Commit graph

924 commits

Author SHA1 Message Date
Yuichi Oneda
8c404ae056
💬 feat: Temporary Chats (#5493)
* feat: add expiredAt property to Conversation and Message models

Added `expiredAt` property to both Conversation and Message schemas.
Configured `expireAfterSeconds` index in MongoDB to automatically delete documents after a specified period.

* feat(data-provider): add isTemporary and expiredAt properties to support temporary chats

Added `isTemporary` property to TPayload and TSubmission for API calls for temporary chat.
Additionally, added `expiredAt` property to `tConversationSchema` to determine if a chat is temporary.

* feat: implement isTemporary state management

Add Recoil state for tracking temporary conversations, update event handlers to respect temporary chat status

* feat: add configuration to interfaceconfig to hide the temporary chat switch

* feat: add Temporary Chat UI with switch and modify related behaviors

- Added a Temporary Chat switch button at the end of dropdown lists in each model.
- Updated the form background color to black when Temporary Chat is enabled.
- Modified Navigation to exclude Temporary Chats from the chat list.

* fix: exclude Temporary Chats from search results

Updated the getConvosQueried query to ensure that Temporary Chats are not included in the search results.

* fix: hide bookmark button for Temporary Chats

Updated the UI to ensure that the bookmark button is not displayed when a chat is as Temporary Chat.

* chore: update isTemporary state management in ChatRoute

* chore: fix to pass the tests
2025-02-06 11:11:47 -05:00
Marco Beretta
73fe0835cf
🎨 style: Prompt UI Refresh & A11Y Improvements (#5614)
* 🚀 feat: Add animated search input and improve filtering UI

* 🏄 refactor: Clean up category options and optimize event handlers in ChatGroupItem

* 🚀 refactor: 'Rename Prompt' option and enhance prompt filtering UI
Changed the useUpdatePromptGroup mutation in prompts.ts to replace the JSON.parse(JSON.stringify(...)) clones with structuredClone. This avoids errors when data contains non‑JSON values and improves data cloning reliability

* 🔧 refactor: Update Sharing Prompts UI; fix: Show info message only after updating switch status

* 🔧 refactor: Simplify condition checks and replace button with custom Button component in SharePrompt

* 🔧 refactor: Update DashGroupItem styles and improve accessibility with updated aria-label

* 🔧 refactor: Adjust layout styles in GroupSidePanel and enhance loading skeletons in List component

* 🔧 refactor: Improve layout and styling of AdvancedSwitch component; adjust DashBreadcrumb margin for better alignment

* 🔧 refactor: Add new surface colors for destructive actions and update localization strings for confirmation prompts

* 🔧 refactor: Update PromptForm and PromptName components for improved layout and styling; replace button with custom Button component

* 🔧 refactor: Enhance styling and layout of DashGroupItem, FilterPrompts, and Label components for improved user experience

* 🔧 refactor: Update DeleteBookmarkButton and Label components for improved layout and text handling

* 🔧 refactor: Simplify CategorySelector usage and update destructive surface colors for a11y

* 🔧 refactor: Update styling and layout of PromptName, SharePrompt, and DashGroupItem components; enhance Dropdown functionality with custom renderValue

* 🔧 refactor: Improve layout and styling of various components; update button sizes and localization strings for better accessibility and user experience

* 🔧 refactor: Add useCurrentPromptData hook and enhance RightPanel component; update CategorySelector for improved functionality and accessibility

* 🔧 refactor: Update input components and styling for Command and Description; enhance layout and accessibility in PromptVariables and PromptForm

* 🔧 refactor: Remove useCurrentPromptData hook and clean up related components; enhance PromptVersions layout

* 🔧 refactor: Enhance accessibility by adding aria-labels to buttons and inputs; improve localization for filter prompts

* 🔧 refactor: Enhance accessibility by adding aria-labels to various components; improve layout and styling in PromptForm and CategorySelector

* 🔧 refactor: Enhance accessibility by adding aria-labels to buttons and components; improve dialog roles and descriptions in SharePrompt and PromptForm

