re-initialized the cache with tools from appConfig
expect(setCachedTools).toHaveBeenCalledWith(mockAppTools);
// Should still return tools successfully
expect(mockRes.status).toHaveBeenCalledWith(200);
const responseData = mockRes.json.mock.calls[0][0];
expect(responseData).toHaveLength(2);
expect(responseData.find((t) => t.pluginKey === 'tool1')).toBeDefined();
expect(responseData.find((t) => t.pluginKey === 'tool2')).toBeDefined();
});
it('should handle cache clear without appConfig.availableTools gracefully', async () => {
// Setup: appConfig without availableTools
getAppConfig.mockResolvedValue({
filteredTools: [],
includedTools: [],
// No availableTools property
});
// Clear availableTools array
require('~/app/clients/tools').availableTools.length = 0;
// Cache returns null (cleared state)
mockCache.get.mockResolvedValue(null);
getCachedTools.mockResolvedValueOnce(null); // Global tools (cache cleared)
mockReq.config = {
filteredTools: [],
includedTools: [],
// No availableTools
};
await getAvailableTools(mockReq, mockRes);
// Should handle gracefully without crashing
expect(mockRes.status).toHaveBeenCalledWith(200);
expect(mockRes.json).toHaveBeenCalledWith([]);
});
});
});

View File

@@ -1,37 +1,33 @@
const { logger } = require('@librechat/data-schemas');
const { logger, webSearchKeys } = require('@librechat/data-schemas');
const { Tools, CacheKeys, Constants, FileSources } = require('librechat-data-provider');
const {
webSearchKeys,
extractWebSearchEnvVars,
normalizeHttpError,
MCPOAuthHandler,
MCPTokenStorage,
normalizeHttpError,
extractWebSearchEnvVars,
} = require('@librechat/api');
const {
getFiles,
findToken,
updateUser,
deleteFiles,
deleteConvos,
deletePresets,
deleteMessages,
deleteUserById,
deleteAllSharedLinks,
deleteAllUserSessions,
} = require('~/models');
const { updateUserPluginAuth, deleteUserPluginAuth } = require('~/server/services/PluginService');
const { updateUserPluginsService, deleteUserKey } = require('~/server/services/UserService');
const { verifyEmail, resendVerificationEmail } = require('~/server/services/AuthService');
const { needsRefresh, getNewS3URL } = require('~/server/services/Files/S3/crud');
const { Tools, Constants, FileSources } = require('librechat-data-provider');
const { processDeleteRequest } = require('~/server/services/Files/process');
const { Transaction, Balance, User, Token } = require('~/db/models');
const { getMCPManager, getFlowStateManager } = require('~/config');
const { getAppConfig } = require('~/server/services/Config');
const { deleteToolCalls } = require('~/models/ToolCall');
const { deleteAllSharedLinks } = require('~/models');
const { getMCPManager } = require('~/config');
const { MCPOAuthHandler } = require('@librechat/api');
const { getFlowStateManager } = require('~/config');
const { CacheKeys } = require('librechat-data-provider');
const { getLogStores } = require('~/cache');
const { clearMCPServerTools } = require('~/server/services/Config/mcpToolsCache');
const { findToken } = require('~/models');
const getUserController = async (req, res) => {
const appConfig = await getAppConfig({ role: req.user?.role });
@@ -331,16 +327,23 @@ const maybeUninstallOAuthMCP = async (userId, pluginKey, appConfig) => {
const revocationEndpointAuthMethodsSupported =
serverConfig.oauth?.revocation_endpoint_auth_methods_supported ??
clientMetadata.revocation_endpoint_auth_methods_supported;
const oauthHeaders = serverConfig.oauth_headers ?? {};
if (tokens?.access_token) {
try {
await MCPOAuthHandler.revokeOAuthToken(serverName, tokens.access_token, 'access', {
serverUrl: serverConfig.url,
clientId: clientInfo.client_id,
clientSecret: clientInfo.client_secret ?? '',
revocationEndpoint,
revocationEndpointAuthMethodsSupported,
});
await MCPOAuthHandler.revokeOAuthToken(
serverName,
tokens.access_token,
'access',
{
serverUrl: serverConfig.url,
clientId: clientInfo.client_id,
clientSecret: clientInfo.client_secret ?? '',
revocationEndpoint,
revocationEndpointAuthMethodsSupported,
},
oauthHeaders,
);
} catch (error) {
logger.error(`Error revoking OAuth access token for ${serverName}:`, error);
}
@@ -348,13 +351,19 @@ const maybeUninstallOAuthMCP = async (userId, pluginKey, appConfig) => {
if (tokens?.refresh_token) {
try {
await MCPOAuthHandler.revokeOAuthToken(serverName, tokens.refresh_token, 'refresh', {
serverUrl: serverConfig.url,
clientId: clientInfo.client_id,
clientSecret: clientInfo.client_secret ?? '',
revocationEndpoint,
revocationEndpointAuthMethodsSupported,
});
await MCPOAuthHandler.revokeOAuthToken(
serverName,
tokens.refresh_token,
'refresh',
{
serverUrl: serverConfig.url,
clientId: clientInfo.client_id,
clientSecret: clientInfo.client_secret ?? '',
revocationEndpoint,
revocationEndpointAuthMethodsSupported,
},
oauthHeaders,
);
} catch (error) {
logger.error(`Error revoking OAuth refresh token for ${serverName}:`, error);
}
@@ -375,9 +384,6 @@ const maybeUninstallOAuthMCP = async (userId, pluginKey, appConfig) => {
const flowId = MCPOAuthHandler.generateFlowId(userId, serverName);
await flowManager.deleteFlow(flowId, 'mcp_get_tokens');
await flowManager.deleteFlow(flowId, 'mcp_oauth');
// 6. clear the tools cache for the server
await clearMCPServerTools({ userId, serverName });
};
module.exports = {

View File

@@ -158,7 +158,7 @@ describe('duplicateAgent', () => {
});
});
it('should handle tool_resources.ocr correctly', async () => {
it('should convert `tool_resources.ocr` to `tool_resources.context`', async () => {
const mockAgent = {
id: 'agent_123',
name: 'Test Agent',
@@ -178,7 +178,7 @@ describe('duplicateAgent', () => {
expect(createAgent).toHaveBeenCalledWith(
expect.objectContaining({
tool_resources: {
ocr: { enabled: true, config: 'test' },
context: { enabled: true, config: 'test' },
},
}),
);

View File

@@ -8,6 +8,7 @@ const {
Tokenizer,
checkAccess,
logAxiosError,
sanitizeTitle,
resolveHeaders,
getBalanceConfig,
memoryInstructions,
@@ -211,16 +212,13 @@ class AgentClient extends BaseClient {
* @returns {Promise<Array<Partial<MongoFile>>>}
*/
async addImageURLs(message, attachments) {
const { files, text, image_urls } = await encodeAndFormat(
const { files, image_urls } = await encodeAndFormat(
this.options.req,
attachments,
this.options.agent.provider,
VisionModes.agents,
);
message.image_urls = image_urls.length ? image_urls : undefined;
if (text && text.length) {
message.ocr = text;
}
return files;
}
@@ -248,19 +246,18 @@ class AgentClient extends BaseClient {
if (this.options.attachments) {
const attachments = await this.options.attachments;
const latestMessage = orderedMessages[orderedMessages.length - 1];
if (this.message_file_map) {
this.message_file_map[orderedMessages[orderedMessages.length - 1].messageId] = attachments;
this.message_file_map[latestMessage.messageId] = attachments;
} else {
this.message_file_map = {
[orderedMessages[orderedMessages.length - 1].messageId]: attachments,
[latestMessage.messageId]: attachments,
};
}
const files = await this.addImageURLs(
orderedMessages[orderedMessages.length - 1],
attachments,
);
await this.addFileContextToMessage(latestMessage, attachments);
const files = await this.processAttachments(latestMessage, attachments);
this.options.attachments = files;
}
@@ -280,21 +277,21 @@ class AgentClient extends BaseClient {
assistantName: this.options?.modelLabel,
});
if (message.ocr && i !== orderedMessages.length - 1) {
if (message.fileContext && i !== orderedMessages.length - 1) {
if (typeof formattedMessage.content === 'string') {
formattedMessage.content = message.ocr + '\n' + formattedMessage.content;
formattedMessage.content = message.fileContext + '\n' + formattedMessage.content;
} else {
const textPart = formattedMessage.content.find((part) => part.type === 'text');
textPart
? (textPart.text = message.ocr + '\n' + textPart.text)
: formattedMessage.content.unshift({ type: 'text', text: message.ocr });
? (textPart.text = message.fileContext + '\n' + textPart.text)
: formattedMessage.content.unshift({ type: 'text', text: message.fileContext });
}
} else if (message.ocr && i === orderedMessages.length - 1) {
systemContent = [systemContent, message.ocr].join('\n');
} else if (message.fileContext && i === orderedMessages.length - 1) {
systemContent = [systemContent, message.fileContext].join('\n');
}
const needsTokenCount =
(this.contextStrategy && !orderedMessages[i].tokenCount) || message.ocr;
(this.contextStrategy && !orderedMessages[i].tokenCount) || message.fileContext;
/* If tokens were never counted, or, is a Vision request and the message has files, count again */
if (needsTokenCount || (this.isVisionModel && (message.image_urls || message.files))) {
@@ -779,6 +776,7 @@ class AgentClient extends BaseClient {
const agentsEConfig = appConfig.endpoints?.[EModelEndpoint.agents];
config = {
runName: 'AgentRun',
configurable: {
thread_id: this.conversationId,
last_agent_index: this.agentConfigs?.size ?? 0,
@@ -1116,11 +1114,18 @@ class AgentClient extends BaseClient {
appConfig.endpoints?.[endpoint] ??
titleProviderConfig.customEndpointConfig;
if (!endpointConfig) {
logger.warn(
'[api/server/controllers/agents/client.js #titleConvo] Error getting endpoint config',
logger.debug(
`[api/server/controllers/agents/client.js #titleConvo] No endpoint config for "${endpoint}"`,
);
}
if (endpointConfig?.titleConvo === false) {
logger.debug(
`[api/server/controllers/agents/client.js #titleConvo] Title generation disabled for endpoint "${endpoint}"`,
);
return;
}
if (endpointConfig?.titleEndpoint && endpointConfig.titleEndpoint !== endpoint) {
try {
titleProviderConfig = getProviderConfig({
@@ -1130,7 +1135,7 @@ class AgentClient extends BaseClient {
endpoint = endpointConfig.titleEndpoint;
} catch (error) {
logger.warn(
`[api/server/controllers/agents/client.js #titleConvo] Error getting title endpoint config for ${endpointConfig.titleEndpoint}, falling back to default`,
`[api/server/controllers/agents/client.js #titleConvo] Error getting title endpoint config for "${endpointConfig.titleEndpoint}", falling back to default`,
error,
);
// Fall back to original provider config
@@ -1230,6 +1235,10 @@ class AgentClient extends BaseClient {
handleLLMEnd,
},
],
configurable: {
thread_id: this.conversationId,
user_id: this.user ?? this.options.req.user?.id,
},
},
});
@@ -1267,7 +1276,7 @@ class AgentClient extends BaseClient {
);
});
return titleResult.title;
return sanitizeTitle(titleResult.title);
} catch (err) {
logger.error('[api/server/controllers/agents/client.js #titleConvo] Error', err);
return;

