Commit graph

20 commits

Author SHA1 Message Date
Danny Avila
3f2e4777cb
🛬 fix: Land MCP OAuth Callbacks on Waiting Connections (#15876)
* 🪪 fix: Adopt MCP OAuth Callback Tokens Without Re-Prompting or Losing the Lease

A chat request loading OAuth tokens joins the `mcp_get_tokens` flow a catalog
discovery left behind and polls it. The OAuth callback deletes that entry when
it stores the new tokens, so the poll ends with "Flow state not found", the
factory reports the tokens missing, drops the `mcp_oauth` flow the callback
just completed, and starts a second interactive flow. Once tokens arrive, the
connection leases the publication generation it captured before the wait; the
callback's publication moved it, so the connection is torn down as it connects
and the agent fails with AGENT_EXPECTED_MCP_TOOLS_UNAVAILABLE.

`createFlowWithHandler` now serves a completed result at once, monitors only
pending attempts and retained failures, and replaces a failure nobody retains;
a waiter whose flow disappears gets `FlowStateNotFoundError`. The factory
treats that as a credential change: it re-reads storage once, after letting
the connection build re-capture its generation. The authorization transaction
and a silent refresh attach the generation they publish to the tokens they
release, and a build adopts that generation for credentials obtained after
its capture.

* 🪪 fix: Claim Flow Attempts Atomically and Lease Under the Stored Generation

A connection now adopts a carried publication generation only while it is the
generation currently stored, instead of comparing the token's exchange time to
its capture, so a callback that exchanged before the build began and published
after it is still adopted and a retired generation still leaves the fence in
place. Installing a flow attempt is an atomic compare-and-set against the
attempt the caller observed, on Redis and on the default in-memory store, so
concurrent replacements of a failed attempt, or concurrent creations of an
absent one, run one handler while the rest join it. An aborted caller is
rejected before a cached result is served, and a joiner that aborts leaves the
shared flow to its owner and the other waiters.

* 🪪 fix: Return Generation-Tagged Callback Tokens and Route Flow Claims Through the Cluster Executor

The authorization transaction now returns the same generation-tagged tokens it
releases to the OAuth completion and the pending token waiters, so the callback
route's tool-flow completion carries the published generation to the connection
waiting on it. The Action OAuth and index-sync flow managers pass the
cluster-aware Redis script executor, so their flow claims and guarded
settlements route through slot-master selection and READONLY recovery instead
of the raw client.
2026-09-13 01:46:41 -04:00
Danny Avila
601ed07870
🫧 fix: Retire Cancelled MCP OAuth State (#15702)
* fix: Clean Up MCP OAuth Teardown State

* fix: Harden OAuth Teardown Boundaries

* fix: harden MCP OAuth teardown races

* fix: avoid flow cache dependency cycle

* fix: bind OAuth teardown to credential generations

* test: cover active OAuth server fixtures

* style: sort OAuth cleanup imports

* fix: discard mismatched OAuth token snapshots

* fix: fence OAuth teardown across callback races

* test: align OAuth callback fixtures with server fencing

* test: complete OAuth callback server fixtures

* fix: version OAuth flow settlement

* fix: fence OAuth teardown snapshots

* test: align OAuth teardown fixtures

* test: complete OAuth snapshot fixtures

* fix: snapshot OAuth deletion lifecycle

* test: bind OAuth revocation snapshots

* test: assert per-record OAuth fence

* fix: harden MCP OAuth teardown consistency

* test: expect snapshotted OAuth readers
2026-09-07 15:43:02 -04:00
Danny Avila
56175af0b5
🎟️ fix: Reconcile MCP OAuth Readiness Across Pods (#14629)
* fix: stabilize MCP OAuth readiness across pods

* fix: harden MCP readiness review findings

* fix: resolve CI type check and terminal OAuth polling

* fix: address MCP OAuth readiness review

* fix: align MCP OAuth readiness state

* test: stabilize MCP OAuth readiness assertion

* fix: reject stale MCP OAuth callbacks

* fix: close distributed MCP OAuth readiness gaps

* style: sort Redis MCP test imports

* fix: preserve MCP OAuth polling across rolling pods

* fix: finalize distributed MCP OAuth readiness

* fix: preserve runtime-detected MCP OAuth

* fix: report runtime MCP OAuth readiness

* fix: preserve live MCP OAuth classification

* style: sort MCP connection imports
2026-08-05 19:42:26 -04:00
Danny Avila
c04bddd304
🪵 refactor: Bound Log Traversal And Remove Legacy api/config Logger (#13813)
Some checks are pending
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Waiting to run
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Waiting to run
GitNexus Index / index (push) Waiting to run
GitNexus Index / post-index (push) Blocked by required conditions
* 🛡️ fix: Bound object-traverse against DAG fan-out and shared refs

Detect cycles via the ancestor chain (so shared, non-circular references in sibling branches / DAGs are traversed correctly) and add defensive maxNodes (100k) / maxDepth (100) caps. The removed global visited set was implicitly bounding work at O(distinct nodes); ancestor-chain-only detection is O(root-to-node paths), exponential on DAGs (a depth-24 diamond went from 26 to 50M visits / 1.6s of synchronous work). The caps bound it to ~9ms while leaving normal traversal untouched. Adds a spec covering shared refs, cycles, DAGs, and both bounds. The lone consumer, debugTraverse, inherits the defaults with no change.

* 🪵 refactor: Remove legacy api/config logger duplicate

The api/config winston logger was a stale parallel implementation of the canonical @librechat/data-schemas logger, with unbounded redaction (regex-only redactFormat, npm traverse-based debugTraverse). Its winston instance and the logger export from api/config/index.js had zero consumers — every ~/config importer uses the MCP/flow-manager exports. The only live tie was ToolService's use of redactMessage.