* 🔧 refactor: Improve accessibility by adding aria-labels and roles; enhance layout and styling in ChatGroupItem, ListCard, and ManagePrompts components

* 🔧 refactor: Update UI components for improved styling and accessibility; replace button elements with custom Button component and enhance layout in VariableForm, PromptDetails, and PromptVariables

* 🔧 refactor: Improve null checks for group and instanceProjectId in SharePrompt component; enhance readability and maintainability

* style: Enhance AnimatedSearchInput component with TypeScript types; improve conditional rendering for search states and accessibility

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2025-02-05 11:37:17 -05:00
Danny Avila
6c33dc2eb3
🤖 refactor: Prevent Vertex AI from Setting Parameter Defaults (#5653)
* refactor: remove google defaults

* refactor: improve GoogleClient stream handling and metadata usage

* chore: update @librechat/agents to version 2.0.1

* fix: return client instance in GoogleClient configuration
2025-02-04 21:45:43 -05:00
Danny Avila
0312d4f4f4
🔧 refactor: Revamp Model and Tool Filtering Logic (#5637)
* 🔧 fix: Update regex to correctly match OpenAI model identifiers

* 🔧 fix: Enhance tool filtering logic in ToolService to handle inclusion and exclusion criteria for basic tools and toolkits

* feat: support o3-mini Azure streaming

* chore: Update model filtering logic to exclude audio and realtime models

* ci: linting error
2025-02-03 16:08:34 -05:00
Ruben Talstra
7c8a930061
feat: added Github Enterprise SSO login (#5621)
* https://github.com/danny-avila/LibreChat/issues/2812

* refactored the code to simplify it.

* removed unneeded code

* removed unneeded code
2025-02-03 15:30:02 -05:00
Ruben Talstra
93f5713c74
🛜 ci: OpenID Strategy Test Async Handling (#5613) 2025-02-03 10:57:49 -05:00
Danny Avila
45dd2b262f
🛂 feat: OpenID Logout Redirect to end_session_endpoint (#5626)
* WIP: end session endpoint

* refactor: move useGetBannerQuery outside of package

* refactor: add queriesEnabled and move useGetEndpointsConfigQuery to data-provider (local)

* refactor: move useGetEndpointsQuery import to data-provider

* refactor: relocate useGetEndpointsQuery import to improve module organization

* refactor: move `useGetStartupConfig` from package to `~/data-provider`

* refactor: move useGetUserBalance to data-provider and update imports

* refactor: update query enabled conditions to include config check

* refactor: remove unused useConfigOverride import from useAppStartup

* refactor: integrate queriesEnabled state into file and search queries and move useGetSearchEnabledQuery to data-provider (local)

* refactor: move useGetUserQuery to data-provider and update imports

* refactor: enhance loginUser mutation with success and error handling as pass in options to hook

* refactor: update enabled condition in queries to handle undefined config

* refactor: enhance authentication mutations with queriesEnabled state management

* refactor: improve conditional rendering for error messages and feature flags in Login component

* refactor: remove unused queriesEnabled state from AuthContextProvider

* refactor: implement queriesEnabled state management in LoginLayout with timeout handling

* refactor: add conditional check for end session endpoint in OpenID strategy

* ci: fix tests after changes

* refactor: remove endSessionEndpoint from user schema and update logoutController to use OpenID issuer's end_session_endpoint

* refactor: update logoutController to use end_session_endpoint from issuer metadata
2025-02-03 10:53:04 -05:00
Danny Avila
d93f5c9061
☁️ feat: Additional AI Gateway Provider Support; fix: Reasoning Effort for Presets/Agents (#5600)
* 🐛 fix: Prevent processing of non-artifact nodes in artifact plugin

* refactor: remove deprecated fields, add `reasoning_effort`

* refactor: move `reasoning_effort` to the second column in OpenAI settings

* feat: add support for additional AI Gateway provider in extractBaseURL function

* refactor: move `reasoning_effort` field to conversationPreset and remove from agentOptions
2025-02-02 09:04:10 -05:00
Danny Avila
352565c9a6
🎥 feat: YouTube Tool (#5582)
* adding youtube tool