View File

@@ -10,6 +10,10 @@ jest.mock('@librechat/agents', () => ({
}),
}));
jest.mock('@librechat/api', () => ({
...jest.requireActual('@librechat/api'),
}));
describe('AgentClient - titleConvo', () => {
let client;
let mockRun;
@@ -252,6 +256,38 @@ describe('AgentClient - titleConvo', () => {
expect(result).toBe('Generated Title');
});
it('should sanitize the generated title by removing think blocks', async () => {
const titleWithThinkBlock = '<think>reasoning about the title</think> User Hi Greeting';
mockRun.generateTitle.mockResolvedValue({
title: titleWithThinkBlock,
});
const text = 'Test conversation text';
const abortController = new AbortController();
const result = await client.titleConvo({ text, abortController });
// Should remove the <think> block and return only the clean title
expect(result).toBe('User Hi Greeting');
expect(result).not.toContain('<think>');
expect(result).not.toContain('</think>');
});
it('should return fallback title when sanitization results in empty string', async () => {
const titleOnlyThinkBlock = '<think>only reasoning no actual title</think>';
mockRun.generateTitle.mockResolvedValue({
title: titleOnlyThinkBlock,
});
const text = 'Test conversation text';
const abortController = new AbortController();
const result = await client.titleConvo({ text, abortController });
// Should return the fallback title since sanitization would result in empty string
expect(result).toBe('Untitled Conversation');
});
it('should handle errors gracefully and return undefined', async () => {
mockRun.generateTitle.mockRejectedValue(new Error('Title generation failed'));
@@ -263,6 +299,125 @@ describe('AgentClient - titleConvo', () => {
expect(result).toBeUndefined();
});
it('should skip title generation when titleConvo is set to false', async () => {
// Set titleConvo to false in endpoint config
mockReq.config = {
endpoints: {
[EModelEndpoint.openAI]: {
titleConvo: false,
titleModel: 'gpt-3.5-turbo',
titlePrompt: 'Custom title prompt',
titleMethod: 'structured',
titlePromptTemplate: 'Template: {{content}}',
},
},
};
const text = 'Test conversation text';
const abortController = new AbortController();
const result = await client.titleConvo({ text, abortController });
// Should return undefined without generating title
expect(result).toBeUndefined();
// generateTitle should NOT have been called
expect(mockRun.generateTitle).not.toHaveBeenCalled();
// recordCollectedUsage should NOT have been called
expect(client.recordCollectedUsage).not.toHaveBeenCalled();
});
it('should skip title generation when titleConvo is false in all config', async () => {
// Set titleConvo to false in "all" config
mockReq.config = {
endpoints: {
all: {
titleConvo: false,
titleModel: 'gpt-4o-mini',
titlePrompt: 'All config title prompt',
titleMethod: 'completion',
titlePromptTemplate: 'All config template',
},
},
};
const text = 'Test conversation text';
const abortController = new AbortController();
const result = await client.titleConvo({ text, abortController });
// Should return undefined without generating title
expect(result).toBeUndefined();
// generateTitle should NOT have been called
expect(mockRun.generateTitle).not.toHaveBeenCalled();
// recordCollectedUsage should NOT have been called
expect(client.recordCollectedUsage).not.toHaveBeenCalled();
});
it('should skip title generation when titleConvo is false for custom endpoint scenario', async () => {
// This test validates the behavior when customEndpointConfig (retrieved via
// getProviderConfig for custom endpoints) has titleConvo: false.
//
// The code path is:
// 1. endpoints?.all is checked (undefined in this test)
// 2. endpoints?.[endpoint] is checked (our test config)
// 3. Would fall back to titleProviderConfig.customEndpointConfig (for real custom endpoints)
//
// We simulate a custom endpoint scenario using a dynamically named endpoint config
// Create a unique endpoint name that represents a custom endpoint
const customEndpointName = 'customEndpoint';
// Configure the endpoint to have titleConvo: false
// This simulates what would be in customEndpointConfig for a real custom endpoint
mockReq.config = {
endpoints: {
// No 'all' config - so it will check endpoints[endpoint]
// This config represents what customEndpointConfig would contain
[customEndpointName]: {
titleConvo: false,
titleModel: 'custom-model-v1',
titlePrompt: 'Custom endpoint title prompt',
titleMethod: 'completion',
titlePromptTemplate: 'Custom template: {{content}}',
baseURL: 'https://api.custom-llm.com/v1',
apiKey: 'test-custom-key',
// Additional custom endpoint properties
models: {
default: ['custom-model-v1', 'custom-model-v2'],
},
},
},
};
// Set up agent to use our custom endpoint
// Use openAI as base but override with custom endpoint name for this test
mockAgent.endpoint = EModelEndpoint.openAI;
mockAgent.provider = EModelEndpoint.openAI;
// Override the endpoint in the config to point to our custom config
mockReq.config.endpoints[EModelEndpoint.openAI] =
mockReq.config.endpoints[customEndpointName];
delete mockReq.config.endpoints[customEndpointName];
const text = 'Test custom endpoint conversation';
const abortController = new AbortController();
const result = await client.titleConvo({ text, abortController });
// Should return undefined without generating title because titleConvo is false
expect(result).toBeUndefined();
// generateTitle should NOT have been called
expect(mockRun.generateTitle).not.toHaveBeenCalled();
// recordCollectedUsage should NOT have been called
expect(client.recordCollectedUsage).not.toHaveBeenCalled();
});
it('should pass titleEndpoint configuration to generateTitle', async () => {
// Mock the API key just for this test
const originalApiKey = process.env.ANTHROPIC_API_KEY;

View File

@@ -2,7 +2,12 @@ const { z } = require('zod');
const fs = require('fs').promises;
const { nanoid } = require('nanoid');
const { logger } = require('@librechat/data-schemas');
const { agentCreateSchema, agentUpdateSchema } = require('@librechat/api');
const {
agentCreateSchema,
agentUpdateSchema,
mergeAgentOcrConversion,
convertOcrToContextInPlace,
} = require('@librechat/api');
const {
Tools,
Constants,
@@ -66,7 +71,7 @@ const createAgentHandler = async (req, res) => {
agentData.author = userId;
agentData.tools = [];
const availableTools = await getCachedTools({ includeGlobal: true });
const availableTools = await getCachedTools();
for (const tool of tools) {
if (availableTools[tool]) {
agentData.tools.push(tool);
@@ -198,19 +203,32 @@ const getAgentHandler = async (req, res, expandProperties = false) => {
* @param {object} req.params - Request params
* @param {string} req.params.id - Agent identifier.
* @param {AgentUpdateParams} req.body - The Agent update parameters.
* @returns {Agent} 200 - success response - application/json
* @returns {Promise<Agent>} 200 - success response - application/json
*/
const updateAgentHandler = async (req, res) => {
try {
const id = req.params.id;
const validatedData = agentUpdateSchema.parse(req.body);
const { _id, ...updateData } = removeNullishValues(validatedData);
// Convert OCR to context in incoming updateData
convertOcrToContextInPlace(updateData);
const existingAgent = await getAgent({ id });
if (!existingAgent) {
return res.status(404).json({ error: 'Agent not found' });
}
// Convert legacy OCR tool resource to context format in existing agent
const ocrConversion = mergeAgentOcrConversion(existingAgent, updateData);
if (ocrConversion.tool_resources) {
updateData.tool_resources = ocrConversion.tool_resources;
}
if (ocrConversion.tools) {
updateData.tools = ocrConversion.tools;
}
let updatedAgent =
Object.keys(updateData).length > 0
? await updateAgent({ id }, updateData, {
@@ -255,7 +273,7 @@ const updateAgentHandler = async (req, res) => {
* @param {object} req - Express Request
* @param {object} req.params - Request params
* @param {string} req.params.id - Agent identifier.
* @returns {Agent} 201 - success response - application/json
* @returns {Promise<Agent>} 201 - success response - application/json
*/
const duplicateAgentHandler = async (req, res) => {
const { id } = req.params;
@@ -288,9 +306,19 @@ const duplicateAgentHandler = async (req, res) => {
hour12: false,
})})`;
if (_tool_resources?.[EToolResources.context]) {
cloneData.tool_resources = {
[EToolResources.context]: _tool_resources[EToolResources.context],
};
}
if (_tool_resources?.[EToolResources.ocr]) {
cloneData.tool_resources = {
[EToolResources.ocr]: _tool_resources[EToolResources.ocr],
/** Legacy conversion from `ocr` to `context` */
[EToolResources.context]: {
...(_tool_resources[EToolResources.context] ?? {}),
..._tool_resources[EToolResources.ocr],
},
};
}
@@ -382,7 +410,7 @@ const duplicateAgentHandler = async (req, res) => {
* @param {object} req - Express Request
* @param {object} req.params - Request params
* @param {string} req.params.id - Agent identifier.
* @returns {Agent} 200 - success response - application/json
* @returns {Promise<Agent>} 200 - success response - application/json
*/
const deleteAgentHandler = async (req, res) => {
try {
@@ -484,7 +512,7 @@ const getListAgentsHandler = async (req, res) => {
* @param {Express.Multer.File} req.file - The avatar image file.
* @param {object} req.body - Request body
* @param {string} [req.body.avatar] - Optional avatar for the agent's avatar.
* @returns {Object} 200 - success response - application/json
* @returns {Promise<void>} 200 - success response - application/json
*/
const uploadAgentAvatarHandler = async (req, res) => {
try {

View File

@@ -512,6 +512,7 @@ describe('Agent Controllers - Mass Assignment Protection', () => {
mockReq.params.id = existingAgentId;
mockReq.body = {
tool_resources: {
/** Legacy conversion from `ocr` to `context` */
ocr: {
file_ids: ['ocr1', 'ocr2'],
},
@@ -531,7 +532,8 @@ describe('Agent Controllers - Mass Assignment Protection', () => {
const updatedAgent = mockRes.json.mock.calls[0][0];
expect(updatedAgent.tool_resources).toBeDefined();
expect(updatedAgent.tool_resources.ocr).toBeDefined();
expect(updatedAgent.tool_resources.ocr).toBeUndefined();
expect(updatedAgent.tool_resources.context).toBeDefined();
expect(updatedAgent.tool_resources.execute_code).toBeDefined();
expect(updatedAgent.tool_resources.invalid_tool).toBeUndefined();
});

