Merge branch 'main' into docs/azure-instance-name-clarification

- Add Azure OpenAI STT/TTS examples to librechat.example.yaml
- Clarify that instanceName should be the <NAME> part only (e.g., 'my-instance')
- Not the full URL (e.g., 'my-instance.cognitiveservices.azure.com')
- Add note that full domain format is still supported for backward compatibility

Examples:
- Correct: instanceName: 'my-instance'
- Also works: instanceName: 'my-instance.cognitiveservices.azure.com'

Related to #10283

.env.example

@@ -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
 
@@ -254,6 +254,10 @@ AZURE_AI_SEARCH_SEARCH_OPTION_SELECT=
 
 # OpenAI Image Tools Customization
 #----------------
+# IMAGE_GEN_OAI_API_KEY= # Create or reuse OpenAI API key for image generation tool
+# IMAGE_GEN_OAI_BASEURL= # Custom OpenAI base URL for image generation tool
+# IMAGE_GEN_OAI_AZURE_API_VERSION= # Custom Azure OpenAI deployments
+# IMAGE_GEN_OAI_DESCRIPTION=
 # IMAGE_GEN_OAI_DESCRIPTION_WITH_FILES=Custom description for image generation tool when files are present
 # IMAGE_GEN_OAI_DESCRIPTION_NO_FILES=Custom description for image generation tool when no files are present
 # IMAGE_EDIT_OAI_DESCRIPTION=Custom description for image editing tool
@@ -459,6 +463,9 @@ 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 +657,12 @@ 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 #
 #===============#
@@ -693,6 +706,16 @@ HELP_AND_FAQ_URL=https://librechat.ai
 # Comma-separated list of CacheKeys (e.g., ROLES,MESSAGES)
 # FORCED_IN_MEMORY_CACHE_NAMESPACES=ROLES,MESSAGES
 
+# Leader Election Configuration (for multi-instance deployments with Redis)
+# Duration in seconds that the leader lease is valid before it expires (default: 25)
+# LEADER_LEASE_DURATION=25
+# Interval in seconds at which the leader renews its lease (default: 10)
+# LEADER_RENEW_INTERVAL=10
+# Maximum number of retry attempts when renewing the lease fails (default: 3)
+# LEADER_RENEW_ATTEMPTS=3
+# Delay in seconds between retry attempts when renewing the lease (default: 0.5)
+# LEADER_RENEW_RETRY_DELAY=0.5
+
 #==================================================#
 #                      Others                      #
 #==================================================#

.github/workflows/cache-integration-tests.yml

@@ -0,0 +1,96 @@
+name: Cache Integration Tests
+
+on:
+  pull_request:
+    branches:
+      - main
+      - dev
+      - release/*
+    paths:
+      - 'packages/api/src/cache/**'
+      - 'packages/api/src/cluster/**'
+      - 'packages/api/src/mcp/**'
+      - 'redis-config/**'
+      - '.github/workflows/cache-integration-tests.yml'
+
+jobs:
+  cache_integration_tests:
+    name: Integration Tests that use actual Redis Cache
+    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:core
+
+      - name: Run cluster integration tests
+        working-directory: packages/api
+        env:
+          NODE_ENV: test
+          USE_REDIS: true
+          REDIS_URI: redis://127.0.0.1:6379
+        run: npm run test:cache-integration:cluster
+
+      - name: Run mcp integration tests
+        working-directory: packages/api
+        env:
+          NODE_ENV: test
+          USE_REDIS: true
+          REDIS_URI: redis://127.0.0.1:6379
+        run: npm run test:cache-integration:mcp
+
+      - 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

.husky/pre-commit

@@ -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

Dockerfile

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

Dockerfile.multi

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

api/app/clients/AnthropicClient.js

@@ -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:';

api/app/clients/BaseClient.js

@@ -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');
 
@@ -1198,8 +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[]>}
    */
@@ -1248,7 +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;

api/app/clients/GoogleClient.js

@@ -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,

api/app/clients/OllamaClient.js

@@ -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;
   }
 
   /**

api/app/clients/OpenAIClient.js

@@ -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');
   }
 
   /**

api/app/clients/TextStream.js

@@ -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 = {}) {

api/app/clients/agents/CustomAgent/outputParser.js

@@ -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) {

api/app/clients/chains/runTitleChain.js

@@ -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).'),

api/app/clients/llm/createLLM.js

@@ -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;

api/app/clients/llm/index.js

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

api/app/clients/memory/summaryBuffer.demo.js

@@ -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));
-})();

api/app/clients/memory/summaryBuffer.js

@@ -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);

api/app/clients/output_parsers/addImages.js

@@ -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`

api/app/clients/prompts/artifacts.js

@@ -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"

api/app/clients/tools/structured/AzureAISearch.js

@@ -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;
 

api/app/clients/tools/structured/DALLE3.js

@@ -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');

api/app/clients/tools/structured/FluxAPI.js

@@ -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.

api/app/clients/tools/structured/OpenAIImageTools.js

@@ -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) {

api/app/clients/tools/structured/StableDiffusion.js

@@ -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.";

api/app/clients/tools/structured/TraversaalSearch.js

@@ -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],

api/app/clients/tools/structured/Wolfram.js

@@ -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) {

api/app/clients/tools/util/handleOpenAIErrors.js

@@ -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.

api/app/clients/tools/util/handleTools.js

@@ -448,7 +448,7 @@ Current Date & Time: ${replaceSpecialVars({ text: '{{iso_datetime}}' })}
         }
         if (!availableTools) {
           try {
-            availableTools = await getMCPServerTools(serverName);
+            availableTools = await getMCPServerTools(safeUser.id, serverName);
           } catch (error) {
             logger.error(`Error fetching available tools for MCP server ${serverName}:`, error);
           }

api/app/clients/tools/util/handleTools.test.js

@@ -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,

api/cache/cacheFactory.js

@@ -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 };

api/cache/cacheFactory.spec.js

@@ -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');
-    });
-  });
-});

api/cache/clearPendingReq.js

@@ -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 ?? {};

api/cache/getLogStores.js

@@ -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' }),

api/cache/index.js

@@ -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 };

api/cache/keyvFiles.js

@@ -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,
-};

api/cache/logViolation.js

@@ -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');