* refactor: use short `url` param instead of `videoUrl`

* refactor: move API key retrieval to a separate credentials module

* refactor: remove unnecessary `isEdited` message property

* refactor: remove unnecessary `isEdited` message property pt. 2

* refactor: YouTube Tool with new `tool()` generator, handle tools already created by new `tool` generator

* fix: only reset request data for multi-convo messages

* refactor: enhance YouTube tool by adding transcript parsing and returning structured JSON responses

* refactor: update transcript parsing to handle raw response and clean up text output

* feat: support toolkits and refactor YouTube tool as a toolkit for better LLM usage

* refactor: remove unused OpenAPI specs and streamline tools transformation in loadAsyncEndpoints

* refactor: implement manifestToolMap for better tool management and streamline authentication handling

* feat: support toolkits for assistants

* refactor: rename loadedTools to toolDefinitions for clarity in PluginController and assistant controllers

* feat: complete support of toolkits for assistants

---------

Co-authored-by: Danilo Pejakovic <danilo.pejakovic@leoninestudios.com>
2025-01-31 19:11:04 -05:00
Danny Avila
33f6093775
🤖 feat: o3-mini (#5581)
* 🤖 feat: `o3-mini`

* chore: re-order vision models list to prioritize gpt-4o as a vision model over o1
2025-01-31 16:49:01 -05:00
Danny Avila
fdf0b41d08
🐛 fix: Handle content generation errors in GoogleClient (#5575) 2025-01-31 11:22:15 -05:00
Danny Avila
6920e23fb2
🤖 fix: Azure Agents after Upstream Breaking Change (#5571)
* 🤖 fix: Azure Agents after Upstream Breaking Change

* chore: bump @langchain/core & @librechat/agents

* fix: correct formatting in assistant actions update logic and use correctly filtered actions variable

* fix: linting errors
2025-01-31 09:50:49 -05:00
Ruben Talstra
e1a6268904
🍎 feat: Apple auth (#5473)
* implemented Apple Auth login.

Closes: #3438

TODO:
- write config Doc

* removed some comments

* removed comment

* Add unit tests for Apple login strategy

Introduce comprehensive tests for the Apple login strategy, covering new user creation, existing user updates, and error handling scenarios during the authentication flow. Mocks implemented for external dependencies to ensure isolated testing.

* Remove unnecessary blank line in socialLogins.js
2025-01-31 09:49:09 -05:00
owengo
8a0c7d92bd
👷 feat: Allow Admin to Edit Agent/Assistant Actions (#4591)
* feat: allows admin to see and edits all actions

* feat: allows admin to see and edits all actions

* rollback: admins can edit all actions, no configuration

* fix: admins don't override the user of existing actions and they preserve the user of the assistant when creating a new action

---------

Co-authored-by: Olivier Schiavo <olivier.schiavo@wengo.com>
2025-01-31 07:45:02 -05:00
Danny Avila
19fa4d9f54
🧹 chore: Remove Deprecated BingAI Code & Address Mobile Focus (#5565)
* chore: remove all bing code

* chore: remove bing code and auto-focus effects

* chore: add back escapeRegExp helper function for regex special character handling

* chore: remove deprecated fields from settings and conversation schema

* fix: ensure default endpoint is set correctly in conversation setup

* feat: add disableFocus option to newConversation for improved search behavior
2025-01-30 17:22:29 -05:00
James Lamine
1226f56d0c
🔧 fix: Add missing finish_reason to stream chunks (#5563) 2025-01-30 15:24:43 -05:00
James Lamine
85c6a706c3
🔧 fix: handle known OpenAI errors with empty intermediate reply (#5562) 2025-01-30 15:20:34 -05:00
Danny Avila
587d46a20b
🚀 feat: o1 Tool Calling & reasoning_effort (#5553)
* fix: Update @librechat/agents to version 1.9.98

* feat: o1 tool calling

* fix: Improve error logging in RouteErrorBoundary

* refactor: Move extractContent function to utils and clean up Artifact component

* refactor: optimize reasoning UI post-streaming and deprecate plugins rendering

* feat: reasoning_effort support

* fix: update request content type handling in openapiToFunction to remove default 'application/x-www-form-urlencoded'