View File

@@ -31,7 +31,7 @@ const createAssistant = async (req, res) => {
delete assistantData.conversation_starters;
delete assistantData.append_current_datetime;
const toolDefinitions = await getCachedTools({ includeGlobal: true });
const toolDefinitions = await getCachedTools();
assistantData.tools = tools
.map((tool) => {
@@ -136,7 +136,7 @@ const patchAssistant = async (req, res) => {
...updateData
} = req.body;
const toolDefinitions = await getCachedTools({ includeGlobal: true });
const toolDefinitions = await getCachedTools();
updateData.tools = (updateData.tools ?? [])
.map((tool) => {

View File

@@ -28,7 +28,7 @@ const createAssistant = async (req, res) => {
delete assistantData.conversation_starters;
delete assistantData.append_current_datetime;
const toolDefinitions = await getCachedTools({ includeGlobal: true });
const toolDefinitions = await getCachedTools();
assistantData.tools = tools
.map((tool) => {
@@ -125,7 +125,7 @@ const updateAssistant = async ({ req, openai, assistant_id, updateData }) => {
let hasFileSearch = false;
for (const tool of updateData.tools ?? []) {
const toolDefinitions = await getCachedTools({ includeGlobal: true });
const toolDefinitions = await getCachedTools();
let actualTool = typeof tool === 'string' ? toolDefinitions[tool] : tool;
if (!actualTool && manifestToolMap[tool] && manifestToolMap[tool].toolkit === true) {

View File

@@ -1,6 +1,6 @@
const { logger } = require('@librechat/data-schemas');
const { generate2FATempToken } = require('~/server/services/twoFactorService');
const { setAuthTokens } = require('~/server/services/AuthService');
const { logger } = require('~/config');
const loginController = async (req, res) => {
try {

View File

@@ -1,8 +1,8 @@
const cookies = require('cookie');
const { getOpenIdConfig } = require('~/strategies');
const { isEnabled } = require('@librechat/api');
const { logger } = require('@librechat/data-schemas');
const { logoutUser } = require('~/server/services/AuthService');
const { isEnabled } = require('~/server/utils');
const { logger } = require('~/config');
const { getOpenIdConfig } = require('~/strategies');
const logoutController = async (req, res) => {
const refreshToken = req.headers.cookie ? cookies.parse(req.headers.cookie).refreshToken : null;

View File

@@ -0,0 +1,126 @@
/**
* MCP Tools Controller
* Handles MCP-specific tool endpoints, decoupled from regular LibreChat tools
*/
const { logger } = require('@librechat/data-schemas');
const { Constants } = require('librechat-data-provider');
const {
cacheMCPServerTools,
getMCPServerTools,
getAppConfig,
} = require('~/server/services/Config');
const { getMCPManager } = require('~/config');
/**
* Get all MCP tools available to the user
*/
const getMCPTools = async (req, res) => {
try {
const userId = req.user?.id;
if (!userId) {
logger.warn('[getMCPTools] User ID not found in request');
return res.status(401).json({ message: 'Unauthorized' });
}
const appConfig = req.config ?? (await getAppConfig({ role: req.user?.role }));
if (!appConfig?.mcpConfig) {
return res.status(200).json({ servers: {} });
}
const mcpManager = getMCPManager();
const configuredServers = Object.keys(appConfig.mcpConfig);
const mcpServers = {};
const cachePromises = configuredServers.map((serverName) =>
getMCPServerTools(serverName).then((tools) => ({ serverName, tools })),
);
const cacheResults = await Promise.all(cachePromises);
const serverToolsMap = new Map();
for (const { serverName, tools } of cacheResults) {
if (tools) {
serverToolsMap.set(serverName, tools);
continue;
}
const serverTools = await mcpManager.getServerToolFunctions(userId, serverName);
if (!serverTools) {
logger.debug(`[getMCPTools] No tools found for server ${serverName}`);
continue;
}
serverToolsMap.set(serverName, serverTools);
if (Object.keys(serverTools).length > 0) {
// Cache asynchronously without blocking
cacheMCPServerTools({ serverName, serverTools }).catch((err) =>
logger.error(`[getMCPTools] Failed to cache tools for ${serverName}:`, err),
);
}
}
// Process each configured server
for (const serverName of configuredServers) {
try {
const serverTools = serverToolsMap.get(serverName);
// Get server config once
const serverConfig = appConfig.mcpConfig[serverName];
const rawServerConfig = mcpManager.getRawConfig(serverName);
// Initialize server object with all server-level data
const server = {
name: serverName,
icon: rawServerConfig?.iconPath || '',
authenticated: true,
authConfig: [],
tools: [],
};
// Set authentication config once for the server
if (serverConfig?.customUserVars) {
const customVarKeys = Object.keys(serverConfig.customUserVars);
if (customVarKeys.length > 0) {
server.authConfig = Object.entries(serverConfig.customUserVars).map(([key, value]) => ({
authField: key,
label: value.title || key,
description: value.description || '',
}));
server.authenticated = false;
}
}
// Process tools efficiently - no need for convertMCPToolToPlugin
if (serverTools) {
for (const [toolKey, toolData] of Object.entries(serverTools)) {
if (!toolData.function || !toolKey.includes(Constants.mcp_delimiter)) {
continue;
}
const toolName = toolKey.split(Constants.mcp_delimiter)[0];
server.tools.push({
name: toolName,
pluginKey: toolKey,
description: toolData.function.description || '',
});
}
}
// Only add server if it has tools or is configured
if (server.tools.length > 0 || serverConfig) {
mcpServers[serverName] = server;
}
} catch (error) {
logger.error(`[getMCPTools] Error loading tools for server ${serverName}:`, error);
}
}
res.status(200).json({ servers: mcpServers });
} catch (error) {
logger.error('[getMCPTools]', error);
res.status(500).json({ message: error.message });
}
};
module.exports = {
getMCPTools,
};

View File

@@ -10,8 +10,14 @@ const compression = require('compression');
const cookieParser = require('cookie-parser');
const { logger } = require('@librechat/data-schemas');
const mongoSanitize = require('express-mongo-sanitize');
const { isEnabled, ErrorController } = require('@librechat/api');
const {
isEnabled,
ErrorController,
performStartupChecks,
initializeFileStorage,
} = require('@librechat/api');
const { connectDb, indexSync } = require('~/db');
const initializeOAuthReconnectManager = require('./services/initializeOAuthReconnectManager');
const createValidateImageRequest = require('./middleware/validateImageRequest');
const { jwtLogin, ldapLogin, passportLogin } = require('~/strategies');
const { updateInterfacePermissions } = require('~/models/interface');
@@ -48,9 +54,11 @@ const startServer = async () => {
app.set('trust proxy', trusted_proxy);
await seedDatabase();
const appConfig = await getAppConfig();
initializeFileStorage(appConfig);
await performStartupChecks(appConfig);
await updateInterfacePermissions(appConfig);
const indexPath = path.join(appConfig.paths.dist, 'index.html');
let indexHTML = fs.readFileSync(indexPath, 'utf8');
@@ -154,7 +162,7 @@ const startServer = async () => {
res.send(updatedIndexHtml);
});
app.listen(port, host, () => {
app.listen(port, host, async () => {
if (host === '0.0.0.0') {
logger.info(
`Server listening on all interfaces at port ${port}. Use http://localhost:${port} to access it`,
@@ -163,7 +171,9 @@ const startServer = async () => {
logger.info(`Server listening at http://${host == '0.0.0.0' ? 'localhost' : host}:${port}`);
}
initializeMCPs().then(() => checkMigrations());
await initializeMCPs();
await initializeOAuthReconnectManager();
await checkMigrations();
});
};

View File

@@ -1,7 +1,7 @@
const { logger } = require('@librechat/data-schemas');
const { PermissionBits, hasPermissions, ResourceType } = require('librechat-data-provider');
const { getEffectivePermissions } = require('~/server/services/PermissionService');
const { getAgent } = require('~/models/Agent');
const { getAgents } = require('~/models/Agent');
const { getFiles } = require('~/models/File');
/**
@@ -10,11 +10,12 @@ const { getFiles } = require('~/models/File');
*/
const checkAgentBasedFileAccess = async ({ userId, role, fileId }) => {
try {
// Find agents that have this file in their tool_resources
const agentsWithFile = await getAgent({
/** Agents that have this file in their tool_resources */
const agentsWithFile = await getAgents({
$or: [
{ 'tool_resources.file_search.file_ids': fileId },
{ 'tool_resources.execute_code.file_ids': fileId },
{ 'tool_resources.file_search.file_ids': fileId },
{ 'tool_resources.context.file_ids': fileId },
{ 'tool_resources.ocr.file_ids': fileId },
],
});
@@ -24,7 +25,7 @@ const checkAgentBasedFileAccess = async ({ userId, role, fileId }) => {
}
// Check if user has access to any of these agents
for (const agent of Array.isArray(agentsWithFile) ? agentsWithFile : [agentsWithFile]) {
for (const agent of agentsWithFile) {
// Check if user is the agent author
if (agent.author && agent.author.toString() === userId) {
logger.debug(`[fileAccess] User is author of agent ${agent.id}`);
@@ -83,7 +84,6 @@ const fileAccess = async (req, res, next) => {
});
}
// Get the file
const [file] = await getFiles({ file_id: fileId });
if (!file) {
return res.status(404).json({
@@ -92,20 +92,18 @@ const fileAccess = async (req, res, next) => {
});
}
// Check if user owns the file
if (file.user && file.user.toString() === userId) {
req.fileAccess = { file };
return next();
}
// Check agent-based access (file inherits agent permissions)
/** Agent-based access (file inherits agent permissions) */
const hasAgentAccess = await checkAgentBasedFileAccess({ userId, role: userRole, fileId });
if (hasAgentAccess) {
req.fileAccess = { file };
return next();
}
// No access
logger.warn(`[fileAccess] User ${userId} denied access to file ${fileId}`);
return res.status(403).json({
error: 'Forbidden',