Re-export redactMessage from @librechat/data-schemas (behaviorally identical, a superset of the regex set), point ToolService at it, delete api/config/winston.js and api/config/parsers.js, drop the dead logger export, and remove the orphaned ~/config/parsers mock from the global test setup.

* 🧹 chore: Drop orphaned traverse dep and stale legacy logger tests

Deleting api/config/{winston,parsers}.js left the npm 'traverse' package unused in api/package.json (flagged by the detect-unused-packages CI check) and orphaned two tests that imported the deleted modules. Remove the traverse dependency (sync package-lock), and delete api/config/__tests__/{parsers,logToFile}.spec.js — the canonical logger's behavior is covered by packages/data-schemas/src/config/parsers.spec.ts.

* 🩹 fix: Make object-traverse caps bound work and survive update()

Address Codex review: (1) break the child loops as soon as the node budget is spent and iterate objects via for...in instead of materializing Object.entries/Object.keys, so maxNodes actually bounds work for wide arrays/objects; (2) detect ancestor cycles against an immutable original-node stack rather than context.node, which a callback's update() can reassign (the debug formatter rewrites array nodes in place). Adds tests for the wide-array bound and the update()-cycle case.

* 🎚️ fix: Tighten object-traverse defaults to a ~1ms log budget

Lower maxNodes 100000 -> 2500 and maxDepth 100 -> 5. Measured cost is ~140ns/node with the debug formatter callback, so 2500 nodes keeps a single log under ~1ms even on slower prod hardware; real log objects are ~25-30 nodes at depth 3-4, leaving ample headroom. maxNodes is the fan-out/cost lever; maxDepth bounds recursion and output readability (depth-5 covers typical logs, deeper renders compactly).
2026-06-17 12:31:32 -04:00
Danny Avila
a7f16911b2
⏳ fix: Extend and Decouple MCP OAuth Flow Timeouts (#13622)
* ⏳ fix: Extend and decouple MCP OAuth flow timeouts

The OAuth auth button disappeared after 2 minutes (the internal OAuth
handling timeout) while the flow state lived for 3 minutes, leaving users
who didn't click immediately stuck in an unrecoverable re-auth loop. The
handling timeouts also reused the connection/init timeout, so a short
initTimeout would shrink the OAuth window further.

- Add MCP_OAUTH_HANDLING_TIMEOUT (10m) and MCP_OAUTH_FLOW_TTL (15m) to mcpConfig
- Decouple the reactive/proactive OAuth waits from initTimeout/connectionTimeout
- Use OAUTH_FLOW_TTL for the FlowStateManager TTL and the UI status window
- Ensure the flow TTL outlives the handling timeout, fixing the
  "Flow state not found" race
- Remove dead FLOW_TTL constant and document new env vars

Fixes #13615

* ⏳ fix: Coordinate OAuth pending window with handling timeout

Address Codex review: the extended OAuth wait was still capped by other
timeouts that were not updated.

- Align PENDING_STALE_MS (button validity + pending-flow reuse window)
  with MCP_OAUTH_HANDLING_TIMEOUT so a flow stays reusable for the full
  wait instead of 2 minutes (Finding 3)
- Clamp MCP_OAUTH_FLOW_TTL to never fall below the handling timeout so a
  callback near the deadline still finds its flow state (Finding 2)
- Floor attemptToConnect's timeout to the handling window for OAuth
  servers so the reactive in-connect OAuth wait is not killed by the
  30s connection timeout (Finding 1)
- Update flow staleness tests to reference the threshold symbolically

* ⏳ fix: Align OAuth window across status, action flows, and client polling

Address Codex round 2: extending the server wait exposed three more
windows that were still capped or now over-extended.

- checkOAuthFlowStatus reports a PENDING flow as active only within the
  usable PENDING_STALE_MS window, not the longer Keyv retention TTL, so
  the connect button reappears instead of a stuck 'connecting' state
- Give Action (custom tool) OAuth its own FlowStateManager on the prior
  3-minute TTL so the longer MCP OAuth TTL can't leave an action tool
  call waiting up to 15 minutes
- Extend the MCP server-card client polling to the 10-minute handling
  window so a user who completes OAuth after 3 minutes is still picked up

* 🧪 test: Make stale-flow CSRF test track PENDING_STALE_MS

The CSRF-fallback stale-flow test hardcoded a 3-minute age, which is now
within the 10-minute PENDING_STALE_MS window and was wrongly treated as
active. Derive the age from PENDING_STALE_MS so it tracks the constant.

* ⏳ fix: Add grace buffers and surface OAuth timeout to the client

Address Codex round 3 (near-deadline edges):

- Clamp MCP_OAUTH_FLOW_TTL to handling timeout + 60s grace (not equality),
  so flow state outlives the wait instead of expiring at the same instant
- Extend attemptToConnect's OAuth floor by a 60s grace so a user who
  authorizes near the deadline still gets the post-OAuth reconnect
- Surface OAUTH_HANDLING_TIMEOUT on the connection-status response and
  have the client poll for the configured window instead of a hardcoded
  10 minutes, so a tuned server deadline isn't capped on the client

* ⏳ fix: Refresh client OAuth timeout from the first status refetch

If the connection-status cache is empty when polling starts, the client
captured the 10-minute fallback and never picked up a tuned oauthTimeout.
Re-read it after each refetch so a longer configured deadline is honored
even on a cold cache.

* 📝 refactor: Type oauthTimeout on MCPConnectionStatusResponse

Declare the oauthTimeout field on the shared response type in
data-provider instead of an ad-hoc inline cast in the client hook, and
replace the pre-existing 'as any' on the status query read with the
typed getQueryData. Type-level only; no runtime change.
2026-06-09 17:50:02 -04:00
Atef Bellaaj
ad6ba4b6d1
🧬 refactor: Wire Database Methods into MCP Package via Registry Pattern (#10715)
* Refactor: MCPServersRegistry Singleton Pattern with Dependency Injection for DB methods consumption

* refactor: error handling in MCP initialization and improve logging for MCPServersRegistry instance creation.