* chore: bump v0.7.696 data-provider
2025-01-30 12:36:35 -05:00
Danny Avila
591a019766
🏄‍♂️ refactor: Optimize Reasoning UI & Token Streaming (#5546)
*  feat: Implement Show Thinking feature; refactor: testing thinking render optimizations

*  feat: Refactor Thinking component styles and enhance Markdown rendering

* chore: add back removed code, revert type changes

* chore: Add back resetCounter effect to Markdown component for improved code block indexing

* chore: bump @librechat/agents and google langchain packages

* WIP: reasoning type updates

* WIP: first pass, reasoning content blocks

* chore: revert code

* chore: bump @librechat/agents

* refactor: optimize reasoning tag handling

* style: ul indent padding

* feat: add Reasoning component to handle reasoning display

* feat: first pass, content reasoning part styling

* refactor: add content placeholder for endpoints using new stream handler

* refactor: only cache messages when requesting stream audio

* fix: circular dep.

* fix: add default param

* refactor: tts, only request after message stream, fix chrome autoplay

* style: update label for submitting state and add localization for 'Thinking...'

* fix: improve global audio pause logic and reset active run ID

* fix: handle artifact edge cases

* fix: remove unnecessary console log from artifact update test

* feat: add support for continued message handling with new streaming method

---------

Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
2025-01-29 19:46:58 -05:00
James Lamine
d60a149ad9
🗨️ fix: Loading Shared Saved Prompts (#5515) 2025-01-28 10:35:17 -05:00
Danny Avila
4110209494
♻️ fix: Prevent Instructions from Removal when nearing Max Context (#5516)
* refactor: getMessagesWithinTokenLimit to accept params object

* refactor: always include instructions in payload if provided

* ci: remove obsolete test

* refactor: update logoutUser to accept request object and handle session destruction

* test: enhance getMessagesWithinTokenLimit tests for instruction handling
2025-01-27 20:37:38 -05:00
Danny Avila
528ee62eb1
🤖 fix: GoogleClient Context Handling & GenAI Parameters (#5503)
* fix: remove legacy code for GoogleClient and fix model parameters for GenAI

* refactor: streamline client init logic

* refactor: remove legacy vertex clients, WIP remote vertex token count

* refactor: enhance GoogleClient with improved type definitions and streamline token count method

* refactor: remove unused methods and consolidate methods

* refactor: remove examples

* refactor: improve input handling logic in DynamicInput component

* refactor: enhance GoogleClient with token usage tracking and context handling improvements

* refactor: update GoogleClient to support 'learnlm' model and streamline model checks

* refactor: remove unused text model handling in GoogleClient

* refactor: record token usage for GoogleClient titles and handle edge cases

* chore: remove unused undici, addresses verbose version warning
2025-01-27 12:21:33 -05:00
Marco Beretta
e7de9c1576
🛡️ refactor: enhance email verification process (#5485) 2025-01-26 20:57:03 -05:00
Danny Avila
12a9a07eb0
🐛 fix: Update deletePromptController to include user role in query (#5488) 2025-01-26 19:03:12 -05:00
Danny Avila
8b31f255f5
🪙 fix: Deepseek Pricing 2025-01-25 10:13:46 -05:00
Danny Avila
60c846b679
🪙 fix: Deepseek Pricing & Titling (#5459) 2025-01-25 10:10:53 -05:00
Danny Avila
af430e46f4
feat: Add Google Parameters, Ollama/Openrouter Reasoning, & UI Optimizations (#5456)
* feat: Google Model Parameters

* fix: dynamic input number value, previously coerced by zod schema

* refactor: support openrouter reasoning tokens and XML for thinking directive to conform to ollama

* fix: virtualize combobox to prevent performance drop on re-renders of long model/agent/assistant lists

* refactor: simplify Fork component by removing unnecessary chat context index

* fix: prevent rendering of Thinking component when children are null

* refactor: update Markdown component to replace <think> tags and simplify remarkPlugins configuration