View File

@@ -0,0 +1,483 @@
const mongoose = require('mongoose');
const { ResourceType, PrincipalType, PrincipalModel } = require('librechat-data-provider');
const { MongoMemoryServer } = require('mongodb-memory-server');
const { fileAccess } = require('./fileAccess');
const { User, Role, AclEntry } = require('~/db/models');
const { createAgent } = require('~/models/Agent');
const { createFile } = require('~/models/File');
describe('fileAccess middleware', () => {
let mongoServer;
let req, res, next;
let testUser, otherUser, thirdUser;
beforeAll(async () => {
mongoServer = await MongoMemoryServer.create();
const mongoUri = mongoServer.getUri();
await mongoose.connect(mongoUri);
});
afterAll(async () => {
await mongoose.disconnect();
await mongoServer.stop();
});
beforeEach(async () => {
await mongoose.connection.dropDatabase();
// Create test role
await Role.create({
name: 'test-role',
permissions: {
AGENTS: {
USE: true,
CREATE: true,
SHARED_GLOBAL: false,
},
},
});
// Create test users
testUser = await User.create({
email: 'test@example.com',
name: 'Test User',
username: 'testuser',
role: 'test-role',
});
otherUser = await User.create({
email: 'other@example.com',
name: 'Other User',
username: 'otheruser',
role: 'test-role',
});
thirdUser = await User.create({
email: 'third@example.com',
name: 'Third User',
username: 'thirduser',
role: 'test-role',
});
// Setup request/response objects
req = {
user: { id: testUser._id.toString(), role: testUser.role },
params: {},
};
res = {
status: jest.fn().mockReturnThis(),
json: jest.fn(),
};
next = jest.fn();
jest.clearAllMocks();
});
describe('basic file access', () => {
test('should allow access when user owns the file', async () => {
// Create a file owned by testUser
await createFile({
user: testUser._id.toString(),
file_id: 'file_owned_by_user',
filepath: '/test/file.txt',
filename: 'file.txt',
type: 'text/plain',
size: 100,
});
req.params.file_id = 'file_owned_by_user';
await fileAccess(req, res, next);
expect(next).toHaveBeenCalled();
expect(req.fileAccess).toBeDefined();
expect(req.fileAccess.file).toBeDefined();
expect(res.status).not.toHaveBeenCalled();
});
test('should deny access when user does not own the file and no agent access', async () => {
// Create a file owned by otherUser
await createFile({
user: otherUser._id.toString(),
file_id: 'file_owned_by_other',
filepath: '/test/file.txt',
filename: 'file.txt',
type: 'text/plain',
size: 100,
});
req.params.file_id = 'file_owned_by_other';
await fileAccess(req, res, next);
expect(next).not.toHaveBeenCalled();
expect(res.status).toHaveBeenCalledWith(403);
expect(res.json).toHaveBeenCalledWith({
error: 'Forbidden',
message: 'Insufficient permissions to access this file',
});
});
test('should return 404 when file does not exist', async () => {
req.params.file_id = 'non_existent_file';
await fileAccess(req, res, next);
expect(next).not.toHaveBeenCalled();
expect(res.status).toHaveBeenCalledWith(404);
expect(res.json).toHaveBeenCalledWith({
error: 'Not Found',
message: 'File not found',
});
});
test('should return 400 when file_id is missing', async () => {
// Don't set file_id in params
await fileAccess(req, res, next);
expect(next).not.toHaveBeenCalled();
expect(res.status).toHaveBeenCalledWith(400);
expect(res.json).toHaveBeenCalledWith({
error: 'Bad Request',
message: 'file_id is required',
});
});
test('should return 401 when user is not authenticated', async () => {
req.user = null;
req.params.file_id = 'some_file';
await fileAccess(req, res, next);
expect(next).not.toHaveBeenCalled();
expect(res.status).toHaveBeenCalledWith(401);
expect(res.json).toHaveBeenCalledWith({
error: 'Unauthorized',
message: 'Authentication required',
});
});
});
describe('agent-based file access', () => {
beforeEach(async () => {
// Create a file owned by otherUser (not testUser)
await createFile({
user: otherUser._id.toString(),
file_id: 'shared_file_via_agent',
filepath: '/test/shared.txt',
filename: 'shared.txt',
type: 'text/plain',
size: 100,
});
});
test('should allow access when user is author of agent with file', async () => {
// Create agent owned by testUser with the file
await createAgent({
id: `agent_${Date.now()}`,
name: 'Test Agent',
provider: 'openai',
model: 'gpt-4',
author: testUser._id,
tool_resources: {
file_search: {
file_ids: ['shared_file_via_agent'],
},
},
});
req.params.file_id = 'shared_file_via_agent';
await fileAccess(req, res, next);
expect(next).toHaveBeenCalled();
expect(req.fileAccess).toBeDefined();
expect(req.fileAccess.file).toBeDefined();
});
test('should allow access when user has VIEW permission on agent with file', async () => {
// Create agent owned by otherUser
const agent = await createAgent({
id: `agent_${Date.now()}`,
name: 'Shared Agent',
provider: 'openai',
model: 'gpt-4',
author: otherUser._id,
tool_resources: {
execute_code: {
file_ids: ['shared_file_via_agent'],
},
},
});
// Grant VIEW permission to testUser
await AclEntry.create({
principalType: PrincipalType.USER,
principalId: testUser._id,
principalModel: PrincipalModel.USER,
resourceType: ResourceType.AGENT,
resourceId: agent._id,
permBits: 1, // VIEW permission
grantedBy: otherUser._id,
});
req.params.file_id = 'shared_file_via_agent';
await fileAccess(req, res, next);
expect(next).toHaveBeenCalled();
expect(req.fileAccess).toBeDefined();
});
test('should check file in ocr tool_resources', async () => {
await createAgent({
id: `agent_ocr_${Date.now()}`,
name: 'OCR Agent',
provider: 'openai',
model: 'gpt-4',
author: testUser._id,
tool_resources: {
ocr: {
file_ids: ['shared_file_via_agent'],
},
},
});
req.params.file_id = 'shared_file_via_agent';
await fileAccess(req, res, next);
expect(next).toHaveBeenCalled();
expect(req.fileAccess).toBeDefined();
});
test('should deny access when user has no permission on agent with file', async () => {
// Create agent owned by otherUser without granting permission to testUser
const agent = await createAgent({
id: `agent_${Date.now()}`,
name: 'Private Agent',
provider: 'openai',
model: 'gpt-4',
author: otherUser._id,
tool_resources: {
file_search: {
file_ids: ['shared_file_via_agent'],
},
},
});
// Create ACL entry for otherUser only (owner)
await AclEntry.create({
principalType: PrincipalType.USER,
principalId: otherUser._id,
principalModel: PrincipalModel.USER,
resourceType: ResourceType.AGENT,
resourceId: agent._id,
permBits: 15, // All permissions
grantedBy: otherUser._id,
});
req.params.file_id = 'shared_file_via_agent';
await fileAccess(req, res, next);
expect(next).not.toHaveBeenCalled();
expect(res.status).toHaveBeenCalledWith(403);
});
});
describe('multiple agents with same file', () => {
/**
* This test suite verifies that when multiple agents have the same file,
* all agents are checked for permissions, not just the first one found.
* This ensures users can access files through any agent they have permission for.
*/
test('should check ALL agents with file, not just first one', async () => {
// Create a file owned by someone else
await createFile({
user: otherUser._id.toString(),
file_id: 'multi_agent_file',
filepath: '/test/multi.txt',
filename: 'multi.txt',
type: 'text/plain',
size: 100,
});
// Create first agent (owned by otherUser, no access for testUser)
const agent1 = await createAgent({
id: 'agent_no_access',
name: 'No Access Agent',
provider: 'openai',
model: 'gpt-4',
author: otherUser._id,
tool_resources: {
file_search: {
file_ids: ['multi_agent_file'],
},
},
});
// Create ACL for agent1 - only otherUser has access
await AclEntry.create({
principalType: PrincipalType.USER,
principalId: otherUser._id,
principalModel: PrincipalModel.USER,
resourceType: ResourceType.AGENT,
resourceId: agent1._id,
permBits: 15,
grantedBy: otherUser._id,
});
// Create second agent (owned by thirdUser, but testUser has VIEW access)
const agent2 = await createAgent({
id: 'agent_with_access',
name: 'Accessible Agent',
provider: 'openai',
model: 'gpt-4',
author: thirdUser._id,
tool_resources: {
file_search: {
file_ids: ['multi_agent_file'],
},
},
});
// Grant testUser VIEW access to agent2
await AclEntry.create({
principalType: PrincipalType.USER,
principalId: testUser._id,
principalModel: PrincipalModel.USER,
resourceType: ResourceType.AGENT,
resourceId: agent2._id,
permBits: 1, // VIEW permission
grantedBy: thirdUser._id,
});
req.params.file_id = 'multi_agent_file';
await fileAccess(req, res, next);
/**
* Should succeed because testUser has access to agent2,
* even though they don't have access to agent1.
* The fix ensures all agents are checked, not just the first one.
*/
expect(next).toHaveBeenCalled();
expect(req.fileAccess).toBeDefined();
expect(res.status).not.toHaveBeenCalled();
});
test('should find file in any agent tool_resources type', async () => {
// Create a file
await createFile({
user: otherUser._id.toString(),
file_id: 'multi_tool_file',
filepath: '/test/tool.txt',
filename: 'tool.txt',
type: 'text/plain',
size: 100,
});
// Agent 1: file in file_search (no access for testUser)
await createAgent({
id: 'agent_file_search',
name: 'File Search Agent',
provider: 'openai',
model: 'gpt-4',
author: otherUser._id,
tool_resources: {
file_search: {
file_ids: ['multi_tool_file'],
},
},
});
// Agent 2: same file in execute_code (testUser has access)
await createAgent({
id: 'agent_execute_code',
name: 'Execute Code Agent',
provider: 'openai',
model: 'gpt-4',
author: thirdUser._id,
tool_resources: {
execute_code: {
file_ids: ['multi_tool_file'],
},
},
});
// Agent 3: same file in ocr (testUser also has access)
await createAgent({
id: 'agent_ocr',
name: 'OCR Agent',
provider: 'openai',
model: 'gpt-4',
author: testUser._id, // testUser owns this one
tool_resources: {
ocr: {
file_ids: ['multi_tool_file'],
},
},
});
req.params.file_id = 'multi_tool_file';
await fileAccess(req, res, next);
/**
* Should succeed because testUser owns agent3,
* even if other agents with the file are found first.
*/
expect(next).toHaveBeenCalled();
expect(req.fileAccess).toBeDefined();
});
});
describe('edge cases', () => {
test('should handle agent with empty tool_resources', async () => {
await createFile({
user: otherUser._id.toString(),
file_id: 'orphan_file',
filepath: '/test/orphan.txt',
filename: 'orphan.txt',
type: 'text/plain',
size: 100,
});
// Create agent with no files in tool_resources
await createAgent({
id: `agent_empty_${Date.now()}`,
name: 'Empty Resources Agent',
provider: 'openai',
model: 'gpt-4',
author: testUser._id,
tool_resources: {},
});
req.params.file_id = 'orphan_file';
await fileAccess(req, res, next);
expect(next).not.toHaveBeenCalled();
expect(res.status).toHaveBeenCalledWith(403);
});
test('should handle agent with null tool_resources', async () => {
await createFile({
user: otherUser._id.toString(),
file_id: 'another_orphan_file',
filepath: '/test/orphan2.txt',
filename: 'orphan2.txt',
type: 'text/plain',
size: 100,
});
// Create agent with null tool_resources
await createAgent({
id: `agent_null_${Date.now()}`,
name: 'Null Resources Agent',
provider: 'openai',
model: 'gpt-4',
author: testUser._id,
tool_resources: null,
});
req.params.file_id = 'another_orphan_file';
await fileAccess(req, res, next);
expect(next).not.toHaveBeenCalled();
expect(res.status).toHaveBeenCalledWith(403);
});
});
});