- Added checks for mongoose instance in ServerConfigsDB constructor and refined error messages for clarity.
- Reorder and use type imports

---------

Co-authored-by: Atef Bellaaj <slalom.bellaaj@external.daimlertruck.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
2025-12-11 16:37:12 -05:00
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
Theo N. Truong
8780a78165
♻️ refactor: MCPManager for Scalability, Fix App-Level Detection, Add Lazy Connections (#8930)
* feat: MCP Connection management overhaul - Making MCPManager manageable

Refactor the monolithic MCPManager into focused, single-responsibility classes:

• MCPServersRegistry: Server configuration discovery and metadata management
• UserConnectionManager: Manages user-level connections
• ConnectionsRepository: Low-level connection pool with lazy loading
• MCPConnectionFactory: Handles MCP connection creation with OAuth support

New Features:
• Lazy loading of app-level connections for horizontal scaling
• Automatic reconnection for app-level connections
• Enhanced OAuth detection with explicit requiresOAuth flag
• Centralized MCP configuration management

Bug Fixes:
• App-level connection detection in MCPManager.callTool
• MCP Connection Reinitialization route behavior

Optimizations:
• MCPConnection.isConnected() caching to reduce overhead
• Concurrent server metadata retrieval instead of sequential

This refactoring addresses scalability bottlenecks and improves reliability
while maintaining backward compatibility with existing configurations.

* feat: Enabled import order in eslint.

* # Moved tests to __tests__ folder
# added tests for MCPServersRegistry.ts

* # Add unit tests for ConnectionsRepository functionality

* # Add unit tests for MCPConnectionFactory functionality

* # Reorganize MCP connection tests and improve error handling

* # reordering imports

* # Update testPathIgnorePatterns in jest.config.mjs to exclude development TypeScript files

* # removed mcp/manager.ts
2025-08-13 11:45:06 -04:00
Danny Avila
ec7370dfe9
🪐 feat: MCP OAuth 2.0 Discovery Support (#7924)
* chore: Update @modelcontextprotocol/sdk to version 1.12.3 in package.json and package-lock.json

- Bump version of @modelcontextprotocol/sdk to 1.12.3 to incorporate recent updates.
- Update dependencies for ajv and cross-spawn to their latest versions.
- Add ajv as a new dependency in the sdk module.
- Include json-schema-traverse as a new dependency in the sdk module.

* feat: @librechat/auth

* feat: Add crypto module exports to auth package

- Introduced a new crypto module by creating index.ts in the crypto directory.
- Updated the main index.ts of the auth package to export from the new crypto module.

* feat: Update package dependencies and build scripts for auth package

- Added @librechat/auth as a dependency in package.json and package-lock.json.
- Updated build scripts to include the auth package in both frontend and bun build processes.
- Removed unused mongoose and openid-client dependencies from package-lock.json for cleaner dependency management.

* refactor: Migrate crypto utility functions to @librechat/auth

- Replaced local crypto utility imports with the new @librechat/auth package across multiple files.
- Removed the obsolete crypto.js file and its exports.
- Updated relevant services and models to utilize the new encryption and decryption methods from @librechat/auth.

* feat: Enhance OAuth token handling and update dependencies in auth package

* chore: Remove Token model and TokenService due to restructuring of OAuth handling

- Deleted the Token.js model and TokenService.js, which were responsible for managing OAuth tokens.
- This change is part of a broader refactor to streamline OAuth token management and improve code organization.

* refactor: imports from '@librechat/auth' to '@librechat/api' and add OAuth token handling functionality

* refactor: Simplify logger usage in MCP and FlowStateManager classes

* chore: fix imports

* feat: Add OAuth configuration schema to MCP with token exchange method support

* feat: FIRST PASS Implement MCP OAuth flow with token management and error handling

- Added a new route for handling OAuth callbacks and token retrieval.
- Integrated OAuth token storage and retrieval mechanisms.
- Enhanced MCP connection to support automatic OAuth flow initiation on 401 errors.
- Implemented dynamic client registration and metadata discovery for OAuth.
- Updated MCPManager to manage OAuth tokens and handle authentication requirements.
- Introduced comprehensive logging for OAuth processes and error handling.

* refactor: Update MCPConnection and MCPManager to utilize new URL handling

- Added a `url` property to MCPConnection for better URL management.
- Refactored MCPManager to use the new `url` property instead of a deprecated method for OAuth handling.
- Changed logging from info to debug level for flow manager and token methods initialization.
- Improved comments for clarity on existing tokens and OAuth event listener setup.

* refactor: Improve connection timeout error messages in MCPConnection and MCPManager and use initTimeout for connection

- Updated the connection timeout error messages to include the duration of the timeout.
- Introduced a configurable `connectTimeout` variable in both MCPConnection and MCPManager for better flexibility.

* chore: cleanup MCP OAuth Token exchange handling; fix: erroneous use of flowsCache and remove verbose logs

* refactor: Update MCPManager and MCPTokenStorage to use TokenMethods for token management

- Removed direct token storage handling in MCPManager and replaced it with TokenMethods for better abstraction.
- Refactored MCPTokenStorage methods to accept parameters for token operations, enhancing flexibility and readability.
- Improved logging messages related to token persistence and retrieval processes.