api/db/indexSync.js

@@ -29,12 +29,64 @@ class MeiliSearchClient {
   }
 }
 
+/**
+ * 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 deleteDocumentsWithoutUserField(index, indexName) {
+  let deletedCount = 0;
+  let offset = 0;
+  const batchSize = 1000;
+
+  try {
+    while (true) {
+      const searchResult = await index.search('', {
+        limit: batchSize,
+        offset: offset,
+      });
+
+      if (searchResult.hits.length === 0) {
+        break;
+      }
+
+      const idsToDelete = searchResult.hits.filter((hit) => !hit.user).map((hit) => hit.id);
+
+      if (idsToDelete.length > 0) {
+        logger.info(
+          `[indexSync] Deleting ${idsToDelete.length} documents without user field from ${indexName} index`,
+        );
+        await index.deleteDocuments(idsToDelete);
+        deletedCount += idsToDelete.length;
+      }
+
+      if (searchResult.hits.length < batchSize) {
+        break;
+      }
+
+      offset += batchSize;
+    }
+
+    if (deletedCount > 0) {
+      logger.info(`[indexSync] Deleted ${deletedCount} orphaned documents from ${indexName} index`);
+    }
+  } catch (error) {
+    logger.error(`[indexSync] Error deleting documents from ${indexName}:`, error);
+  }
+
+  return deletedCount;
+}
+
 /**
  * Ensures indexes have proper filterable attributes configured and checks if documents have user field
  * @param {MeiliSearch} client - MeiliSearch client instance
- * @returns {Promise<boolean>} - true if configuration was updated or re-sync is needed
+ * @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 {
@@ -47,16 +99,17 @@ async function ensureFilterableAttributes(client) {
           filterableAttributes: ['user'],
         });
         logger.info('[indexSync] Messages index configured for user filtering');
-        logger.info('[indexSync] Index configuration updated. Full re-sync will be triggered.');
-        return true;
+        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, re-sync needed');
-          return true;
+          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);
@@ -78,16 +131,17 @@ async function ensureFilterableAttributes(client) {
           filterableAttributes: ['user'],
         });
         logger.info('[indexSync] Convos index configured for user filtering');
-        logger.info('[indexSync] Index configuration updated. Full re-sync will be triggered.');
-        return true;
+        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, re-sync needed');
-          return true;
+          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);
@@ -97,101 +151,143 @@ async function ensureFilterableAttributes(client) {
         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 false;
+  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() {
-  const client = MeiliSearchClient.getInstance();
+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 configUpdated = await ensureFilterableAttributes(client);
-
-  let messagesSync = false;
-  let convosSync = false;
-
-  // If configuration was just updated or documents are missing user field, force a full re-sync
-  if (configUpdated) {
-    logger.info('[indexSync] Forcing full re-sync to ensure user field is properly indexed...');
-
-    // 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 || configUpdated) {
-    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;
+    const { status } = await client.health();
+    if (status !== 'available') {
+      throw new Error('Meilisearch not available');
     }
-  } 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 || configUpdated) {
-    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 (indexingDisabled === true) {
+      logger.info('[indexSync] Indexing is disabled, skipping...');
+      return { messagesSync: false, convosSync: false };
     }
-  } else {
-    logger.info(
-      `[indexSync] Conversations are fully synced: ${convoProgress.totalProcessed}/${convoProgress.totalDocuments}`,
-    );
-  }
 
-  return { messagesSync, convosSync };
+    /** 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);
+      }
+    }
+  }
 }
 
 /**
@@ -204,24 +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');

api/models/Agent.js

@@ -62,25 +62,38 @@ const getAgents = async (searchParameter) => await Agent.find(searchParameter).l
  *
  * @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;
+  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);
+  const userId = req.user?.id; // note: userId cannot be undefined at runtime
+  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);
   }
 
@@ -90,7 +103,7 @@ const loadEphemeralAgent = async ({ req, agent_id, endpoint, model_parameters: _
       if (addedServers.has(mcpServer)) {
         continue;
       }
-      const serverTools = await getMCPServerTools(mcpServer);
+      const serverTools = await getMCPServerTools(userId, mcpServer);
       if (!serverTools) {
         tools.push(`${mcp_all}${mcp_delimiter}${mcpServer}`);
         addedServers.add(mcpServer);
@@ -122,17 +135,18 @@ 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,

api/models/Agent.spec.js

@@ -1931,7 +1931,7 @@ describe('models/Agent', () => {
       });
 
       // Mock getMCPServerTools to return tools for each server
-      getMCPServerTools.mockImplementation(async (server) => {
+      getMCPServerTools.mockImplementation(async (_userId, server) => {
         if (server === 'server1') {
           return { tool1_mcp_server1: {} };
         } else if (server === 'server2') {
@@ -2125,7 +2125,7 @@ describe('models/Agent', () => {
         getCachedTools.mockResolvedValue(availableTools);
 
         // Mock getMCPServerTools to return all tools for server1
-        getMCPServerTools.mockImplementation(async (server) => {
+        getMCPServerTools.mockImplementation(async (_userId, server) => {
           if (server === 'server1') {
             return availableTools; // All 100 tools belong to server1
           }
@@ -2674,7 +2674,7 @@ describe('models/Agent', () => {
       });
 
       // Mock getMCPServerTools to return only tools matching the server
-      getMCPServerTools.mockImplementation(async (server) => {
+      getMCPServerTools.mockImplementation(async (_userId, server) => {
         if (server === 'server1') {
           // Only return tool that correctly matches server1 format
           return { tool_mcp_server1: {} };

api/models/Categories.js

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

api/models/spendTokens.js

@@ -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.

api/models/tx.js

@@ -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 },
 };
 
@@ -71,89 +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 },
+    'command-r-plus': { prompt: 3, completion: 15 },
+    'command-text': { prompt: 1.5, completion: 2.0 },
     'deepseek-reasoner': { prompt: 0.28, completion: 0.42 },
-    deepseek: { prompt: 0.28, completion: 0.42 },
-    /* 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: 0.3, completion: 2.5 },
-    'gemini-2.5-flash-lite': { prompt: 0.075, completion: 0.4 },
-    '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 },
+    '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,
 );
@@ -184,67 +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;

api/models/tx.spec.js

@@ -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(
@@ -772,6 +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(
@@ -788,6 +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',
@@ -865,3 +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([]);
+  });
+});

api/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@librechat/backend",
-  "version": "v0.8.0",
+  "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": "^2.4.82",
+    "@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",

api/server/controllers/AuthController.js

@@ -116,11 +116,15 @@ const refreshController = async (req, res) => {
       const token = await setAuthTokens(userId, res, session);
 
       // trigger OAuth MCP server reconnection asynchronously (best effort)
-      void getOAuthReconnectionManager()
-        .reconnectServers(userId)
-        .catch((err) => {
-          logger.error('Error reconnecting OAuth MCP servers:', err);
-        });
+      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) {

api/server/controllers/ModelController.js

@@ -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

api/server/controllers/UserController.js

@@ -1,7 +1,6 @@
-const { logger } = require('@librechat/data-schemas');
+const { logger, webSearchKeys } = require('@librechat/data-schemas');
 const { Tools, CacheKeys, Constants, FileSources } = require('librechat-data-provider');
 const {
-  webSearchKeys,
   MCPOAuthHandler,
   MCPTokenStorage,
   normalizeHttpError,
@@ -29,6 +28,7 @@ const { getMCPManager, getFlowStateManager } = require('~/config');
 const { getAppConfig } = require('~/server/services/Config');
 const { deleteToolCalls } = require('~/models/ToolCall');
 const { getLogStores } = require('~/cache');
+const { mcpServersRegistry } = require('@librechat/api');
 
 const getUserController = async (req, res) => {
   const appConfig = await getAppConfig({ role: req.user?.role });
@@ -199,7 +199,7 @@ const updateUserPluginsController = async (req, res) => {
       // If auth was updated successfully, disconnect MCP sessions as they might use these credentials
       if (pluginKey.startsWith(Constants.mcp_prefix)) {
         try {
-          const mcpManager = getMCPManager(user.id);
+          const mcpManager = getMCPManager();
           if (mcpManager) {
             // Extract server name from pluginKey (format: "mcp_<serverName>")
             const serverName = pluginKey.replace(Constants.mcp_prefix, '');
@@ -296,10 +296,11 @@ const maybeUninstallOAuthMCP = async (userId, pluginKey, appConfig) => {
   }
 
   const serverName = pluginKey.replace(Constants.mcp_prefix, '');
-  const mcpManager = getMCPManager(userId);
-  const serverConfig = mcpManager.getRawConfig(serverName) ?? appConfig?.mcpServers?.[serverName];
-
-  if (!mcpManager.getOAuthServers().has(serverName)) {
+  const serverConfig =
+    (await mcpServersRegistry.getServerConfig(serverName, userId)) ??
+    appConfig?.mcpServers?.[serverName];
+  const oauthServers = await mcpServersRegistry.getOAuthServers();
+  if (!oauthServers.has(serverName)) {
     // this server does not use OAuth, so nothing to do here as well
     return;
   }
@@ -328,16 +329,23 @@ 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);
     }
@@ -345,13 +353,19 @@ 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);
     }

api/server/controllers/agents/client.js

@@ -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,
@@ -1116,8 +1114,8 @@ 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}"`,
       );
     }
 
@@ -1237,6 +1235,10 @@ class AgentClient extends BaseClient {
               handleLLMEnd,
             },
           ],
+          configurable: {
+            thread_id: this.conversationId,
+            user_id: this.user ?? this.options.req.user?.id,
+          },
         },
       });
 