View File

@@ -1,6 +1,6 @@
const { isEnabled } = require('@librechat/api');
const { logger } = require('@librechat/data-schemas');
const { SystemRoles } = require('librechat-data-provider');
const { isEnabled } = require('~/server/utils');
const { logger } = require('~/config');
/**
* Checks if the user can delete their account

View File

@@ -1,9 +1,9 @@
const { Keyv } = require('keyv');
const uap = require('ua-parser-js');
const { logger } = require('@librechat/data-schemas');
const { isEnabled, keyvMongo } = require('@librechat/api');
const { ViolationTypes } = require('librechat-data-provider');
const { isEnabled, removePorts } = require('~/server/utils');
const keyvMongo = require('~/cache/keyvMongo');
const { removePorts } = require('~/server/utils');
const denyRequest = require('./denyRequest');
const { getLogStores } = require('~/cache');
const { findUser } = require('~/models');

View File

@@ -1,5 +1,5 @@
const { logger } = require('@librechat/data-schemas');
const { isEmailDomainAllowed } = require('~/server/services/domains');
const { isEmailDomainAllowed } = require('@librechat/api');
const { getAppConfig } = require('~/server/services/Config');
/**

View File

@@ -1,6 +1,6 @@
const { logger } = require('@librechat/data-schemas');
const { PrincipalType, PermissionTypes, Permissions } = require('librechat-data-provider');
const { getRoleByName } = require('~/models/Role');
const { logger } = require('~/config');
/**
* Middleware to check if user has permission to access people picker functionality

View File

@@ -1,10 +1,11 @@
const { logger } = require('@librechat/data-schemas');
const { PrincipalType, PermissionTypes, Permissions } = require('librechat-data-provider');
const { checkPeoplePickerAccess } = require('./checkPeoplePickerAccess');
const { getRoleByName } = require('~/models/Role');
const { logger } = require('~/config');
jest.mock('~/models/Role');
jest.mock('~/config', () => ({
jest.mock('@librechat/data-schemas', () => ({
...jest.requireActual('@librechat/data-schemas'),
logger: {
error: jest.fn(),
},

View File

@@ -1,7 +1,7 @@
const { isEnabled } = require('@librechat/api');
const { Time, CacheKeys, ViolationTypes } = require('librechat-data-provider');
const clearPendingReq = require('~/cache/clearPendingReq');
const { logViolation, getLogStores } = require('~/cache');
const { isEnabled } = require('~/server/utils');
const denyRequest = require('./denyRequest');
const {

View File

@@ -1,6 +1,6 @@
const rateLimit = require('express-rate-limit');
const { limiterCache } = require('@librechat/api');
const { ViolationTypes } = require('librechat-data-provider');
const { limiterCache } = require('~/cache/cacheFactory');
const logViolation = require('~/cache/logViolation');
const getEnvironmentVariables = () => {

View File

@@ -1,6 +1,6 @@
const rateLimit = require('express-rate-limit');
const { limiterCache } = require('@librechat/api');
const { ViolationTypes } = require('librechat-data-provider');
const { limiterCache } = require('~/cache/cacheFactory');
const logViolation = require('~/cache/logViolation');
const getEnvironmentVariables = () => {

View File

@@ -1,7 +1,7 @@
const rateLimit = require('express-rate-limit');
const { limiterCache } = require('@librechat/api');
const { ViolationTypes } = require('librechat-data-provider');
const { removePorts } = require('~/server/utils');
const { limiterCache } = require('~/cache/cacheFactory');
const { logViolation } = require('~/cache');
const { LOGIN_WINDOW = 5, LOGIN_MAX = 7, LOGIN_VIOLATION_SCORE: score } = process.env;

View File

@@ -1,7 +1,7 @@
const rateLimit = require('express-rate-limit');
const { limiterCache } = require('@librechat/api');
const { ViolationTypes } = require('librechat-data-provider');
const denyRequest = require('~/server/middleware/denyRequest');
const { limiterCache } = require('~/cache/cacheFactory');
const { logViolation } = require('~/cache');
const {

View File

@@ -1,7 +1,7 @@
const rateLimit = require('express-rate-limit');
const { limiterCache } = require('@librechat/api');
const { ViolationTypes } = require('librechat-data-provider');
const { removePorts } = require('~/server/utils');
const { limiterCache } = require('~/cache/cacheFactory');
const { logViolation } = require('~/cache');
const { REGISTER_WINDOW = 60, REGISTER_MAX = 5, REGISTRATION_VIOLATION_SCORE: score } = process.env;

View File

@@ -1,7 +1,7 @@
const rateLimit = require('express-rate-limit');
const { limiterCache } = require('@librechat/api');
const { ViolationTypes } = require('librechat-data-provider');
const { removePorts } = require('~/server/utils');
const { limiterCache } = require('~/cache/cacheFactory');
const { logViolation } = require('~/cache');
const {

View File

@@ -1,6 +1,6 @@
const rateLimit = require('express-rate-limit');
const { limiterCache } = require('@librechat/api');
const { ViolationTypes } = require('librechat-data-provider');
const { limiterCache } = require('~/cache/cacheFactory');
const logViolation = require('~/cache/logViolation');
const getEnvironmentVariables = () => {

View File

@@ -1,6 +1,6 @@
const rateLimit = require('express-rate-limit');
const { limiterCache } = require('@librechat/api');
const { ViolationTypes } = require('librechat-data-provider');
const { limiterCache } = require('~/cache/cacheFactory');
const logViolation = require('~/cache/logViolation');
const { TOOL_CALL_VIOLATION_SCORE: score } = process.env;

View File

@@ -1,7 +1,7 @@
const rateLimit = require('express-rate-limit');
const { limiterCache } = require('@librechat/api');
const { ViolationTypes } = require('librechat-data-provider');
const logViolation = require('~/cache/logViolation');
const { limiterCache } = require('~/cache/cacheFactory');
const getEnvironmentVariables = () => {
const TTS_IP_MAX = parseInt(process.env.TTS_IP_MAX) || 100;

View File

@@ -1,6 +1,6 @@
const rateLimit = require('express-rate-limit');
const { limiterCache } = require('@librechat/api');
const { ViolationTypes } = require('librechat-data-provider');
const { limiterCache } = require('~/cache/cacheFactory');
const logViolation = require('~/cache/logViolation');
const getEnvironmentVariables = () => {

View File

@@ -1,7 +1,7 @@
const rateLimit = require('express-rate-limit');
const { limiterCache } = require('@librechat/api');
const { ViolationTypes } = require('librechat-data-provider');
const { removePorts } = require('~/server/utils');
const { limiterCache } = require('~/cache/cacheFactory');
const { logViolation } = require('~/cache');
const {

View File

@@ -1,4 +1,4 @@
const { logger } = require('~/config');
const { logger } = require('@librechat/data-schemas');
/**
* Middleware to log Forwarded Headers

View File

@@ -1,8 +1,8 @@
const axios = require('axios');
const { isEnabled } = require('@librechat/api');
const { logger } = require('@librechat/data-schemas');
const { ErrorTypes } = require('librechat-data-provider');
const { isEnabled } = require('~/server/utils');
const denyRequest = require('./denyRequest');
const { logger } = require('~/config');
async function moderateText(req, res, next) {
if (!isEnabled(process.env.OPENAI_MODERATION)) {

View File

@@ -1,6 +1,6 @@
const cookies = require('cookie');
const { isEnabled } = require('~/server/utils');
const passport = require('passport');
const { isEnabled } = require('@librechat/api');
// This middleware does not require authentication,
// but if the user is authenticated, it will set the user object.

View File

@@ -1,6 +1,6 @@
const passport = require('passport');
const cookies = require('cookie');
const { isEnabled } = require('~/server/utils');
const passport = require('passport');
const { isEnabled } = require('@librechat/api');
/**
* Custom Middleware to handle JWT authentication, with support for OpenID token reuse

View File

@@ -1,5 +1,5 @@
const passport = require('passport');
const { logger } = require('~/config');
const { logger } = require('@librechat/data-schemas');
const requireLocalAuth = (req, res, next) => {
passport.authenticate('local', (err, user, info) => {

View File

@@ -1,5 +1,5 @@
const { isEnabled } = require('~/server/utils');
const { logger } = require('~/config');
const { isEnabled } = require('@librechat/api');
const { logger } = require('@librechat/data-schemas');
function validatePasswordReset(req, res, next) {
if (isEnabled(process.env.ALLOW_PASSWORD_RESET)) {

View File

@@ -1,4 +1,4 @@
const { isEnabled } = require('~/server/utils');
const { isEnabled } = require('@librechat/api');
function validateRegistration(req, res, next) {
if (req.invite) {