* refactor: Update MCP OAuth handling to use static methods and improve flow management

- Refactored MCPOAuthHandler to utilize static methods for initiating and completing OAuth flows, enhancing clarity and reducing instance dependencies.
- Updated MCPManager to pass flowManager explicitly to OAuth handling methods, improving flexibility in flow state management.
- Enhanced comments and logging for better understanding of OAuth processes and flow state retrieval.

* refactor: Integrate token methods into createMCPTool for enhanced token management

* refactor: Change logging from info to debug level in MCPOAuthHandler for improved log management

* chore: clean up logging

* feat: first pass, auth URL from MCP OAuth flow

* chore: Improve logging format for OAuth authentication URL display

* chore: cleanup mcp manager comments

* feat: add connection reconnection logic in MCPManager

* refactor: reorganize token storage handling in MCP

- Moved token storage logic from MCPManager to a new MCPTokenStorage class for better separation of concerns.
- Updated imports to reflect the new token storage structure.
- Enhanced methods for storing, retrieving, updating, and deleting OAuth tokens, improving overall token management.

* chore: update comment for SYSTEM_USER_ID in MCPManager for clarity

* feat: implement refresh token functionality in MCP

- Added refresh token handling in MCPManager to support token renewal for both app-level and user-specific connections.
- Introduced a refreshTokens function to facilitate token refresh logic.
- Enhanced MCPTokenStorage to manage client information and refresh token processes.
- Updated logging for better traceability during token operations.

* chore: cleanup @librechat/auth

* feat: implement MCP server initialization in a separate service

- Added a new service to handle the initialization of MCP servers, improving code organization and readability.
- Refactored the server startup logic to utilize the new initializeMCP function.
- Removed redundant MCP initialization code from the main server file.

* fix: don't log auth url for user connections

* feat: enhance OAuth flow with success and error handling components

- Updated OAuth callback routes to redirect to new success and error pages instead of sending status messages.
- Introduced `OAuthSuccess` and `OAuthError` components to provide user feedback during authentication.
- Added localization support for success and error messages in the translation files.
- Implemented countdown functionality in the success component for a better user experience.

* fix: refresh token handling for user connections, add missing URL and methods

- add standard enum for system user id and helper for determining app-lvel vs. user-level connections

* refactor: update token handling in MCPManager and MCPTokenStorage

* fix: improve error logging in OAuth authentication handler

* fix: concurrency issues for both login url emission and concurrency of oauth flows for shared flows (same user, same server, multiple calls for same server)

* fix: properly fail shared flows for concurrent server calls and prevent duplication of tokens

* chore: remove unused auth package directory from update configuration

* ci: fix mocks in samlStrategy tests

* ci: add mcpConfig to AppService test setup

* chore: remove obsolete MCP OAuth implementation documentation

* fix: update build script for API to use correct command

* chore: bump version of @librechat/api to 1.2.4

* fix: update abort signal handling in createMCPTool function

* fix: add optional clientInfo parameter to refreshTokensFunction metadata

* refactor: replace app.locals.availableTools with getCachedTools in multiple services and controllers for improved tool management

* fix: concurrent refresh token handling issue

* refactor: add signal parameter to getUserConnection method for improved abort handling

* chore: JSDoc typing for `loadEphemeralAgent`

* refactor: update isConnectionActive method to use destructured parameters for improved readability

* feat: implement caching for MCP tools to handle app-level disconnects for loading list of tools

* ci: fix agent test
2025-06-17 13:50:33 -04:00
Danny Avila
5f2d1c5dc9
👁️ feat: Azure Mistral OCR Strategy (#7888)
* 👁️ feat: Add Azure Mistral OCR strategy and endpoint integration

This commit introduces a new OCR strategy named 'azure_mistral_ocr', allowing the use of a Mistral OCR endpoint deployed on Azure. The configuration, schemas, and file upload strategies have been updated to support this integration, enabling seamless OCR processing via Azure-hosted Mistral services.

* 🗑️ chore: Clean up .gitignore by removing commented-out uncommon directory name

* chore: remove unused vars

* refactor: Move createAxiosInstance to packages/api/utils and update imports

- Removed the createAxiosInstance function from the config module and relocated it to a new utils module for better organization.
- Updated import paths in relevant files to reflect the new location of createAxiosInstance.
- Added tests for createAxiosInstance to ensure proper functionality and proxy configuration handling.

* chore: move axios helpers to packages/api

- Added logAxiosError function to @librechat/api for centralized error logging.
- Updated imports across various files to use the new logAxiosError function.
- Removed the old axios.js utility file as it is no longer needed.

* chore: Update Jest moduleNameMapper for improved path resolution

- Added a new mapping for '~/' to resolve module paths in Jest configuration, enhancing import handling for the project.

* feat: Implement Mistral OCR API integration in TS

* chore: Update MistralOCR tests based on new imports

* fix: Enhance MistralOCR configuration handling and tests

- Introduced helper functions for resolving configuration values from environment variables or hardcoded settings.
- Updated the uploadMistralOCR and uploadAzureMistralOCR functions to utilize the new configuration resolution logic.
- Improved test cases to ensure correct behavior when mixing environment variables and hardcoded values.
- Mocked file upload and signed URL responses in tests to validate functionality without external dependencies.

* feat: Enhance MistralOCR functionality with improved configuration and error handling

- Introduced helper functions for loading authentication configuration and resolving values from environment variables.
- Updated uploadMistralOCR and uploadAzureMistralOCR functions to utilize the new configuration logic.
- Added utility functions for processing OCR results and creating error messages.
- Improved document type determination and result aggregation for better OCR processing.

* refactor: Reorganize OCR type imports in Mistral CRUD file

- Moved OCRResult, OCRResultPage, and OCRImage imports to a more logical grouping for better readability and maintainability.