@@ -1274,7 +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;

api/server/controllers/agents/client.test.js

@@ -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'));
 

api/server/controllers/auth/LoginController.js

@@ -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 {

api/server/controllers/auth/LogoutController.js

@@ -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;

api/server/controllers/mcp.js

@@ -10,6 +10,7 @@ const {
   getAppConfig,
 } = require('~/server/services/Config');
 const { getMCPManager } = require('~/config');
+const { mcpServersRegistry } = require('@librechat/api');
 
 /**
  * Get all MCP tools available to the user
@@ -32,7 +33,7 @@ const getMCPTools = async (req, res) => {
     const mcpServers = {};
 
     const cachePromises = configuredServers.map((serverName) =>
-      getMCPServerTools(serverName).then((tools) => ({ serverName, tools })),
+      getMCPServerTools(userId, serverName).then((tools) => ({ serverName, tools })),
     );
     const cacheResults = await Promise.all(cachePromises);
 
@@ -52,7 +53,7 @@ const getMCPTools = async (req, res) => {
 
       if (Object.keys(serverTools).length > 0) {
         // Cache asynchronously without blocking
-        cacheMCPServerTools({ serverName, serverTools }).catch((err) =>
+        cacheMCPServerTools({ userId, serverName, serverTools }).catch((err) =>
           logger.error(`[getMCPTools] Failed to cache tools for ${serverName}:`, err),
         );
       }
@@ -65,7 +66,7 @@ const getMCPTools = async (req, res) => {
 
         // Get server config once
         const serverConfig = appConfig.mcpConfig[serverName];
-        const rawServerConfig = mcpManager.getRawConfig(serverName);
+        const rawServerConfig = await mcpServersRegistry.getServerConfig(serverName, userId);
 
         // Initialize server object with all server-level data
         const server = {

api/server/index.js

@@ -10,7 +10,12 @@ 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');
@@ -49,9 +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');
 

api/server/middleware/canDeleteAccount.js

@@ -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

api/server/middleware/checkBan.js

@@ -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');

api/server/middleware/checkPeoplePickerAccess.js

@@ -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

api/server/middleware/checkPeoplePickerAccess.spec.js

@@ -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(),
   },

api/server/middleware/concurrentLimiter.js

@@ -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 {

api/server/middleware/limiters/forkLimiters.js

@@ -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 = () => {

api/server/middleware/limiters/importLimiters.js

@@ -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 = () => {

api/server/middleware/limiters/loginLimiter.js

@@ -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;

api/server/middleware/limiters/messageLimiters.js

@@ -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 {

api/server/middleware/limiters/registerLimiter.js

@@ -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;

api/server/middleware/limiters/resetPasswordLimiter.js

@@ -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 {

api/server/middleware/limiters/sttLimiters.js

@@ -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 = () => {

api/server/middleware/limiters/toolCallLimiter.js

@@ -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;

api/server/middleware/limiters/ttsLimiters.js

@@ -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;

api/server/middleware/limiters/uploadLimiters.js

@@ -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 = () => {

api/server/middleware/limiters/verifyEmailLimiter.js

@@ -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 {

api/server/middleware/logHeaders.js

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

api/server/middleware/moderateText.js

@@ -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)) {

api/server/middleware/optionalJwtAuth.js

@@ -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.

api/server/middleware/requireJwtAuth.js

@@ -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

api/server/middleware/requireLocalAuth.js

@@ -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) => {

api/server/middleware/validatePasswordReset.js

@@ -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)) {

api/server/middleware/validateRegistration.js

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

api/server/routes/__tests__/ldap.spec.js

@@ -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();
 

api/server/routes/__tests__/mcp.spec.js

@@ -15,6 +15,10 @@ jest.mock('@librechat/api', () => ({
     storeTokens: jest.fn(),
   },
   getUserMCPAuthMap: jest.fn(),
+  mcpServersRegistry: {
+    getServerConfig: jest.fn(),
+    getOAuthServers: jest.fn(),
+  },
 }));
 
 jest.mock('@librechat/data-schemas', () => ({
@@ -47,6 +51,7 @@ jest.mock('~/models', () => ({
 jest.mock('~/server/services/Config', () => ({
   setCachedTools: jest.fn(),
   getCachedTools: jest.fn(),
+  getMCPServerTools: jest.fn(),
   loadCustomConfig: jest.fn(),
 }));
 
@@ -114,7 +119,7 @@ describe('MCP Routes', () => {
   });
 
   describe('GET /:serverName/oauth/initiate', () => {
-    const { MCPOAuthHandler } = require('@librechat/api');
+    const { MCPOAuthHandler, mcpServersRegistry } = require('@librechat/api');
     const { getLogStores } = require('~/cache');
 
     it('should initiate OAuth flow successfully', async () => {
@@ -129,6 +134,7 @@ describe('MCP Routes', () => {
 
       getLogStores.mockReturnValue({});
       require('~/config').getFlowStateManager.mockReturnValue(mockFlowManager);
+      mcpServersRegistry.getServerConfig.mockResolvedValue({});
 
       MCPOAuthHandler.initiateOAuthFlow.mockResolvedValue({
         authorizationUrl: 'https://oauth.example.com/auth',
@@ -146,6 +152,7 @@ describe('MCP Routes', () => {
         'test-server',
         'https://test-server.com',
         'test-user-id',
+        {},
         { clientId: 'test-client-id' },
       );
     });
@@ -281,6 +288,7 @@ describe('MCP Routes', () => {
     });
 
     it('should handle OAuth callback successfully', async () => {
+      const { mcpServersRegistry } = require('@librechat/api');
       const mockFlowManager = {
         completeFlow: jest.fn().mockResolvedValue(),
         deleteFlow: jest.fn().mockResolvedValue(true),
@@ -300,6 +308,7 @@ describe('MCP Routes', () => {
       MCPOAuthHandler.getFlowState.mockResolvedValue(mockFlowState);
       MCPOAuthHandler.completeOAuthFlow.mockResolvedValue(mockTokens);
       MCPTokenStorage.storeTokens.mockResolvedValue();
+      mcpServersRegistry.getServerConfig.mockResolvedValue({});
       getLogStores.mockReturnValue({});
       require('~/config').getFlowStateManager.mockReturnValue(mockFlowManager);
 
@@ -336,6 +345,7 @@ describe('MCP Routes', () => {
         'test-flow-id',
         'test-auth-code',
         mockFlowManager,
+        {},
       );
       expect(MCPTokenStorage.storeTokens).toHaveBeenCalledWith(
         expect.objectContaining({
@@ -370,6 +380,7 @@ describe('MCP Routes', () => {
     });
 
     it('should handle system-level OAuth completion', async () => {
+      const { mcpServersRegistry } = require('@librechat/api');
       const mockFlowManager = {
         completeFlow: jest.fn().mockResolvedValue(),
         deleteFlow: jest.fn().mockResolvedValue(true),
@@ -389,6 +400,7 @@ describe('MCP Routes', () => {
       MCPOAuthHandler.getFlowState.mockResolvedValue(mockFlowState);
       MCPOAuthHandler.completeOAuthFlow.mockResolvedValue(mockTokens);
       MCPTokenStorage.storeTokens.mockResolvedValue();
+      mcpServersRegistry.getServerConfig.mockResolvedValue({});
       getLogStores.mockReturnValue({});
       require('~/config').getFlowStateManager.mockReturnValue(mockFlowManager);
 
@@ -403,6 +415,7 @@ describe('MCP Routes', () => {
     });
 
     it('should handle reconnection failure after OAuth', async () => {
+      const { mcpServersRegistry } = require('@librechat/api');
       const mockFlowManager = {
         completeFlow: jest.fn().mockResolvedValue(),
         deleteFlow: jest.fn().mockResolvedValue(true),
@@ -422,6 +435,7 @@ describe('MCP Routes', () => {
       MCPOAuthHandler.getFlowState.mockResolvedValue(mockFlowState);
       MCPOAuthHandler.completeOAuthFlow.mockResolvedValue(mockTokens);
       MCPTokenStorage.storeTokens.mockResolvedValue();
+      mcpServersRegistry.getServerConfig.mockResolvedValue({});
       getLogStores.mockReturnValue({});
       require('~/config').getFlowStateManager.mockReturnValue(mockFlowManager);
 