View File

@@ -1,680 +0,0 @@
const express = require('express');
const request = require('supertest');
const mongoose = require('mongoose');
const { MongoMemoryServer } = require('mongodb-memory-server');
jest.mock('@librechat/data-schemas', () => ({
logger: {
debug: jest.fn(),
info: jest.fn(),
warn: jest.fn(),
error: jest.fn(),
},
createMethods: jest.fn(() => ({})),
createModels: jest.fn(() => ({})),
}));
jest.mock('~/server/middleware', () => ({
requireJwtAuth: (req, res, next) => next(),
validateMessageReq: (req, res, next) => next(),
}));
jest.mock('~/models', () => ({
getConvo: jest.fn(),
saveConvo: jest.fn(),
saveMessage: jest.fn(),
getMessage: jest.fn(),
getMessages: jest.fn(),
updateMessage: jest.fn(),
deleteMessages: jest.fn(),
}));
jest.mock('~/db/models', () => {
let User, Message, Transaction, Conversation;
return {
get User() {
return User;
},
get Message() {
return Message;
},
get Transaction() {
return Transaction;
},
get Conversation() {
return Conversation;
},
setUser: (model) => {
User = model;
},
setMessage: (model) => {
Message = model;
},
setTransaction: (model) => {
Transaction = model;
},
setConversation: (model) => {
Conversation = model;
},
};
});
describe('Costs Endpoint', () => {
let app;
let mongoServer;
let messagesRouter;
let User, Message, Transaction, Conversation;
beforeAll(async () => {
mongoServer = await MongoMemoryServer.create();
await mongoose.connect(mongoServer.getUri());
const userSchema = new mongoose.Schema({
_id: String,
name: String,
email: String,
});
const conversationSchema = new mongoose.Schema({
conversationId: String,
user: String,
title: String,
createdAt: Date,
});
const messageSchema = new mongoose.Schema({
messageId: String,
conversationId: String,
user: String,
isCreatedByUser: Boolean,
tokenCount: Number,
createdAt: Date,
});
const transactionSchema = new mongoose.Schema({
conversationId: String,
user: String,
tokenType: String,
tokenValue: Number,
createdAt: Date,
});
User = mongoose.model('User', userSchema);
Conversation = mongoose.model('Conversation', conversationSchema);
Message = mongoose.model('Message', messageSchema);
Transaction = mongoose.model('Transaction', transactionSchema);
const dbModels = require('~/db/models');
dbModels.setUser(User);
dbModels.setMessage(Message);
dbModels.setTransaction(Transaction);
dbModels.setConversation(Conversation);
require('~/db/models');
try {
messagesRouter = require('../messages');
} catch (error) {
console.error('Error loading messages router:', error);
throw error;
}
app = express();
app.use(express.json());
app.use((req, res, next) => {
req.user = { id: 'test-user-id' };
next();
});
app.use('/api/messages', messagesRouter);
});
afterAll(async () => {
await mongoose.disconnect();
await mongoServer.stop();
});
beforeEach(async () => {
await User.deleteMany({});
await Conversation.deleteMany({});
await Message.deleteMany({});
await Transaction.deleteMany({});
});
describe('GET /:conversationId/costs', () => {
const conversationId = 'test-conversation-123';
const userId = 'test-user-id';
it('should return cost data for valid conversation', async () => {
const { getConvo } = require('~/models');
getConvo.mockResolvedValue({
conversationId,
user: userId,
title: 'Test Conversation',
});
const conversation = new Conversation({
conversationId,
user: userId,
title: 'Test Conversation',
createdAt: new Date('2024-01-01T09:00:00Z'),
});
await conversation.save();
const userMessage = new Message({
messageId: 'user-msg-1',
conversationId,
user: userId,
isCreatedByUser: true,
tokenCount: 100,
createdAt: new Date('2024-01-01T10:00:00Z'),
});
const aiMessage = new Message({
messageId: 'ai-msg-1',
conversationId,
user: userId,
isCreatedByUser: false,
tokenCount: 150,
createdAt: new Date('2024-01-01T10:01:00Z'),
});
await Promise.all([userMessage.save(), aiMessage.save()]);
const promptTransaction = new Transaction({
conversationId,
user: userId,
tokenType: 'prompt',
tokenValue: 500000,
createdAt: new Date('2024-01-01T10:00:30Z'),
});
const completionTransaction = new Transaction({
conversationId,
user: userId,
tokenType: 'completion',
tokenValue: 750000,
createdAt: new Date('2024-01-01T10:01:30Z'),
});
await Promise.all([promptTransaction.save(), completionTransaction.save()]);
const response = await request(app).get(`/api/messages/${conversationId}/costs`);
expect(response.status).toBe(200);
expect(response.body).toMatchObject({
conversationId,
totals: {
prompt: { usd: 0.5, tokenCount: 100 },
completion: { usd: 0.75, tokenCount: 150 },
total: { usd: 1.25, tokenCount: 250 },
},
perMessage: [
{ messageId: 'user-msg-1', tokenType: 'prompt', tokenCount: 100, usd: 0.5 },
{ messageId: 'ai-msg-1', tokenType: 'completion', tokenCount: 150, usd: 0.75 },
],
});
});
it('should return empty data for conversation with no messages', async () => {
const { getConvo } = require('~/models');
getConvo.mockResolvedValue({
conversationId,
user: userId,
title: 'Test Conversation',
});
const conversation = new Conversation({
conversationId,
user: userId,
title: 'Test Conversation',
createdAt: new Date('2024-01-01T09:00:00Z'),
});
await conversation.save();
const response = await request(app).get(`/api/messages/${conversationId}/costs`);
expect(response.status).toBe(200);
expect(response.body).toMatchObject({
conversationId,
totals: {
prompt: { usd: 0, tokenCount: 0 },
completion: { usd: 0, tokenCount: 0 },
total: { usd: 0, tokenCount: 0 },
},
perMessage: [],
});
});
it('should handle messages without transactions', async () => {
const { getConvo } = require('~/models');
getConvo.mockResolvedValue({
conversationId,
user: userId,
title: 'Test Conversation',
});
const conversation = new Conversation({
conversationId,
user: userId,
title: 'Test Conversation',
createdAt: new Date('2024-01-01T09:00:00Z'),
});
await conversation.save();
const userMessage = new Message({
messageId: 'user-msg-1',
conversationId,
user: userId,
isCreatedByUser: true,
tokenCount: 100,
createdAt: new Date('2024-01-01T10:00:00Z'),
});
const aiMessage = new Message({
messageId: 'ai-msg-1',
conversationId,
user: userId,
isCreatedByUser: false,
tokenCount: 150,
createdAt: new Date('2024-01-01T10:01:00Z'),
});
await Promise.all([userMessage.save(), aiMessage.save()]);
const response = await request(app).get(`/api/messages/${conversationId}/costs`);
expect(response.status).toBe(200);
expect(response.body.totals.prompt.usd).toBe(0);
expect(response.body.totals.completion.usd).toBe(0);
expect(response.body.totals.total.usd).toBe(0);
});
it('should aggregate multiple transactions correctly', async () => {
const { getConvo } = require('~/models');
getConvo.mockResolvedValue({
conversationId,
user: userId,
title: 'Test Conversation',
});
const conversation = new Conversation({
conversationId,
user: userId,
title: 'Test Conversation',
createdAt: new Date('2024-01-01T09:00:00Z'),
});
await conversation.save();
const userMessage = new Message({
messageId: 'user-msg-1',
conversationId,
user: userId,
isCreatedByUser: true,
tokenCount: 100,
createdAt: new Date('2024-01-01T10:00:00Z'),
});
await userMessage.save();
const promptTransaction1 = new Transaction({
conversationId,
user: userId,
tokenType: 'prompt',
tokenValue: 300000,
createdAt: new Date('2024-01-01T10:00:30Z'),
});
const promptTransaction2 = new Transaction({
conversationId,
user: userId,
tokenType: 'prompt',
tokenValue: 200000,
createdAt: new Date('2024-01-01T10:00:45Z'),
});
await Promise.all([promptTransaction1.save(), promptTransaction2.save()]);
const response = await request(app).get(`/api/messages/${conversationId}/costs`);
expect(response.status).toBe(200);
expect(response.body.totals.prompt.usd).toBe(0.5);
expect(response.body.perMessage[0].usd).toBe(0.5);
});
it('should handle null tokenCount values', async () => {
const { getConvo } = require('~/models');
getConvo.mockResolvedValue({
conversationId,
user: userId,
title: 'Test Conversation',
});
const conversation = new Conversation({
conversationId,
user: userId,
title: 'Test Conversation',
createdAt: new Date('2024-01-01T09:00:00Z'),
});
await conversation.save();
const userMessage = new Message({
messageId: 'user-msg-1',
conversationId,
user: userId,
isCreatedByUser: true,
tokenCount: null,
createdAt: new Date('2024-01-01T10:00:00Z'),
});
await userMessage.save();
const response = await request(app).get(`/api/messages/${conversationId}/costs`);
expect(response.status).toBe(200);
expect(response.body.totals.prompt.tokenCount).toBe(0);
});
it('should handle null tokenValue in transactions', async () => {
const { getConvo } = require('~/models');
getConvo.mockResolvedValue({
conversationId,
user: userId,
title: 'Test Conversation',
});
const conversation = new Conversation({
conversationId,
user: userId,
title: 'Test Conversation',
createdAt: new Date('2024-01-01T09:00:00Z'),
});
await conversation.save();
const userMessage = new Message({
messageId: 'user-msg-1',
conversationId,
user: userId,
isCreatedByUser: true,
tokenCount: 100,
createdAt: new Date('2024-01-01T10:00:00Z'),
});
await userMessage.save();
const promptTransaction = new Transaction({
conversationId,
user: userId,
tokenType: 'prompt',
tokenValue: null,
createdAt: new Date('2024-01-01T10:00:30Z'),
});
await promptTransaction.save();
const response = await request(app).get(`/api/messages/${conversationId}/costs`);
expect(response.status).toBe(200);
expect(response.body.totals.prompt.usd).toBe(0);
});
it('should handle negative tokenValue using Math.abs', async () => {
const { getConvo } = require('~/models');
getConvo.mockResolvedValue({
conversationId,
user: userId,
title: 'Test Conversation',
});
const conversation = new Conversation({
conversationId,
user: userId,
title: 'Test Conversation',
createdAt: new Date('2024-01-01T09:00:00Z'),
});
await conversation.save();
const userMessage = new Message({
messageId: 'user-msg-1',
conversationId,
user: userId,
isCreatedByUser: true,
tokenCount: 100,
createdAt: new Date('2024-01-01T10:00:00Z'),
});
await userMessage.save();
const promptTransaction = new Transaction({
conversationId,
user: userId,
tokenType: 'prompt',
tokenValue: -500000,
createdAt: new Date('2024-01-01T10:00:30Z'),
});
await promptTransaction.save();
const response = await request(app).get(`/api/messages/${conversationId}/costs`);
expect(response.status).toBe(200);
expect(response.body.totals.prompt.usd).toBe(0.5);
});
it('should filter by user correctly', async () => {
const { getConvo } = require('~/models');
getConvo.mockResolvedValue({
conversationId,
user: userId,
title: 'Test Conversation',
});
const conversation = new Conversation({
conversationId,
user: userId,
title: 'Test Conversation',
createdAt: new Date('2024-01-01T09:00:00Z'),
});
await conversation.save();
const otherUserId = 'other-user-id';
const userMessage = new Message({
messageId: 'user-msg-1',
conversationId,
user: userId,
isCreatedByUser: true,
tokenCount: 100,
createdAt: new Date('2024-01-01T10:00:00Z'),
});
const otherUserMessage = new Message({
messageId: 'other-user-msg-1',
conversationId,
user: otherUserId,
isCreatedByUser: true,
tokenCount: 200,
createdAt: new Date('2024-01-01T10:00:00Z'),
});
await Promise.all([userMessage.save(), otherUserMessage.save()]);
const userTransaction = new Transaction({
conversationId,
user: userId,
tokenType: 'prompt',
tokenValue: 500000,
createdAt: new Date('2024-01-01T10:00:30Z'),
});
const otherUserTransaction = new Transaction({
conversationId,
user: otherUserId,
tokenType: 'prompt',
tokenValue: 1000000,
createdAt: new Date('2024-01-01T10:00:30Z'),
});
await Promise.all([userTransaction.save(), otherUserTransaction.save()]);
const response = await request(app).get(`/api/messages/${conversationId}/costs`);
expect(response.status).toBe(200);
expect(response.body.totals.prompt.usd).toBe(0.5);
expect(response.body.perMessage).toHaveLength(1);
expect(response.body.perMessage[0].messageId).toBe('user-msg-1');
});
it('should filter transactions by tokenType', async () => {
const { getConvo } = require('~/models');
getConvo.mockResolvedValue({
conversationId,
user: userId,
title: 'Test Conversation',
});
const conversation = new Conversation({
conversationId,
user: userId,
title: 'Test Conversation',
createdAt: new Date('2024-01-01T09:00:00Z'),
});
await conversation.save();
const userMessage = new Message({
messageId: 'user-msg-1',
conversationId,
user: userId,
isCreatedByUser: true,
tokenCount: 100,
createdAt: new Date('2024-01-01T10:00:00Z'),
});
await userMessage.save();
const promptTransaction = new Transaction({
conversationId,
user: userId,
tokenType: 'prompt',
tokenValue: 500000,
createdAt: new Date('2024-01-01T10:00:30Z'),
});
const otherTransaction = new Transaction({
conversationId,
user: userId,
tokenType: 'other',
tokenValue: 1000000,
createdAt: new Date('2024-01-01T10:00:30Z'),
});
await Promise.all([promptTransaction.save(), otherTransaction.save()]);
const response = await request(app).get(`/api/messages/${conversationId}/costs`);
expect(response.status).toBe(200);
expect(response.body.totals.prompt.usd).toBe(0.5);
expect(response.body.totals.completion.usd).toBe(0);
expect(response.body.totals.total.usd).toBe(0.5);
});
it('should map transactions to messages chronologically', async () => {
const { getConvo } = require('~/models');
getConvo.mockResolvedValue({
conversationId,
user: userId,
title: 'Test Conversation',
});
const conversation = new Conversation({
conversationId,
user: userId,
title: 'Test Conversation',
createdAt: new Date('2024-01-01T09:00:00Z'),
});
await conversation.save();
const userMessage1 = new Message({
messageId: 'user-msg-1',
conversationId,
user: userId,
isCreatedByUser: true,
tokenCount: 100,
createdAt: new Date('2024-01-01T10:00:00Z'),
});
const userMessage2 = new Message({
messageId: 'user-msg-2',
conversationId,
user: userId,
isCreatedByUser: true,
tokenCount: 200,
createdAt: new Date('2024-01-01T10:01:00Z'),
});
await Promise.all([userMessage1.save(), userMessage2.save()]);
const promptTransaction1 = new Transaction({
conversationId,
user: userId,
tokenType: 'prompt',
tokenValue: 500000,
createdAt: new Date('2024-01-01T10:00:30Z'),
});
const promptTransaction2 = new Transaction({
conversationId,
user: userId,
tokenType: 'prompt',
tokenValue: 1000000,
createdAt: new Date('2024-01-01T10:01:30Z'),
});
await Promise.all([promptTransaction1.save(), promptTransaction2.save()]);
const response = await request(app).get(`/api/messages/${conversationId}/costs`);
expect(response.status).toBe(200);
expect(response.body.perMessage).toHaveLength(2);
expect(response.body.perMessage[0].messageId).toBe('user-msg-1');
expect(response.body.perMessage[0].usd).toBe(0.5);
expect(response.body.perMessage[1].messageId).toBe('user-msg-2');
expect(response.body.perMessage[1].usd).toBe(1.0);
});
it('should handle database errors', async () => {
const { getConvo } = require('~/models');
getConvo.mockResolvedValue({
conversationId,
user: userId,
title: 'Test Conversation',
});
const conversation = new Conversation({
conversationId,
user: userId,
title: 'Test Conversation',
createdAt: new Date('2024-01-01T09:00:00Z'),
});
await conversation.save();
await mongoose.connection.close();
const response = await request(app).get(`/api/messages/${conversationId}/costs`);
expect(response.status).toBe(500);
expect(response.body).toHaveProperty('error');
});
});
});