* feat: Add file exports to API and create files index

* chore: Update OCR types for enhanced structure and clarity

- Redesigned OCRImage interface to include mandatory fields and improved naming conventions.
- Added PageDimensions interface for better representation of page metrics.
- Updated OCRResultPage to include dimensions and mandatory images array.
- Refined OCRResult to include document annotation and usage information.

* refactor: use TS counterpart of uploadOCR methods

* ci: Update MistralOCR tests to reflect new OCR result structure

* chore: Bump version of @librechat/api to 1.2.3 in package.json and package-lock.json

* chore: Update CONFIG_VERSION to 1.2.8

* chore: remove unused sendEvent function from config module (now imported from '@librechat/api')

* chore: remove MistralOCR service files and tests (now in '@librechat/api')

* ci: update logger import in ModelService tests to use @librechat/data-schemas

---------

Co-authored-by: arthurolivierfortin <arthurolivier.fortin@gmail.com>
2025-06-13 15:14:57 -04:00
Danny Avila
29ef91b4dd
🧠 feat: User Memories for Conversational Context (#7760)
* 🧠 feat: User Memories for Conversational Context

chore: mcp typing, use `t`

WIP: first pass, Memories UI

- Added MemoryViewer component for displaying, editing, and deleting user memories.
- Integrated data provider hooks for fetching, updating, and deleting memories.
- Implemented pagination and loading states for better user experience.
- Created unit tests for MemoryViewer to ensure functionality and interaction with data provider.
- Updated translation files to include new UI strings related to memories.

chore: move mcp-related files to own directory

chore: rename librechat-mcp to librechat-api

WIP: first pass, memory processing and data schemas

chore: linting in fileSearch.js query description

chore: rename librechat-api to @librechat/api across the project

WIP: first pass, functional memory agent

feat: add MemoryEditDialog and MemoryViewer components for managing user memories

- Introduced MemoryEditDialog for editing memory entries with validation and toast notifications.
- Updated MemoryViewer to support editing and deleting memories, including pagination and loading states.
- Enhanced data provider to handle memory updates with optional original key for better management.
- Added new localization strings for memory-related UI elements.

feat: add memory permissions management

- Implemented memory permissions in the backend, allowing roles to have specific permissions for using, creating, updating, and reading memories.
- Added new API endpoints for updating memory permissions associated with roles.
- Created a new AdminSettings component for managing memory permissions in the frontend.
- Integrated memory permissions into the existing roles and permissions schemas.
- Updated the interface to include memory settings and permissions.
- Enhanced the MemoryViewer component to conditionally render admin settings based on user roles.
- Added localization support for memory permissions in the translation files.

feat: move AdminSettings component to a new position in MemoryViewer for better visibility

refactor: clean up commented code in MemoryViewer component

feat: enhance MemoryViewer with search functionality and improve MemoryEditDialog integration

- Added a search input to filter memories in the MemoryViewer component.
- Refactored MemoryEditDialog to accept children for better customization.
- Updated MemoryViewer to utilize the new EditMemoryButton and DeleteMemoryButton components for editing and deleting memories.
- Improved localization support by adding new strings for memory filtering and deletion confirmation.

refactor: optimize memory filtering in MemoryViewer using match-sorter

- Replaced manual filtering logic with match-sorter for improved search functionality.
- Enhanced performance and readability of the filteredMemories computation.

feat: enhance MemoryEditDialog with triggerRef and improve updateMemory mutation handling

feat: implement access control for MemoryEditDialog and MemoryViewer components

refactor: remove commented out code and create runMemory method

refactor: rename role based files

feat: implement access control for memory usage in AgentClient

refactor: simplify checkVisionRequest method in AgentClient by removing commented-out code

refactor: make `agents` dir in api package

refactor: migrate Azure utilities to TypeScript and consolidate imports

refactor: move sanitizeFilename function to a new file and update imports, add related tests

refactor: update LLM configuration types and consolidate Azure options in the API package

chore: linting

chore: import order

refactor: replace getLLMConfig with getOpenAIConfig and remove unused LLM configuration file

chore: update winston-daily-rotate-file to version 5.0.0 and add object-hash dependency in package-lock.json

refactor: move primeResources and optionalChainWithEmptyCheck functions to resources.ts and update imports

refactor: move createRun function to a new run.ts file and update related imports

fix: ensure safeAttachments is correctly typed as an array of TFile

chore: add node-fetch dependency and refactor fetch-related functions into packages/api/utils, removing the old generators file

refactor: enhance TEndpointOption type by using Pick to streamline endpoint fields and add new properties for model parameters and client options

feat: implement initializeOpenAIOptions function and update OpenAI types for enhanced configuration handling

fix: update types due to new TEndpointOption typing

fix: ensure safe access to group parameters in initializeOpenAIOptions function

fix: remove redundant API key validation comment in initializeOpenAIOptions function

refactor: rename initializeOpenAIOptions to initializeOpenAI for consistency and update related documentation

refactor: decouple req.body fields and tool loading from initializeAgentOptions

chore: linting

refactor: adjust column widths in MemoryViewer for improved layout

refactor: simplify agent initialization by creating loadAgent function and removing unused code

feat: add memory configuration loading and validation functions

WIP: first pass, memory processing with config

feat: implement memory callback and artifact handling

feat: implement memory artifacts display and processing updates

feat: add memory configuration options and schema validation for validKeys

fix: update MemoryEditDialog and MemoryViewer to handle memory state and display improvements

refactor: remove padding from BookmarkTable and MemoryViewer headers for consistent styling

WIP: initial tokenLimit config and move Tokenizer to @librechat/api

refactor: update mongoMeili plugin methods to use callback for better error handling

feat: enhance memory management with token tracking and usage metrics

- Added token counting for memory entries to enforce limits and provide usage statistics.
- Updated memory retrieval and update routes to include total token usage and limit.
- Enhanced MemoryEditDialog and MemoryViewer components to display memory usage and token information.
- Refactored memory processing functions to handle token limits and provide feedback on memory capacity.