* refactor: reorder remarkPlugins to improve plugin configuration in Markdown component
2025-01-24 18:15:47 -05:00
Danny Avila
7818ae5c60
🐳 feat: Deepseek Reasoning UI (#5440) 2025-01-24 10:52:08 -05:00
Danny Avila
ed57bb4711
🚀 feat: Artifact Editing & Downloads (#5428)
* refactor: expand container

* chore: bump @codesandbox/sandpack-react to latest

* WIP: first pass, show editor

* feat: implement ArtifactCodeEditor and ArtifactTabs components for enhanced artifact management

* refactor: fileKey

* refactor: auto scrolling code editor and add messageId to artifact

* feat: first pass, editing artifact

* feat: first pass, robust artifact replacement

* fix: robust artifact replacement & re-render when expected

* feat: Download Artifacts

* refactor: improve artifact editing UX

* fix: layout shift of new download button

* fix: enhance missing output checks and logging in StreamRunManager
2025-01-23 18:19:04 -05:00
Danny Avila
87383fec27
🔧 chore: Update Deepseek Pricing, Google Safety Settings (#5409)
* fix: google-thinking model safety settings fix

* chore: update pricing/context for deepseek models

* ci: update Deepseek model token limits to use dynamic mapping
2025-01-22 07:50:09 -05:00
Danny Avila
199e5e6eaf
🛠️ fix: Optionally add OpenID Sig. Algo. from Server Discovery (#5398)
* fix: Optionally add OpenID Sig. Algorithm from Server Discovery

* chore: bump vite to 5.4.14 for CVE-2025-24010

* chore: remove deprecated code

* fix: install missing undici

* fix: Add @waylaidwanderer/fetch-event-source package
2025-01-21 21:49:27 -05:00
Marco Beretta
fa9e778399
🔗 feat: Enhance Share Functionality, Optimize DataTable & Fix Critical Bugs (#5220)
* 🔄 refactor: frontend and backend share link logic; feat: qrcode for share link; feat: refresh link

* 🐛 fix: Conditionally render shared link and refactor share link creation logic

* 🐛 fix: Correct conditional check for shareId in ShareButton component

* 🔄 refactor: Update shared links API and data handling; improve query parameters and response structure

* 🔄 refactor: Update shared links pagination and response structure; replace pageNumber with cursor for improved data fetching

* 🔄 refactor: DataTable performance optimization

* fix: delete shared link cache update

* 🔄 refactor: Enhance shared links functionality; add conversationId to shared link model and update related components

* 🔄 refactor: Add delete functionality to SharedLinkButton; integrate delete mutation and confirmation dialog

* 🔄 feat: Add AnimatedSearchInput component with gradient animations and search functionality; update search handling in API and localization

* 🔄 refactor: Improve SharedLinks component; enhance delete functionality and loading states, optimize AnimatedSearchInput, and refine DataTable scrolling behavior

* fix: mutation type issues with deleted shared link mutation

* fix: MutationOptions types

* fix: Ensure only public shared links are retrieved in getSharedLink function

* fix: `qrcode.react` install location

* fix: ensure non-public shared links are not fetched when checking for existing shared links, and remove deprecated .exec() method for queries

* fix: types and import order

* refactor: cleanup share button UI logic, make more intuitive

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2025-01-21 09:31:05 -05:00
Danny Avila
d6b4d83b68
🔥 feat: deepseek-reasoner Thought Streaming (#5379)
* 🔧 refactor: Remove unused penalties and enhance reasoning token handling in OpenAIClient

* 🔧 refactor: `addInstructions` default to adding instructions at index 0, flag for legacy behavior

* chore: remove long placeholder

* chore: update localization strings across multiple languages

* ci: adjust tests for new `addInstructions` behavior
2025-01-20 18:21:18 -05:00
Ragavendaran Puliyadi
a2305c3a7c
🐛 fix: use OpenID token signature algo as discovered from the server (#5348)
* 🐛 fix: use OpenID token signature algo as discovered from the server.

* 📜 refactor: Keeping other props that uses alg.