View File

@@ -1,10 +1,13 @@
const request = require('supertest');
const express = require('express');
const request = require('supertest');
const { isEnabled } = require('@librechat/api');
const { getLdapConfig } = require('~/server/services/Config/ldap');
const { isEnabled } = require('~/server/utils');
jest.mock('~/server/services/Config/ldap');
jest.mock('~/server/utils');
jest.mock('@librechat/api', () => ({
...jest.requireActual('@librechat/api'),
isEnabled: jest.fn(),
}));
const app = express();

View File

@@ -11,6 +11,9 @@ jest.mock('@librechat/api', () => ({
completeOAuthFlow: jest.fn(),
generateFlowId: jest.fn(),
},
MCPTokenStorage: {
storeTokens: jest.fn(),
},
getUserMCPAuthMap: jest.fn(),
}));
@@ -47,8 +50,8 @@ jest.mock('~/server/services/Config', () => ({
loadCustomConfig: jest.fn(),
}));
jest.mock('~/server/services/Config/mcpToolsCache', () => ({
updateMCPUserTools: jest.fn(),
jest.mock('~/server/services/Config/mcp', () => ({
updateMCPServerTools: jest.fn(),
}));
jest.mock('~/server/services/MCP', () => ({
@@ -124,8 +127,13 @@ describe('MCP Routes', () => {
}),
};
const mockMcpManager = {
getRawConfig: jest.fn().mockReturnValue({}),
};
getLogStores.mockReturnValue({});
require('~/config').getFlowStateManager.mockReturnValue(mockFlowManager);
require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
MCPOAuthHandler.initiateOAuthFlow.mockResolvedValue({
authorizationUrl: 'https://oauth.example.com/auth',
@@ -143,6 +151,7 @@ describe('MCP Routes', () => {
'test-server',
'https://test-server.com',
'test-user-id',
{},
{ clientId: 'test-client-id' },
);
});
@@ -234,7 +243,7 @@ describe('MCP Routes', () => {
});
describe('GET /:serverName/oauth/callback', () => {
const { MCPOAuthHandler } = require('@librechat/api');
const { MCPOAuthHandler, MCPTokenStorage } = require('@librechat/api');
const { getLogStores } = require('~/cache');
it('should redirect to error page when OAuth error is received', async () => {
@@ -280,6 +289,7 @@ describe('MCP Routes', () => {
it('should handle OAuth callback successfully', async () => {
const mockFlowManager = {
completeFlow: jest.fn().mockResolvedValue(),
deleteFlow: jest.fn().mockResolvedValue(true),
};
const mockFlowState = {
serverName: 'test-server',
@@ -295,6 +305,7 @@ describe('MCP Routes', () => {
MCPOAuthHandler.getFlowState.mockResolvedValue(mockFlowState);
MCPOAuthHandler.completeOAuthFlow.mockResolvedValue(mockTokens);
MCPTokenStorage.storeTokens.mockResolvedValue();
getLogStores.mockReturnValue({});
require('~/config').getFlowStateManager.mockReturnValue(mockFlowManager);
@@ -309,6 +320,7 @@ describe('MCP Routes', () => {
};
const mockMcpManager = {
getUserConnection: jest.fn().mockResolvedValue(mockUserConnection),
getRawConfig: jest.fn().mockReturnValue({}),
};
require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
@@ -331,12 +343,26 @@ describe('MCP Routes', () => {
'test-flow-id',
'test-auth-code',
mockFlowManager,
{},
);
expect(MCPTokenStorage.storeTokens).toHaveBeenCalledWith(
expect.objectContaining({
userId: 'test-user-id',
serverName: 'test-server',
tokens: mockTokens,
clientInfo: mockFlowState.clientInfo,
metadata: mockFlowState.metadata,
}),
);
const storeInvocation = MCPTokenStorage.storeTokens.mock.invocationCallOrder[0];
const connectInvocation = mockMcpManager.getUserConnection.mock.invocationCallOrder[0];
expect(storeInvocation).toBeLessThan(connectInvocation);
expect(mockFlowManager.completeFlow).toHaveBeenCalledWith(
'tool-flow-123',
'mcp_oauth',
mockTokens,
);
expect(mockFlowManager.deleteFlow).toHaveBeenCalledWith('test-flow-id', 'mcp_get_tokens');
});
it('should redirect to error page when callback processing fails', async () => {
@@ -354,6 +380,7 @@ describe('MCP Routes', () => {
it('should handle system-level OAuth completion', async () => {
const mockFlowManager = {
completeFlow: jest.fn().mockResolvedValue(),
deleteFlow: jest.fn().mockResolvedValue(true),
};
const mockFlowState = {
serverName: 'test-server',
@@ -369,9 +396,15 @@ describe('MCP Routes', () => {
MCPOAuthHandler.getFlowState.mockResolvedValue(mockFlowState);
MCPOAuthHandler.completeOAuthFlow.mockResolvedValue(mockTokens);
MCPTokenStorage.storeTokens.mockResolvedValue();
getLogStores.mockReturnValue({});
require('~/config').getFlowStateManager.mockReturnValue(mockFlowManager);
const mockMcpManager = {
getRawConfig: jest.fn().mockReturnValue({}),
};
require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
const response = await request(app).get('/api/mcp/test-server/oauth/callback').query({
code: 'test-auth-code',
state: 'test-flow-id',
@@ -379,11 +412,13 @@ describe('MCP Routes', () => {
expect(response.status).toBe(302);
expect(response.headers.location).toBe('/oauth/success?serverName=test-server');
expect(mockFlowManager.deleteFlow).toHaveBeenCalledWith('test-flow-id', 'mcp_get_tokens');
});
it('should handle reconnection failure after OAuth', async () => {
const mockFlowManager = {
completeFlow: jest.fn().mockResolvedValue(),
deleteFlow: jest.fn().mockResolvedValue(true),
};
const mockFlowState = {
serverName: 'test-server',
@@ -399,11 +434,13 @@ describe('MCP Routes', () => {
MCPOAuthHandler.getFlowState.mockResolvedValue(mockFlowState);
MCPOAuthHandler.completeOAuthFlow.mockResolvedValue(mockTokens);
MCPTokenStorage.storeTokens.mockResolvedValue();
getLogStores.mockReturnValue({});
require('~/config').getFlowStateManager.mockReturnValue(mockFlowManager);
const mockMcpManager = {
getUserConnection: jest.fn().mockRejectedValue(new Error('Reconnection failed')),
getRawConfig: jest.fn().mockReturnValue({}),
};
require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
@@ -418,6 +455,46 @@ describe('MCP Routes', () => {
expect(response.status).toBe(302);
expect(response.headers.location).toBe('/oauth/success?serverName=test-server');
expect(MCPTokenStorage.storeTokens).toHaveBeenCalled();
expect(mockFlowManager.deleteFlow).toHaveBeenCalledWith('test-flow-id', 'mcp_get_tokens');
});
it('should redirect to error page if token storage fails', async () => {
const mockFlowManager = {
completeFlow: jest.fn().mockResolvedValue(),
deleteFlow: jest.fn().mockResolvedValue(true),
};
const mockFlowState = {
serverName: 'test-server',
userId: 'test-user-id',
metadata: { toolFlowId: 'tool-flow-123' },
clientInfo: {},
codeVerifier: 'test-verifier',
};
const mockTokens = {
access_token: 'test-access-token',
refresh_token: 'test-refresh-token',
};
MCPOAuthHandler.getFlowState.mockResolvedValue(mockFlowState);
MCPOAuthHandler.completeOAuthFlow.mockResolvedValue(mockTokens);
MCPTokenStorage.storeTokens.mockRejectedValue(new Error('store failed'));
getLogStores.mockReturnValue({});
require('~/config').getFlowStateManager.mockReturnValue(mockFlowManager);
const mockMcpManager = {
getUserConnection: jest.fn(),
};
require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
const response = await request(app).get('/api/mcp/test-server/oauth/callback').query({
code: 'test-auth-code',
state: 'test-flow-id',
});
expect(response.status).toBe(302);
expect(response.headers.location).toBe('/oauth/error?error=callback_failed');
expect(mockMcpManager.getUserConnection).not.toHaveBeenCalled();
});
});
@@ -778,10 +855,10 @@ describe('MCP Routes', () => {
require('~/cache').getLogStores.mockReturnValue({});
const { getCachedTools, setCachedTools } = require('~/server/services/Config');
const { updateMCPUserTools } = require('~/server/services/Config/mcpToolsCache');
const { updateMCPServerTools } = require('~/server/services/Config/mcp');
getCachedTools.mockResolvedValue({});
setCachedTools.mockResolvedValue();
updateMCPUserTools.mockResolvedValue();
updateMCPServerTools.mockResolvedValue();
require('~/server/services/Tools/mcp').reinitMCPServer.mockResolvedValue({
success: true,
@@ -836,10 +913,10 @@ describe('MCP Routes', () => {
]);
const { getCachedTools, setCachedTools } = require('~/server/services/Config');
const { updateMCPUserTools } = require('~/server/services/Config/mcpToolsCache');
const { updateMCPServerTools } = require('~/server/services/Config/mcp');
getCachedTools.mockResolvedValue({});
setCachedTools.mockResolvedValue();
updateMCPUserTools.mockResolvedValue();
updateMCPServerTools.mockResolvedValue();
require('~/server/services/Tools/mcp').reinitMCPServer.mockResolvedValue({
success: true,
@@ -1143,7 +1220,11 @@ describe('MCP Routes', () => {
describe('GET /:serverName/oauth/callback - Edge Cases', () => {
it('should handle OAuth callback without toolFlowId (falsy toolFlowId)', async () => {
const { MCPOAuthHandler } = require('@librechat/api');
const { MCPOAuthHandler, MCPTokenStorage } = require('@librechat/api');
const mockTokens = {
access_token: 'edge-access-token',
refresh_token: 'edge-refresh-token',
};
MCPOAuthHandler.getFlowState = jest.fn().mockResolvedValue({
id: 'test-flow-id',
userId: 'test-user-id',
@@ -1155,6 +1236,8 @@ describe('MCP Routes', () => {
clientInfo: {},
codeVerifier: 'test-verifier',
});
MCPOAuthHandler.completeOAuthFlow = jest.fn().mockResolvedValue(mockTokens);
MCPTokenStorage.storeTokens.mockResolvedValue();
const mockFlowManager = {
completeFlow: jest.fn(),
@@ -1165,6 +1248,7 @@ describe('MCP Routes', () => {
getUserConnection: jest.fn().mockResolvedValue({
fetchTools: jest.fn().mockResolvedValue([]),
}),
getRawConfig: jest.fn().mockReturnValue({}),
};
require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
@@ -1179,6 +1263,11 @@ describe('MCP Routes', () => {
it('should handle null cached tools in OAuth callback (triggers || {} fallback)', async () => {
const { getCachedTools } = require('~/server/services/Config');
getCachedTools.mockResolvedValue(null);
const { MCPOAuthHandler, MCPTokenStorage } = require('@librechat/api');
const mockTokens = {
access_token: 'edge-access-token',
refresh_token: 'edge-refresh-token',
};
const mockFlowManager = {
getFlowState: jest.fn().mockResolvedValue({
@@ -1191,6 +1280,15 @@ describe('MCP Routes', () => {
completeFlow: jest.fn(),
};
require('~/config').getFlowStateManager.mockReturnValue(mockFlowManager);
MCPOAuthHandler.getFlowState.mockResolvedValue({
serverName: 'test-server',
userId: 'test-user-id',
metadata: { serverUrl: 'https://example.com', oauth: {} },
clientInfo: {},
codeVerifier: 'test-verifier',
});
MCPOAuthHandler.completeOAuthFlow.mockResolvedValue(mockTokens);
MCPTokenStorage.storeTokens.mockResolvedValue();
const mockMcpManager = {
getUserConnection: jest.fn().mockResolvedValue({
@@ -1198,6 +1296,7 @@ describe('MCP Routes', () => {
.fn()
.mockResolvedValue([{ name: 'test-tool', description: 'Test tool' }]),
}),
getRawConfig: jest.fn().mockReturnValue({}),
};
require('~/config').getMCPManager.mockReturnValue(mockMcpManager);