feat: implement memory artifact handling in attachment handler

- Enhanced useAttachmentHandler to process memory artifacts when receiving updates.
- Introduced handleMemoryArtifact utility to manage memory updates and deletions.
- Updated query client to reflect changes in memory state based on incoming data.

refactor: restructure web search key extraction logic

- Moved the logic for extracting API keys from the webSearchAuth configuration into a dedicated function, getWebSearchKeys.
- Updated webSearchKeys to utilize the new function for improved clarity and maintainability.
- Prevents build time errors

feat: add personalization settings and memory preferences management

- Introduced a new Personalization tab in settings to manage user memory preferences.
- Implemented API endpoints and client-side logic for updating memory preferences.
- Enhanced user interface components to reflect personalization options and memory usage.
- Updated permissions to allow users to opt out of memory features.
- Added localization support for new settings and messages related to personalization.

style: personalization switch class

feat: add PersonalizationIcon and align Side Panel UI

feat: implement memory creation functionality

- Added a new API endpoint for creating memory entries, including validation for key and value.
- Introduced MemoryCreateDialog component for user interface to facilitate memory creation.
- Integrated token limit checks to prevent exceeding user memory capacity.
- Updated MemoryViewer to include a button for opening the memory creation dialog.
- Enhanced localization support for new messages related to memory creation.

feat: enhance message processing with configurable window size

- Updated AgentClient to use a configurable message window size for processing messages.
- Introduced messageWindowSize option in memory configuration schema with a default value of 5.
- Improved logic for selecting messages to process based on the configured window size.

chore: update librechat-data-provider version to 0.7.87 in package.json and package-lock.json

chore: remove OpenAPIPlugin and its associated tests

chore: remove MIGRATION_README.md as migration tasks are completed

ci: fix backend tests

chore: remove unused translation keys from localization file

chore: remove problematic test file and unused var in AgentClient

chore: remove unused import and import directly for JSDoc

* feat: add api package build stage in Dockerfile for improved modularity

* docs: reorder build steps in contributing guide for clarity
2025-06-07 18:52:22 -04:00
Danny Avila
64bd373bc8
🔧 fix: Keyv and Proxy Issues, and More Memory Optimizations (#6867)
* chore: update @librechat/agents dependency to version 2.4.15

* refactor: Prevent memory leaks by nullifying boundModel.client in disposeClient function

* fix: use of proxy, use undici

* chore: update @librechat/agents dependency to version 2.4.16

* Revert "fix: use of proxy, use undici"

This reverts commit 83153cd582.

* fix: ensure fetch is imported for HTTP requests

* fix: replace direct OpenAI import with CustomOpenAIClient from @librechat/agents

* fix: update keyv peer dependency to version 5.3.2

* fix: update keyv dependency to version 5.3.2

* refactor: replace KeyvMongo with custom implementation and update flow state manager usage

* fix: update @librechat/agents dependency to version 2.4.17

* ci: update OpenAIClient tests to use CustomOpenAIClient from @librechat/agents

* refactor: remove KeyvMongo mock and related dependencies
2025-04-13 23:01:55 -04:00
Danny Avila
37964975c1
🤖 refactor: Improve Agents Memory Usage, Bump Keyv, Grok 3 (#6850)
* chore: remove unused redis file

* chore: bump keyv dependencies, and update related imports

* refactor: Implement IoRedis client for rate limiting across middleware, as node-redis via keyv not compatible

* fix: Set max listeners to expected amount

* WIP: memory improvements

* refactor: Simplify getAbortData assignment in createAbortController

* refactor: Update getAbortData to use WeakRef for content management

* WIP: memory improvements in agent chat requests

* refactor: Enhance memory management with finalization registry and cleanup functions

* refactor: Simplify domainParser calls by removing unnecessary request parameter

* refactor: Update parameter types for action tools and agent loading functions to use minimal configs

* refactor: Simplify domainParser tests by removing unnecessary request parameter

* refactor: Simplify domainParser call by removing unnecessary request parameter

* refactor: Enhance client disposal by nullifying additional properties to improve memory management

* refactor: Improve title generation by adding abort controller and timeout handling, consolidate request cleanup

* refactor: Update checkIdleConnections to skip current user when checking for idle connections if passed

* refactor: Update createMCPTool to derive userId from config and handle abort signals

* refactor: Introduce createTokenCounter function and update tokenCounter usage; enhance disposeClient to reset Graph values

* refactor: Update getMCPManager to accept userId parameter for improved idle connection handling

* refactor: Extract logToolError function for improved error handling in AgentClient

* refactor: Update disposeClient to clear handlerRegistry and graphRunnable references in client.run

* refactor: Extract createHandleNewToken function to streamline token handling in initializeClient

* chore: bump @librechat/agents

* refactor: Improve timeout handling in addTitle function for better error management

* refactor: Introduce createFetch instead of using class method

* refactor: Enhance client disposal and request data handling in AskController and EditController

* refactor: Update import statements for AnthropicClient and OpenAIClient to use specific paths

* refactor: Use WeakRef for response handling in SplitStreamHandler to prevent memory leaks

* refactor: Simplify client disposal and rename getReqData to processReqData in AskController and EditController

* refactor: Improve logging structure and parameter handling in OpenAIClient

* refactor: Remove unused GraphEvents and improve stream event handling in AnthropicClient and OpenAIClient

* refactor: Simplify client initialization in AskController and EditController

* refactor: Remove unused mock functions and implement in-memory store for KeyvMongo

* chore: Update dependencies in package-lock.json to latest versions

* refactor: Await token usage recording in OpenAIClient to ensure proper async handling