@@ -446,6 +460,7 @@ describe('MCP Routes', () => {
     });
 
     it('should redirect to error page if token storage fails', async () => {
+      const { mcpServersRegistry } = require('@librechat/api');
       const mockFlowManager = {
         completeFlow: jest.fn().mockResolvedValue(),
         deleteFlow: jest.fn().mockResolvedValue(true),
@@ -465,6 +480,7 @@ describe('MCP Routes', () => {
       MCPOAuthHandler.getFlowState.mockResolvedValue(mockFlowState);
       MCPOAuthHandler.completeOAuthFlow.mockResolvedValue(mockTokens);
       MCPTokenStorage.storeTokens.mockRejectedValue(new Error('store failed'));
+      mcpServersRegistry.getServerConfig.mockResolvedValue({});
       getLogStores.mockReturnValue({});
       require('~/config').getFlowStateManager.mockReturnValue(mockFlowManager);
 
@@ -715,12 +731,14 @@ describe('MCP Routes', () => {
   });
 
   describe('POST /:serverName/reinitialize', () => {
+    const { mcpServersRegistry } = require('@librechat/api');
+
     it('should return 404 when server is not found in configuration', async () => {
       const mockMcpManager = {
-        getRawConfig: jest.fn().mockReturnValue(null),
         disconnectUserConnection: jest.fn().mockResolvedValue(),
       };
 
+      mcpServersRegistry.getServerConfig.mockResolvedValue(null);
       require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
       require('~/config').getFlowStateManager.mockReturnValue({});
       require('~/cache').getLogStores.mockReturnValue({});
@@ -735,9 +753,6 @@ describe('MCP Routes', () => {
 
     it('should handle OAuth requirement during reinitialize', async () => {
       const mockMcpManager = {
-        getRawConfig: jest.fn().mockReturnValue({
-          customUserVars: {},
-        }),
         disconnectUserConnection: jest.fn().mockResolvedValue(),
         mcpConfigs: {},
         getUserConnection: jest.fn().mockImplementation(async ({ oauthStart }) => {
@@ -748,6 +763,9 @@ describe('MCP Routes', () => {
         }),
       };
 
+      mcpServersRegistry.getServerConfig.mockResolvedValue({
+        customUserVars: {},
+      });
       require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
       require('~/config').getFlowStateManager.mockReturnValue({});
       require('~/cache').getLogStores.mockReturnValue({});
@@ -773,12 +791,12 @@ describe('MCP Routes', () => {
 
     it('should return 500 when reinitialize fails with non-OAuth error', async () => {
       const mockMcpManager = {
-        getRawConfig: jest.fn().mockReturnValue({}),
         disconnectUserConnection: jest.fn().mockResolvedValue(),
         mcpConfigs: {},
         getUserConnection: jest.fn().mockRejectedValue(new Error('Connection failed')),
       };
 
+      mcpServersRegistry.getServerConfig.mockResolvedValue({});
       require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
       require('~/config').getFlowStateManager.mockReturnValue({});
       require('~/cache').getLogStores.mockReturnValue({});
@@ -794,11 +812,12 @@ describe('MCP Routes', () => {
 
     it('should return 500 when unexpected error occurs', async () => {
       const mockMcpManager = {
-        getRawConfig: jest.fn().mockImplementation(() => {
-          throw new Error('Config loading failed');
-        }),
+        disconnectUserConnection: jest.fn(),
       };
 
+      mcpServersRegistry.getServerConfig.mockImplementation(() => {
+        throw new Error('Config loading failed');
+      });
       require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
 
       const response = await request(app).post('/api/mcp/test-server/reinitialize');
@@ -831,11 +850,11 @@ describe('MCP Routes', () => {
       };
 
       const mockMcpManager = {
-        getRawConfig: jest.fn().mockReturnValue({ endpoint: 'http://test-server.com' }),
         disconnectUserConnection: jest.fn().mockResolvedValue(),
         getUserConnection: jest.fn().mockResolvedValue(mockUserConnection),
       };
 
+      mcpServersRegistry.getServerConfig.mockResolvedValue({ endpoint: 'http://test-server.com' });
       require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
       require('~/config').getFlowStateManager.mockReturnValue({});
       require('~/cache').getLogStores.mockReturnValue({});
@@ -876,16 +895,16 @@ describe('MCP Routes', () => {
       };
 
       const mockMcpManager = {
-        getRawConfig: jest.fn().mockReturnValue({
-          endpoint: 'http://test-server.com',
-          customUserVars: {
-            API_KEY: 'some-env-var',
-          },
-        }),
         disconnectUserConnection: jest.fn().mockResolvedValue(),
         getUserConnection: jest.fn().mockResolvedValue(mockUserConnection),
       };
 
+      mcpServersRegistry.getServerConfig.mockResolvedValue({
+        endpoint: 'http://test-server.com',
+        customUserVars: {
+          API_KEY: 'some-env-var',
+        },
+      });
       require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
       require('~/config').getFlowStateManager.mockReturnValue({});
       require('~/cache').getLogStores.mockReturnValue({});
@@ -1090,17 +1109,17 @@ describe('MCP Routes', () => {
 
   describe('GET /:serverName/auth-values', () => {
     const { getUserPluginAuthValue } = require('~/server/services/PluginService');
+    const { mcpServersRegistry } = require('@librechat/api');
 
     it('should return auth value flags for server', async () => {
-      const mockMcpManager = {
-        getRawConfig: jest.fn().mockReturnValue({
-          customUserVars: {
-            API_KEY: 'some-env-var',
-            SECRET_TOKEN: 'another-env-var',
-          },
-        }),
-      };
+      const mockMcpManager = {};
 
+      mcpServersRegistry.getServerConfig.mockResolvedValue({
+        customUserVars: {
+          API_KEY: 'some-env-var',
+          SECRET_TOKEN: 'another-env-var',
+        },
+      });
       require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
       getUserPluginAuthValue.mockResolvedValueOnce('some-api-key-value').mockResolvedValueOnce('');
 
@@ -1120,10 +1139,9 @@ describe('MCP Routes', () => {
     });
 
     it('should return 404 when server is not found in configuration', async () => {
-      const mockMcpManager = {
-        getRawConfig: jest.fn().mockReturnValue(null),
-      };
+      const mockMcpManager = {};
 
+      mcpServersRegistry.getServerConfig.mockResolvedValue(null);
       require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
 
       const response = await request(app).get('/api/mcp/non-existent-server/auth-values');
@@ -1135,14 +1153,13 @@ describe('MCP Routes', () => {
     });
 
     it('should handle errors when checking auth values', async () => {
-      const mockMcpManager = {
-        getRawConfig: jest.fn().mockReturnValue({
-          customUserVars: {
-            API_KEY: 'some-env-var',
-          },
-        }),
-      };
+      const mockMcpManager = {};
 
+      mcpServersRegistry.getServerConfig.mockResolvedValue({
+        customUserVars: {
+          API_KEY: 'some-env-var',
+        },
+      });
       require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
       getUserPluginAuthValue.mockRejectedValue(new Error('Database error'));
 
@@ -1159,12 +1176,11 @@ describe('MCP Routes', () => {
     });
 
     it('should return 500 when auth values check throws unexpected error', async () => {
-      const mockMcpManager = {
-        getRawConfig: jest.fn().mockImplementation(() => {
-          throw new Error('Config loading failed');
-        }),
-      };
+      const mockMcpManager = {};
 