View File

@@ -1,20 +1,19 @@
const express = require('express');
const { nanoid } = require('nanoid');
const { logger } = require('@librechat/data-schemas');
const { generateCheckAccess } = require('@librechat/api');
const { generateCheckAccess, isActionDomainAllowed } = require('@librechat/api');
const {
Permissions,
ResourceType,
PermissionBits,
PermissionTypes,
actionDelimiter,
PermissionBits,
removeNullishValues,
} = require('librechat-data-provider');
const { encryptMetadata, domainParser } = require('~/server/services/ActionService');
const { findAccessibleResources } = require('~/server/services/PermissionService');
const { getAgent, updateAgent, getListAgentsByAccess } = require('~/models/Agent');
const { updateAction, getActions, deleteAction } = require('~/models/Action');
const { isActionDomainAllowed } = require('~/server/services/domains');
const { canAccessAgentResource } = require('~/server/middleware');
const { getRoleByName } = require('~/models/Role');

View File

@@ -1,4 +1,5 @@
const express = require('express');
const { isEnabled } = require('@librechat/api');
const {
uaParser,
checkBan,
@@ -8,7 +9,6 @@ const {
concurrentLimiter,
messageUserLimiter,
} = require('~/server/middleware');
const { isEnabled } = require('~/server/utils');
const { v1 } = require('./v1');
const chat = require('./chat');

View File

@@ -1,12 +1,12 @@
const express = require('express');
const { nanoid } = require('nanoid');
const { logger } = require('@librechat/data-schemas');
const { isActionDomainAllowed } = require('@librechat/api');
const { actionDelimiter, EModelEndpoint, removeNullishValues } = require('librechat-data-provider');
const { encryptMetadata, domainParser } = require('~/server/services/ActionService');
const { getOpenAIClient } = require('~/server/controllers/assistants/helpers');
const { updateAction, getActions, deleteAction } = require('~/models/Action');
const { updateAssistantDoc, getAssistant } = require('~/models/Assistant');
const { isActionDomainAllowed } = require('~/server/services/domains');
const router = express.Router();

View File

@@ -115,6 +115,9 @@ router.get('/', async function (req, res) {
sharePointPickerGraphScope: process.env.SHAREPOINT_PICKER_GRAPH_SCOPE,
sharePointPickerSharePointScope: process.env.SHAREPOINT_PICKER_SHAREPOINT_SCOPE,
openidReuseTokens,
conversationImportMaxFileSize: process.env.CONVERSATION_IMPORT_MAX_FILE_SIZE_BYTES
? parseInt(process.env.CONVERSATION_IMPORT_MAX_FILE_SIZE_BYTES, 10)
: 0,
};
const minPasswordLength = parseInt(process.env.MIN_PASSWORD_LENGTH, 10);
@@ -156,7 +159,7 @@ router.get('/', async function (req, res) {
if (
webSearchConfig != null &&
(webSearchConfig.searchProvider ||
webSearchConfig.scraperType ||
webSearchConfig.scraperProvider ||
webSearchConfig.rerankerType)
) {
payload.webSearch = {};
@@ -165,8 +168,8 @@ router.get('/', async function (req, res) {
if (webSearchConfig?.searchProvider) {
payload.webSearch.searchProvider = webSearchConfig.searchProvider;
}
if (webSearchConfig?.scraperType) {
payload.webSearch.scraperType = webSearchConfig.scraperType;
if (webSearchConfig?.scraperProvider) {
payload.webSearch.scraperProvider = webSearchConfig.scraperProvider;
}
if (webSearchConfig?.rerankerType) {
payload.webSearch.rerankerType = webSearchConfig.rerankerType;

View File

@@ -1,19 +1,19 @@
const { isEnabled } = require('@librechat/api');
const { EModelEndpoint } = require('librechat-data-provider');
const {
validateConvoAccess,
messageUserLimiter,
concurrentLimiter,
messageIpLimiter,
requireJwtAuth,
checkBan,
uaParser,
} = require('~/server/middleware');
const anthropic = require('./anthropic');
const express = require('express');
const openAI = require('./openAI');
const custom = require('./custom');
const google = require('./google');
const anthropic = require('./anthropic');
const { isEnabled } = require('~/server/utils');
const { EModelEndpoint } = require('librechat-data-provider');
const {
checkBan,
uaParser,
requireJwtAuth,
messageIpLimiter,
concurrentLimiter,
messageUserLimiter,
validateConvoAccess,
} = require('~/server/middleware');
const { LIMIT_CONCURRENT_MESSAGES, LIMIT_MESSAGE_IP, LIMIT_MESSAGE_USER } = process.env ?? {};

View File

@@ -1,6 +1,7 @@
const fs = require('fs').promises;
const express = require('express');
const { EnvVar } = require('@librechat/agents');
const { logger } = require('@librechat/data-schemas');
const {
Time,
isUUID,
@@ -30,7 +31,6 @@ const { cleanFileName } = require('~/server/utils/files');
const { getAssistant } = require('~/models/Assistant');
const { getAgent } = require('~/models/Agent');
const { getLogStores } = require('~/cache');
const { logger } = require('~/config');
const { Readable } = require('stream');
const router = express.Router();

Some files were not shown because too many files have changed in this diff Show More