* 🔧 fix: handle missing property

* 📘 refactor: add comment block
2025-01-20 17:14:07 -05:00
Ragavendaran P R
d048a10b2e
📜 refactor: Log Error Messages when OAuth Fails (#5337) 2025-01-18 09:32:41 -05:00
Danny Avila
e6670cd411
🔧 chore: bump mongoose to patch CVE-2025-23061 (#5351) 2025-01-17 13:09:46 -05:00
Danny Avila
b35a8b78e2
🔧 refactor: Improve Agent Context & Minor Fixes (#5349)
* refactor: Improve Context for Agents

* 🔧 fix: Safeguard against undefined properties in OpenAIClient response handling

* refactor: log error before re-throwing for original stack trace

* refactor: remove toolResource state from useFileHandling, allow svg files

* refactor: prevent verbose logs from axios errors when using actions

* refactor: add silent method recordTokenUsage in AgentClient

* refactor: streamline token count assignment in BaseClient

* refactor: enhance safety settings handling for Gemini 2.0 model

* fix: capabilities structure in MCPConnection

* refactor: simplify civic integrity threshold handling in GoogleClient and llm

* refactor: update token count retrieval method in BaseClient tests

* ci: fix test for svg
2025-01-17 12:55:48 -05:00
Danny Avila
0855677a36
🌤️ feat: Add OpenWeather Tool for Weather Data Retrieval (#5246)
*  feat: Add OpenWeather Tool for Weather Data Retrieval 🌤️

* chore: linting

* chore: move test files

* fix: tool icon, allow user-provided keys, conform to app key assignment pattern

* chore: linting not included in #5212

---------

Co-authored-by: Jonathan Addington <jonathan.addington@jmaddington.com>
2025-01-10 08:54:08 -05:00
Danny Avila
ea1a5c8a30
🐛 fix: Handle optional endpoints in processModelSpecs function 2025-01-09 18:18:14 -05:00
Danny Avila
687ab32bd3
🔧 fix: Streamline Builder Links and Enhance UI Consistency (#5229)
* fix: Include iconURL in Bedrock client initialization

* fix: unnecessary filtering for agent file_search files

* chore: use theme bg colors

* refactor: rely on endpoint config for enabling builder links in side navigation instead of parameters

* fix: remove unnecessary keyProvided check for agent builder link
2025-01-09 12:03:35 -05:00
Lars Kiesow
dd927583a7
Provide production-ready memory store for eypress-session (#5212)
The `express-session` library comes with a session storage meant for
testing by default. That is why you get a message like this when you
start up LibreChat with OIDC enabled:

    Warning: connect.session() MemoryStore is not
    designed for a production environment, as it will leak
    memory, and will not scale past a single process.

LibreChat can already use Redis as a session storage, although Redis support
is still marked as experimental. It also makes the set-up more complex, since
you will need to configure and run yet another service.

This pull request provides a simple alternative by using a in-memory session
store marked as a production-ready alternative by the guys from
`express-session`¹. You can still configure Redis, but this provides a simple,
good default for everyone else.

See also https://github.com/danny-avila/LibreChat/discussions/1014

¹⁾ https://github.com/expressjs/session?tab=readme-ov-file#compatible-session-stores
2025-01-09 11:23:51 -05:00
Danny Avila
69a9b8b911
🐛 fix: Ensure Default ModelSpecs Are Set Correctly (#5218)
* 🐛 fix: default modelSpecs not being set

* feat: Add imageDetail parameter for OpenAI endpoints in tQueryParamsSchema

* feat: Implement processModelSpecs function to enhance model specs processing from configuration

* feat: Refactor configuration schemas and types for improved structure and clarity

* feat: Add append_current_datetime parameter to tQueryParamsSchema for enhanced endpoint functionality

* fix: Add endpointType to getSaveOptions and enhance endpoint handling in Settings component

* fix: Change endpointType to be nullable and optional in tConversationSchema for improved flexibility

* fix: allow save & submit for google endpoint
2025-01-08 21:57:00 -05:00
Danny Avila
916faf6447
🐛 fix: Correct Endpoint/Icon Handling, Update Module Resolutions (#5205)
* fix: agent modelSpec iconURLs not being recorded