+      mcpServersRegistry.getServerConfig.mockImplementation(() => {
+        throw new Error('Config loading failed');
+      });
       require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
 
       const response = await request(app).get('/api/mcp/test-server/auth-values');
@@ -1174,12 +1190,11 @@ describe('MCP Routes', () => {
     });
 
     it('should handle customUserVars that is not an object', async () => {
-      const mockMcpManager = {
-        getRawConfig: jest.fn().mockReturnValue({
-          customUserVars: 'not-an-object',
-        }),
-      };
+      const mockMcpManager = {};
 
+      mcpServersRegistry.getServerConfig.mockResolvedValue({
+        customUserVars: 'not-an-object',
+      });
       require('~/config').getMCPManager.mockReturnValue(mockMcpManager);
 
       const response = await request(app).get('/api/mcp/test-server/auth-values');
@@ -1206,7 +1221,7 @@ describe('MCP Routes', () => {
 
   describe('GET /:serverName/oauth/callback - Edge Cases', () => {
     it('should handle OAuth callback without toolFlowId (falsy toolFlowId)', async () => {
-      const { MCPOAuthHandler, MCPTokenStorage } = require('@librechat/api');
+      const { MCPOAuthHandler, MCPTokenStorage, mcpServersRegistry } = require('@librechat/api');
       const mockTokens = {
         access_token: 'edge-access-token',
         refresh_token: 'edge-refresh-token',
@@ -1224,6 +1239,7 @@ describe('MCP Routes', () => {
       });
       MCPOAuthHandler.completeOAuthFlow = jest.fn().mockResolvedValue(mockTokens);
       MCPTokenStorage.storeTokens.mockResolvedValue();
+      mcpServersRegistry.getServerConfig.mockResolvedValue({});
 
       const mockFlowManager = {
         completeFlow: jest.fn(),
@@ -1248,7 +1264,7 @@ 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 { MCPOAuthHandler, MCPTokenStorage, mcpServersRegistry } = require('@librechat/api');
       const mockTokens = {
         access_token: 'edge-access-token',
         refresh_token: 'edge-refresh-token',
@@ -1274,6 +1290,7 @@ describe('MCP Routes', () => {
       });
       MCPOAuthHandler.completeOAuthFlow.mockResolvedValue(mockTokens);
       MCPTokenStorage.storeTokens.mockResolvedValue();
+      mcpServersRegistry.getServerConfig.mockResolvedValue({});
 
       const mockMcpManager = {
         getUserConnection: jest.fn().mockResolvedValue({

api/server/routes/agents/index.js

@@ -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');
 

api/server/routes/config.js

@@ -12,6 +12,7 @@ const { getAppConfig } = require('~/server/services/Config/app');
 const { getProjectByName } = require('~/models/Project');
 const { getMCPManager } = require('~/config');
 const { getLogStores } = require('~/cache');
+const { mcpServersRegistry } = require('@librechat/api');
 
 const router = express.Router();
 const emailLoginEnabled =
@@ -115,6 +116,9 @@ 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);
@@ -122,7 +126,7 @@ router.get('/', async function (req, res) {
       payload.minPasswordLength = minPasswordLength;
     }
 
-    const getMCPServers = () => {
+    const getMCPServers = async () => {
       try {
         if (appConfig?.mcpConfig == null) {
           return;
@@ -131,9 +135,8 @@ router.get('/', async function (req, res) {
         if (!mcpManager) {
           return;
         }
-        const mcpServers = mcpManager.getAllServers();
+        const mcpServers = await mcpServersRegistry.getAllServerConfigs();
         if (!mcpServers) return;
-        const oauthServers = mcpManager.getOAuthServers();
         for (const serverName in mcpServers) {
           if (!payload.mcpServers) {
             payload.mcpServers = {};
@@ -142,7 +145,7 @@ router.get('/', async function (req, res) {
           payload.mcpServers[serverName] = removeNullishValues({
             startup: serverConfig?.startup,
             chatMenu: serverConfig?.chatMenu,
-            isOAuth: oauthServers?.has(serverName),
+            isOAuth: serverConfig.requiresOAuth,
             customUserVars: serverConfig?.customUserVars,
           });
         }
@@ -151,12 +154,12 @@ router.get('/', async function (req, res) {
       }
     };
 
-    getMCPServers();
+    await getMCPServers();
     const webSearchConfig = appConfig?.webSearch;
     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;

api/server/routes/edit/index.js

@@ -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 ?? {};
 

api/server/routes/files/files.js

@@ -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();

api/server/routes/files/speech/tts.js

@@ -1,9 +1,9 @@
 const multer = require('multer');
 const express = require('express');
+const { logger } = require('@librechat/data-schemas');
 const { CacheKeys } = require('librechat-data-provider');
 const { getVoices, streamAudio, textToSpeech } = require('~/server/services/Files/Audio');
 const { getLogStores } = require('~/cache');
-const { logger } = require('~/config');
 
 const router = express.Router();
 const upload = multer();

api/server/routes/mcp.js

@@ -6,6 +6,7 @@ const {
   MCPOAuthHandler,
   MCPTokenStorage,
   getUserMCPAuthMap,
+  mcpServersRegistry,
 } = require('@librechat/api');
 const { getMCPManager, getFlowStateManager, getOAuthReconnectionManager } = require('~/config');
 const { getMCPSetupData, getServerConnectionStatus } = require('~/server/services/MCP');
@@ -61,10 +62,12 @@ router.get('/:serverName/oauth/initiate', requireJwtAuth, async (req, res) => {
       return res.status(400).json({ error: 'Invalid flow state' });
     }
 
+    const oauthHeaders = await getOAuthHeaders(serverName, userId);
     const { authorizationUrl, flowId: oauthFlowId } = await MCPOAuthHandler.initiateOAuthFlow(
       serverName,
       serverUrl,
       userId,
+      oauthHeaders,
       oauthConfig,
     );
 
@@ -132,7 +135,8 @@ router.get('/:serverName/oauth/callback', async (req, res) => {
     });
 
     logger.debug('[MCP OAuth] Completing OAuth flow');
-    const tokens = await MCPOAuthHandler.completeOAuthFlow(flowId, code, flowManager);
+    const oauthHeaders = await getOAuthHeaders(serverName, flowState.userId);
+    const tokens = await MCPOAuthHandler.completeOAuthFlow(flowId, code, flowManager, oauthHeaders);
     logger.info('[MCP OAuth] OAuth flow completed, tokens received in callback route');
 
     /** Persist tokens immediately so reconnection uses fresh credentials */
@@ -199,6 +203,7 @@ router.get('/:serverName/oauth/callback', async (req, res) => {
 
         const tools = await userConnection.fetchTools();
         await updateMCPServerTools({
+          userId: flowState.userId,
           serverName,
           tools,
         });
@@ -349,7 +354,7 @@ router.post('/:serverName/reinitialize', requireJwtAuth, async (req, res) => {
     logger.info(`[MCP Reinitialize] Reinitializing server: ${serverName}`);
 
     const mcpManager = getMCPManager();
-    const serverConfig = mcpManager.getRawConfig(serverName);
+    const serverConfig = await mcpServersRegistry.getServerConfig(serverName, user.id);
     if (!serverConfig) {
       return res.status(404).json({
         error: `MCP server '${serverName}' not found in configuration`,
@@ -498,8 +503,7 @@ router.get('/:serverName/auth-values', requireJwtAuth, async (req, res) => {
       return res.status(401).json({ error: 'User not authenticated' });
     }
 
-    const mcpManager = getMCPManager();
-    const serverConfig = mcpManager.getRawConfig(serverName);
+    const serverConfig = await mcpServersRegistry.getServerConfig(serverName, user.id);
     if (!serverConfig) {
       return res.status(404).json({
         error: `MCP server '${serverName}' not found in configuration`,
@@ -538,4 +542,9 @@ router.get('/:serverName/auth-values', requireJwtAuth, async (req, res) => {
   }
 });
 