* refactor: Remove handleAbort route from multiple endpoints and enhance client disposal logic

* refactor: Enhance abort controller logic by managing abortKey more effectively

* refactor: Add newConversation handling in useEventHandlers for improved conversation management

* fix: dropparams

* refactor: Use optional chaining for safer access to request properties in BaseClient

* refactor: Move client disposal and request data processing logic to cleanup module for better organization

* refactor: Remove aborted request check from addTitle function for cleaner logic

* feat: Add Grok 3 model pricing and update tests for new models

* chore: Remove trace warnings and inspect flags from backend start script used for debugging

* refactor: Replace user identifier handling with userId for consistency across controllers, use UserId in clientRegistry

* refactor: Enhance client disposal logic to prevent memory leaks by clearing additional references

* chore: Update @librechat/agents to version 2.4.14 in package.json and package-lock.json
2025-04-12 18:46:36 -04:00
Danny Avila
e16a6190a5
💾 chore: Enhance Local Storage Handling and Update MCP SDK (#6809)
* feat: Update MCP package version and dependencies; refactor ToolContentPart type

* refactor: Change module type to commonjs and update rollup configuration, remove unused dev dependency

* refactor: Change async calls to synchronous for MCP and FlowStateManager retrieval

* chore: Add eslint disable comment for i18next rule in DropdownPopup component

* fix: improve statefulness of mcp servers selected if some were removed since last session

* feat: implement conversation storage cleanup functions and integrate them into mutation success handlers

* feat: enhance storage condition logic in useLocalStorageAlt to prevent unnecessary local storage writes

* refactor: streamline local storage update logic in useLocalStorageAlt
2025-04-09 18:38:48 -04:00
Danny Avila
cf03731cc8
🔧 fix: Axios Proxy Usage And Bump mongoose (#6298)
* fix: bump mongoose to fix nested schema errors

* fix: Enhance Axios instance creation with improved proxy handling and error logging

* fix: Refactor Axios instance creation and remove proxy handling from file upload functions

* fix: Update proxy configuration in Axios instance creation and add unit tests
2025-03-11 14:44:54 -04:00
Danny Avila
ded3cd8876
🔍 feat: Mistral OCR API / Upload Files as Text (#6274)
* refactor: move `loadAuthValues` to `~/services/Tools/credentials`

* feat: add createAxiosInstance function to configure axios with proxy support

* WIP: First pass mistral ocr

* refactor: replace getConvoFiles with getToolFiles for improved file retrieval logic

* refactor: improve document formatting in encodeAndFormat function

* refactor: remove unused resendFiles parameter from buildOptions function (this option comes from the agent config)

* fix: update getFiles call to include files with `text` property as well

* refactor: move file handling to `initializeAgentOptions`

* refactor: enhance addImageURLs method to handle OCR text and improve message formatting

* refactor: update message formatting to handle OCR text in various content types

* refactor: remove unused resendFiles property from compactAgentsSchema

* fix: add error handling for Mistral OCR document upload and logging

* refactor: integrate OCR capability into file upload options and configuration

* refactor: skip processing for text source files in delete request, as they are directly tied to database

* feat: add metadata field to ExtendedFile type and update PanelColumns and PanelTable components for localization and metadata handling

* fix: source icon styling

* wip: first pass, frontend file context agent resources

* refactor: add hover card with contextual information for File Context (OCR) in FileContext component

* feat: enhance file processing by integrating file retrieval for OCR resources in agent initialization

* feat: implement OCR config; fix: agent resource deletion for ocr files

* feat: enhance agent initialization by adding OCR capability check in resource priming

* ci: fix `~/config` module mock

* ci: add OCR property expectation in AppService tests

* refactor: simplify OCR config loading by removing environment variable extraction, to be done when OCR is actually performed

* ci: add unit test to ensure environment variable references are not parsed in OCR config

* refactor: disable base64 image inclusion in OCR request

* refactor: enhance OCR configuration handling by validating environment variables and providing defaults

* refactor: use file stream from disk for mistral ocr api
2025-03-10 17:23:46 -04:00
Ruben Talstra
d99a9db3f6
✨feat: OAuth for Actions (#5693)
* ✨feat: OAuth for Actions

* WIP: PoC flow state manager

* refactor: Add identifier field to token model from action schema

* chore: fix potential file type issues

* ci: fix type issue with action metadata auth

* fix: ensure FlowManagerOptions has a default ttl value

* WIP: OAUTH actions

* WIP: first pass OAuth Action

* fix: standardize identifier usage in OAuth flow handling

* fix: update token retrieval to include userId in query and use correct identifier

* refacotr: update token retrieval to use userId for OAuth token query

* feat: Tool Call Auth styling

* fix: streamline token creation and add type field to token schema

* refactor: cleanup OAuth flow by encrypting client credentials and ensuring oauth operations only run under condition

* refactor: use encrypted credentials in OAuth callback

* fix: update Token collection indexes to use expiresAt TTL index and not createdAt legacy index

* refactor: enhance Token index cleanup by improving logging and removing redundant index creation logic

* refactor: remove unused OAuth login route and related logic for improved clarity

* refactor: replace fetch with axios for OAuth token exchange and improve error handling

* refactor: better UX after authentication before oauth tool execution

* refactor: implement cleanup handlers for FlowStateManager intervals to enhance resource management

* refactor: encrypt OAuth tokens before storing and decrypt upon retrieval for enhanced security

* refactor: enhance authentication success page with improved styling and countdown feature

* refactor: add response_type parameter to OAuth redirect URI for improved compatibility

* chore: update translation.json new localizations

* chore: remove unused OGDialog import from OGDialogTemplate component

* refactor: Actions Auth using new Dialog styling, use same component with Agents/Assistants

* refactor: update removeNullishValues function to support removal of empty strings and adjust transform usage in schemas