* fix: prioritize message properties over conversation defaults in icon data

* fix: determine endpoint type from endpointsConfig

* chore: type issue with setting.columnSpan

* chore: remove redundant key indexing for keySchema

* chore: bump version to 0.7.691 in package.json

* chore: add stricter remark-gfm and mdast-util-gfm resolutions/overrides

* chore: remove rollup override and bump vite-plugin-pwa

* chore: reinstall remark-gfm for correct module resolution

* chore: reinstall vite-plugun-pwa
2025-01-07 11:09:18 -05:00
Danny Avila
7c61115a88
🐛 fix: Prevent Default Values in OpenAI/Custom Endpoint Agents (#5180)
* fix: prevent OpenAI/custom-endpoint agents from using default values

* fix: order of assigning client options

* chore: typing for runnable config
2025-01-04 09:41:59 -05:00
Danny Avila
c26b54c74d
🔄 refactor: Consolidate Tokenizer; Fix Jest Open Handles (#5175)
* refactor: consolidate tokenizer to singleton

* fix: remove legacy tokenizer code, add Tokenizer singleton tests

* ci: fix jest open handles
2025-01-03 18:11:14 -05:00
Danny Avila
bf0a84e45a
®️ feat: Support Rscript for Code Interpreter & recursionLimit for Agents (#5170)
* chore: bump @librechat/agents to v1.9.8 for rscript support

* chore: fix @langchain/google-genai dep., match agents

* chore: fix @langchain/google-vertexai to v0.1.5, match with agents

* chore: bump @librechat/agents to v1.9.9

* chore: update @librechat/agents to v1.9.91 and @langchain/google-vertexai to v0.1.6

* chore: increase MAX_FILE_SIZE to 150MB for file uploads

* chore: bump @librechat/agents to v1.9.92

* feat: support `recursionLimit` for agents

* chore: update configuration version to 1.2.1 in librechat.yaml and config.ts

* feat: add R language SVG icon to the assets and include it in ApiKeyDialog

* feat: add support for new vision model 'o1' and exclude 'o1-mini'
2025-01-03 16:50:00 -05:00
Thinger Soft
65b2d647a1
🔧 fix: Handle Concurrent File Mgmt. For Agents (#5159)
* fix: handle concurrent file upload for agents rag

Closes #4746:

* fix: handle concurrent file deletions for agents rag

Closes #5160:

* refactor: remove useless promise wrapping
2025-01-02 08:29:07 -05:00
Danny Avila
6c9a468b8e
🐛 fix: Artifacts Type Error, Tool Token Counts, and Agent Chat Import (#5142)
* fix: message import functionality to support content field

* fix: handle tool calls token counts in context window management

* fix: handle potential undefined size in FilePreview component
2024-12-30 13:01:47 -05:00
Danny Avila
d9c59b08e6
🔑 feat: Implement TTL Mgmt. for In-Memory Keyv Stores (#5127)
This commit updates the cache stores in the `getLogStores.js` file to use Redis as the store if the `USE_REDIS` environment variable is enabled. It also adds a new environment variable `DEBUG_MEMORY_CACHE` to enable debugging of the memory cache.
2024-12-28 17:32:05 -05:00
Danny Avila
24cad6bbd4
🤖 feat: Support Google Agents, fix Various Provider Configurations (#5126)
* feat: Refactor ModelEndHandler to collect usage metadata only if it exists

* feat: google tool end handling, custom anthropic class for better token ux

* refactor: differentiate between client <> request options

* feat: initial support for google agents

* feat: only cache messages with non-empty text

* feat: Cache non-empty messages in chatV2 controller

* fix: anthropic llm client options llmConfig

* refactor: streamline client options handling in LLM configuration

* fix: VertexAI Agent Auth & Tool Handling

* fix: additional fields for llmConfig, however customHeaders are not supported by langchain, requires PR

* feat: set default location for vertexai LLM configuration

* fix: outdated OpenAI Client options for getLLMConfig

* chore: agent provider options typing

* chore: add note about currently unsupported customHeaders in langchain GenAI client

* fix: skip transaction creation when rawAmount is NaN
2024-12-28 17:15:03 -05:00