+async function getOAuthHeaders(serverName, userId) {
+  const serverConfig = await mcpServersRegistry.getServerConfig(serverName, userId);
+  return serverConfig?.oauth_headers ?? {};
+}
+
 module.exports = router;

api/server/routes/presets.js

@@ -1,8 +1,8 @@
-const express = require('express');
 const crypto = require('crypto');
+const express = require('express');
+const { logger } = require('@librechat/data-schemas');
 const { getPresets, savePreset, deletePresets } = require('~/models');
 const requireJwtAuth = require('~/server/middleware/requireJwtAuth');
-const { logger } = require('~/config');
 
 const router = express.Router();
 router.use(requireJwtAuth);

api/server/routes/search.js

@@ -1,7 +1,7 @@
 const express = require('express');
 const { MeiliSearch } = require('meilisearch');
+const { isEnabled } = require('@librechat/api');
 const requireJwtAuth = require('~/server/middleware/requireJwtAuth');
-const { isEnabled } = require('~/server/utils');
 
 const router = express.Router();
 

api/server/routes/share.js

@@ -99,7 +99,8 @@ router.get('/link/:conversationId', requireJwtAuth, async (req, res) => {
 
 router.post('/:conversationId', requireJwtAuth, async (req, res) => {
   try {
-    const created = await createSharedLink(req.user.id, req.params.conversationId);
+    const { targetMessageId } = req.body;
+    const created = await createSharedLink(req.user.id, req.params.conversationId, targetMessageId);
     if (created) {
       res.status(200).json(created);
     } else {

api/server/routes/static.js

@@ -1,7 +1,7 @@
 const express = require('express');
+const { isEnabled } = require('@librechat/api');
 const staticCache = require('../utils/staticCache');
 const paths = require('~/config/paths');
-const { isEnabled } = require('~/server/utils');
 
 const skipGzipScan = !isEnabled(process.env.ENABLE_IMAGE_OUTPUT_GZIP_SCAN);
 

api/server/routes/tokenizer.js

@@ -1,8 +1,9 @@
 const express = require('express');
-const router = express.Router();
+const { logger } = require('@librechat/data-schemas');
 const requireJwtAuth = require('~/server/middleware/requireJwtAuth');
 const { countTokens } = require('~/server/utils');
-const { logger } = require('~/config');
+
+const router = express.Router();
 
 router.post('/', requireJwtAuth, async (req, res) => {
   try {

api/server/services/AppService.interface.spec.js

@@ -1,198 +0,0 @@
-jest.mock('@librechat/data-schemas', () => ({
-  logger: {
-    info: jest.fn(),
-    warn: jest.fn(),
-    error: jest.fn(),
-  },
-}));
-
-jest.mock('@librechat/api', () => ({
-  ...jest.requireActual('@librechat/api'),
-  loadDefaultInterface: jest.fn(),
-}));
-jest.mock('./start/tools', () => ({
-  loadAndFormatTools: jest.fn().mockReturnValue({}),
-}));
-jest.mock('./start/checks', () => ({
-  checkVariables: jest.fn(),
-  checkHealth: jest.fn(),
-  checkConfig: jest.fn(),
-  checkAzureVariables: jest.fn(),
-  checkWebSearchConfig: jest.fn(),
-}));
-
-jest.mock('./Config/loadCustomConfig', () => jest.fn());
-
-const AppService = require('./AppService');
-const { loadDefaultInterface } = require('@librechat/api');
-
-describe('AppService interface configuration', () => {
-  let mockLoadCustomConfig;
-
-  beforeEach(() => {
-    jest.resetModules();
-    jest.clearAllMocks();
-    mockLoadCustomConfig = require('./Config/loadCustomConfig');
-  });
-
-  it('should set prompts and bookmarks to true when loadDefaultInterface returns true for both', async () => {
-    mockLoadCustomConfig.mockResolvedValue({});
-    loadDefaultInterface.mockResolvedValue({ prompts: true, bookmarks: true });
-
-    const result = await AppService();
-
-    expect(result).toEqual(
-      expect.objectContaining({
-        interfaceConfig: expect.objectContaining({
-          prompts: true,
-          bookmarks: true,
-        }),
-      }),
-    );
-    expect(loadDefaultInterface).toHaveBeenCalled();
-  });
-
-  it('should set prompts and bookmarks to false when loadDefaultInterface returns false for both', async () => {
-    mockLoadCustomConfig.mockResolvedValue({ interface: { prompts: false, bookmarks: false } });
-    loadDefaultInterface.mockResolvedValue({ prompts: false, bookmarks: false });
-
-    const result = await AppService();
-
-    expect(result).toEqual(
-      expect.objectContaining({
-        interfaceConfig: expect.objectContaining({
-          prompts: false,
-          bookmarks: false,
-        }),
-      }),
-    );
-    expect(loadDefaultInterface).toHaveBeenCalled();
-  });
-
-  it('should not set prompts and bookmarks when loadDefaultInterface returns undefined for both', async () => {
-    mockLoadCustomConfig.mockResolvedValue({});
-    loadDefaultInterface.mockResolvedValue({});
-
-    const result = await AppService();
-
-    expect(result).toEqual(
-      expect.objectContaining({
-        interfaceConfig: expect.anything(),
-      }),
-    );
-
-    // Verify that prompts and bookmarks are undefined when not provided
-    expect(result.interfaceConfig.prompts).toBeUndefined();
-    expect(result.interfaceConfig.bookmarks).toBeUndefined();
-    expect(loadDefaultInterface).toHaveBeenCalled();
-  });
-
-  it('should set prompts and bookmarks to different values when loadDefaultInterface returns different values', async () => {
-    mockLoadCustomConfig.mockResolvedValue({ interface: { prompts: true, bookmarks: false } });
-    loadDefaultInterface.mockResolvedValue({ prompts: true, bookmarks: false });
-
-    const result = await AppService();
-
-    expect(result).toEqual(
-      expect.objectContaining({
-        interfaceConfig: expect.objectContaining({
-          prompts: true,
-          bookmarks: false,
-        }),
-      }),
-    );
-    expect(loadDefaultInterface).toHaveBeenCalled();
-  });
-
-  it('should correctly configure peoplePicker permissions including roles', async () => {
-    mockLoadCustomConfig.mockResolvedValue({
-      interface: {
-        peoplePicker: {
-          users: true,
-          groups: true,
-          roles: true,
-        },
-      },
-    });
-    loadDefaultInterface.mockResolvedValue({
-      peoplePicker: {
-        users: true,
-        groups: true,
-        roles: true,
-      },
-    });
-
-    const result = await AppService();
-
-    expect(result).toEqual(
-      expect.objectContaining({
-        interfaceConfig: expect.objectContaining({
-          peoplePicker: expect.objectContaining({
-            users: true,
-            groups: true,
-            roles: true,
-          }),
-        }),
-      }),
-    );
-    expect(loadDefaultInterface).toHaveBeenCalled();
-  });
-
-  it('should handle mixed peoplePicker permissions', async () => {
-    mockLoadCustomConfig.mockResolvedValue({
-      interface: {
-        peoplePicker: {
-          users: true,
-          groups: false,
-          roles: true,
-        },
-      },
-    });
-    loadDefaultInterface.mockResolvedValue({
-      peoplePicker: {
-        users: true,
-        groups: false,
-        roles: true,
-      },
-    });
-
-    const result = await AppService();
-
-    expect(result).toEqual(
-      expect.objectContaining({
-        interfaceConfig: expect.objectContaining({
-          peoplePicker: expect.objectContaining({
-            users: true,
-            groups: false,
-            roles: true,
-          }),
-        }),
-      }),
-    );
-  });
-
-  it('should set default peoplePicker permissions when not provided', async () => {
-    mockLoadCustomConfig.mockResolvedValue({});
-    loadDefaultInterface.mockResolvedValue({
-      peoplePicker: {
-        users: true,
-        groups: true,
-        roles: true,
-      },
-    });
-
-    const result = await AppService();
-
-    expect(result).toEqual(
-      expect.objectContaining({
-        interfaceConfig: expect.objectContaining({
-          peoplePicker: expect.objectContaining({
-            users: true,
-            groups: true,
-            roles: true,
-          }),
-        }),
-      }),
-    );
-  });
-});