* chore: bump version of librechat-data-provider to 0.7.6991

* refactor: integrate removeNullishValues function to clean metadata before encryption in agent and assistant routes

* refactor: update OAuth input fields to use 'password' type for better security

* refactor: update localization placeholders for sign-in message to use double curly braces

* refactor: add access_type parameter for offline access in createActionTool function

* refactor: implement handleOAuthToken function for token management and encryption

* feat: refresh token support

* refactor: add default expiration for access token and error handling for missing token

* feat: localizations for ActionAuth

* refactor: set refresh token expiration to null to not expire if expiry never given

* fix: prevent crash fromerror within async handleAbortError in AskController, EditController, and AgentController

* feat: Action Callback URL

* 🌍 i18n: Update translation.json with latest translations

* refactor: handle errors in flow state checking to prevent unhandled promise rejections

* fix: improve flow state concurrency to prevent multiple token creation calls

* refactor: RequestExecutor to use separate axios instance

* refactor: improve concurrency flows by keeping completed state until TTL expiry

* refactor: increase TTL for flow state management and adjust monitoring interval

* ci: mock axios instance creation in actions spec

* feat: add Babel and Jest configuration files; implement FlowStateManager tests with concurrency handling

* chore: add disableOAuth prop to ActionsAuth (not implemented for Assistants yet)

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-02-10 15:56:08 -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
Danny Avila
e391347b9e
🔧 feat: Initial MCP Support (Tools) (#5015)
* 📝 chore: Add comment to clarify purpose of check_updates.sh script

* feat: mcp package

* feat: add librechat-mcp package and update dependencies

* feat: refactor MCPConnectionSingleton to handle transport initialization and connection management

* feat: change private methods to public in MCPConnectionSingleton for improved accessibility

* feat: filesystem demo

* chore: everything demo and move everything under mcp workspace

* chore: move ts-node to mcp workspace

* feat: mcp examples

* feat: working sse MCP example

* refactor: rename MCPConnectionSingleton to MCPConnection for clarity

* refactor: replace MCPConnectionSingleton with MCPConnection for consistency

* refactor: manager/connections

* refactor: update MCPConnection to use type definitions from mcp types

* refactor: update MCPManager to use winston logger and enhance server initialization

* refactor: share logger between connections and manager

* refactor: add schema definitions and update MCPManager to accept logger parameter

* feat: map available MCP tools

* feat: load manifest tools

* feat: add MCP tools delimiter constant and update plugin key generation

* feat: call MCP tools

* feat: update librechat-data-provider version to 0.7.63 and enhance StdioOptionsSchema with additional properties

* refactor: simplify typing

* chore: update types/packages

* feat: MCP Tool Content parsing

* chore: update dependencies and improve package configurations

* feat: add 'mcp' directory to package and update configurations

* refactor: return CONTENT_AND_ARTIFACT format for MCP callTool

* chore: bump @librechat/agents

* WIP: MCP artifacts

* chore: bump @librechat/agents to v1.8.7

* fix: ensure filename has extension when saving base64 image

* fix: move base64 buffer conversion before filename extension check

* chore: update backend review workflow to install MCP package

* fix: use correct `mime` method

* fix: enhance file metadata with message and tool call IDs in image saving process

* fix: refactor ToolCall component to handle MCP tool calls and improve domain extraction

* fix: update ToolItem component for default isInstalled value and improve localization in ToolSelectDialog

* fix: update ToolItem component to use consistent text color for tool description

* style: add theming to ToolSelectDialog

* fix: improve domain extraction logic in ToolCall component

* refactor: conversation item theming, fix rename UI bug, optimize props, add missing types

* feat: enhance MCP options schema with base options (iconPath to start) and make transport type optional, infer based on other option fields

* fix: improve reconnection logic with parallel init and exponential backoff and enhance transport debug logging

* refactor: improve logging format

* refactor: improve logging of available tools by displaying tool names

* refactor: improve reconnection/connection logic

* feat: add MCP package build process to Dockerfile

* feat: add fallback icon for tools without an image in ToolItem component

* feat: Assistants Support for MCP Tools

* fix(build): configure rollup to use output.dir for dynamic imports

* chore: update @librechat/agents to version 1.8.8 and add @langchain/anthropic dependency

* fix: update CONFIG_VERSION to 1.2.0
2024-12-17 13:12:57 -05:00
Danny Avila
ea1dd59ef4
refactor(api): Central Logging 📜 (#1348)
* WIP: initial logging changes
add several transports in ~/config/winston
omit messages in logs, truncate long strings
add short blurb in dotenv for debug logging
GoogleClient: using logger
OpenAIClient: using logger, handleOpenAIErrors
Adding typedef for payload message
bumped winston and using winston-daily-rotate-file
moved config for server paths to ~/config dir
Added `DEBUG_LOGGING=true` to .env.example

* WIP: Refactor logging statements in code

* WIP: Refactor logging statements and import configurations

* WIP: Refactor logging statements and import configurations

* refactor: broadcast Redis initialization message with `info` not `debug`

* refactor: complete Refactor logging statements and import configurations

* chore: delete unused tools

* fix: circular dependencies due to accessing logger

* refactor(handleText): handle booleans and write tests

* refactor: redact sensitive values, better formatting

* chore: improve log formatting, avoid passing strings to 2nd arg

* fix(ci): fix jest tests due to logger changes

* refactor(getAvailablePluginsController): cache plugins as they are static and avoids async addOpenAPISpecs call every time

* chore: update docs

* chore: update docs

* chore: create separate meiliSync logger, clean up logs to avoid being unnecessarily verbose

* chore: spread objects where they are commonly logged to allow string truncation

* chore: improve error log formatting
2023-12-14 07:49:27 -05:00