api/server/services/Config/__tests__/getCachedTools.spec.js

@@ -0,0 +1,10 @@
+const { ToolCacheKeys } = require('../getCachedTools');
+
+describe('getCachedTools - Cache Isolation Security', () => {
+  describe('ToolCacheKeys.MCP_SERVER', () => {
+    it('should generate cache keys that include userId', () => {
+      const key = ToolCacheKeys.MCP_SERVER('user123', 'github');
+      expect(key).toBe('tools:mcp:user123:github');
+    });
+  });
+});

api/server/services/Config/app.js

@@ -1,11 +1,25 @@
-const { logger } = require('@librechat/data-schemas');
 const { CacheKeys } = require('librechat-data-provider');
-const AppService = require('~/server/services/AppService');
+const { logger, AppService } = require('@librechat/data-schemas');
+const { loadAndFormatTools } = require('~/server/services/start/tools');
+const loadCustomConfig = require('./loadCustomConfig');
 const { setCachedTools } = require('./getCachedTools');
 const getLogStores = require('~/cache/getLogStores');
+const paths = require('~/config/paths');
 
 const BASE_CONFIG_KEY = '_BASE_';
 
+const loadBaseConfig = async () => {
+  /** @type {TCustomConfig} */
+  const config = (await loadCustomConfig()) ?? {};
+  /** @type {Record<string, FunctionTool>} */
+  const systemTools = loadAndFormatTools({
+    adminFilter: config.filteredTools,
+    adminIncluded: config.includedTools,
+    directory: paths.structuredTools,
+  });
+  return AppService({ config, paths, systemTools });
+};
+
 /**
  * Get the app configuration based on user context
  * @param {Object} [options]
@@ -29,7 +43,7 @@ async function getAppConfig(options = {}) {
   let baseConfig = await cache.get(BASE_CONFIG_KEY);
   if (!baseConfig) {
     logger.info('[getAppConfig] App configuration not initialized. Initializing AppService...');
-    baseConfig = await AppService();
+    baseConfig = await loadBaseConfig();
 
     if (!baseConfig) {
       throw new Error('Failed to initialize app configuration through AppService.');

api/server/services/Config/getCachedTools.js

@@ -7,24 +7,25 @@ const getLogStores = require('~/cache/getLogStores');
 const ToolCacheKeys = {
   /** Global tools available to all users */
   GLOBAL: 'tools:global',
-  /** MCP tools cached by server name */
-  MCP_SERVER: (serverName) => `tools:mcp:${serverName}`,
+  /** MCP tools cached by user ID and server name */
+  MCP_SERVER: (userId, serverName) => `tools:mcp:${userId}:${serverName}`,
 };
 
 /**
  * Retrieves available tools from cache
  * @function getCachedTools
  * @param {Object} options - Options for retrieving tools
+ * @param {string} [options.userId] - User ID for user-specific MCP tools
  * @param {string} [options.serverName] - MCP server name to get cached tools for
  * @returns {Promise<LCAvailableTools|null>} The available tools object or null if not cached
  */
 async function getCachedTools(options = {}) {
   const cache = getLogStores(CacheKeys.CONFIG_STORE);
-  const { serverName } = options;
+  const { userId, serverName } = options;
 
   // Return MCP server-specific tools if requested
-  if (serverName) {
-    return await cache.get(ToolCacheKeys.MCP_SERVER(serverName));
+  if (serverName && userId) {
+    return await cache.get(ToolCacheKeys.MCP_SERVER(userId, serverName));
   }
 
   // Default to global tools
@@ -36,17 +37,18 @@ async function getCachedTools(options = {}) {
  * @function setCachedTools
  * @param {Object} tools - The tools object to cache
  * @param {Object} options - Options for caching tools
+ * @param {string} [options.userId] - User ID for user-specific MCP tools
  * @param {string} [options.serverName] - MCP server name for server-specific tools
  * @param {number} [options.ttl] - Time to live in milliseconds
  * @returns {Promise<boolean>} Whether the operation was successful
  */
 async function setCachedTools(tools, options = {}) {
   const cache = getLogStores(CacheKeys.CONFIG_STORE);
-  const { serverName, ttl } = options;
+  const { userId, serverName, ttl } = options;
 
-  // Cache by MCP server if specified
-  if (serverName) {
-    return await cache.set(ToolCacheKeys.MCP_SERVER(serverName), tools, ttl);
+  // Cache by MCP server if specified (requires userId)
+  if (serverName && userId) {
+    return await cache.set(ToolCacheKeys.MCP_SERVER(userId, serverName), tools, ttl);
   }
 
   // Default to global cache
@@ -57,13 +59,14 @@ async function setCachedTools(tools, options = {}) {
  * Invalidates cached tools
  * @function invalidateCachedTools
  * @param {Object} options - Options for invalidating tools
+ * @param {string} [options.userId] - User ID for user-specific MCP tools
  * @param {string} [options.serverName] - MCP server name to invalidate
  * @param {boolean} [options.invalidateGlobal=false] - Whether to invalidate global tools
  * @returns {Promise<void>}
  */
 async function invalidateCachedTools(options = {}) {
   const cache = getLogStores(CacheKeys.CONFIG_STORE);
-  const { serverName, invalidateGlobal = false } = options;
+  const { userId, serverName, invalidateGlobal = false } = options;
 
   const keysToDelete = [];
 
@@ -71,22 +74,23 @@ async function invalidateCachedTools(options = {}) {
     keysToDelete.push(ToolCacheKeys.GLOBAL);
   }
 
-  if (serverName) {
-    keysToDelete.push(ToolCacheKeys.MCP_SERVER(serverName));
+  if (serverName && userId) {
+    keysToDelete.push(ToolCacheKeys.MCP_SERVER(userId, serverName));
   }
 
   await Promise.all(keysToDelete.map((key) => cache.delete(key)));
 }
 
 /**
- * Gets MCP tools for a specific server from cache or merges with global tools
+ * Gets MCP tools for a specific server from cache
  * @function getMCPServerTools
+ * @param {string} userId - The user ID
  * @param {string} serverName - The MCP server name
  * @returns {Promise<LCAvailableTools|null>} The available tools for the server
  */
-async function getMCPServerTools(serverName) {
+async function getMCPServerTools(userId, serverName) {
   const cache = getLogStores(CacheKeys.CONFIG_STORE);
-  const serverTools = await cache.get(ToolCacheKeys.MCP_SERVER(serverName));
+  const serverTools = await cache.get(ToolCacheKeys.MCP_SERVER(userId, serverName));
 
   if (serverTools) {
     return serverTools;

api/server/services/Config/handleRateLimits.js

@@ -1,48 +0,0 @@
-const { RateLimitPrefix } = require('librechat-data-provider');
-
-/**
- *
- * @param {TCustomConfig['rateLimits'] | undefined} rateLimits
- */
-const handleRateLimits = (rateLimits) => {
-  if (!rateLimits) {
-    return;
-  }
-
-  const rateLimitKeys = {
-    fileUploads: RateLimitPrefix.FILE_UPLOAD,
-    conversationsImport: RateLimitPrefix.IMPORT,
-    tts: RateLimitPrefix.TTS,
-    stt: RateLimitPrefix.STT,
-  };
-
-  Object.entries(rateLimitKeys).forEach(([key, prefix]) => {
-    const rateLimit = rateLimits[key];
-    if (rateLimit) {
-      setRateLimitEnvVars(prefix, rateLimit);
-    }
-  });
-};
-
-/**
- * Set environment variables for rate limit configurations
- *
- * @param {string} prefix - Prefix for environment variable names
- * @param {object} rateLimit - Rate limit configuration object
- */
-const setRateLimitEnvVars = (prefix, rateLimit) => {
-  const envVarsMapping = {
-    ipMax: `${prefix}_IP_MAX`,
-    ipWindowInMinutes: `${prefix}_IP_WINDOW`,
-    userMax: `${prefix}_USER_MAX`,
-    userWindowInMinutes: `${prefix}_USER_WINDOW`,
-  };
-
-  Object.entries(envVarsMapping).forEach(([key, envVar]) => {
-    if (rateLimit[key] !== undefined) {
-      process.env[envVar] = rateLimit[key];
-    }
-  });
-};
-
-module.exports = handleRateLimits;

api/server/services/Config/ldap.js

@@ -1,4 +1,4 @@
-const { isEnabled } = require('~/server/utils');
+const { isEnabled } = require('@librechat/api');
 
 /** @returns {TStartupConfig['ldap'] | undefined} */
 const getLdapConfig = () => {

api/server/services/Config/loadConfigModels.js

@@ -57,7 +57,7 @@ async function loadConfigModels(req) {
 
   for (let i = 0; i < customEndpoints.length; i++) {
     const endpoint = customEndpoints[i];
-    const { models, name: configName, baseURL, apiKey } = endpoint;
+    const { models, name: configName, baseURL, apiKey, headers: endpointHeaders } = endpoint;
     const name = normalizeEndpointName(configName);
     endpointsMap[name] = endpoint;
 
@@ -76,6 +76,8 @@ async function loadConfigModels(req) {
           apiKey: API_KEY,
           baseURL: BASE_URL,
           user: req.user.id,
+          userObject: req.user,
+          headers: endpointHeaders,
           direct: endpoint.directEndpoint,
           userIdQuery: models.userIdQuery,
         });
@@ -85,7 +87,9 @@ async function loadConfigModels(req) {
     }
 
     if (Array.isArray(models.default)) {
-      modelsConfig[name] = models.default;
+      modelsConfig[name] = models.default.map((model) =>
+        typeof model === 'string' ? model : model.name,
+      );
     }
   }
 

api/server/services/Config/loadConfigModels.spec.js

@@ -254,8 +254,8 @@ describe('loadConfigModels', () => {
     // For groq and ollama, since the apiKey is "user_provided", models should not be fetched
     // Depending on your implementation's behavior regarding "default" models without fetching,
     // you may need to adjust the following assertions:
-    expect(result.groq).toBe(exampleConfig.endpoints.custom[2].models.default);
-    expect(result.ollama).toBe(exampleConfig.endpoints.custom[3].models.default);
+    expect(result.groq).toEqual(exampleConfig.endpoints.custom[2].models.default);
+    expect(result.ollama).toEqual(exampleConfig.endpoints.custom[3].models.default);
 
     // Verifying fetchModels was not called for groq and ollama
     expect(fetchModels).not.toHaveBeenCalledWith(

api/server/services/Config/loadCustomConfig.js

@@ -5,14 +5,12 @@ const keyBy = require('lodash/keyBy');
 const { loadYaml } = require('@librechat/api');
 const { logger } = require('@librechat/data-schemas');
 const {
-  CacheKeys,
   configSchema,
   paramSettings,
   EImageOutputType,
   agentParamSettings,
   validateSettingDefinitions,
 } = require('librechat-data-provider');
-const getLogStores = require('~/cache/getLogStores');
 
 const projectRoot = path.resolve(__dirname, '..', '..', '..', '..');
 const defaultConfigPath = path.resolve(projectRoot, 'librechat.yaml');
@@ -119,7 +117,6 @@ https://www.librechat.ai/docs/configuration/stt_tts`);
     .filter((endpoint) => endpoint.customParams)
     .forEach((endpoint) => parseCustomParams(endpoint.name, endpoint.customParams));
 
-
   if (result.data.modelSpecs) {
     customConfig.modelSpecs = result.data.modelSpecs;
   }

api/server/services/Config/mcp.js

@@ -6,11 +6,12 @@ const { getLogStores } = require('~/cache');
 /**
  * Updates MCP tools in the cache for a specific server
  * @param {Object} params - Parameters for updating MCP tools
+ * @param {string} params.userId - User ID for user-specific caching
  * @param {string} params.serverName - MCP server name
  * @param {Array} params.tools - Array of tool objects from MCP server
  * @returns {Promise<LCAvailableTools>}
  */
-async function updateMCPServerTools({ serverName, tools }) {
+async function updateMCPServerTools({ userId, serverName, tools }) {
   try {
     const serverTools = {};
     const mcpDelimiter = Constants.mcp_delimiter;
@@ -27,14 +28,16 @@ async function updateMCPServerTools({ serverName, tools }) {
       };
     }
 
-    await setCachedTools(serverTools, { serverName });
+    await setCachedTools(serverTools, { userId, serverName });
 
     const cache = getLogStores(CacheKeys.CONFIG_STORE);
     await cache.delete(CacheKeys.TOOLS);
-    logger.debug(`[MCP Cache] Updated ${tools.length} tools for server ${serverName}`);
+    logger.debug(
+      `[MCP Cache] Updated ${tools.length} tools for server ${serverName} (user: ${userId})`,
+    );
     return serverTools;
   } catch (error) {
-    logger.error(`[MCP Cache] Failed to update tools for ${serverName}:`, error);
+    logger.error(`[MCP Cache] Failed to update tools for ${serverName} (user: ${userId}):`, error);
     throw error;
   }
 }
@@ -65,21 +68,22 @@ async function mergeAppTools(appTools) {
 /**
  * Caches MCP server tools (no longer merges with global)
  * @param {object} params
+ * @param {string} params.userId - User ID for user-specific caching
  * @param {string} params.serverName
  * @param {import('@librechat/api').LCAvailableTools} params.serverTools
  * @returns {Promise<void>}
  */
-async function cacheMCPServerTools({ serverName, serverTools }) {
+async function cacheMCPServerTools({ userId, serverName, serverTools }) {
   try {
     const count = Object.keys(serverTools).length;
     if (!count) {
       return;
     }
     // Only cache server-specific tools, no merging with global
-    await setCachedTools(serverTools, { serverName });
-    logger.debug(`Cached ${count} MCP server tools for ${serverName}`);
+    await setCachedTools(serverTools, { userId, serverName });
+    logger.debug(`Cached ${count} MCP server tools for ${serverName} (user: ${userId})`);
   } catch (error) {
-    logger.error(`Failed to cache MCP server tools for ${serverName}:`, error);
+    logger.error(`Failed to cache MCP server tools for ${serverName} (user: ${userId}):`, error);
     throw error;
   }
 }

api/server/services/Endpoints/agents/agent.js

@@ -134,16 +134,16 @@ const initializeAgent = async ({
   });
 
   const tokensModel =
-    agent.provider === EModelEndpoint.azureOpenAI ? agent.model : modelOptions.model;
-  const maxTokens = optionalChainWithEmptyCheck(
-    modelOptions.maxOutputTokens,
-    modelOptions.maxTokens,
+    agent.provider === EModelEndpoint.azureOpenAI ? agent.model : options.llmConfig?.model;
+  const maxOutputTokens = optionalChainWithEmptyCheck(
+    options.llmConfig?.maxOutputTokens,
+    options.llmConfig?.maxTokens,
     0,
   );
   const agentMaxContextTokens = optionalChainWithEmptyCheck(
     maxContextTokens,
     getModelMaxTokens(tokensModel, providerEndpointMap[provider], options.endpointTokenConfig),
-    4096,
+    18000,
   );
 
   if (
@@ -203,7 +203,7 @@ const initializeAgent = async ({
     userMCPAuthMap,
     toolContextMap,
     useLegacyContent: !!options.useLegacyContent,
-    maxContextTokens: Math.round((agentMaxContextTokens - maxTokens) * 0.9),
+    maxContextTokens: Math.round((agentMaxContextTokens - maxOutputTokens) * 0.9),
   };
 };